foray-commit Mailing List for FOray

Modular XSL-FO Implementation for Java.

Status: Alpha

Brought to you by: victormote

foray-commit — FOray repository commit log messages

You can subscribe to this list here.

2006	Jan	Feb	Mar (139)	Apr (98)	May (250)	Jun (394)	Jul (84)	Aug (13)	Sep (420)	Oct (186)	Nov (1)	Dec (3)
2007	Jan (108)	Feb (202)	Mar (291)	Apr (247)	May (374)	Jun (227)	Jul (231)	Aug (60)	Sep (31)	Oct (45)	Nov (18)	Dec
2008	Jan (38)	Feb (71)	Mar (142)	Apr	May (59)	Jun (6)	Jul (10)	Aug	Sep	Oct	Nov	Dec
2009	Jan (12)	Feb (4)	Mar (88)	Apr (121)	May (17)	Jun (30)	Jul	Aug (5)	Sep	Oct (1)	Nov	Dec
2010	Jan (11)	Feb (76)	Mar (11)	Apr	May (11)	Jun	Jul	Aug (44)	Sep (14)	Oct (7)	Nov	Dec
2011	Jan	Feb	Mar	Apr	May (9)	Jun	Jul	Aug	Sep	Oct (10)	Nov	Dec
2012	Jan	Feb	Mar	Apr	May	Jun (3)	Jul (4)	Aug	Sep	Oct	Nov	Dec
2016	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec (168)
2017	Jan (77)	Feb (11)	Mar	Apr	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec
2018	Jan	Feb	Mar (1)	Apr (6)	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec
2019	Jan	Feb (88)	Mar (118)	Apr (1)	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec
2020	Jan	Feb	Mar	Apr	May (6)	Jun	Jul	Aug	Sep	Oct	Nov	Dec (141)
2021	Jan (170)	Feb (20)	Mar	Apr	May	Jun	Jul (1)	Aug	Sep	Oct (62)	Nov (189)	Dec (162)
2022	Jan (201)	Feb (118)	Mar (8)	Apr	May (2)	Jun (47)	Jul (19)	Aug (14)	Sep (3)	Oct	Nov (28)	Dec (235)
2023	Jan (112)	Feb (23)	Mar (2)	Apr (2)	May	Jun (1)	Jul	Aug (70)	Sep (92)	Oct (20)	Nov (1)	Dec (1)
2024	Jan	Feb	Mar (1)	Apr (1)	May (14)	Jun (11)	Jul (1)	Aug	Sep	Oct	Nov	Dec
2025	Jan (10)	Feb (29)	Mar	Apr (162)	May (245)	Jun (83)	Jul	Aug (1)	Sep	Oct	Nov (4)	Dec (23)
2026	Jan (119)	Feb (335)	Mar (103)	Apr (43)	May (154)	Jun (107)	Jul (187)	Aug (4)	Sep	Oct	Nov	Dec

Flat | Threaded

1 2 3 .. 323 > >> (Page 1 of 323)

[FOray-commit] SF.net SVN: foray:[14959] trunk/foray/foray-orthograp hy/src/main/java/org/foray/orthography/DictionaryResource.jav a

From: <vic...@us...> - 2026-08-01 16:38:56

Revision: 14959
          http://sourceforge.net/p/foray/code/14959
Author:   victormote
Date:     2026-08-01 16:38:54 +0000 (Sat, 01 Aug 2026)
Log Message:
-----------
Throw exception if more than one dictionary is parsed from a configured dictionary resource.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/DictionaryResource.java

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/DictionaryResource.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/DictionaryResource.java	2026-08-01 15:57:32 UTC (rev 14958)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/DictionaryResource.java	2026-08-01 16:38:54 UTC (rev 14959)
@@ -38,6 +38,7 @@
 import java.io.IOException;
 import java.io.InputStream;
 import java.net.URL;
+import java.util.List;
 
 /**
  * Configuration information for a dictionary resource.
@@ -81,7 +82,14 @@
         SegmentDictionary dictionary = null;
         try {
             final InputSource source = new InputSource(url.toExternalForm());
-            dictionary = parser.parse(source).get(0);
+            final List<SegmentDictionary> dictionaries = parser.parse(source);
+            /* The parser can return more than one dictionary, but that should never happen for /configured/
+             * resources. */
+            if (dictionaries.size() > 1) {
+                throw new IllegalArgumentException("Configured dictionary resource " + url +
+                        " should contain only one dictionary");
+            }
+            dictionary = dictionaries.get(0);
         } catch (final IOException e) {
             LoggerFactory.getLogger(this.getClass()).error("IOException", e);
             return null;

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14958] trunk/foray/foray-orthograp hy/src/main/java/org/foray/orthography/Orthography4a.java

From: <vic...@us...> - 2026-08-01 15:57:35

Revision: 14958
          http://sourceforge.net/p/foray/code/14958
Author:   victormote
Date:     2026-08-01 15:57:32 +0000 (Sat, 01 Aug 2026)
Log Message:
-----------
Minor internal refactoring, for clarity.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java	2026-08-01 15:44:03 UTC (rev 14957)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java	2026-08-01 15:57:32 UTC (rev 14958)
@@ -114,27 +114,6 @@
      */
     public abstract WritingSystem4a getWritingSystem();
 
-    /**
-     * Indicates whether a given word is found in the match rules for this orthography, i.e. rules looking for
-     * non-dictionary items such as numbers, currency, etc.
-     * @param wordChars The word to be tested.
-     * @return True if and only if {@code word} matches at least one match rule for this orthography.
-     */
-    public StringWord foundInMatchRules(final CharSequence wordChars) {
-        for (int idIndex = 0; idIndex < getMatchRuleListIds().size(); idIndex ++) {
-            final String ruleListId = getMatchRuleListIds().get(idIndex);
-            final List<Pattern> validWordPatterns = getServer().getMatchRules(ruleListId);
-            for (int index = 0; index < validWordPatterns.size(); index ++) {
-                final Pattern pattern = validWordPatterns.get(index);
-                final Matcher matcher = pattern.matcher(wordChars);
-                if (matcher.matches()) {
-                    return new StringWord(0, wordChars);
-                }
-            }
-        }
-        return null;
-    }
-
     @Override
     public Word4a recognizeWord(final CharSequence wordCharsIn, final int offset, final int length,
             final PartOfSpeech pos) {
@@ -168,7 +147,7 @@
         }
 
         /* 2. Check the match rules. */
-        word = foundInMatchRules(wordChars);
+        word = findInMatchRules(wordChars);
         if (word != null) {
             return handleCase(word, wordChars);
         }
@@ -260,6 +239,27 @@
         return null;
     }
 
+    /**
+     * Indicates whether a given word is found in the match rules for this orthography, i.e. rules looking for
+     * non-dictionary items such as numbers, currency, etc.
+     * @param wordChars The word to be tested.
+     * @return True if and only if {@code word} matches at least one match rule for this orthography.
+     */
+    private StringWord findInMatchRules(final CharSequence wordChars) {
+        for (int idIndex = 0; idIndex < getMatchRuleListIds().size(); idIndex ++) {
+            final String ruleListId = getMatchRuleListIds().get(idIndex);
+            final List<Pattern> validWordPatterns = getServer().getMatchRules(ruleListId);
+            for (int index = 0; index < validWordPatterns.size(); index ++) {
+                final Pattern pattern = validWordPatterns.get(index);
+                final Matcher matcher = pattern.matcher(wordChars);
+                if (matcher.matches()) {
+                    return new StringWord(0, wordChars);
+                }
+            }
+        }
+        return null;
+    }
+
     @Override
     public Word4a hyphenateUnrecognizedWord(final CharSequence word, final int offset, final int length) {
         /* The character sequence containing the characters in the word that we are looking for. */

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14957] trunk/foray/foray-orthograp hy/src/main/data/dictionaries/eng-Latn-ZZZ-theology.dict.xm l

From: <vic...@us...> - 2026-08-01 15:44:05

Revision: 14957
          http://sourceforge.net/p/foray/code/14957
Author:   victormote
Date:     2026-08-01 15:44:03 +0000 (Sat, 01 Aug 2026)
Log Message:
-----------
Normal dictionary editing.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ-theology.dict.xml

Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ-theology.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ-theology.dict.xml	2026-08-01 10:16:17 UTC (rev 14956)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ-theology.dict.xml	2026-08-01 15:44:03 UTC (rev 14957)
@@ -89,6 +89,7 @@
 <w><t>Hin-nom</t><noun/></w>
 <w><t>Ho-bab</t><noun><convertible-to-possessive/></noun></w>
 <w><t>Hol-werd-a</t><noun/><comment>Author.</comment></w>
+<w><t>home-go-ing</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>hon-our</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>Hur</t><noun><convertible-to-possessive/><proper/></noun><comment>Ex. 17:8-9.</comment></w>
 <w><t>Hy-men-aen</t><adjective><extensible value="false"/></adjective></w>

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14956] trunk/foray/foray-orthograp hy/src/main/data

From: <vic...@us...> - 2026-08-01 10:16:20

Revision: 14956
          http://sourceforge.net/p/foray/code/14956
Author:   victormote
Date:     2026-08-01 10:16:17 +0000 (Sat, 01 Aug 2026)
Log Message:
-----------
Normal dictionary editing.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/dictionaries/emen-Latn-ZZZ.dict.xml
    trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ-theology.dict.xml
    trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
    trunk/foray/foray-orthography/src/main/data/dictionaries/lat-Latn-ZZZ.dict.xml
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml

Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/emen-Latn-ZZZ.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/emen-Latn-ZZZ.dict.xml	2026-07-31 09:57:31 UTC (rev 14955)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/emen-Latn-ZZZ.dict.xml	2026-08-01 10:16:17 UTC (rev 14956)
@@ -17,11 +17,18 @@
 
 <w><t>bear-eth</t><verb><lemma>bear</lemma></verb></w>
 <w><t>bring-eth</t><verb><lemma>bring</lemma></verb></w>
-<w><t>cleans-eth</t><verb><lemma>cleanse</lemma></verb></w>
-<w><t>fad-eth</t><verb><lemma>fade</lemma></verb></w>
+<w><t>caus-eth</t><verb><lemma>cause</lemma></verb><comment>Regular verb. Remove.</comment></w>
+<w><t>cleans-eth</t><verb><lemma>cleanse</lemma></verb><comment>Regular verb. Remove.</comment></w>
+<w><t>de-clin-eth</t><verb><lemma>decline</lemma></verb><comment>Regular verb. Remove.</comment></w>
+<w><t>en-dur-eth</t><verb><lemma>endure</lemma></verb><comment>Regular verb. Remove.</comment></w>
+<w><t>fad-eth</t><verb><lemma>fade</lemma></verb><comment>Regular verb. Remove.</comment></w>
 <w><t>grow-eth</t><verb><lemma>grow</lemma></verb></w>
 <w><t>hear-eth</t><verb><lemma>hear</lemma></verb></w>
-<w><t>shin-eth</t><verb><lemma>shine</lemma></verb></w>
+<w><t>keep-eth</t><verb><lemma>keep</lemma></verb></w>
+<w><t>liv-eth</t><verb><lemma>live</lemma></verb><comment>Regular verb. Remove.</comment></w>
+<w><t>mak-eth</t><verb><lemma>make</lemma></verb></w>
+<w><t>mas-ter-build-er</t></w>
+<w><t>shin-eth</t><verb><lemma>shine</lemma></verb><comment>Regular verb. Remove.</comment></w>
 <w><t>un-der-stand-eth</t><verb><lemma>understand</lemma></verb></w>
 
 

Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ-theology.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ-theology.dict.xml	2026-07-31 09:57:31 UTC (rev 14955)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ-theology.dict.xml	2026-08-01 10:16:17 UTC (rev 14956)
@@ -21,6 +21,7 @@
 <w><t>Ab-i-ez-rite</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>A-bi-ram</t></w>
 <w><t>Ach-te-mei-er</t><comment>Author.</comment></w>
+<w><t>Ad-o-ni-ram</t><noun><proper/></noun><comment>First name of missionary Judson.</comment></w>
 <w><t>Al-phae-us</t><noun/></w>
 <w><t>A-mo-rite</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>A-moz</t><noun/></w>
@@ -89,6 +90,7 @@
 <w><t>Ho-bab</t><noun><convertible-to-possessive/></noun></w>
 <w><t>Hol-werd-a</t><noun/><comment>Author.</comment></w>
 <w><t>hon-our</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
+<w><t>Hur</t><noun><convertible-to-possessive/><proper/></noun><comment>Ex. 17:8-9.</comment></w>
 <w><t>Hy-men-aen</t><adjective><extensible value="false"/></adjective></w>
 <w><t>Hy-men-ae-us</t><noun><convertible-to-possessive/></noun></w>
 <w><t>Hy-men-æ-us</t><noun><convertible-to-possessive/></noun></w>
@@ -102,6 +104,7 @@
 <w><t>Jo-ses</t><noun/></w>
 <w><t>Jo-tham</t><noun/></w>
 <w><t>Judg</t><abbrev referenced-word="Judges"/></w>
+<w><t>Jud-son</t><noun><pluralizable/><convertible-to-possessive/></noun><comment>Missionary</comment></w>
 <w><t>Ke-desh</t><noun/></w>
 <w><t>Keil</t><noun/><comment>Author.</comment></w>
 <w><t>Ken-ite</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -176,6 +179,8 @@
 <w><t>Shi-mon</t><noun/><comment>Alt. for Simon.</comment></w>
 <w><t>Si-hon</t><noun><singular/></noun></w>
 <w><t>Sos-the-nes</t><noun/></w>
+<w><t>soul-win-ner</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>soul-win-ning</t><noun><singular/><convertible-to-possessive/></noun></w>
 <w><t>Steph-a-nas</t><noun/></w>
 <w><t>Strong</t><noun><convertible-to-possessive/></noun><comment>Concordance author.</comment></w>
 <w><t>Sty-lites</t><comment>Simeon, 5th century Syrian ascetic.</comment></w>
@@ -186,6 +191,7 @@
 <w><t>Ter-tul-lus</t><noun/></w>
 <w><t>Th</t><abbrev referenced-word="Thessalonians"/></w>
 <w><t>Theu-das</t><noun/></w>
+<w><t>Toplady</t><comment>Augustus. Author.</comment></w>
 <w><t>TULIP</t><abbrev referenced-word="Total... Unconditional... Limited... Irresistible... Perseverance..."/></w>
 <w><t>Tych-ic-us</t><noun/></w>
 <w><t>Ty-ran-nus</t><noun><convertible-to-possessive/></noun></w>
@@ -193,6 +199,7 @@
 <w><t>U-phar-sin</t><noun/></w>
 <w><t>Ur</t><noun/></w>
 <w><t>Uz</t><noun/></w>
+<w><t>VBS</t><abbrev referenced-word="Vacation Bible School"/><noun><convertible-to-possessive/></noun></w>
 <w><t>Wal-voord</t><noun/><comment>Author.</comment></w>
 <w><t>works=o-ri-ent-ed</t><adjective/></w>
 <w><t>WWJD</t><abbrev referenced-word="What Would Jesus Do"/></w>
@@ -201,6 +208,7 @@
 <w><t>Ze-lo-tes</t><noun/></w>
 <w><t>Ze-rah</t><noun/></w>
 <w><t>Zeus O-lym-pi-os</t></w>
+<w><t>Zon-der-van</t><noun><convertible-to-possessive/></noun><comment>Modern publisher</comment></w>
 <w><t>Zuck</t><noun/><comment>Author.</comment></w>
 
 

Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-31 09:57:31 UTC (rev 14955)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-08-01 10:16:17 UTC (rev 14956)
@@ -65,12 +65,18 @@
 <section description="A">
 <section description="A abbrev">
 <w><t>a</t></w>
-<w><t>A.D.</t><abbrev referenced-word="anno Domini"/><comment>Latin "year of our Lord"</comment></w>
-<w><t>a.d.</t><abbrev referenced-word="anno Domini"/><comment>Latin "year of our Lord"</comment></w>
-<w><t>a.&#xA0;d.</t><abbrev referenced-word="anno Domini"/><comment>Latin "year of our Lord"</comment></w>
-<w><t>a.m.</t><abbrev referenced-word="ante meridian"/><comment>Latin "before noon"</comment></w>
-<w><t>a.&#xA0;m.</t><abbrev referenced-word="ante meridian"/><comment>Latin "before noon"</comment></w>
+<word-choice>
+  <w><t>A.D.</t><abbrev referenced-word="anno Domini"/><comment>Latin "year of our Lord"</comment></w>
+  <w><t>a.d.</t><abbrev referenced-word="anno Domini"/><comment>Latin "year of our Lord"</comment></w>
+  <w><t>a.&#xA0;d.</t><abbrev referenced-word="anno Domini"/><comment>Latin "year of our Lord"</comment></w>
+  <w><t>ad</t><abbrev referenced-word="anno Domini"/><comment>Latin "year of our Lord"</comment></w>
+</word-choice>
+<word-choice>
+  <w><t>a.m.</t><abbrev referenced-word="ante meridian"/><comment>Latin "before noon"</comment></w>
+  <w><t>a.&#xA0;m.</t><abbrev referenced-word="ante meridian"/><comment>Latin "before noon"</comment></w>
+</word-choice>
 </section>
+
 <section description="Aa">
 <w><t>a-a</t></w>
 <w><t>Aa-chen</t></w>
@@ -3873,7 +3879,7 @@
 <w><t>Al-cock</t></w>
 <w><t>al-co-hol</t></w>
 <w><t>al-co-hol-ate</t></w>
-<w><t>al-co-hol-ic</t></w>
+<w><t>al-co-hol-ic</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>al-co-hol-i-cal-ly</t></w>
 <w><t>al-co-hol-ic-i-ty</t></w>
 <phrase><t>Al-co-hol-ics A-non-y-mous</t></phrase>
@@ -3988,7 +3994,7 @@
 <phrase><t>A-lep-po gall</t></phrase>
 <w><t>a-ler-ce</t></w>
 <w><t>a-le-ri-on</t></w>
-<w><t>a-lert</t></w>
+<w><t>a-lert</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb><adjective></adjective></w>
 <w><t>a-lert-ly</t></w>
 <w><t>a-lert-ness</t></w>
 <w><t>A-le-si-a</t></w>
@@ -5003,7 +5009,7 @@
 <w><t>am-au-rot-ic</t></w>
 <w><t>a-maut</t></w>
 <w><t>A-may-a</t></w>
-<w><t>a-maze</t></w>
+<w><t>a-maze</t><verb><regular-root/></verb></w>
 <w><t>a-mazed</t></w>
 <w><t>a-maz-ed-ly</t></w>
 <w><t>a-maz-ed-ness</t></w>
@@ -5207,7 +5213,7 @@
 <w><t>a-merce-ment</t></w>
 <w><t>a-merc-er</t></w>
 <w><t>a-merc-ing</t></w>
-<w><t>A-mer-i-ca</t></w>
+<w><t>A-mer-i-ca</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>A-mer-i-can</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>A-mer-i-ca-na</t></w>
 <phrase><t>A-mer-i-can al-oe</t></phrase>
@@ -5683,7 +5689,7 @@
 <w><t>a-mu-sive</t></w>
 <w><t>a-mu-sive-ly</t></w>
 <w><t>a-mu-sive-ness</t></w>
-<w><t>A-my</t></w>
+<w><t>A-my</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>a-my-a-ton-ic</t></w>
 <w><t>A-my-clas</t></w>
 <w><t>Am-y-cus</t></w>
@@ -7836,7 +7842,7 @@
 <w><t>an-ti-qua-ted-ness</t></w>
 <w><t>an-ti-quat-ing</t></w>
 <w><t>an-ti-qua-tion</t></w>
-<w><t>an-tique</t></w>
+<w><t>an-tique</t><noun><pluralizable/><convertible-to-possessive/></noun><adjective><extensible value="false"/></adjective></w>
 <w><t>an-tiqued</t></w>
 <w><t>an-tique-ly</t></w>
 <w><t>an-tique-ness</t></w>
@@ -11385,7 +11391,7 @@
 <w><t>Au-gus-ta-les</t></w>
 <w><t>Au-gus-tan</t></w>
 <w><t>Au-guste</t></w>
-<w><t>Au-gus-tine</t></w>
+<w><t>Au-gus-tine</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Au-gus-tin-i-an</t></w>
 <w><t>Au-gus-tin-i-an-ism</t></w>
 <w><t>Au-gus-tin-ism</t></w>
@@ -12271,11 +12277,15 @@
 </section>
 
 <section description="B">
+<section description="B abbrev">
 <w><t>b/f</t></w>
 <w><t>b/l</t></w>
 <w><t>b/s</t></w>
 <w><t>b.</t><abbrev referenced-word="book"/></w>
 <w><t>b.c.</t><abbrev referenced-word="Before Christ"/></w>
+</section>
+
+<section description="Ba">
 <w><t>baa</t></w>
 <w><t>BAA</t></w>
 <phrase><t>Baa-der=Mein-hof Gang</t></phrase>
@@ -14342,7 +14352,7 @@
 <w><t>Bax</t></w>
 <w><t>B=ax-es</t></w>
 <w><t>Bax-ley</t></w>
-<w><t>Bax-ter</t></w>
+<w><t>Bax-ter</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>bay</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>ba-ya</t></w>
 <w><t>ba-ya-dere</t></w>
@@ -14384,6 +14394,9 @@
 <w><t>ba-zoo</t></w>
 <w><t>ba-zoo-ka</t></w>
 <w><t>ba-zoo-ka-man</t></w>
+</section>
+
+<section description="Bb to Bd">
 <phrase><t>B bat-ter-y</t></phrase>
 <w><t>bb-bish</t></w>
 <w><t>BBC</t></w>
@@ -14401,6 +14414,9 @@
 <w><t>bdl</t></w>
 <w><t>BDS</t></w>
 <w><t>bds</t></w>
+</section>
+
+<section description="Be">
 <w><t>be</t></w>
 <w><t>Bea</t></w>
 <w><t>BEA</t></w>
@@ -14522,6 +14538,7 @@
 <w><t>bear-like</t></w>
 <w><t>Bé-ar-naise</t></w>
 <w><t>bear-paw</t></w>
+<w><t>bears</t><noun><plural/></noun><verb><lemma>bear</lemma><vf></vf></verb></w>
 <w><t>bear’s=breech-es</t></w>
 <w><t>bear-skin</t></w>
 <w><t>bear-wood</t></w>
@@ -14979,6 +14996,7 @@
 <w><t>Bei-der-becke</t></w>
 <w><t>beige</t></w>
 <w><t>bei-gel</t></w>
+<w><t>Bei-jing</t><noun><singular/><convertible-to-possessive/><proper/></noun></w>
 <w><t>be-ing</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root value="false"/></verb></w>
 <w><t>Bei-ra</t></w>
 <w><t>Bei-rut</t></w>
@@ -15920,6 +15938,9 @@
 <w><t>be-zo-ni-an</t></w>
 <w><t>Bez-wa-da</t></w>
 <w><t>bez-zant</t></w>
+</section>
+
+<section description="Bh">
 <w><t>Bha-bha</t></w>
 <w><t>Bhad-gaon</t></w>
 <w><t>Bha-gal-pur</t></w>
@@ -15963,6 +15984,9 @@
 <w><t>Bhu-tan-ese</t></w>
 <w><t>Bhu-ta-ta-tha-ta</t></w>
 <w><t>Bhut-to</t></w>
+</section>
+
+<section description="Bi">
 <w><t>Bi-a</t></w>
 <w><t>bi-a-ce-tyl</t></w>
 <w><t>Bi-a-di-ce</t></w>
@@ -16267,7 +16291,7 @@
 <w><t>big-ness</t></w>
 <w><t>big-no-ni-a</t></w>
 <w><t>big-no-ni-a-ceous</t></w>
-<w><t>big-ot</t></w>
+<w><t>big-ot</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>big-ot-ed</t></w>
 <w><t>big-ot-ed-ly</t></w>
 <w><t>big-ot-ry</t></w>
@@ -16977,6 +17001,9 @@
 <w><t>bi-zone</t></w>
 <w><t>Bi-zo-ni-a</t></w>
 <w><t>Biz-tha</t></w>
+</section>
+
+<section description="Bj to Bk">
 <w><t>B-jart</t></w>
 <w><t>Bj-ne-borg</t></w>
 <w><t>Bjoer-ling</t></w>
@@ -16987,6 +17014,9 @@
 <w><t>bkg</t></w>
 <w><t>bkpt</t></w>
 <w><t>bks</t></w>
+</section>
+
+<section description="Bl">
 <w><t>blab</t></w>
 <w><t>blab-ber</t></w>
 <w><t>blab-ber-mouth</t></w>
@@ -17787,10 +17817,16 @@
 <w><t>Blyth</t></w>
 <w><t>Blythe</t></w>
 <w><t>Blythe-ville</t></w>
+</section>
+
+<section description="Bm">
 <w><t>BMA</t></w>
 <w><t>B-me</t></w>
 <w><t>BMJ</t></w>
 <w><t>BMus</t></w>
+</section>
+
+<section description="Bo">
 <w><t>bo-a</t></w>
 <w><t>Bo-ab-dil</t></w>
 <w><t>BOAC</t></w>
@@ -18414,7 +18450,7 @@
 <w><t>book-mak-er</t></w>
 <w><t>book-mak-ing</t></w>
 <w><t>book-man</t></w>
-<w><t>book-mark</t></w>
+<w><t>book-mark</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>book-mark-er</t></w>
 <w><t>book-mo-bile</t></w>
 <phrase><t>book of ac-count</t></phrase>
@@ -19115,10 +19151,16 @@
 <w><t>Bo-zen</t></w>
 <w><t>bo-zo</t></w>
 <w><t>Boz-za-ris</t></w>
+</section>
+
+<section description="Bp">
 <w><t>Bp</t><abbrev referenced-word="Bishop"/></w>
 <w><t>BPC</t></w>
 <w><t>bpi</t></w>
 <w><t>bpt</t></w>
+</section>
+
+<section description="Br">
 <w><t>bra</t></w>
 <w><t>braa-ta</t></w>
 <w><t>braa-tas</t></w>
@@ -19269,7 +19311,7 @@
 <w><t>brain-child</t></w>
 <w><t>brain-chil-dren</t></w>
 <phrase><t>brain cor-al</t></phrase>
-<w><t>Brai-nerd</t></w>
+<w><t>Brai-nerd</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <phrase><t>brain fe-ver</t></phrase>
 <phrase><t>brain=fe-ver bird</t></phrase>
 <w><t>brain-i-er</t></w>
@@ -19568,7 +19610,7 @@
 <w><t>break-o-ver</t></w>
 <w><t>break-point</t></w>
 <w><t>breaks</t><verb><regular-root value="false"/></verb></w>
-<w><t>break-through</t></w>
+<w><t>break-through</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>break-up</t></w>
 <w><t>break-wa-ter</t></w>
 <w><t>break-weath-er</t></w>
@@ -20461,6 +20503,9 @@
 <w><t>Bryth-on</t></w>
 <w><t>Bry-thon-ic</t></w>
 <w><t>Brze-giem</t></w>
+</section>
+
+<section description="Bs to Bt">
 <w><t>Bs/L</t></w>
 <w><t>BSc</t></w>
 <phrase><t>B Spe-cial</t></phrase>
@@ -20475,6 +20520,9 @@
 <w><t>btry</t></w>
 <w><t>btu</t></w>
 <w><t>BTU</t></w>
+</section>
+
+<section description="Bu">
 <w><t>bub</t></w>
 <w><t>Bub</t></w>
 <w><t>bu-bal</t></w>
@@ -20613,7 +20661,7 @@
 <phrase><t>Buddh Ga-ya</t></phrase>
 <w><t>bud-dhi</t></w>
 <w><t>Bud-dhism</t></w>
-<w><t>Bud-dhist</t></w>
+<w><t>Bud-dhist</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>Bud-dhis-tic</t></w>
 <w><t>Bud-dhis-ti-cal</t></w>
 <w><t>Bud-dhis-ti-cal-ly</t></w>
@@ -21483,7 +21531,7 @@
 <w><t>Bux-ton</t></w>
 <w><t>buy</t><verb><regular-root value="false"/></verb></w>
 <w><t>buy-a-ble</t></w>
-<w><t>buy-er</t></w>
+<w><t>buy-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>buy-ers’ mar-ket</t></phrase>
 <w><t>buy-ing</t></w>
 <phrase><t>buy in-to</t></phrase>
@@ -21496,9 +21544,15 @@
 <w><t>buzz-er</t></w>
 <w><t>buzz-ing-ly</t></w>
 <w><t>buzz-wig</t></w>
+</section>
+
+<section description="Bv to Bw">
 <w><t>BVM</t></w>
 <w><t>bwa-na</t></w>
 <w><t>BWG</t></w>
+</section>
+
+<section description="By to Bz">
 <w><t>by</t></w>
 <w><t>By-am</t></w>
 <w><t>by=bid-der</t></w>
@@ -21579,6 +21633,7 @@
 <w><t>By-zas</t></w>
 <w><t>B-ziers</t></w>
 </section>
+</section>
 
