foray-commit — FOray repository commit log messages

[FOray-commit] SF.net SVN: foray:[12076] trunk/foray/foray-orthography/src

[<vic...@us...>]

Revision: 12076
          http://sourceforge.net/p/foray/code/12076
Author:   victormote
Date:     2021-11-17 14:02:41 +0000 (Wed, 17 Nov 2021)
Log Message:
-----------
Get all tokenizer tests to pass. Much reorganization of code to follow.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.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	2021-11-17 12:35:51 UTC (rev 12075)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java	2021-11-17 14:02:41 UTC (rev 12076)
@@ -47,7 +47,7 @@
         WORD_CHAR,
 
         /** Character is non-word break content. */
-        NON_WORD_BREAK_CHAR,
+        BREAK_CHAR,
 
         /** Character is a leading attached punctuation item such as (in English) an opening quotation mark or opening
          * parenthesis. */
@@ -61,7 +61,7 @@
         END,
 
         /** Character is none of the above. */
-        OTHER;
+        OTHER,
 
     }
 
@@ -118,7 +118,7 @@
      */
     public CharType computeCharType(final int c) {
         if (isBreakChar(c)) {
-            return CharType.NON_WORD_BREAK_CHAR;
+            return CharType.BREAK_CHAR;
         }
         if (isWordChar(c)) {
             return CharType.WORD_CHAR;

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	2021-11-17 12:35:51 UTC (rev 12075)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java	2021-11-17 14:02:41 UTC (rev 12076)
@@ -50,7 +50,7 @@
      * @param sequence The sequence whose breaks are needed.
      * @return The sequence of breaks, indexes into {@code sequence}.
      */
-    IntSequence findRawBreaks(final CharSequence sequence) {
+    protected IntSequence findRawBreaks(final CharSequence sequence) {
         final IntArrayBuilder result = new IntArrayBuilder(sequence.length());
         /* TODO: BreakIterators are reusable, not thread-safe, and expensive to create. Reuse this after figuring out
          * how instances of this class are used/reused. */
@@ -72,7 +72,7 @@
      * @return An array with a one-to-one correspondence with {@code rawBreaks}, containing the type of character at
      * that break.
      */
-    CharType[] findBreakTypes(final CharSequence sequence, final IntSequence rawBreaks) {
+    protected CharType[] findBreakTypes(final CharSequence sequence, final IntSequence rawBreaks) {
         final CharType[] breakTypes = new CharType[rawBreaks.length()];
         for (int breakIndex = 0; breakIndex < rawBreaks.length(); breakIndex ++) {
             if (breakIndex >= rawBreaks.length() - 1) {
@@ -86,164 +86,119 @@
         return breakTypes;
     }
 
-    @Override
-    public List<CharSequence> tokenize(final CharSequence sequence) {
-        if (sequence == null
-                || sequence.length() < 1) {
-            return Collections.emptyList();
+    /**
+     * Combine and eliminate the elements in the charTypes array.
+     * The touchstone here is the known word breaks which are always interword content.
+     * Anything between them must be either attached to the word break to become a part of the interword content, or
+     * must get coalesced into a "word" whether it is recognized as word content or not. If done properly, every element
+     * in the array, when finished, should be either {@link CharType#WORD_CHAR} or {@link CharType#BREAK_CHAR}.
+     * Anything not in those two categories will be treated in the final tokenization as {@link CharType#WORD_CHAR}.
+     * @param breakTypes The array of charTypes.
+     */
+    protected void filterBreakTypes(final CharType[] breakTypes) {
+        /* Convert attached trailing punctuation immediately after word content to interword. */
+        for (int breakIndex = 1; breakIndex < breakTypes.length; breakIndex ++) {
+            final CharType currentBreakType = breakTypes[breakIndex];
+            if (currentBreakType == CharType.ATTACHED_TRAILING_PUNCTUATION) {
+                final CharType previousBreakType = breakTypes[breakIndex - 1];
+                if (previousBreakType != CharType.BREAK_CHAR) {
+                    breakTypes[breakIndex] = CharType.BREAK_CHAR;
+                }
+            }
         }
+        /* Convert attached leading punctuation immediately before word content to interword. */
+        for (int breakIndex = 1; breakIndex < breakTypes.length; breakIndex ++) {
+            final CharType currentBreakType = breakTypes[breakIndex];
+            if (currentBreakType == CharType.ATTACHED_LEADING_PUNCTUATION) {
+                final CharType nextBreakType = breakTypes[breakIndex + 1];
+                if (nextBreakType != CharType.BREAK_CHAR) {
+                    breakTypes[breakIndex] = CharType.BREAK_CHAR;
+                }
+            }
+        }
+    }
 
-        /* First pass is to find all of the breaks that the BreakIterator can find. */
-        final IntSequence rawBreaks = findRawBreaks(sequence);
 
-
-        /* The BreakIterator is helpful, but for our purposes does not dig deeply enough.
-         * Our purpose is to find where words start and end and to treat all other content as non-word or interword
-         * content.
-         * So our second pass is to find out the type of each character that is at a break. */
-        final CharType[] breakTypes = findBreakTypes(sequence, rawBreaks);
-
-        /* The third pass detects which of the breaks we care about based on their type and context. */
+    protected List<CharSequence> createTokens(final CharSequence sequence, final IntSequence rawBreaks,
+            final CharType[] breakTypes) {
         final List<CharSequence> tokens = new ArrayList<CharSequence>();
+        boolean inWord = false;
+        int startNextToken = 0;
 
-        /* Handle the case of only one break. It is either a single-token word, or non-word content that must be
-         * preceded by an empty word. We will treat anything that is not a break char as part of a word. */
-        if (breakTypes.length == 1) {
-            if (breakTypes[0] == CharType.NON_WORD_BREAK_CHAR) {
-                tokens.add(StringUtils.EMPTY_STRING);
-            }
-            tokens.add(sequence);
-            return tokens;
-        }
-
-        /* There are at least two tokens. */
-
-        /* Index 0 is special. */
-        switch (breakTypes[0]) {
-        case NON_WORD_BREAK_CHAR: {
+        /* First token. */
+        switch(breakTypes[0]) {
+        case BREAK_CHAR: {
+            /* Sequence starts with a break. Add the empty dummy word that signals that fact. */
             tokens.add(StringUtils.EMPTY_STRING);
+            inWord = false;
             break;
         }
-        case WORD_CHAR: {
-            break;
+        default: {
+            /* Sequence starts with a word. */
+            inWord = true;
         }
-        case ATTACHED_LEADING_PUNCTUATION:
-        case ATTACHED_TRAILING_PUNCTUATION:
-        case OTHER: {
-            if (breakTypes[1] == CharType.NON_WORD_BREAK_CHAR) {
-                /* Treat this as a word. */
-            } else {
-                /* The next token starts a word. Threat this is non-word. */
-                tokens.add(StringUtils.EMPTY_STRING);
-            }
-            break;
         }
-        case END:
-            /* This shouldn't happen. */
-            break;
-        }
 
 
-        /* Now iterate the remaining breaks. */
-        int startNextToken = 0;
+        /* Iterate all remaining tokens. */
         for (int breakIndex = 1; breakIndex < breakTypes.length; breakIndex ++) {
+            final CharType currentBreakType = breakTypes[breakIndex];
             final int sequenceIndex = rawBreaks.intAt(breakIndex);
-            final CharType currentBreakType = breakTypes[breakIndex];
-            final CharType previousBreakType = breakTypes[breakIndex - 1];
-            final CharType nextBreakType = currentBreakType == CharType.END ? null : breakTypes[breakIndex + 1];
 
-            currentBreakType: {
-                switch (currentBreakType) {
-                case END: {
-                    tokens.add(sequence.subSequence(startNextToken, sequence.length()));
-                    break currentBreakType;
+            switch (currentBreakType) {
+            case END: {
+                tokens.add(sequence.subSequence(startNextToken, sequence.length()));
+                break;
+            }
+            case BREAK_CHAR: {
+                if (inWord) {
+                    /* Write the word and roll forward. */
+                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                    startNextToken = sequenceIndex;
+                    inWord = false;
+                } else {
+                    /* There is no state change. Nothing to do. */
                 }
-                case NON_WORD_BREAK_CHAR: {
-                    previousBreakType: {
-                        switch (previousBreakType) {
-                        case WORD_CHAR: {
-                            tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
-                            startNextToken = sequenceIndex;
-                            break previousBreakType;
-                        }
-                        case OTHER: {
-//                            nextBreakType: {
-//
-//                            }
-//                            tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
-//                            startNextToken = sequenceIndex;
-                            break previousBreakType;
-                        }
-                        default: {
-                            break previousBreakType;
-                        }
-                        }
-                    }
-                    break currentBreakType;
+                break;
+            }
+            default: {
+                /* This is considered the start of word content. */
+                if (inWord) {
+                    /* There is no state change. Nothing to do. */
+                } else {
+                    /* Write the interword content and roll forward. */
+                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                    startNextToken = sequenceIndex;
+                    inWord = true;
                 }
-                case WORD_CHAR: {
-                    if (previousBreakType == CharType.NON_WORD_BREAK_CHAR) {
-                        tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
-                        startNextToken = sequenceIndex;
-                    }
-                    break currentBreakType;
-                }
-                case ATTACHED_LEADING_PUNCTUATION:
-                case ATTACHED_TRAILING_PUNCTUATION:
-                case OTHER: {
-                    previousBreakType: {
-                        switch (previousBreakType) {
-                        case WORD_CHAR: {
-                            /* The previous item is a word and this is not. Treat it as the beginning of a non-word
-                             * sequence. */
-                            tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
-                            startNextToken = sequenceIndex;
-                            break previousBreakType;
-                        }
-                        case ATTACHED_LEADING_PUNCTUATION:
-                        case ATTACHED_TRAILING_PUNCTUATION:
-                        case OTHER: {
-                            /* There is no change. Nothing to do here. */
-                            break previousBreakType;
-                        }
-                        case NON_WORD_BREAK_CHAR: {
-                            nextBreakType:
-                                switch(nextBreakType) {
-                                case NON_WORD_BREAK_CHAR: {
-                                    /* Sitting between two word breaks. Treat this as a word. */
-                                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
-                                    startNextToken = sequenceIndex;
-                                    break nextBreakType;
-                                }
-                                case ATTACHED_LEADING_PUNCTUATION:
-                                case ATTACHED_TRAILING_PUNCTUATION:
-                                case OTHER: {
-                                    break nextBreakType;
-                                }
-                                case WORD_CHAR: {
-                                    /* After a break and before a word. This is interword content. */
-                                    break nextBreakType;
-                                }
-                                case END: {
-                                    /* This can't happen. */
-                                    break nextBreakType;
-                                }
-                                }
-                            break previousBreakType;
-                        }
-                        case END: {
-                            /* This shouldn't happen. */
-                            break previousBreakType;
-                        }
-                        }
-                        break currentBreakType;
-                    }
-                }
-                }
             }
+            }
         }
-
         return tokens;
     }
 
+    @Override
+    public List<CharSequence> tokenize(final CharSequence sequence) {
+        if (sequence == null
+                || sequence.length() < 1) {
+            return Collections.emptyList();
+        }
+
+        /* First pass is to find all of the breaks that the BreakIterator can find. */
+        final IntSequence rawBreaks = findRawBreaks(sequence);
+
+
+        /* The BreakIterator is helpful, but for our purposes does not dig deeply enough.
+         * Our purpose is to find where words start and end and to treat all other content as non-word or interword
+         * content.
+         * So our second pass is to find out the type of each character that is at a break. */
+        final CharType[] breakTypes = findBreakTypes(sequence, rawBreaks);
+
+        /* Third pass. Simplify the breakTypes array. */
+        filterBreakTypes(breakTypes);
+
+        /* The fourth step iterates over the resolved break types and turns them into tokens. */
+        return createTokens(sequence, rawBreaks, breakTypes);
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java	2021-11-17 12:35:51 UTC (rev 12075)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java	2021-11-17 14:02:41 UTC (rev 12076)
@@ -30,7 +30,6 @@
 
 import org.junit.Assert;
 import org.junit.Before;
-import org.junit.Ignore;
 import org.junit.Test;
 
 import java.util.List;
@@ -79,7 +78,7 @@
     public void testMedium() {
         final String testString = "39. It was the best of times. It was the worst of times.   <----";
         final List<CharSequence> actual = this.out.tokenize(testString);
-        Assert.assertEquals(28,      actual.size());
+        Assert.assertEquals(27,      actual.size());
         Assert.assertEquals("39",    actual.get(0));
         Assert.assertEquals(". ",    actual.get(1));
         Assert.assertEquals("It",    actual.get(2));
@@ -106,8 +105,7 @@
         Assert.assertEquals(" ",     actual.get(23));
         Assert.assertEquals("times", actual.get(24));
         Assert.assertEquals(".   ",  actual.get(25));
-        Assert.assertEquals("<",     actual.get(26));
-        Assert.assertEquals("----",  actual.get(27));
+        Assert.assertEquals("<----",  actual.get(26));
     }
 
     /**
@@ -156,7 +154,6 @@
      * However, because each one is between hard word breaks, should be tokenized as words.
      */
     @Test
-    @Ignore
     public void testWithSymbolsAsWords() {
         final String testString = "! @ # $ %";
         final List<CharSequence> actual = this.out.tokenize(testString);
@@ -178,7 +175,6 @@
      * treated as a word.
      */
     @Test
-    @Ignore
     public void testWithAttachedPunctuation() {
         final String testString = "Parentheses (as I stated earlier) are a matching pair of ( and ) characters.";
         final List<CharSequence> actual = this.out.tokenize(testString);

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

[FOray-commit] SF.net SVN: foray:[12075] trunk/foray/foray-common/src

[<vic...@us...>]

Revision: 12075
          http://sourceforge.net/p/foray/code/12075
Author:   victormote
Date:     2021-11-17 12:35:51 +0000 (Wed, 17 Nov 2021)
Log Message:
-----------
Add method for search-and-replace in an array of Objects.

Added Paths:
-----------
    trunk/foray/foray-common/src/main/java/org/foray/common/primitive/ArrayUtils.java
    trunk/foray/foray-common/src/test/java/org/foray/common/primitive/ArrayUtilsTests.java

Added: trunk/foray/foray-common/src/main/java/org/foray/common/primitive/ArrayUtils.java
===================================================================
--- trunk/foray/foray-common/src/main/java/org/foray/common/primitive/ArrayUtils.java	                        (rev 0)
+++ trunk/foray/foray-common/src/main/java/org/foray/common/primitive/ArrayUtils.java	2021-11-17 12:35:51 UTC (rev 12075)
@@ -0,0 +1,89 @@
+/*
+ * Copyright 2021 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.common.primitive;
+
+public final class ArrayUtils {
+
+    private ArrayUtils() { }
+
+    /**
+     * Index-safe element retrieval from an array.
+     * If {@code index} is out of bounds, null is returned instead of throwing an {@link IndexOutOfBoundsException}.
+     * Useful mostly for making look-behind and look-ahead searches more readable.
+     * @param <T> The type of the array.
+     * @param array The array.
+     * @param index The index into {@code array} containing the element that should be returned.
+     * @return The element at {@code index} or null if the index is out of bounds.
+     */
+    public static <T extends Object> T elementAt(final T[] array, final int index) {
+        if (index < 0
+                || index >= array.length) {
+            return null;
+        }
+        return array[index];
+    }
+
+    /**
+     * Searches the elements of an array for all occurrences of a match pattern and performs an in-place replacement of
+     * those matching elements with those from a replacement pattern.
+     * For example, an array of Integers {1, 2, 3, 4, 1, 2, 3, 4}, a match pattern of {2, 3}, and a replace pattern of
+     * {3, 2}, change the original array to {1, 3, 2, 4, 1, 3, 2, 4}.
+     * If the length of {@code match} exceeds that of {@code replace}, the extra matching elements are left unchanged.
+     * @param <T> The type of the array being searched.
+     * @param array The array being searched.
+     * @param match The match pattern.
+     * @param replace The replacement pattern.
+     * @throws IllegalArgumentException If the lengths of {@code match} and {@code replace} are different.
+     */
+    public static <T extends Object> void matchAndReplace(final T[] array, final T[] match, final T[] replace) {
+        if (replace.length > match.length) {
+            throw new IllegalArgumentException("Length of \"replace\" cannot exceed length of \"match.\"");
+        }
+        for (int arrayIndex = 0; arrayIndex < array.length; arrayIndex ++) {
+            boolean matchFound = true;
+            for (int matchIndex = 0; matchIndex < match.length; matchIndex ++) {
+                final int arrayOffset = arrayIndex + matchIndex;
+                final T arrayElement = elementAt(array, arrayOffset);
+                final T matchElement = match[matchIndex];
+                if (! ObjectUtils.safeEquals(arrayElement, matchElement)) {
+                    matchFound = false;
+                }
+            }
+            if (matchFound) {
+                for (int replaceIndex = 0; replaceIndex < replace.length; replaceIndex ++) {
+                    final int arrayOffset = arrayIndex + replaceIndex;
+                    array[arrayOffset] = replace[replaceIndex];
+                }
+            }
+
+        }
+
+    }
+
+}


Property changes on: trunk/foray/foray-common/src/main/java/org/foray/common/primitive/ArrayUtils.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Added: trunk/foray/foray-common/src/test/java/org/foray/common/primitive/ArrayUtilsTests.java
===================================================================
--- trunk/foray/foray-common/src/test/java/org/foray/common/primitive/ArrayUtilsTests.java	                        (rev 0)
+++ trunk/foray/foray-common/src/test/java/org/foray/common/primitive/ArrayUtilsTests.java	2021-11-17 12:35:51 UTC (rev 12075)
@@ -0,0 +1,66 @@
+/*
+ * Copyright 2021 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.common.primitive;
+
+import org.junit.Assert;
+import org.junit.Test;
+
+/**
+ * Tests of {@link ArrayUtils}.
+ */
+public class ArrayUtilsTests {
+
+    /**
+     * Tests of {@link ArrayUtils#elementAt(Object[], int)}.
+     */
+    @Test
+    public void elementAtTests() {
+        final Integer[] testArray = {1, 2, 3};
+        Assert.assertNull(ArrayUtils.elementAt(testArray, -1));
+        Assert.assertTrue(ArrayUtils.elementAt(testArray, 0).equals(1));
+        Assert.assertTrue(ArrayUtils.elementAt(testArray, 1).equals(2));
+        Assert.assertTrue(ArrayUtils.elementAt(testArray, 2).equals(3));
+        Assert.assertNull(ArrayUtils.elementAt(testArray, 3));
+    }
+
+    /**
+     * Tests of {@link ArrayUtils#matchAndReplace(Object[], Object[], Object[])}.
+     * Tests the example used in the javadocs.
+     */
+    @Test
+    public void matchAndReplaceTests() {
+        final Integer[] actual = {1, 2, 3, 4, 1, 2, 3, 4};
+        final Integer[] match = {2, 3};
+        final Integer[] replace = {3, 2};
+        ArrayUtils.matchAndReplace(actual, match, replace);
+        final Integer[] expected = {1, 3, 2, 4, 1, 3, 2, 4};
+        Assert.assertArrayEquals(expected, actual);
+    }
+
+}


Property changes on: trunk/foray/foray-common/src/test/java/org/foray/common/primitive/ArrayUtilsTests.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:[12074] trunk/foray/foray-orthography/src

[<vic...@us...>]

Revision: 12074
          http://sourceforge.net/p/foray/code/12074
Author:   victormote
Date:     2021-11-17 00:08:43 +0000 (Wed, 17 Nov 2021)
Log Message:
-----------
Improvements on the edges of lexers.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.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	2021-11-16 20:50:33 UTC (rev 12073)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java	2021-11-17 00:08:43 UTC (rev 12074)
@@ -28,6 +28,8 @@
 
 package org.foray.orthography;
 
+import org.foray.common.primitive.CharacterUtils;
+
 import org.axsl.orthography.optional.Lexer;
 
 /**
@@ -47,10 +49,18 @@
         /** Character is non-word break content. */
         NON_WORD_BREAK_CHAR,
 
+        /** Character is a leading attached punctuation item such as (in English) an opening quotation mark or opening
+         * parenthesis. */
+        ATTACHED_LEADING_PUNCTUATION,
+
+        /** Character is a trailing attached punctuation mark such as (in English) a comma, semicolon, or closing
+         * parenthesis. */
+        ATTACHED_TRAILING_PUNCTUATION,
+
         /** There is no character here -- this is the end of the character sequence. */
         END,
 
-        /** Character is neither a word chard nor a break char. */
+        /** Character is none of the above. */
         OTHER;
 
     }
@@ -113,6 +123,12 @@
         if (isWordChar(c)) {
             return CharType.WORD_CHAR;
         }
+        if (CharacterUtils.isAttachedLeadingPunctuation(c)) {
+            return CharType.ATTACHED_LEADING_PUNCTUATION;
+        }
+        if (CharacterUtils.isAttachedTrailingPunctuation(c)) {
+            return CharType.ATTACHED_TRAILING_PUNCTUATION;
+        }
         return CharType.OTHER;
     }
 

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	2021-11-16 20:50:33 UTC (rev 12073)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java	2021-11-17 00:08:43 UTC (rev 12074)
@@ -127,6 +127,8 @@
         case WORD_CHAR: {
             break;
         }
+        case ATTACHED_LEADING_PUNCTUATION:
+        case ATTACHED_TRAILING_PUNCTUATION:
         case OTHER: {
             if (breakTypes[1] == CharType.NON_WORD_BREAK_CHAR) {
                 /* Treat this as a word. */
@@ -148,12 +150,14 @@
             final int sequenceIndex = rawBreaks.intAt(breakIndex);
             final CharType currentBreakType = breakTypes[breakIndex];
             final CharType previousBreakType = breakTypes[breakIndex - 1];
+            final CharType nextBreakType = currentBreakType == CharType.END ? null : breakTypes[breakIndex + 1];
 
             currentBreakType: {
                 switch (currentBreakType) {
-                case END:
+                case END: {
                     tokens.add(sequence.subSequence(startNextToken, sequence.length()));
                     break currentBreakType;
+                }
                 case NON_WORD_BREAK_CHAR: {
                     previousBreakType: {
                         switch (previousBreakType) {
@@ -162,6 +166,14 @@
                             startNextToken = sequenceIndex;
                             break previousBreakType;
                         }
+                        case OTHER: {
+//                            nextBreakType: {
+//
+//                            }
+//                            tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+//                            startNextToken = sequenceIndex;
+                            break previousBreakType;
+                        }
                         default: {
                             break previousBreakType;
                         }
@@ -176,6 +188,8 @@
                     }
                     break currentBreakType;
                 }
+                case ATTACHED_LEADING_PUNCTUATION:
+                case ATTACHED_TRAILING_PUNCTUATION:
                 case OTHER: {
                     previousBreakType: {
                         switch (previousBreakType) {
@@ -186,12 +200,13 @@
                             startNextToken = sequenceIndex;
                             break previousBreakType;
                         }
+                        case ATTACHED_LEADING_PUNCTUATION:
+                        case ATTACHED_TRAILING_PUNCTUATION:
                         case OTHER: {
                             /* There is no change. Nothing to do here. */
                             break previousBreakType;
                         }
                         case NON_WORD_BREAK_CHAR: {
-                            final CharType nextBreakType = breakTypes[breakIndex + 1];
                             nextBreakType:
                                 switch(nextBreakType) {
                                 case NON_WORD_BREAK_CHAR: {
@@ -200,6 +215,8 @@
                                     startNextToken = sequenceIndex;
                                     break nextBreakType;
                                 }
+                                case ATTACHED_LEADING_PUNCTUATION:
+                                case ATTACHED_TRAILING_PUNCTUATION:
                                 case OTHER: {
                                     break nextBreakType;
                                 }

Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java	2021-11-16 20:50:33 UTC (rev 12073)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java	2021-11-17 00:08:43 UTC (rev 12074)
@@ -172,4 +172,45 @@
         Assert.assertEquals("%", actual.get(8));
     }
 
+    /**
+     * Test of {@link LexerLatin1#breakIntoWords(CharSequence)} with attached leading and trailing punctuation.
+     * That punctuation should be included in the interword text unless it is detached, in which case it should be
+     * treated as a word.
+     */
+    @Test
+    @Ignore
+    public void testWithAttachedPunctuation() {
+        final String testString = "Parentheses (as I stated earlier) are a matching pair of ( and ) characters.";
+        final List<CharSequence> actual = this.out.tokenize(testString);
+        Assert.assertEquals(28,            actual.size());
+        Assert.assertEquals("Parentheses", actual.get(0));
+        Assert.assertEquals(" (",          actual.get(1));
+        Assert.assertEquals("as",          actual.get(2));
+        Assert.assertEquals(" ",           actual.get(3));
+        Assert.assertEquals("I",           actual.get(4));
+        Assert.assertEquals(" ",           actual.get(5));
+        Assert.assertEquals("stated",      actual.get(6));
+        Assert.assertEquals(" ",           actual.get(7));
+        Assert.assertEquals("earlier",     actual.get(8));
+        Assert.assertEquals(") ",          actual.get(9));
+        Assert.assertEquals("are",         actual.get(10));
+        Assert.assertEquals(" ",           actual.get(11));
+        Assert.assertEquals("a",           actual.get(12));
+        Assert.assertEquals(" ",           actual.get(13));
+        Assert.assertEquals("matching",    actual.get(14));
+        Assert.assertEquals(" ",           actual.get(15));
+        Assert.assertEquals("pair",        actual.get(16));
+        Assert.assertEquals(" ",           actual.get(17));
+        Assert.assertEquals("of",          actual.get(18));
+        Assert.assertEquals(" ",           actual.get(19));
+        Assert.assertEquals("(",           actual.get(20));
+        Assert.assertEquals(" ",           actual.get(21));
+        Assert.assertEquals("and",         actual.get(22));
+        Assert.assertEquals(" ",           actual.get(23));
+        Assert.assertEquals(")",           actual.get(24));
+        Assert.assertEquals(" ",           actual.get(25));
+        Assert.assertEquals("characters",  actual.get(26));
+        Assert.assertEquals(".",           actual.get(27));
+    }
+
 }

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

[FOray-commit] SF.net SVN: foray:[12073] trunk/foray/foray-orthography/src

[<vic...@us...>]

Revision: 12073
          http://sourceforge.net/p/foray/code/12073
Author:   victormote
Date:     2021-11-16 20:50:33 +0000 (Tue, 16 Nov 2021)
Log Message:
-----------
Progress on word-breaking rework.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java

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	2021-11-16 19:29:31 UTC (rev 12072)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java	2021-11-16 20:50:33 UTC (rev 12073)
@@ -146,44 +146,84 @@
         int startNextToken = 0;
         for (int breakIndex = 1; breakIndex < breakTypes.length; breakIndex ++) {
             final int sequenceIndex = rawBreaks.intAt(breakIndex);
+            final CharType currentBreakType = breakTypes[breakIndex];
             final CharType previousBreakType = breakTypes[breakIndex - 1];
 
-            switch (breakTypes[breakIndex]) {
-            case END:
-                tokens.add(sequence.subSequence(startNextToken, sequence.length()));
-                break;
-            case NON_WORD_BREAK_CHAR: {
-                if (previousBreakType == CharType.WORD_CHAR) {
-                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
-                    startNextToken = sequenceIndex;
+            currentBreakType: {
+                switch (currentBreakType) {
+                case END:
+                    tokens.add(sequence.subSequence(startNextToken, sequence.length()));
+                    break currentBreakType;
+                case NON_WORD_BREAK_CHAR: {
+                    previousBreakType: {
+                        switch (previousBreakType) {
+                        case WORD_CHAR: {
+                            tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                            startNextToken = sequenceIndex;
+                            break previousBreakType;
+                        }
+                        default: {
+                            break previousBreakType;
+                        }
+                        }
+                    }
+                    break currentBreakType;
                 }
-                break;
-            }
-            case WORD_CHAR: {
-                if (previousBreakType == CharType.NON_WORD_BREAK_CHAR) {
-                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
-                    startNextToken = sequenceIndex;
+                case WORD_CHAR: {
+                    if (previousBreakType == CharType.NON_WORD_BREAK_CHAR) {
+                        tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                        startNextToken = sequenceIndex;
+                    }
+                    break currentBreakType;
                 }
-                break;
-            }
-            case OTHER: {
-                final CharType nextBreakType = breakTypes[breakIndex + 1];
-                if (previousBreakType == CharType.WORD_CHAR) {
-                    /* The previous item is a word and this is not. Treat it as the beginning of a non-word sequence. */
-                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
-                    startNextToken = sequenceIndex;
-                    break;
+                case OTHER: {
+                    previousBreakType: {
+                        switch (previousBreakType) {
+                        case WORD_CHAR: {
+                            /* The previous item is a word and this is not. Treat it as the beginning of a non-word
+                             * sequence. */
+                            tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                            startNextToken = sequenceIndex;
+                            break previousBreakType;
+                        }
+                        case OTHER: {
+                            /* There is no change. Nothing to do here. */
+                            break previousBreakType;
+                        }
+                        case NON_WORD_BREAK_CHAR: {
+                            final CharType nextBreakType = breakTypes[breakIndex + 1];
+                            nextBreakType:
+                                switch(nextBreakType) {
+                                case NON_WORD_BREAK_CHAR: {
+                                    /* Sitting between two word breaks. Treat this as a word. */
+                                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                                    startNextToken = sequenceIndex;
+                                    break nextBreakType;
+                                }
+                                case OTHER: {
+                                    break nextBreakType;
+                                }
+                                case WORD_CHAR: {
+                                    /* After a break and before a word. This is interword content. */
+                                    break nextBreakType;
+                                }
+                                case END: {
+                                    /* This can't happen. */
+                                    break nextBreakType;
+                                }
+                                }
+                            break previousBreakType;
+                        }
+                        case END: {
+                            /* This shouldn't happen. */
+                            break previousBreakType;
+                        }
+                        }
+                        break currentBreakType;
+                    }
                 }
-                if (nextBreakType == CharType.NON_WORD_BREAK_CHAR) {
-                    /* Treat this as a word. */
-                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
-                    startNextToken = sequenceIndex;
-                } else {
-                    /* The next token starts a word. Treat this is non-word. */
                 }
-                break;
             }
-            }
         }
 
         return tokens;

Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java	2021-11-16 19:29:31 UTC (rev 12072)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java	2021-11-16 20:50:33 UTC (rev 12073)
@@ -76,11 +76,10 @@
      * A more complicated test of {@link LexerLatin1#breakIntoWords(CharSequence)}.
      */
     @Test
-    @Ignore
     public void testMedium() {
         final String testString = "39. It was the best of times. It was the worst of times.   <----";
         final List<CharSequence> actual = this.out.tokenize(testString);
-        Assert.assertEquals(27,      actual.size());
+        Assert.assertEquals(28,      actual.size());
         Assert.assertEquals("39",    actual.get(0));
         Assert.assertEquals(". ",    actual.get(1));
         Assert.assertEquals("It",    actual.get(2));
@@ -107,7 +106,8 @@
         Assert.assertEquals(" ",     actual.get(23));
         Assert.assertEquals("times", actual.get(24));
         Assert.assertEquals(".   ",  actual.get(25));
-        Assert.assertEquals("<----", actual.get(26));
+        Assert.assertEquals("<",     actual.get(26));
+        Assert.assertEquals("----",  actual.get(27));
     }
 
     /**

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

[FOray-commit] SF.net SVN: foray:[12072] trunk/foray

[<vic...@us...>]

Revision: 12072
          http://sourceforge.net/p/foray/code/12072
Author:   victormote
Date:     2021-11-16 19:29:31 +0000 (Tue, 16 Nov 2021)
Log Message:
-----------
Rework the lexers. This work is incomplete.

Modified Paths:
--------------
    trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CharacterUtils.java
    trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerDefault.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java
    trunk/foray/foray-orthography/src/test/resources/orthography-config.xml

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java

Modified: trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CharacterUtils.java
===================================================================
--- trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CharacterUtils.java	2021-11-16 19:28:30 UTC (rev 12071)
+++ trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CharacterUtils.java	2021-11-16 19:29:31 UTC (rev 12072)
@@ -44,7 +44,7 @@
 public final class CharacterUtils {
 
     /** The maximum printable ASCII character, a tilde ~, 0x7E, 126. */
-    public static final char MAX_PRINTABLE_ASCII_CHAR = '\u007E';
+    public static final char MAX_PRINTABLE_ASCII_CHAR = Basic_Latin_Block.TILDE;
 
     /** The punctuation characters which, when they immediately precede a word, should not be separated from that word
      * during line-breaking. TODO: This list is not comprehensive and should be improved. */

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	2021-11-16 19:28:30 UTC (rev 12071)
+++ trunk/foray/foray-orthography/src/main/data/orthographies/foray-orthography-config.xml	2021-11-16 19:29:31 UTC (rev 12072)
@@ -196,7 +196,7 @@
     <dictionary reference="dictionary-eng-moby"/>
     <hyphenation-patterns reference="hyph-patterns-eng"/>
     <derivative-factories reference="eng-999-derivatives"/>
-    <lexer class="org.foray.orthography.LexerLatin1"/>
+    <lexer class="org.foray.orthography.LexerJavaBreakIterator"/>
     <orthography language-iso-3char="eng" country-iso-3char="USA" script-iso-4char="Latn"/>
     <orthography language-iso-3char="eng" country-iso-3char="USA" script-iso-4char="Zyyy"/>
     <orthography language-iso-3char="eng" country-iso-3char="999" script-iso-4char="Latn"/>

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	2021-11-16 19:28:30 UTC (rev 12071)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Lexer4a.java	2021-11-16 19:29:31 UTC (rev 12072)
@@ -28,14 +28,8 @@
 
 package org.foray.orthography;
 
-import org.foray.common.sequence.IntArray;
-import org.foray.common.sequence.IntArrayBuilder;
-
 import org.axsl.orthography.optional.Lexer;
 
-import java.util.ArrayList;
-import java.util.List;
-
 /**
  * Implementations know how to break a character sequence into words and interword content.
  */
@@ -47,132 +41,28 @@
      */
     public enum CharType {
 
-        /** Character is always part of a word. */
-        ALWAYS_WORD_CHAR,
+        /** Character is part of a word. */
+        WORD_CHAR,
 
-        /** Character is never part of a word. */
-        NEVER_WORD_CHAR,
+        /** Character is non-word break content. */
+        NON_WORD_BREAK_CHAR,
 
-        /** Character may be part of a word, depending on context. */
-        SOMETIMES_WORD_CHAR;
+        /** There is no character here -- this is the end of the character sequence. */
+        END,
 
-    }
+        /** Character is neither a word chard nor a break char. */
+        OTHER;
 
-    /**
-     * Returns the word and interword content of a given character sequence.
-     * Even-numbered indexes in the array always contain a word, and odd-numbered indexes always contain interword
-     * content.
-     * In the case that the sequence actually starts with interword content (instead of the more normal case of starting
-     * with a word), element 0 will contain an empty string.
-     * @param sequence The character sequence to be parsed.
-     * @return The list of word and interword content parsed from {@code sequence}.
-     */
-    public List<CharSequence> tokenize(final CharSequence sequence) {
-        final IntArray wordBreaks = findWordBreaks(sequence);
-        final List<CharSequence> wordChunks = new ArrayList<CharSequence>(wordBreaks.length());
-        if (wordBreaks.length() < 1) {
-            return wordChunks;
-        }
-        for (int index = 0; index < wordBreaks.length() - 1; index ++) {
-            final int start = Math.max(0, wordBreaks.intAt(index));
-            final int end = wordBreaks.intAt(index + 1);
-            final CharSequence wordChunk = sequence.subSequence(start, end);
-            wordChunks.add(wordChunk);
-        }
-        final int finalStart = wordBreaks.lastInt();
-        final int finalEnd = sequence.length();
-        final CharSequence finalWordChunk = sequence.subSequence(finalStart, finalEnd);
-        wordChunks.add(finalWordChunk);
-        return wordChunks;
     }
 
-    /**
-     * Records the index to the beginning of each word and interword area in an integer array.
-     * Even-numbered indexes in the array always point to the beginning of a word, and odd-numbered indexes always point
-     * to interword content.
-     * In the normal case that the sequence starts with a word, element 0 will always be 0.
-     * In the case that the sequence actually starts with interword content, element 0 will always be -1,
-     * element 1 will always be 0 to mark the beginning of the leading interword content, and element 2 will always mark
-     * the beginning of the first word.
-     * The element at index n+1 will always be greater than the element at index n.
-     * All content in the sequence is accounted for.
-     * @param sequence The character sequence to be parsed.
-     * @return An array of integers that marks the beginning of each word and interword item.
-     */
-    public IntArray findWordBreaks(final CharSequence sequence) {
-        final IntArrayBuilder builder = new IntArrayBuilder();
-        boolean inWord = false;
 
-        for (int index = 0; index < sequence.length(); index++) {
-            final boolean isWordChar = isWordChar(sequence, index);
-            switch (index) {
-            case 0: {
-                if (isWordChar) {
-                    inWord = true;
-                    builder.append(index);
-                } else {
-                    builder.append(-1);
-                    builder.append(index);
-                }
-                break;
-            }
-            default: {
-                if (isWordChar) {
-                    if (! inWord) {
-                        inWord = true;
-                        builder.append(index);
-                    }
-                } else {
-                    if (inWord) {
-                        inWord = false;
-                        builder.append(index);
-                    }
-                }
-
-            }
-            }
-        }
-
-        return builder.toIntArray();
-    }
-
     /**
-     * Indicates whether a given character in a sequence should be treated as a word character or not, taking the
-     * context into consideration where necessary.
-     * @param sequence The character sequence.
-     * @param index The index to the item in {@code sequence} that is being tested.
-     * @return True if and only if the char at {@code index} should be treated as a word character.
-     */
-    public boolean isWordChar(final CharSequence sequence, final int index) {
-        if (index < 0
-                || index >= sequence.length()) {
-            return false;
-        }
-        final char c = sequence.charAt(index);
-        final CharType charType = isWordChar(c);
-        switch (charType) {
-        case ALWAYS_WORD_CHAR: {
-            return true;
-        }
-        case NEVER_WORD_CHAR: {
-            return false;
-        }
-        case SOMETIMES_WORD_CHAR: {
-            return resolveSometimesCase(sequence, index);
-        }
-        default: {
-            throw new IllegalStateException("Unexpected isWordChar value: " + charType);
-        }
-        }
-    }
-
-    /**
-     * Indicates whether a given character is a word character.
+     * Indicates whether a given Unicode code point is a word character.
      * Subclasses should override this as needed.
      * @param c The character being tested.
      * @return Indication of whether {@code c} is always a word character, never one, or sometimes one.
      */
-    public CharType isWordChar(final char c) {
+    public boolean isWordChar(final int c) {
         final int type = Character.getType(c);
 
         switch (type) {
@@ -188,81 +78,42 @@
         case Character.LETTER_NUMBER:
         case Character.OTHER_NUMBER:
         case Character.OTHER_SYMBOL: {
-            return CharType.ALWAYS_WORD_CHAR;
+            return true;
         }
-        /* Comment out the "false" values, for performance. */
-//        case Character.COMBINING_SPACING_MARK:
-//        case Character.CONNECTOR_PUNCTUATION:
-//        case Character.CONTROL:
-//        case Character.DASH_PUNCTUATION:
-//        case Character.ENCLOSING_MARK:
-//        case Character.END_PUNCTUATION:
-//        case Character.FINAL_QUOTE_PUNCTUATION:
-//        case Character.FORMAT:
-//        case Character.INITIAL_QUOTE_PUNCTUATION:
-//        case Character.LINE_SEPARATOR:
-//        case Character.MODIFIER_SYMBOL:
-//        case Character.NON_SPACING_MARK:
-//        case Character.OTHER_PUNCTUATION:
-//        case Character.PARAGRAPH_SEPARATOR:
-//        case Character.PRIVATE_USE:
-//        case Character.SPACE_SEPARATOR:
-//        case Character.START_PUNCTUATION:
-//        case Character.SURROGATE:
-//        case Character.UNASSIGNED: {
-//            return false;
-//        }
         default: {
-            break;
+            return false;
         }
         }
-
-        if (isSometimesWordChar(c)) {
-            return CharType.SOMETIMES_WORD_CHAR;
-        }
-        return CharType.NEVER_WORD_CHAR;
     }
 
     /**
-     * Indicates whether a char is a possible word character, depending on context.
-     * For example, in English, a single quote or typographic apostrophe could be the end of a quotation (not a word
-     * character), or mark a contraction or possession (is a word character).
-     * @param c The character to be tested.
-     * @return True if and only if {@code c} is sometimes (but not always) a word character.
+     * Indicates whether a given Unicode code point is a break character.
+     * @param c The codepoint to be tested.
+     * @return True if and only if {@code c} is a break character.
      */
-    public abstract boolean isSometimesWordChar(char c);
+    public boolean isBreakChar(final int c) {
+        switch(c) {
+        case ' ': return true;
+        case '\r': return true;
+        case '\n': return true;
+        case '\t': return true;
+        }
+        return false;
+    }
 
     /**
-     * Indicates whether a given character, which should have already been identified as being
-     * {@link CharType#SOMETIMES_WORD_CHAR} a word character, should be treated as a word character, taking context
-     * into consideration.
-     * @param sequence The entire sequence under examination.
-     * @param index The index of the character being tested.
-     * @return True if and only if the character at {@code index} should be considered a word character in this
-     * context.
+     * Computes the word-breaking type of a char.
+     * @param c The char being tested.
+     * @return The word-breaking type of {@code c}.
      */
-    public abstract boolean resolveSometimesCase(CharSequence sequence, int index);
-
-    /**
-     * Index-safe query into a specific char in a sequence, indicating whether it is always a word char or not.
-     * A return value of false does <em>not</em> mean that the char should not be treated as a word char in this case,
-     * only that it might not be.
-     * This is a convenience method that helps subclasses see other characters in the context of the entire sequence.
-     * For example, if the index "i" being tested in {@link #isWordChar(char)} contains a "sometimes" char, this method
-     * can be used to easily determine if the previous char is always a word char: isAlwaysWordChar(sequence, n - 1).
-     * @param sequence The sequence to be tested.
-     * @param index The index to the char in {@code sequence} that is being tested.
-     * If this index is an out-of-bounds value, this method will return false.
-     * @return True if and only if the char at {@code index} is always a word char.
-     */
-    public boolean isAlwaysWordChar(final CharSequence sequence, final int index) {
-        if (index < 0
-                || index >= sequence.length()) {
-            return false;
+    public CharType computeCharType(final int c) {
+        if (isBreakChar(c)) {
+            return CharType.NON_WORD_BREAK_CHAR;
         }
-        final char c = sequence.charAt(index);
-        final CharType charType = isWordChar(c);
-        return charType == CharType.ALWAYS_WORD_CHAR;
+        if (isWordChar(c)) {
+            return CharType.WORD_CHAR;
+        }
+        return CharType.OTHER;
     }
 
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerDefault.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerDefault.java	2021-11-16 19:28:30 UTC (rev 12071)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerDefault.java	2021-11-16 19:29:31 UTC (rev 12072)
@@ -32,16 +32,6 @@
  * A default Lexer implementation that uses only the Unicode character information to determine whether a given
  * character in a sequence is part of a word or not.
  */
-public class LexerDefault extends Lexer4a {
+public class LexerDefault extends LexerJavaBreakIterator {
 
-    @Override
-    public boolean isSometimesWordChar(final char c) {
-        return false;
-    }
-
-    @Override
-    public boolean resolveSometimesCase(final CharSequence sequence, final int index) {
-        return false;
-    }
-
 }