 <section description="C">
 <section description="C abbrev">
@@ -22347,7 +22402,7 @@
 <w><t>Cal-va-ry</t><noun><convertible-to-possessive/></noun></w>
 <w><t>cal-va-ry</t></w>
 <phrase><t>Cal-va-ry cross</t></phrase>
-<w><t>calve</t></w>
+<w><t>calve</t><verb><regular-root/></verb></w>
 <w><t>Cal-vé</t></w>
 <w><t>Cal-vert</t></w>
 <w><t>calves</t></w>
@@ -23004,7 +23059,7 @@
 <w><t>ca-nu-lar</t></w>
 <w><t>can-u-late</t></w>
 <w><t>Ca-nute</t></w>
-<w><t>can-vas</t></w>
+<w><t>can-vas</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>can-vas-back</t></w>
 <w><t>can-vas-like</t></w>
 <w><t>can-vass</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
@@ -23553,7 +23608,7 @@
 <w><t>ca-reen</t></w>
 <w><t>ca-reen-age</t></w>
 <w><t>ca-reen-er</t></w>
-<w><t>ca-reer</t></w>
+<w><t>ca-reer</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>ca-reer girl</t></phrase>
 <w><t>ca-reer-ism</t></w>
 <w><t>ca-reer-ist</t></w>
@@ -24886,6 +24941,7 @@
 <w><t>CBS</t></w>
 <w><t>C-ce-res</t></w>
 <w><t>C-cu-ta</t></w>
+<w><t>CD</t><abbrev referenced-word="compact disk"/><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>C-de-nas</t></w>
 <w><t>C-diz</t></w>
 <w><t>Cdn</t></w>
@@ -27292,7 +27348,7 @@
 <w><t>choice-ly</t></w>
 <w><t>choice-ness</t></w>
 <w><t>choic-er</t></w>
-<w><t>choir</t></w>
+<w><t>choir</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>choir-boy</t></w>
 <w><t>choir-girl</t></w>
 <w><t>choir-like</t></w>
@@ -33675,7 +33731,7 @@
 <w><t>cord-wain-er</t></w>
 <w><t>cord-wain-er-y</t></w>
 <w><t>cord-wood</t></w>
-<w><t>core</t></w>
+<w><t>core</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>CORE</t></w>
 <w><t>Co-re</t></w>
 <w><t>co-re-la-tion</t></w>
@@ -36061,7 +36117,7 @@
 <w><t>cru-ci-fy</t><verb><regular-root/></verb></w>
 <w><t>cru-ci-fy-ing</t></w>
 <w><t>Cru-cis</t></w>
-<w><t>cruck</t></w>
+<w><t>cruck</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>crud</t></w>
 <w><t>crud-ded</t></w>
 <w><t>crud-ding</t></w>
@@ -36640,7 +36696,7 @@
 <w><t>cup</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Cu-pa-vo</t></w>
 <w><t>cup-bear-er</t></w>
-<w><t>cup-board</t></w>
+<w><t>cup-board</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>cup-board love</t></phrase>
 <w><t>cup-cake</t></w>
 <w><t>cu-pel</t></w>
@@ -37258,7 +37314,7 @@
 <w><t>Cyn-a-ra</t></w>
 <w><t>Cyn-e-wulf</t></w>
 <w><t>cyn-gha-nedd</t></w>
-<w><t>cyn-ic</t></w>
+<w><t>cyn-ic</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Cyn-ic</t></w>
 <w><t>cyn-i-cal</t></w>
 <w><t>cyn-i-cal-ly</t></w>
@@ -38978,7 +39034,7 @@
 <w><t>ded-i-cate</t></w>
 <w><t>ded-i-cat-ed</t></w>
 <w><t>ded-i-cat-ing</t></w>
-<w><t>ded-i-ca-tion</t></w>
+<w><t>ded-i-ca-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>ded-i-ca-tion-al</t></w>
 <w><t>ded-i-ca-tive</t></w>
 <w><t>ded-i-ca-tor</t></w>
@@ -40590,7 +40646,7 @@
 <w><t>de-ri-so-ry</t></w>
 <w><t>deriv</t></w>
 <w><t>de-riv-a-ble</t></w>
-<w><t>der-i-va-tion</t></w>
+<w><t>der-i-va-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>der-i-va-tion-al</t></w>
 <w><t>der-i-va-tion-al-ly</t></w>
 <w><t>de-riv-a-tive</t></w>
@@ -41567,8 +41623,7 @@
 <w><t>Di-ahann</t></w>
 <w><t>di-a-ki-ne-sis</t></w>
 <w><t>di-a-kon-i-kon</t></w>
-<w><t>dial</t></w>
-<w><t>di-al</t></w>
+<w><t>di-al</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>di-a-lect</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>di-a-lec-tal</t></w>
 <w><t>di-a-lec-tal-ly</t></w>
@@ -41666,7 +41721,7 @@
 <phrase><t>di-a-mond wed-ding</t></phrase>
 <w><t>di-a-mor-phine</t></w>
 <w><t>Di-a-mox</t></w>
-<w><t>Di-an-a</t></w>
+<w><t>Di-an-a</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>di-an-drous</t></w>
 <w><t>Di-ane</t></w>
 <w><t>di-a-net-ics</t></w>
@@ -46093,7 +46148,7 @@
 <w><t>du-et-tist</t></w>
 <w><t>Du-fay</t></w>
 <w><t>duff</t></w>
-<w><t>Duff</t></w>
+<w><t>Duff</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>duf-fel</t></w>
 <phrase><t>duf-fel bag</t></phrase>
 <phrase><t>duf-fel coat</t></phrase>
@@ -47300,7 +47355,7 @@
 <w><t>e-de-ma</t></w>
 <w><t>e-de-ma-ta</t></w>
 <w><t>e-dem-a-tous</t></w>
-<w><t>E-den</t></w>
+<w><t>E-den</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>E-den-ic</t></w>
 <w><t>E-den-ta-ta</t></w>
 <w><t>e-den-tate</t></w>
@@ -47361,8 +47416,8 @@
 <w><t>Ed-in-burgh</t><noun><singular/><convertible-to-possessive/><proper/></noun></w>
 <w><t>E-dir-ne</t></w>
 <w><t>Ed-i-son</t></w>
-<w><t>edit</t></w>
 <w><t>ed-it</t><verb><regular-root/></verb></w>
+<w><t>edit.</t><abbrev referenced-word="edited, edition, editor"/></w>
 <w><t>E-dith</t></w>
 <w><t>E-dithe</t></w>
 <w><t>e-di-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -48849,7 +48904,7 @@
 <w><t>Em-i-lie</t></w>
 <w><t>E-mi-lio</t></w>
 <w><t>E-mi-li-o</t></w>
-<w><t>Em-i-ly</t></w>
+<w><t>Em-i-ly</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Em-i-na</t></w>
 <w><t>Em-i-nence</t></w>
 <w><t>em-i-nence</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -50090,7 +50145,7 @@
 <w><t>en-train</t></w>
 <w><t>en-train-er</t></w>
 <w><t>en-tram-mel</t></w>
-<w><t>en-trance</t></w>
+<w><t>en-trance</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>en-tranced</t></w>
 <w><t>en-trance-ment</t></w>
 <w><t>en-trance-way</t></w>
@@ -51154,7 +51209,7 @@
 <w><t>ERS</t></w>
 <w><t>er-satz</t></w>
 <w><t>Erse</t></w>
-<w><t>Er-skine</t></w>
+<w><t>Er-skine</t><noun><convertible-to-possessive/></noun></w>
 <w><t>erst</t></w>
 <w><t>erst-while</t></w>
 <w><t>Er-te-bol-le</t></w>
@@ -52266,7 +52321,7 @@
 <w><t>e-va-sive-ly</t></w>
 <w><t>e-va-sive-ness</t></w>
 <w><t>Ev-att</t></w>
-<w><t>Eve</t></w>
+<w><t>Eve</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>eve</t></w>
 <w><t>e-vec-tion</t></w>
 <w><t>e-vec-tion-al</t></w>
@@ -52479,7 +52534,7 @@
 <w><t>ex-alt-ed-ly</t></w>
 <w><t>ex-alt-ed-ness</t></w>
 <w><t>ex-alt-er</t></w>
-<w><t>ex-am</t></w>
+<w><t>ex-am</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>ex-a-men</t></w>
 <w><t>ex-am-in-a-ble</t></w>
 <w><t>ex-am-i-nant</t></w>
@@ -53827,7 +53882,7 @@
 <phrase><t>face pow-der</t></phrase>
 <w><t>fac-er</t></w>
 <w><t>face=sav-ing</t></w>
-<w><t>fac-et</t></w>
+<w><t>fac-et</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>fa-cete</t></w>
 <w><t>fac-et-ed</t></w>
 <w><t>fa-cete-ly</t></w>
@@ -56012,7 +56067,7 @@
 <w><t>fin-ger=paint</t></w>
 <phrase><t>fin-ger paint-ing</t></phrase>
 <phrase><t>fin-ger post</t></phrase>
-<w><t>fin-ger-print</t></w>
+<w><t>fin-ger-print</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>fin-ger’s breadth</t></phrase>
 <w><t>fin-ger-stall</t></w>
 <phrase><t>fin-ger tight</t></phrase>
@@ -56422,7 +56477,7 @@
 <w><t>flac-on</t></w>
 <w><t>fla-con</t></w>
 <w><t>flac-ons</t></w>
-<w><t>flag</t></w>
+<w><t>flag</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>flag cap-tain</t></phrase>
 <w><t>fla-gel-la</t></w>
 <w><t>flag-el-lant</t></w>
@@ -56907,7 +56962,7 @@
 <w><t>flint-lock</t></w>
 <w><t>Flint-shire</t></w>
 <w><t>flint-y</t></w>
-<w><t>flip</t></w>
+<w><t>flip</t><verb><regular-root/></verb></w>
 <w><t>flip=flop</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>flip-pan-cy</t></w>
 <w><t>flip-pant</t></w>
@@ -57919,7 +57974,7 @@
 <w><t>fo-ren-si-cal-i-ty</t></w>
 <w><t>fo-ren-si-cal-ly</t></w>
 <w><t>fo-ren-sics</t></w>
-<w><t>fore-or-dain</t></w>
+<w><t>fore-or-dain</t><verb><regular-root/></verb></w>
 <w><t>fore-or-dain-ment</t></w>
 <w><t>fore-or-di-nate</t></w>
 <w><t>fore-or-di-nat-ed</t></w>
@@ -61676,10 +61731,11 @@
 <w><t>ge-ol-o-gise</t></w>
 <w><t>ge-ol-o-gised</t></w>
 <w><t>ge-ol-o-gis-ing</t></w>
+<w><t>ge-ol-o-gist</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>ge-ol-o-gize</t></w>
 <w><t>ge-ol-o-gized</t></w>
 <w><t>ge-ol-o-giz-ing</t></w>
-<w><t>ge-ol-o-gy</t></w>
+<w><t>ge-ol-o-gy</t><noun><convertible-to-possessive/></noun></w>
 <w><t>geom</t></w>
 <w><t>ge-o-mag-net-ic</t></w>
 <w><t>ge-o-mag-ne-ti-cian</t></w>
@@ -62962,7 +63018,7 @@
 <w><t>glu-cos-u-ri-a</t></w>
 <w><t>glu-co-su-ri-a</t></w>
 <w><t>glu-cu-ron-ide</t></w>
-<w><t>glue</t></w>
+<w><t>glue</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>glue-like</t></w>
 <w><t>glue-pot</t></w>
 <w><t>glu-er</t></w>
@@ -63245,8 +63301,15 @@
 <w><t>go-by</t></w>
 <w><t>go=by</t></w>
 <w><t>GOC</t></w>
-<w><t>go=cart</t></w>
-<w><t>Go-clen-i-us</t></w>
+<word-choice>
+  <w><t>go=cart</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+  <w><t>go=kart</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+</word-choice>
+<word-choice>
+  <w><t>go=cart-ing</t><noun><singular/><convertible-to-possessive/></noun></w>
+  <w><t>go=cart-ing</t><noun><singular/><convertible-to-possessive/></noun></w>
+</word-choice>
+    <w><t>Go-clen-i-us</t></w>
 <w><t>God</t><noun><singular/><convertible-to-possessive/></noun></w>
 <w><t>god</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Go-dard</t></w>
@@ -65515,7 +65578,7 @@
 <w><t>guid-wil-lie</t></w>
 <w><t>Gui-enne</t></w>
 <w><t>guige</t></w>
-<w><t>guild</t></w>
+<w><t>guild</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>guil-der</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Guild-ford</t></w>
 <w><t>guild-hall</t></w>
@@ -66412,7 +66475,7 @@
 <phrase><t>Hail Mar-y</t></phrase>
 <w><t>hail-stone</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>hail-stoned</t></w>
-<w><t>hail-storm</t></w>
+<w><t>hail-storm</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Hail-wood</t></w>
 <w><t>Hai-nan</t></w>
 <phrase><t>Hai-nan Tao</t></phrase>
@@ -67221,7 +67284,7 @@
 <w><t>hand-sewed</t></w>
 <w><t>hand-sew-ing</t></w>
 <w><t>hand-sewn</t></w>
-<w><t>hand-shake</t></w>
+<w><t>hand-shake</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>hand-shak-er</t></w>
 <w><t>hand-shak-ing</t></w>
 <w><t>hand-some</t></w>
@@ -68100,7 +68163,7 @@
 <w><t>head-frame</t></w>
 <w><t>head-gear</t></w>
 <w><t>head-hunt</t></w>
-<w><t>head-hunt-er</t></w>
+<w><t>head-hunt-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>head-hunt-ing</t></w>
 <w><t>head=hunt-ing</t></w>
 <w><t>head-i-er</t></w>
@@ -68569,7 +68632,7 @@
 <w><t>Hei-drun</t></w>
 <w><t>Hei-duc</t></w>
 <w><t>Hei-duk</t></w>
-<w><t>heif-er</t></w>
+<w><t>heif-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Hei-fetz</t></w>
 <w><t>heigh</t></w>
 <w><t>height</t><noun><pluralizable/></noun></w>
@@ -68636,9 +68699,9 @@
 <w><t>Hel-den-te-nor</t></w>
 <w><t>hel-den-ten-ors</t></w>
 <w><t>hel-den-ten-te-no-re</t></w>
-<w><t>Hel-en</t></w>
+<w><t>Hel-en</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>Hel-e-na</t></w>
-<w><t>He-le-na</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>He-le-na</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>He-lene</t></w>
 <w><t>He-le-nor</t></w>
 <w><t>Hel-ens</t></w>
@@ -70866,7 +70929,7 @@
 <w><t>hol-pen</t></w>
 <w><t>hols</t></w>
 <w><t>Holst</t></w>
-<w><t>Hol-stein</t></w>
+<w><t>Hol-stein</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Hol-stein=Frie-sian</t></w>
 <w><t>hol-ster</t></w>
 <w><t>hol-stered</t></w>
@@ -72056,7 +72119,7 @@
 <w><t>huff-ish-ness</t></w>
 <w><t>huff-y</t></w>
 <w><t>Hu-fuf</t></w>
-<w><t>hug</t></w>
+<w><t>hug</t><verb><regular-root/></verb></w>
 <w><t>huge</t></w>
 <w><t>Hü-gel</t></w>
 <w><t>huge-ly</t></w>
@@ -72346,7 +72409,7 @@
 <w><t>hur-cheon</t></w>
 <w><t>Hurd</t></w>
 <w><t>hur-dies</t></w>
-<w><t>hur-dle</t></w>
+<w><t>hur-dle</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>hur-dler</t></w>
 <w><t>hurds</t></w>
 <w><t>hur-dy=gur-dies</t></w>
@@ -72890,11 +72953,11 @@
 <w><t>Hy-met-ti-us</t></w>
 <w><t>Hy-met-tus</t></w>
 <w><t>hymn</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
-<w><t>hym-nal</t></w>
+<w><t>hym-nal</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>hym-nar-i-a</t></w>
 <w><t>hym-nar-i-um</t></w>
 <w><t>hym-na-ry</t></w>
-<w><t>hymn-book</t></w>
+<w><t>hymn-book</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>hymn-er</t></w>
 <w><t>hym-nist</t></w>
 <w><t>hymn-less</t></w>
@@ -74934,7 +74997,7 @@
 <w><t>Im-o-gene</t></w>
 <w><t>Imp</t></w>
 <w><t>imp</t></w>
-<w><t>im-pact</t></w>
+<w><t>im-pact</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>im-pact-ed</t></w>
 <w><t>im-pact-ful</t></w>
 <w><t>im-pac-tion</t></w>
@@ -75363,7 +75426,7 @@
 <w><t>im-preg-na-ble-ness</t></w>
 <w><t>im-preg-na-bly</t></w>
 <w><t>im-preg-na-ta-ble</t></w>
-<w><t>im-preg-nate</t></w>
+<w><t>im-preg-nate</t><verb><regular-root/></verb></w>
 <w><t>im-preg-na-tion</t></w>
 <w><t>im-preg-na-tor</t></w>
 <w><t>im-preg-na-to-ry</t></w>
@@ -75509,7 +75572,7 @@
 <section description="In">
 <w><t>in</t><noun><pluralizable/></noun></w>
 <w><t>I-na</t></w>
-<w><t>in-a-bil-i-ty</t></w>
+<w><t>in-a-bil-i-ty</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>in ab-sen-ti-a</t></phrase>
 <w><t>in-ac-ces-si-bil-i-ty</t></w>
 <w><t>in-ac-ces-si-ble</t></w>
@@ -80074,7 +80137,7 @@
 <w><t>Ir-gun</t></w>
 <w><t>Ir-gun-ist</t></w>
 <phrase><t>Ir-i-an Bar-at</t></phrase>
-<phrase><t>Ir-i-an Ja-ya</t></phrase>
+<w><t>Ir-i-an Ja-ya</t></w>
 <w><t>I-ri-cise</t></w>
 <w><t>I-ri-cised</t></w>
 <w><t>I-ri-cis-ing</t></w>
@@ -80539,7 +80602,7 @@
 <w><t>Is-lam-ized</t></w>
 <w><t>Is-lam-iz-ing</t></w>
 <w><t>is-land</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
-<w><t>is-land-er</t></w>
+<w><t>is-land-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>is-land-ish</t></w>
 <w><t>is-land-less</t></w>
 <w><t>is-land-like</t></w>
@@ -81575,7 +81638,7 @@
 <w><t>Jean</t></w>
 <w><t>Jean=Chris-tophe</t></w>
 <w><t>Jean-er-ette</t></w>
-<w><t>Jean-ie</t></w>
+<w><t>Jean-ie</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Jean-net-ta</t></w>
 <w><t>Jean-nette</t></w>
 <w><t>Jean-nie</t></w>
@@ -83913,7 +83976,7 @@
 <w><t>kil-li-fish-es</t></w>
 <w><t>kil-li-ki-nic</t></w>
 <w><t>kil-li-ki-nick</t></w>
-<w><t>kill-ing</t></w>
+<w><t>kill-ing</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><lemma>kill</lemma><vf/></verb></w>
 <w><t>kill-ing-ly</t></w>
 <w><t>kil-loch</t></w>
 <w><t>kil-lock</t></w>
@@ -84542,6 +84605,7 @@
 <w><t>know-ing</t></w>
 <w><t>know-ing-ly</t></w>
 <w><t>know-ing-ness</t></w>
+<w><t>know=it=all</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>knowl-edg-a-ble</t></w>
 <w><t>knowl-edg-a-ble-ness</t></w>
 <w><t>knowl-edg-a-bly</t></w>
@@ -85663,7 +85727,7 @@
 <w><t>lam</t></w>
 <w><t>Lam</t></w>
 <w><t>la-m</t></w>
-<w><t>la-ma</t></w>
+<w><t>la-ma</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>La-ma-ism</t></w>
 <w><t>La-ma-ist</t></w>
 <w><t>La-ma-is-tic</t></w>
@@ -86144,6 +86208,7 @@
 <w><t>lap-streak</t></w>
 <w><t>lap-sus</t></w>
 <phrase><t>Lap-tev Sea</t></phrase>
+<w><t>lap-top</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>La-pu-ta</t></w>
 <w><t>lap-wing</t></w>
 <w><t>la-que-i</t></w>
@@ -86162,7 +86227,7 @@
 <w><t>lar-ce-nous</t></w>
 <w><t>lar-ce-nous-ly</t></w>
 <w><t>lar-ce-ny</t></w>
-<w><t>larch</t></w>
+<w><t>larch</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>larch-er</t></w>
 <w><t>Larch-mont</t></w>
 <w><t>lard</t></w>
@@ -86655,10 +86720,10 @@
 <w><t>law-ren-ci-um</t></w>
 <w><t>Law-ren-tian</t></w>
 <phrase><t>Law So-ci-e-ty</t></phrase>
-<w><t>Law-son</t></w>
+<w><t>Law-son</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <phrase><t>law sta-tion-er</t></phrase>
 <w><t>law-suit</t></w>
-<w><t>Law-ton</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>Law-ton</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>law-yer</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>law-yer-like</t></w>
 <w><t>law-yer-ly</t></w>
@@ -87447,7 +87512,7 @@
 <w><t>Le-pan-to</t></w>
 <w><t>Le-paute</t></w>
 <w><t>Le-pa-ya</t></w>
-<w><t>lep-er</t></w>
+<w><t>lep-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>le-pid-o-lite</t></w>
 <w><t>lep-i-dop-ter-a</t></w>
 <w><t>Lep-i-dop-ter-a</t></w>
@@ -88294,9 +88359,9 @@
 <w><t>like-li-hood</t></w>
 <w><t>like-li-ness</t></w>
 <w><t>like-ly</t></w>
-<w><t>like=mind-ed</t></w>
-<w><t>like=mind-ed-ly</t></w>
-<w><t>like=mind-ed-ness</t></w>
+<w><t>like=mind-ed</t><adjective/></w>
+<w><t>like=mind-ed-ly</t><adverb/></w>
+<w><t>like=mind-ed-ness</t><noun><singular/></noun></w>
 <w><t>lik-en</t><verb><regular-root/></verb></w>
 <w><t>like-ness</t></w>
 <w><t>lik-er</t></w>
@@ -88613,7 +88678,7 @@
 <w><t>lin-i-ment</t></w>
 <w><t>li-nin</t></w>
 <w><t>lin-ing</t></w>
-<w><t>link</t></w>
+<w><t>link</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>link-age</t></w>
 <w><t>link-boy</t></w>
 <w><t>linked</t></w>
@@ -88820,7 +88885,7 @@
 <w><t>lir-i-o-den-dron</t></w>
 <w><t>lir-i-pipe</t></w>
 <w><t>lir-i-poop</t></w>
-<w><t>Li-sa</t></w>
+<w><t>Li-sa</t><noun><convertible-to-possessive/><proper/></noun></w>
 <w><t>Lis-bo-a</t></w>
 <w><t>Lis-bon</t></w>
 <w><t>Li-se</t></w>
@@ -89502,10 +89567,13 @@
 <w><t>log-o-mach-ic</t></w>
 <w><t>lo-gom-a-chist</t></w>
 <w><t>lo-gom-a-chy</t></w>
+<w><t>log-o-ma-ni-a</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>log-o-ma-ni-ac</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>log-o-pae-dics</t></w>
 <w><t>log-o-pe-di-a</t></w>
 <w><t>log-o-pe-dic</t></w>
 <w><t>log-o-pe-dics</t></w>
+<w><t>log-o-phile</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>log-or-rhe-a</t></w>
 <w><t>log-or-rhe-ic</t></w>
 <w><t>log-or-rhoe-a</t></w>
@@ -91101,7 +91169,7 @@
 <w><t>mac-in-tosh</t></w>
 <w><t>Mac-I-ver</t></w>
 <w><t>mack</t></w>
-<w><t>Mac-kay</t></w>
+<w><t>Mac-kay</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>Ma-cke</t></w>
 <w><t>Mack-en-sen</t></w>
 <w><t>Mac-ken-zie</t></w>
@@ -92809,7 +92877,7 @@
 <w><t>marked</t></w>
 <w><t>mark-ed-ly</t></w>
 <w><t>mark-ed-ness</t></w>
-<w><t>mark-er</t></w>
+<w><t>mark-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>mark-er=off</t></w>
 <w><t>mar-kers=off</t></w>
 <w><t>mar-ket</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
@@ -93146,7 +93214,7 @@
 <w><t>ma-ser</t></w>
 <w><t>Mas-e-ru</t></w>
 <w><t>Ma-se-ru</t></w>
-<w><t>mash</t></w>
+<w><t>mash</t><verb><regular-root/></verb></w>
 <w><t>Mash-ar-brum</t></w>
 <w><t>Mash-er-brum</t></w>
 <w><t>mash-gi-ach</t></w>
@@ -93978,8 +94046,7 @@
 <w><t>Me-chan-ics-burg</t></w>
 <w><t>Me-chan-ics-ville</t></w>
 <w><t>mech-a-nise</t></w>
-<w><t>mech-an-ism</t></w>
-<w><t>mech-a-nism</t></w>
+<w><t>mech-an-ism</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>mech-an-isma</t></w>
 <w><t>mech-a-nis-mic</t></w>
 <w><t>mech-a-nist</t></w>
@@ -94127,7 +94194,7 @@
 <w><t>med-i-tat-ed</t></w>
 <w><t>med-i-tat-ing</t></w>
 <w><t>med-i-tat-ing-ly</t></w>
-<w><t>med-i-ta-tion</t><noun><singular/><convertible-to-possessive/></noun></w>
+<w><t>med-i-ta-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>med-i-ta-tive-ly</t></w>
 <w><t>med-i-ta-tive-ness</t></w>
 <w><t>med-i-ta-tor</t></w>
@@ -95895,7 +95962,7 @@
 <phrase><t>Mid-dle States</t></phrase>
 <phrase><t>Mid-dle Tem-ple</t></phrase>
 <phrase><t>mid-dle term</t></phrase>
-<w><t>Mid-dle-ton</t></w>
+<w><t>Mid-dle-ton</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>mid-dle-tone</t></w>
 <w><t>Mid-dle-town</t></w>
 <phrase><t>mid-dle watch</t></phrase>
@@ -96334,7 +96401,7 @@
 <w><t>mine-field</t></w>
 <w><t>mine-lay-er</t></w>
 <w><t>Min-e-o-la</t></w>
-<w><t>min-er</t></w>
+<w><t>min-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>min-er-al</t></w>
 <w><t>min-er-al-ise</t></w>
 <w><t>min-er-al-ised</t></w>
@@ -97192,8 +97259,8 @@
 <w><t>mis-spac-ing</t></w>
 <w><t>mis-speak</t></w>
 <w><t>mis-speak-ing</t></w>
-<w><t>mis-spell</t></w>
-<w><t>mis-spell-ing</t></w>
+<w><t>mis-spell</t><verb><regular-root/></verb></w>
+<w><t>mis-spell-ing</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>mis-spelt</t></w>
 <w><t>mis-spend</t></w>
 <w><t>mis-spoke</t></w>
@@ -97899,7 +97966,7 @@
 <w><t>mo-nar-da</t></w>
 <w><t>mon-as</t></w>
 <w><t>mon-as-te-ri-al</t></w>
-<w><t>mon-as-ter-y</t></w>
+<w><t>mon-as-ter-y</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>mo-nas-tic</t></w>
 <w><t>mo-nas-ti-cal</t></w>
 <w><t>mo-nas-ti-cal-ly</t></w>
@@ -97964,11 +98031,11 @@
 <w><t>mon-ger</t></w>
 <w><t>mon-go</t></w>
 <w><t>mon-goe</t></w>
-<w><t>Mon-gol</t></w>
+<w><t>Mon-gol</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>mon-gol</t></w>
 <w><t>Mon-go-li-a</t></w>
 <w><t>mon-go-li-an</t></w>
-<w><t>Mon-go-li-an</t></w>
+<w><t>Mon-go-li-an</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>mon-go-li-an id-i-o-cy</t></phrase>
 <w><t>Mon-go-li-an-ism</t></w>
 <phrase><t>Mon-go-li-an Peo-ple’s Re-pub-lic</t></phrase>
@@ -98869,7 +98936,7 @@
 <w><t>moth-i-est</t></w>
 <w><t>moth-proof</t></w>
 <w><t>moth-y</t></w>
-<w><t>mo-tif</t></w>
+<w><t>mo-tif</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Mo-ti-lal</t></w>
 <w><t>mo-tile</t></w>
 <w><t>mo-til-i-ty</t></w>
@@ -98942,7 +99009,11 @@
 <w><t>mot-tled</t></w>
 <w><t>mot-tle-ment</t></w>
 <w><t>mot-tler</t></w>
-<w><t>mot-to</t></w>
+<w><t>mot-to</t><noun><singular/></noun></w>
+<word-choice>
+  <w><t>mot-toes</t><noun><plural/></noun></w>
+  <w><t>mot-tos</t><noun><plural/></noun></w>
+</word-choice>
 <w><t>mot-tram-ite</t></w>
 <w><t>Mo-tu</t></w>
 <phrase><t>mo-tu pro-pri-o</t></phrase>
@@ -99301,7 +99372,7 @@
 <w><t>Mul-ci-ber</t></w>
 <w><t>mulct</t><noun><pluralizable/><convertible-to-possessive/></noun><verb/></w>
 <w><t>Mul-doon</t></w>
-<w><t>mule</t><noun><plural/><convertible-to-possessive/></noun></w>
+<w><t>mule</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Mule-shoe</t></w>
 <phrase><t>mule skin-ner</t></phrase>
 <w><t>mu-le-ta</t></w>
@@ -100270,9 +100341,13 @@
 </section>
 </section>
 <section description="N">
+<section description="N abbrev">
 <w><t>N/F</t></w>
 <w><t>N/S/F</t></w>
 <w><t>N.C.</t><abbrev referenced-word="North Carolina"/></w>
+</section>
+
+<section description="Na">
 <w><t>NAAFI</t></w>
 <w><t>nab</t></w>
 <w><t>Na-bal</t></w>
@@ -100711,7 +100786,7 @@
 <w><t>Na-tick</t></w>
 <w><t>na-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Na-tion-al</t></w>
-<w><t>na-tion-al</t></w>
+<w><t>na-tion-al</t><noun><pluralizable/><convertible-to-possessive/></noun><adjective></adjective></w>
 <phrase><t>na-tion-al ac-count-ing</t></phrase>
 <phrase><t>na-tion-al an-them</t></phrase>
 <phrase><t>Na-tion-al As-sem-bly</t></phrase>
@@ -100919,6 +100994,9 @@
 <w><t>Na-zi-mo-va</t></w>
 <w><t>na-zir</t></w>
 <w><t>Naz-i-rite</t></w>
+</section>
+
+<section description="Nb to Nd">
 <w><t>N-berg</t></w>
 <w><t>NBG</t></w>
 <w><t>N=bomb</t></w>
@@ -100929,6 +101007,9 @@
 <w><t>Nde-be-le</t></w>
 <w><t>Ndja-me-na</t></w>
 <w><t>Ndo-la</t></w>
+</section>
+
+<section description="Ne">
 <w><t>Ne-ae-ra</t></w>
 <w><t>Neagh</t></w>
 <w><t>Neal</t></w>
@@ -100953,6 +101034,7 @@
 <w><t>neat</t><adjective><extensible/></adjective></w>
 <w><t>neat-en</t></w>
 <w><t>neath</t></w>
+<w><t>’neath</t><contraction referenced-word="beneath"/></w>
 <w><t>neat-ly</t></w>
 <w><t>neat-ness</t></w>
 <w><t>neb</t></w>
@@ -101487,6 +101569,7 @@
 <w><t>ne-ral</t></w>
 <w><t>Ner-bud-da</t></w>
 <w><t>NERC</t></w>
+<w><t>nerd</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Ne-re-id</t></w>
 <w><t>ne-re-is</t></w>
 <w><t>Ne-re-us</t></w>
@@ -101752,7 +101835,7 @@
 <w><t>ne-void</t></w>
 <w><t>Nev-ski</t></w>
 <w><t>ne-vus</t></w>
-<w><t>new</t></w>
+<w><t>new</t><adjective><extensible/></adjective></w>
 <phrase><t>New Am-ster-dam</t></phrase>
 <w><t>New-ark</t></w>
 <phrase><t>New Bed-ford</t></phrase>
@@ -101866,7 +101949,7 @@
 <w><t>news-i-ness</t></w>
 <w><t>news-less</t></w>
 <w><t>news-less-ness</t></w>
-<w><t>news-let-ter</t></w>
+<w><t>news-let-ter</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>news-mag-a-zine</t></w>
 <w><t>news-man</t></w>
 <w><t>news-mon-ger</t></w>
@@ -101906,6 +101989,9 @@
 <w><t>nex-us</t></w>
 <w><t>Ney</t></w>
 <phrase><t>Nez Per-cé</t></phrase>
+</section>
+
+<section description="Nf to Ng">
 <w><t>NFL</t><abbrev referenced-word="National Football League"/></w>
 <w><t>NGA</t></w>
 <w><t>ngai-o</t></w>
@@ -101916,6 +102002,9 @@
 <w><t>ngo-ma</t></w>
 <w><t>Ngu-ni</t></w>
 <w><t>ngwee</t></w>
+</section>
+
+<section description="Ni">
 <w><t>ni-a-cin</t></w>
 <w><t>ni-a-cin-a-mide</t></w>
 <w><t>Ni-ag-a-ra</t></w>
@@ -102419,6 +102508,9 @@
 <w><t>ni-zam-ate</t></w>
 <phrase><t>Nizh-ni Nov-go-rod</t></phrase>
 <phrase><t>Nizh-ni Ta-gil</t></phrase>
+</section>
+
+<section description="Nj to Nn">
 <w><t>Njord</t></w>
 <w><t>Njorth</t></w>
 <w><t>NKGB</t></w>
@@ -102432,6 +102524,9 @@
 <w><t>Nnam-di</t></w>
 <w><t>NNE</t></w>
 <w><t>NNW</t></w>
+</section>
+
+<section description="No">
 <w><t>no</t><noun><singular/></noun></w>
 <w><t>no=ac-count</t></w>
 <w><t>No-a-chi-an</t></w>
@@ -108337,6 +108432,9 @@
 <w><t>Noyes</t></w>
 <w><t>Noy-on</t></w>
 <w><t>noz-zle</t></w>
+</section>
+
+<section description="Np to Nt">
 <w><t>NPA</t></w>
 <w><t>N-pak-tos</t></w>
 <w><t>NPL</t></w>
@@ -108351,6 +108449,9 @@
 <w><t>NTP</t></w>
 <w><t>n=tu-ple</t></w>
 <w><t>n=type</t></w>
+</section>
+
+<section description="Nu">
 <w><t>NUAAW</t></w>
 <w><t>nu-ance</t></w>
 <w><t>nu-anc-es</t></w>
@@ -108645,8 +108746,14 @@
 <w><t>nu=val-ue</t></w>
 <phrase><t>nux vom-i-ca</t></phrase>
 <w><t>nuz-zle</t></w>
+</section>
+
+<section description="Nv to Nw">
 <w><t>n-v</t></w>
 <w><t>NWT</t></w>
+</section>
+
+<section description="Ny to Nz">
 <w><t>Ny-ack</t></w>
 <w><t>nya-la</t></w>
 <w><t>Nyan-ja</t></w>
@@ -108708,6 +108815,7 @@
 <w><t>Nyx</t></w>
 <w><t>NZBC</t></w>
 </section>
+</section>
 
 <section description="O">
 <w><t>o/c</t></w>
@@ -109728,7 +109836,7 @@
 <phrase><t>Old Har-ry</t></phrase>
 <phrase><t>Old High Ger-man</t></phrase>
 <phrase><t>Old Ice-land-ic</t></phrase>
-<w><t>old-ie</t></w>
+<w><t>old-ie</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>Old I-rish</t></phrase>
 <phrase><t>Old King-dom</t></phrase>
 <phrase><t>old la-dy</t></phrase>
@@ -110048,7 +110156,7 @@
 <w><t>on-lay</t></w>
 <w><t>on-lay-ing</t></w>
 <w><t>on=lim-its</t></w>
-<w><t>on=line</t></w>
+<w><t>on-line</t><adjective></adjective><adverb/></w>
 <w><t>on-look-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>on-ly</t></w>
 <w><t>on-ly=be-got-ten</t></w>
@@ -110493,7 +110601,7 @@
 <w><t>op-ti-mized</t></w>
 <w><t>op-ti-miz-ing</t></w>
 <w><t>op-ti-mum</t></w>
-<w><t>op-tion</t></w>
+<w><t>op-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>op-tion-al</t></w>
 <w><t>op-tion-al-i-ty</t></w>
 <w><t>op-tion-al-ly</t></w>
@@ -110812,7 +110920,7 @@
 <w><t>Or-i-gen-ism</t></w>
 <w><t>Or-i-gen-ist</t></w>
 <w><t>Or-i-gen-is-tic</t></w>
-<w><t>or-i-gin</t></w>
+<w><t>or-i-gin</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>o-rig-i-na-ble</t></w>
 <w><t>o-rig-i-nal</t><noun><pluralizable/><convertible-to-possessive/></noun><adjective/></w>
 <w><t>o-rig-i-nal-i-ty</t></w>
@@ -114016,11 +114124,12 @@
 <w><t>o-ver-se-cu-ri-ty</t></w>
 <w><t>o-ver-se-cur-ly</t></w>
 <w><t>o-ver-se-da-tion</t></w>
-<w><t>o-ver-see</t></w>
+<w><t>o-ver-see</t><verb><regular-root value="false"/></verb></w>
 <w><t>o-ver-seed</t></w>
 <w><t>o-ver-see-ing</t></w>
 <w><t>o-ver-seen</t></w>
 <w><t>o-ver-se-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>o-ver-sees</t><verb><lemma>oversee</lemma></verb></w>
 <w><t>o-ver-sell</t></w>
 <w><t>o-ver-sell-ing</t></w>
 <w><t>o-ver-sen-si-ble</t></w>
@@ -114489,7 +114598,7 @@
 <w><t>Ox-en-stjer-na</t></w>
 <w><t>ox-eye</t></w>
 <w><t>ox=eyed</t></w>
-<w><t>Ox-ford</t></w>
+<w><t>Ox-ford</t><noun><convertible-to-possessive/></noun></w>
 <w><t>ox-ford</t></w>
 <phrase><t>Ox-ford ac-cent</t></phrase>
 <phrase><t>Ox-ford bags</t></phrase>
@@ -116215,7 +116324,7 @@
 <w><t>parl-ey-voo</t></w>
 <w><t>par-lia-ment</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Par-lia-ment</t></w>
-<w><t>par-lia-men-tar-i-an</t></w>
+<w><t>par-lia-men-tar-i-an</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Par-lia-men-tar-i-an</t></w>
 <w><t>par-lia-men-tar-i-an-ism</t></w>
 <w><t>par-lia-men-ta-ri-ly</t></w>
@@ -117465,7 +117574,7 @@
 <w><t>pee-wee</t></w>
 <w><t>pee-wit</t></w>
 <w><t>Peg</t></w>
-<w><t>peg</t></w>
+<w><t>peg</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>Pe-ga-si-an</t></w>
 <w><t>Peg-a-sus</t></w>
 <w><t>peg-board</t></w>
@@ -119106,6 +119215,7 @@
 <w><t>pfen-nigs</t></w>
 <w><t>Pfitz-ner</t></w>
 <w><t>Pforz-heim</t></w>
+<w><t>pg.</t><abbrev referenced-word="page"/></w>
 <w><t>PGA</t></w>
 <w><t>phac-o-lite</t></w>
 <w><t>Phae-a</t></w>
@@ -119735,8 +119845,8 @@
 <w><t>pho-to-con-duc-tive</t></w>
 <w><t>pho-to-con-duc-tiv-i-ty</t></w>
 <w><t>pho-to-con-duc-tor</t></w>
-<w><t>pho-to-cop-i-er</t></w>
-<w><t>pho-to-cop-y</t></w>
+<w><t>pho-to-cop-i-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>pho-to-cop-y</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>pho-to-cur-rent</t></w>
 <w><t>pho-to-dis-in-te-gra-tion</t></w>
 <w><t>pho-to-dis-so-ci-a-tion</t></w>
@@ -120413,7 +120523,7 @@
 <w><t>pig-gish-ly</t></w>
 <w><t>pig-gish-ness</t></w>
 <w><t>Pig-gott</t></w>
-<w><t>pig-gy</t></w>
+<w><t>pig-gy</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>pig-gy-back</t></w>
 <phrase><t>pig-gy bank</t></phrase>
 <w><t>pig=head-ed</t></w>
@@ -120578,7 +120688,7 @@
 <w><t>pim-ple</t></w>
 <w><t>pim-pled</t></w>
 <w><t>pim-ply</t></w>
-<w><t>pin</t></w>
+<w><t>pin</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>pi-ña</t></w>
 <w><t>pi-na-ceous</t></w>
 <phrase><t>pi-na cloth</t></phrase>
@@ -121671,7 +121781,7 @@
 <w><t>plo-ce</t></w>
 <w><t>plod</t></w>
 <w><t>plod-ded</t></w>
-<w><t>plod-der</t></w>
+<w><t>plod-der</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>plod-ding</t></w>
 <w><t>plod-ding-ly</t></w>
 <w><t>plod-ding-ness</t></w>
@@ -122002,8 +122112,8 @@
 <w><t>po-em</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>poe-nol-o-gy</t></w>
 <w><t>po-e-sy</t></w>
-<w><t>poet</t></w>
 <w><t>po-et</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>poet.</t><abbrev referenced-word="poetic"/></w>
 <w><t>po-et-as-ter</t></w>
 <w><t>po-et-as-ter-ing</t></w>
 <w><t>po-et-as-ter-ism</t></w>
@@ -123244,7 +123354,7 @@
 <w><t>post-en-ceph-a-lit-ic</t></w>
 <w><t>post=E-o-cene</t></w>
 <w><t>post-ep-i-lep-tic</t></w>
-<w><t>post-er</t></w>
+<w><t>post-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>poste res-tante</t></phrase>
 <w><t>pos-ter-i-ad</t></w>
 <w><t>pos-te-ri-or</t></w>
@@ -131042,6 +131152,7 @@
 </section>
 