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.java	2021-11-16 19:29:31 UTC (rev 12072)
@@ -0,0 +1,192 @@
+/*
+ * Copyright 2021 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;
+
+import org.foray.common.primitive.StringUtils;
+import org.foray.common.sequence.IntArrayBuilder;
+
+import org.axsl.common.sequence.IntSequence;
+import org.axsl.orthography.optional.Lexer;
+
+import java.text.BreakIterator;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+import java.util.Locale;
+
+/**
+ * {@link Lexer} implementation that uses the Java {@link BreakIterator}.
+ */
+public class LexerJavaBreakIterator extends Lexer4a {
+
+    /**
+     * Uses the Java BreakIterator to find the breaks that it detects.
+     * @param sequence The sequence whose breaks are needed.
+     * @return The sequence of breaks, indexes into {@code sequence}.
+     */
+    IntSequence findRawBreaks(final CharSequence sequence) {
+        final IntArrayBuilder result = new IntArrayBuilder(sequence.length());
+        /* TODO: BreakIterators are reusable, not thread-safe, and expensive to create. Reuse this after figuring out
+         * how instances of this class are used/reused. */
+        final BreakIterator wordIterator = BreakIterator.getWordInstance(Locale.US);
+        wordIterator.setText(sequence.toString());
+        int boundary = wordIterator.first();
+
+        while (boundary != BreakIterator.DONE) {
+            result.append(boundary);
+            boundary = wordIterator.next();
+        }
+        return result;
+    }
+
+    /**
+     * Determines the type of character that triggered each raw break.
+     * @param sequence The characters being tokenized.
+     * @param rawBreaks The raw breaks.
+     * @return An array with a one-to-one correspondence with {@code rawBreaks}, containing the type of character at
+     * that break.
+     */
+    CharType[] findBreakTypes(final CharSequence sequence, final IntSequence rawBreaks) {
+        final CharType[] breakTypes = new CharType[rawBreaks.length()];
+        for (int breakIndex = 0; breakIndex < rawBreaks.length(); breakIndex ++) {
+            if (breakIndex >= rawBreaks.length() - 1) {
+                breakTypes[breakIndex] = CharType.END;
+            } else {
+                final int sequenceIndex = rawBreaks.intAt(breakIndex);
+                final int testChar = sequence.charAt(sequenceIndex);
+                breakTypes[breakIndex] = computeCharType(testChar);
+            }
+        }
+        return breakTypes;
+    }
+
+    @Override
+    public List<CharSequence> tokenize(final CharSequence sequence) {
+        if (sequence == null
+                || sequence.length() < 1) {
+            return Collections.emptyList();
+        }
+
+        /* First pass is to find all of the breaks that the BreakIterator can find. */
+        final IntSequence rawBreaks = findRawBreaks(sequence);
+
+
+        /* The BreakIterator is helpful, but for our purposes does not dig deeply enough.
+         * Our purpose is to find where words start and end and to treat all other content as non-word or interword
+         * content.
+         * So our second pass is to find out the type of each character that is at a break. */
+        final CharType[] breakTypes = findBreakTypes(sequence, rawBreaks);
+
+        /* The third pass detects which of the breaks we care about based on their type and context. */
+        final List<CharSequence> tokens = new ArrayList<CharSequence>();
+
+        /* Handle the case of only one break. It is either a single-token word, or non-word content that must be
+         * preceded by an empty word. We will treat anything that is not a break char as part of a word. */
+        if (breakTypes.length == 1) {
+            if (breakTypes[0] == CharType.NON_WORD_BREAK_CHAR) {
+                tokens.add(StringUtils.EMPTY_STRING);
+            }
+            tokens.add(sequence);
+            return tokens;
+        }
+
+        /* There are at least two tokens. */
+
+        /* Index 0 is special. */
+        switch (breakTypes[0]) {
+        case NON_WORD_BREAK_CHAR: {
+            tokens.add(StringUtils.EMPTY_STRING);
+            break;
+        }
+        case WORD_CHAR: {
+            break;
+        }
+        case OTHER: {
+            if (breakTypes[1] == CharType.NON_WORD_BREAK_CHAR) {
+                /* Treat this as a word. */
+            } else {
+                /* The next token starts a word. Threat this is non-word. */
+                tokens.add(StringUtils.EMPTY_STRING);
+            }
+            break;
+        }
+        case END:
+            /* This shouldn't happen. */
+            break;
+        }
+
+
+        /* Now iterate the remaining breaks. */
+        int startNextToken = 0;
+        for (int breakIndex = 1; breakIndex < breakTypes.length; breakIndex ++) {
+            final int sequenceIndex = rawBreaks.intAt(breakIndex);
+            final CharType previousBreakType = breakTypes[breakIndex - 1];
+
+            switch (breakTypes[breakIndex]) {
+            case END:
+                tokens.add(sequence.subSequence(startNextToken, sequence.length()));
+                break;
+            case NON_WORD_BREAK_CHAR: {
+                if (previousBreakType == CharType.WORD_CHAR) {
+                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                    startNextToken = sequenceIndex;
+                }
+                break;
+            }
+            case WORD_CHAR: {
+                if (previousBreakType == CharType.NON_WORD_BREAK_CHAR) {
+                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                    startNextToken = sequenceIndex;
+                }
+                break;
+            }
+            case OTHER: {
+                final CharType nextBreakType = breakTypes[breakIndex + 1];
+                if (previousBreakType == CharType.WORD_CHAR) {
+                    /* The previous item is a word and this is not. Treat it as the beginning of a non-word sequence. */
+                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                    startNextToken = sequenceIndex;
+                    break;
+                }
+                if (nextBreakType == CharType.NON_WORD_BREAK_CHAR) {
+                    /* Treat this as a word. */
+                    tokens.add(sequence.subSequence(startNextToken, sequenceIndex));
+                    startNextToken = sequenceIndex;
+                } else {
+                    /* The next token starts a word. Treat this is non-word. */
+                }
+                break;
+            }
+            }
+        }
+
+        return tokens;
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerJavaBreakIterator.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/LexerLatin1.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java	2021-11-16 19:28:30 UTC (rev 12071)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java	2021-11-16 19:29:31 UTC (rev 12072)
@@ -28,67 +28,9 @@
 
 package org.foray.orthography;
 
-import org.axsl.unicode.block.Basic_Latin_Block;
-import org.axsl.unicode.block.General_Punctuation_Block;
-
 /**
  * A {@link Lexer4a} implementation that is intended for general use for Latin writing systems.
  */
-public class LexerLatin1 extends Lexer4a {
+public class LexerLatin1 extends LexerJavaBreakIterator {
 
-    @Override
-    public CharType isWordChar(final char c) {
-        switch (c) {
-        case '-': return CharType.ALWAYS_WORD_CHAR;
-        case '&': return CharType.ALWAYS_WORD_CHAR;
-        default: return super.isWordChar(c);
-        }
-    }
-
-    @Override
-    public boolean isSometimesWordChar(final char c) {
-        switch (c) {
-        /* Typographic apostrophe. */
-        case General_Punctuation_Block.RIGHT_SINGLE_QUOTATION_MARK:
-        case Basic_Latin_Block.APOSTROPHE: {
-            return true;
-        }
-        default: {
-            return false;
-        }
-        }
-    }
-
-    @Override
-    public boolean resolveSometimesCase(final CharSequence sequence, final int index) {
-        boolean returnValue = false;
-        final char c = sequence.charAt(index);
-//        final boolean previousIsAlwaysWordChar = isAlwaysWordChar(sequence, index - 1);
-        final boolean nextIsAlwaysWordChar = isAlwaysWordChar(sequence, index + 1);
-
-        switch (c) {
-        case General_Punctuation_Block.RIGHT_SINGLE_QUOTATION_MARK: {
-            if (nextIsAlwaysWordChar) {
-                /* Looks like a contraction (like can't or 'tis) or possessive (like Harold's). */
-                returnValue = true;
-            }
-            /* TODO: Add logic checking whether this is a closing single quotation mark. */
-            break;
-        }
-        case Basic_Latin_Block.APOSTROPHE: {
-            /* Similar to single quotation mark, but this character can also act as an opening quotation mark. */
-            if (nextIsAlwaysWordChar) {
-                /* Looks like a contraction (like can't or 'tis) or possessive (like Harold's). */
-                returnValue = true;
-            }
-            /* TODO: Add logic checking whether this is a closing single quotation mark. */
-            break;
-        }
-        default: {
-            returnValue = false;
-        }
-        }
-        return returnValue;
-    }
-
 }

Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java	2021-11-16 19:28:30 UTC (rev 12071)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/LexerLatin1Tests.java	2021-11-16 19:29:31 UTC (rev 12072)
@@ -30,6 +30,7 @@
 
 import org.junit.Assert;
 import org.junit.Before;
+import org.junit.Ignore;
 import org.junit.Test;
 
 import java.util.List;
@@ -40,7 +41,8 @@
 public class LexerLatin1Tests {
 
     /** The object under test. */
-    private LexerLatin1 out;
+    private LexerJavaBreakIterator out;
+    /* TODO: This is temporarily referencing the wrong type. */
 
     /**
      * Setup the test.
@@ -47,7 +49,7 @@
      */
     @Before
     public void setupTest() {
-        this.out = new LexerLatin1();
+        this.out = new LexerJavaBreakIterator();
     }
 
     /**
@@ -74,6 +76,7 @@
      * A more complicated test of {@link LexerLatin1#breakIntoWords(CharSequence)}.
      */
     @Test
+    @Ignore
     public void testMedium() {
         final String testString = "39. It was the best of times. It was the worst of times.   <----";
         final List<CharSequence> actual = this.out.tokenize(testString);
@@ -148,4 +151,25 @@
         Assert.assertEquals("thing",  actual.get(6));
     }
 
+    /**
+     * Test of {@link LexerLatin1#breakIntoWords(CharSequence)} with a bunch of symbols that are not really words.
+     * However, because each one is between hard word breaks, should be tokenized as words.
+     */
+    @Test
+    @Ignore
+    public void testWithSymbolsAsWords() {
+        final String testString = "! @ # $ %";
+        final List<CharSequence> actual = this.out.tokenize(testString);
+        Assert.assertEquals(9,  actual.size());
+        Assert.assertEquals("!", actual.get(0));
+        Assert.assertEquals(" ", actual.get(1));
+        Assert.assertEquals("@", actual.get(2));
+        Assert.assertEquals(" ", actual.get(3));
+        Assert.assertEquals("#", actual.get(4));
+        Assert.assertEquals(" ", actual.get(5));
+        Assert.assertEquals("$", actual.get(6));
+        Assert.assertEquals(" ", actual.get(7));
+        Assert.assertEquals("%", actual.get(8));
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/test/resources/orthography-config.xml
===================================================================
--- trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2021-11-16 19:28:30 UTC (rev 12071)
+++ trunk/foray/foray-orthography/src/test/resources/orthography-config.xml	2021-11-16 19:29:31 UTC (rev 12072)
@@ -129,7 +129,7 @@
     <dictionary reference="dictionary-eng-moby"/>
     <hyphenation-patterns reference="hyph-patterns-eng"/>
     <derivative-factories reference="derivatives-eng"/>
-    <lexer class="org.foray.orthography.LexerLatin1"/>
+    <lexer class="org.foray.orthography.LexerJavaBreakIterator"/>
     <orthography language-iso-3char="eng" country-iso-3char="USA" script-iso-4char="Latn"/>
     <orthography language-iso-3char="eng" country-iso-3char="USA" script-iso-4char="Zyyy"/>
   </configuration>

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

[FOray-commit] SF.net SVN: foray:[12071] trunk/foray/foray-app/src/test/java/org/foray/ app/fo/FoDocumentReader.java

[<vic...@us...>]

Revision: 12071
          http://sourceforge.net/p/foray/code/12071
Author:   victormote
Date:     2021-11-16 19:28:30 +0000 (Tue, 16 Nov 2021)
Log Message:
-----------
Hard-code the location of the orthography file for the tests of record.

Modified Paths:
--------------
    trunk/foray/foray-app/src/test/java/org/foray/app/fo/FoDocumentReader.java

Modified: trunk/foray/foray-app/src/test/java/org/foray/app/fo/FoDocumentReader.java
===================================================================
--- trunk/foray/foray-app/src/test/java/org/foray/app/fo/FoDocumentReader.java	2021-11-16 14:31:11 UTC (rev 12070)
+++ trunk/foray/foray-app/src/test/java/org/foray/app/fo/FoDocumentReader.java	2021-11-16 19:28:30 UTC (rev 12071)
@@ -57,7 +57,6 @@
 import java.io.IOException;
 import java.io.InputStream;
 import java.net.URL;
-import java.util.Properties;
 
 import javax.xml.parsers.ParserConfigurationException;
 
@@ -83,10 +82,7 @@
      * objects.
      */
     private FoDocumentReader() throws IOException, ForayException {
-        final Properties buildProperties = Environment.getBuildProperties();
-        final String foraySandbox = buildProperties.getProperty("foray.sandbox");
-        final String orthographyConfigPath =
-                foraySandbox + "/foray-orthography/src/test/resources/orthography-config.xml";
+        final String orthographyConfigPath = "../foray-orthography/src/test/resources/orthography-config.xml";
         final URL orthographyFile =  new URL("file", null, orthographyConfigPath);
 
         final Logger logger = LoggerFactory.getLogger(FoDocumentReader.class);

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

[FOray-commit] SF.net SVN: foray:[12070] trunk/foray

[<vic...@us...>]

Revision: 12070
          http://sourceforge.net/p/foray/code/12070
Author:   victormote
Date:     2021-11-16 14:31:11 +0000 (Tue, 16 Nov 2021)
Log Message:
-----------
Move some uses of character definitions to the Unicode code blocks.

Modified Paths:
--------------
    trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CharacterUtils.java
    trunk/foray/foray-linebreak/src/main/java/org/foray/text/line/solitary/SolitaryLineBreaker.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java

Modified: trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CharacterUtils.java
===================================================================
--- trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CharacterUtils.java	2021-11-15 13:12:15 UTC (rev 12069)
+++ trunk/foray/foray-common/src/main/java/org/foray/common/primitive/CharacterUtils.java	2021-11-16 14:31:11 UTC (rev 12070)
@@ -43,18 +43,6 @@
  */
 public final class CharacterUtils {
 
-    /** The typographical single open quotation mark: \u2018. */
-    public static final char SINGLE_OPEN_QUOTATION_MARK = '\u2018';
-
-    /** The typographical apostrophe or single close quotation mark: \u2019. */
-    public static final char SINGLE_CLOSE_QUOTATION_MARK = '\u2019';
-
-    /** The typographical double open quotation mark: \u201C. */
-    public static final char DOUBLE_OPEN_QUOTATION_MARK = '\u201C';
-
-    /** The typographical double close quotation mark: \u201D. */
-    public static final char DOUBLE_CLOSE_QUOTATION_MARK = '\u201D';
-
     /** The maximum printable ASCII character, a tilde ~, 0x7E, 126. */
     public static final char MAX_PRINTABLE_ASCII_CHAR = '\u007E';
 
@@ -61,17 +49,27 @@
     /** The punctuation characters which, when they immediately precede a word, should not be separated from that word
      * during line-breaking. TODO: This list is not comprehensive and should be improved. */
     private static final String ATTACHED_LEADING_PUNCTUATION = new String(new char[] {
-            '(', '[',
-            SINGLE_OPEN_QUOTATION_MARK,
-            DOUBLE_OPEN_QUOTATION_MARK,
+            Basic_Latin_Block.LEFT_PARENTHESIS,
+            Basic_Latin_Block.LEFT_SQUARE_BRACKET,
+            General_Punctuation_Block.LEFT_SINGLE_QUOTATION_MARK,
+            General_Punctuation_Block.LEFT_DOUBLE_QUOTATION_MARK,
             });
 
     /** The punctuation characters which, when they immediately follow a word, should not be separated from that word
      * during line-breaking. TODO: This list is not comprehensive and should be improved. */
     private static final String ATTACHED_TRAILING_PUNCTUATION = new String(new char[] {
-            '.', ',', ';', ':', '!', '?', '\'', '"', ')', ']',
-            SINGLE_CLOSE_QUOTATION_MARK,
-            DOUBLE_CLOSE_QUOTATION_MARK,
+            Basic_Latin_Block.FULL_STOP,   // A period '.'
+            Basic_Latin_Block.COMMA,
+            Basic_Latin_Block.SEMICOLON,
+            Basic_Latin_Block.COLON,
+            Basic_Latin_Block.EXCLAMATION_MARK,
+            Basic_Latin_Block.QUESTION_MARK,
+            Basic_Latin_Block.APOSTROPHE,
+            Basic_Latin_Block.QUOTATION_MARK,
+            Basic_Latin_Block.RIGHT_PARENTHESIS,
+            Basic_Latin_Block.RIGHT_SQUARE_BRACKET,
+            General_Punctuation_Block.RIGHT_SINGLE_QUOTATION_MARK,
+            General_Punctuation_Block.RIGHT_DOUBLE_QUOTATION_MARK,
             });
 
     /** The punctuation characters which, when they immediately follow a word, can be separated from that word during
@@ -78,7 +76,7 @@
      * line-breaking, but which preferably should not be separated. TODO: This list is not comprehensive and should be
      * improved. */
     private static final String DETACHABLE_PUNCTUATION = new String(new char[] {
-            0x2013, /* En-dash */
+            General_Punctuation_Block.EN_DASH,
     });
 
     /** The punctuation characters which, when they immediately follow a word, can be separated from that word during
@@ -85,7 +83,7 @@
      * line-breaking, but which preferably should not be separated. TODO: This list is not comprehensive and should be
      * improved.*/
     private static final String DETACHED_PUNCTUATION = new String(new char[] {
-            0x2014, /* Em-dash */
+            General_Punctuation_Block.EM_DASH,
     });
 
     /**

Modified: trunk/foray/foray-linebreak/src/main/java/org/foray/text/line/solitary/SolitaryLineBreaker.java
===================================================================
--- trunk/foray/foray-linebreak/src/main/java/org/foray/text/line/solitary/SolitaryLineBreaker.java	2021-11-15 13:12:15 UTC (rev 12069)
+++ trunk/foray/foray-linebreak/src/main/java/org/foray/text/line/solitary/SolitaryLineBreaker.java	2021-11-16 14:31:11 UTC (rev 12070)
@@ -28,7 +28,6 @@
 
 package org.foray.text.line.solitary;
 
-import org.foray.common.primitive.CharacterUtils;
 import org.foray.text.TextServer4a;
 import org.foray.text.line.EagerLineBreaker;
 
@@ -41,6 +40,7 @@
 import org.axsl.text.TextException;
 import org.axsl.text.line.LineBreakHandler;
 import org.axsl.text.line.LineText;
+import org.axsl.unicode.block.General_Punctuation_Block;
 
 /**
  * An "eager" line-breaking implementaton which considers only the current line
@@ -578,7 +578,7 @@
     private boolean isSometimesWordChar(final char c) {
         switch (c) {
         /* Typographic apostrophe. */
-        case CharacterUtils.SINGLE_CLOSE_QUOTATION_MARK:
+        case General_Punctuation_Block.RIGHT_SINGLE_QUOTATION_MARK:
         case '\'': {
             return true;
         }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java	2021-11-15 13:12:15 UTC (rev 12069)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java	2021-11-16 14:31:11 UTC (rev 12070)
@@ -28,7 +28,8 @@
 
 package org.foray.orthography;
 
-import org.foray.common.primitive.CharacterUtils;
+import org.axsl.unicode.block.Basic_Latin_Block;
+import org.axsl.unicode.block.General_Punctuation_Block;
 
 /**
  * A {@link Lexer4a} implementation that is intended for general use for Latin writing systems.
@@ -48,8 +49,8 @@
     public boolean isSometimesWordChar(final char c) {
         switch (c) {
         /* Typographic apostrophe. */
-        case CharacterUtils.SINGLE_CLOSE_QUOTATION_MARK:
-        case '\'': {
+        case General_Punctuation_Block.RIGHT_SINGLE_QUOTATION_MARK:
+        case Basic_Latin_Block.APOSTROPHE: {
             return true;
         }
         default: {
@@ -66,7 +67,7 @@
         final boolean nextIsAlwaysWordChar = isAlwaysWordChar(sequence, index + 1);
 
         switch (c) {
-        case CharacterUtils.SINGLE_CLOSE_QUOTATION_MARK: {
+        case General_Punctuation_Block.RIGHT_SINGLE_QUOTATION_MARK: {
             if (nextIsAlwaysWordChar) {
                 /* Looks like a contraction (like can't or 'tis) or possessive (like Harold's). */
                 returnValue = true;
@@ -74,7 +75,7 @@
             /* TODO: Add logic checking whether this is a closing single quotation mark. */
             break;
         }
-        case '\'': {
+        case Basic_Latin_Block.APOSTROPHE: {
             /* Similar to single quotation mark, but this character can also act as an opening quotation mark. */
             if (nextIsAlwaysWordChar) {
                 /* Looks like a contraction (like can't or 'tis) or possessive (like Harold'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:[12069] trunk/foray

[<vic...@us...>]

Revision: 12069
          http://sourceforge.net/p/foray/code/12069
Author:   victormote
Date:     2021-11-15 13:12:15 +0000 (Mon, 15 Nov 2021)
Log Message:
-----------
1. Conform to aXSL change: Require WritingSystem for graphics containing text. 2. Use same to remove remaining hard-coded instances of WritingSystem.