 <section description="Q">
+<w><t>q</t><abbrev referenced-word="question"/><noun><pluralizable/></noun></w>
 <w><t>q. v.</t><abbrev referenced-word="quod vode (for which, see)"/></w>
 <phrase><t>Qa-boos bin Said</t></phrase>
 <w><t>Qad-a-rite</t></w>
@@ -133858,7 +133969,7 @@
 <w><t>re-a-rouse</t></w>
 <w><t>re-a-roused</t></w>
 <w><t>re-a-rous-ing</t></w>
-<w><t>re-ar-range</t></w>
+<w><t>re-ar-range</t><verb><regular-root/></verb></w>
 <w><t>re-ar-range-a-ble</t></w>
 <w><t>re-ar-ranged</t></w>
 <w><t>re-ar-range-ment</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -133997,8 +134108,10 @@
 <w><t>Re-bec-ca</t></w>
 <w><t>re-beck</t></w>
 <w><t>Re-bek-ah</t></w>
-<w><t>reb-el</t></w>
-<w><t>re-bel</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
+<ambiguous-word>
+  <w><t>reb-el</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+  <w><t>re-bel</t><verb><regular-root/></verb></w>
+</ambiguous-word>
 <w><t>reb-el-dom</t></w>
 <w><t>reb-el-like</t></w>
 <w><t>re-bel-lion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -136645,7 +136758,7 @@
 <w><t>re-mod-u-lat-ed</t></w>
 <w><t>re-mod-u-lat-ing</t></w>
 <w><t>re-mo-lade</t></w>
-<w><t>re-mold</t></w>
+<w><t>re-mold</t><verb><regular-root/></verb></w>
 <w><t>re-mol-li-fied</t></w>
 <w><t>re-mol-li-fy</t></w>
 <w><t>re-mol-li-fy-ing</t></w>
@@ -137072,7 +137185,7 @@
 <w><t>re-pique</t></w>
 <w><t>re-place</t><verb><regular-root/></verb></w>
 <w><t>re-placed</t></w>
-<w><t>re-place-ment</t></w>
+<w><t>re-place-ment</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>re-plac-ing</t></w>
 <w><t>re-plan</t></w>
 <w><t>re-plane</t></w>
@@ -137497,7 +137610,7 @@
 <w><t>res-e-da</t></w>
 <w><t>re-se-da</t></w>
 <w><t>res-e-da-ceous</t></w>
-<w><t>re-seed</t></w>
+<w><t>re-seed</t><verb><regular-root/></verb></w>
 <w><t>re-seek</t></w>
 <w><t>re-seek-ing</t></w>
 <w><t>re-seg-re-gate</t></w>
@@ -139005,7 +139118,7 @@
 <w><t>rhum-ba</t></w>
 <w><t>rhum-ba-tron</t></w>
 <w><t>rhy-ac-o-lite</t></w>
-<w><t>rhyme</t></w>
+<w><t>rhyme</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <phrase><t>rhyme roy-al</t></phrase>
 <w><t>rhyme-ster</t></w>
 <w><t>rhym-ing</t></w>
@@ -141198,7 +141311,7 @@
 <w><t>sad</t><adjective><extensible/></adjective></w>
 <w><t>sa-da-qat</t></w>
 <w><t>Sa-dat</t></w>
-<w><t>sad-den</t></w>
+<w><t>sad-den</t><verb><regular-root/></verb></w>
 <w><t>sad-dhu</t></w>
 <w><t>sad-dle</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>sad-dle-back</t></w>
@@ -141287,7 +141400,7 @@
 <w><t>saf-ra-nine</t></w>
 <w><t>saf-rol</t></w>
 <w><t>saf-role</t></w>
-<w><t>sag</t></w>
+<w><t>sag</t><verb><regular-root/></verb></w>
 <w><t>sa-ga</t></w>
 <w><t>sa-ga-cious</t></w>
 <w><t>sa-ga-cious-ly</t></w>
@@ -141725,7 +141838,7 @@
 <w><t>sal-vag-er</t></w>
 <w><t>sal-vag-ing</t></w>
 <w><t>Sal-var-san</t></w>
-<w><t>sal-va-tion</t></w>
+<w><t>sal-va-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>sal-va-tion-al</t></w>
 <phrase><t>Sal-va-tion Ar-my</t></phrase>
 <w><t>sal-va-tion-ism</t></w>
@@ -142550,8 +142663,7 @@
 <w><t>sav-ing-ly</t></w>
 <phrase><t>sav-ings ac-count</t></phrase>
 <phrase><t>sav-ings bank</t></phrase>
-<w><t>sav-ior</t></w>
-<w><t>Sav-ior</t></w>
+<w><t>sav-ior</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>sav-ior-hood</t></w>
 <w><t>sav-ior-ship</t></w>
 <w><t>sav-iour</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -143135,10 +143247,10 @@
 <w><t>school-child</t></w>
 <w><t>school-chil-dren</t></w>
 <w><t>School-craft</t></w>
-<w><t>school-fel-low</t></w>
-<w><t>school-girl</t></w>
+<w><t>school-fel-low</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>school-girl</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>school-girl-ish</t></w>
-<w><t>school-house</t></w>
+<w><t>school-house</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>school-hous-es</t></w>
 <w><t>school-ie</t></w>
 <w><t>school-ing</t></w>
@@ -146701,6 +146813,7 @@
 <w><t>se-tal</t></w>
 <w><t>se-tar-i-a</t></w>
 <phrase><t>set a-side</t></phrase>
+<w><t>set-back</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Se-t-bal</t></w>
 <phrase><t>set chis-el</t></phrase>
 <phrase><t>se ten-ant</t></phrase>
@@ -146812,7 +146925,7 @@
 <w><t>Sé-vi-gné</t></w>
 <w><t>Se-ville</t></w>
 <phrase><t>Se-ville or-ange</t></phrase>
-<w><t>sew</t></w>
+<w><t>sew</t><verb><regular-root/></verb></w>
 <w><t>sew-a-ble</t></w>
 <w><t>sew-age</t></w>
 <phrase><t>sew-age farm</t></phrase>
@@ -147758,7 +147871,7 @@
 <phrase><t>shoot-ing star</t></phrase>
 <phrase><t>shoot-ing stick</t></phrase>
 <w><t>shoots</t><verb><vf></vf></verb></w>
-<w><t>shop</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>shop</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <phrase><t>shop a-round</t></phrase>
 <phrase><t>shop as-sis-tant</t></phrase>
 <w><t>shop-ful</t></w>
@@ -148128,7 +148241,7 @@
 <w><t>Sic-i-ly</t></w>
 <w><t>sick</t></w>
 <w><t>sick-bay</t></w>
-<w><t>sick-en</t></w>
+<w><t>sick-en</t><verb><regular-root/></verb></w>
 <w><t>sick-en-er</t></w>
 <w><t>sick-en-ing</t></w>
 <w><t>sick-en-ing-ly</t></w>
@@ -149844,7 +149957,7 @@
 <w><t>sluice-way</t></w>
 <w><t>sluic-ing</t></w>
 <w><t>sluit</t></w>
-<w><t>slum</t></w>
+<w><t>slum</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>slum-ber</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>slum-ber-er</t></w>
 <w><t>slum-ber-land</t></w>
@@ -149958,7 +150071,8 @@
 <w><t>smear-i-est</t></w>
 <w><t>smear-i-ness</t></w>
 <w><t>smear-y</t></w>
-<w><t>Smea-ton</t></w>
+<w><t>Smea-ton</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
+<w><t>Smea-ton-i-an</t><adjective/></w>
 <w><t>smec-tic</t></w>
 <w><t>Smed-ley</t></w>
 <w><t>smeek</t></w>
@@ -150595,7 +150709,7 @@
 <w><t>so-ci-op-a-thy</t></w>
 <w><t>so-ci-o-po-lit-i-cal</t></w>
 <w><t>so-ci-o-psy-cho-log-i-cal</t></w>
-<w><t>sock</t></w>
+<w><t>sock</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>sock a-way</t></phrase>
 <w><t>sock-dol-a-ger</t></w>
 <w><t>sock-dol-o-ger</t></w>
@@ -151011,7 +151125,7 @@
 <w><t>some-day</t></w>
 <w><t>some-deal</t></w>
 <w><t>some-how</t></w>
-<w><t>some-one</t></w>
+<w><t>some-one</t><noun><singular/><convertible-to-possessive/></noun><pronoun></pronoun></w>
 <w><t>some-place</t></w>
 <w><t>Som-er-dale</t></w>
 <w><t>som-er-sault</t></w>
@@ -151104,7 +151218,7 @@
 <w><t>so-nif-er-ous</t></w>
 <w><t>son-less</t></w>
 <w><t>son-like</t></w>
-<w><t>son-net</t></w>
+<w><t>son-net</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>son-net-eer</t></w>
 <w><t>son-net-ise</t></w>
 <w><t>son-net-ised</t></w>
@@ -151573,7 +151687,7 @@
 <w><t>Spa</t></w>
 <w><t>Spaak</t></w>
 <w><t>Spaatz</t></w>
-<w><t>space</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>space</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>space-band</t></w>
 <phrase><t>space cap-sule</t></phrase>
 <w><t>space-craft</t></w>
@@ -151636,7 +151750,7 @@
 <w><t>spal-peen</t></w>
 <w><t>Spam</t></w>
 <w><t>Span</t></w>
-<w><t>span</t></w>
+<w><t>span</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>spa-nae-mi-a</t></w>
 <w><t>spa-nae-mic</t></w>
 <w><t>span-cel</t></w>
@@ -151705,7 +151819,7 @@
 <w><t>spar-ing</t></w>
 <w><t>spar-ing-ly</t></w>
 <w><t>spar-ing-ness</t></w>
-<w><t>spark</t></w>
+<w><t>spark</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>Spark</t></w>
 <phrase><t>spark cham-ber</t></phrase>
 <w><t>spark-er</t></w>
@@ -152026,7 +152140,7 @@
 <w><t>spell-down</t></w>
 <w><t>spell-er</t></w>
 <w><t>spel-li-can</t></w>
-<w><t>spell-ing</t></w>
+<w><t>spell-ing</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>spell-ing bee</t></phrase>
 <w><t>spell-ing-ly</t></w>
 <phrase><t>spell-ing pro-nun-ci-a-tion</t></phrase>
@@ -152947,7 +153061,7 @@
 <w><t>spur</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>spurge</t></w>
 <phrase><t>spurge lau-rel</t></phrase>
-<w><t>Spur-geon</t></w>
+<w><t>Spur-geon</t><noun><pluralizable/><convertible-to-possessive/><proper/></noun></w>
 <w><t>spu-ri-ous</t></w>
 <w><t>spu-ri-ous-ly</t></w>
 <w><t>spu-ri-ous-ness</t></w>
@@ -152962,7 +153076,7 @@
 <w><t>spurr-ite</t></w>
 <w><t>spur=row-el</t></w>
 <w><t>spur-ry</t></w>
-<w><t>spurt</t></w>
+<w><t>spurt</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>spurt-er</t></w>
 <w><t>spur-tive</t></w>
 <w><t>spur-tive-ly</t></w>
@@ -153259,7 +153373,7 @@
 <w><t>stad-le</t></w>
 <w><t>stadt-hold-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>stadt-hold-er-ship</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
-<w><t>staff</t></w>
+<w><t>staff</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Staf-fa</t></w>
 <phrase><t>staff col-lege</t></phrase>
 <w><t>staff-er</t></w>
@@ -153875,11 +153989,12 @@
 <w><t>steel-work</t></w>
 <w><t>steel-work-er</t></w>
 <w><t>steel-works</t></w>
+<w><t>steel-y</t><adjective><extensible/></adjective></w>
 <w><t>steel-yard</t></w>
 <w><t>Steen</t></w>
 <w><t>steen-bok</t></w>
 <w><t>steen-ing</t></w>
-<w><t>steep</t></w>
+<w><t>steep</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb><adjective><extensible/></adjective></w>
 <w><t>steep-en</t></w>
 <w><t>steep-er</t></w>
 <w><t>stee-ple</t></w>
@@ -154999,7 +155114,7 @@
 <w><t>streak-like</t></w>
 <w><t>streak-y</t></w>
 <w><t>stream</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
-<w><t>stream-er</t></w>
+<w><t>stream-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>stream-i-er</t></w>
 <w><t>stream-i-est</t></w>
 <w><t>stream-i-ness</t></w>
@@ -158734,7 +158849,7 @@
 <w><t>Sup-pé</t></w>
 <w><t>sup-pe-da-ne-a</t></w>
 <w><t>sup-pe-da-ne-um</t></w>
-<w><t>sup-per</t></w>
+<w><t>sup-per</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>sup-per club</t></phrase>
 <w><t>sup-per-less</t></w>
 <w><t>sup-per-time</t></w>
@@ -159628,7 +159743,7 @@
 <w><t>syl-la-bize</t></w>
 <w><t>syl-la-bized</t></w>
 <w><t>syl-la-biz-ing</t></w>
-<w><t>syl-la-ble</t></w>
+<w><t>syl-la-ble</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>syl-lab-o-gram</t></w>
 <w><t>syl-lab-og-ra-phy</t></w>
 <w><t>syl-la-bub</t></w>
@@ -160110,6 +160225,7 @@
 </section>
 
 <section description="T">
+<section description="Ta">
 <w><t>Taal</t></w>
 <w><t>Ta-al</t></w>
 <w><t>taa-ta</t></w>
@@ -160159,7 +160275,7 @@
 <phrase><t>ta-ble salt</t></phrase>
 <w><t>ta-ble-spoon</t></w>
 <w><t>ta-ble-spoon-ful</t></w>
-<w><t>tab-let</t></w>
+<w><t>tab-let</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>tab-let-ed</t></w>
 <phrase><t>ta-ble ten-nis</t></phrase>
 <w><t>tab-let-ing</t></w>
@@ -160257,7 +160373,7 @@
 <w><t>tack-ies</t></w>
 <w><t>tack-i-est</t></w>
 <w><t>tack-i-ness</t></w>
-<w><t>tack-le</t></w>
+<w><t>tack-le</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>tack-ler</t></w>
 <w><t>tack-less</t></w>
 <w><t>tack-ling</t></w>
@@ -161188,6 +161304,9 @@
 <phrase><t>Tay-side Re-gion</t></phrase>
 <w><t>Taze-well</t></w>
 <w><t>taz-za</t></w>
+</section>
+
+<section description="Tb to Td">
 <w><t>T=bev-el</t></w>
 <w><t>T-bi</t></w>
 <w><t>Tbi-li-si</t></w>
@@ -161200,6 +161319,9 @@
 <w><t>tcher-vo-netz</t></w>
 <w><t>tcher-vo-von-tzi</t></w>
 <phrase><t>t dis-tri-bu-tion</t></phrase>
+</section>
+
+<section description="Te to Tg">
 <w><t>tea</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>tea-ber-ry</t></w>
 <phrase><t>tea bis-cuit</t></phrase>
@@ -162369,7 +162491,7 @@
 <w><t>text</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>text-book</t></w>
 <w><t>text-book-ish</t></w>
-<w><t>tex-tile</t></w>
+<w><t>tex-tile</t><noun><pluralizable/><convertible-to-possessive/></nou...
 
[truncated message content]

[FOray-commit] SF.net SVN: foray:[14955] trunk/foray/foray-orthograp hy/src/main

From: <vic...@us...> - 2026-07-31 09:57:34

Revision: 14955
          http://sourceforge.net/p/foray/code/14955
Author:   victormote
Date:     2026-07-31 09:57:31 +0000 (Fri, 31 Jul 2026)
Log Message:
-----------
Conform to aXSL change: Add word-choice element to group proper but conflicting spellings together.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/DictionaryParser.java

Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-30 17:23:12 UTC (rev 14954)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-31 09:57:31 UTC (rev 14955)
@@ -63599,8 +63599,10 @@
 <w><t>Good-a-cre</t></w>
 <phrase><t>good af-ter-noon</t></phrase>
 <phrase><t>good ar-vo</t></phrase>
-<w><t>good-by</t></w>
-<w><t>good-bye</t></w>
+<word-choice>
+  <w><t>good-bye</t><noun><pluralizable/></noun><interjection/></w>
+  <w><t>good-by</t><noun><pluralizable/></noun><interjection/></w>
+</word-choice>
 <phrase><t>good eve-ning</t></phrase>
 <w><t>good=fel-low-ship</t></w>
 <w><t>good=for=noth-ing</t></w>

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/DictionaryParser.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/DictionaryParser.java	2026-07-30 17:23:12 UTC (rev 14954)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/DictionaryParser.java	2026-07-31 09:57:31 UTC (rev 14955)
@@ -193,6 +193,9 @@
     /** The system ID of the input source being parsed. */
     private URL systemId;
 
+    /** The list of words inside a word-choice element. */
+    private List<StringWord> currentWordChoice;
+
     /**
      * Constructor.
      * @param orthographyServer The orthography server.
@@ -362,6 +365,7 @@
                     StringUtils.EMPTY_STRING, attributes, "allow-duplicates", false);
 
             this.lastWord = StringUtils.EMPTY_STRING;
+            this.currentWordChoice = null;
             break;
         }
         case "import-standard-dictionary": {
@@ -463,6 +467,11 @@
             this.unresolvedDuplicate = true;
             break;
         }
+        /* TODO: Store word-choice in a way that allows a selection to be enforced. */
+        case "word-choice": {
+            this.currentWordChoice = new ArrayList<StringWord>(2);
+            break;
+        }
         default: {
             throw new IllegalStateException("Unknown element started: " + localName + ", " +
                     getLocationString(getLocator()));
@@ -479,8 +488,13 @@
         case "w": {
             final StringWord word = new StringWord(this.posBuilder.value(), this.currentSegments);
             final String actualContent = word.getActualContent().toString();
-            checkCollation(actualContent, word.getCollatingContent().toString());
 
+            /* Within a word-choice, the words may be out of order, so we check only the first item. */
+            if (this.currentWordChoice == null
+                    || this.currentWordChoice.size() < 1) {
+                checkCollation(actualContent, word.getCollatingContent().toString());
+            }
+
             if (this.ambiguousWordComponents == null) {
                 /* Add it to normal words. */
                 if (this.currentDictionaryElement.wordMap.get(actualContent) == null) {
@@ -494,6 +508,9 @@
             } else {
                 this.ambiguousWordComponents.add(word);
             }
+            if (this.currentWordChoice != null) {
+                this.currentWordChoice.add(word);
+            }
             break;
         }
         case "t": {
@@ -626,6 +643,10 @@
             this.unresolvedDuplicate = false;
             break;
         }
+        case "word-choice": {
+            this.currentWordChoice = null;
+            break;
+        }
         default: {
             throw new IllegalStateException("Unknown element ended: " + localName);
         }

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14954] trunk/foray/foray-orthograp hy/src/main/java/org/foray/orthography/util/SpellChecker.java

From: <vic...@us...> - 2026-07-30 17:23:15

Revision: 14954
          http://sourceforge.net/p/foray/code/14954
Author:   victormote
Date:     2026-07-30 17:23:12 +0000 (Thu, 30 Jul 2026)
Log Message:
-----------
Minor cleanup.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java	2026-07-30 17:05:44 UTC (rev 14953)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java	2026-07-30 17:23:12 UTC (rev 14954)
@@ -367,7 +367,6 @@
         element.column = columnString == null ? -1 : Integer.parseInt(columnString);
         element.xpath = XPATH_ATTRIBUTE.getValue(attributes);
         this.elementStack.push(element);
-
     }
 
     @Override
@@ -375,15 +374,13 @@
         if (this.elementStack.size() < 1) {
             throw new SAXException("Element stack is empty but should not be.");
         }
-        final WritingSystem4a oldWritingSystem = getCurrentWritingSystem();
 
-        final Element element;
+        final Element currentElement = this.elementStack.peek();
+
         if ("marker".equals(localName)) {
-            /* The "marker" element did not go on the stack. Don't pop it or check it. */
-            element = null;
+            /* The "marker" element did not go on the stack. Don't try to check it. */
         } else {
-            element = this.elementStack.pop();
-            if (! element.matches(uri, localName, qName)) {
+            if (! currentElement.matches(uri, localName, qName)) {
                 throw new SAXException("Closing element does not match top of stack.");
             }
         }
@@ -394,15 +391,14 @@
              * startElement. What is in the text buffer right now should be exactly the content of the "word"
              * element. */
             final String text = getAndClearText();
-            lexer.addWordToken(text, oldWritingSystem);
+            lexer.addWordToken(text, getCurrentWritingSystem());
             break;
         }
         case ("text"): {
             /* We are at the end of a terminal element. Check the spelling. */
             final String text = getAndClearText();
-            lexer.addUntokenized(text, oldWritingSystem);
-            final TextElement textElement = (TextElement) element;
-            checkWords(textElement);
+            lexer.addUntokenized(text, getCurrentWritingSystem());
+            checkWords();
             break;
         }
         case ("marker"): {
@@ -419,14 +415,20 @@
             throw new SAXException("Unexpected end element: " + localName);
         }
         }
+
+        if ("marker".equals(localName)) {
+            /* The "marker" element did not go on the stack. Don't pop it or check it. */
+        } else {
+            this.elementStack.pop();
+        }
+
     }
 
 
     /**
      * Iterate the tokens from the Lexer and spell-check the words.
-     * @param element The element containing the content being tokenized.
      */
-    private void checkWords(final TextElement element) {
+    private void checkWords() {
         this.lexer.lock();
 
         /* Writing system should never be null, but orthography could be. */
@@ -450,7 +452,7 @@
                 } else {
                     final Word4a word = orthography.recognizeWord(token, this.lexer);
                     if (word == null) {
-                        final String message = createNotFoundMessage(token, element);
+                        final String message = createNotFoundMessage(token);
                         this.output.println(message);
                         this.notFoundCounter ++;
                     }
@@ -463,20 +465,20 @@
     /**
      * Creates the text message to be reported to the user if a token is not found.
      * @param token The token being reported.
-     * @param element The raw element containing {@code token}.
      * @return The message to be reported to the user.
      */
-    String createNotFoundMessage(final Lexer.Token token, final TextElement element) {
-
+    String createNotFoundMessage(final Lexer.Token token) {
         final FlowElement flowElement = getCurrentFlow();
+        final Element topElement = this.elementStack.peek();
+        final TextElement textElement = (TextElement) topElement;
 
         final String lineAndColumn;
-        if (element.line != -1
-                | element.column != -1) {
-            final int actualLine = element.line + token.getLine() - 1;
+        if (textElement.line != -1
+                | textElement.column != -1) {
+            final int actualLine = textElement.line + token.getLine() - 1;
             int actualColumn = token.getColumn();
             if (token.getLine() == 1) {
-                actualColumn += element.column;
+                actualColumn += textElement.column;
             }
             lineAndColumn = String.format(" (%s:%s)", actualLine, actualColumn);
         } else {
@@ -484,10 +486,10 @@
         }
 
         final String xpath;
-        if (element.xpath == null) {
+        if (textElement.xpath == null) {
             xpath = StringUtils.EMPTY_STRING;
         } else {
-            xpath = String.format(" (xpath: %s)", element.xpath);
+            xpath = String.format(" (xpath: %s)", textElement.xpath);
         }
 
         final String marker;

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14953] trunk/foray/foray-orthograp hy/src/main/java/org/foray/orthography/util/SpellChecker.java

From: <vic...@us...> - 2026-07-30 17:05:47

Revision: 14953
          http://sourceforge.net/p/foray/code/14953
Author:   victormote
Date:     2026-07-30 17:05:44 +0000 (Thu, 30 Jul 2026)
Log Message:
-----------
Fix problem of nested text elements picking up the wrong writing system.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java	2026-07-30 16:19:25 UTC (rev 14952)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java	2026-07-30 17:05:44 UTC (rev 14953)
@@ -322,6 +322,9 @@
             break;
         }
         case ("text"): {
+            /* Push any existing content to the lexer. */
+            final String text = getAndClearText();
+            lexer.addUntokenized(text, oldWritingSystem);
             createAndPushTextElement(uri, localName, qName, attributes);
             break;
         }

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14952] trunk/foray/foray-orthograp hy/src

From: <vic...@us...> - 2026-07-30 16:19:28

Revision: 14952
          http://sourceforge.net/p/foray/code/14952
Author:   victormote
Date:     2026-07-30 16:19:25 +0000 (Thu, 30 Jul 2026)
Log Message:
-----------
1. Remove requirement for server to create a Lexer4a. 2. Roll up SpellChecker method, for clarity.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerIcu4jBreakIterator.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/OrthographyServer4aStandard.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerEnglishIcu4jTests.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerEnglishJavaTests.java

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java	2026-07-30 14:13:14 UTC (rev 14951)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java	2026-07-30 16:19:25 UTC (rev 14952)
@@ -349,10 +349,8 @@
 
     /**
      * Constructor.
-     * @param server The parent server.
      */
-    public Lexer4a(final OrthographyServer4aStandard server) {
-//        this.server = server;
+    public Lexer4a() {
         this.isLocked = false;
         this.iteratorIndex = 0;
     }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerIcu4jBreakIterator.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerIcu4jBreakIterator.java	2026-07-30 14:13:14 UTC (rev 14951)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerIcu4jBreakIterator.java	2026-07-30 16:19:25 UTC (rev 14952)
@@ -52,14 +52,6 @@
      * are cached because they are expensive to create. */
     private Map<WritingSystem, BreakIterator> iteratorMap = new HashMap<WritingSystem, BreakIterator>();
 
-    /**
-     * Constructor.
-     * @param server The parent server.
-     */
-    public LexerIcu4jBreakIterator(final OrthographyServer4aStandard server) {
-        super(server);
-    }
-
     @Override
     protected IntSequence findRawBreaks(final CharSequence sequence, final WritingSystem writingSystem) {
         BreakIterator wordBreakIterator = this.iteratorMap.get(writingSystem);

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java	2026-07-30 14:13:14 UTC (rev 14951)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java	2026-07-30 16:19:25 UTC (rev 14952)
@@ -42,14 +42,6 @@
  */
 public class LexerJavaBreakIterator extends Lexer4a {
 
-    /**
-     * Constructor.
-     * @param server The parent server.
-     */
-    public LexerJavaBreakIterator(final OrthographyServer4aStandard server) {
-        super(server);
-    }
-
     @Override
     protected IntSequence findRawBreaks(final CharSequence sequence, final WritingSystem writingSystem) {
         final IntArrayBuilder result = new IntArrayBuilder(sequence.length());

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/OrthographyServer4aStandard.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/OrthographyServer4aStandard.java	2026-07-30 14:13:14 UTC (rev 14951)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/OrthographyServer4aStandard.java	2026-07-30 16:19:25 UTC (rev 14952)
@@ -176,7 +176,7 @@
     @Override
     public Lexer4a getLexer() {
         if (this.lexer == null) {
-            this.lexer = new LexerJavaBreakIterator(this);
+            this.lexer = new LexerJavaBreakIterator();
         }
         return this.lexer;
     }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java	2026-07-30 14:13:14 UTC (rev 14951)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java	2026-07-30 16:19:25 UTC (rev 14952)
@@ -440,7 +440,18 @@
                     orthography = this.server.getOrthography(token.getWritingSystem());
                 }
                 lastWritingSystem = token.getWritingSystem();
-                checkWord(orthography, token, element);
+                if (orthography == null) {
+                    /* Treat as an error. */
+                    final String message = "(no config) " + token.getText();
+                    this.output.println(message);
+                } else {
+                    final Word4a word = orthography.recognizeWord(token, this.lexer);
+                    if (word == null) {
+                        final String message = createNotFoundMessage(token, element);
+                        this.output.println(message);
+                        this.notFoundCounter ++;
+                    }
+                }
             }
         }
         lexer.clear();
@@ -447,30 +458,6 @@
     }
 
     /**
-     * Spell-check a word.
-     * @param orthography The orthography to be used to spell-check {@code word}.
-     * @param token The word token to be checked.
-     * @param element The element containing the content being tokenized.
-     */
-    private void checkWord(final Orthography4a orthography, final Lexer4a.Token4a token, final TextElement element) {
-        if (orthography == null) {
-            /* Treat as an error. */
-            final String message = "(no config) " + token.getText();
-            this.output.println(message);
-        } else {
-            final Word4a word = orthography.recognizeWord(token, this.lexer);
-            if (word != null) {
-                return;
-            }
-        }
-
-        final String message = createNotFoundMessage(token, element);
-        this.output.println(message);
-        this.notFoundCounter ++;
-    }
-
-
-    /**
      * Creates the text message to be reported to the user if a token is not found.
      * @param token The token being reported.
      * @param element The raw element containing {@code token}.

Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerEnglishIcu4jTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerEnglishIcu4jTests.java	2026-07-30 14:13:14 UTC (rev 14951)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerEnglishIcu4jTests.java	2026-07-30 16:19:25 UTC (rev 14952)
@@ -54,8 +54,7 @@
      */
     @BeforeEach
     public void setupTest() throws IOException, OrthographyException {
-        final OrthographyServer4aStandard server = createServer();
-        this.out = new LexerIcu4jBreakIterator(server);
+        this.out = new LexerIcu4jBreakIterator();
     }
 
     @Override

Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerEnglishJavaTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerEnglishJavaTests.java	2026-07-30 14:13:14 UTC (rev 14951)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerEnglishJavaTests.java	2026-07-30 16:19:25 UTC (rev 14952)
@@ -49,8 +49,7 @@
      */
     @BeforeEach
     public void setupTest() throws IOException, OrthographyException {
-        final OrthographyServer4aStandard server = createServer();
-        this.out = new LexerJavaBreakIterator(server);
+        this.out = new LexerJavaBreakIterator();
     }
 
     @Override

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14951] trunk/foray/foray-orthograp hy/src/main/java/org/foray/orthography

From: <vic...@us...> - 2026-07-30 14:13:16

Revision: 14951
          http://sourceforge.net/p/foray/code/14951
Author:   victormote
Date:     2026-07-30 14:13:14 +0000 (Thu, 30 Jul 2026)
Log Message:
-----------
Move token-based word recognition logic from SpellChecker to Orthography4a, for reuse.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java	2026-07-30 13:27:21 UTC (rev 14950)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java	2026-07-30 14:13:14 UTC (rev 14951)
@@ -470,7 +470,7 @@
     }
 
     @Override
-    public Token previous() {
+    public Token4a previous() {
         if (! this.isLocked) {
             throw new IllegalStateException("This lexer is not locked.");
         }
@@ -482,6 +482,17 @@
         return returnToken;
     }
 
+    /**
+     * Does exactly what {@link #next()} does, but without incrementing the next token.
+     * This allows client code to see the next token without advancing to it.
+     * @return The next token.
+     */
+    public Token4a peekPrevious() {
+        final Token4a token = previous();
+        this.iteratorIndex ++;
+        return token;
+    }
+
     @Override
     public void remove() {
         throw new UnsupportedOperationException("Method \"remove\" is not supported.");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java	2026-07-30 13:27:21 UTC (rev 14950)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java	2026-07-30 14:13:14 UTC (rev 14951)
@@ -230,6 +230,36 @@
         return null;
     }
 
+    /**
+     * Recognizes a word from a lexer token and its lexer.
+     * @param token The token whose content should be converted to a word, if possible.
+     * @param lexer The lexer that produced {@code token}, in case context is needed.
+     * @return The word from this orthography that matches {@code token}, or null if none exists.
+     */
+    public Word4a recognizeWord(final Lexer4a.Token4a token, final Lexer4a lexer) {
+        if (token.getTokenType() != Lexer.TokenType.WORD) {
+            throw new IllegalArgumentException("Token must be a word token.");
+        }
+        final CharSequence text = token.getText();
+        Word4a recognizedWord = recognizeWord(text, 0, text.length(), null);
+        if (recognizedWord == null) {
+            final Lexer.Token savedToken = token.getImmutableCopy();
+            if (lexer.hasNext()) {
+                final Lexer4a.Token4a nextToken = lexer.peekNext();
+                if (nextToken.getTokenType() == Lexer.TokenType.AMBIGUOUS_TRAILING_PUNCTUATION) {
+                    final String testWord = savedToken.getText().toString() + nextToken.getText().toString();
+                    recognizedWord = recognizeWord(testWord, 0, testWord.length(), null);
+                    if (recognizedWord != null) {
+                        return recognizedWord;
+                    }
+                }
+            }
+        } else {
+            return recognizedWord;
+        }
+        return null;
+    }
+
     @Override
     public Word4a hyphenateUnrecognizedWord(final CharSequence word, final int offset, final int length) {
         /* The character sequence containing the characters in the word that we are looking for. */

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java	2026-07-30 13:27:21 UTC (rev 14950)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/SpellChecker.java	2026-07-30 14:13:14 UTC (rev 14951)
@@ -434,7 +434,7 @@
             orthography = this.server.getOrthography(lastWritingSystem);
         }
         while (lexer.hasNext()) {
-            final Lexer.Token token = lexer.next();
+            final Lexer4a.Token4a token = lexer.next();
             if (token.getTokenType() == TokenType.WORD) {
                 if (! lastWritingSystem.equals(token.getWritingSystem())) {
                     orthography = this.server.getOrthography(token.getWritingSystem());
@@ -452,27 +452,14 @@
      * @param token The word token to be checked.
      * @param element The element containing the content being tokenized.
      */
-    private void checkWord(final Orthography4a orthography, final Lexer.Token token, final TextElement element) {
-        CharSequence text = StringUtils.EMPTY_STRING;
+    private void checkWord(final Orthography4a orthography, final Lexer4a.Token4a token, final TextElement element) {
         if (orthography == null) {
             /* Treat as an error. */
-            text = "(no config) " + token.getText();
+            final String message = "(no config) " + token.getText();
+            this.output.println(message);
         } else {
-            text = token.getText();
-            Word4a recognizedWord = orthography.recognizeWord(text, 0, text.length(), null);
-            if (recognizedWord == null) {
-                final Lexer.Token savedToken = token.getImmutableCopy();
-                if (this.lexer.hasNext()) {
-                    final Lexer.Token nextToken = lexer.peekNext();
-                    if (nextToken.getTokenType() == Lexer.TokenType.AMBIGUOUS_TRAILING_PUNCTUATION) {
-                        final String testWord = savedToken.getText().toString() + nextToken.getText().toString();
-                        recognizedWord = orthography.recognizeWord(testWord, 0, testWord.length(), null);
-                        if (recognizedWord != null) {
-                            return;
-                        }
-                    }
-                }
-            } else {
+            final Word4a word = orthography.recognizeWord(token, this.lexer);
+            if (word != null) {
                 return;
             }
         }

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14950] trunk/foray/foray-orthograp hy/src/main/java/org/foray/orthography/Lexer4a.java

From: <vic...@us...> - 2026-07-30 13:27:23

Revision: 14950
          http://sourceforge.net/p/foray/code/14950
Author:   victormote
Date:     2026-07-30 13:27:21 +0000 (Thu, 30 Jul 2026)
Log Message:
-----------
Conform to aXSL change: Make Lexer implement ListIterator instead of Iterator, to improve client code understanding of context.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java	2026-07-30 11:02:16 UTC (rev 14949)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java	2026-07-30 13:27:21 UTC (rev 14950)
@@ -334,8 +334,9 @@
     /** The input that has been submitted for processing. */
     private Input input = new Input();
 
-    /** The index into the result arrays that will be used by the next call to {@link #next()}. */
-    private int nextResultIndex;
+    /** The current index within {@link output} to the iterator. The iterator's current position conceptually sits
+     * immediately after ({@link leafIndex} - 1) and immediately before ({@link leafIndex}). */
+    private int iteratorIndex;
 
     /** The list of output tokens to be returned. */
     private List<Token4a> output = new ArrayList<Token4a>();
@@ -353,6 +354,7 @@
     public Lexer4a(final OrthographyServer4aStandard server) {
 //        this.server = server;
         this.isLocked = false;
+        this.iteratorIndex = 0;
     }
 
     @Override
@@ -417,9 +419,23 @@
         this.input.items.clear();
         this.output.clear();
         this.isLocked = false;
+        this.iteratorIndex = 0;
     }
 
     @Override
+    public boolean hasNext() {
+        if (! this.isLocked) {
+            throw new IllegalStateException("This lexer is not locked.");
+        }
+        return this.iteratorIndex < this.output.size();
+    }
+
+    @Override
+    public int nextIndex() {
+        return this.iteratorIndex;
+    }
+
+    @Override
     public Token4a next() {
         if (! this.isLocked) {
             throw new IllegalStateException("This lexer is not locked.");
@@ -427,8 +443,8 @@
         if (! hasNext()) {
             throw new NoSuchElementException();
         }
-        final Token4a returnToken = this.output.get(this.nextResultIndex);
-        this.nextResultIndex ++;
+        final Token4a returnToken = this.output.get(nextIndex());
+        this.iteratorIndex ++;
         return returnToken;
     }
 
@@ -439,24 +455,54 @@
      */
     public Token4a peekNext() {
         final Token4a token = next();
-        this.nextResultIndex --;
+        this.iteratorIndex --;
         return token;
     }
 
     @Override
-    public boolean hasNext() {
+    public boolean hasPrevious() {
+        return this.iteratorIndex > 0;
+    }
+
+    @Override
+    public int previousIndex() {
+        return this.iteratorIndex - 1;
+    }
+
+    @Override
+    public Token previous() {
         if (! this.isLocked) {
             throw new IllegalStateException("This lexer is not locked.");
         }
-        return this.nextResultIndex < this.output.size();
+        if (! hasNext()) {
+            throw new NoSuchElementException();
+        }
+        final Token4a returnToken = this.output.get(previousIndex());
+        this.iteratorIndex --;
+        return returnToken;
     }
 
+    @Override
+    public void remove() {
+        throw new UnsupportedOperationException("Method \"remove\" is not supported.");
+    }
+
+    @Override
+    public void set(final Token e) {
+        throw new UnsupportedOperationException("Method \"set\" is not supported.");
+    }
+
+    @Override
+    public void add(final Token e) {
+        throw new UnsupportedOperationException("Method \"add\" is not supported.");
+    }
+
     /**
      * Tokenize the content and create the output.
      */
     private void process() {
         this.output.clear();
-        this.nextResultIndex = 0;
+        this.iteratorIndex = 0;
         if (this.input.items.size() < 1) {
             return;
         }

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14949] trunk/foray/foray-orthograp hy/src/main/data

From: <vic...@us...> - 2026-07-30 11:02:20

Revision: 14949
          http://sourceforge.net/p/foray/code/14949
Author:   victormote
Date:     2026-07-30 11:02:16 +0000 (Thu, 30 Jul 2026)
Log Message:
-----------
Normal dictionary editing.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml

Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-29 22:32:37 UTC (rev 14948)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-30 11:02:16 UTC (rev 14949)
@@ -856,7 +856,7 @@
 <w><t>ac-cept-ee</t></w>
 <w><t>ac-cept-er</t></w>
 <w><t>ac-cep-tor</t></w>
-<w><t>ac-cess</t></w>
+<w><t>ac-cess</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>ac-ces-sa-ri-ly</t></w>
 <w><t>ac-ces-sa-ri-ness</t></w>
 <w><t>ac-ces-sa-ry</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -3652,7 +3652,7 @@
 <w><t>a-lack-a-day</t></w>
 <w><t>a-lac-ri-tous</t></w>
 <w><t>a-lac-ri-ty</t></w>
-<w><t>A-lad-din</t></w>
+<w><t>A-lad-din</t><noun><convertible-to-possessive/><proper/></noun></w>
 <w><t>a-lae</t></w>
 <w><t>A-la-g</t></w>
 <w><t>A-la-gez</t></w>
@@ -16587,7 +16587,7 @@
 <w><t>bi-o-graph-ic</t></w>
 <w><t>bi-o-graph-i-cal</t></w>
 <w><t>bi-o-graph-i-cal-ly</t></w>
-<w><t>bi-og-ra-phy</t></w>
+<w><t>bi-og-ra-phy</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>bi-o-herm</t></w>
 <w><t>biol</t></w>
 <w><t>bi-o-log-ic</t></w>
@@ -17560,7 +17560,7 @@
 <w><t>blood-y-ing</t></w>
 <phrase><t>Blood-y Mar-y</t></phrase>
 <w><t>blood-y=mind-ed</t></w>
-<w><t>bloom</t></w>
+<w><t>bloom</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>bloomed</t></w>
 <w><t>bloom-er</t></w>
 <w><t>Bloo-mer</t></w>
@@ -18474,7 +18474,7 @@
 <w><t>boot-er-y</t></w>
 <w><t>Bo-o-tes</t></w>
 <w><t>Bo-ö-tes</t></w>
-<w><t>booth</t></w>
+<w><t>booth</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Booth</t></w>
 <w><t>Boo-thi-a</t></w>
 <phrase><t>Boo-thi-a Pen-in-su-la</t></phrase>
@@ -27442,7 +27442,7 @@
 <w><t>chor-do-phone</t></w>
 <w><t>chor-do-to-nal</t></w>
 <phrase><t>chord sym-bol</t></phrase>
-<w><t>chore</t></w>
+<w><t>chore</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>cho-re-a</t></w>
 <w><t>cho-re-al</t></w>
 <w><t>cho-re-at-ic</t></w>
@@ -33697,7 +33697,7 @@
 <w><t>corf</t></w>
 <w><t>Cor-fam</t></w>
 <w><t>Cor-fu</t></w>
-<w><t>cor-gi</t></w>
+<w><t>cor-gi</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Co-ri</t></w>
 <w><t>co-ri-a</t></w>
 <w><t>co-ri-a-ceous</t></w>
@@ -49860,6 +49860,7 @@
 <w><t>en-roll-ment</t></w>
 <w><t>en-rol-ment</t></w>
 <w><t>en-root</t></w>
+<w><t>en route</t></w>
 <w><t>Ens</t></w>
 <w><t>ens</t></w>
 <w><t>en-sam-ple</t><noun><pluralizable/></noun></w>
@@ -68103,7 +68104,7 @@
 <w><t>head-i-er</t></w>
 <w><t>head-i-est</t></w>
 <w><t>head-i-ly</t></w>
-<w><t>head-ing</t></w>
+<w><t>head-ing</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>head-lamp</t></w>
 <w><t>Head-land</t></w>
 <w><t>head-land</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -70062,9 +70063,7 @@
 <w><t>high=lev-el</t></w>
 <phrase><t>high=lev-el lan-guage</t></phrase>
 <w><t>high-life</t></w>
-<w><t>high-light</t></w>
-<w><t>high-light-ed</t></w>
-<w><t>high-light-ing</t></w>
+<w><t>high-light</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>high-line</t></w>
 <w><t>high-low</t></w>
 <w><t>high-ly</t></w>
@@ -82296,7 +82295,7 @@
 <w><t>jour-nal-ish</t></w>
 <w><t>jour-nal-is-ing</t></w>
 <w><t>jour-nal-ism</t></w>
-<w><t>jour-nal-ist</t></w>
+<w><t>jour-nal-ist</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>jour-nal-is-tic</t></w>
 <w><t>jour-nal-is-ti-cal-ly</t></w>
 <w><t>jour-nal-i-za-tion</t></w>
@@ -137236,7 +137235,7 @@
 <w><t>re-prime</t></w>
 <w><t>re-primed</t></w>
 <w><t>re-prim-ing</t></w>
-<w><t>re-print</t></w>
+<w><t>re-print</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>re-print-er</t></w>
 <w><t>re-pris-al</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>re-prise</t></w>
@@ -150278,7 +150277,7 @@
 <w><t>snipe</t></w>
 <w><t>snipe-fish</t></w>
 <w><t>snipe-like</t></w>
-<w><t>snip-er</t></w>
+<w><t>snip-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>snip-er-scope</t></w>
 <w><t>snipe’s-bill</t></w>
 <w><t>snipes-bill</t></w>
@@ -161239,7 +161238,7 @@
 <w><t>tea=of=heav-en</t></w>
 <w><t>tea-pot</t></w>
 <w><t>tea-poy</t></w>
-<w><t>tear</t></w>
+<w><t>tear</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>tear-a-ble</t></w>
 <w><t>tear-a-ble-ness</t></w>
 <phrase><t>tear a-way</t></phrase>
@@ -164506,7 +164505,7 @@
 <w><t>toot-sy=woot-sies</t></w>
 <w><t>toot-sy=woot-sy</t></w>
 <w><t>Too-woom-ba</t></w>
-<w><t>top</t></w>
+<w><t>top</t><noun><singular/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>top-arch</t></w>
 <w><t>to-paz</t></w>
 <w><t>To-paze</t></w>
@@ -167957,7 +167956,7 @@
 <w><t>Uj-jain</t></w>
 <w><t>Uj-pest</t></w>
 <phrase><t>U-jung Pan-dang</t></phrase>
-<w><t>UK</t><abbrev referenced-word="United Kingdom"/></w>
+<w><t>UK</t><abbrev referenced-word="United Kingdom"/><noun><singular/><convertible-to-possessive/></noun></w>
 <w><t>u-kase</t></w>
 <w><t>uke</t></w>
 <w><t>u-ke-le-le</t></w>

Modified: trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-29 22:32:37 UTC (rev 14948)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-30 11:02:16 UTC (rev 14949)
@@ -21,7 +21,8 @@
     <match desc="English ordinal ending in 0 or 4 thru 9">^[0-9]*[04-9]th(ly)?$</match>
     <match desc="English ordinal ending in 10 thru 19">^[0-9]*1[0-9]th(ly)?$</match>
     <match desc="English ordinal ending in multiple of 10">^[0-9]*[0-9]0th(ly)?$</match>
-    <match desc="A single capital letter, such as a person's initial">^[A-Z]$</match>
+    <match desc="A single capital letter, such as a person's initial">^[A-Z]\.?$</match>
+    <match desc="Two capital letters, such as a person's first and middle initials">^[A-Z]\.[A-Z]\.$</match>
     <match desc="Contracted year">^’[0-9]+$</match>
     <match desc="Two dimensions">^[0-9]{1,3}(,[0-9]{3})*(\.[0-9]*)?&#x00D7;[0-9]{1,3}(,[0-9]{3})*(\.[0-9]*)?$</match>
     <match desc="Standalone symbols">^[§\[\]\/=&#x2026;]$</match>

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14948] trunk/foray/foray-orthograp hy/src

From: <vic...@us...> - 2026-07-29 22:32:39

Revision: 14948
          http://sourceforge.net/p/foray/code/14948
Author:   victormote
Date:     2026-07-29 22:32:37 +0000 (Wed, 29 Jul 2026)
Log Message:
-----------
Conform to aXSL change: Simplify language, script, and country attributes. Move size and source to the comments.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/OrthographyParser.java
    trunk/foray/foray-orthography/src/test/resources/orthography-config.xml

Modified: trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-29 21:54:47 UTC (rev 14947)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-29 22:32:37 UTC (rev 14948)
@@ -162,7 +162,7 @@
     <resource-location parsed="false" url="file:../hyph-patterns/eng.xml"/>
   </hyphenation-patterns-resource>
 
-  <orthography language-iso-3char="eng" script-iso-4char="Latn" country-iso-3char="USA">
+  <orthography language="eng" script="Latn" country="USA">
     <match-rules reference="eng-Latn-match-rules"/>
     <dictionary reference="org.foray.eng.Latn.USA"/>
     <hyphenation-patterns reference="hyph-patterns-eng"/>
@@ -169,7 +169,7 @@
     <derivative-factories reference="eng-Latn-derivatives"/>
   </orthography>
 
-  <orthography language-iso-3char="eng" script-iso-4char="Latn" country-iso-3char="GBR">
+  <orthography language="eng" script="Latn" country="GBR">
     <match-rules reference="eng-Latn-match-rules"/>
     <dictionary reference="org.foray.eng.Latn.GBR"/>
     <hyphenation-patterns reference="hyph-patterns-eng"/>
@@ -176,7 +176,7 @@
     <derivative-factories reference="eng-Latn-derivatives"/>
   </orthography>
 
-  <orthography language-iso-3char="emen" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="emen" script="Latn" country="ZZZ">
     <match-rules reference="eng-Latn-match-rules"/>
     <dictionary reference="org.foray.emen.Latn.ZZZ"/>
     <hyphenation-patterns reference="hyph-patterns-eng"/>
@@ -184,55 +184,55 @@
     <derivative-factory class="org.foray.orthography.inflection.emen.EmenLatnSuffix_eth_Factory"/>
   </orthography>
 
-  <orthography language-iso-3char="lat" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="lat" script="Latn" country="ZZZ">
     <match-rules reference="lat-Latn-match-rules"/>
     <dictionary reference="org.foray.lat.Latn.ZZZ"/>
   </orthography>
 
-  <orthography language-iso-3char="ita" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="ita" script="Latn" country="ZZZ">
     <dictionary reference="org.foray.ita.Latn.ZZZ"/>
   </orthography>
 
-  <orthography language-iso-3char="fre" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="fre" script="Latn" country="ZZZ">
     <match-rules reference="fre-Latn-match-rules"/>
     <derivative-rules reference="fre-Latn-derivative-patterns"/>
     <dictionary reference="org.foray.fre.Latn.ZZZ"/>
   </orthography>
 
-  <orthography language-iso-3char="ger" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="ger" script="Latn" country="ZZZ">
     <derivative-rules reference="ger-Latn-derivative-patterns"/>
     <dictionary reference="org.foray.ger.Latn.ZZZ"/>
   </orthography>
 
-  <orthography language-iso-3char="grc" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="grc" script="Latn" country="ZZZ">
     <dictionary reference="org.foray.grc.Latn.ZZZ"/>
   </orthography>
 
-  <orthography language-iso-3char="grc" script-iso-4char="Grek" country-iso-3char="ZZZ">
+  <orthography language="grc" script="Grek" country="ZZZ">
     <dictionary reference="org.foray.grc.Grek.ZZZ"/>
   </orthography>
 
-  <orthography language-iso-3char="heb" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="heb" script="Latn" country="ZZZ">
     <dictionary reference="org.foray.heb.Latn.ZZZ"/>
   </orthography>
 
   <!-- Aramaic. -->
-  <orthography language-iso-3char="arc" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="arc" script="Latn" country="ZZZ">
     <dictionary reference="org.foray.arc.Latn.ZZZ"/>
   </orthography>
 
   <!-- Old Norse. -->
-  <orthography language-iso-3char="non" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="non" script="Latn" country="ZZZ">
     <dictionary reference="org.foray.non.Latn.ZZZ"/>
   </orthography>
 
   <!-- Polish. -->
-  <orthography language-iso-3char="pol" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="pol" script="Latn" country="ZZZ">
     <dictionary reference="org.foray.pol.Latn.ZZZ"/>
   </orthography>
 
   <!-- Portuguese. -->
-  <orthography language-iso-3char="por" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="por" script="Latn" country="ZZZ">
     <dictionary reference="org.foray.por.Latn.ZZZ"/>
   </orthography>
 

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/OrthographyParser.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/OrthographyParser.java	2026-07-29 21:54:47 UTC (rev 14947)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/OrthographyParser.java	2026-07-29 22:32:37 UTC (rev 14948)
@@ -390,9 +390,9 @@
      * @return The parsed writing system.
      */
     private WritingSystem4a parseWritingSystem(final Attributes attributes) {
-        final String languageString = attributes.getValue("language-iso-3char");
-        final String countryString = attributes.getValue("country-iso-3char");
-        final String scriptString = attributes.getValue("script-iso-4char");
+        final String languageString = attributes.getValue("language");
+        final String countryString = attributes.getValue("country");
+        final String scriptString = attributes.getValue("script");
         final Language4a language = Language4a.findFrom3Char(languageString);
         if (language == null) {
             errorMessage("Unable to find language for: {}", languageString);

Modified: trunk/foray/foray-orthography/src/test/resources/orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-29 21:54:47 UTC (rev 14947)
+++ trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-29 22:32:37 UTC (rev 14948)
@@ -97,47 +97,47 @@
     <resource-location parsed="false" url="file:../../main/data/hyph-patterns/spa.xml"/>
   </hyphenation-patterns-resource>
 
-  <orthography language-iso-3char="eng" script-iso-4char="Latn" country-iso-3char="USA">
+  <orthography language="eng" script="Latn" country="USA">
     <dictionary reference="org.foray.eng.Latn.ZZZ"/>
     <hyphenation-patterns reference="hyph-patterns-eng"/>
     <derivative-factories reference="derivatives-eng"/>
   </orthography>
 
-  <orthography language-iso-3char="eng" script-iso-4char="Zyyy" country-iso-3char="USA">
+  <orthography language="eng" script="Zyyy" country="USA">
     <dictionary reference="org.foray.eng.Latn.ZZZ"/>
     <hyphenation-patterns reference="hyph-patterns-eng"/>
     <derivative-factories reference="derivatives-eng"/>
   </orthography>
 
-  <orthography language-iso-3char="fin" script-iso-4char="Latn" country-iso-3char="FIN">
+  <orthography language="fin" script="Latn" country="FIN">
     <hyphenation-patterns reference="hyph-patterns-fin"/>
   </orthography>
 
-  <orthography language-iso-3char="hun" script-iso-4char="Latn" country-iso-3char="HUN">
+  <orthography language="hun" script="Latn" country="HUN">
     <hyphenation-patterns reference="hyph-patterns-hun"/>
   </orthography>
 
-  <orthography language-iso-3char="ita" script-iso-4char="Latn" country-iso-3char="ITA">
+  <orthography language="ita" script="Latn" country="ITA">
     <hyphenation-patterns reference="hyph-patterns-ita"/>
   </orthography>
 
-  <orthography language-iso-3char="pol" script-iso-4char="Latn" country-iso-3char="POL">
+  <orthography language="pol" script="Latn" country="POL">
     <hyphenation-patterns reference="hyph-patterns-pol"/>
   </orthography>
 
-  <orthography language-iso-3char="por" script-iso-4char="Latn" country-iso-3char="PRT">
+  <orthography language="por" script="Latn" country="PRT">
     <hyphenation-patterns reference="hyph-patterns-por"/>
   </orthography>
 
-  <orthography language-iso-3char="rus" script-iso-4char="Cyrl" country-iso-3char="RUS">
+  <orthography language="rus" script="Cyrl" country="RUS">
     <hyphenation-patterns reference="hyph-patterns-rus"/>
   </orthography>
     
-  <orthography language-iso-3char="spa" script-iso-4char="Latn" country-iso-3char="ESP">
+  <orthography language="spa" script="Latn" country="ESP">
     <hyphenation-patterns reference="hyph-patterns-spa"/>
   </orthography>
 
-  <orthography language-iso-3char="lat" script-iso-4char="Latn" country-iso-3char="ZZZ">
+  <orthography language="lat" script="Latn" country="ZZZ">
     <dictionary reference="org.foray.lat.Latn.ZZZ"/>
   </orthography>
 

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14947] trunk/foray/foray-orthograp hy/src/main/data/dictionaries

From: <vic...@us...> - 2026-07-29 21:54:51

Revision: 14947
          http://sourceforge.net/p/foray/code/14947
Author:   victormote
Date:     2026-07-29 21:54:47 +0000 (Wed, 29 Jul 2026)
Log Message:
-----------
Normal dictionary editing.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/data/dictionaries/emen-Latn-ZZZ.dict.xml

Added: trunk/foray/foray-orthography/src/main/data/dictionaries/emen-Latn-ZZZ.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/emen-Latn-ZZZ.dict.xml	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/emen-Latn-ZZZ.dict.xml	2026-07-29 21:54:47 UTC (rev 14947)
@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="UTF-8"?>
+
+<!DOCTYPE axsl-dictionary
+   PUBLIC "-//aXSL//DTD Dictionary V0.1//EN"
+   "http://www.axsl.org/dtds/0.1/en/axsl-dictionary.dtd">
+
+<axsl-dictionary
+    id="org.foray.emen.Latn.ZZZ"
+    language="emen" script="Latn" country="ZZZ"
+    hard-hyphen-char="=" soft-hyphen-char="-">
+<import-standard-dictionary id="org.foray.eng.Latn.GBR"/>
+
+<!--
+This dictionary contains words found in Early Modern English that 1) are not
+used in modern dictionaries, and 2) cannot be inferred from derivative forms.
+-->
+
+<w><t>bear-eth</t><verb><lemma>bear</lemma></verb></w>
+<w><t>bring-eth</t><verb><lemma>bring</lemma></verb></w>
+<w><t>cleans-eth</t><verb><lemma>cleanse</lemma></verb></w>
+<w><t>fad-eth</t><verb><lemma>fade</lemma></verb></w>
+<w><t>grow-eth</t><verb><lemma>grow</lemma></verb></w>
+<w><t>hear-eth</t><verb><lemma>hear</lemma></verb></w>
+<w><t>shin-eth</t><verb><lemma>shine</lemma></verb></w>
+<w><t>un-der-stand-eth</t><verb><lemma>understand</lemma></verb></w>
+
+
+</axsl-dictionary>


Property changes on: trunk/foray/foray-orthography/src/main/data/dictionaries/emen-Latn-ZZZ.dict.xml
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-29 21:54:00 UTC (rev 14946)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-29 21:54:47 UTC (rev 14947)
@@ -23237,7 +23237,7 @@
 <w><t>cap-tious</t></w>
 <w><t>cap-tious-ly</t></w>
 <w><t>cap-tious-ness</t></w>
-<w><t>cap-ti-vate</t></w>
+<w><t>cap-ti-vate</t><verb><regular-root/></verb></w>
 <w><t>cap-ti-vat-ed</t></w>
 <w><t>cap-ti-vat-ing</t></w>
 <w><t>cap-ti-vat-ing-ly</t></w>
@@ -27893,7 +27893,7 @@
 <w><t>church-wom-an</t></w>
 <w><t>church-wom-en</t></w>
 <w><t>church-y</t></w>
-<w><t>church-yard</t></w>
+<w><t>church-yard</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>chu-ri-dars</t></w>
 <w><t>chu-rin-ga</t></w>
 <w><t>churl</t></w>
@@ -29933,7 +29933,7 @@
 <w><t>cof-fered</t></w>
 <w><t>cof-fer-like</t></w>
 <w><t>Cof-fey-ville</t></w>
-<w><t>cof-fin</t></w>
+<w><t>cof-fin</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Cof-fin</t></w>
 <phrase><t>cof-fin bone</t></phrase>
 <w><t>coff-ing</t></w>
@@ -32692,7 +32692,7 @@
 <w><t>con-tain-a-ble</t></w>
 <w><t>con-tained</t></w>
 <w><t>con-tain-ed-ly</t></w>
-<w><t>con-tain-er</t></w>
+<w><t>con-tain-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>con-tain-er-board</t></w>
 <w><t>con-tain-er-ise</t></w>
 <w><t>con-tain-er-i-za-tion</t></w>
@@ -32859,7 +32859,7 @@
 <w><t>con-tort-ed</t></w>
 <w><t>con-tort-ed-ly</t></w>
 <w><t>con-tort-ed-ness</t></w>
-<w><t>con-tor-tion</t></w>
+<w><t>con-tor-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>con-tor-tion-al</t></w>
 <w><t>con-tor-tioned</t></w>
 <w><t>con-tor-tion-ist</t></w>
@@ -33085,7 +33085,7 @@
 <w><t>con-ven-ing</t></w>
 <w><t>con-ven-or</t></w>
 <w><t>con-vent</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
-<w><t>con-ven-ti-cle</t></w>
+<w><t>con-ven-ti-cle</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>con-ven-ti-cler</t></w>
 <w><t>con-ven-tic-u-lar</t></w>
 <w><t>con-ven-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -35231,7 +35231,7 @@
 <w><t>cra-zi-ly</t></w>
 <w><t>cra-zi-ness</t></w>
 <w><t>craz-ing</t></w>
-<w><t>cra-zy</t></w>
+<w><t>cra-zy</t><adjective><extensible/></adjective></w>
 <phrase><t>cra-zy bone</t></phrase>
 <phrase><t>cra-zy pav-ing</t></phrase>
 <phrase><t>cra-zy quilt</t></phrase>
@@ -40505,7 +40505,7 @@
 <w><t>dep-re-ter</t></w>
 <w><t>de-priv-a-ble</t></w>
 <w><t>de-priv-al</t></w>
-<w><t>dep-ri-va-tion</t><noun><plural/><convertible-to-possessive/></noun></w>
+<w><t>dep-ri-va-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>de-priv-a-tive</t></w>
 <w><t>de-prive</t><verb><regular-root/></verb></w>
 <w><t>de-prived</t></w>
@@ -64462,6 +64462,7 @@
 <w><t>Graves</t></w>
 <phrase><t>Graves’ dis-ease</t></phrase>
 <w><t>Graves-end</t></w>
+<w><t>grave-site</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>grav-est</t></w>
 <w><t>grave-stone</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Gra-vett-i-an</t></w>
@@ -73800,10 +73801,14 @@
 </section>
 
 <section description="I">
+<section description="I abbrev">
 <w><t>i/c</t></w>
 <w><t>I/O</t></w>
 <w><t>i.e.</t><abbrev referenced-word="id est"/><comment>Latin "that is."</comment></w>
 <w><t>i.&#xA0;e.</t><abbrev referenced-word="id est"/><comment>Latin "that is."</comment></w>
+</section>
+
+<section description="Ia">
 <w><t>I-ac-chus</t></w>
 <w><t>I-a-che</t></w>
 <w><t>IAEA</t></w>
@@ -73843,6 +73848,9 @@
 <w><t>i-at-ro-chem-is-try</t></w>
 <w><t>i-at-ro-gen-ic</t></w>
 <w><t>i-at-ro-ge-nic-i-ty</t></w>
+</section>
+
+<section description="Ib">
 <w><t>I-ba-da</t></w>
 <w><t>I-ba-dan</t></w>
 <w><t>I-ba-dhi</t></w>
@@ -73880,6 +73888,9 @@
 <w><t>Ib-se-ni-an</t></w>
 <w><t>Ib-sen-ism</t></w>
 <w><t>Ib-y-cus</t></w>
+</section>
+
+<section description="Ic">
 <w><t>I-c</t></w>
 <w><t>ICA</t></w>
 <w><t>I-ça</t></w>
@@ -74029,6 +74040,9 @@
 <w><t>ic-tus-es</t></w>
 <w><t>i-cy</t></w>
 <phrase><t>i-cy pole</t></phrase>
+</section>
+
+<section description="Id">
 <w><t>I’d</t></w>
 <w><t>i-d</t></w>
 <w><t>IDA</t></w>
@@ -74234,6 +74248,9 @@
 <w><t>i-dyl-lic</t></w>
 <w><t>i-dyl-li-cal-ly</t></w>
 <w><t>i-dyl-list</t></w>
+</section>
+
+<section description="Ie to If">
 <w><t>I-e-da</t></w>
 <w><t>IEE</t></w>
 <w><t>I-e-lene</t></w>
@@ -74247,6 +74264,9 @@
 <w><t>If-ni</t></w>
 <w><t>IFS</t></w>
 <w><t>I-fu-gao</t></w>
+</section>
+
+<section description="Ig to Ik">
 <w><t>Ig-bo</t></w>
 <w><t>Ig-dra-sil</t></w>
 <w><t>I-gerne</t></w>
@@ -74332,6 +74352,9 @@
 <w><t>I-ke-ya=Se-ki</t></w>
 <w><t>Ikh-na-ton</t></w>
 <w><t>i-kon</t></w>
+</section>
+
+<section description="Il">
 <w><t>I-la</t></w>
 <w><t>I-l-a</t></w>
 <w><t>i-lang=i-lang</t></w>
@@ -74584,6 +74607,9 @@
 <w><t>Il-se-dore</t></w>
 <w><t>ilth</t></w>
 <w><t>Il-ya</t></w>
+</section>
+
+<section description="Im">
 <w><t>I’m</t></w>
 <w><t>I-ma</t></w>
 <w><t>im-age</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -75477,6 +75503,9 @@
 <w><t>Im-re</t></w>
 <w><t>Im-roz</t></w>
 <w><t>IMS</t></w>
+</section>
+
+<section description="In">
 <w><t>in</t><noun><pluralizable/></noun></w>
 <w><t>I-na</t></w>
 <w><t>in-a-bil-i-ty</t></w>
@@ -77700,7 +77729,7 @@
 <w><t>in-sid-i-ous</t></w>
 <w><t>in-sid-i-ous-ly</t></w>
 <w><t>in-sid-i-ous-ness</t></w>
-<w><t>in-sight</t></w>
+<w><t>in-sight</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>in-sight-ful</t></w>
 <w><t>in-sig-ne</t></w>
 <w><t>in-sig-ni-a</t></w>
@@ -78892,6 +78921,7 @@
 <w><t>in-tern-ee</t></w>
 <w><t>in-ter-neg-a-tive</t></w>
 <w><t>in-terne-ship</t></w>
+<w><t>in-ter-net</t><noun><singular/><convertible-to-possessive/></noun></w>
 <w><t>in-ter-net-ted</t></w>
 <w><t>in-ter-neu-ral</t></w>
 <w><t>in-ter-neu-ron</t></w>
@@ -79876,6 +79906,9 @@
 <w><t>in-wrought</t></w>
 <w><t>in-ya-la</t></w>
 <w><t>i-nyl</t></w>
+</section>
+
+<section description="Io">
 <w><t>I-o</t></w>
 <w><t>Io-an-ni-na</t></w>
 <w><t>I-ob-a-tes</t></w>
@@ -79959,6 +79992,9 @@
 <w><t>IOW</t></w>
 <w><t>I-o-wa</t></w>
 <w><t>I-ox-us</t></w>
+</section>
+
+<section description="Ip to Iq">
 <w><t>IPA</t></w>
 <w><t>ip-e-cac</t></w>
 <w><t>ip-e-cac-u-an-ha</t></w>
@@ -79989,6 +80025,9 @@
 <w><t>Iq-bal</t></w>
 <w><t>I-qui-que</t></w>
 <w><t>I-qui-tos</t></w>
+</section>
+
+<section description="Ir">
 <w><t>IRA</t></w>
 <w><t>I-ra</t></w>
 <w><t>i-ra-cund</t></w>
@@ -80389,6 +80428,9 @@
 <w><t>Ir-ving</t></w>
 <w><t>Ir-ving-ton</t></w>
 <w><t>Ir-win</t></w>
+</section>
+
+<section description="Is">
 <w><t>I’s</t></w>
 <w><t>is</t></w>
 <w><t>I-s</t></w>
@@ -80801,6 +80843,9 @@
 <w><t>Is-tri-a</t></w>
 <w><t>Is-tri-an</t></w>
 <w><t>I-sus</t></w>
+</section>
+
+<section description="It to Iu">
 <w><t>it</t></w>
 <w><t>ita</t></w>
 <w><t>ITA</t></w>
@@ -80917,6 +80962,9 @@
 <w><t>I-tys</t></w>
 <w><t>Itz-hak</t></w>
 <w><t>I-u-lus</t></w>
+</section>
+
+<section description="Iv">
 <w><t>I-van</t></w>
 <w><t>I-van-hoe</t></w>
 <phrase><t>I-van III</t></phrase>
@@ -80952,6 +81000,9 @@
 <w><t>i-vy-ber-ry</t></w>
 <phrase><t>i-vy League</t></phrase>
 <w><t>i-vy-like</t></w>
+</section>
+
+<section description="Iw to Iz">
 <w><t>I-wa-o</t></w>
 <w><t>i-wis</t></w>
 <w><t>I-wo</t></w>
@@ -80984,6 +81035,7 @@
 <w><t>iz-zard</t></w>
 <w><t>iz-zat</t></w>
 </section>
+</section>
 
 <section description="J">
 <w><t>jaap</t></w>
@@ -89125,7 +89177,7 @@
 <w><t>l=nor-ep-i-neph-rine</t></w>
 <w><t>L-nos</t></w>
 <w><t>loach</t></w>
-<w><t>load</t></w>
+<w><t>load</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <phrase><t>load dis-place-ment</t></phrase>
 <w><t>load-ed</t></w>
 <w><t>load-er</t></w>
@@ -90900,8 +90952,12 @@
 </section>
 
 <section description="M">
+<section description="M abbrev">
 <w><t>M=16</t></w>
 <phrase><t>M=1 ri-fle</t></phrase>
+</section>
+
+<section description="Ma">
 <w><t>MA</t><abbrev referenced-word="Massachusetts"/></w>
 <w><t>ma’am</t></w>
 <w><t>maar</t></w>
@@ -92755,7 +92811,7 @@
 <w><t>mark-er</t></w>
 <w><t>mark-er=off</t></w>
 <w><t>mar-kers=off</t></w>
-<w><t>mar-ket</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>mar-ket</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>mar-ket-a-bil-i-ty</t></w>
 <w><t>mar-ket-a-ble</t></w>
 <w><t>mar-ket-a-ble-ness</t></w>
@@ -93712,6 +93768,9 @@
 <w><t>ma-zy</t></w>
 <w><t>maz-zard</t></w>
 <w><t>Maz-zi-ni</t></w>
+</section>
+
+<section description="Mb to Md">
 <w><t>MBA</t></w>
 <w><t>Mba-ba-ne</t></w>
 <w><t>Mban-da-ka</t></w>
@@ -93780,6 +93839,9 @@
 <w><t>M-doc</t></w>
 <w><t>MDS</t></w>
 <w><t>mdse</t></w>
+</section>
+
+<section description="Me">
 <w><t>me</t></w>
 <w><t>mea-con</t></w>
 <phrase><t>me-a cul-pa</t></phrase>
@@ -95246,7 +95308,7 @@
 <w><t>me-te-or-ol-o-gy</t></w>
 <w><t>me-te-or-o-path-o-log-ic</t></w>
 <phrase><t>me-te-or show-er</t></phrase>
-<w><t>me-ter</t></w>
+<w><t>me-ter</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Me-ter</t></w>
 <w><t>me-ter-age</t></w>
 <w><t>me-ter=can-dle</t></w>
@@ -95472,6 +95534,9 @@
 <w><t>mez-zo=so-pra-no</t></w>
 <w><t>mez-zo-tint</t></w>
 <w><t>mez-zo-tint-er</t></w>
+</section>
+
+<section description="Mf to Mi">
 <w><t>mfd</t></w>
 <w><t>mfg</t></w>
 <w><t>MFH</t></w>
@@ -97368,6 +97433,9 @@
 <w><t>miz-zen</t></w>
 <w><t>miz-zen-mast</t></w>
 <w><t>miz-zle</t></w>
+</section>
+
+<section description="Mj to Mn">
 <w><t>M-ji-co</t></w>
 <w><t>Mjoll-nir</t></w>
 <w><t>Mjöll-nir</t></w>
@@ -97405,6 +97473,9 @@
 <w><t>mne-mo-tech-nics</t></w>
 <w><t>Mnes-i-cles</t></w>
 <w><t>M-ni-drome</t></w>
+</section>
+
+<section description="Mo">
 <w><t>mo-a</t></w>
 <w><t>Mo-ab</t></w>
 <w><t>Mo-a-bite</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -97920,7 +97991,7 @@
 <w><t>mon-grel-ness</t></w>
 <w><t>mo-ni-al</t></w>
 <w><t>mon-ic</t></w>
-<w><t>Mon-i-ca</t></w>
+<w><t>Mon-i-ca</t><noun><convertible-to-possessive/><proper/></noun></w>
 <w><t>mon-ick-er</t></w>
 <w><t>mon-ied</t></w>
 <w><t>mon-ies</t></w>
@@ -99040,6 +99111,9 @@
 <w><t>moz-za-rel-la</t></w>
 <w><t>moz-zet-ta</t></w>
 <w><t>moz-zet-te</t></w>
+</section>
+
+<section description="Mp to Mt">
 <w><t>mpg</t></w>
 <w><t>mph</t></w>
 <w><t>MPh</t></w>
@@ -99076,6 +99150,9 @@
 <w><t>M-tif</t></w>
 <w><t>M-tis</t></w>
 <w><t>M-twa-ra</t></w>
+</section>
+
+<section description="Mu">
 <w><t>much</t></w>
 <w><t>much-ness</t></w>
 <w><t>mu-cic</t></w>
@@ -99943,6 +100020,9 @@
 <w><t>muz-zler</t></w>
 <phrase><t>muz-zle ve-loc-i-ty</t></phrase>
 <w><t>muz-zy</t></w>
+</section>
+
+<section description="Mv to Mz">
 <w><t>MVD</t></w>
 <w><t>MVO</t></w>
 <w><t>MVS</t></w>
@@ -100187,7 +100267,7 @@
 <w><t>M-zi</t></w>
 <w><t>mzun-gu</t></w>
 </section>
-
+</section>
 <section description="N">
 <w><t>N/F</t></w>
 <w><t>N/S/F</t></w>
@@ -114556,6 +114636,7 @@
 </section>
 
 <section description="P">
+<section description="P abbrev">
 <w><t>p</t><abbrev referenced-word="post, as in ’post meridian’ or ’p. m."/></w>
 <w><t>p/c</t></w>
 <w><t>P/C</t></w>
@@ -114562,6 +114643,9 @@
 <w><t>P/N</t></w>
 <w><t>p.m.</t><abbrev referenced-word="post meridian"/><comment>Latin "after noon"</comment></w>
 <w><t>p.&#xA0;m.</t><abbrev referenced-word="post meridian"/><comment>Latin "after noon"</comment></w>
+</section>
+
+<section description="Pa to Pc">
 <w><t>paal</t></w>
 <w><t>Paa-si-ki-vi</t></w>
 <w><t>PABA</t></w>
@@ -115308,7 +115392,7 @@
 <w><t>pan-du-ri-form</t></w>
 <w><t>pan-dy</t></w>
 <w><t>pan-dy-bat</t></w>
-<w><t>pane</t></w>
+<w><t>pane</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>pa-né</t></w>
 <w><t>paned</t></w>
 <w><t>pan-e-gyr-ic</t></w>
@@ -117016,6 +117100,9 @@
 <w><t>PBX</t></w>
 <w><t>P=Celt-ic</t></w>
 <w><t>pct</t></w>
+</section>
+
+<section description="Pe">
 <w><t>pea</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Pea-bod-y</t></w>
 <w><t>peace</t></w>
@@ -118797,7 +118884,7 @@
 <w><t>pest</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Pes-ta-loz-zi</t></w>
 <w><t>Pes-ta-loz-zi-an-ism</t></w>
-<w><t>pes-ter</t></w>
+<w><t>pes-ter</t><verb><regular-root/></verb></w>
 <w><t>pes-ter-er</t></w>
 <w><t>pes-ter-ing-ly</t></w>
 <w><t>pes-ter-some</t></w>
@@ -119009,6 +119096,9 @@
 <w><t>Pey-ton</t></w>
 <w><t>pey-tral</t></w>
 <w><t>pey-trel</t></w>
+</section>
+
+<section description="Pf to Ph">
 <w><t>Pfalz</t></w>
 <w><t>pfen-nig</t></w>
 <w><t>pfen-ni-ge</t></w>
@@ -120025,6 +120115,9 @@
 <w><t>phy-to-tox-in</t></w>
 <w><t>phy-to-tron</t></w>
 <w><t>Phyx-i-us</t></w>
+</section>
+
+<section description="Pi">
 <w><t>Pi-a</t></w>
 <w><t>Pia-cen-za</t></w>
 <w><t>pi-ac-u-lar</t></w>
@@ -120939,6 +121032,9 @@
 <w><t>piz-ze-ri-a</t></w>
 <w><t>piz-zi-ca-to</t></w>
 <w><t>piz-zle</t></w>
+</section>
+
+<section description="Pk to Pl">
 <w><t>pkg</t></w>
 <w><t>pkt</t></w>
 <w><t>PL/1</t></w>
@@ -121749,6 +121845,9 @@
 <w><t>ply-wood</t></w>
 <w><t>Pl-ze</t></w>
 <w><t>Plzen</t></w>
+</section>
+
+<section description="Pm to Pn">
 <w><t>PMG</t></w>
 <w><t>pneu-drau-lic</t></w>
 <w><t>pneu-ma</t></w>
@@ -121795,6 +121894,9 @@
 <w><t>pneu-mo-no-ul-tra-mi-cro-scop-ic-sil-i-co-vol-ca-no-ko-ni-o-sis</t></w>
 <w><t>pneu-mo-tho-rax</t></w>
 <phrase><t>p=n junc-tion</t></phrase>
+</section>
+
+<section description="Po to Pp">
 <w><t>Po</t><noun><convertible-to-possessive/></noun></w>
 <w><t>po-a-ceous</t></w>
 <w><t>poach</t></w>
@@ -123756,6 +123858,10 @@
 <w><t>ppm</t></w>
 <w><t>ppr</t></w>
 <w><t>PPS</t></w>
+</section>
+
+<section description="Pr">
+<section description="Pra to Prc">
 <w><t>praam</t></w>
 <w><t>pra-cha-rak</t></w>
 <w><t>prac-tic</t></w>
@@ -123895,6 +124001,9 @@
 <phrase><t>pray-ing man-tis</t></phrase>
 <w><t>PRB</t></w>
 <w><t>pr-cis</t></w>
+</section>
+
+<section description="Pre">
 <w><t>pre-ab-sorb</t></w>
 <w><t>pre-ab-sorb-ent</t></w>
 <w><t>pre-ab-stract</t></w>
@@ -127403,6 +127512,9 @@
 <w><t>pre-youth-ful</t></w>
 <w><t>pre-zy-go-mat-ic</t></w>
 <w><t>prez-zie</t></w>
+</section>
+
+<section description="Pri">
 <w><t>Pri</t></w>
 <w><t>Pri-am</t></w>
 <w><t>pri-a-pe-an</t></w>
@@ -127425,7 +127537,7 @@
 <phrase><t>price sup-port</t></phrase>
 <w><t>price-y</t></w>
 <w><t>pric-ing</t></w>
-<w><t>prick</t></w>
+<w><t>prick</t><verb><regular-root/></verb></w>
 <w><t>prick-er</t></w>
 <w><t>prick-et</t></w>
 <w><t>prick-ing</t></w>
@@ -127712,6 +127824,9 @@
 <w><t>prize-fight-ing</t></w>
 <phrase><t>prize mon-ey</t></phrase>
 <w><t>priz-ing</t></w>
+</section>
+
+<section description="Pro to Prs">
 <w><t>pro</t></w>
 <w><t>PRO</t></w>
 <w><t>pro-a</t></w>
@@ -127728,6 +127843,7 @@
 <w><t>pro-ac-quit-tal</t></w>
 <w><t>pro-act-ing</t></w>
 <w><t>pro-ac-tion</t></w>
+<w><t>pro-ac-tive</t><adjective/></w>
 <phrase><t>pro-ac-tive in-hi-bi-tion</t></phrase>
 <w><t>pro-ad-journ-ment</t></w>
 <w><t>pro-ad-min-is-tra-tion</t></w>
@@ -129257,6 +129373,9 @@
 <w><t>pro=Zi-on-ism</t></w>
 <w><t>pro=Zi-o-nist</t></w>
 <w><t>prs</t></w>
+</section>
+
+<section description="Pru to Prv">
 <w><t>Pru</t></w>
 <w><t>prude</t></w>
 <w><t>Pru-dence</t></w>
@@ -129319,6 +129438,9 @@
 <w><t>pru-tah</t></w>
 <w><t>Pr-vert</t></w>
 <phrase><t>Pr-vost d’Ex-iles</t></phrase>
+</section>
+
+<section description="Pry to Prz">
 <w><t>pry</t></w>
 <w><t>pry-er</t></w>
 <w><t>pry-ing</t></w>
@@ -129331,6 +129453,10 @@
 <w><t>pryth-ee</t></w>
 <w><t>Prze-my</t></w>
 <phrase><t>Prze-wal-ski’s horse</t></phrase>
+</section>
+</section>
+
+<section description="Ps">
 <w><t>Psa</t></w>
 <w><t>psalm</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>psalm-book</t></w>
@@ -129938,6 +130064,9 @@
 <w><t>psyl-la</t></w>
 <w><t>psyl-lid</t></w>
 <w><t>Psy-Ops</t><abbrev referenced-word="Psychological Operations"/></w>
+</section>
+
+<section description="Pt">
 <w><t>p-t</t></w>
 <w><t>pta</t></w>
 <w><t>PTA</t></w>
@@ -130008,6 +130137,9 @@
 <w><t>pty-a-lin</t></w>
 <w><t>pty-a-lism</t></w>
 <w><t>p=type</t></w>
+</section>
+
+<section description="Pu">
 <w><t>pub</t></w>
 <w><t>pu-ber-ty</t></w>
 <w><t>pu-ber-u-lent</t></w>
@@ -130643,6 +130775,9 @@
 <w><t>puz-zling-ness</t></w>
 <w><t>puz-zo-lan</t></w>
 <w><t>puz-zo-la-na</t></w>
+</section>
+
+<section description="Pv to Py">
 <w><t>PVA</t></w>
 <w><t>PVC</t></w>
 <phrase><t>P-vid’s deer</t></phrase>
@@ -130903,6 +131038,7 @@
 <w><t>pyx-is</t></w>
 <w><t>Pyx-is</t></w>
 </section>
+</section>
 
 <section description="Q">
 <w><t>q. v.</t><abbrev referenced-word="quod vode (for which, see)"/></w>
@@ -132302,6 +132438,7 @@
 </section>
 
 <section description="R">
+<section description="Ra">
 <w><t>Raab</t></w>
 <w><t>RAAF</t></w>
 <w><t>Ra-am-ses</t></w>
@@ -133370,6 +133507,9 @@
 <w><t>raz-zi-a</t></w>
 <w><t>raz-zle=daz-zle</t></w>
 <w><t>razz-ma-tazz</t></w>
+</section>
+
+<section description="Rb to Rd">
 <w><t>RBE</t></w>
 <w><t>RCA</t></w>
 <w><t>RCAF</t></w>
@@ -133390,7 +133530,11 @@
 <w><t>rct</t></w>
 <w><t>RCT</t></w>
 <w><t>RCVS</t></w>
+<w><t>Rd</t><abbrev referenced-word="Road"/></w>
 <w><t>R-dhos</t></w>
+</section>
+
+<section description="Re">
 <w><t>re-a-ban-don</t></w>
 <w><t>re-a-bridge</t></w>
 <w><t>re-a-bridged</t></w>
@@ -138616,6 +138760,9 @@
 <w><t>re-zone</t></w>
 <w><t>re-zoned</t></w>
 <w><t>re-zon-ing</t></w>
+</section>
+
+<section description="Rf to Rg">
 <w><t>RFC</t></w>
 <w><t>R-gen</t></w>
 <w><t>r-gen</t></w>
@@ -138631,6 +138778,9 @@
 <w><t>r-gis-seur</t></w>
 <w><t>RGS</t></w>
 <w><t>Rgt</t></w>
+</section>
+
+<section description="Rh">
 <w><t>Rh</t></w>
 <w><t>RHA</t></w>
 <w><t>rhab-do-man-cy</t></w>
@@ -138872,6 +139022,9 @@
 <phrase><t>rhythm meth-od</t></phrase>
 <phrase><t>rhythm sec-tion</t></phrase>
 <w><t>rhy-ton</t></w>
+</section>
+
+<section description="Ri">
 <w><t>ri-a</t></w>
 <w><t>ri-al</t></w>
 <w><t>ri-al-to</t></w>
@@ -139399,6 +139552,9 @@
 <w><t>riz-ar</t></w>
 <w><t>riz-zar</t></w>
 <w><t>Riz-zio</t></w>
+</section>
+
+<section description="Rl to Rn">
 <w><t>r=less</t></w>
 <w><t>rly</t></w>
 <w><t>RMA</t></w>
@@ -139413,6 +139569,9 @@
 <w><t>RNVR</t></w>
 <w><t>RNZAF</t></w>
 <w><t>RNZN</t></w>
+</section>
+
+<section description="Ro">
 <w><t>roach</t></w>
 <w><t>roach-es</t></w>
 <w><t>road</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
@@ -139885,7 +140044,7 @@
 <w><t>room-i-ly</t></w>
 <w><t>room-i-ness</t></w>
 <phrase><t>room-ing house</t></phrase>
-<w><t>room-mate</t></w>
+<w><t>room-mate</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>room ser-vice</t></phrase>
 <phrase><t>room tem-per-a-ture</t></phrase>
 <w><t>room-y</t></w>
@@ -140353,6 +140512,9 @@
 <w><t>roze-ner</t></w>
 <w><t>Ro-zi</t></w>
 <w><t>roz-zer</t></w>
+</section>
+
+<section description="Rp to Rt">
 <w><t>RPC</t></w>
 <w><t>rpm</t></w>
 <w><t>rps</t></w>
@@ -140373,6 +140535,9 @@
 <w><t>RTR</t></w>
 <w><t>RTT</t></w>
 <w><t>RTTY</t></w>
+</section>
+
+<section description="Ru">
 <w><t>Ru-an-da=U-run-di</t></w>
 <w><t>rub</t></w>
 <w><t>rub-a-boo</t></w>
@@ -140546,7 +140711,6 @@
 <w><t>ru-gos-i-ty</t></w>
 <w><t>ru-gu-lose</t></w>
 <w><t>Ruhr</t></w>
-<w><t>ruin</t></w>
 <w><t>ru-in</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>ru-in-a-ble</t></w>
 <w><t>ru-in-a-tion</t></w>
@@ -140823,6 +140987,9 @@
 <w><t>Ru-wen-zo-ri</t></w>
 <w><t>Ruys-dael</t></w>
 <w><t>Ruy-ter</t></w>
+</section>
+
+<section description="Rw to Ry">
 <w><t>RWA</t></w>
 <w><t>Rwan-da</t></w>
 <w><t>rwd</t></w>
@@ -140849,9 +141016,14 @@
 <w><t>Ryu-no-su-ke</t></w>
 <w><t>Ryu-rik</t></w>
 </section>
+</section>
 
 <section description="S">
+<section description="S abbrev">
 <w><t>S.C.</t><abbrev referenced-word="South Carolina"/></w>
+</section>
+
+<section description="Sa">
 <w><t>Saa-di</t></w>
 <w><t>Saar</t></w>
 <w><t>Saar-br-en</t></w>
@@ -141778,7 +141950,7 @@
 <w><t>San-dus-ky</t></w>
 <phrase><t>sand vi-per</t></phrase>
 <w><t>Sand-wich</t></w>
-<w><t>sand-wich</t></w>
+<w><t>sand-wich</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <phrase><t>sand-wich board</t></phrase>
 <phrase><t>sand-wich cake</t></phrase>
 <phrase><t>sand-wich com-pound</t></phrase>
@@ -142373,7 +142545,7 @@
 <w><t>sav-er</t></w>
 <w><t>sav-in</t></w>
 <w><t>sav-ine</t></w>
-<w><t>sav-ing</t></w>
+<w><t>sav-ing</t><noun><pluralizable/></noun></w>
 <w><t>sav-ing-ly</t></w>
 <phrase><t>sav-ings ac-count</t></phrase>
 <phrase><t>sav-ings bank</t></phrase>
@@ -142482,6 +142654,9 @@
 <w><t>say-yid</t></w>
 <w><t>saz-e-rac</t></w>
 <w><t>Saz-e-rac</t></w>
+</section>
+
+<section description="Sc to Sd">
 <w><t>SC</t><abbrev referenced-word="South Carolina"/></w>
 <w><t>scab</t></w>
 <w><t>scab-bard</t></w>
@@ -143626,6 +143801,9 @@
 <w><t>Scyth-i-an</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>scyth-ing</t></w>
 <w><t>SDRs</t></w>
+</section>
+
+<section description="Se">
 <w><t>sea</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>sea an-chor</t></phrase>
 <phrase><t>sea a-nem-o-ne</t></phrase>
@@ -146724,6 +146902,9 @@
 <w><t>Sey-han</t></w>
 <w><t>Sey-mour</t></w>
 <w><t>Se-zes-sion</t></w>
+</section>
+
+<section description="Sf to Sg">
 <w><t>Sfax</t></w>
 <w><t>sfer-ics</t></w>
 <w><t>Sfor-za</t></w>
@@ -146736,6 +146917,9 @@
 <w><t>SGP</t></w>
 <w><t>sgraf-fi-to</t></w>
 <w><t>Sgt</t></w>
+</section>
+
+<section description="Sh">
 <w><t>SHA</t></w>
 <w><t>Shaa-ban</t></w>
 <w><t>Sha-ba</t></w>
@@ -147563,7 +147747,7 @@
 <w><t>shook</t></w>
 <w><t>shool</t></w>
 <w><t>shoon</t></w>
-<w><t>shoot</t></w>
+<w><t>shoot</t><verb><regular-root value="false"/></verb></w>
 <w><t>shoot-er</t></w>
 <phrase><t>shoot-ing box</t></phrase>
 <phrase><t>shoot-ing brake</t></phrase>
@@ -147572,6 +147756,7 @@
 <phrase><t>shoot-ing script</t></phrase>
 <phrase><t>shoot-ing star</t></phrase>
 <phrase><t>shoot-ing stick</t></phrase>
+<w><t>shoots</t><verb><vf></vf></verb></w>
 <w><t>shop</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>shop a-round</t></phrase>
 <phrase><t>shop as-sis-tant</t></phrase>
@@ -147880,6 +148065,9 @@
 <w><t>shy-ness</t></w>
 <w><t>shy-poo</t></w>
 <w><t>shy-ster</t></w>
+</section>
+
+<section description="Si to Sj">
 <w><t>si-al</t></w>
 <w><t>si-al-a-gog-ic</t></w>
 <w><t>si-al-a-gogue</t></w>
@@ -148814,7 +149002,7 @@
 <w><t>si-tar-ist</t></w>
 <w><t>sit-a-tun-ga</t></w>
 <w><t>sit-com</t></w>
-<w><t>site</t></w>
+<w><t>site</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>sit-ed</t></w>
 <w><t>si-tel-la</t></w>
 <w><t>sit-fast</t></w>
@@ -148930,6 +149118,9 @@
 <w><t>sjam-bok</t></w>
 <w><t>SJD</t></w>
 <w><t>Sj-land</t></w>
+</section>
+
+<section description="Sk">
 <w><t>Ska-gen</t></w>
 <w><t>Skag-er-rak</t></w>
 <w><t>Skag-way</t></w>
@@ -149225,6 +149416,9 @@
 <w><t>sky-writ-ing</t></w>
 <w><t>sky-writ-ten</t></w>
 <w><t>sky-wrote</t></w>
+</section>
+
+<section description="Sl">
 <w><t>slab</t></w>
 <w><t>slab-ber</t></w>
 <w><t>slab-ber-y</t></w>
@@ -149693,6 +149887,9 @@
 <w><t>sly-ly</t></w>
 <w><t>sly-ness</t></w>
 <w><t>slype</t></w>
+</section>
+
+<section description="Sm">
 <w><t>smack</t></w>
 <w><t>smack-er</t></w>
 <w><t>smack-er-oo</t></w>
@@ -149922,6 +150119,9 @@
 <w><t>Smyr-na</t></w>
 <w><t>Smyr-ne-an</t></w>
 <w><t>smy-trie</t></w>
+</section>
+
+<section description="Sn">
 <w><t>snack</t></w>
 <w><t>snack-ette</t></w>
 <w><t>snaf-fle</t></w>
@@ -150245,6 +150445,9 @@
 <w><t>sny</t></w>
 <w><t>snye</t></w>
 <w><t>sny-ing</t></w>
+</section>
+
+<section description="So">
 <w><t>so</t></w>
 <w><t>soak</t><verb><regular-root/></verb></w>
 <w><t>soak-age</t></w>
@@ -151362,6 +151565,9 @@
 <w><t>So-yuz</t></w>
 <w><t>so-zin</t></w>
 <w><t>soz-zled</t></w>
+</section>
+
+<section description="Sp">
 <w><t>spa</t></w>
 <w><t>Spa</t></w>
 <w><t>Spaak</t></w>
@@ -152766,6 +152972,9 @@
 <w><t>spy</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>spy-glass</t></w>
 <w><t>spy-ing</t></w>
+</section>
+
+<section description="Sq">
 <w><t>sqq</t></w>
 <w><t>squab</t></w>
 <w><t>squab-bi-er</t></w>
@@ -152959,6 +153168,9 @@
 <w><t>sqush-i-est</t></w>
 <w><t>sqush-y</t></w>
 <w><t>squush</t></w>
+</section>
+
+<section description="Sr to Ss">
 <w><t>Sr</t><abbrev referenced-word="senior, señor"/></w>
 <w><t>Sra</t><abbrev referenced-word="señora"/></w>
 <w><t>s-rac</t></w>
@@ -152982,6 +153194,9 @@
 <w><t>SSR</t></w>
 <w><t>SST</t></w>
 <w><t>SSW</t></w>
+</section>
+
+<section description="St">
 <w><t>st</t><abbrev referenced-word="street or saint"/></w>
 <w><t>St. Croix</t></w>
 <w><t>sta</t></w>
@@ -155277,6 +155492,9 @@
 <w><t>sty-rene</t></w>
 <w><t>Styr-i-a</t></w>
 <w><t>Styx</t></w>
+</section>
+
+<section description="Su">
 <w><t>su-a-bil-i-ty</t></w>
 <w><t>su-a-ble</t></w>
 <w><t>su-a-bly</t></w>
@@ -158928,6 +159146,9 @@
 <w><t>su-ze-rain-ty</t></w>
 <w><t>Su-zie</t></w>
 <w><t>Su-zu-ki</t></w>
+</section>
+
+<section description="Sv">
 <w><t>Sval-bard</t></w>
 <w><t>sva-ra-bhak-ti</t></w>
 <w><t>Sved-berg</t></w>
@@ -158939,6 +159160,9 @@
 <w><t>Svet-la-na</t></w>
 <w><t>S-vi-gn</t></w>
 <w><t>Sviz-ze-ra</t></w>
+</section>
+
+<section description="Sw">
 <w><t>SWA</t></w>
 <w><t>swab</t></w>
 <w><t>swab-ber</t></w>
@@ -159343,6 +159567,9 @@
 <w><t>swum</t></w>
 <w><t>swung</t></w>
 <w><t>swy</t></w>
+</section>
+
+<section description="Sy">
 <w><t>Syb-a-ris</t></w>
 <w><t>syb-a-rite</t></w>
 <w><t>Syb-a-rite</t></w>
@@ -159860,6 +160087,9 @@
 <phrase><t>sys-tems a-nal-y-sis</t></phrase>
 <phrase><t>sys-tems en-gi-neer-ing</t></phrase>
 <w><t>sys-to-le</t></w>
+</section>
+
+<section description="Sz">
 <w><t>Syz-ran</t></w>
 <w><t>sy-zyg-i-al</t></w>
 <w><t>syz-y-gy</t></w>
@@ -159876,6 +160106,7 @@
 <w><t>Szy-man-ows-ki</t></w>
 <w><t>Szy-ma-now-ski</t></w>
 </section>
+</section>
 
 <section description="T">
 <w><t>Taal</t></w>
@@ -170604,7 +170835,7 @@
 <w><t>un-der-div-ing</t></w>
 <w><t>un-der-do</t></w>
 <w><t>un-der-doc-tor</t></w>
-<w><t>un-der-dog</t></w>
+<w><t>un-der-dog</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>un-der-do-ing</t></w>
 <w><t>un-der-done</t></w>
 <w><t>un-der-dose</t></w>
@@ -171111,7 +171342,7 @@
 <w><t>un-der-stage</t></w>
 <w><t>un-der-stain</t></w>
 <w><t>un-der-stamp</t></w>
-<w><t>un-der-stand</t><verb/></w>
+<w><t>un-der-stand</t><verb><regular-root value="false"/></verb></w>
 <w><t>un-der-stand-a-bil-i-ty</t></w>
 <w><t>un-der-stand-a-ble</t></w>
 <w><t>un-der-stand-a-ble-ness</t></w>
@@ -182974,7 +183205,11 @@
 </section>
 
 <section description="W">
+<section description="W abbrev">
 <w><t>w/o</t></w>
+</section>
+
+<section description="Wa">
 <w><t>WAAAF</t></w>
 <w><t>WAAC</t></w>
 <w><t>Waadt</t></w>
@@ -183942,10 +184177,16 @@
 <w><t>wayz-goose</t></w>
 <w><t>Wa-zir-a-bad</t></w>
 <w><t>Wa-zir-i-stan</t></w>
+</section>
+
+<section description="Wb to Wc">
 <w><t>WBC</t></w>
 <w><t>W-burg</t></w>
 <w><t>WCC</t></w>
 <w><t>WCTU</t></w>
+</section>
+
+<section description="We to Wf">
 <w><t>we</t></w>
 <w><t>weak</t><adjective><extensible/></adjective></w>
 <w><t>weak-en</t><verb><regular-root/></verb></w>
@@ -185056,6 +185297,9 @@
 <w><t>Weyl</t></w>
 <w><t>Wey-mouth</t></w>
 <w><t>WFTU</t></w>
+</section>
+
+<section description="Wh">
 <w><t>whack</t></w>
 <w><t>whack-er</t></w>
 <w><t>whack-i-er</t></w>
@@ -185537,6 +185781,9 @@
 <w><t>why’ll</t></w>
 <w><t>why’re</t></w>
 <w><t>why’s</t></w>
+</section>
+
+<section description="Wi">
 <w><t>Wi-ak</t></w>
 <w><t>Wich-i-ta</t></w>
 <w><t>wick</t></w>
@@ -186256,6 +186503,9 @@
 <w><t>wiz-en</t></w>
 <w><t>wi-zen</t></w>
 <w><t>wiz-ened</t></w>
+</section>
+
+<section description="Wk to Wn">
 <w><t>wkly</t></w>
 <w><t>Wla-dy-slaw</t></w>
 <w><t>WLM</t></w>
@@ -186264,6 +186514,9 @@
 <w><t>WMO</t></w>
 <w><t>WNP</t></w>
 <w><t>WNW</t></w>
+</section>
+
+<section description="Wo to Wp">
 <w><t>woad</t></w>
 <w><t>woad-ed</t></w>
 <w><t>woad-wax</t></w>
@@ -186737,6 +186990,9 @@
 <w><t>wpb</t></w>
 <w><t>WPC</t></w>
 <w><t>wpm</t></w>
+</section>
+
+<section description="Wr">
 <w><t>WRAAC</t></w>
 <w><t>Wraac</t></w>
 <w><t>WRAAF</t></w>
@@ -186756,7 +187012,7 @@
 <w><t>wrap-a-round</t></w>
 <w><t>wrap=a-round</t></w>
 <w><t>wrapped</t></w>
-<w><t>wrap-per</t></w>
+<w><t>wrap-per</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>wrap-ping</t></w>
 <w><t>wrap-round</t></w>
 <w><t>wrapt</t><verb><lemma>wrap</lemma></verb><comment>archaic, past tense of "wrap"</comment></w>
@@ -186880,6 +187136,9 @@
 <w><t>wry-neck</t></w>
 <w><t>wry-necked</t></w>
 <w><t>wry-ness</t></w>
+</section>
+
+<section description="Ws to Wy">
 <w><t>WSW</t></w>
 <w><t>W-tem-berg</t></w>
 <w><t>Wu-chang</t></w>
@@ -186938,6 +187197,7 @@
 <w><t>wyt-ing</t></w>
 <w><t>wy-vern</t></w>
 </section>
+</section>
 
 <section description="X">
 <w><t>xa-lo-stock-ite</t></w>

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14946] trunk/foray/foray-orthograp hy/src/main

From: <vic...@us...> - 2026-07-29 21:54:02

Revision: 14946
          http://sourceforge.net/p/foray/code/14946
Author:   victormote
Date:     2026-07-29 21:54:00 +0000 (Wed, 29 Jul 2026)
Log Message:
-----------
Conform to aXSL change: Allow individual derivative factory to be added to an orthography.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4aStandard.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/OrthographyParser.java

Modified: trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-29 15:34:17 UTC (rev 14945)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-29 21:54:00 UTC (rev 14946)
@@ -102,6 +102,10 @@
     <resource-location parsed="false" url="file:../dictionaries/eng-Latn-ZZZ-epoch-01.dict.xml"/>
   </dictionary-resource>
 
+  <dictionary-resource id="org.foray.emen.Latn.ZZZ">
+    <resource-location parsed="false" url="file:../dictionaries/emen-Latn-ZZZ.dict.xml"/>
+  </dictionary-resource>
+
   <dictionary-resource id="org.foray.ita.Latn.ZZZ">
     <resource-location parsed="false" url="file:../dictionaries/ita-Latn-ZZZ.dict.xml"/>
   </dictionary-resource>
@@ -172,6 +176,14 @@
     <derivative-factories reference="eng-Latn-derivatives"/>
   </orthography>
 
+  <orthography language-iso-3char="emen" script-iso-4char="Latn" country-iso-3char="ZZZ">
+    <match-rules reference="eng-Latn-match-rules"/>
+    <dictionary reference="org.foray.emen.Latn.ZZZ"/>
+    <hyphenation-patterns reference="hyph-patterns-eng"/>
+    <derivative-factories reference="eng-Latn-derivatives"/>
+    <derivative-factory class="org.foray.orthography.inflection.emen.EmenLatnSuffix_eth_Factory"/>
+  </orthography>
+
   <orthography language-iso-3char="lat" script-iso-4char="Latn" country-iso-3char="ZZZ">
     <match-rules reference="lat-Latn-match-rules"/>
     <dictionary reference="org.foray.lat.Latn.ZZZ"/>

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4aStandard.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4aStandard.java	2026-07-29 15:34:17 UTC (rev 14945)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4aStandard.java	2026-07-29 21:54:00 UTC (rev 14946)
@@ -155,6 +155,14 @@
         this.wordWrapperFactories = wordWrapperFactories;
     }
 
+    /**
+     * Adds a single word wrapper factory to the list.
+     * @param factory The word wrapper factory to set.
+     */
+    public void registerWordWrapperFactory(final InflectionFactory<?> factory) {
+        this.wordWrapperFactories.add(factory);
+    }
+
     @Override
     public SegmentDictionary getDictionary() {
         if (this.dictionaryResource == null) {

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/OrthographyParser.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/OrthographyParser.java	2026-07-29 15:34:17 UTC (rev 14945)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/util/OrthographyParser.java	2026-07-29 21:54:00 UTC (rev 14946)
@@ -197,7 +197,11 @@
                 errorMessage("derivative-factory not found: {}", factoryClassName);
                 return;
             }
-            this.currentDerivateFactoryList.add(factory);
+            if (this.currentDerivateFactoryList != null) {
+                this.currentDerivateFactoryList.add(factory);
+            } else {
+                this.currentOrthographyConfig.registerWordWrapperFactory(factory);
+            }
             return;
         }
         case "dictionary": {

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14945] trunk/foray/foray-orthograp hy/src

From: <vic...@us...> - 2026-07-29 15:34:20

Revision: 14945
          http://sourceforge.net/p/foray/code/14945
Author:   victormote
Date:     2026-07-29 15:34:17 +0000 (Wed, 29 Jul 2026)
Log Message:
-----------
Add inflection classes for Early Modern English words regular verb forms ending in -eth.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatn.java

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Factory.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/package-info.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_FactoryTests.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Tests.java

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth.java	2026-07-29 15:34:17 UTC (rev 14945)
@@ -0,0 +1,68 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.emen;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.WordSegment4a;
+import org.foray.orthography.inflection.InflectedWord;
+import org.foray.orthography.inflection.eng.EngLatn;
+
+import java.util.regex.Pattern;
+
+/**
+ * (For Early Modern English), wraps a regular verb, and adds "eth" to the end to make it present tense.
+ * For example, the English word "hold" would be wrapped to make the word "holdeth".
+ */
+public class EmenLatnSuffix_eth extends InflectedWord {
+
+    /** The pattern to be matched by words with this inflection. */
+    public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)eth$");
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = -2482073895198981184L;
+
+    /**
+     * Constructor.
+     * @param wrappedWord The wrapped word.
+     */
+    public EmenLatnSuffix_eth(final Word4a wrappedWord) {
+        super(wrappedWord);
+    }
+
+    @Override
+    public WordSegment4a getAppendedSegment() {
+        return EngLatn.ETH_SEGMENT;
+    }
+
+    @Override
+    public WordSegment4a getModifiedSegment() {
+        return null;
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Factory.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Factory.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Factory.java	2026-07-29 15:34:17 UTC (rev 14945)
@@ -0,0 +1,84 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.emen;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.inflection.InflectionFactory;
+
+import org.axsl.orthography.PartOfSpeech;
+import org.axsl.orthography.PosQualifier;
+
+import java.util.regex.Matcher;
+
+/**
+ * Factory class for {@link EmenLatnSuffix_eth}.
+ */
+public final class EmenLatnSuffix_eth_Factory extends InflectionFactory<EmenLatnSuffix_eth> {
+
+    /** The singleton instance. */
+    private static final EmenLatnSuffix_eth_Factory THE_INSTANCE = new EmenLatnSuffix_eth_Factory();
+
+    /**
+     * Private constructor for this singleton class.
+     */
+    private EmenLatnSuffix_eth_Factory() { }
+
+    /**
+     * Returns the singleton instance.
+     * @return The singleton instance.
+     */
+    public static EmenLatnSuffix_eth_Factory getInstance() {
+        return THE_INSTANCE;
+    }
+
+    @Override
+    public CharSequence findLemmaChars(final CharSequence chars) {
+        final Matcher matcher = EmenLatnSuffix_eth.PATTERN.matcher(chars);
+        if (! matcher.matches()) {
+            return null;
+        }
+
+        final String lemmaChars = matcher.group(1);
+        return lemmaChars;
+    }
+
+    @Override
+    public boolean isValidLemma(final Word4a lemma) {
+        if (lemma.isOfQualifiedType(PartOfSpeech.VERB, PosQualifier.REGULAR_ROOT)) {
+            return true;
+        }
+        return false;
+    }
+
+    @Override
+    protected EmenLatnSuffix_eth makeInstance(final Word4a lemma) {
+        return new EmenLatnSuffix_eth(lemma);
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Factory.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/package-info.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/package-info.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/package-info.java	2026-07-29 15:34:17 UTC (rev 14945)
@@ -0,0 +1,35 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+/**
+ * <p>Classes English-language inflection classes.
+ * Classes in this package are subclasses of {@link org.foray.orthography.WordWrapper} or
+ * {@link org.foray.orthography.inflection.InflectionFactory}.</p>
+ */
+
+package org.foray.orthography.inflection.emen;


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/emen/package-info.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatn.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatn.java	2026-07-29 14:13:05 UTC (rev 14944)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatn.java	2026-07-29 15:34:17 UTC (rev 14945)
@@ -56,6 +56,8 @@
     /** Common word segment "ing" in English inflections. */
     public static final StringWordSegmentUtf16 ING_SEGMENT = new StringWordSegmentUtf16("ing");
 
+    /** Common word segment "eth" in Early Modern English inflections. */
+    public static final StringWordSegmentUtf16 ETH_SEGMENT = new StringWordSegmentUtf16("eth");
 
     /**
      * Private constructor. This utility class should never be instantiated.

Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_FactoryTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_FactoryTests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_FactoryTests.java	2026-07-29 15:34:17 UTC (rev 14945)
@@ -0,0 +1,80 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.emen;
+
+import org.foray.orthography.Dictionary4a;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.assertj.core.api.AssertionsForClassTypes;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+import org.mockito.Mockito;
+
+/**
+ * Tests of {@link EmenLatnSuffix_eth_Factory}.
+ */
+public class EmenLatnSuffix_eth_FactoryTests {
+
+    /** The object under test. */
+    private EmenLatnSuffix_eth_Factory out;
+
+    /** A dictionary to use for these tests. */
+    private Dictionary4a dictionary;
+
+    /**
+     * Test setup.
+     */
+    @BeforeEach
+    public void before() {
+        this.out = EmenLatnSuffix_eth_Factory.getInstance();
+        this.dictionary = Mockito.mock(Dictionary4a.class);
+        Mockito.when(dictionary.getWord("talk")).thenReturn(StringWordTests.WORD_TALK);
+    }
+
+    /**
+     * Test of a String for which the factory should not be able to create an instance.
+     */
+    @Test
+    public void testInvalid() {
+        AssertionsForClassTypes.assertThat(out.makeInstance("talking", this.dictionary)).isNull();
+    }
+
+    /**
+     * Test of a String for which the factory should be able to create an instance.
+     */
+    @Test
+    public void testValid() {
+        final EmenLatnSuffix_eth word = out.makeInstance("talketh", this.dictionary);
+        /* Test for instance equality. */
+        AssertionsForClassTypes.assertThat(word.getWrappedWord()).isEqualTo(StringWordTests.WORD_TALK);
+        assertThat(word.getActualContent().toString()).isEqualTo("talketh");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_FactoryTests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Tests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Tests.java	2026-07-29 15:34:17 UTC (rev 14945)
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.emen;
+
+import org.foray.orthography.StringWord;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.junit.jupiter.api.Test;
+
+/**
+ * Tests of {@link EmenLatnSuffix_eth}.
+ */
+public class EmenLatnSuffix_eth_Tests {
+
+    /**
+     * Tests various aspects of words ending in -eth.
+     */
+    @Test
+    public void test01() {
+        final StringWord word = StringWordTests.WORD_TALK;
+        final EmenLatnSuffix_eth wrapper = new EmenLatnSuffix_eth(word);
+
+        assertThat(wrapper.toString()).isEqualTo("talk-eth");
+        assertThat(wrapper.getNormalizedContent()).isEqualTo("talk");
+        assertThat(wrapper.getActualContent().toString()).isEqualTo("talketh");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/emen/EmenLatnSuffix_eth_Tests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14944] trunk/foray/foray-common/sr c

From: <vic...@us...> - 2026-07-29 14:13:08

Revision: 14944
          http://sourceforge.net/p/foray/code/14944
Author:   victormote
Date:     2026-07-29 14:13:05 +0000 (Wed, 29 Jul 2026)
Log Message:
-----------
Allow 4-character language codes.