Modified Paths:
--------------
    trunk/foray/foray-graphic/src/main/java/org/foray/graphic/batik/PdfTextPainter.java
    trunk/foray/foray-graphic/src/main/java/org/foray/graphic/output/SvgPdf.java
    trunk/foray/foray-linebreak/src/main/java/org/foray/text/line/LineBreaker.java
    trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformMath.java
    trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformSvg.java

Modified: trunk/foray/foray-graphic/src/main/java/org/foray/graphic/batik/PdfTextPainter.java
===================================================================
--- trunk/foray/foray-graphic/src/main/java/org/foray/graphic/batik/PdfTextPainter.java	2021-11-15 12:39:53 UTC (rev 12068)
+++ trunk/foray/foray-graphic/src/main/java/org/foray/graphic/batik/PdfTextPainter.java	2021-11-15 13:12:15 UTC (rev 12069)
@@ -34,8 +34,8 @@
 package org.foray.graphic.batik;
 
 import org.foray.common.WellKnownConstants;
-import org.foray.common.i18n.WritingSystem4a;
 
+import org.axsl.common.i18n.WritingSystem;
 import org.axsl.font.Font;
 import org.axsl.font.FontConsumer;
 import org.axsl.font.FontException;
@@ -80,6 +80,9 @@
     /** The FontConsumer that should be used for font resolution. */
     private FontConsumer fontConsumer;
 
+    /** The writing system. */
+    private WritingSystem writingSystem;
+
     /** The font family name used by this text. */
     private String fontFamily = null;
 
@@ -89,9 +92,11 @@
     /**
      * Constructor.
      * @param consumer The FontConsumer that should be used for font resolution.
+     * @param writingSystem The writing system.
      */
-    public PdfTextPainter(final FontConsumer consumer) {
+    public PdfTextPainter(final FontConsumer consumer, final WritingSystem writingSystem) {
         this.fontConsumer = consumer;
+        this.writingSystem = writingSystem;
     }
 
     @Override
@@ -277,10 +282,10 @@
         fontToUse.registerCharsUsed(txt);
         /* TODO: If letter-spacing is used, it needs to come from the SVG. */
         final int letterSpacing = 0;
-        /* TODO: Pass the font options and orthography below instead of hard-coding them. */
+        /* TODO: Pass the font options below instead of hard-coding them. */
         final int width = fontToUse.width(txt, 0, txt.length(),
                 awtFontSize * WellKnownConstants.MILLIPOINTS_PER_POINT, letterSpacing, 0, FontOptions.DEFAULT,
-                WritingSystem4a.USA);
+                this.writingSystem);
         final float advance = WellKnownConstants.millipointsToPoints(width);
         float tx = 0;
         if (anchor != null) {

Modified: trunk/foray/foray-graphic/src/main/java/org/foray/graphic/output/SvgPdf.java
===================================================================
--- trunk/foray/foray-graphic/src/main/java/org/foray/graphic/output/SvgPdf.java	2021-11-15 12:39:53 UTC (rev 12068)
+++ trunk/foray/foray-graphic/src/main/java/org/foray/graphic/output/SvgPdf.java	2021-11-15 13:12:15 UTC (rev 12069)
@@ -34,6 +34,7 @@
 import org.foray.graphic.batik.PdfTextPainter;
 import org.foray.graphic.batik.PdfaElementBridge;
 
+import org.axsl.common.i18n.WritingSystem;
 import org.axsl.font.FontConsumer;
 import org.axsl.graphic.GraphicException;
 
@@ -69,7 +70,8 @@
     }
 
     @Override
-    public void drawVectorContent(final Graphics2D graphic2d, final FontConsumer fontConsumer) throws GraphicException {
+    public void drawVectorContent(final Graphics2D graphic2d, final FontConsumer fontConsumer,
+            final WritingSystem writingSystem) throws GraphicException {
         /* If not running in a graphical environment, log an error message
          * and skip the SVG. */
         if (! Environment.isGraphicalEnvironment()) {
@@ -87,7 +89,7 @@
         if (fontConsumer == null) {
             textPainter = new StrokingTextPainter();
         } else {
-            textPainter = new PdfTextPainter(fontConsumer);
+            textPainter = new PdfTextPainter(fontConsumer, writingSystem);
         }
         ctx.setTextPainter(textPainter);
 

Modified: trunk/foray/foray-linebreak/src/main/java/org/foray/text/line/LineBreaker.java
===================================================================
--- trunk/foray/foray-linebreak/src/main/java/org/foray/text/line/LineBreaker.java	2021-11-15 12:39:53 UTC (rev 12068)
+++ trunk/foray/foray-linebreak/src/main/java/org/foray/text/line/LineBreaker.java	2021-11-15 13:12:15 UTC (rev 12069)
@@ -28,7 +28,6 @@
 
 package org.foray.text.line;
 
-import org.foray.common.i18n.WritingSystem4a;
 import org.foray.text.TextServer4a;
 
 import org.axsl.font.FontConsumer;
@@ -332,9 +331,8 @@
     public int getWordWidth(final LineText lineText, final CharSequence word, final int offset, final int length) {
         final FontUse fontUse = lineText.inlinePrimaryFont();
         fontUse.registerCharsUsed(word);
-        /* TODO: Pass the orthography below instead of hard-coding it. */
         return fontUse.width(word, offset, length, lineText.inlineFontSize(), lineText.inlineLetterSpacingOptimum(), 0,
-                lineText.inlineFontOptions(), WritingSystem4a.USA);
+                lineText.inlineFontOptions(), lineText.inlineWritingSystem());
     }
 
     /**

Modified: trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformMath.java
===================================================================
--- trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformMath.java	2021-11-15 12:39:53 UTC (rev 12068)
+++ trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformMath.java	2021-11-15 13:12:15 UTC (rev 12069)
@@ -86,7 +86,7 @@
         final GraphicPdf graphicPdf = (GraphicPdf) graphicOutput;
 //        graphicPdf.drawVectorContent(outputStream, doc, this.fontConsumer, this.strokeText, false);
         final Graphics2D graphic2D = new PdfGraphics2D(this.writingSystem, this.fontConsumer, doc, outputStream);
-        graphicPdf.drawVectorContent(graphic2D, fontConsumer);
+        graphicPdf.drawVectorContent(graphic2D, this.fontConsumer, this.writingSystem);
         return outputStream.toByteArray();
     }
 

Modified: trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformSvg.java
===================================================================
--- trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformSvg.java	2021-11-15 12:39:53 UTC (rev 12068)
+++ trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformSvg.java	2021-11-15 13:12:15 UTC (rev 12069)
@@ -86,7 +86,7 @@
         final GraphicPdf graphicPdf = (GraphicPdf) graphicOutput;
 //        graphicPdf.drawVectorContent(outputStream, doc, this.fontConsumer, this.strokeText, false);
         final Graphics2D graphic2D = new PdfGraphics2D(this.writingSystem, this.fontConsumer, doc, outputStream);
-        graphicPdf.drawVectorContent(graphic2D, fontConsumer);
+        graphicPdf.drawVectorContent(graphic2D, this.fontConsumer, this.writingSystem);
         return outputStream.toByteArray();
     }
 

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

[FOray-commit] SF.net SVN: foray:[12068] trunk/foray

[<vic...@us...>]

Revision: 12068
          http://sourceforge.net/p/foray/code/12068
Author:   victormote
Date:     2021-11-15 12:39:53 +0000 (Mon, 15 Nov 2021)
Log Message:
-----------
Remove some instances of hard-coded WritingSystem.

Modified Paths:
--------------
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractAncestralInlineArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/ScalingValueCitationArea.java
    trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractAncestralInlineArea.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractAncestralInlineArea.java	2021-11-15 12:25:19 UTC (rev 12067)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractAncestralInlineArea.java	2021-11-15 12:39:53 UTC (rev 12068)
@@ -28,10 +28,7 @@
 
 package org.foray.area;
 
-import org.foray.common.i18n.WritingSystem4a;
-
 import org.axsl.area.AreaTreeException;
-import org.axsl.common.i18n.WritingSystem;
 import org.axsl.fo.fo.BasicLink;
 import org.axsl.fo.fo.BidiOverride;
 import org.axsl.fo.fo.CharacterSequence;
@@ -219,13 +216,4 @@
         return FontOptions.DEFAULT;
     }
 
-    /**
-     * Returns the orthography.
-     * @return The orthography.
-     */
-    public WritingSystem writingSystem() {
-        /* TODO: Get this from the FOTree. */
-        return WritingSystem4a.USA;
-    }
-
 }

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/ScalingValueCitationArea.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/ScalingValueCitationArea.java	2021-11-15 12:25:19 UTC (rev 12067)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/ScalingValueCitationArea.java	2021-11-15 12:39:53 UTC (rev 12068)
@@ -28,10 +28,7 @@
 
 package org.foray.area;
 
-import org.foray.common.i18n.WritingSystem4a;
-
 import org.axsl.area.AreaTreeException;
-import org.axsl.common.i18n.WritingSystem;
 import org.axsl.fo.Fo;
 import org.axsl.fo.fo.GraftingPoint;
 import org.axsl.fo.fo.ScalingValueCitation;
@@ -321,13 +318,4 @@
         return FontOptions.DEFAULT;
     }
 
-    /**
-     * Returns the orthography.
-     * @return The orthography.
-     */
-    public WritingSystem writingSystem() {
-        /* TODO: Get this from the FOTree. */
-        return WritingSystem4a.USA;
-    }
-
 }

Modified: trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java
===================================================================
--- trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java	2021-11-15 12:25:19 UTC (rev 12067)
+++ trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java	2021-11-15 12:39:53 UTC (rev 12068)
@@ -34,7 +34,6 @@
 package org.foray.render.pdf;
 
 import org.foray.common.WellKnownConstants;
-import org.foray.common.i18n.WritingSystem4a;
 import org.foray.render.PrintRenderer;
 
 import org.axsl.common.FormattedIntegerType;
@@ -305,7 +304,7 @@
         final Rectangle2D.Float pdfClipRectangle = convertMillipointRectangle(
                 clipRectangle);
         try {
-            final PdfXobject xObject = this.pdfDoc.createXobject(image, WritingSystem4a.USA, getFontConsumer());
+            final PdfXobject xObject = this.pdfDoc.createXobject(image, area.writingSystem(), getFontConsumer());
             getContentStream().drawXobject(xObject, pdfContentRectangle, pdfClipRectangle);
         } catch (final PdfException e) {
             throw new GalleyVisitorException(e);
@@ -321,7 +320,8 @@
                 toPoints(foreign.referenceBpd()));
         final SvgGraphic svgGraphic = area.getGraphic();
         try {
-            final PdfXobject xObject = this.pdfDoc.createXobject(svgGraphic, WritingSystem4a.USA, getFontConsumer());
+            final PdfXobject xObject = this.pdfDoc.createXobject(svgGraphic, area.getParent().writingSystem(),
+                    getFontConsumer());
             getContentStream().drawXobject(xObject, contentRectangle, null);
         } catch (final PdfException e) {
             throw new GalleyVisitorException(e);
@@ -338,7 +338,8 @@
                 toPoints(foreign.referenceBpd()));
         final MathGraphic mathGraphic = area.getGraphic();
         try {
-            final PdfXobject xObject = this.pdfDoc.createXobject(mathGraphic, WritingSystem4a.USA, getFontConsumer());
+            final PdfXobject xObject = this.pdfDoc.createXobject(mathGraphic, area.getParent().writingSystem(),
+                    getFontConsumer());
             getContentStream().drawXobject(xObject, contentRectangle, null);
         } catch (final PdfException e) {
             throw new GalleyVisitorException(e);

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

[FOray-commit] SF.net SVN: foray:[12067] trunk/foray

[<vic...@us...>]

Revision: 12067
          http://sourceforge.net/p/foray/code/12067
Author:   victormote
Date:     2021-11-15 12:25:19 +0000 (Mon, 15 Nov 2021)
Log Message:
-----------
Conform to aXSL changes: Add methods in both axsl-fo and axsl-galley to get the WritingSystem and Orthography for all nodes.

Modified Paths:
--------------
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode4a.java
    trunk/foray/foray-fotree/src/main/java/org/foray/fotree/FoObj.java

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode4a.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode4a.java	2021-11-15 00:21:54 UTC (rev 12066)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode4a.java	2021-11-15 12:25:19 UTC (rev 12067)
@@ -34,11 +34,13 @@
 import org.axsl.area.AreaNode;
 import org.axsl.area.AreaTreeException;
 import org.axsl.area.BlockContentFactory;
+import org.axsl.common.i18n.WritingSystem;
 import org.axsl.fo.Fo;
 import org.axsl.fo.fo.GraftingPoint;
 import org.axsl.fo.fo.Table;
 import org.axsl.fo.fo.prop.ColorPa;
 import org.axsl.galley.Galley;
+import org.axsl.orthography.Orthography;
 
 import org.slf4j.Logger;
 
@@ -768,4 +770,22 @@
         return this.getParent().getColor();
     }
 
+    @Override
+    public WritingSystem writingSystem() {
+        final Fo generatedBy = this.traitGeneratedBy();
+        if (generatedBy != null) {
+            return generatedBy.getWritingSystem();
+        }
+        return null;
+    }
+
+    @Override
+    public Orthography orthography() {
+        final Fo generatedBy = this.traitGeneratedBy();
+        if (generatedBy != null) {
+            return generatedBy.getOrthography();
+        }
+        return null;
+    }
+
 }

Modified: trunk/foray/foray-fotree/src/main/java/org/foray/fotree/FoObj.java
===================================================================
--- trunk/foray/foray-fotree/src/main/java/org/foray/fotree/FoObj.java	2021-11-15 00:21:54 UTC (rev 12066)
+++ trunk/foray/foray-fotree/src/main/java/org/foray/fotree/FoObj.java	2021-11-15 12:25:19 UTC (rev 12067)
@@ -120,7 +120,6 @@
 import org.axsl.common.value.WhiteSpaceTreatment;
 import org.axsl.common.value.WrapOption;
 import org.axsl.fo.Fo;
-import org.axsl.fo.FoAllProperties;
 import org.axsl.fo.FoContext;
 import org.axsl.fo.FoInlineContext;
 import org.axsl.fo.FoTreeException;
@@ -134,6 +133,7 @@
 import org.axsl.font.FontUse;
 import org.axsl.graphic.Graphic;
 import org.axsl.graphic.GraphicServer;
+import org.axsl.orthography.Orthography;
 import org.axsl.orthography.OrthographyServer;
 import org.axsl.speech.SpeechException;
 import org.axsl.speech.SpeechServer;
@@ -155,7 +155,7 @@
 /**
  * Base class for formatting objects.
  */
-public abstract class FoObj extends AbstractOrderedTreeNode implements Fo, FoAllProperties, ParaConfig {
+public abstract class FoObj extends AbstractOrderedTreeNode implements Fo, ParaConfig {
 
     /** A static empty and immutable list of children, suitable for return by
      * objects that have no children. */
@@ -3930,4 +3930,10 @@
         return WritingSystem4a.find(language, country, script);
     }
 
+    public Orthography getOrthography() {
+        final OrthographyServer server = getOrthographyServer();
+        final WritingSystem writingSystem = getWritingSystem();
+        return server.getOrthography(writingSystem);
+    }
+
 }

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

[FOray-commit] SF.net SVN: foray:[12066] trunk/foray/foray-areatree/src/main/java/org/ foray/area

[<vic...@us...>]

Revision: 12066
          http://sourceforge.net/p/foray/code/12066
Author:   victormote
Date:     2021-11-15 00:21:54 +0000 (Mon, 15 Nov 2021)
Log Message:
-----------
Conform to aXSL changes: Start process of making axsl-area extend axsl-galley.

Modified Paths:
--------------
    trunk/foray/foray-areatree/src/main/java/org/foray/area/Area4a.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode4a.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaTree4a.java

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/Area4a.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/Area4a.java	2021-11-14 23:19:35 UTC (rev 12065)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/Area4a.java	2021-11-15 00:21:54 UTC (rev 12066)
@@ -30,6 +30,7 @@
 
 import org.foray.common.WellKnownConstants;
 
+import org.axsl.area.Area;
 import org.axsl.area.AreaTreeException;
 import org.axsl.area.BlockContainerRefArea;
 import org.axsl.common.value.AbsoluteAxis;
@@ -52,8 +53,7 @@
 /**
  * Abstract superclass for all Areas in the AreaTree.
  */
-public abstract class Area4a extends AreaNode4a implements org.axsl.galley.Area,
-        org.axsl.area.Area {
+public abstract class Area4a extends AreaNode4a implements Area {
 
     /**
      * Constructor.

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode4a.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode4a.java	2021-11-14 23:19:35 UTC (rev 12065)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode4a.java	2021-11-15 00:21:54 UTC (rev 12066)
@@ -31,6 +31,7 @@
 import org.foray.common.data.AbstractOrderedTreeNode;
 import org.foray.common.data.OrderedTreeNode;
 
+import org.axsl.area.AreaNode;
 import org.axsl.area.AreaTreeException;
 import org.axsl.area.BlockContentFactory;
 import org.axsl.fo.Fo;
@@ -49,8 +50,7 @@
 /**
  * Abstract superclass for all nodes in the AreaTree.
  */
-public abstract class AreaNode4a extends AbstractOrderedTreeNode
-        implements org.axsl.galley.AreaNode, org.axsl.area.AreaNode {
+public abstract class AreaNode4a extends AbstractOrderedTreeNode implements AreaNode {
 
     /**
      * Constructor.

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaTree4a.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaTree4a.java	2021-11-14 23:19:35 UTC (rev 12065)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaTree4a.java	2021-11-15 00:21:54 UTC (rev 12066)
@@ -28,6 +28,7 @@
 
 package org.foray.area;
 
+import org.axsl.area.AreaTree;
 import org.axsl.area.AreaTreeEvent;
 import org.axsl.area.AreaTreeException;
 import org.axsl.area.AreaTreeListener;
@@ -52,8 +53,7 @@
 /**
  * The root of the AreaTree.
  */
-public final class AreaTree4a extends NonArea implements org.axsl.galley.Galley,
-        org.axsl.area.AreaTree {
+public final class AreaTree4a extends NonArea implements AreaTree {
 
     /** The initial size at which the linkage map should be created. */
     private static final short INITIAL_LINKAGE_MAP_SIZE = 200;

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

[FOray-commit] SF.net SVN: foray:[12065] trunk/foray

[<vic...@us...>]

Revision: 12065
          http://sourceforge.net/p/foray/code/12065
Author:   victormote
Date:     2021-11-14 23:19:35 +0000 (Sun, 14 Nov 2021)
Log Message:
-----------
Rename some Foray implementation classes to help distinguish them from the aXSL interface names.

Modified Paths:
--------------
    trunk/foray/foray-app/src/test/java/org/foray/app/area/AbstractAreaTreeTest.java
    trunk/foray/foray-app/src/test/java/org/foray/app/area/AreaTreeCreator.java
    trunk/foray/foray-app/src/test/java/org/foray/app/area/TestBlock.java
    trunk/foray/foray-app/src/test/java/org/foray/app/area/TestBorder.java
    trunk/foray/foray-app/src/test/java/org/foray/app/area/TestGraphicArea.java
    trunk/foray/foray-app/src/test/java/org/foray/app/area/TestInline.java
    trunk/foray/foray-app/src/test/java/org/foray/app/area/TestMetadata.java
    trunk/foray/foray-app/src/test/java/org/foray/app/area/TestVertical.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractInlineArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractListItemContent.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractTablePartContainer.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaFixed.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaFlexible.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaTreeFactory4a.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/BasicLinkArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/BeforeFloatRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/BidiOverrideArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/BlockArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/BlockContainerRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/BookmarkTreeArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/ExternalGraphicArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/FoLinkage.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/FoLinkageMarker.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/FoLinkageNormal.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/FootnoteRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/ForeignObjectArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/IndexPageCitationListArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/InlineArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/InlineContainerArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/LeaderArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/LineArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/ListBlockArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/ListItemArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/MainRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/NonArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/NormalBlockArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/NormalFlowRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/PageCollection.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/PageNumberArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/PageNumberCitationArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/PageNumberCitationLastArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/PageRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/RegionRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/RegionRaBody.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/ScalingValueCitationArea.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/SpanRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/TableBodyContainer.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/TableCellRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/TableFooterContainer.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/TableHeaderContainer.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/TableRa.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/TableRowContainer.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/TextArea.java

Added Paths:
-----------
    trunk/foray/foray-areatree/src/main/java/org/foray/area/Area4a.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode4a.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaTree4a.java

Removed Paths:
-------------
    trunk/foray/foray-areatree/src/main/java/org/foray/area/Area.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaNode.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/AreaTree.java

Modified: trunk/foray/foray-app/src/test/java/org/foray/app/area/AbstractAreaTreeTest.java
===================================================================
--- trunk/foray/foray-app/src/test/java/org/foray/app/area/AbstractAreaTreeTest.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-app/src/test/java/org/foray/app/area/AbstractAreaTreeTest.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -28,8 +28,8 @@
 
 package org.foray.app.area;
 
-import org.foray.area.AreaNode;
-import org.foray.area.AreaTree;
+import org.foray.area.AreaNode4a;
+import org.foray.area.AreaTree4a;
 import org.foray.area.MainRa;
 import org.foray.area.NormalFlowRa;
 import org.foray.area.PageCollection;
@@ -92,13 +92,13 @@
      * @param areaTree The area tree being tested.
      * @return The first normal-flow reference area in {@code areaTree}.
      */
-    protected NormalFlowRa getFirstNormalFlowArea(final AreaTree areaTree) {
+    protected NormalFlowRa getFirstNormalFlowArea(final AreaTree4a areaTree) {
         final PageCollection pageCollection = getPageCollection(areaTree, 1);
         final PageRa firstPage = getPage(pageCollection, 1);
         final RegionRaBody regionBody = firstPage.getRegionBody(
                 "xsl-region-body");
         final MainRa main = regionBody.getMainRefArea();
-        AreaNode node = main.getChildAt(0);
+        AreaNode4a node = main.getChildAt(0);
         Assert.assertTrue(node instanceof SpanRa);
         final SpanRa span = (SpanRa) node;
         node = span.getChildAt(0);
@@ -115,9 +115,9 @@
      * etc.
      * @return The requested page collection, or null if it does not exist.
      */
-    protected PageCollection getPageCollection(final AreaTree areaTree,
+    protected PageCollection getPageCollection(final AreaTree4a areaTree,
             final int collectionNum) {
-        final AreaNode node = areaTree.getChildAt(0);
+        final AreaNode4a node = areaTree.getChildAt(0);
         Assert.assertTrue(node instanceof PageCollection);
         final PageCollection pageCollection = (PageCollection) node;
         return pageCollection;
@@ -138,7 +138,7 @@
         final int index = pageNum - 1;
         Assert.assertTrue(index >= 0);
         Assert.assertTrue(index < pageCollection.getChildCount());
-        final AreaNode node = pageCollection.getChildAt(index);
+        final AreaNode4a node = pageCollection.getChildAt(index);
         Assert.assertTrue(node instanceof PageRa);
         final PageRa page = (PageRa) node;
         return page;
@@ -153,7 +153,7 @@
      * @param node The node whose descendant text should be returned.
      * @return The String concatenating all descendant text items.
      */
-    protected String getText(final AreaNode node) {
+    protected String getText(final AreaNode4a node) {
         final StringBuilder builder = new StringBuilder();
         final Iterator<OrderedTreeNode> iterator =
                 node.postOrderDescendantIterator();

Modified: trunk/foray/foray-app/src/test/java/org/foray/app/area/AreaTreeCreator.java
===================================================================
--- trunk/foray/foray-app/src/test/java/org/foray/app/area/AreaTreeCreator.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-app/src/test/java/org/foray/app/area/AreaTreeCreator.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -30,7 +30,7 @@
 
 import org.foray.app.ForaySpecific;
 import org.foray.app.fo.FoDocumentReader;
-import org.foray.area.AreaTree;
+import org.foray.area.AreaTree4a;
 import org.foray.area.AreaTreeFactory4a;
 import org.foray.area.PageCollection;
 import org.foray.core.ForayException;
@@ -100,11 +100,11 @@
      * @return The parsed FO Tree instance.
      * @throws ForayException For errors building the FO Tree.
      */
-    public AreaTree buildAreaTree(final String file) throws ForayException {
+    public AreaTree4a buildAreaTree(final String file) throws ForayException {
         final FoDocumentReader foReader = FoDocumentReader.getInstance();
         final FoTreeBuilder foTree = foReader.buildFoTree(file);
         final Root root = foTree.getRootFo();
-        final AreaTree areaTree = this.areaTreeFactory.makeAreaTree(root);
+        final AreaTree4a areaTree = this.areaTreeFactory.makeAreaTree(root);
         final PioneerLayoutStrategy layout = this.layoutFactory.makeLayout();
         final Iterator<PageSequence> iterator = root.getPageSequenceIterator();
         while (iterator.hasNext()) {

Modified: trunk/foray/foray-app/src/test/java/org/foray/app/area/TestBlock.java
===================================================================
--- trunk/foray/foray-app/src/test/java/org/foray/app/area/TestBlock.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-app/src/test/java/org/foray/app/area/TestBlock.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -29,8 +29,8 @@
 package org.foray.app.area;
 
 
-import org.foray.area.AreaNode;
-import org.foray.area.AreaTree;
+import org.foray.area.AreaNode4a;
+import org.foray.area.AreaTree4a;
 import org.foray.area.LineArea;
 import org.foray.area.NormalBlockArea;
 import org.foray.area.NormalFlowRa;
@@ -73,13 +73,13 @@
     @Ignore
     public void testBlock001() throws ForayException {
         final AreaTreeCreator creator = AreaTreeCreator.getInstance();
-        final AreaTree areaTree = creator.buildAreaTree(
+        final AreaTree4a areaTree = creator.buildAreaTree(
                 "fo/block-001.fo");
         final NormalFlowRa firstNormalFlowArea = this.getFirstNormalFlowArea(
                 areaTree);
 
         /* The outer block area. */
-        AreaNode node = firstNormalFlowArea.getChildAt(0);
+        AreaNode4a node = firstNormalFlowArea.getChildAt(0);
         Assert.assertTrue(node instanceof NormalBlockArea);
         final NormalBlockArea outerBlockArea = (NormalBlockArea) node;
         /* 1 inch left margin. */
@@ -172,7 +172,7 @@
     @Ignore
     public void testBlock002() throws ForayException {
         final AreaTreeCreator creator = AreaTreeCreator.getInstance();
-        final AreaTree areaTree = creator.buildAreaTree(
+        final AreaTree4a areaTree = creator.buildAreaTree(
                 "fo/block-002.fo");
         final PageCollection pageCollection = this.getPageCollection(areaTree,
                 1);
@@ -254,13 +254,13 @@
     public void testBlock003() throws ForayException, FontException {
         final AreaTreeCreator creator = AreaTreeCreator.getInstance();
 
-        final AreaTree areaTree = creator.buildAreaTree(
+        final AreaTree4a areaTree = creator.buildAreaTree(
                 "fo/block-003.fo");
         final NormalFlowRa firstNormalFlowArea = this.getFirstNormalFlowArea(
                 areaTree);
 
         /* Test location and dimensions of the block area. */
-        AreaNode node = firstNormalFlowArea.getChildAt(0);
+        AreaNode4a node = firstNormalFlowArea.getChildAt(0);
         Assert.assertTrue(node instanceof NormalBlockArea);
         final NormalBlockArea blockArea = (NormalBlockArea) node;
         /* 1 inch left margin. */
@@ -318,13 +318,13 @@
     @Ignore
     public void testBlock004() throws ForayException, FontException {
         final AreaTreeCreator creator = AreaTreeCreator.getInstance();
-        final AreaTree areaTree = creator.buildAreaTree(
+        final AreaTree4a areaTree = creator.buildAreaTree(
                 "fo/block-004.fo");
         final NormalFlowRa firstNormalFlowArea = this.getFirstNormalFlowArea(
                 areaTree);
 
         /* Test location and dimensions of the block area. */
-        AreaNode node = firstNormalFlowArea.getChildAt(0);
+        AreaNode4a node = firstNormalFlowArea.getChildAt(0);
         Assert.assertTrue(node instanceof NormalBlockArea);
         final NormalBlockArea blockArea = (NormalBlockArea) node;
         /* 1 inch left margin. */

Modified: trunk/foray/foray-app/src/test/java/org/foray/app/area/TestBorder.java
===================================================================
--- trunk/foray/foray-app/src/test/java/org/foray/app/area/TestBorder.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-app/src/test/java/org/foray/app/area/TestBorder.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -28,8 +28,8 @@
 
 package org.foray.app.area;
 
-import org.foray.area.AreaNode;
-import org.foray.area.AreaTree;
+import org.foray.area.AreaNode4a;
+import org.foray.area.AreaTree4a;
 import org.foray.area.NormalBlockArea;
 import org.foray.area.NormalFlowRa;
 import org.foray.core.ForayException;
@@ -51,12 +51,12 @@
     @Ignore
     public void testBorderStyle001() throws ForayException {
         final AreaTreeCreator creator = AreaTreeCreator.getInstance();
-        final AreaTree areaTree = creator.buildAreaTree(
+        final AreaTree4a areaTree = creator.buildAreaTree(
                 "fo/border-style-001.fo");
         final NormalFlowRa firstNormalFlowArea = this.getFirstNormalFlowArea(
                 areaTree);
 
-        final AreaNode node = firstNormalFlowArea.getChildAt(0);
+        final AreaNode4a node = firstNormalFlowArea.getChildAt(0);
         Assert.assertTrue(node instanceof NormalBlockArea);
         final NormalBlockArea blockArea = (NormalBlockArea) node;
         Assert.assertEquals(72000, blockArea.brOriginX());

Modified: trunk/foray/foray-app/src/test/java/org/foray/app/area/TestGraphicArea.java
===================================================================
--- trunk/foray/foray-app/src/test/java/org/foray/app/area/TestGraphicArea.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-app/src/test/java/org/foray/app/area/TestGraphicArea.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -28,8 +28,8 @@
 
 package org.foray.app.area;
 
-import org.foray.area.AreaNode;
-import org.foray.area.AreaTree;
+import org.foray.area.AreaNode4a;
+import org.foray.area.AreaTree4a;
 import org.foray.area.ExternalGraphicArea;
 import org.foray.area.LineArea;
 import org.foray.area.NormalBlockArea;
@@ -55,7 +55,7 @@
     @Ignore
     public void testGraphic002() throws ForayException {
         final AreaTreeCreator creator = AreaTreeCreator.getInstance();
-        final AreaTree areaTree = creator.buildAreaTree(
+        final AreaTree4a areaTree = creator.buildAreaTree(
                 "fo/graphic-002.fo");
         final NormalFlowRa firstNormalFlowArea = this.getFirstNormalFlowArea(
                 areaTree);
@@ -64,7 +64,7 @@
         Assert.assertEquals(2, firstNormalFlowArea.getChildCount());
 
         /* The second one contains the graphic. */
-        AreaNode node = firstNormalFlowArea.getChildAt(1);
+        AreaNode4a node = firstNormalFlowArea.getChildAt(1);
         Assert.assertTrue(node instanceof NormalBlockArea);
 
         /* It has one child, a LineArea ... */

Modified: trunk/foray/foray-app/src/test/java/org/foray/app/area/TestInline.java
===================================================================
--- trunk/foray/foray-app/src/test/java/org/foray/app/area/TestInline.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-app/src/test/java/org/foray/app/area/TestInline.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -28,8 +28,8 @@
 
 package org.foray.app.area;
 
-import org.foray.area.AreaNode;
-import org.foray.area.AreaTree;
+import org.foray.area.AreaNode4a;
+import org.foray.area.AreaTree4a;
 import org.foray.area.InlineArea;
 import org.foray.area.LineArea;
 import org.foray.area.NormalBlockArea;
@@ -56,7 +56,7 @@
     @Ignore
     public void testInline001() throws ForayException {
         final AreaTreeCreator creator = AreaTreeCreator.getInstance();
-        final AreaTree areaTree = creator.buildAreaTree(
+        final AreaTree4a areaTree = creator.buildAreaTree(
                 "fo/inline-001.fo");
         final NormalFlowRa firstNormalFlowArea = this.getFirstNormalFlowArea(
                 areaTree);
@@ -63,7 +63,7 @@
         Assert.assertEquals(1, firstNormalFlowArea.getChildCount());
 
         /* The block area. */
-        AreaNode node = firstNormalFlowArea.getChildAt(0);
+        AreaNode4a node = firstNormalFlowArea.getChildAt(0);
         Assert.assertTrue(node instanceof NormalBlockArea);
         final NormalBlockArea blockArea = (NormalBlockArea) node;
         Assert.assertEquals(1, blockArea.getChildCount());

Modified: trunk/foray/foray-app/src/test/java/org/foray/app/area/TestMetadata.java
===================================================================
--- trunk/foray/foray-app/src/test/java/org/foray/app/area/TestMetadata.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-app/src/test/java/org/foray/app/area/TestMetadata.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -28,7 +28,7 @@
 
 package org.foray.app.area;
 
-import org.foray.area.AreaTree;
+import org.foray.area.AreaTree4a;
 import org.foray.core.ForayException;
 
 import org.junit.Assert;
@@ -48,7 +48,7 @@
     @Ignore
     public void testMetadata001() throws ForayException {
         final AreaTreeCreator creator = AreaTreeCreator.getInstance();
-        final AreaTree areaTree = creator.buildAreaTree(
+        final AreaTree4a areaTree = creator.buildAreaTree(
                 "fo/metadata-001.fo");
         Assert.assertNotNull(areaTree);
         Assert.assertEquals("Test Title", areaTree.getTitle());

Modified: trunk/foray/foray-app/src/test/java/org/foray/app/area/TestVertical.java
===================================================================
--- trunk/foray/foray-app/src/test/java/org/foray/app/area/TestVertical.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-app/src/test/java/org/foray/app/area/TestVertical.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -28,8 +28,8 @@
 
 package org.foray.app.area;
 
-import org.foray.area.AreaNode;
-import org.foray.area.AreaTree;
+import org.foray.area.AreaNode4a;
+import org.foray.area.AreaTree4a;
 import org.foray.area.InlineArea;
 import org.foray.area.LineArea;
 import org.foray.area.NormalBlockArea;
@@ -56,12 +56,12 @@
     @Ignore
     public void testVertical001() throws ForayException {
         final AreaTreeCreator creator = AreaTreeCreator.getInstance();
-        final AreaTree areaTree = creator.buildAreaTree("fo/vertical-001.fo");
+        final AreaTree4a areaTree = creator.buildAreaTree("fo/vertical-001.fo");
         final NormalFlowRa firstNormalFlowArea = this.getFirstNormalFlowArea(
                 areaTree);
 
         /* The block area. */
-        AreaNode node = firstNormalFlowArea.getChildAt(0);
+        AreaNode4a node = firstNormalFlowArea.getChildAt(0);
         Assert.assertTrue(node instanceof NormalBlockArea);
         final NormalBlockArea blockArea = (NormalBlockArea) node;
         final FontUse font = blockArea.getPrimaryFont();

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractInlineArea.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractInlineArea.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractInlineArea.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -65,7 +65,7 @@
     }
 
     @Override
-    public Area getOverflowArea(final Area childRequesting)
+    public Area4a getOverflowArea(final Area4a childRequesting)
             throws AreaTreeException {
         return ancestorArea().getOverflowArea(this);
     }
@@ -95,7 +95,7 @@
     @Override
     public int baselineY() {
         int dominantBaselinePosition = 0;
-        final Area ancestorArea = this.ancestorArea();
+        final Area4a ancestorArea = this.ancestorArea();
         if (ancestorArea instanceof LineArea) {
             dominantBaselinePosition = ((LineArea) ancestorArea).alignmentPointY();
         } else if (ancestorArea instanceof AbstractAncestralInlineArea) {
@@ -177,7 +177,7 @@
      * @throws AreaTreeException If the node is not either a {@link LineArea} or
      * an {@link AbstractInlineArea}.
      */
-    protected Area validateNewParent(final AreaNode node)
+    protected Area4a validateNewParent(final AreaNode4a node)
             throws AreaTreeException {
         if (node instanceof LineArea) {
             return (LineArea) node;

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractListItemContent.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractListItemContent.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractListItemContent.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -55,7 +55,7 @@
     private ListItemArea parent;
 
     /** The children of this node. */
-    private List<Area> children = new ArrayList<Area>();
+    private List<Area4a> children = new ArrayList<Area4a>();
 
     /**
      * Private Constructor.
@@ -76,7 +76,7 @@
     }
 
     @Override
-    public void setParent(final AreaNode node) throws AreaTreeException {
+    public void setParent(final AreaNode4a node) throws AreaTreeException {
         if (node instanceof ListItemArea) {
             this.parent = (ListItemArea) node;
         } else {
@@ -87,7 +87,7 @@
     }
 
     @Override
-    public List<Area> getChildren() {
+    public List<Area4a> getChildren() {
         return this.children;
     }
 
@@ -154,7 +154,7 @@
      */
     public int getProgressionDimension() {
         int pd = 0;
-        for (Area area : this.children) {
+        for (Area4a area : this.children) {
             /* TODO: This is not right. We need the space-before, etc.
              * considered also. */
             pd += area.brBpd();

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractTablePartContainer.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractTablePartContainer.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/AbstractTablePartContainer.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -90,7 +90,7 @@
     }
 
     @Override
-    public void setParent(final AreaNode node) throws AreaTreeException {
+    public void setParent(final AreaNode4a node) throws AreaTreeException {
         if (node instanceof TableRa) {
             this.parent = (TableRa) node;
         } else {