Modified Paths:
--------------
    trunk/foray/foray-common/src/main/java/org/foray/common/i18n/Language4a.java
    trunk/foray/foray-common/src/test/java/org/foray/common/i18n/Language4aTests.java

Modified: trunk/foray/foray-common/src/main/java/org/foray/common/i18n/Language4a.java
===================================================================
--- trunk/foray/foray-common/src/main/java/org/foray/common/i18n/Language4a.java	2026-07-29 10:22:22 UTC (rev 14943)
+++ trunk/foray/foray-common/src/main/java/org/foray/common/i18n/Language4a.java	2026-07-29 14:13:05 UTC (rev 14944)
@@ -109,13 +109,16 @@
     /** The length, in chars, of the 3-character code. */
     private static final int PATTERN_3CHAR_LENGTH = 3;
 
+    /** The length, in chars, of the 4-character code. */
+    private static final int PATTERN_4CHAR_LENGTH = 4;
+
     /** Regular expression pattern for matching a 2-character code. BCP 47 specifies that the language code is
      * case-insensitive. */
     private static final Pattern PATTERN_2CHAR = Pattern.compile("[A-Za-z]{2}");
 
-    /** Regular expression pattern for matching a 3-character code. BCP 47 specifies that the language code is
-     * case-insensitive. */
-    private static final Pattern PATTERN_3CHAR = Pattern.compile("[A-Za-z]{3}");
+    /** Regular expression pattern for matching a 3-character or 4-character ISO 639 code. BCP 47 specifies that the
+     * language code is case-insensitive. */
+    private static final Pattern PATTERN_3_OR_4CHAR = Pattern.compile("[A-Za-z]{3,4}");
 
     /** The initial capacity of the data structures. */
     private static final int INITIAL_CAPACITY = 600;
@@ -276,6 +279,8 @@
                 Script4a.GREEK));
         Language4a.register(new Language4a("elx", null, "Elamite", "élamite", null));
         Language4a.register(new Language4a("eng", "en", "English", "anglais", Script4a.LATIN));
+        /* The "emen" language code was part of the since-withdrawn ISO 639-6 proposed standard. */
+        Language4a.register(new Language4a("emen", null, "Early Modern English", "[unknown]", Script4a.LATIN));
         Language4a.register(new Language4a("enm", null, "English, Middle(1100-1500)", "anglais moyen(1100-1500)",
                 null));
         Language4a.register(new Language4a("epo", "eo", "Esperanto", "espéranto", null));
@@ -729,8 +734,8 @@
      */
     public Language4a(final String alpha3Code, final String alpha2Code, final String englishName,
             final String frenchName, final Script4a defaultScript) {
-        if (! matches3CharacterPattern(alpha3Code)) {
-            final String template = "Alpha 3 code expected pattern: " + PATTERN_3CHAR.toString() + ", actual: %s";
+        if (! matches3or4CharacterPattern(alpha3Code)) {
+            final String template = "Alpha 3 code expected pattern: " + PATTERN_3_OR_4CHAR.toString() + ", actual: %s";
             throw new IllegalArgumentException(String.format(template, alpha3Code));
         }
         /* Alpha 2 code can be null. */
@@ -889,19 +894,19 @@
     }
 
     /**
-     * Indicates whether a given string fits the pattern of a 3-character language code.
+     * Indicates whether a given string fits the pattern of a 3-character or 4-character language code.
      * This does NOT validate the language code, but only indicates that the pattern fits.
      * This is useful when parsing a string like "eng-USA-Latn" by helping to distinguish which part of the string could
      * be a valid language code.
      * @param testString The string to be tested, e.g. "eng" or "rus".
-     * @return True if and only if {@code testString} fits the pattern of a 3-character language code, i.e. that it
-     * consists of exactly two lowercase characters from the Latin alphabet.
+     * @return True if and only if {@code testString} fits the pattern of a 3-character or 4-character language code,
+     * i.e. that it consists of exactly three or four lowercase characters from the Latin alphabet.
      */
-    public static boolean matches3CharacterPattern(final CharSequence testString) {
+    public static boolean matches3or4CharacterPattern(final CharSequence testString) {
         if (testString == null) {
             return false;
         }
-        final Matcher matcher = PATTERN_3CHAR.matcher(testString);
+        final Matcher matcher = PATTERN_3_OR_4CHAR.matcher(testString);
         return matcher.matches();
     }
 
@@ -920,7 +925,8 @@
         }
         switch (testString.length()) {
         case PATTERN_2CHAR_LENGTH: return matches2CharacterPattern(testString);
-        case PATTERN_3CHAR_LENGTH: return matches3CharacterPattern(testString);
+        case PATTERN_3CHAR_LENGTH: return matches3or4CharacterPattern(testString);
+        case PATTERN_4CHAR_LENGTH: return matches3or4CharacterPattern(testString);
         default: return false;
         }
     }

Modified: trunk/foray/foray-common/src/test/java/org/foray/common/i18n/Language4aTests.java
===================================================================
--- trunk/foray/foray-common/src/test/java/org/foray/common/i18n/Language4aTests.java	2026-07-29 10:22:22 UTC (rev 14943)
+++ trunk/foray/foray-common/src/test/java/org/foray/common/i18n/Language4aTests.java	2026-07-29 14:13:05 UTC (rev 14944)
@@ -86,13 +86,16 @@
     @Test
     public void matches3CharacterPatternTests() {
         /* String should match. */
-        assertThat(Language4a.matches3CharacterPattern("aaa")).isTrue();
+        assertThat(Language4a.matches3or4CharacterPattern("aaa")).isTrue();
 
+        /* String should match. */
+        assertThat(Language4a.matches3or4CharacterPattern("aaaa")).isTrue();
+
         /* String too long. */
-        assertThat(Language4a.matches3CharacterPattern("aaaa")).isFalse();
+        assertThat(Language4a.matches3or4CharacterPattern("aaaaa")).isFalse();
 
         /* String too short. */
-        assertThat(Language4a.matches3CharacterPattern("aa")).isFalse();
+        assertThat(Language4a.matches3or4CharacterPattern("aa")).isFalse();
     }
 
 }

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14943] trunk/foray/foray-orthograp hy/src

From: <vic...@us...> - 2026-07-29 10:22:26

Revision: 14943
          http://sourceforge.net/p/foray/code/14943
Author:   victormote
Date:     2026-07-29 10:22:22 +0000 (Wed, 29 Jul 2026)
Log Message:
-----------
Convert last XML derivative-pattern to java classes.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
    trunk/foray/foray-orthography/src/test/resources/orthography-config.xml

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Factory.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_FactoryTests.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Tests.java

Modified: trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-29 00:02:47 UTC (rev 14942)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-29 10:22:22 UTC (rev 14943)
@@ -42,17 +42,6 @@
     <match desc="A single capital letter, such as a person's initial">^[A-Z]$</match>
   </match-rule-list>
 
-  <derivative-pattern-list id="eng-Latn-derivative-patterns">
-    <derivative-pattern desc="ends with /-iest/, root ends with /-y/">
-      <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)iest$</match>
-      <replace>$1y</replace>
-      <derivative-rule>
-        <adjective><extensible/></adjective>
-        <derivative-type type="superlative"/>
-      </derivative-rule>
-    </derivative-pattern>
-  </derivative-pattern-list>
-
   <derivative-pattern-list id="fre-Latn-derivative-patterns">
     <derivative-pattern desc="ends with /-s/">
       <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)s$</match>
@@ -89,6 +78,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_iest_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est2_Factory"/>
@@ -170,7 +160,6 @@
 
   <orthography language-iso-3char="eng" script-iso-4char="Latn" country-iso-3char="USA">
     <match-rules reference="eng-Latn-match-rules"/>
-    <derivative-rules reference="eng-Latn-derivative-patterns"/>
     <dictionary reference="org.foray.eng.Latn.USA"/>
     <hyphenation-patterns reference="hyph-patterns-eng"/>
     <derivative-factories reference="eng-Latn-derivatives"/>
@@ -178,7 +167,6 @@
 
   <orthography language-iso-3char="eng" script-iso-4char="Latn" country-iso-3char="GBR">
     <match-rules reference="eng-Latn-match-rules"/>
-    <derivative-rules reference="eng-Latn-derivative-patterns"/>
     <dictionary reference="org.foray.eng.Latn.GBR"/>
     <hyphenation-patterns reference="hyph-patterns-eng"/>
     <derivative-factories reference="eng-Latn-derivatives"/>

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest.java	2026-07-29 10:22:22 UTC (rev 14943)
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.WordSegment4a;
+import org.foray.orthography.inflection.InflectedWord;
+import org.foray.orthography.inflection.mods.Replace_y_by_i;
+
+import java.util.regex.Pattern;
+
+/**
+ * Wraps an adjective ending in "y", converting the "y" to "iest" make it comparatively greater than the lemma.
+ * For example, the English word "crazy" would be wrapped to make the word "craziest".
+ */
+public class EngLatnSuffix_iest extends InflectedWord {
+
+    /** The pattern to be matched by words with this inflection. */
+    public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)iest$");
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = 215291249289142549L;
+
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
+    /**
+     * Constructor.
+     * @param wrappedWord The wrapped word.
+     */
+    public EngLatnSuffix_iest(final Word4a wrappedWord) {
+        super(wrappedWord);
+        this.modifiedSegment = new Replace_y_by_i(wrappedWord.getLastWordSegment());
+    }
+
+    @Override
+    public WordSegment4a getAppendedSegment() {
+        return EngLatn.EST_SEGMENT;
+    }
+
+    @Override
+    public WordSegment4a getModifiedSegment() {
+        return this.modifiedSegment;
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Factory.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Factory.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Factory.java	2026-07-29 10:22:22 UTC (rev 14943)
@@ -0,0 +1,87 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.inflection.InflectionFactory;
+
+import org.axsl.orthography.PartOfSpeech;
+import org.axsl.orthography.PosQualifier;
+
+import java.util.regex.Matcher;
+
+/**
+ * Factory class for {@link EngLatnSuffix_iest}.
+ */
+public final class EngLatnSuffix_iest_Factory extends InflectionFactory<EngLatnSuffix_iest> {
+
+    /** The singleton instance. */
+    private static final EngLatnSuffix_iest_Factory THE_INSTANCE = new EngLatnSuffix_iest_Factory();
+
+    /**
+     * Private constructor for this singleton class.
+     */
+    private EngLatnSuffix_iest_Factory() { }
+
+    /**
+     * Returns the singleton instance.
+     * @return The singleton instance.
+     */
+    public static EngLatnSuffix_iest_Factory getInstance() {
+        return THE_INSTANCE;
+    }
+
+    @Override
+    public CharSequence findLemmaChars(final CharSequence chars) {
+        final Matcher matcher = EngLatnSuffix_iest.PATTERN.matcher(chars);
+        if (! matcher.matches()) {
+            return null;
+        }
+
+        final String lemmaChars = matcher.group(1) + "y";
+        return lemmaChars;
+    }
+
+    @Override
+    public boolean isValidLemma(final Word4a lemma) {
+        if (lemma.isOfQualifiedType(PartOfSpeech.ADJECTIVE, PosQualifier.EXTENSIBLE)) {
+            /*
+             <derivative-type type="superlative" desc="single-syllable root"/>
+             */
+            return true;
+        }
+        return false;
+    }
+
+    @Override
+    protected EngLatnSuffix_iest makeInstance(final Word4a lemma) {
+        return new EngLatnSuffix_iest(lemma);
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Factory.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_FactoryTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_FactoryTests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_FactoryTests.java	2026-07-29 10:22:22 UTC (rev 14943)
@@ -0,0 +1,80 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Dictionary4a;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.assertj.core.api.AssertionsForClassTypes;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+import org.mockito.Mockito;
+
+/**
+ * Tests of {@link EngLatnSuffix_iest_Factory}.
+ */
+public class EngLatnSuffix_iest_FactoryTests {
+
+    /** The object under test. */
+    private EngLatnSuffix_iest_Factory out;
+
+    /** A dictionary to use for these tests. */
+    private Dictionary4a dictionary;
+
+    /**
+     * Test setup.
+     */
+    @BeforeEach
+    public void before() {
+        this.out = EngLatnSuffix_iest_Factory.getInstance();
+        this.dictionary = Mockito.mock(Dictionary4a.class);
+        Mockito.when(dictionary.getWord("crazy")).thenReturn(StringWordTests.WORD_CRAZY);
+    }
+
+    /**
+     * Test of a String for which the factory should not be able to create an instance.
+     */
+    @Test
+    public void testInvalid() {
+        AssertionsForClassTypes.assertThat(out.makeInstance("crazier", this.dictionary)).isNull();
+    }
+
+    /**
+     * Test of a String for which the factory should be able to create an instance.
+     */
+    @Test
+    public void testValid() {
+        final EngLatnSuffix_iest word = out.makeInstance("craziest", this.dictionary);
+        /* Test for instance equality. */
+        AssertionsForClassTypes.assertThat(word.getWrappedWord()).isEqualTo(StringWordTests.WORD_CRAZY);
+        assertThat(word.getActualContent().toString()).isEqualTo("craziest");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_FactoryTests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Tests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Tests.java	2026-07-29 10:22:22 UTC (rev 14943)
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.StringWord;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.junit.jupiter.api.Test;
+
+/**
+ * Tests of {@link EngLatnSuffix_iest}.
+ */
+public class EngLatnSuffix_iest_Tests {
+
+    /**
+     * Tests various aspects word ending in -iest.
+     */
+    @Test
+    public void test01() {
+        final StringWord word = StringWordTests.WORD_CRAZY;
+        final EngLatnSuffix_iest wrapper = new EngLatnSuffix_iest(word);
+
+        assertThat(wrapper.toString()).isEqualTo("cra-zi-est");
+        assertThat(wrapper.getNormalizedContent()).isEqualTo("crazy");
+        assertThat(wrapper.getActualContent().toString()).isEqualTo("craziest");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_iest_Tests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/test/resources/orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-29 00:02:47 UTC (rev 14942)
+++ trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-29 10:22:22 UTC (rev 14943)
@@ -33,6 +33,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_iest_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est2_Factory"/>

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14942] trunk/foray/foray-orthograp hy/src

From: <vic...@us...> - 2026-07-29 00:02:49

Revision: 14942
          http://sourceforge.net/p/foray/code/14942
Author:   victormote
Date:     2026-07-29 00:02:47 +0000 (Wed, 29 Jul 2026)
Log Message:
-----------
Convert another XML derivative-pattern to java classes.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java
    trunk/foray/foray-orthography/src/test/resources/orthography-config.xml

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Factory.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_i.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_FactoryTests.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Tests.java

Modified: trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-28 23:34:10 UTC (rev 14941)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-29 00:02:47 UTC (rev 14942)
@@ -43,14 +43,6 @@
   </match-rule-list>
 
   <derivative-pattern-list id="eng-Latn-derivative-patterns">
-    <derivative-pattern desc="ends with /-ier/, root ends with /-y/">
-      <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)ier$</match>
-      <replace>$1y</replace>
-      <derivative-rule>
-        <adjective><extensible/></adjective>
-        <derivative-type type="comparative"/>
-      </derivative-rule>
-    </derivative-pattern>
     <derivative-pattern desc="ends with /-iest/, root ends with /-y/">
       <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)iest$</match>
       <replace>$1y</replace>
@@ -92,6 +84,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ier_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier.java	2026-07-29 00:02:47 UTC (rev 14942)
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.WordSegment4a;
+import org.foray.orthography.inflection.InflectedWord;
+import org.foray.orthography.inflection.mods.Replace_y_by_i;
+
+import java.util.regex.Pattern;
+
+/**
+ * Wraps an adjective ending in "y", converting the "y" to "ier" make it comparatively greater than the lemma.
+ * For example, the English word "crazy" would be wrapped to make the word "crazier".
+ */
+public class EngLatnSuffix_ier extends InflectedWord {
+
+    /** The pattern to be matched by words with this inflection. */
+    public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)ier$");
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = 6349215976483323091L;
+
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
+    /**
+     * Constructor.
+     * @param wrappedWord The wrapped word.
+     */
+    public EngLatnSuffix_ier(final Word4a wrappedWord) {
+        super(wrappedWord);
+        this.modifiedSegment = new Replace_y_by_i(wrappedWord.getLastWordSegment());
+    }
+
+    @Override
+    public WordSegment4a getAppendedSegment() {
+        return EngLatn.ER_SEGMENT;
+    }
+
+    @Override
+    public WordSegment4a getModifiedSegment() {
+        return this.modifiedSegment;
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Factory.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Factory.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Factory.java	2026-07-29 00:02:47 UTC (rev 14942)
@@ -0,0 +1,87 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.inflection.InflectionFactory;
+
+import org.axsl.orthography.PartOfSpeech;
+import org.axsl.orthography.PosQualifier;
+
+import java.util.regex.Matcher;
+
+/**
+ * Factory class for {@link EngLatnSuffix_ier}.
+ */
+public final class EngLatnSuffix_ier_Factory extends InflectionFactory<EngLatnSuffix_ier> {
+
+    /** The singleton instance. */
+    private static final EngLatnSuffix_ier_Factory THE_INSTANCE = new EngLatnSuffix_ier_Factory();
+
+    /**
+     * Private constructor for this singleton class.
+     */
+    private EngLatnSuffix_ier_Factory() { }
+
+    /**
+     * Returns the singleton instance.
+     * @return The singleton instance.
+     */
+    public static EngLatnSuffix_ier_Factory getInstance() {
+        return THE_INSTANCE;
+    }
+
+    @Override
+    public CharSequence findLemmaChars(final CharSequence chars) {
+        final Matcher matcher = EngLatnSuffix_ier.PATTERN.matcher(chars);
+        if (! matcher.matches()) {
+            return null;
+        }
+
+        final String lemmaChars = matcher.group(1) + "y";
+        return lemmaChars;
+    }
+
+    @Override
+    public boolean isValidLemma(final Word4a lemma) {
+        if (lemma.isOfQualifiedType(PartOfSpeech.ADJECTIVE, PosQualifier.EXTENSIBLE)) {
+            /*
+             <derivative-type type="comparative" desc="single-syllable root"/>
+             */
+            return true;
+        }
+        return false;
+    }
+
+    @Override
+    protected EngLatnSuffix_ier makeInstance(final Word4a lemma) {
+        return new EngLatnSuffix_ier(lemma);
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Factory.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_i.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_i.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_i.java	2026-07-29 00:02:47 UTC (rev 14942)
@@ -0,0 +1,61 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.mods;
+
+import org.foray.orthography.inflection.ModifiedWordSegment;
+
+import org.axsl.orthography.WordSegment;
+
+/**
+ * Replaces a trailing "y" with "i" in the wrapped word segment.
+ */
+public class Replace_y_by_i extends ModifiedWordSegment {
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = 7801850814679870505L;
+
+    /**
+     * Constructor.
+     * @param wrappedSegment The wrapped segment.
+     */
+    public Replace_y_by_i(final WordSegment wrappedSegment) {
+        super(wrappedSegment);
+    }
+
+    @Override
+    public String getNormalForm() {
+        return "y";
+    }
+
+    @Override
+    public String getWrappedForm() {
+        return "i";
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_i.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java	2026-07-28 23:34:10 UTC (rev 14941)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java	2026-07-29 00:02:47 UTC (rev 14942)
@@ -140,11 +140,20 @@
     public static final StringWord WORD_THIN = new StringWord(EXTENSIBLE_ADJECTIVE, "thin");
 
     /** An adjective test word: thinner. */
-    public static final StringWord WORD_THINNER = new StringWord(EXTENSIBLE_ADJECTIVE, "thin", "ner");
+    public static final StringWord WORD_THINNER = new StringWord(PosBuilder.ADJECTIVE, "thin", "ner");
 
     /** An adjective test word: thinnest. */
-    public static final StringWord WORD_THINNEST = new StringWord(EXTENSIBLE_ADJECTIVE, "thin", "nest");
+    public static final StringWord WORD_THINNEST = new StringWord(PosBuilder.ADJECTIVE, "thin", "nest");
 
+    /** An extensible adjective test word: crazy. */
+    public static final StringWord WORD_CRAZY = new StringWord(EXTENSIBLE_ADJECTIVE, "cra", "zy");
+
+    /** An adjective test word: crazier. */
+    public static final StringWord WORD_CRAZIER = new StringWord(PosBuilder.ADJECTIVE, "cra", "zi", "er");
+
+    /** An adjective test word: craziest. */
+    public static final StringWord WORD_CRAZIEST = new StringWord(PosBuilder.ADJECTIVE, "cra", "zi", "est");
+
     /**
      * Test of {@link StringWord#getWordComponent(int)}.
      */

Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_FactoryTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_FactoryTests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_FactoryTests.java	2026-07-29 00:02:47 UTC (rev 14942)
@@ -0,0 +1,80 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Dictionary4a;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.assertj.core.api.AssertionsForClassTypes;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+import org.mockito.Mockito;
+
+/**
+ * Tests of {@link EngLatnSuffix_ier_Factory}.
+ */
+public class EngLatnSuffix_ier_FactoryTests {
+
+    /** The object under test. */
+    private EngLatnSuffix_ier_Factory out;
+
+    /** A dictionary to use for these tests. */
+    private Dictionary4a dictionary;
+
+    /**
+     * Test setup.
+     */
+    @BeforeEach
+    public void before() {
+        this.out = EngLatnSuffix_ier_Factory.getInstance();
+        this.dictionary = Mockito.mock(Dictionary4a.class);
+        Mockito.when(dictionary.getWord("crazy")).thenReturn(StringWordTests.WORD_CRAZY);
+    }
+
+    /**
+     * Test of a String for which the factory should not be able to create an instance.
+     */
+    @Test
+    public void testInvalid() {
+        AssertionsForClassTypes.assertThat(out.makeInstance("craziest", this.dictionary)).isNull();
+    }
+
+    /**
+     * Test of a String for which the factory should be able to create an instance.
+     */
+    @Test
+    public void testValid() {
+        final EngLatnSuffix_ier word = out.makeInstance("crazier", this.dictionary);
+        /* Test for instance equality. */
+        AssertionsForClassTypes.assertThat(word.getWrappedWord()).isEqualTo(StringWordTests.WORD_CRAZY);
+        assertThat(word.getActualContent().toString()).isEqualTo("crazier");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_FactoryTests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Tests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Tests.java	2026-07-29 00:02:47 UTC (rev 14942)
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.StringWord;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.junit.jupiter.api.Test;
+
+/**
+ * Tests of {@link EngLatnSuffix_ier}.
+ */
+public class EngLatnSuffix_ier_Tests {
+
+    /**
+     * Tests various aspects word ending in -ier.
+     */
+    @Test
+    public void test01() {
+        final StringWord word = StringWordTests.WORD_CRAZY;
+        final EngLatnSuffix_ier wrapper = new EngLatnSuffix_ier(word);
+
+        assertThat(wrapper.toString()).isEqualTo("cra-zi-er");
+        assertThat(wrapper.getNormalizedContent()).isEqualTo("crazy");
+        assertThat(wrapper.getActualContent().toString()).isEqualTo("crazier");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ier_Tests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/test/resources/orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-28 23:34:10 UTC (rev 14941)
+++ trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-29 00:02:47 UTC (rev 14942)
@@ -28,6 +28,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ier_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14941] trunk/foray/foray-orthograp hy/src

From: <vic...@us...> - 2026-07-28 23:34:13

Revision: 14941
          http://sourceforge.net/p/foray/code/14941
Author:   victormote
Date:     2026-07-28 23:34:10 +0000 (Tue, 28 Jul 2026)
Log Message:
-----------
Convert another XML derivative-pattern to java classes.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_est.java
    trunk/foray/foray-orthography/src/test/resources/orthography-config.xml

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Factory.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_er.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_FactoryTests.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Tests.java

Modified: trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-28 23:14:26 UTC (rev 14940)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-28 23:34:10 UTC (rev 14941)
@@ -43,14 +43,6 @@
   </match-rule-list>
 
   <derivative-pattern-list id="eng-Latn-derivative-patterns">
-    <derivative-pattern desc="ends with certain double consonants, then /-er/">
-      <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)([d])(\2)er$</match>
-      <replace>$1$2</replace>
-      <derivative-rule>
-        <adjective><extensible/></adjective>
-        <derivative-type type="comparative"/>
-      </derivative-rule>
-    </derivative-pattern>
     <derivative-pattern desc="ends with /-ier/, root ends with /-y/">
       <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)ier$</match>
       <replace>$1y</replace>
@@ -100,6 +92,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>
 

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er.java	2026-07-28 23:34:10 UTC (rev 14941)
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.WordSegment4a;
+import org.foray.orthography.inflection.InflectedWord;
+import org.foray.orthography.inflection.mods.Full_2c_er;
+
+import java.util.regex.Pattern;
+
+/**
+ * Wraps an extensible adjective that ends with a vowel and then a consonant, doubles that consonant, then adds "er" at
+ * the end to make it a comparative.
+ * For example, the English word "thin" would be wrapped to make the word "thinner".
+ */
+public class EngLatnSuffix_2c_er extends InflectedWord {
+
+    /** The pattern to be matched by words with this inflection. */
+    public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)([dgnt])(\\2)er$");
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = -3858054928625944035L;
+
+    /**
+     * Constructor.
+     * @param wrappedWord The wrapped word.
+     */
+    public EngLatnSuffix_2c_er(final Word4a wrappedWord) {
+        super(wrappedWord);
+    }
+
+    @Override
+    public WordSegment4a getAppendedSegment() {
+        final WordSegment4a lastSegment = getWrappedWord().getLastWordSegment();
+        final int lastIndex = lastSegment.length() - 1;
+        final char lastChar = lastSegment.charAt(lastIndex);
+        return Full_2c_er.getInstance(lastChar);
+    }
+
+    @Override
+    public WordSegment4a getModifiedSegment() {
+        return null;
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Factory.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Factory.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Factory.java	2026-07-28 23:34:10 UTC (rev 14941)
@@ -0,0 +1,88 @@
+/*
+ * Copyright 2019 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.inflection.InflectionFactory;
+
+import org.axsl.orthography.PartOfSpeech;
+import org.axsl.orthography.PosQualifier;
+
+import java.util.regex.Matcher;
+
+/**
+ * Factory class for {@link EngLatnSuffix_2c_er}.
+ */
+public final class EngLatnSuffix_2c_er_Factory extends InflectionFactory<EngLatnSuffix_2c_er> {
+
+    /** The singleton instance. */
+    private static final EngLatnSuffix_2c_er_Factory THE_INSTANCE = new EngLatnSuffix_2c_er_Factory();
+
+    /**
+     * Private constructor for this singleton class.
+     */
+    private EngLatnSuffix_2c_er_Factory() { }
+
+    /**
+     * Returns the singleton instance.
+     * @return The singleton instance.
+     */
+    public static EngLatnSuffix_2c_er_Factory getInstance() {
+        return THE_INSTANCE;
+    }
+
+    @Override
+    public CharSequence findLemmaChars(final CharSequence chars) {
+        final Matcher matcher = EngLatnSuffix_2c_er.PATTERN.matcher(chars);
+        if (! matcher.matches()) {
+            return null;
+        }
+
+        final String lemmaChars = matcher.group(1) + matcher.group(2);
+        return lemmaChars;
+    }
+
+    @Override
+    public boolean isValidLemma(final Word4a lemma) {
+        if (lemma.isOfQualifiedType(PartOfSpeech.ADJECTIVE, PosQualifier.EXTENSIBLE)) {
+            /*
+             <adjective><extensible/></adjective>
+             <derivative-type type="comparative"/>
+             */
+            return true;
+        }
+        return false;
+    }
+
+    @Override
+    protected EngLatnSuffix_2c_er makeInstance(final Word4a lemma) {
+        return new EngLatnSuffix_2c_er(lemma);
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Factory.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est.java	2026-07-28 23:14:26 UTC (rev 14940)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est.java	2026-07-28 23:34:10 UTC (rev 14941)
@@ -43,7 +43,7 @@
 public class EngLatnSuffix_2c_est extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
-    public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)([dn])(\\2)est$");
+    public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)([dgnt])(\\2)est$");
 
     /** Constant needed for serialization. */
     private static final long serialVersionUID = 8397674653229148700L;

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_er.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_er.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_er.java	2026-07-28 23:34:10 UTC (rev 14941)
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.mods;
+
+import org.foray.common.primitive.CodePointUtils;
+import org.foray.orthography.StringWordSegmentLatin1;
+import org.foray.orthography.WordSegment4a;
+
+/**
+ * Full segment composed of a single consonant following by "er".
+ */
+public final class Full_2c_er {
+
+    /** Pre-constructed instance staring with "d". */
+    private static final StringWordSegmentLatin1 D_INSTANCE = new StringWordSegmentLatin1("der");
+
+    /** Pre-constructed instance staring with "g". */
+    private static final StringWordSegmentLatin1 G_INSTANCE = new StringWordSegmentLatin1("ger");
+
+    /** Pre-constructed instance staring with "n". */
+    private static final StringWordSegmentLatin1 N_INSTANCE = new StringWordSegmentLatin1("ner");
+
+    /** Pre-constructed instance staring with "t". */
+    private static final StringWordSegmentLatin1 T_INSTANCE = new StringWordSegmentLatin1("ter");
+
+    /**
+     * Private constructor. This is a utility class that should not be instantiated.
+     */
+    private Full_2c_er() { }
+
+    /**
+     * Gets the segment instance that beings with a specified consonant.
+     * @param consonant The consonant for which the segment instance is needed.
+     * @return The segment instance for {@code consonant}.
+     */
+    public static WordSegment4a getInstance(final int consonant) {
+        switch (consonant) {
+        case 'd': return D_INSTANCE;
+        case 'g': return G_INSTANCE;
+        case 'n': return N_INSTANCE;
+        case 't': return T_INSTANCE;
+        }
+        throw new IllegalArgumentException("Unexpected leading consonant: " + CodePointUtils.toString(consonant));
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_er.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_est.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_est.java	2026-07-28 23:14:26 UTC (rev 14940)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_est.java	2026-07-28 23:34:10 UTC (rev 14941)
@@ -40,9 +40,15 @@
     /** Pre-constructed instance staring with "d". */
     private static final StringWordSegmentLatin1 D_INSTANCE = new StringWordSegmentLatin1("dest");
 
+    /** Pre-constructed instance staring with "g". */
+    private static final StringWordSegmentLatin1 G_INSTANCE = new StringWordSegmentLatin1("gest");
+
     /** Pre-constructed instance staring with "n". */
     private static final StringWordSegmentLatin1 N_INSTANCE = new StringWordSegmentLatin1("nest");
 
+    /** Pre-constructed instance staring with "t". */
+    private static final StringWordSegmentLatin1 T_INSTANCE = new StringWordSegmentLatin1("test");
+
     /**
      * Private constructor. This is a utility class that should not be instantiated.
      */
@@ -56,7 +62,9 @@
     public static WordSegment4a getInstance(final int consonant) {
         switch (consonant) {
         case 'd': return D_INSTANCE;
+        case 'g': return G_INSTANCE;
         case 'n': return N_INSTANCE;
+        case 't': return T_INSTANCE;
         }
         throw new IllegalArgumentException("Unexpected leading consonant: " + CodePointUtils.toString(consonant));
     }

Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_FactoryTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_FactoryTests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_FactoryTests.java	2026-07-28 23:34:10 UTC (rev 14941)
@@ -0,0 +1,81 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Dictionary4a;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.assertj.core.api.AssertionsForClassTypes;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+import org.mockito.Mockito;
+
+/**
+ * Tests of {@link EngLatnSuffix_2c_er_Factory}.
+ */
+public class EngLatnSuffix_2c_er_FactoryTests {
+
+    /** The object under test. */
+    private EngLatnSuffix_2c_er_Factory out;
+
+    /** A dictionary to use for these tests. */
+    private Dictionary4a dictionary;
+
+    /**
+     * Test setup.
+     */
+    @BeforeEach
+    public void before() {
+        this.out = EngLatnSuffix_2c_er_Factory.getInstance();
+        this.dictionary = Mockito.mock(Dictionary4a.class);
+        Mockito.when(dictionary.getWord("thin")).thenReturn(StringWordTests.WORD_THIN);
+    }
+
+    /**
+     * Test of a String for which the factory should not be able to create an instance.
+     */
+    @Test
+    public void testInvalid() {
+        final EngLatnSuffix_2c_er word = out.makeInstance("thinnest", this.dictionary);
+        AssertionsForClassTypes.assertThat(word).isNull();
+    }
+
+    /**
+     * Test of a String for which the factory should be able to create an instance.
+     */
+    @Test
+    public void testValid() {
+        final EngLatnSuffix_2c_er word = out.makeInstance("thinner", this.dictionary);
+        /* Test for instance equality. */
+        AssertionsForClassTypes.assertThat(word.getWrappedWord()).isSameAs(StringWordTests.WORD_THIN);
+        assertThat(word.getActualContent().toString()).isEqualTo("thinner");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_FactoryTests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Tests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Tests.java	2026-07-28 23:34:10 UTC (rev 14941)
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.StringWord;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.junit.jupiter.api.Test;
+
+/**
+ * Tests of {@link EngLatnSuffix_2c_er}.
+ */
+public class EngLatnSuffix_2c_er_Tests {
+
+    /**
+     * Tests for words ending in double-consonant following by "er".
+     */
+    @Test
+    public void test01() {
+        final StringWord word = StringWordTests.WORD_THIN;
+        final EngLatnSuffix_2c_er wrapper = new EngLatnSuffix_2c_er(word);
+
+        assertThat(wrapper.toString()).isEqualTo("thin-ner");
+        assertThat(wrapper.getNormalizedContent()).isEqualTo("thin");
+        assertThat(wrapper.getActualContent().toString()).isEqualTo("thinner");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_er_Tests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/test/resources/orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-28 23:14:26 UTC (rev 14940)
+++ trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-28 23:34:10 UTC (rev 14941)
@@ -28,6 +28,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>
 

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14940] trunk/foray/foray-orthograp hy/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml

From: <vic...@us...> - 2026-07-28 23:14:29

Revision: 14940
          http://sourceforge.net/p/foray/code/14940
Author:   victormote
Date:     2026-07-28 23:14:26 +0000 (Tue, 28 Jul 2026)
Log Message:
-----------
Normal dictionary editing.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml

Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-28 23:14:04 UTC (rev 14939)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-28 23:14:26 UTC (rev 14940)
@@ -17440,7 +17440,7 @@
 <w><t>blithe-some</t></w>
 <w><t>blithe-some-ly</t></w>
 <w><t>blithe-some-ness</t></w>
-<w><t>blitz</t></w>
+<w><t>blitz</t><noun><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>Blitz</t></w>
 <w><t>blitz-krieg</t></w>
 <w><t>Blitz-stein</t></w>
@@ -21581,6 +21581,7 @@
 </section>
 
 <section description="C">
+<section description="C abbrev">
 <w><t>C/A</t></w>
 <w><t>c/d</t></w>
 <w><t>c/f</t></w>
@@ -21588,6 +21589,9 @@
 <w><t>c/n</t></w>
 <w><t>c/o</t></w>
 <w><t>C=3</t></w>
+</section>
+
+<section description="Ca">
 <w><t>Caa-ba</t></w>
 <w><t>Ca-an-thus</t></w>
 <w><t>CAB</t></w>
@@ -24869,6 +24873,9 @@
 <w><t>cay-use</t></w>
 <w><t>Caz-e-no-vi-a</t></w>
 <w><t>ca-zique</t></w>
+</section>
+
+<section description="Cb to Cd">
 <phrase><t>C bat-ter-y</t></phrase>
 <w><t>CBC</t></w>
 <w><t>CBD</t></w>
@@ -24887,6 +24894,9 @@
 <w><t>C-do-va</t></w>
 <w><t>Cdr</t></w>
 <w><t>CDT</t></w>
+</section>
+
+<section description="Ce to Cg">
 <w><t>ce-a-no-thus</t></w>
 <w><t>Cea-r</t></w>
 <w><t>Ce-a-rá</t></w>
@@ -25548,6 +25558,9 @@
 <w><t>CGM</t></w>
 <w><t>CGS</t></w>
 <phrase><t>cgs u-nits</t></phrase>
+</section>
+
+<section description="Ch">
 <w><t>ch.</t><abbrev referenced-word="chapter"/></w>
 <w><t>chab-a-zite</t></w>
 <w><t>Chab-lis</t></w>
@@ -27924,6 +27937,9 @@
 <w><t>chy-mo-tryp-sin-o-gen</t></w>
 <w><t>chy-mous</t></w>
 <w><t>chypre</t></w>
+</section>
+
+<section description="Ci">
 <w><t>CIA</t></w>
 <w><t>Cia-no</t></w>
 <w><t>ciao</t></w>
@@ -28505,6 +28521,9 @@
 <w><t>civ-ism</t></w>
 <w><t>civ-vies</t></w>
 <w><t>civ-vy</t></w>
+</section>
+
+<section description="Cl">
 <w><t>clab-ber</t></w>
 <w><t>clab-u-lar-i-a</t></w>
 <w><t>clab-u-lar-i-um</t></w>
@@ -29406,6 +29425,9 @@
 <w><t>Clyt-i-a</t></w>
 <w><t>Cly-ti-ë</t></w>
 <w><t>Cly-ti-us</t></w>
+</section>
+
+<section description="Cm to Cn">
 <w><t>Cmdr</t></w>
 <w><t>CMF</t></w>
 <w><t>CMG</t></w>
@@ -29433,6 +29455,7 @@
 <w><t>C=note</t></w>
 <w><t>CNS</t></w>
 <w><t>Cnut</t></w>
+</section>
 
 <section description="Co">
 <w><t>CO</t><abbrev referenced-word="Colorado"/></w>
@@ -34803,6 +34826,7 @@
 <w><t>cov-et-ous-ly</t></w>
 <w><t>cov-et-ous-ness</t></w>
 <w><t>cov-ey</t></w>
+<w><t>COVID</t><noun><convertible-to-possessive/></noun></w>
 <w><t>cov-in</t></w>
 <w><t>Co-vi-na</t></w>
 <w><t>cov-ing</t></w>
@@ -34922,6 +34946,7 @@
 <w><t>Coz-zens</t></w>
 </section>
 
+<section description="Cp to Cr">
 <w><t>cpd</t></w>
 <w><t>Cpl</t></w>
 <w><t>CPO</t></w>
@@ -36283,6 +36308,9 @@
 <phrase><t>crys-tal sys-tem</t></phrase>
 <phrase><t>crys-tal vi-o-let</t></phrase>
 <w><t>cr-zette</t></w>
+</section>
+
+<section description="Cs to Ct">
 <w><t>C’s</t></w>
 <w><t>CSB</t></w>
 <w><t>csc</t></w>
@@ -36313,6 +36341,9 @@
 <w><t>ctr</t></w>
 <w><t>cts</t></w>
 <w><t>CTV</t></w>
+</section>
+
+<section description="Cu">
 <w><t>cua-dril-la</t></w>
 <w><t>cua-dril-las</t></w>
 <w><t>cua-mu-chil</t></w>
@@ -37018,6 +37049,9 @@
 <w><t>Cu-ya-bá</t></w>
 <w><t>Cuyp</t></w>
 <w><t>Cuz-co</t></w>
+</section>
+
+<section description="Cv to Cz">
 <w><t>CVA</t></w>
 <w><t>C-vennes</t></w>
 <w><t>CVO</t></w>
@@ -37397,6 +37431,7 @@
 <w><t>Cz-sto-cho-wa</t></w>
 <w><t>C-zur</t></w>
 </section>
+</section>
 
 <section description="D">
 <w><t>D/A</t></w>
@@ -46668,8 +46703,11 @@
 </section>
 