Deleted: trunk/foray/foray-areatree/src/main/java/org/foray/area/Area.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/Area.java	2021-11-14 22:36:02 UTC (rev 12064)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/Area.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -1,1019 +0,0 @@
-/*
- * Copyright 2004 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.area;
-
-import org.foray.common.WellKnownConstants;
-
-import org.axsl.area.AreaTreeException;
-import org.axsl.area.BlockContainerRefArea;
-import org.axsl.common.value.AbsoluteAxis;
-import org.axsl.common.value.AbsoluteDirection;
-import org.axsl.common.value.LinkType;
-import org.axsl.common.value.RelativeAxis;
-import org.axsl.common.value.WhiteSpaceTreatment;
-import org.axsl.common.value.WritingMode;
-import org.axsl.fo.Fo;
-import org.axsl.fo.fo.BasicLink;
-import org.axsl.fo.fo.Block;
-import org.axsl.fo.fo.prop.IdPa;
-import org.axsl.fo.fo.prop.WritingModePa;
-import org.axsl.font.Font;
-import org.axsl.galley.BackgroundArea;
-
-import java.awt.geom.Rectangle2D;
-import java.util.List;
-
-/**
- * Abstract superclass for all Areas in the AreaTree.
- */
-public abstract class Area extends AreaNode implements org.axsl.galley.Area,
-        org.axsl.area.Area {
-
-    /**
-     * Constructor.
-     */
-    protected Area() {
-    }
-
-    /**
-     * Returns the nearest ancestor area that is a block container.
-     * @return The nearest ancestor area that is a block container.
-     */
-    public BlockContainerRefArea getNearestAncestorAreaContainer() {
-        AreaNode areaNode = this.getParent();
-        while (areaNode != null
-                && !(areaNode instanceof BlockContainerRefArea)) {
-            areaNode = areaNode.getParent();
-        }
-        return (BlockContainerRefArea) areaNode;
-    }
-
-    @Override
-    public boolean generatedByExists() {
-        return getLinkage() != null;
-    }
-
-    @Override
-    public String generatedByName() {
-        return traitGeneratedBy().getName();
-    }
-
-    /**
-     * Returns the end-indent trait.
-     * @return The end-indent trait.
-     */
-    public abstract int traitEndIndent();
-
-    /**
-     * Returns the start-indent trait.
-     * @return The start-indent trait.
-     */
-    public abstract int traitStartIndent();
-
-    /**
-     * Returns the allocation width of this area's parent.
-     * @return The allocation width of this area's parent.
-     */
-    public int parentAllocationWidth() {
-        if (! (getParent() instanceof Area)) {
-            return 0;
-        }
-        return ((Area) getParent()).narIPD();
-    }
-
-    /**
-     * Indicates whether this area is its parent's first child.
-     * @return True iff this area is its parent's first child.
-     */
-    protected boolean isFirstChildOfParent() {
-        if (getParent() == null) {
-            return true;
-        }
-        final List<? extends AreaNode> siblings = getParent().getChildren();
-        if (siblings == null
-                || siblings.size() < 1) {
-            return true;
-        }
-        if (siblings.get(0) == this) {
-            return true;
-        }
-        return false;
-    }
-
-    /**
-     * Indicates whether this area is its parent's last child.
-     * @return True iff this area is its parent's last child.
-     */
-    protected boolean isLastChildOfParent() {
-        if (getParent() == null) {
-            return true;
-        }
-        final List<? extends AreaNode> siblings = getParent().getChildren();
-        if (siblings == null) {
-            return true;
-        }
-        /*
-         * This loop is necessary because the children include DisplaySpace
-         * instances which are not considered for this test.
-         */
-        for (int i = siblings.size() - 1; i >= 0; i--) {
-            if (siblings.get(i) instanceof Area) {
-                if (siblings.get(i) == this) {
-                    return true;
-                }
-                return false;
-            }
-        }
-        return false;
-    }
-
-    /**
-     * Returns the parent Area.
-     * @return The parent if it is an Area, or null if it is not.
-     */
-    public Area getAreaParent() {
-        if (getParent() == null) {
-            return null;
-        }
-        if (getParent() instanceof Area) {
-            return (Area) getParent();
-        }
-        return null;
-    }
-
-    /**
-     * Returns the total amount of the progression-dimension that has been
-     * used by siblings.
-     * @return The total amount of the progression-dimension that has been
-     * used by siblings.
-     */
-    public abstract int pdUsedBySiblings();
-
-    @Override
-    public int brIpd() {
-        return prIpd() + traitBorderStartWidth() + traitBorderEndWidth();
-    }
-
-    @Override
-    public int brBpd() {
-        return prBpd() + traitBorderBeforeWidth() + traitBorderAfterWidth();
-    }
-
-    /**
-     * The difference, in millipoints, between the page-viewport-area's
-     * start-edge and this Area's border-rectangle start-edge.
-     * This assumes for now that the IP Direction is the same for all areas.
-     * @return The IPD offset of the border rectangle.
-     */
-    public int brOriginIPDOffset() {
-        // Start with this Area's content-rectangle offset.
-        int offset = crOriginIPDOffset();
-        offset -= traitPaddingStart();
-        return offset;
-    }
-
-    /**
-     * The difference, in millipoints, between the page-viewport-area's
-     * before-edge and this Area's border-rectangle before-edge.
-     * This assumes for now that the BP Direction is the same for all areas.
-     * @return The BPD offset of the border rectangle.
-     */
-    public int brOriginBPDOffset() {
-        // Start with this Area's content-rectangle offset.
-        int offset = crOriginBPDOffset();
-        offset -= traitPaddingBefore();
-        return offset;
-    }
-
-    @Override
-    public int brOriginX() {
-        // Start at the padding-rectangle origin.
-        int x = prOriginX();
-        final WritingMode writingMode = this.getWritingMode();
-        if (this.getBPAxis() == AbsoluteAxis.VERTICAL) {
-            // Our BP Axis is vertical
-            final boolean goingRight = writingMode.getIpDirectionOdd()
-                    == AbsoluteDirection.LEFT_TO_RIGHT;
-            if (goingRight) {
-                x -= this.traitBorderStartWidth();
-            } else {
-                x += this.traitBorderStartWidth();
-            }
-        } else {
-            // Our BP Axis is horizontal
-            final boolean goingRight = writingMode.getBpDirection()
-                    == AbsoluteDirection.LEFT_TO_RIGHT;
-            if (goingRight) {
-                x -= this.traitBorderBeforeWidth();
-            } else {
-                x += this.traitBorderBeforeWidth();
-            }
-        }
-        return x;
-    }
-
-    @Override
-    public int brOriginY() {
-        // Start at the padding-rectangle origin.
-        int y = prOriginY();
-        final WritingMode writingMode = this.getWritingMode();
-        if (this.getBPAxis() == AbsoluteAxis.VERTICAL) {
-            // Our BP Axis is vertical
-            final boolean goingDown = writingMode.getBpDirection()
-                    == AbsoluteDirection.TOP_TO_BOTTOM;
-            if (goingDown) {
-                y += this.traitBorderBeforeWidth();
-            } else {
-                y -= this.traitBorderBeforeWidth();
-            }
-        } else {
-            // Our BP Axis is horizontal
-            final boolean goingUp = writingMode.getIpDirectionOdd()
-                    == AbsoluteDirection.BOTTOM_TO_TOP;
-            if (goingUp) {
-                y -= this.traitBorderStartWidth();
-            } else {
-                y += this.traitBorderStartWidth();
-            }
-        }
-        return y;
-    }
-
-    /**
-     * Returns the IPD of the PR.
-     * @return The inline-progression-dimension of the padding-rectangle for
-     * this Area.
-     */
-    public int prIpd() {
-        return crIpd() + traitPaddingStart() + traitPaddingEnd();
-    }
-
-    /**
-     * Returns the BPD of the PR.
-     * @return The block-progression-dimension of the padding-rectangle for
-     * this Area.
-     */
-    public int prBpd() {
-        return crBpd() + traitPaddingBefore() + traitPaddingAfter();
-    }
-
-    /**
-     * The difference, in millipoints, between the page-viewport-area's
-     * start-edge and this Area's padding-rectangle start-edge.
-     * This assumes for now that the IP Direction is the same for all areas.
-     * @return The IPD offset of the padding rectangle.
-     */
-    public int prOriginIPDOffset() {
-        // Start with this Area's content-rectangle offset.
-        int offset = crOriginIPDOffset();
-        offset -= traitPaddingStart();
-        return offset;
-    }
-
-    /**
-     * The difference, in millipoints, between the page-viewport-area's
-     * before-edge and this Area's padding-rectangle before-edge.
-     * This assumes for now that the BP Direction is the same for all areas.
-     * @return The BPD offset of the padding rectangle.
-     */
-    public int prOriginBPDOffset() {
-        // Start with this Area's content-rectangle offset.
-        int offset = crOriginBPDOffset();
-        offset -= traitPaddingBefore();
-        return offset;
-    }
-
-    /**
-     * Implementation of {@link BackgroundArea#prOriginX}.
-     * @return The padding-rectangle point-of-origin x coordinate.
-     */
-    public int prOriginX() {
-        // Start at the content-rectangle origin.
-        int x = crOriginX();
-        final WritingMode writingMode = this.getWritingMode();
-        if (this.getBPAxis() == AbsoluteAxis.VERTICAL) {
-            // Our BP Axis is vertical
-            final boolean goingRight = writingMode.getIpDirectionOdd()
-                    == AbsoluteDirection.LEFT_TO_RIGHT;
-            if (goingRight) {
-                x -= this.traitPaddingStart();
-            } else {
-                x += this.traitPaddingStart();
-            }
-        } else {
-            // Our BP Axis is horizontal
-            final boolean goingRight = writingMode.getBpDirection()
-                    == AbsoluteDirection.LEFT_TO_RIGHT;
-            if (goingRight) {
-                x -= this.traitPaddingBefore();
-            } else {
-                x += this.traitPaddingBefore();
-            }
-        }
-        return x;
-    }
-
-    /**
-     * Implementation of {@link BackgroundArea#prOriginY}.
-     * @return The padding-rectangle point-of-origin y coordinate.
-     */
-    public int prOriginY() {
-        // Start at the content-rectangle origin.
-        int y = crOriginY();
-        final WritingMode writingMode = this.getWritingMode();
-        if (this.getBPAxis() == AbsoluteAxis.VERTICAL) {
-            final boolean goingDown = writingMode.getBpDirection()
-                    == AbsoluteDirection.TOP_TO_BOTTOM;
-            if (goingDown) {
-                y += this.traitPaddingBefore();
-            } else {
-                y -= this.traitPaddingBefore();
-            }
-        } else {
-            // Our BP Axis is horizontal
-            final boolean goingRight = writingMode.getBpDirection()
-                    == AbsoluteDirection.LEFT_TO_RIGHT;
-            if (goingRight) {
-                y -= this.traitPaddingBefore();
-            } else {
-                y += this.traitPaddingBefore();
-            }
-        }
-        return y;
-    }
-
-    @Override
-    public abstract int crIpd();
-
-    @Override
-    public abstract int crBpd();
-
-    /**
-     * The difference, in millipoints, between the page-viewport-area's
-     * start-edge and this Area's content-rectangle start-edge.
-     * This assumes for now that the IP Direction is the same for all areas.
-     * @return The IPD offset of the content rectangle.
-     */
-    public abstract int crOriginIPDOffset();
-
-    /**
-     * The difference, in millipoints, between the page-viewport-area's
-     * before-edge and this Area's content-rectangle before-edge.
-     * This assumes for now that the BP Direction is the same for all areas.
-     * @return The BPD offset of the content rectangle.
-     */
-    public abstract int crOriginBPDOffset();
-
-    @Override
-    public int crOriginX() {
-        return computeCrOriginX();
-    }
-
-    /**
-     * Computes the x coordinate of the point of origin of this area's content
-     * rectangle.
-     * @return The computed x coordinate of the content rectangle.
-     */
-    private int computeCrOriginX() {
-        // Start at the parent's content origin.
-        int x = crReferenceX();
-        final AbsoluteDirection ipOdd = getWritingMode().getIpDirectionOdd();
-        if (ipOdd == AbsoluteDirection.LEFT_TO_RIGHT) {
-            x += this.crOriginIPDOffset();
-            return x;
-        }
-        if (ipOdd == AbsoluteDirection.RIGHT_TO_LEFT) {
-            x -= this.crOriginIPDOffset();
-            return x;
-        }
-        final AbsoluteDirection bpd = getWritingMode().getBpDirection();
-        if (bpd == AbsoluteDirection.LEFT_TO_RIGHT) {
-            x += this.crOriginBPDOffset();
-            return x;
-        }
-        if (bpd == AbsoluteDirection.RIGHT_TO_LEFT) {
-            x -= this.crOriginBPDOffset();
-            return x;
-        }
-        return x;
-    }
-
-    /**
-     * Returns the reference X value.
-     * @return The x value (from an appropriate parent) from which this Area's
-     * content-rectangle is computed, that is, the starting point.
-     */
-    int crReferenceX() {
-        return getContainingReferenceArea().crOriginX();
-    }
-
-    @Override
-    public int crOriginY() {
-        return computeCrOriginY();
-    }
-
-    /**
-     * Computes the y coordinate of the point of origin of this area's content
-     * rectangle.
-     * @return The computed y coordinate of the content rectangle.
-     */
-    private int computeCrOriginY() {
-        // Start at the parent's content origin.
-        int y = ancestorArea().crOriginY();
-        final AbsoluteDirection bpd = getWritingMode().getBpDirection();
-        if (bpd == AbsoluteDirection.TOP_TO_BOTTOM) {
-            y -= this.crOriginBPDOffset();
-            return y;
-        }
-        if (bpd == AbsoluteDirection.BOTTOM_TO_TOP) {
-            y += this.crOriginBPDOffset();
-            return y;
-        }
-        final AbsoluteDirection ipOdd = getWritingMode().getIpDirectionOdd();
-        if (ipOdd == AbsoluteDirection.TOP_TO_BOTTOM) {
-            y -= this.crOriginIPDOffset();
-            return y;
-        }
-        if (ipOdd == AbsoluteDirection.RIGHT_TO_LEFT) {
-            y += this.crOriginIPDOffset();
-            return y;
-        }
-        return y;
-    }
-
-    /**
-     * Returns the IPD of the NAR.
-     * @return The inline-progression-dimension of the
-     * normal-allocation-rectangle for this Area.
-     */
-    public int narIPD() {
-        if (isBlockArea()) {
-            return crIpd() + traitStartIndent() + traitEndIndent();
-        }
-        return brIpd();
-    }
-
-    /**
-     * Retursn the BPD of the NAR.
-     * @return The block-progression-dimension of the
-     * normal-allocation-rectangle for this Area.
-     */
-    public int narBPD() {
-        if (isBlockArea()) {
-            return brBpd();
-        }
-        return crBpd();
-    }
-
-    /**
-     * See {@link #brOriginX()} where point-of-origin is defined.
-     * @return The absolute cartesian X value, on the page, of the point of
-     * origin of the normal-allocation-rectangle.
-     */
-    public int narOriginX() {
-        return 0;
-    }
-
-    /**
-     * See {@link #brOriginX()} where point-of-origin is defined.
-     * @return The absolute cartesian Y value, on the page, of the point of
-     * origin of the normal-allocation-rectangle.
-     */
-    public int narOriginY() {
-        return 0;
-    }
-
-    /**
-     * Returns the IPD of the LAR.
-     * @return The inline-progression-dimension of the
-     * large-allocation-rectangle for this Area.
-     */
-    public int larIPD() {
-        // LAR is the same as the BR
-        return brIpd();
-    }
-
-    /**
-     * Returns the BPD of the LAR.
-     * @return The block-progression-dimension of the large-allocation-rectangle
-     * for this Area.
-     */
-    public int larBPD() {
-        // LAR is the same as the BR
-        return brBpd();
-    }
-
-    /**
-     * See {@link #brOriginX()} where point-of-origin is defined.
-     * @return The absolute cartesian X value, on the page, of the point of
-     * origin of the large-allocation-rectangle.
-     */
-    public int larOriginX() {
-        // LAR is the same as the BR
-        return brOriginX();
-    }
-
-    /**
-     * See {@link #brOriginX()} where point-of-origin is defined.
-     * @return The absolute cartesian Y value, on the page, of the point of
-     * origin of the large-allocation-rectangle.
-     */
-    public int larOriginY() {
-        // LAR is the same as the BR
-        return brOriginY();
-    }
-
-    /**
-     * Indicates whether this Area is a block area.
-     * @return True if this Area is a block-area, false if it is an inline-area.
-     * Defaults to true. Inline areas should override this method.
-     */
-    public boolean isBlockArea() {
-        return true;
-    }
-
-    /**
-     * Returns the space-before optimum trait for this area.
-     * @return The space-before optimum trait for this area.
-     */
-    public abstract int traitSpaceBeforeOptimum();
-
-    /**
-     * Returns the space-after optimum trait for this area.
-     * @return The space-after optimum trait for this area.
-     */
-    public abstract int traitSpaceAfterOptimum();
-
-    /**
-     * Returns the space-start optimum trait for this area.
-     * @return The space-start optimum trait for this area.
-     */
-    public abstract int traitSpaceStartOptimum();
-
-    /**
-     * Returns the space-end optimum trait for this area.
-     * @return The space-end optimum trait for this area.
-     */
-    public abstract int traitSpaceEndOptimum();
-
-    /**
-     * Tells which axis (horizontal or vertical) is the block-progression axis.
-     * @return Either {@link AbsoluteAxis#HORIZONTAL} or
-     * {@link AbsoluteAxis#VERTICAL}, or null if writing-mode is invalid.
-     */
-    public AbsoluteAxis getBPAxis() {
-        return getWritingMode().getBpAxis();
-    }
-
-    /**
-     * Tells which axis (horizontal or vertical) is the inline-progression axis.
-     * @return Either {@link AbsoluteAxis#HORIZONTAL} or
-     * {@link AbsoluteAxis#VERTICAL}, or null if writing-mode is invalid.
-     */
-    public AbsoluteAxis getIPAxis() {
-        return getWritingMode().getIpAxis();
-    }
-
-    /**
-     * Returns the writing-mode for this area.
-     * @return The writing-mode for this area.
-     */
-    public WritingMode getWritingMode() {
-        final Fo generatedBy = traitGeneratedBy();
-        if (generatedBy instanceof WritingModePa) {
-            return ((WritingModePa) generatedBy).traitWritingMode(this);
-        }
-        return this.ancestorArea().getWritingMode();
-    }
-
-    /**
-     * Returns the content stacking axis for this area.
-     * @return Either {@link RelativeAxis#BLOCK_PROGRESSION} or
-     * {@link RelativeAxis#INLINE_PROGRESSION}, depending on whether the
-     * contents of this area stack in the block-progression-direction or the
-     * inline-progression-direction.
-     * The default value is that contents stack in the BPD. Classes that
-     * stack in the IPD should override this method.
-     */
-    public abstract RelativeAxis contentStackingAxis();
-
-    /**
-     * Return the absolute axis for this area.
-     * @return Either {@link AbsoluteAxis#HORIZONTAL} or
-     * {@link AbsoluteAxis#VERTICAL}, depending on the relative content stacking
-     * axis and the writing-mode.
-     * @see #contentStackingAxis()
-     */
-    public AbsoluteAxis contentStackingAxisAbsolute() {
-        return getWritingMode().getAbsoluteAxis(contentStackingAxis());
-    }
-
-    /**
-     * Return the absolute direction for this area.
-     * @return One of {@link AbsoluteDirection#TOP_TO_BOTTOM},
-     * {@link AbsoluteDirection#BOTTOM_TO_TOP},
-     * {@link AbsoluteDirection#LEFT_TO_RIGHT},
-     * or {@link AbsoluteDirection#RIGHT_TO_LEFT}, depending on the
-     * writing-mode.
-     */
-    public AbsoluteDirection contentStackingDirectionAbsolute() {
-        final RelativeAxis relative = contentStackingAxis();
-        return getWritingMode().getAbsoluteDirFromRelativeAxis(relative);
-    }
-
-    @Override
-    public abstract int pdAvailable();
-
-    /**
-     * <p>Returns the actual total value, in millipoints, of the size of this
-     * area (not counting space-before, etc.) in its progression direction.
-     * This value does <em>not</em> include space-before, etc., but
-     * <em>does</em> include borders and padding.
-     * For block areas, the progression dimension is the
-     * block-progression-dimension.
-     * For inline areas, it is the inline-progression-dimension.</p>
-     * @return The progressionDimension.
-     */
-    public abstract int getProgressionDimension();
-
-    /**
-     * Sets the progression-dimension used by this Area.
-     * @param progressionDimension The new progression-dimension value for this
-     * Area.
-     */
-    public abstract void setProgressionDimension(int progressionDimension);
-
-    /**
-     * Set the minimum progression dimension for this Area. If the current
-     * progression dimension value is less than this value, it will be
-     * increased to this minimum. Otherwise, it is ignored.
-     * @param minimumPD The minimum progression dimension to set.
-     */
-    public abstract void setMinimumProgressionDimension(int minimumPD);
-
-    /**
-     * Change the progression-dimension used by this Area.
-     * @param incrementAmount The amount by which the progression-dimension
-     * should be changed for this area.
-     * Positive values increase the progression-dimension, negative values
-     * decrease it.
-     */
-    public abstract void incrementProgressionDimension(int incrementAmount);
-
-    /**
-     * This method is used by child Areas to ask the parent Area into which
-     * Area the child Area's overflow should be placed.
-     * Overflows start when a new LineArea cannot be create for the current
-     * BlockArea.
-     * General strategy for overflow is to recursively go up the tree until
-     * getting to any Area that knows how to solve the overflow. One general
-     * case is the page-reference-area, which should know how to create a
-     * new page.
-     * @param childRequesting Child Areas ask
-     * @return The younger sister Area that should be used to handle the
-     * overflow condition.
-     * @throws AreaTreeException If the Area is unable to find or create the
-     * overflow area.
-     */
-    public abstract Area getOverflowArea(Area childRequesting)
-            throws AreaTreeException;
-
-    /**
-     * Indicates whether this area is a reference area.
-     * @return True iff this area is a reference area.
-     */
-    public boolean traitIsReferenceArea() {
-        return traitGeneratedBy().traitIsReferenceArea();
-    }
-
-    /**
-     * Returns the cumulative reference orientation for this area.
-     * @return The cumulative reference orientation for this area, in degrees.
-     */
-    public short referenceOrientationCumulative() {
-        /* TODO: This needs to be rewritten. There is a mismatch between the
-         * FoValue items returned and the "degrees" concept that needs to be
-         * resolved. */
-        return 0;
-//        final Area containingRA = this.getContainingReferenceArea();
-//        short cumulative = containingRA.traitReferenceOrientation();
-        /*
-         * The FObj method from which the following line is derived returns
-         * a 0 for FOs that do not generate reference-areas.
-         */
-//        cumulative += this.traitReferenceOrientation();
-//        if (cumulative < 0) {
-//            cumulative += WellKnownConstants.DEGREES_PER_CIRCLE;
-//        }
-//        return (short) (cumulative % WellKnownConstants.DEGREES_PER_CIRCLE);
-    }
-
-    /**
-     * Returns the whitespace-treatment trait for this area.
-     * @return The whitespace-treatment trait for this area.
-     */
-    public WhiteSpaceTreatment traitWhiteSpaceTreatment() {
-        final NormalBlockArea nearestBlockArea = this.nearestNormalBlockArea();
-        final Block block = nearestBlockArea.traitGeneratedBy();
-        return block.traitWhiteSpaceTreatment(nearestBlockArea);
-    }
-
-    /**
-     * Indicates whether this is the first child of the "generated by".
-     * @return True iff this is the first child of the "generated by".
-     */
-    public boolean traitIsFirst() {
-        return this.isFirstChildOfGeneratedBy();
-    }
-
-    /**
-     * Indicates whether this is the last child of the "generated by".
-     * @return True iff this is the last child of the "generated by".
-     */
-    public boolean traitIsLast() {
-        return this.isLastChildOfGeneratedBy();
-    }
-
-    @Override
-    public String destinationName() {
-        final String id = traitId();
-        if (id == null || id.equals("")) {
-            return null;
-        }
-        /*
-         * Only one Area should be used to create the destination, and it must
-         * be the first. For example, if an fo:block starts at the bottom of
-         * page N, and continues at the top of Page N+1, the destination should
-         * point to the bottom of N.
-         */
-        if (! (this.isFirstChildOfGeneratedBy())) {
-            return null;
-        }
-        return id;
-    }
-
-    @Override
-    public boolean isLinkRoot() {
-        if (linkType() == null) {
-            return false;
-        }
-        if (this.ancestorArea() != null
-                && this.ancestorArea().linkType() != null) {
-            return false;
-        }
-        return true;
-    }
-
-    @Override
-    public LinkType linkType() {
-        final BasicLink link = this.traitGeneratedBy().ancestorBasicLink(this);
-        if (link == null) {
-            return null;
-        }
-        return link.getLinkType();
-    }
-
-    @Override
-    public String linkDestination() {
-        final BasicLink link = this.traitGeneratedBy().ancestorBasicLink(this);
-        if (link == null) {
-            return null;
-        }
-        return link.getDestination();
-    }
-
-    /**
-     * Returns the content rectangle measured in points (1/72 of an inch).
-     * @return The content rectangle in points.
-     */
-    public Rectangle2D.Float crPoints() {
-        return new Rectangle2D.Float(
-                crOriginX() / WellKnownConstants.MILLIPOINTS_PER_POINT,
-                crOriginY() / WellKnownConstants.MILLIPOINTS_PER_POINT,
-                crIpd() / WellKnownConstants.MILLIPOINTS_PER_POINT,
-                crBpd() / WellKnownConstants.MILLIPOINTS_PER_POINT);
-    }
-
-    /**
-     * Returns the border rectangle measured in points (1/72 of an inch).
-     * @return The border rectangle in points.
-     */
-    public Rectangle2D.Float brPoints() {
-        return new Rectangle2D.Float(
-                brOriginX() / WellKnownConstants.MILLIPOINTS_PER_POINT,
-                brOriginY() / WellKnownConstants.MILLIPOINTS_PER_POINT,
-                brIpd() / WellKnownConstants.MILLIPOINTS_PER_POINT,
-                brBpd() / WellKnownConstants.MILLIPOINTS_PER_POINT);
-    }
-
-    /**
-     * Indicates whether this Area is positioned absolutely or relatively.
-     * @return True iff this Area is absolutely positioned.
-     */
-    public abstract boolean isAbsolutelyPositioned();
-
-    /**
-     * Indicates whether this Area is part of the normal flow.
-     * See XSL-FO 1.0, Section 7.5, where absolutely-positioned Areas are
-     * excluded from the normal flow, and do not affect the positioning of later
-     * siblings.
-     * @return True iff this Area is part of the normal flow and affects the
-     * positioning of later siblings.
-     */
-    public boolean isInNormalFlow() {
-        if (this.isAbsolutelyPositioned()) {
-            return false;
-        }
-        return true;
-    }
-
-    /**
-     * Indicates whether the parent progression dimension should be adjusted.
-     * @return True iff the parent progression dimension should be adjusted.
-     */
-    public boolean shouldAdjustParentPD() {
-        /* If not in the normal flow, the parent's dimensions are not used up
-         * as this grows. */
-        if (! this.isInNormalFlow()) {
-            return false;
-        }
-        final Area parent = ancestorArea();
-        if (parent instanceof LineArea) {
-            /* LineArea children grow in the IPD, LineArea grows in the BPD. */
-            return false;
-        }
-        if (parent instanceof TableRowContainer) {
-            /* TableRowContainer children grow in the IPD, LineArea grows in the
-             * BPD. */
-            return false;
-        }
-        return true;
-    }
-
-    /**
-     * Returns the area-class trait for this Area.
-     * @return The area-class trait for this Area.
-     * @see "XSL-FO 1.1, Section 4.2.5."
-     */
-    public AreaClass traitAreaClass() {
-        /* TODO: This method is incomplete. */
-        final FootnoteRa footnoteArea = this.nearestFootnoteArea();
-        if (footnoteArea != null) {
-            return AreaClass.XSL_FOOTNOTE;
-        }
-        final BeforeFloatRa beforeFloatArea = this.nearestBeforeFloatArea();
-        if (beforeFloatArea != null) {
-            return AreaClass.XSL_BEFORE_FLOAT;
-        }
-        return AreaClass.XSL_NORMAL;
-    }
-
-    /**
-     * Indicates whether there is an absolute fence preceding this Area for
-     * purposes of stacking constraints.
-     * This method is only relevant for block-areas as inline-areas have a more
-     * complicated fencing procedure.
-     * @return True iff this Area has a fence preceding it.
-     * @see "XSL-FO 1.1, Section 4.2.5, under 'Block-stacking constraints'."
-     */
-    public boolean hasFencePreceding() {
-        if (this.isBlockArea()) {
-            if (this.traitIsReferenceArea()) {
-                return true;
-            }
-            if (this.traitBorderBeforeWidth() != 0) {
-                return true;
-            }
-            if (this.traitPaddingBefore() != 0) {
-                return true;
-            }
-        }
-        return false;
-    }
-
-    /**
-     * Indicates whether there is an absolute fence following this Area for
-     * purposes of stacking constraints.
-     * This method is only relevant for block-areas as inline-areas have a more
-     * complicated fencing procedure.
-     * @return True iff this Area has a fence following it.
-     * @see "XSL-FO 1.1, Section 4.2.5, under 'Block-stacking constraints'."
-     */
-    public boolean hasFenceFollowing() {
-        if (this.isBlockArea()) {
-            if (this.traitIsReferenceArea()) {
-                return true;
-            }
-            if (this.traitBorderAfterWidth() != 0) {
-                return true;
-            }
-            if (this.traitPaddingAfter() != 0) {
-                return true;
-            }
-        }
-        return false;
-    }
-
-    @Override
-    public Area nearestArea() {
-        /* Overrides the AreaNode implementation, because this is the nearest
-         * Area. */
-        return this;
-    }
-
-    @Override
-    public String traitId() {
-        final Fo generatedBy = this.traitGeneratedBy();
-        if (generatedBy instanceof IdPa) {
-            return ((IdPa) generatedBy).traitId();
-        }
-        return null;
-    }
-
-    /**
-     * Returns the border-start-width trait for this area.
-     * @return The border-start-width trait for this area.
-     */
-    public abstract int traitBorderStartWidth();
-
-    /**
-     * Returns the border-end-width trait for this area.
-     * @return The border-end-width trait for this area.
-     */
-    public abstract int traitBorderEndWidth();
-
-    /**
-     * Returns the border-before-width trait for this area.
-     * @return The border-before-width trait for this area.
-     */
-    public abstract int traitBorderBeforeWidth();
-
-    /**
-     * Returns the border-after-width trait for this area.
-     * @return The border-after-width trait for this area.
-     */
-    public abstract int traitBorderAfterWidth();
-
-    /**
-     * Returns the padding-start trait for this area.
-     * @return The padding-start trait for this area.
-     */
-    public abstract int traitPaddingStart();
-
-    /**
-     * Returns the padding-end trait for this area.
-     * @return The padding-end trait for this area.
-     */
-    public abstract int traitPaddingEnd();
-
-    /**
-     * Returns the padding-before trait for this area.
-     * @return The padding-before trait for this area.
-     */
-    public abstract int traitPaddingBefore();
-
-    /**
-     * Returns the padding-after trait for this area.
-     * @return The padding-after trait for this area.
-     */
-    public abstract int traitPaddingAfter();
-
-    /**
-     * Returns the writing mode associated with this Area.
-     * @return The writing mode (vertical or horizontal) that is associated with this Area.
-     */
-    public Font.WritingMode getFontWritingMode() {
-        final AbsoluteAxis axis = this.getWritingMode().getIpAxis();
-        if (axis == AbsoluteAxis.VERTICAL) {
-            return Font.WritingMode.VERTICAL;
-        }
-        return Font.WritingMode.HORIZONTAL;
-    }
-
-}