 <section description="E">
+<section description="E abbrev">
 <w><t>e.g.</t><abbrev referenced-word="exempli gratia"/><comment>Latin "for example."</comment></w>
 <w><t>e.&#xA0;g.</t><abbrev referenced-word="exempli gratia"/><comment>Latin "for example."</comment></w>
+</section>
+<section description="Ea">
 <w><t>e-a-bly</t></w>
 <w><t>each</t></w>
 <phrase><t>each oth-er</t></phrase>
@@ -46921,6 +46959,8 @@
 <w><t>eaves-dropped</t></w>
 <w><t>eaves-drop-per</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>eaves-drop-ping</t></w>
+</section>
+<section description="Eb">
 <w><t>ebb</t><verb><regular-root/></verb></w>
 <w><t>EBCDIC</t></w>
 <w><t>Eb-e-ne-zer</t></w>
@@ -46952,6 +46992,9 @@
 <w><t>e-bul-li-os-co-py</t></w>
 <w><t>eb-ul-li-tion</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>e-bur-na-tion</t></w>
+</section>
+
+<section description="Ec">
 <w><t>e-cad</t></w>
 <w><t>e-cal-ca-rate</t></w>
 <w><t>e-car-i-nate</t></w>
@@ -47224,6 +47267,9 @@
 <w><t>ec-ze-ma</t></w>
 <w><t>ec-ze-ma-toid</t></w>
 <w><t>ec-zem-a-tous</t></w>
+</section>
+
+<section description="Ed">
 <w><t>ed.</t><abbrev referenced-word="editor, edited"/></w>
 <w><t>Ed-a</t></w>
 <w><t>e-da-cious</t></w>
@@ -47415,6 +47461,9 @@
 <w><t>E-dyie</t></w>
 <w><t>E-dyth</t></w>
 <w><t>E-dythe</t></w>
+</section>
+
+<section description="Ee">
 <w><t>EEC</t></w>
 <w><t>EEG</t></w>
 <w><t>eel</t></w>
@@ -47437,6 +47486,9 @@
 <w><t>Eer-o-te-ma</t></w>
 <w><t>ee-ry</t></w>
 <w><t>E-ë-ti-on</t></w>
+</section>
+
+<section description="Ef">
 <w><t>E-fa-h</t></w>
 <w><t>E-fa-han</t></w>
 <w><t>eff</t></w>
@@ -47559,6 +47611,9 @@
 <w><t>EFTA</t></w>
 <w><t>eft-soon</t></w>
 <w><t>eft-soons</t></w>
+</section>
+
+<section description="Eg">
 <w><t>e-gad</t></w>
 <w><t>E-ga-di</t></w>
 <w><t>e-gal</t></w>
@@ -47640,6 +47695,9 @@
 <w><t>E-gyp-to-log-i-cal</t></w>
 <w><t>E-gyp-tol-o-gist</t></w>
 <w><t>E-gyp-tol-o-gy</t></w>
+</section>
+
+<section description="Eh to Ei">
 <w><t>EHF</t></w>
 <w><t>Eh-ren-breit-stein</t></w>
 <w><t>Eh-ren-burg</t></w>
@@ -47731,6 +47789,9 @@
 <w><t>eis-tedd-fods</t></w>
 <w><t>ei-ther</t></w>
 <w><t>ei-ther=or</t></w>
+</section>
+
+<section description="Ej to Ek">
 <w><t>e-jac-u-late</t><verb><regular-root/></verb></w>
 <w><t>e-jac-u-lat-ed</t></w>
 <w><t>e-jac-u-lat-ing</t></w>
@@ -47755,6 +47816,9 @@
 <w><t>ek-ing</t></w>
 <w><t>e-kis-tics</t></w>
 <w><t>ek-te-ne</t></w>
+</section>
+
+<section description="El">
 <phrase><t>El Aai-un</t></phrase>
 <w><t>e-lab-o-rate</t></w>
 <w><t>e-lab-o-rat-ed</t></w>
@@ -48509,6 +48573,9 @@
 <w><t>El-ze-vier</t></w>
 <w><t>El-ze-vir</t></w>
 <w><t>El-ze-vir-i-an</t></w>
+</section>
+
+<section description="Em">
 <w><t>’em</t><contraction referenced-word="them"/></w>
 <w><t>e-ma-ci-ate</t></w>
 <w><t>e-ma-ci-at-ed</t></w>
@@ -48515,6 +48582,8 @@
 <w><t>e-ma-ci-at-ing</t></w>
 <w><t>e-ma-ci-a-tion</t></w>
 <w><t>em-a-gram</t></w>
+<w><t>e-mail</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
+<w><t>e=mail</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>em-a-nant</t></w>
 <w><t>em-a-nate</t><verb><regular-root/></verb></w>
 <w><t>em-a-nat-ed</t></w>
@@ -49008,6 +49077,9 @@
 <w><t>e-munc-to-ry</t></w>
 <w><t>e-mu=wren</t></w>
 <w><t>em-yrie</t></w>
+</section>
+
+<section description="En">
 <w><t>E-na</t></w>
 <w><t>en-a-ble</t><verb><regular-root/></verb></w>
 <w><t>en-a-bler</t></w>
@@ -50167,6 +50239,9 @@
 <w><t>en-zy-mol-y-sis</t></w>
 <w><t>en-zy-mo-lyt-ic</t></w>
 <w><t>en-zy-mo-sis</t></w>
+</section>
+
+<section description="Eo">
 <w><t>e-o-bi-ont</t></w>
 <w><t>E-o-cene</t></w>
 <w><t>E-o-gene</t></w>
@@ -50195,6 +50270,9 @@
 <w><t>e-o-sin-o-phil-ic</t></w>
 <w><t>e-o-si-noph-i-lous</t></w>
 <w><t>E-o-zo-ic</t></w>
+</section>
+
+<section description="Ep">
 <w><t>e-p</t></w>
 <w><t>EPA</t></w>
 <w><t>e-pact</t></w>
@@ -50670,6 +50748,9 @@
 <w><t>ep-u-lo-nes</t></w>
 <w><t>ep-u-ra-tion</t></w>
 <w><t>e-pyl-li-on</t></w>
+</section>
+
+<section description="Eq">
 <w><t>eq-ua-bil-i-ty</t></w>
 <w><t>eq-ua-ble</t></w>
 <w><t>eq-ua-ble-ness</t></w>
@@ -50824,6 +50905,9 @@
 <w><t>E-quu-le-i</t></w>
 <w><t>E-quul-e-us</t></w>
 <w><t>E-quu-le-us</t></w>
+</section>
+
+<section description="Er">
 <w><t>e-ra</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>e-ra-di-ate</t></w>
 <w><t>e-ra-di-at-ed</t></w>
@@ -51138,6 +51222,9 @@
 <w><t>Er-ze-rum</t></w>
 <w><t>Erz-ge-bir-ge</t></w>
 <w><t>Er-zu-rum</t></w>
+</section>
+
+<section description="Es">
 <phrase><t>E-sa-ki di-ode</t></phrase>
 <w><t>E-sau</t></w>
 <w><t>ESB</t></w>
@@ -51481,6 +51568,9 @@
 <w><t>e-su-ri-en-cy</t></w>
 <w><t>e-su-ri-ent</t></w>
 <w><t>e-su-ri-ent-ly</t></w>
+</section>
+
+<section description="Et">
 <w><t>ETA</t></w>
 <w><t>Et-a</t></w>
 <w><t>E-ta</t></w>
@@ -51729,6 +51819,9 @@
 <w><t>et-y-mol-o-gy</t></w>
 <w><t>et-y-mon</t></w>
 <w><t>Et-zel</t></w>
+</section>
+
+<section description="Eu">
 <w><t>Eu-aech-me</t></w>
 <w><t>eu-bac-te-ri-a</t></w>
 <w><t>eu-bac-te-ri-um</t></w>
@@ -52074,6 +52167,9 @@
 <w><t>eux-e-nite</t></w>
 <w><t>Eux-ine</t></w>
 <phrase><t>Eux-ine Sea</t></phrase>
+</section>
+
+<section description="Ev">
 <w><t>EVA</t></w>
 <w><t>E-va</t></w>
 <w><t>e-vac-u-ant</t></w>
@@ -52335,6 +52431,9 @@
 <w><t>Ev-voi-a</t></w>
 <w><t>Ev-y-leen</t></w>
 <w><t>ev-zone</t></w>
+</section>
+
+<section description="Ew to Ex">
 <w><t>E-wa</t></w>
 <w><t>E-wald</t></w>
 <w><t>Ew-an</t></w>
@@ -53581,6 +53680,9 @@
 <w><t>ex-u-vi-at-ing</t></w>
 <w><t>ex-u-vi-a-tion</t></w>
 <phrase><t>ex vo-to</t></phrase>
+</section>
+
+<section description="Ey to Ez">
 <w><t>e-ya-let</t></w>
 <w><t>ey-as</t></w>
 <w><t>ey-ass</t></w>
@@ -53673,6 +53775,7 @@
 <w><t>Ez-ra</t></w>
 <w><t>Ez-zard</t></w>
 </section>
+</section>
 
 <section description="F">
 <w><t>fab</t></w>
@@ -54827,8 +54930,8 @@
 <w><t>Fe-do-ra</t></w>
 <w><t>fee</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>fee-ble</t><adjective><extensible/></adjective></w>
-<w><t>fee-ble=mind-ed</t></w>
-<w><t>fee-ble=mind-ed-ness</t></w>
+<w><t>fee-ble-mind-ed</t></w>
+<w><t>fee-ble-mind-ed-ness</t></w>
 <w><t>fee-ble-ness</t></w>
 <w><t>fee-ble=voiced</t></w>
 <w><t>fee-blish</t></w>
@@ -97653,7 +97756,7 @@
 <w><t>mo-lyb-de-num</t></w>
 <w><t>mo-lyb-dic</t></w>
 <w><t>mo-lyb-dous</t></w>
-<w><t>mom</t></w>
+<w><t>mom</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Mom-ba-sa</t></w>
 <w><t>mome</t></w>
 <w><t>Mo-mence</t></w>
@@ -115571,7 +115674,7 @@
 <w><t>par-a-chor</t></w>
 <w><t>pa-rach-ro-nism</t></w>
 <w><t>par-ach-ro-nis-tic</t></w>
-<w><t>par-a-chute</t></w>
+<w><t>par-a-chute</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>par-a-chut-ed</t></w>
 <w><t>par-a-chut-er</t></w>
 <w><t>par-a-chut-ic</t></w>
@@ -119376,7 +119479,7 @@
 <w><t>pho-na-tion</t></w>
 <w><t>pho-na-to-ry</t></w>
 <w><t>phon-au-to-graph</t></w>
-<w><t>phone</t></w>
+<w><t>phone</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
 <w><t>pho-ne-mat-ic</t></w>
 <w><t>pho-ne-mat-ics</t></w>
 <w><t>pho-neme</t></w>
@@ -126619,7 +126722,8 @@
 <w><t>pres-by-ter-ies</t></w>
 <w><t>pres-by-ter-y</t></w>
 <w><t>pre-scho-las-tic</t></w>
-<w><t>pre-school</t></w>
+<w><t>pre-school</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
+<w><t>pre-school-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>pres-ci-ence</t></w>
 <w><t>pre-sci-ence</t></w>
 <w><t>pre-sci-ent</t></w>
@@ -134431,7 +134535,7 @@
 <w><t>rec-u-sant</t></w>
 <w><t>re-cut</t></w>
 <w><t>re-cut-ting</t></w>
-<w><t>re-cy-cle</t></w>
+<w><t>re-cy-cle</t><verb><regular-root/></verb></w>
 <w><t>Red</t></w>
 <w><t>red</t></w>
 <w><t>re-dact</t></w>
@@ -138438,6 +138542,7 @@
 <w><t>re-wak-ing</t></w>
 <w><t>re-wan</t></w>
 <w><t>re-ward</t><noun><pluralizable/><convertible-to-possessive/></noun><verb><regular-root/></verb></w>
+<w><t>re-ward-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>re-ward-ing</t></w>
 <w><t>re-wa=re-wa</t></w>
 <w><t>re-warm</t></w>
@@ -143069,7 +143174,7 @@
 <w><t>sconce</t></w>
 <w><t>scon-cheon</t></w>
 <w><t>sconc-ing</t></w>
-<w><t>scone</t></w>
+<w><t>scone</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>Scone</t></w>
 <w><t>scoop</t></w>
 <w><t>scoop-er</t></w>
@@ -143328,7 +143433,7 @@
 <w><t>scrim-maged</t></w>
 <w><t>scrim-mag-er</t></w>
 <w><t>scrim-mag-ing</t></w>
-<w><t>scrimp</t></w>
+<w><t>scrimp</t><verb><regular-root/></verb></w>
 <w><t>scrimp-i-er</t></w>
 <w><t>scrimp-i-est</t></w>
 <w><t>scrimp-y</t></w>
@@ -151418,7 +151523,7 @@
 <w><t>spar-oid</t></w>
 <w><t>spar-ring</t></w>
 <phrase><t>spar-ring part-ner</t></phrase>
-<w><t>spar-row</t></w>
+<w><t>spar-row</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>spar-row-grass</t></w>
 <w><t>spar-row-hawk</t></w>
 <phrase><t>spar-row hawk</t></phrase>
@@ -166748,7 +166853,7 @@
 <w><t>Tu-can-a</t></w>
 <w><t>Tu-can-ae</t></w>
 <w><t>tu-chun</t></w>
-<w><t>tuck</t></w>
+<w><t>tuck</t><verb><regular-root/></verb></w>
 <w><t>Tuck</t></w>
 <w><t>Tuck-a-hoe</t></w>
 <phrase><t>tuck a-way</t></phrase>

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14939] trunk/foray/foray-orthograp hy/src

From: <vic...@us...> - 2026-07-28 23:14:06

Revision: 14939
          http://sourceforge.net/p/foray/code/14939
Author:   victormote
Date:     2026-07-28 23:14:04 +0000 (Tue, 28 Jul 2026)
Log Message:
-----------
Convert another XML derivative-pattern to java classes.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
    trunk/foray/foray-orthography/src/test/resources/orthography-config.xml

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Factory.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_ing.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_FactoryTests.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Tests.java

Modified: trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-28 17:18:45 UTC (rev 14938)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-28 23:14:04 UTC (rev 14939)
@@ -43,14 +43,6 @@
   </match-rule-list>
 
   <derivative-pattern-list id="eng-Latn-derivative-patterns">
-    <derivative-pattern desc="ends with certain double consonants, then /-ing/">
-      <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)([bcdfgklmnprstvz])(\2)ing$</match>
-      <replace>$1$2</replace>
-      <derivative-rule>
-        <verb><regular-root/></verb>
-        <derivative-type type="present-participle"/>
-      </derivative-rule>
-    </derivative-pattern>
     <derivative-pattern desc="ends with certain double consonants, then /-er/">
       <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)([d])(\2)er$</match>
       <replace>$1$2</replace>
@@ -104,6 +96,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ed_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ed2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing2_Factory"/>
 

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing.java	2026-07-28 23:14:04 UTC (rev 14939)
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.WordSegment4a;
+import org.foray.orthography.inflection.InflectedWord;
+import org.foray.orthography.inflection.mods.Full_2c_ing;
+
+import java.util.regex.Pattern;
+
+/**
+ * Wraps an extensible adjective that ends with a vowel and then a consonant, doubles that consonant, then adds "ing" at
+ * the end.
+ * For example, the English word "beg" would be wrapped to make the word "beg-ging".
+ */
+public class EngLatnSuffix_2c_ing extends InflectedWord {
+
+    /** The pattern to be matched by words with this inflection. */
+    public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)([bdfgklmnprstvz])(\\2)ing$");
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = -2590657455118804639L;
+
+    /**
+     * Constructor.
+     * @param wrappedWord The wrapped word.
+     */
+    public EngLatnSuffix_2c_ing(final Word4a wrappedWord) {
+        super(wrappedWord);
+    }
+
+    @Override
+    public WordSegment4a getAppendedSegment() {
+        final WordSegment4a lastSegment = getWrappedWord().getLastWordSegment();
+        final int lastIndex = lastSegment.length() - 1;
+        final char lastChar = lastSegment.charAt(lastIndex);
+        return Full_2c_ing.getInstance(lastChar);
+    }
+
+    @Override
+    public WordSegment4a getModifiedSegment() {
+        return null;
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Factory.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Factory.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Factory.java	2026-07-28 23:14:04 UTC (rev 14939)
@@ -0,0 +1,88 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.inflection.InflectionFactory;
+
+import org.axsl.orthography.PartOfSpeech;
+import org.axsl.orthography.PosQualifier;
+
+import java.util.regex.Matcher;
+
+/**
+ * Factory class for {@link EngLatnSuffix_2c_ing}.
+ */
+public final class EngLatnSuffix_2c_ing_Factory extends InflectionFactory<EngLatnSuffix_2c_ing> {
+
+    /** The singleton instance. */
+    private static final EngLatnSuffix_2c_ing_Factory THE_INSTANCE = new EngLatnSuffix_2c_ing_Factory();
+
+    /**
+     * Private constructor for this singleton class.
+     */
+    private EngLatnSuffix_2c_ing_Factory() { }
+
+    /**
+     * Returns the singleton instance.
+     * @return The singleton instance.
+     */
+    public static EngLatnSuffix_2c_ing_Factory getInstance() {
+        return THE_INSTANCE;
+    }
+
+    @Override
+    public CharSequence findLemmaChars(final CharSequence chars) {
+        final Matcher matcher = EngLatnSuffix_2c_ing.PATTERN.matcher(chars);
+        if (! matcher.matches()) {
+            return null;
+        }
+
+        final String lemmaChars = matcher.group(1) + matcher.group(2);
+        return lemmaChars;
+    }
+
+    @Override
+    public boolean isValidLemma(final Word4a lemma) {
+        if (lemma.isOfQualifiedType(PartOfSpeech.VERB, PosQualifier.REGULAR_ROOT)) {
+            /*
+             <verb><regular-root/></verb>
+             <derivative-type type="present-participle"/>
+             */
+            return true;
+        }
+        return false;
+    }
+
+    @Override
+    protected EngLatnSuffix_2c_ing makeInstance(final Word4a lemma) {
+        return new EngLatnSuffix_2c_ing(lemma);
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Factory.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_ing.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_ing.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_ing.java	2026-07-28 23:14:04 UTC (rev 14939)
@@ -0,0 +1,112 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.mods;
+
+import org.foray.common.primitive.CodePointUtils;
+import org.foray.orthography.StringWordSegmentLatin1;
+import org.foray.orthography.WordSegment4a;
+
+/**
+ * Full segment composed of a single consonant following by "ing".
+ */
+public final class Full_2c_ing {
+
+    /** Pre-constructed instance staring with "b". */
+    private static final StringWordSegmentLatin1 B_INSTANCE = new StringWordSegmentLatin1("bing");
+
+    /** Pre-constructed instance staring with "d". */
+    private static final StringWordSegmentLatin1 D_INSTANCE = new StringWordSegmentLatin1("ding");
+
+    /** Pre-constructed instance staring with "f". */
+    private static final StringWordSegmentLatin1 F_INSTANCE = new StringWordSegmentLatin1("fing");
+
+    /** Pre-constructed instance staring with "g". */
+    private static final StringWordSegmentLatin1 G_INSTANCE = new StringWordSegmentLatin1("ging");
+
+    /** Pre-constructed instance staring with "k". */
+    private static final StringWordSegmentLatin1 K_INSTANCE = new StringWordSegmentLatin1("king");
+
+    /** Pre-constructed instance staring with "l". */
+    private static final StringWordSegmentLatin1 L_INSTANCE = new StringWordSegmentLatin1("ling");
+
+    /** Pre-constructed instance staring with "m". */
+    private static final StringWordSegmentLatin1 M_INSTANCE = new StringWordSegmentLatin1("ming");
+
+    /** Pre-constructed instance staring with "n". */
+    private static final StringWordSegmentLatin1 N_INSTANCE = new StringWordSegmentLatin1("ning");
+
+    /** Pre-constructed instance staring with "p". */
+    private static final StringWordSegmentLatin1 P_INSTANCE = new StringWordSegmentLatin1("ping");
+
+    /** Pre-constructed instance staring with "r". */
+    private static final StringWordSegmentLatin1 R_INSTANCE = new StringWordSegmentLatin1("ring");
+
+    /** Pre-constructed instance staring with "s". */
+    private static final StringWordSegmentLatin1 S_INSTANCE = new StringWordSegmentLatin1("sing");
+
+    /** Pre-constructed instance staring with "t". */
+    private static final StringWordSegmentLatin1 T_INSTANCE = new StringWordSegmentLatin1("ting");
+
+    /** Pre-constructed instance staring with "v". */
+    private static final StringWordSegmentLatin1 V_INSTANCE = new StringWordSegmentLatin1("ving");
+
+    /** Pre-constructed instance staring with "z". */
+    private static final StringWordSegmentLatin1 Z_INSTANCE = new StringWordSegmentLatin1("zing");
+
+    /**
+     * Private constructor. This is a utility class that should not be instantiated.
+     */
+    private Full_2c_ing() { }
+
+    /**
+     * Gets the segment instance that beings with a specified consonant.
+     * @param consonant The consonant for which the segment instance is needed.
+     * @return The segment instance for {@code consonant}.
+     */
+    public static WordSegment4a getInstance(final int consonant) {
+        switch (consonant) {
+        case 'b': return B_INSTANCE;
+        case 'd': return D_INSTANCE;
+        case 'f': return F_INSTANCE;
+        case 'g': return G_INSTANCE;
+        case 'k': return K_INSTANCE;
+        case 'l': return L_INSTANCE;
+        case 'm': return M_INSTANCE;
+        case 'n': return N_INSTANCE;
+        case 'p': return P_INSTANCE;
+        case 'r': return R_INSTANCE;
+        case 's': return S_INSTANCE;
+        case 't': return T_INSTANCE;
+        case 'v': return V_INSTANCE;
+        case 'z': return Z_INSTANCE;
+        }
+        throw new IllegalArgumentException("Unexpected leading consonant: " + CodePointUtils.toString(consonant));
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_ing.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_FactoryTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_FactoryTests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_FactoryTests.java	2026-07-28 23:14:04 UTC (rev 14939)
@@ -0,0 +1,81 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Dictionary4a;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.assertj.core.api.AssertionsForClassTypes;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+import org.mockito.Mockito;
+
+/**
+ * Tests of {@link EngLatnSuffix_2c_ing_Factory}.
+ */
+public class EngLatnSuffix_2c_ing_FactoryTests {
+
+    /** The object under test. */
+    private EngLatnSuffix_2c_ing_Factory out;
+
+    /** A dictionary to use for these tests. */
+    private Dictionary4a dictionary;
+
+    /**
+     * Test setup.
+     */
+    @BeforeEach
+    public void before() {
+        this.out = EngLatnSuffix_2c_ing_Factory.getInstance();
+        this.dictionary = Mockito.mock(Dictionary4a.class);
+        Mockito.when(dictionary.getWord("plan")).thenReturn(StringWordTests.WORD_PLAN);
+    }
+
+    /**
+     * Test of a String for which the factory should not be able to create an instance.
+     */
+    @Test
+    public void testInvalid() {
+        final EngLatnSuffix_2c_ing word = out.makeInstance("planned", this.dictionary);
+        AssertionsForClassTypes.assertThat(word).isNull();
+    }
+
+    /**
+     * Test of a String for which the factory should be able to create an instance.
+     */
+    @Test
+    public void testValid() {
+        final EngLatnSuffix_2c_ing word = out.makeInstance("planning", this.dictionary);
+        /* Test for instance equality. */
+        AssertionsForClassTypes.assertThat(word.getWrappedWord()).isSameAs(StringWordTests.WORD_PLAN);
+        assertThat(word.getActualContent().toString()).isEqualTo("planning");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_FactoryTests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Tests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Tests.java	2026-07-28 23:14:04 UTC (rev 14939)
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.StringWord;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.junit.jupiter.api.Test;
+
+/**
+ * Tests of {@link EngLatnSuffix_2c_ing}.
+ */
+public class EngLatnSuffix_2c_ing_Tests {
+
+    /**
+     * Tests for words ending in double-consonant following by "ing".
+     */
+    @Test
+    public void test01() {
+        final StringWord word = StringWordTests.WORD_PLAN;
+        final EngLatnSuffix_2c_ing wrapper = new EngLatnSuffix_2c_ing(word);
+
+        assertThat(wrapper.toString()).isEqualTo("plan-ning");
+        assertThat(wrapper.getNormalizedContent()).isEqualTo("plan");
+        assertThat(wrapper.getActualContent().toString()).isEqualTo("planning");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ing_Tests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/test/resources/orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-28 17:18:45 UTC (rev 14938)
+++ trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-28 23:14:04 UTC (rev 14939)
@@ -24,6 +24,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ed_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ed2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing2_Factory"/>
 

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14938] trunk/foray

From: <vic...@us...> - 2026-07-28 17:18:48

Revision: 14938
          http://sourceforge.net/p/foray/code/14938
Author:   victormote
Date:     2026-07-28 17:18:45 +0000 (Tue, 28 Jul 2026)
Log Message:
-----------
Convert another XML derivative-pattern to java classes.

Modified Paths:
--------------
    trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CodePointUtils.java
    trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java
    trunk/foray/foray-orthography/src/test/resources/orthography-config.xml

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Factory.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_est.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_FactoryTests.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Tests.java

Modified: trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CodePointUtils.java
===================================================================
--- trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CodePointUtils.java	2026-07-28 14:59:23 UTC (rev 14937)
+++ trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CodePointUtils.java	2026-07-28 17:18:45 UTC (rev 14938)
@@ -385,4 +385,14 @@
         }
     }
 
+    /**
+     * Converts a Unicode codePoint to a String containing its char(s).
+     * @param codePoint The Unicode codePoint to be converted.
+     * @return A String containing the char(s) in {@code codePoint}.
+     */
+    public static String toString(final int codePoint) {
+        /* TODO: After upgrading to Java 11+, replace use of this method with Character.toString(int codePoint). */
+        return new String(Character.toChars(codePoint));
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-28 14:59:23 UTC (rev 14937)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/eng-Latn-ZZZ.dict.xml	2026-07-28 17:18:45 UTC (rev 14938)
@@ -11146,7 +11146,7 @@
 <phrase><t>at-tend-ance cen-tre</t></phrase>
 <w><t>at-tend-ant</t><noun><pluralizable/><convertible-to-possessive/></noun><adjective><extensible value="false"/></adjective></w>
 <w><t>at-tend-ant-ly</t></w>
-<w><t>at-tend-er</t></w>
+<w><t>at-tend-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>at-tend-ing</t></w>
 <w><t>at-tend-ing-ly</t></w>
 <w><t>at-tent</t></w>
@@ -27265,7 +27265,7 @@
 <w><t>chock-er</t></w>
 <w><t>chock-stone</t></w>
 <w><t>choc-o</t></w>
-<w><t>choc-o-late</t></w>
+<w><t>choc-o-late</t><noun><pluralizable/><convertible-to-possessive/></noun><adjective></adjective></w>
 <w><t>choc-o-late=box</t></w>
 <w><t>choc-o-late=flow-er</t></w>
 <w><t>choc-o-lat-y</t></w>
@@ -55912,7 +55912,7 @@
 <phrase><t>fin-ger’s breadth</t></phrase>
 <w><t>fin-ger-stall</t></w>
 <phrase><t>fin-ger tight</t></phrase>
-<w><t>fin-ger-tip</t></w>
+<w><t>fin-ger-tip</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <phrase><t>fin-ger wave</t></phrase>
 <w><t>fin-ger-y</t></w>
 <w><t>Fin-go</t></w>
@@ -70447,7 +70447,7 @@
 <w><t>hob-bler</t></w>
 <phrase><t>hob-ble skirt</t></phrase>
 <w><t>Hobbs</t></w>
-<w><t>hob-by</t></w>
+<w><t>hob-by</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>hob-by-horse</t></w>
 <w><t>hob-by=horse</t></w>
 <w><t>hob-by-ist</t></w>
@@ -89764,7 +89764,7 @@
 <w><t>los-sy</t></w>
 <w><t>lost</t></w>
 <phrase><t>Lost Gen-er-a-tion</t></phrase>
-<w><t>Lot</t></w>
+<w><t>Lot</t><noun><convertible-to-possessive/><proper/></noun></w>
 <w><t>lot</t></w>
 <w><t>lo-ta</t></w>
 <w><t>L’O-tage</t></w>
@@ -111811,7 +111811,7 @@
 <w><t>out-raved</t></w>
 <w><t>out-rav-ing</t></w>
 <w><t>ou-tré</t></w>
-<w><t>out-reach</t></w>
+<w><t>out-reach</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>out-read</t></w>
 <w><t>out-read-ing</t></w>
 <w><t>out-rea-son</t></w>
@@ -114681,7 +114681,7 @@
 <w><t>pain-ful</t></w>
 <w><t>pain-ful-ly</t></w>
 <w><t>pain-ful-ness</t></w>
-<w><t>pain-kill-er</t></w>
+<w><t>pain-kill-er</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>pain-kil-ler</t></w>
 <w><t>pain-less</t></w>
 <w><t>pains</t></w>
@@ -180976,6 +180976,7 @@
 <w><t>veg-e-ta-tion-al</t></w>
 <w><t>veg-e-ta-tion-less</t></w>
 <w><t>veg-e-ta-tive</t></w>
+<w><t>veg-gie</t><noun><pluralizable/><convertible-to-possessive/></noun></w>
 <w><t>ve-he-mence</t></w>
 <w><t>ve-he-men-cy</t></w>
 <w><t>ve-he-ment</t></w>

Modified: trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-28 14:59:23 UTC (rev 14937)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-28 17:18:45 UTC (rev 14938)
@@ -59,14 +59,6 @@
         <derivative-type type="comparative"/>
       </derivative-rule>
     </derivative-pattern>
-    <derivative-pattern desc="ends with certain double consonants, then /-est/">
-      <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)([d])(\2)est$</match>
-      <replace>$1$2</replace>
-      <derivative-rule>
-        <adjective><extensible/></adjective>
-        <derivative-type type="superlative"/>
-      </derivative-rule>
-    </derivative-pattern>
     <derivative-pattern desc="ends with /-ier/, root ends with /-y/">
       <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)ier$</match>
       <replace>$1y</replace>
@@ -118,6 +110,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est2_Factory"/>
   </derivative-factory-list>

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est.java	2026-07-28 17:18:45 UTC (rev 14938)
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2019 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.WordSegment4a;
+import org.foray.orthography.inflection.InflectedWord;
+import org.foray.orthography.inflection.mods.Full_2c_est;
+
+import java.util.regex.Pattern;
+
+/**
+ * Wraps an extensible adjective that ends with a vowel and then a consonant, doubles that consonant, then adds "est" at
+ * the end to make it a superlative.
+ * For example, the English word "thin" would be wrapped to make the word "thinnest".
+ */
+public class EngLatnSuffix_2c_est extends InflectedWord {
+
+    /** The pattern to be matched by words with this inflection. */
+    public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)([dn])(\\2)est$");
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = 8397674653229148700L;
+
+    /**
+     * Constructor.
+     * @param wrappedWord The wrapped word.
+     */
+    public EngLatnSuffix_2c_est(final Word4a wrappedWord) {
+        super(wrappedWord);
+    }
+
+    @Override
+    public WordSegment4a getAppendedSegment() {
+        final WordSegment4a lastSegment = getWrappedWord().getLastWordSegment();
+        final int lastIndex = lastSegment.length() - 1;
+        final char lastChar = lastSegment.charAt(lastIndex);
+        return Full_2c_est.getInstance(lastChar);
+    }
+
+    @Override
+    public WordSegment4a getModifiedSegment() {
+        return null;
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Factory.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Factory.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Factory.java	2026-07-28 17:18:45 UTC (rev 14938)
@@ -0,0 +1,88 @@
+/*
+ * Copyright 2019 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.inflection.InflectionFactory;
+
+import org.axsl.orthography.PartOfSpeech;
+import org.axsl.orthography.PosQualifier;
+
+import java.util.regex.Matcher;
+
+/**
+ * Factory class for {@link EngLatnSuffix_2c_est}.
+ */
+public final class EngLatnSuffix_2c_est_Factory extends InflectionFactory<EngLatnSuffix_2c_est> {
+
+    /** The singleton instance. */
+    private static final EngLatnSuffix_2c_est_Factory THE_INSTANCE = new EngLatnSuffix_2c_est_Factory();
+
+    /**
+     * Private constructor for this singleton class.
+     */
+    private EngLatnSuffix_2c_est_Factory() { }
+
+    /**
+     * Returns the singleton instance.
+     * @return The singleton instance.
+     */
+    public static EngLatnSuffix_2c_est_Factory getInstance() {
+        return THE_INSTANCE;
+    }
+
+    @Override
+    public CharSequence findLemmaChars(final CharSequence chars) {
+        final Matcher matcher = EngLatnSuffix_2c_est.PATTERN.matcher(chars);
+        if (! matcher.matches()) {
+            return null;
+        }
+
+        final String lemmaChars = matcher.group(1) + matcher.group(2);
+        return lemmaChars;
+    }
+
+    @Override
+    public boolean isValidLemma(final Word4a lemma) {
+        if (lemma.isOfQualifiedType(PartOfSpeech.ADJECTIVE, PosQualifier.EXTENSIBLE)) {
+            /*
+             <adjective><extensible/></adjective>
+             <derivative-type type="superlative"/>
+             */
+            return true;
+        }
+        return false;
+    }
+
+    @Override
+    protected EngLatnSuffix_2c_est makeInstance(final Word4a lemma) {
+        return new EngLatnSuffix_2c_est(lemma);
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Factory.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_est.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_est.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_est.java	2026-07-28 17:18:45 UTC (rev 14938)
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.mods;
+
+import org.foray.common.primitive.CodePointUtils;
+import org.foray.orthography.StringWordSegmentLatin1;
+import org.foray.orthography.WordSegment4a;
+
+/**
+ * Full segment composed of a single consonant following by "est".
+ */
+public final class Full_2c_est {
+
+    /** Pre-constructed instance staring with "d". */
+    private static final StringWordSegmentLatin1 D_INSTANCE = new StringWordSegmentLatin1("dest");
+
+    /** Pre-constructed instance staring with "n". */
+    private static final StringWordSegmentLatin1 N_INSTANCE = new StringWordSegmentLatin1("nest");
+
+    /**
+     * Private constructor. This is a utility class that should not be instantiated.
+     */
+    private Full_2c_est() { }
+
+    /**
+     * Gets the segment instance that beings with a specified consonant.
+     * @param consonant The consonant for which the segment instance is needed.
+     * @return The segment instance for {@code consonant}.
+     */
+    public static WordSegment4a getInstance(final int consonant) {
+        switch (consonant) {
+        case 'd': return D_INSTANCE;
+        case 'n': return N_INSTANCE;
+        }
+        throw new IllegalArgumentException("Unexpected leading consonant: " + CodePointUtils.toString(consonant));
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Full_2c_est.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java	2026-07-28 14:59:23 UTC (rev 14937)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java	2026-07-28 17:18:45 UTC (rev 14938)
@@ -136,6 +136,15 @@
     /** A verb test word: replied. */
     public static final StringWord WORD_REPLIED = new StringWord(REGULAR_VERB, "re", "plied");
 
+    /** An adjective test word: thin. */
+    public static final StringWord WORD_THIN = new StringWord(EXTENSIBLE_ADJECTIVE, "thin");
+
+    /** An adjective test word: thinner. */
+    public static final StringWord WORD_THINNER = new StringWord(EXTENSIBLE_ADJECTIVE, "thin", "ner");
+
+    /** An adjective test word: thinnest. */
+    public static final StringWord WORD_THINNEST = new StringWord(EXTENSIBLE_ADJECTIVE, "thin", "nest");
+
     /**
      * Test of {@link StringWord#getWordComponent(int)}.
      */

Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_FactoryTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_FactoryTests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_FactoryTests.java	2026-07-28 17:18:45 UTC (rev 14938)
@@ -0,0 +1,81 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Dictionary4a;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.assertj.core.api.AssertionsForClassTypes;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+import org.mockito.Mockito;
+
+/**
+ * Tests of {@link EngLatnSuffix_2c_est_Factory}.
+ */
+public class EngLatnSuffix_2c_est_FactoryTests {
+
+    /** The object under test. */
+    private EngLatnSuffix_2c_est_Factory out;
+
+    /** A dictionary to use for these tests. */
+    private Dictionary4a dictionary;
+
+    /**
+     * Test setup.
+     */
+    @BeforeEach
+    public void before() {
+        this.out = EngLatnSuffix_2c_est_Factory.getInstance();
+        this.dictionary = Mockito.mock(Dictionary4a.class);
+        Mockito.when(dictionary.getWord("thin")).thenReturn(StringWordTests.WORD_THIN);
+    }
+
+    /**
+     * Test of a String for which the factory should not be able to create an instance.
+     */
+    @Test
+    public void testInvalid() {
+        final EngLatnSuffix_2c_est word = out.makeInstance("thinner", this.dictionary);
+        AssertionsForClassTypes.assertThat(word).isNull();
+    }
+
+    /**
+     * Test of a String for which the factory should be able to create an instance.
+     */
+    @Test
+    public void testValid() {
+        final EngLatnSuffix_2c_est word = out.makeInstance("thinnest", this.dictionary);
+        /* Test for instance equality. */
+        AssertionsForClassTypes.assertThat(word.getWrappedWord()).isSameAs(StringWordTests.WORD_THIN);
+        assertThat(word.getActualContent().toString()).isEqualTo("thinnest");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_FactoryTests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Tests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Tests.java	2026-07-28 17:18:45 UTC (rev 14938)
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.StringWord;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.junit.jupiter.api.Test;
+
+/**
+ * Tests of {@link EngLatnSuffix_2c_est}.
+ */
+public class EngLatnSuffix_2c_est_Tests {
+
+    /**
+     * Tests for words ending in double-consonant following by "est".
+     */
+    @Test
+    public void test01() {
+        final StringWord word = StringWordTests.WORD_THIN;
+        final EngLatnSuffix_2c_est wrapper = new EngLatnSuffix_2c_est(word);
+
+        assertThat(wrapper.toString()).isEqualTo("thin-nest");
+        assertThat(wrapper.getNormalizedContent()).isEqualTo("thin");
+        assertThat(wrapper.getActualContent().toString()).isEqualTo("thinnest");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_est_Tests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/test/resources/orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-28 14:59:23 UTC (rev 14937)
+++ trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-28 17:18:45 UTC (rev 14938)
@@ -30,6 +30,7 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>
 