Copied: trunk/foray/foray-areatree/src/main/java/org/foray/area/Area4a.java (from rev 12032, trunk/foray/foray-areatree/src/main/java/org/foray/area/Area.java)
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/Area4a.java	                        (rev 0)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/Area4a.java	2021-11-14 23:19:35 UTC (rev 12065)
@@ -0,0 +1,1019 @@
+/*
+ * Copyright 2004 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.area;
+
+import org.foray.common.WellKnownConstants;
+
+import org.axsl.area.AreaTreeException;
+import org.axsl.area.BlockContainerRefArea;
+import org.axsl.common.value.AbsoluteAxis;
+import org.axsl.common.value.AbsoluteDirection;
+import org.axsl.common.value.LinkType;
+import org.axsl.common.value.RelativeAxis;
+import org.axsl.common.value.WhiteSpaceTreatment;
+import org.axsl.common.value.WritingMode;
+import org.axsl.fo.Fo;
+import org.axsl.fo.fo.BasicLink;
+import org.axsl.fo.fo.Block;
+import org.axsl.fo.fo.prop.IdPa;
+import org.axsl.fo.fo.prop.WritingModePa;
+import org.axsl.font.Font;
+import org.axsl.galley.BackgroundArea;
+
+import java.awt.geom.Rectangle2D;
+import java.util.List;
+
+/**
+ * Abstract superclass for all Areas in the AreaTree.
+ */
+public abstract class Area4a extends AreaNode4a implements org.axsl.galley.Area,
+        org.axsl.area.Area {
+
+   ...
 
[truncated message content]

[FOray-commit] SF.net SVN: foray:[12064] trunk/foray

[<vic...@us...>]

Revision: 12064
          http://sourceforge.net/p/foray/code/12064
Author:   victormote
Date:     2021-11-14 22:36:02 +0000 (Sun, 14 Nov 2021)
Log Message:
-----------
Conform to aXSL change: Require WritingSystem. This effectively pushes the hard-coded WritingSystem arguments upstream.

Modified Paths:
--------------
    trunk/foray/foray-areatree/src/main/java/org/foray/area/TextArea.java
    trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfDocument4a.java
    trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformMath.java
    trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformSvg.java
    trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXobject4a.java
    trunk/foray/foray-pdf/src/main/java/org/foray/pdf/util/PdfGraphics2D.java
    trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/TextArea.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/TextArea.java	2021-11-14 20:40:14 UTC (rev 12063)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/TextArea.java	2021-11-14 22:36:02 UTC (rev 12064)
@@ -65,7 +65,7 @@
  * Please note that a given FOText node may have more than one TextArea that
  * springs from it (they would have to be in different LineAreas or use
  * different Fonts due to overriding).
- * However , a TextSegment always springs from exactly one FOText node.
+ * However, a TextSegment always springs from exactly one FOText node.
  */
 public final class TextArea extends AbstractInlineArea
         implements org.axsl.galley.TextArea, org.axsl.area.GlyphAreaSequence {

Modified: trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfDocument4a.java
===================================================================
--- trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfDocument4a.java	2021-11-14 20:40:14 UTC (rev 12063)
+++ trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfDocument4a.java	2021-11-14 22:36:02 UTC (rev 12064)
@@ -45,6 +45,7 @@
 import org.foray.pdf.PdfParser;
 
 import org.axsl.common.Gradient;
+import org.axsl.common.i18n.WritingSystem;
 import org.axsl.common.sequence.IntPrimitiveIterator;
 import org.axsl.font.Font;
 import org.axsl.font.FontConsumer;
@@ -766,10 +767,11 @@
     }
 
     @Override
-    public PdfXobject createXobject(final Graphic graphic, final FontConsumer fontConsumer) throws PdfException {
+    public PdfXobject createXobject(final Graphic graphic, final WritingSystem writingSystem,
+            final FontConsumer fontConsumer) throws PdfException {
         final PdfXobject4a xObject;
         try {
-            xObject = PdfXobject4a.makeXObject(this, graphic, fontConsumer);
+            xObject = PdfXobject4a.makeXObject(this, graphic, writingSystem, fontConsumer);
         } catch (final GraphicException e) {
             throw new PdfException(e);
         }

Modified: trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformMath.java
===================================================================
--- trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformMath.java	2021-11-14 20:40:14 UTC (rev 12063)
+++ trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformMath.java	2021-11-14 22:36:02 UTC (rev 12064)
@@ -33,6 +33,7 @@
 import org.foray.pdf.util.PdfGraphics2D;
 
 import org.axsl.common.data.BoundingBox;
+import org.axsl.common.i18n.WritingSystem;
 import org.axsl.font.FontConsumer;
 import org.axsl.graphic.GraphicException;
 import org.axsl.graphic.MathGraphic;
@@ -55,15 +56,21 @@
     /** The FontConsumer to use for resolving fonts in the MathML document. */
     private FontConsumer fontConsumer;
 
+    /** The writing system. */
+    private WritingSystem writingSystem;
+
     /**
      * Constructor.
      * @param doc The parent PDF document.
      * @param graphic The form to be encapsulated.
+     * @param writingSystem The writing system.
      * @param fontConsumer The font consumer to use for resolving fonts in the SVG.
      */
-    public PdfXformMath(final PdfDocument4a doc, final MathGraphic graphic, final FontConsumer fontConsumer) {
+    public PdfXformMath(final PdfDocument4a doc, final MathGraphic graphic, final WritingSystem writingSystem,
+            final FontConsumer fontConsumer) {
         super(doc, graphic);
         this.graphic = graphic;
+        this.writingSystem = writingSystem;
         this.fontConsumer = fontConsumer;
     }
 
@@ -78,7 +85,7 @@
         }
         final GraphicPdf graphicPdf = (GraphicPdf) graphicOutput;
 //        graphicPdf.drawVectorContent(outputStream, doc, this.fontConsumer, this.strokeText, false);
-        final Graphics2D graphic2D = new PdfGraphics2D(fontConsumer, doc, outputStream);
+        final Graphics2D graphic2D = new PdfGraphics2D(this.writingSystem, this.fontConsumer, doc, outputStream);
         graphicPdf.drawVectorContent(graphic2D, fontConsumer);
         return outputStream.toByteArray();
     }

Modified: trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformSvg.java
===================================================================
--- trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformSvg.java	2021-11-14 20:40:14 UTC (rev 12063)
+++ trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXformSvg.java	2021-11-14 22:36:02 UTC (rev 12064)
@@ -33,6 +33,7 @@
 import org.foray.pdf.util.PdfGraphics2D;
 
 import org.axsl.common.data.BoundingBox;
+import org.axsl.common.i18n.WritingSystem;
 import org.axsl.font.FontConsumer;
 import org.axsl.graphic.GraphicException;
 import org.axsl.graphic.SvgGraphic;
@@ -55,16 +56,22 @@
     /** The FontConsumer to use for resolving fonts in the SVG. */
     private FontConsumer fontConsumer;
 
+    /** The writing system. */
+    private WritingSystem writingSystem;
+
     /**
      * Constructor.
      * @param doc The parent PDF document.
      * @param graphic The form to be encapsulated.
+     * @param writingSystem The writing system.
      * @param fontConsumer The font consumer to use for resolving fonts in the SVG.
      */
-    public PdfXformSvg(final PdfDocument4a doc, final SvgGraphic graphic, final FontConsumer fontConsumer) {
+    public PdfXformSvg(final PdfDocument4a doc, final SvgGraphic graphic, final WritingSystem writingSystem,
+            final FontConsumer fontConsumer) {
         super(doc, graphic);
         this.graphic = graphic;
         this.fontConsumer = fontConsumer;
+        this.writingSystem = writingSystem;
     }
 
     @Override
@@ -78,7 +85,7 @@
         }
         final GraphicPdf graphicPdf = (GraphicPdf) graphicOutput;
 //        graphicPdf.drawVectorContent(outputStream, doc, this.fontConsumer, this.strokeText, false);
-        final Graphics2D graphic2D = new PdfGraphics2D(fontConsumer, doc, outputStream);
+        final Graphics2D graphic2D = new PdfGraphics2D(this.writingSystem, this.fontConsumer, doc, outputStream);
         graphicPdf.drawVectorContent(graphic2D, fontConsumer);
         return outputStream.toByteArray();
     }

Modified: trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXobject4a.java
===================================================================
--- trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXobject4a.java	2021-11-14 20:40:14 UTC (rev 12063)
+++ trunk/foray/foray-pdf/src/main/java/org/foray/pdf/object/PdfXobject4a.java	2021-11-14 22:36:02 UTC (rev 12064)
@@ -34,6 +34,7 @@
 
 package org.foray.pdf.object;
 
+import org.axsl.common.i18n.WritingSystem;
 import org.axsl.font.FontConsumer;
 import org.axsl.graphic.EpsGraphic;
 import org.axsl.graphic.Graphic;
@@ -85,12 +86,13 @@
      * PdfXobject instance.
      * @param pdfDoc The parent PDF document.
      * @param img The graphic to be encapsulated.
+     * @param writingSystem The writing system.
      * @param fontConsumer The font consumer to use for resolving fonts in the SVG.
      * @return An appropriate PdfXobject instance that encapsulates the input.
      * @throws GraphicException For errors getting the appropriate filter.
      */
     public static PdfXobject4a makeXObject(final PdfDocument4a pdfDoc, final Graphic img,
-            final FontConsumer fontConsumer) throws GraphicException {
+            final WritingSystem writingSystem, final FontConsumer fontConsumer) throws GraphicException {
         /* If it has already been created, reuse it ... */
         PdfXobject4a xObject = pdfDoc.findXObject(img);
         if (xObject != null) {
@@ -103,10 +105,10 @@
             xObject = new PdfXformEps(pdfDoc, epsGraphic);
         } else if (img instanceof SvgGraphic) {
             final SvgGraphic svgGraphic = (SvgGraphic) img;
-            xObject = new PdfXformSvg(pdfDoc, svgGraphic, fontConsumer);
+            xObject = new PdfXformSvg(pdfDoc, svgGraphic, writingSystem, fontConsumer);
         } else if (img instanceof MathGraphic) {
             final MathGraphic mathGraphic = (MathGraphic) img;
-            xObject = new PdfXformMath(pdfDoc, mathGraphic, fontConsumer);
+            xObject = new PdfXformMath(pdfDoc, mathGraphic, writingSystem, fontConsumer);
         } else if (img.getGraphicType() == Graphic.Type.PDF) {
             xObject = new PdfXreference(pdfDoc, img);
         } else {

Modified: trunk/foray/foray-pdf/src/main/java/org/foray/pdf/util/PdfGraphics2D.java
===================================================================
--- trunk/foray/foray-pdf/src/main/java/org/foray/pdf/util/PdfGraphics2D.java	2021-11-14 20:40:14 UTC (rev 12063)
+++ trunk/foray/foray-pdf/src/main/java/org/foray/pdf/util/PdfGraphics2D.java	2021-11-14 22:36:02 UTC (rev 12064)
@@ -36,12 +36,12 @@
 import org.foray.common.CharacterOutputStream;
 import org.foray.common.Gradient4a;
 import org.foray.common.WellKnownConstants;
-import org.foray.common.i18n.WritingSystem4a;
 import org.foray.common.ps.PsColor;
 import org.foray.common.ps.PsUtil;
 import org.foray.pdf.PdfConstants;
 import org.foray.pdf.object.PdfColor4a;
 
+import org.axsl.common.i18n.WritingSystem;
 import org.axsl.font.FontConsumer;
 import org.axsl.font.FontOptions;
 import org.axsl.font.FontUse;
@@ -158,6 +158,9 @@
      * the next "restore". */
     private Stack<PdfGraphics2D.PdfGraphicsState> graphicsStateStack = new Stack<PdfGraphics2D.PdfGraphicsState>();
 
+    /** The current writing system. */
+    private WritingSystem writingSystem;
+
     /** Lazily-loaded logger. Use {@link getLogger()} to obtain the instance. */
     private Logger logger;
 
@@ -164,11 +167,12 @@
     /**
      * Create a new PdfGraphics2D with the given pdf document info.
      * This is used to create a Graphics object for use inside an already existing document.
+     * @param writingSystem The writing system in use.
      * @param fontConsumer The font consumer for this document.
      * @param pdfContext The PDF context in which this content is being written.
      * @param outputStream The output stream to which this processor writes its PDF output.
      */
-    public PdfGraphics2D(final FontConsumer fontConsumer,
+    public PdfGraphics2D(final WritingSystem writingSystem, final FontConsumer fontConsumer,
             final GraphicOutputContext pdfContext, final OutputStream outputStream) {
         super(fontConsumer == null);
         this.gc = new GraphicContext();
@@ -179,6 +183,7 @@
         this.fontConsumer = fontConsumer;
         this.pdfContext = pdfContext;
         this.graphicsStateStack.push(new PdfGraphicsState(null));
+        this.writingSystem = writingSystem;
     }
 
     /**
@@ -675,7 +680,7 @@
         this.write(matrixString + "cm");
         this.write("1 0 0 -1 0 0 Tm ");
 
-        final CharSequence outputString = font.textToPdf(s, FontOptions.DEFAULT, WritingSystem4a.USA);
+        final CharSequence outputString = font.textToPdf(s, FontOptions.DEFAULT, this.writingSystem);
         this.write(outputString);
 
         this.write("ET");

Modified: trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java
===================================================================
--- trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java	2021-11-14 20:40:14 UTC (rev 12063)
+++ trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java	2021-11-14 22:36:02 UTC (rev 12064)
@@ -34,6 +34,7 @@
 package org.foray.render.pdf;
 
 import org.foray.common.WellKnownConstants;
+import org.foray.common.i18n.WritingSystem4a;
 import org.foray.render.PrintRenderer;
 
 import org.axsl.common.FormattedIntegerType;
@@ -304,7 +305,7 @@
         final Rectangle2D.Float pdfClipRectangle = convertMillipointRectangle(
                 clipRectangle);
         try {
-            final PdfXobject xObject = this.pdfDoc.createXobject(image, getFontConsumer());
+            final PdfXobject xObject = this.pdfDoc.createXobject(image, WritingSystem4a.USA, getFontConsumer());
             getContentStream().drawXobject(xObject, pdfContentRectangle, pdfClipRectangle);
         } catch (final PdfException e) {
             throw new GalleyVisitorException(e);
@@ -320,7 +321,7 @@
                 toPoints(foreign.referenceBpd()));
         final SvgGraphic svgGraphic = area.getGraphic();
         try {
-            final PdfXobject xObject = this.pdfDoc.createXobject(svgGraphic, getFontConsumer());
+            final PdfXobject xObject = this.pdfDoc.createXobject(svgGraphic, WritingSystem4a.USA, getFontConsumer());
             getContentStream().drawXobject(xObject, contentRectangle, null);
         } catch (final PdfException e) {
             throw new GalleyVisitorException(e);
@@ -337,7 +338,7 @@
                 toPoints(foreign.referenceBpd()));
         final MathGraphic mathGraphic = area.getGraphic();
         try {
-            final PdfXobject xObject = this.pdfDoc.createXobject(mathGraphic, getFontConsumer());
+            final PdfXobject xObject = this.pdfDoc.createXobject(mathGraphic, WritingSystem4a.USA, getFontConsumer());
             getContentStream().drawXobject(xObject, contentRectangle, null);
         } catch (final PdfException e) {
             throw new GalleyVisitorException(e);

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

[FOray-commit] SF.net SVN: foray:[12063] trunk/foray/foray-areatree/src/main/java/org/ foray/area

[<vic...@us...>]

Revision: 12063
          http://sourceforge.net/p/foray/code/12063
Author:   victormote
Date:     2021-11-14 20:40:14 +0000 (Sun, 14 Nov 2021)
Log Message:
-----------
Add method that retrieves the WritingSystem from the FO tree. Use that to remove a hard-coded instance.

Modified Paths:
--------------
    trunk/foray/foray-areatree/src/main/java/org/foray/area/FoLinkage.java
    trunk/foray/foray-areatree/src/main/java/org/foray/area/TextArea.java

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/FoLinkage.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/FoLinkage.java	2021-11-14 20:38:39 UTC (rev 12062)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/FoLinkage.java	2021-11-14 20:40:14 UTC (rev 12063)
@@ -28,7 +28,9 @@
 
 package org.foray.area;
 
+import org.axsl.common.i18n.WritingSystem;
 import org.axsl.fo.Fo;
+import org.axsl.fo.FoLineText;
 import org.axsl.fo.fo.GraftingPoint;
 
 /**
@@ -63,4 +65,16 @@
      */
     public abstract GraftingPoint getRetrieveMarker(AreaNode areaNode);
 
+    /**
+     * Retrieves the writing system, if any, for the wrapped FO.
+     * @return The writing system for the wrapped FO, of null if the FO does not have one.
+     */
+    public WritingSystem getWritingSystem() {
+        if (this.foGenerator instanceof FoLineText) {
+            final FoLineText lt = (FoLineText) this.foGenerator;
+            return lt.inlineWritingSystem();
+        }
+        return null;
+    }
+
 }

Modified: trunk/foray/foray-areatree/src/main/java/org/foray/area/TextArea.java
===================================================================
--- trunk/foray/foray-areatree/src/main/java/org/foray/area/TextArea.java	2021-11-14 20:38:39 UTC (rev 12062)
+++ trunk/foray/foray-areatree/src/main/java/org/foray/area/TextArea.java	2021-11-14 20:40:14 UTC (rev 12063)
@@ -29,7 +29,6 @@
 package org.foray.area;
 
 import org.foray.common.CharSequenceSubset;
-import org.foray.common.i18n.WritingSystem4a;
 import org.foray.common.primitive.XmlCharacterUtils;
 
 import org.axsl.area.AreaTreeException;
@@ -679,8 +678,7 @@
 
     @Override
     public WritingSystem writingSystem() {
-        /* TODO: Get this from the FOTree. */
-        return WritingSystem4a.USA;
+        return this.generatedBy.getWritingSystem();
     }
 
     @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:[12062] trunk/foray/foray-render/src/main/java/org/foray /render/pdf/PdfRenderer.java

[<vic...@us...>]

Revision: 12062
          http://sourceforge.net/p/foray/code/12062
Author:   victormote
Date:     2021-11-14 20:38:39 +0000 (Sun, 14 Nov 2021)
Log Message:
-----------
Remove dependency on hard-coded writing system

Modified Paths:
--------------
    trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java

Modified: trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java
===================================================================
--- trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java	2021-11-14 19:46:18 UTC (rev 12061)
+++ trunk/foray/foray-render/src/main/java/org/foray/render/pdf/PdfRenderer.java	2021-11-14 20:38:39 UTC (rev 12062)
@@ -34,7 +34,6 @@
 package org.foray.render.pdf;
 
 import org.foray.common.WellKnownConstants;
-import org.foray.common.i18n.WritingSystem4a;
 import org.foray.render.PrintRenderer;
 
 import org.axsl.common.FormattedIntegerType;
@@ -481,7 +480,7 @@
 
         /* Paint the text. */
         final CharSequence textToWrite = text.subSequence(startIndex, startIndex + size);
-        getContentStream().drawText(textToWrite, fontOptions, WritingSystem4a.USA);
+        getContentStream().drawText(textToWrite, fontOptions, orthography);
     }
 
     @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:[12061] trunk/foray/foray-orthography/src/main

[<vic...@us...>]

Revision: 12061
          http://sourceforge.net/p/foray/code/12061
Author:   victormote
Date:     2021-11-14 19:46:18 +0000 (Sun, 14 Nov 2021)
Log Message:
-----------
Allow Punctuation4a to silently return a null. Fix some minor side-effects of that.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/data/dictionaries/eng-999-Latn.dict.xml
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java

Modified: trunk/foray/foray-orthography/src/main/data/dictionaries/eng-999-Latn.dict.xml
===================================================================
--- trunk/foray/foray-orthography/src/main/data/dictionaries/eng-999-Latn.dict.xml	2021-11-14 16:56:39 UTC (rev 12060)
+++ trunk/foray/foray-orthography/src/main/data/dictionaries/eng-999-Latn.dict.xml	2021-11-14 19:46:18 UTC (rev 12061)
@@ -53,6 +53,7 @@
 # web site, or submit a patch request.
 -->
 