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est2_Factory"/>
   </derivative-factory-list>

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14937] trunk/foray/foray-orthograp hy/src

From: <vic...@us...> - 2026-07-28 14:59:26

Revision: 14937
          http://sourceforge.net/p/foray/code/14937
Author:   victormote
Date:     2026-07-28 14:59:23 +0000 (Tue, 28 Jul 2026)
Log Message:
-----------
Convert another XML derivative-pattern to java classes.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/WordWrapperTests.java
    trunk/foray/foray-orthography/src/test/resources/orthography-config.xml

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Factory.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_ied.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/package-info.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_FactoryTests.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Tests.java

Modified: trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-28 12:42:36 UTC (rev 14936)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2026-07-28 14:59:23 UTC (rev 14937)
@@ -43,15 +43,6 @@
   </match-rule-list>
 
   <derivative-pattern-list id="eng-Latn-derivative-patterns">
-    <derivative-pattern desc="ends with /-ied/, stem ends with /y/">
-      <match>^([a-zæœëöA-ZÆŒ\-‘’ ]+)ied$</match>
-      <replace>$1y</replace>
-      <derivative-rule>
-        <verb><regular-root/></verb>
-        <derivative-type type="verb-form" desc="past tense"/>
-        <derivative-type type="past-participle"/>
-      </derivative-rule>
-    </derivative-pattern>
     <derivative-pattern desc="ends with certain double consonants, then /-ing/">
       <match>^([a-zæœëéöA-ZÆŒ\-‘’ ]+)([bcdfgklmnprstvz])(\2)ing$</match>
       <replace>$1$2</replace>
@@ -115,13 +106,18 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_es_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_apos_s_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_s_Factory"/>
+
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ied_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_ed_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ed_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ed2_Factory"/>
+
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing2_Factory"/>
+
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>
+
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est2_Factory"/>
   </derivative-factory-list>

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied.java	2026-07-28 14:59:23 UTC (rev 14937)
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.WordSegment4a;
+import org.foray.orthography.inflection.InflectedWord;
+import org.foray.orthography.inflection.mods.Replace_y_by_ied;
+
+import java.util.regex.Pattern;
+
+/**
+ * Wraps a word, usually a regular verb, whose last segment ends in a consonant and a "y", converting the "y" to "ied".
+ * An example of a word where this might be used is to convert "re-ply" to "re-plied".
+ */
+public class EngLatnSuffix_ied extends InflectedWord {
+
+    /** The pattern to be matched by words with this inflection. One or more characters, followed by a single consonant,
+     * followed by "ied". */
+    public static final Pattern PATTERN = Pattern.compile(
+            "^(" + EngLatn.WORD_CHARS + "+" + EngLatn.CONSONANT_CHARS + ")ied$");
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = -5727030865320206765L;
+
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
+    /**
+     * Constructor.
+     * @param wrappedWord The wrapped word.
+     */
+    public EngLatnSuffix_ied(final Word4a wrappedWord) {
+        super(wrappedWord);
+        this.modifiedSegment = new Replace_y_by_ied(wrappedWord.getLastWordSegment());
+    }
+
+    @Override
+    public WordSegment4a getAppendedSegment() {
+        return null;
+    }
+
+    @Override
+    public WordSegment4a getModifiedSegment() {
+        return this.modifiedSegment;
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Factory.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Factory.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Factory.java	2026-07-28 14:59:23 UTC (rev 14937)
@@ -0,0 +1,88 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Word4a;
+import org.foray.orthography.inflection.InflectionFactory;
+
+import org.axsl.orthography.PartOfSpeech;
+import org.axsl.orthography.PosQualifier;
+
+import java.util.regex.Matcher;
+
+/**
+ * Factory class for {@link EngLatnSuffix_ied}.
+ */
+public final class EngLatnSuffix_ied_Factory extends InflectionFactory<EngLatnSuffix_ied> {
+
+    /** The singleton instance. */
+    private static final EngLatnSuffix_ied_Factory THE_INSTANCE = new EngLatnSuffix_ied_Factory();
+
+    /**
+     * Private constructor for this singleton class.
+     */
+    private EngLatnSuffix_ied_Factory() { }
+
+    /**
+     * Returns the singleton instance.
+     * @return The singleton instance.
+     */
+    public static EngLatnSuffix_ied_Factory getInstance() {
+        return THE_INSTANCE;
+    }
+
+    @Override
+    public CharSequence findLemmaChars(final CharSequence chars) {
+        final Matcher matcher = EngLatnSuffix_ied.PATTERN.matcher(chars);
+        if (! matcher.matches()) {
+            return null;
+        }
+
+        final String lemmaChars = matcher.group(1) + "y";
+        return lemmaChars;
+    }
+
+    @Override
+    public boolean isValidLemma(final Word4a lemma) {
+        if (lemma.isOfQualifiedType(PartOfSpeech.VERB, PosQualifier.REGULAR_ROOT)) {
+            /*
+             <derivative-type type="verb-form" desc="past tense"/>
+             <derivative-type type="past-participle"/>
+             */
+            return true;
+        }
+        return false;
+    }
+
+    @Override
+    protected EngLatnSuffix_ied makeInstance(final Word4a lemma) {
+        return new EngLatnSuffix_ied(lemma);
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Factory.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_ied.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_ied.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_ied.java	2026-07-28 14:59:23 UTC (rev 14937)
@@ -0,0 +1,61 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.mods;
+
+import org.foray.orthography.inflection.ModifiedWordSegment;
+
+import org.axsl.orthography.WordSegment;
+
+/**
+ * Replaces a trailing "y" with "ied" in the wrapped word segment.
+ */
+public class Replace_y_by_ied extends ModifiedWordSegment {
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = 3690654458482335436L;
+
+    /**
+     * Constructor.
+     * @param wrappedSegment The wrapped segment.
+     */
+    public Replace_y_by_ied(final WordSegment wrappedSegment) {
+        super(wrappedSegment);
+    }
+
+    @Override
+    public String getNormalForm() {
+        return "y";
+    }
+
+    @Override
+    public String getWrappedForm() {
+        return "ied";
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/Replace_y_by_ied.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/package-info.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/package-info.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/package-info.java	2026-07-28 14:59:23 UTC (rev 14937)
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+/**
+ * <p>Classes modifying word segments for inflected words.</p>
+ */
+
+package org.foray.orthography.inflection.mods;


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/mods/package-info.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java	2026-07-28 12:42:36 UTC (rev 14936)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/StringWordTests.java	2026-07-28 14:59:23 UTC (rev 14937)
@@ -128,8 +128,14 @@
     public static final StringWord WORD_THRIVED = new StringWord(REGULAR_VERB, "thrived");
 
     /** A verb test word: thriving. */
-    public static final StringWord WORD_THRIVING = new StringWord(REGULAR_VERB, "thriv-ing");
+    public static final StringWord WORD_THRIVING = new StringWord(REGULAR_VERB, "thriv", "ing");
 
+    /** A regular verb test word: reply. */
+    public static final StringWord WORD_REPLY = new StringWord(REGULAR_VERB, "re", "ply");
+
+    /** A verb test word: replied. */
+    public static final StringWord WORD_REPLIED = new StringWord(REGULAR_VERB, "re", "plied");
+
     /**
      * Test of {@link StringWord#getWordComponent(int)}.
      */

Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/WordWrapperTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/WordWrapperTests.java	2026-07-28 12:42:36 UTC (rev 14936)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/WordWrapperTests.java	2026-07-28 14:59:23 UTC (rev 14937)
@@ -110,13 +110,11 @@
 
         assertThatThrownBy(() -> {
             this.out.charAt(-1);
-        }).isInstanceOf(IndexOutOfBoundsException.class)
-            .hasMessage("String index out of range: -1");
+        }).isInstanceOf(IndexOutOfBoundsException.class);
 
         assertThatThrownBy(() -> {
             this.out.charAt(10);
-        }).isInstanceOf(IndexOutOfBoundsException.class)
-            .hasMessage("String index out of range: 10");
+        }).isInstanceOf(IndexOutOfBoundsException.class);
     }
 
     /**

Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_FactoryTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_FactoryTests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_FactoryTests.java	2026-07-28 14:59:23 UTC (rev 14937)
@@ -0,0 +1,80 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.Dictionary4a;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.assertj.core.api.AssertionsForClassTypes;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+import org.mockito.Mockito;
+
+/**
+ * Tests of {@link EngLatnSuffix_ied_Factory}.
+ */
+public class EngLatnSuffix_ied_FactoryTests {
+
+    /** The object under test. */
+    private EngLatnSuffix_ied_Factory out;
+
+    /** A dictionary to use for these tests. */
+    private Dictionary4a dictionary;
+
+    /**
+     * Test setup.
+     */
+    @BeforeEach
+    public void before() {
+        this.out = EngLatnSuffix_ied_Factory.getInstance();
+        this.dictionary = Mockito.mock(Dictionary4a.class);
+        Mockito.when(dictionary.getWord("reply")).thenReturn(StringWordTests.WORD_REPLY);
+    }
+
+    /**
+     * Test of a String for which the factory should not be able to create an instance.
+     */
+    @Test
+    public void testInvalid() {
+        AssertionsForClassTypes.assertThat(out.makeInstance("replies", this.dictionary)).isNull();
+    }
+
+    /**
+     * Test of a String for which the factory should be able to create an instance.
+     */
+    @Test
+    public void testValid() {
+        final EngLatnSuffix_ied word = out.makeInstance("replied", this.dictionary);
+        /* Test for instance equality. */
+        AssertionsForClassTypes.assertThat(word.getWrappedWord()).isSameAs(StringWordTests.WORD_REPLY);
+        assertThat(word.getActualContent().toString()).isEqualTo("replied");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_FactoryTests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Tests.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Tests.java	2026-07-28 14:59:23 UTC (rev 14937)
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2026 The FOray Project.
+ *      http://www.foray.org
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This work is in part derived from the following work(s), used with the
+ * permission of the licensor:
+ *      Apache FOP, licensed by the Apache Software Foundation
+ *
+ */
+
+/*
+ * $LastChangedRevision$
+ * $LastChangedDate$
+ * $LastChangedBy$
+ */
+
+package org.foray.orthography.inflection.eng;
+
+import org.foray.orthography.StringWord;
+import org.foray.orthography.StringWordTests;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import org.junit.jupiter.api.Test;
+
+/**
+ * Tests of {@link EngLatnSuffix_ied}.
+ */
+public class EngLatnSuffix_ied_Tests {
+
+    /**
+     * Tests various aspects of word ending in -ied.
+     */
+    @Test
+    public void test01() {
+        final StringWord word = StringWordTests.WORD_REPLY;
+        final EngLatnSuffix_ied wrapper = new EngLatnSuffix_ied(word);
+
+        assertThat(wrapper.toString()).isEqualTo("re-plied");
+        assertThat(wrapper.getNormalizedContent()).isEqualTo("reply");
+        assertThat(wrapper.getActualContent().toString()).isEqualTo("replied");
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ied_Tests.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-orthography/src/test/resources/orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-28 12:42:36 UTC (rev 14936)
+++ trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2026-07-28 14:59:23 UTC (rev 14937)
@@ -18,13 +18,18 @@
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_es_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_apos_s_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_s_Factory"/>
+
+    <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ied_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_2c_ed_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ed_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ed2_Factory"/>
+
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_ing2_Factory"/>
+
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_er2_Factory"/>
+
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est_Factory"/>
     <derivative-factory class="org.foray.orthography.inflection.eng.EngLatnSuffix_est2_Factory"/>
   </derivative-factory-list>

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14936] trunk/foray/foray-orthograp hy/src/main/java/org/foray/orthography/inflection

From: <vic...@us...> - 2026-07-28 12:42:39

Revision: 14936
          http://sourceforge.net/p/foray/code/14936
Author:   victormote
Date:     2026-07-28 12:42:36 +0000 (Tue, 28 Jul 2026)
Log Message:
-----------
Remove no-longer useful abstract subclasses of InflectedWord.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ed.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_apos_s.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed2.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er2.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_es.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est2.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ies.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing2.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_s.java

Removed Paths:
-------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentAddedWord.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentModifiedWord.java

Deleted: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentAddedWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentAddedWord.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentAddedWord.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -1,49 +0,0 @@
-/*
- * Copyright 2019 The FOray Project.
- *      http://www.foray.org
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *      http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- *
- * This work is in part derived from the following work(s), used with the
- * permission of the licensor:
- *      Apache FOP, licensed by the Apache Software Foundation
- *
- */
-
-/*
- * $LastChangedRevision$
- * $LastChangedDate$
- * $LastChangedBy$
- */
-
-package org.foray.orthography.inflection;
-
-import org.foray.orthography.Word4a;
-
-/**
- * Wraps a word to add a final segment.
- */
-public abstract class FinalSegmentAddedWord extends InflectedWord {
-
-    /** Constant needed for serialization. */
-    private static final long serialVersionUID = -2950517772926478039L;
-
-    /**
-     * Constructor.
-     * @param wrappedWord The wrapped word.
-     */
-    public FinalSegmentAddedWord(final Word4a wrappedWord) {
-        super(wrappedWord);
-    }
-
-}

Deleted: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentModifiedWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentModifiedWord.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentModifiedWord.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -1,49 +0,0 @@
-/*
- * Copyright 2019 The FOray Project.
- *      http://www.foray.org
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *      http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- *
- * This work is in part derived from the following work(s), used with the
- * permission of the licensor:
- *      Apache FOP, licensed by the Apache Software Foundation
- *
- */
-
-/*
- * $LastChangedRevision$
- * $LastChangedDate$
- * $LastChangedBy$
- */
-
-package org.foray.orthography.inflection;
-
-import org.foray.orthography.Word4a;
-
-/**
- * Abstract superclass for word wrappers that modify the final segment of the word.
- */
-public abstract class FinalSegmentModifiedWord extends InflectedWord {
-
-    /** Constant needed for serialization. */
-    private static final long serialVersionUID = 8075477767144178967L;
-
-    /**
-     * Constructor.
-     * @param wrappedWord The wrapped word.
-     */
-    protected FinalSegmentModifiedWord(final Word4a wrappedWord) {
-        super(wrappedWord);
-    }
-
-}

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ed.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ed.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ed.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentModifiedWord;
+import org.foray.orthography.inflection.InflectedWord;
 import org.foray.orthography.inflection.mods.Add_2c_ed;
 
 import java.util.regex.Pattern;
@@ -40,7 +40,7 @@
  * to make it past tense or a past participle.
  * For example, the English word "plan" would be wrapped to make the word "planned".
  */
-public class EngLatnSuffix_2c_ed extends FinalSegmentModifiedWord {
+public class EngLatnSuffix_2c_ed extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)([bcdfgklmnprstvz])(\\2)ed");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_apos_s.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_apos_s.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_apos_s.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentModifiedWord;
+import org.foray.orthography.inflection.InflectedWord;
 import org.foray.orthography.inflection.mods.Add_apos_s;
 
 import java.util.regex.Pattern;
@@ -38,7 +38,7 @@
 /**
  * Wraps a singular word and adds the suffix "’s" to make it possessive or a contraction.
  */
-public class EngLatnSuffix_apos_s extends FinalSegmentModifiedWord {
+public class EngLatnSuffix_apos_s extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)’s$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentModifiedWord;
+import org.foray.orthography.inflection.InflectedWord;
 import org.foray.orthography.inflection.mods.Add_ed;
 
 import java.util.regex.Pattern;
@@ -39,7 +39,7 @@
  * Wraps a word, usually a verb, and adds a syllable "ed" to the end to make it past tense.
  * For example, the English word "astonish" would be wrapped to make the word "astonished".
  */
-public class EngLatnSuffix_ed extends FinalSegmentModifiedWord {
+public class EngLatnSuffix_ed extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)ed$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed2.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed2.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed2.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentModifiedWord;
+import org.foray.orthography.inflection.InflectedWord;
 import org.foray.orthography.inflection.mods.Add_d;
 
 import java.util.regex.Pattern;
@@ -39,7 +39,7 @@
  * Wraps a word, usually a verb ending in "e", and adds a "d" to the end to make it past tense.
  * For example, the English word "enable" would be wrapped to make the word "enabled".
  */
-public class EngLatnSuffix_ed2 extends FinalSegmentModifiedWord {
+public class EngLatnSuffix_ed2 extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+e)d$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentAddedWord;
+import org.foray.orthography.inflection.InflectedWord;
 
 import java.util.regex.Pattern;
 
@@ -39,7 +39,7 @@
  * than the lemma.
  * For example, the English word "hard" would be wrapped to make the word "harder".
  */
-public class EngLatnSuffix_er extends FinalSegmentAddedWord {
+public class EngLatnSuffix_er extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)er$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er2.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er2.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er2.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentAddedWord;
+import org.foray.orthography.inflection.InflectedWord;
 import org.foray.orthography.inflection.mods.Delete_e;
 
 import java.util.regex.Pattern;
@@ -40,7 +40,7 @@
  * end to make it comparatively greater than the lemma.
  * For example, the English word "wise" would be wrapped to make the word "wis-er".
  */
-public class EngLatnSuffix_er2 extends FinalSegmentAddedWord {
+public class EngLatnSuffix_er2 extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+e)r$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_es.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_es.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_es.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -31,7 +31,7 @@
 import org.foray.orthography.StringWordSegmentUtf16;
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentAddedWord;
+import org.foray.orthography.inflection.InflectedWord;
 
 import java.util.regex.Pattern;
 
@@ -45,7 +45,7 @@
  *   <li>Pluralize a cardinal like "six," converting it to "sixes."</li>
  * </ol>
  */
-public class EngLatnSuffix_es extends FinalSegmentAddedWord {
+public class EngLatnSuffix_es extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)([sxz]|sh|ch)es$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentAddedWord;
+import org.foray.orthography.inflection.InflectedWord;
 
 import java.util.regex.Pattern;
 
@@ -38,7 +38,7 @@
  * Wraps a word, usually a one-syllable adjective, and adds a syllable "est" to the end to make it a superlative.
  * For example, the English word "great" would be wrapped to make the word "greatest".
  */
-public class EngLatnSuffix_est extends FinalSegmentAddedWord {
+public class EngLatnSuffix_est extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)est$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est2.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est2.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est2.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentAddedWord;
+import org.foray.orthography.inflection.InflectedWord;
 import org.foray.orthography.inflection.mods.Delete_e;
 
 import java.util.regex.Pattern;
@@ -40,7 +40,7 @@
  * end to make it superlative to the lemma.
  * For example, the English word "wise" would be wrapped to make the word "wis-est".
  */
-public class EngLatnSuffix_est2 extends FinalSegmentAddedWord {
+public class EngLatnSuffix_est2 extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+e)st$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ies.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ies.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ies.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentModifiedWord;
+import org.foray.orthography.inflection.InflectedWord;
 import org.foray.orthography.inflection.mods.Replace_y_by_ies;
 
 import java.util.regex.Pattern;
@@ -40,7 +40,7 @@
  * the "y" to "ies", thus making the plural form of the word.
  * An example of a word where this might be used is to convert "com-pa-ny" to "com-pa-nies".
  */
-public class EngLatnSuffix_ies extends FinalSegmentModifiedWord {
+public class EngLatnSuffix_ies extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. One or more characters, followed by a single consonant,
      * followed by "ies". */

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentAddedWord;
+import org.foray.orthography.inflection.InflectedWord;
 
 import java.util.regex.Pattern;
 
@@ -38,7 +38,7 @@
  * Wraps a word, usually a verb, and adds a syllable "ing" to the end to make it a present participle.
  * For example, the English word "talk" would be wrapped to make the word "talking".
  */
-public class EngLatnSuffix_ing extends FinalSegmentAddedWord {
+public class EngLatnSuffix_ing extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)ing$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing2.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing2.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing2.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentAddedWord;
+import org.foray.orthography.inflection.InflectedWord;
 import org.foray.orthography.inflection.mods.Delete_e;
 
 import java.util.regex.Pattern;
@@ -40,7 +40,7 @@
  * make it a present participle.
  * For example, the English word "thrive" would be wrapped to make the word "thriving".
  */
-public class EngLatnSuffix_ing2 extends FinalSegmentAddedWord {
+public class EngLatnSuffix_ing2 extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)ing$");

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_s.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_s.java	2026-07-28 12:37:32 UTC (rev 14935)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_s.java	2026-07-28 12:42:36 UTC (rev 14936)
@@ -30,7 +30,7 @@
 
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
-import org.foray.orthography.inflection.FinalSegmentModifiedWord;
+import org.foray.orthography.inflection.InflectedWord;
 import org.foray.orthography.inflection.mods.Add_s;
 
 import java.util.regex.Pattern;
@@ -38,7 +38,7 @@
 /**
  * Wraps a singular word and adds the suffix "s" to make it plural.
  */
-public final class EngLatnSuffix_s extends FinalSegmentModifiedWord {
+public final class EngLatnSuffix_s extends InflectedWord {
 
     /** The pattern to be matched by words with this inflection. */
     public static final Pattern PATTERN = Pattern.compile("^(" + EngLatn.WORD_CHARS + "+)s$");

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

[FOray-commit] SF.net SVN: foray:[14935] trunk/foray/foray-orthograp hy/src/main/java/org/foray/orthography

From: <vic...@us...> - 2026-07-28 12:37:35

Revision: 14935
          http://sourceforge.net/p/foray/code/14935
Author:   victormote
Date:     2026-07-28 12:37:32 +0000 (Tue, 28 Jul 2026)
Log Message:
-----------
Unify wordSegmentAt() method for all InflectedWord subclasses.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Word4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentAddedWord.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentModifiedWord.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/InflectedWord.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ed.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_apos_s.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed2.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er2.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est2.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ies.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing2.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_s.java

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Word4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Word4a.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Word4a.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -213,6 +213,15 @@
     @Override
     public abstract WordSegment4a wordSegmentAt(int segmentIndex);
 
+    /**
+     * Convenience method that returns the last segment of this word.
+     * @return The last segment of this word.
+     */
+    public WordSegment4a getLastWordSegment() {
+        final int lastSegmentIndex = qtyWordSegments() - 1;
+        return wordSegmentAt(lastSegmentIndex);
+    }
+
     @Override
     public Type getKpNodeType() {
         return KpNode.Type.BRANCH;

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentAddedWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentAddedWord.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentAddedWord.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -29,7 +29,6 @@
 package org.foray.orthography.inflection;
 
 import org.foray.orthography.Word4a;
-import org.foray.orthography.WordSegment4a;
 
 /**
  * Wraps a word to add a final segment.
@@ -47,15 +46,4 @@
         super(wrappedWord);
     }
 
-    @Override
-    public WordSegment4a wordSegmentAt(final int segmentIndex) {
-        if (segmentIndex < getWrappedWord().qtyWordSegments()) {
-            return getWrappedWord().wordSegmentAt(segmentIndex);
-        }
-        if (segmentIndex < qtyWordSegments()) {
-            return getAppendedSegment();
-        }
-        throw new IndexOutOfBoundsException(Integer.toString(segmentIndex));
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentModifiedWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentModifiedWord.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/FinalSegmentModifiedWord.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -29,10 +29,7 @@
 package org.foray.orthography.inflection;
 
 import org.foray.orthography.Word4a;
-import org.foray.orthography.WordSegment4a;
 
-import org.axsl.orthography.WordSegment;
-
 /**
  * Abstract superclass for word wrappers that modify the final segment of the word.
  */
@@ -41,9 +38,6 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = 8075477767144178967L;
 
-    /** The word segment that replaces the last word segment in the wrapped word. */
-    private WordSegment4a lastSegment;
-
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -50,24 +44,6 @@
      */
     protected FinalSegmentModifiedWord(final Word4a wrappedWord) {
         super(wrappedWord);
-        final int lastSegmentIndex = wrappedWord.qtyWordSegments() - 1;
-        final WordSegment unmodifiedSegment = wrappedWord.wordSegmentAt(lastSegmentIndex);
-        this.lastSegment = createModifiedSegment(unmodifiedSegment);
     }
 
-    @Override
-    public WordSegment4a wordSegmentAt(final int segmentIndex) {
-        if (segmentIndex == qtyWordSegments() - 1) {
-            return this.lastSegment;
-        }
-        return getWrappedWord().wordSegmentAt(segmentIndex);
-    }
-
-    /**
-     * Returns the segment wrapper that should be treated as the final segment of this word.
-     * @param unmodifiedSegment The segment that should be wrapped to create the substitute.
-     * @return The segment that replaces the final segment.
-     */
-    protected abstract WordSegment4a createModifiedSegment(WordSegment unmodifiedSegment);
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/InflectedWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/InflectedWord.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/InflectedWord.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -28,6 +28,7 @@
 
 package org.foray.orthography.inflection;
 
+import org.foray.common.MarkedIndexOutOfBoundsException;
 import org.foray.orthography.Word4a;
 import org.foray.orthography.WordSegment4a;
 import org.foray.orthography.WordWrapper;
@@ -54,6 +55,32 @@
         return getWrappedWord().qtyWordSegments() + addedSegments;
     }
 
+    @Override
+    public WordSegment4a wordSegmentAt(final int segmentIndex) {
+        if (segmentIndex >= qtyWordSegments()) {
+            throw new MarkedIndexOutOfBoundsException(segmentIndex, qtyWordSegments());
+        }
+
+        if (getAppendedSegment() == null) {
+            if (segmentIndex == qtyWordSegments() - 1) {
+                if (getModifiedSegment() != null) {
+                    return getModifiedSegment();
+                }
+            }
+        } else {
+            if (segmentIndex == qtyWordSegments() - 1) {
+                return getAppendedSegment();
+            }
+            if (segmentIndex == qtyWordSegments() - 2) {
+                if (getModifiedSegment() != null) {
+                    return getModifiedSegment();
+                }
+            }
+        }
+
+        return getWrappedWord().wordSegmentAt(segmentIndex);
+    }
+
     /**
      * Returns the word segment to be appended, if any.
      * @return The segment to be appended, or null if none should be appended.

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ed.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ed.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_2c_ed.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -33,8 +33,6 @@
 import org.foray.orthography.inflection.FinalSegmentModifiedWord;
 import org.foray.orthography.inflection.mods.Add_2c_ed;
 
-import org.axsl.orthography.WordSegment;
-
 import java.util.regex.Pattern;
 
 /**
@@ -50,6 +48,9 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = 8394051902368166495L;
 
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -56,6 +57,7 @@
      */
     public EngLatnSuffix_2c_ed(final Word4a wrappedWord) {
         super(wrappedWord);
+        this.modifiedSegment = new Add_2c_ed(wrappedWord.getLastWordSegment());
     }
 
     @Override
@@ -65,12 +67,7 @@
 
     @Override
     public WordSegment4a getModifiedSegment() {
-        return null;
+        return this.modifiedSegment;
     }
 
-    @Override
-    protected WordSegment4a createModifiedSegment(final WordSegment unmodifiedSegment) {
-        return new Add_2c_ed(unmodifiedSegment);
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_apos_s.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_apos_s.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_apos_s.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -33,8 +33,6 @@
 import org.foray.orthography.inflection.FinalSegmentModifiedWord;
 import org.foray.orthography.inflection.mods.Add_apos_s;
 
-import org.axsl.orthography.WordSegment;
-
 import java.util.regex.Pattern;
 
 /**
@@ -48,6 +46,9 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = 3005622022724534906L;
 
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -54,6 +55,7 @@
      */
     public EngLatnSuffix_apos_s(final Word4a wrappedWord) {
         super(wrappedWord);
+        this.modifiedSegment = new Add_apos_s(wrappedWord.getLastWordSegment());
     }
 
     @Override
@@ -63,12 +65,7 @@
 
     @Override
     public WordSegment4a getModifiedSegment() {
-        return null;
+        return this.modifiedSegment;
     }
 
-    @Override
-    protected WordSegment4a createModifiedSegment(final WordSegment unmodifiedSegment) {
-        return new Add_apos_s(unmodifiedSegment);
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -33,8 +33,6 @@
 import org.foray.orthography.inflection.FinalSegmentModifiedWord;
 import org.foray.orthography.inflection.mods.Add_ed;
 
-import org.axsl.orthography.WordSegment;
-
 import java.util.regex.Pattern;
 
 /**
@@ -49,6 +47,9 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = -6300334484689323279L;
 
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -55,6 +56,7 @@
      */
     public EngLatnSuffix_ed(final Word4a wrappedWord) {
         super(wrappedWord);
+        this.modifiedSegment = new Add_ed(wrappedWord.getLastWordSegment());
     }
 
     @Override
@@ -64,12 +66,7 @@
 
     @Override
     public WordSegment4a getModifiedSegment() {
-        return null;
+        return this.modifiedSegment;
     }
 
-    @Override
-    protected WordSegment4a createModifiedSegment(final WordSegment unmodifiedSegment) {
-        return new Add_ed(unmodifiedSegment);
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed2.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed2.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ed2.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -33,8 +33,6 @@
 import org.foray.orthography.inflection.FinalSegmentModifiedWord;
 import org.foray.orthography.inflection.mods.Add_d;
 
-import org.axsl.orthography.WordSegment;
-
 import java.util.regex.Pattern;
 
 /**
@@ -49,6 +47,9 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = -8582365946868677749L;
 
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -55,6 +56,7 @@
      */
     public EngLatnSuffix_ed2(final Word4a wrappedWord) {
         super(wrappedWord);
+        this.modifiedSegment = new Add_d(wrappedWord.getLastWordSegment());
     }
 
     @Override
@@ -64,12 +66,7 @@
 
     @Override
     public WordSegment4a getModifiedSegment() {
-        return null;
+        return this.modifiedSegment;
     }
 
-    @Override
-    protected WordSegment4a createModifiedSegment(final WordSegment unmodifiedSegment) {
-        return new Add_d(unmodifiedSegment);
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er2.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er2.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_er2.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -48,6 +48,9 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = 844895335860248111L;
 
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -54,6 +57,7 @@
      */
     public EngLatnSuffix_er2(final Word4a wrappedWord) {
         super(wrappedWord);
+        this.modifiedSegment = new Delete_e(wrappedWord.getLastWordSegment());
     }
 
     @Override
@@ -63,23 +67,7 @@
 
     @Override
     public WordSegment4a getModifiedSegment() {
-        return null;
+        return this.modifiedSegment;
     }
 
-    @Override
-    public WordSegment4a wordSegmentAt(final int segmentIndex) {
-        if (segmentIndex >= qtyWordSegments()) {
-            throw new IndexOutOfBoundsException(Integer.toString(segmentIndex));
-        }
-        if (segmentIndex == qtyWordSegments() - 1) {
-            return getAppendedSegment();
-        }
-        if (segmentIndex == qtyWordSegments() - 2) {
-            final WordSegment4a segment = getWrappedWord().wordSegmentAt(segmentIndex);
-            final Delete_e replacement = new Delete_e(segment);
-            return replacement;
-        }
-        return getWrappedWord().wordSegmentAt(segmentIndex);
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est2.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est2.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_est2.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -48,6 +48,9 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = 844895335860248111L;
 
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -54,6 +57,7 @@
      */
     public EngLatnSuffix_est2(final Word4a wrappedWord) {
         super(wrappedWord);
+        this.modifiedSegment = new Delete_e(wrappedWord.getLastWordSegment());
     }
 
     @Override
@@ -63,23 +67,7 @@
 
     @Override
     public WordSegment4a getModifiedSegment() {
-        return null;
+        return this.modifiedSegment;
     }
 
-    @Override
-    public WordSegment4a wordSegmentAt(final int segmentIndex) {
-        if (segmentIndex >= qtyWordSegments()) {
-            throw new IndexOutOfBoundsException(Integer.toString(segmentIndex));
-        }
-        if (segmentIndex == qtyWordSegments() - 1) {
-            return getAppendedSegment();
-        }
-        if (segmentIndex == qtyWordSegments() - 2) {
-            final WordSegment4a segment = getWrappedWord().wordSegmentAt(segmentIndex);
-            final Delete_e replacement = new Delete_e(segment);
-            return replacement;
-        }
-        return getWrappedWord().wordSegmentAt(segmentIndex);
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ies.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ies.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ies.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -33,8 +33,6 @@
 import org.foray.orthography.inflection.FinalSegmentModifiedWord;
 import org.foray.orthography.inflection.mods.Replace_y_by_ies;
 
-import org.axsl.orthography.WordSegment;
-
 import java.util.regex.Pattern;
 
 /**
@@ -52,6 +50,9 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = -7424864981681700754L;
 
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -58,6 +59,7 @@
      */
     public EngLatnSuffix_ies(final Word4a wrappedWord) {
         super(wrappedWord);
+        this.modifiedSegment = new Replace_y_by_ies(wrappedWord.getLastWordSegment());
     }
 
     @Override
@@ -67,12 +69,7 @@
 
     @Override
     public WordSegment4a getModifiedSegment() {
-        return null;
+        return this.modifiedSegment;
     }
 
-    @Override
-    protected WordSegment4a createModifiedSegment(final WordSegment unmodifiedSegment) {
-        return new Replace_y_by_ies(unmodifiedSegment);
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing2.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing2.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_ing2.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -48,6 +48,9 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = -7846984985428239100L;
 
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -54,6 +57,7 @@
      */
     public EngLatnSuffix_ing2(final Word4a wrappedWord) {
         super(wrappedWord);
+        this.modifiedSegment = new Delete_e(wrappedWord.getLastWordSegment());
     }
 
     @Override
@@ -63,23 +67,7 @@
 
     @Override
     public WordSegment4a getModifiedSegment() {
-        return null;
+        return this.modifiedSegment;
     }
 
-    @Override
-    public WordSegment4a wordSegmentAt(final int segmentIndex) {
-        if (segmentIndex >= qtyWordSegments()) {
-            throw new IndexOutOfBoundsException(Integer.toString(segmentIndex));
-        }
-        if (segmentIndex == qtyWordSegments() - 1) {
-            return getAppendedSegment();
-        }
-        if (segmentIndex == qtyWordSegments() - 2) {
-            final WordSegment4a segment = getWrappedWord().wordSegmentAt(segmentIndex);
-            final Delete_e replacement = new Delete_e(segment);
-            return replacement;
-        }
-        return getWrappedWord().wordSegmentAt(segmentIndex);
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_s.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_s.java	2026-07-28 11:36:01 UTC (rev 14934)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/inflection/eng/EngLatnSuffix_s.java	2026-07-28 12:37:32 UTC (rev 14935)
@@ -33,8 +33,6 @@
 import org.foray.orthography.inflection.FinalSegmentModifiedWord;
 import org.foray.orthography.inflection.mods.Add_s;
 
-import org.axsl.orthography.WordSegment;
-
 import java.util.regex.Pattern;
 
 /**
@@ -48,6 +46,9 @@
     /** Constant needed for serialization. */
     private static final long serialVersionUID = -7424864981681700754L;
 
+    /** The word segment that replaces the last word segment in the wrapped word. */
+    private WordSegment4a modifiedSegment;
+
     /**
      * Constructor.
      * @param wrappedWord The wrapped word.
@@ -54,6 +55,7 @@
      */
     public EngLatnSuffix_s(final Word4a wrappedWord) {
         super(wrappedWord);
+        this.modifiedSegment = new Add_s(wrappedWord.getLastWordSegment());
     }
 
     @Override
@@ -63,12 +65,7 @@
 
     @Override
     public WordSegment4a getModifiedSegment() {
-        return null;
+        return this.modifiedSegment;
     }
 
-    @Override
-    protected WordSegment4a createModifiedSegment(final WordSegment unmodifiedSegment) {
-        return new Add_s(unmodifiedSegment);
-    }
-
 }

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.

10 messages has been excluded from this view by a project administrator.

Flat | Threaded

1 2 3 .. 323 > >> (Page 1 of 323)