+<w><t>&amp;</t></w>
 <w><t>a</t></w>
 <phrase><t>a cap-pel-la</t></phrase>
 <phrase><t>a for-ti-o-ri</t></phrase>

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java	2021-11-14 16:56:39 UTC (rev 12060)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/LexerLatin1.java	2021-11-14 19:46:18 UTC (rev 12061)
@@ -39,6 +39,7 @@
     public CharType isWordChar(final char c) {
         switch (c) {
         case '-': return CharType.ALWAYS_WORD_CHAR;
+        case '&': return CharType.ALWAYS_WORD_CHAR;
         default: return super.isWordChar(c);
         }
     }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java	2021-11-14 16:56:39 UTC (rev 12060)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java	2021-11-14 19:46:18 UTC (rev 12061)
@@ -39,8 +39,6 @@
 import org.axsl.common.para.ParaPenalty;
 import org.axsl.orthography.Punctuation;
 
-import org.slf4j.LoggerFactory;
-
 import java.util.ArrayList;
 import java.util.List;
 
@@ -108,8 +106,17 @@
     public static final Punctuation4a CLOSE_SQUARE_BRACKET = new Punctuation4a("]");
 
     /** Common punctuation item. */
+    public static final Punctuation4a FORWARD_SLASH = new Punctuation4a("/");
+
+    /** Common punctuation item. */
+    public static final Punctuation4a ELLIPSIS = new Punctuation4a("\u2026");
+
+    /** Common punctuation item. */
     public static final Punctuation4a ZERO_WIDTH_SPACE = new Punctuation4a("\u200B");
 
+    /** Common punctuation item. */
+    public static final Punctuation4a ZERO_WIDTH_NO_BREAK_SPACE = new Punctuation4a("\uFEFF");
+
     /** The list of common interword items. */
     private static final List<Punctuation4a> COMMON_PUNCTUATION = new ArrayList<Punctuation4a>(25);
     static {
@@ -133,7 +140,10 @@
         COMMON_PUNCTUATION.add(CLOSE_PAREN);
         COMMON_PUNCTUATION.add(OPEN_SQUARE_BRACKET);
         COMMON_PUNCTUATION.add(CLOSE_SQUARE_BRACKET);
+        COMMON_PUNCTUATION.add(FORWARD_SLASH);
+        COMMON_PUNCTUATION.add(ELLIPSIS);
         COMMON_PUNCTUATION.add(ZERO_WIDTH_SPACE);
+        COMMON_PUNCTUATION.add(ZERO_WIDTH_NO_BREAK_SPACE);
 
     }
 
@@ -153,7 +163,7 @@
      * Using this method instead of a constructor allows this class to reduce unnecessary object creation be reusing
      * existing instances of this class instead of creating identical ones.
      * @param content The content of the interword item.
-     * @return An instance of this class wrapping the given content.
+     * @return An instance of this class wrapping the given content, or null if no instance is found.
      */
     public static Punctuation4a findInstance(final CharSequence content) {
         for (int index = 0; index < COMMON_PUNCTUATION.size(); index ++) {
@@ -162,8 +172,7 @@
                 return punctuation;
             }
         }
-        LoggerFactory.getLogger(Punctuation4a.class).warn("Standard punctuation not found: [" + content + "]");
-        return new Punctuation4a(content);
+        return null;
     }
 
     @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:[12060] trunk/foray

[<vic...@us...>]

Revision: 12060
          http://sourceforge.net/p/foray/code/12060
Author:   victormote
Date:     2021-11-14 16:56:39 +0000 (Sun, 14 Nov 2021)
Log Message:
-----------
1. Conform to aXSL change: Add method to ParaBranch that returns the count of its descendant leaf nodes. 2. Add assertion for this count in TotalFitLbTests.

Modified Paths:
--------------
    trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaBranch4a.java
    trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/SegmentDictionaryWord.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/StringWord.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/CapitalizedWord.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/ExactWord.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPast1Word.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPlural1Word.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPlural2Word.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPossessive1Word.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPossessive2Word.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/UppercaseWord.java

Modified: trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaBranch4a.java
===================================================================
--- trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaBranch4a.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaBranch4a.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -81,6 +81,22 @@
     }
 
     @Override
+    public int getQtyParaLeafDescendants() {
+        int returnValue = 0;
+        for (int index = 0; index < getQtyParaNodeChildren(); index ++) {
+            final ParaBranch childBranch = getParaNodeChild(index).asParaBranch();
+            if (childBranch == null) {
+                /* Child node is a leaf. */
+                returnValue ++;
+            } else {
+                /* Child node is a branch. */
+                returnValue += childBranch.getQtyParaLeafDescendants();
+            }
+        }
+        return returnValue;
+    }
+
+    @Override
     public ParaConfig getParaConfig() {
         return this.config;
     }

Modified: trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java
===================================================================
--- trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -112,7 +112,7 @@
         para.addNodeAndSpace(Punctuation4a.COMMA);
         para.addWordAndSpace("was");
         para.addWordAndSpace("aston-ished");            // 2 segments
-        para.addWordAndSpace("when-ever");
+        para.addWordAndSpace("when-ever");              // 2 segments
         para.addWordAndSpace("it");
         para.addWordAndSpace("shone");
         para.addWordAndSpace("in");
@@ -218,8 +218,12 @@
          *                             -----     -----
          *   totals                      126       238
          *                             =====     =====  */
+        Assert.assertEquals(238, para.getQtyParaNodeChildren());
 
-        Assert.assertEquals(238, para.getQtyParaNodeChildren());
+        /* Of the words added, 12 are two-syllable, and 2 are three-syllable, which should add
+         * (13 x 1) + (2 x 2) = 17 additional leaf nodes. */
+        Assert.assertEquals(255, para.getQtyParaLeafDescendants());
+
         return para;
     }
 

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/SegmentDictionaryWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/SegmentDictionaryWord.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/SegmentDictionaryWord.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -107,4 +107,9 @@
         return PosUtils.isOfQualifiedType(this.partsOfSpeech, pos, qualifier);
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        return this.segments.length;
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/StringWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/StringWord.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/StringWord.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -119,4 +119,9 @@
         return this.partsOfSpeech;
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        return this.segments.length;
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/CapitalizedWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/CapitalizedWord.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/CapitalizedWord.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -99,4 +99,10 @@
         }
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        /* Capitalizing the word does not change the number of leaf descendants. */
+        return this.getWrappedWord().getQtyParaLeafDescendants();
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/ExactWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/ExactWord.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/ExactWord.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -82,4 +82,10 @@
         return this.exact;
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        /* Changing the case of chars in the word does not change the number of leaf descendants. */
+        return this.getWrappedWord().getQtyParaLeafDescendants();
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPast1Word.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPast1Word.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPast1Word.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -57,4 +57,10 @@
         return LatinPast1Word.SUFFIX;
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        /* This wrapper should add one leaf descendant to the size of the wrapped word. */
+        return this.getWrappedWord().getQtyParaLeafDescendants() + 1;
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPlural1Word.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPlural1Word.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPlural1Word.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -86,4 +86,10 @@
         return new Segment(unmodifiedSegment);
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        /* We think this wrapper should not change the number of leaf descendants. */
+        return this.getWrappedWord().getQtyParaLeafDescendants();
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPlural2Word.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPlural2Word.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPlural2Word.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -89,4 +89,10 @@
         return new Segment(unmodifiedSegment);
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        /* We think this wrapper should not change the number of leaf descendants. */
+        return this.getWrappedWord().getQtyParaLeafDescendants();
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPossessive1Word.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPossessive1Word.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPossessive1Word.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -87,4 +87,10 @@
         return new Segment(unmodifiedSegment);
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        /* We think this wrapper should not change the number of leaf descendants. */
+        return this.getWrappedWord().getQtyParaLeafDescendants();
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPossessive2Word.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPossessive2Word.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/LatinPossessive2Word.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -87,4 +87,10 @@
         return new Segment(unmodifiedSegment);
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        /* We think this wrapper should not change the number of leaf descendants. */
+        return this.getWrappedWord().getQtyParaLeafDescendants();
+    }
+
 }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/UppercaseWord.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/UppercaseWord.java	2021-11-14 15:04:23 UTC (rev 12059)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/wrapper/UppercaseWord.java	2021-11-14 16:56:39 UTC (rev 12060)
@@ -90,4 +90,10 @@
         return new Segment(segment);
     }
 
+    @Override
+    public int getQtyParaLeafDescendants() {
+        /* Converting the word to uppercase does not change the number of leaf descendants. */
+        return this.getWrappedWord().getQtyParaLeafDescendants();
+    }
+
 }

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

[FOray-commit] SF.net SVN: foray:[12059] trunk/foray/foray-orthography/src/main/java/org/ foray/orthography/Orthography4a.java

[<vic...@us...>]

Revision: 12059
          http://sourceforge.net/p/foray/code/12059
Author:   victormote
Date:     2021-11-14 15:04:23 +0000 (Sun, 14 Nov 2021)
Log Message:
-----------
Push decision about whether punctuation or not over to Punctuation4a.

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	2021-11-14 14:37:28 UTC (rev 12058)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java	2021-11-14 15:04:23 UTC (rev 12059)
@@ -31,7 +31,6 @@
 import org.foray.common.para.ParaBranch4a;
 import org.foray.common.primitive.BooleanUtils;
 import org.foray.common.primitive.CharSequenceUtils;
-import org.foray.common.primitive.CharacterUtils;
 import org.foray.common.primitive.NumberUtils;
 import org.foray.orthography.wrapper.CapitalizedWord;
 import org.foray.orthography.wrapper.ExactWord;
@@ -438,18 +437,17 @@
     private void parseInterwordContent(final ParaBranch4a wordSequence, final CharSequence interword) {
         int index = 0;
         while (index < interword.length()) {
-            if (CharacterUtils.isPunctuation(interword.charAt(index))) {
-                final Punctuation4a punctuation = Punctuation4a.findInstance(interword.subSequence(index, index + 1));
+            final char contentChar = interword.charAt(index);
+            final Punctuation4a punctuation = Punctuation4a.findInstance(interword.subSequence(index, index + 1));
+            if (punctuation != null) {
                 wordSequence.add(punctuation);
                 index ++;
-            } else if (Character.isWhitespace(interword.charAt(index))) {
+            } else if (Character.isWhitespace(contentChar)) {
                 final Whitespace4a whitespace = Whitespace4a.findInstance(interword.subSequence(index, index + 1));
                 wordSequence.add(whitespace);
                 index ++;
             } else {
-                final Interword4a unknown = Interword4a.findInstance(interword.subSequence(index, index + 1));
-                wordSequence.add(unknown);
-                index ++;
+                throw new IllegalStateException("Don't know how to handle interword content: " + contentChar);
             }
         }
 

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

[FOray-commit] SF.net SVN: foray:[12058] trunk/foray/foray-orthography/src

[<vic...@us...>]

Revision: 12058
          http://sourceforge.net/p/foray/code/12058
Author:   victormote
Date:     2021-11-14 14:37:28 +0000 (Sun, 14 Nov 2021)
Log Message:
-----------
1. Conform to aXSL change: Change the notion of interword content from a ParaBranch to ParaLeaf. 2. Remove no-longer-needed Whitespace4a class and related test class.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java

Removed Paths:
-------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Interword4a.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/Interword4aTests.java

Deleted: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Interword4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Interword4a.java	2021-11-13 20:37:22 UTC (rev 12057)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Interword4a.java	2021-11-14 14:37:28 UTC (rev 12058)
@@ -1,325 +0,0 @@
-/*
- * Copyright 2017 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;
-
-import org.foray.common.para.ParaBoxChars;
-import org.foray.common.para.ParaGlueChars;
-import org.foray.common.primitive.CharSequenceUtils;
-import org.foray.common.primitive.CharacterUtils;
-import org.foray.common.primitive.StringUtils;
-
-import org.axsl.common.para.ParaBranch;
-import org.axsl.common.para.ParaConfig;
-import org.axsl.common.para.ParaLeaf;
-import org.axsl.common.para.ParaNode;
-import org.axsl.orthography.Interword;
-
-import org.slf4j.LoggerFactory;
-
-import java.util.ArrayList;
-import java.util.List;
-
-/**
- * FOray implementation of {link Interword}.
- * Instances of this class are immutable.
- */
-public final class Interword4a implements Interword {
-
-    /** The glue for an interword space. */
-    private static final ParaGlueChars SPACE_GLUE = new ParaGlueChars(" ");
-
-    /** Common interword item. */
-    private static final Interword4a SPACE = new Interword4a(new ParaLeaf[] {
-            SPACE_GLUE
-    });
-
-    /** Common interword item. */
-    private static final Interword4a COMMA = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars(",")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a COLON = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars(":")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a SEMICOLON = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars(";")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a PERIOD = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars(".")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a QUESTION = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("?")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a EXCLAMATION = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("!")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a COMMA_AND_SPACE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars(","),
-            SPACE_GLUE
-    });
-
-    /** Common interword item. */
-    private static final Interword4a SEMICOLON_AND_SPACE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars(";"),
-            SPACE_GLUE
-    });
-
-    /** Common interword item. */
-    private static final Interword4a COLON_AND_SPACE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars(":"),
-            SPACE_GLUE
-    });
-
-    /** Common interword item. */
-    private static final Interword4a PERIOD_AND_SPACE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("."),
-            SPACE_GLUE
-    });
-
-    /** Common interword item. */
-    private static final Interword4a QUESTION_AND_SPACE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("?"),
-            SPACE_GLUE
-    });
-
-    /** Common interword item. */
-    private static final Interword4a EXCLAMATION_AND_SPACE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("!"),
-            SPACE_GLUE
-    });
-
-    /** Common interword item. */
-    private static final Interword4a LINE_FEED = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("\n")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a CARRIAGE_RETURN_AND_LINE_FEED = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("\r\n")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a CARRIAGE_RETURN = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("\r")
-    });
-
-    /** Common interword item. TODO: This needs to be treated differently. */
-    private static final Interword4a APOSTROPHE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars(StringUtils.EMPTY_STRING + CharacterUtils.SINGLE_CLOSE_QUOTATION_MARK)
-    });
-
-    /** Common interword item. */
-    private static final Interword4a MANDATORY_HYPHEN = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("-")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a SPACE_AND_DOUBLE_QUOTE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars(" \"")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a DOUBLE_QUOTE_AND_SPACE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("\" ")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a DOUBLE_QUOTE_COMMA_AND_SPACE = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("\", ")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a LF_TWO_SPACES = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("\n  ")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a CR_TWO_SPACES = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("\r  ")
-    });
-
-    /** Common interword item. */
-    private static final Interword4a CR_LF_TWO_SPACES = new Interword4a(new ParaLeaf[] {
-            new ParaBoxChars("\r\n  ")
-    });
-
-    /** The list of common interword items. */
-    private static final List<Interword4a> COMMON_INTERWORDS = new ArrayList<Interword4a>(20);
-    static {
-        COMMON_INTERWORDS.add(SPACE);
-
-        COMMON_INTERWORDS.add(COMMA);
-        COMMON_INTERWORDS.add(SEMICOLON);
-        COMMON_INTERWORDS.add(COLON);
-        COMMON_INTERWORDS.add(PERIOD);
-        COMMON_INTERWORDS.add(QUESTION);
-        COMMON_INTERWORDS.add(EXCLAMATION);
-
-        COMMON_INTERWORDS.add(COMMA_AND_SPACE);
-        COMMON_INTERWORDS.add(SEMICOLON_AND_SPACE);
-        COMMON_INTERWORDS.add(COLON_AND_SPACE);
-        COMMON_INTERWORDS.add(PERIOD_AND_SPACE);
-        COMMON_INTERWORDS.add(QUESTION_AND_SPACE);
-        COMMON_INTERWORDS.add(EXCLAMATION_AND_SPACE);
-
-        COMMON_INTERWORDS.add(LINE_FEED);
-        COMMON_INTERWORDS.add(CARRIAGE_RETURN_AND_LINE_FEED);
-        COMMON_INTERWORDS.add(CARRIAGE_RETURN);
-
-        COMMON_INTERWORDS.add(APOSTROPHE);
-        COMMON_INTERWORDS.add(MANDATORY_HYPHEN);
-        COMMON_INTERWORDS.add(SPACE_AND_DOUBLE_QUOTE);
-        COMMON_INTERWORDS.add(DOUBLE_QUOTE_AND_SPACE);
-        COMMON_INTERWORDS.add(DOUBLE_QUOTE_COMMA_AND_SPACE);
-        COMMON_INTERWORDS.add(LF_TWO_SPACES);
-        COMMON_INTERWORDS.add(CR_TWO_SPACES);
-        COMMON_INTERWORDS.add(CR_LF_TWO_SPACES);
-    }
-
-    /** The list of discovered interword items. */
-    private static final List<Interword4a> DISCOVERED_INTERWORDS = new ArrayList<Interword4a>(20);
-
-    /** The content of this interword item. */
-    private ParaLeaf[] content;
-
-    /**
-     * Private constructor. Use {@link #findInterword4a(CharSequence)} to obtain an instance of this class.
-     * @param content The content of this interword item.
-     */
-    private Interword4a(final ParaLeaf[] content) {
-        this.content = content;
-    }
-
-    /**
-     * Finds or creates an Interword4a instance for given content.
-     * Using this method instead of a constructor allows this class to reduce unnecessary object creation be reusing
-     * existing instances of this class instead of creating identical ones.
-     * @param content The content of the interword item.
-     * @return An instance of this class wrapping the given content.
-     */
-    public static Interword4a findInstance(final CharSequence content) {
-        for (int index = 0; index < COMMON_INTERWORDS.size(); index ++) {
-            final Interword4a interword = COMMON_INTERWORDS.get(index);
-            if (CharSequenceUtils.areEquivalent(interword, content)) {
-                return interword;
-            }
-        }
-        for (int index = 0; index < DISCOVERED_INTERWORDS.size(); index ++) {
-            final Interword4a interword = DISCOVERED_INTERWORDS.get(index);
-            if (CharSequenceUtils.areEquivalent(interword, content)) {
-                return interword;
-            }
-        }
-        LoggerFactory.getLogger(Interword4a.class).warn("Standard interword not found: [" + content + "]");
-        final Interword4a newInterword = new Interword4a(new ParaLeaf[] {new ParaBoxChars(content)});
-        DISCOVERED_INTERWORDS.add(newInterword);
-        return newInterword;
-    }
-
-    @Override
-    public CharSequence getContent() {
-        /* Performance not considered here as it seems unlikely this will be used much. */
-        final StringBuilder builder = new StringBuilder();
-        for (int index = 0; index < this.content.length; index ++) {
-            builder.append(this.content[index].getText());
-        }
-        /* Avoid the cost of converting to String. */
-        return builder;
-    }
-
-    @Override
-    public int length() {
-        /* Performance not considered here as it seems unlikely this will be used much. */
-        return getContent().length();
-    }
-
-    @Override
-    public char charAt(final int index) {
-        /* Performance not considered here as it seems unlikely this will be used much. */
-        return getContent().charAt(index);
-    }
-
-    @Override
-    /* Performance not considered here as it seems unlikely this will be used much. */
-    public CharSequence subSequence(final int start, final int end) {
-        return getContent().subSequence(start, end);
-    }
-
-    @Override
-    public String toString() {
-        return getContent().toString();
-    }
-
-    @Override
-    public int getQtyParaNodeChildren() {
-        return this.content.length;
-    }
-
-    @Override
-    public ParaNode getParaNodeChild(final int index) {
-        return this.content[index];
-    }
-
-    @Override
-    public ParaConfig getParaConfig() {
-        return null;
-    }
-
-    @Override
-    public void setParaConfig(final ParaConfig config) {
-        /* Nothing to do here. */
-    }
-
-    @Override
-    public Type getParaNodeType() {
-        return ParaNode.Type.BRANCH;
-    }
-
-    @Override
-    public ParaLeaf asParaLeaf() {
-        return null;
-    }
-
-    @Override
-    public ParaBranch asParaBranch() {
-        return this;
-    }
-
-}

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java	2021-11-13 20:37:22 UTC (rev 12057)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java	2021-11-14 14:37:28 UTC (rev 12058)
@@ -107,9 +107,11 @@
     /** Common punctuation item. */
     public static final Punctuation4a CLOSE_SQUARE_BRACKET = new Punctuation4a("]");
 
+    /** Common punctuation item. */
+    public static final Punctuation4a ZERO_WIDTH_SPACE = new Punctuation4a("\u200B");
 
     /** The list of common interword items. */
-    private static final List<Punctuation4a> COMMON_PUNCTUATION = new ArrayList<Punctuation4a>(20);
+    private static final List<Punctuation4a> COMMON_PUNCTUATION = new ArrayList<Punctuation4a>(25);
     static {
 
         COMMON_PUNCTUATION.add(COMMA);
@@ -131,6 +133,7 @@
         COMMON_PUNCTUATION.add(CLOSE_PAREN);
         COMMON_PUNCTUATION.add(OPEN_SQUARE_BRACKET);
         COMMON_PUNCTUATION.add(CLOSE_SQUARE_BRACKET);
+        COMMON_PUNCTUATION.add(ZERO_WIDTH_SPACE);
 
     }
 
@@ -219,26 +222,6 @@
     }
 
     @Override
-    public int getQtyParaNodeChildren() {
-        return 0;
-    }
-
-    @Override
-    public ParaNode getParaNodeChild(final int index) {
-        return null;
-    }
-
-    @Override
-    public ParaConfig getParaConfig() {
-        return null;
-    }
-
-    @Override
-    public void setParaConfig(final ParaConfig config) {
-        /* Nothing to do here. */
-    }
-
-    @Override
     public int length() {
         return this.content.length();
     }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java	2021-11-13 20:37:22 UTC (rev 12057)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java	2021-11-14 14:37:28 UTC (rev 12058)
@@ -35,7 +35,6 @@
 import org.axsl.common.para.ParaConfig;
 import org.axsl.common.para.ParaGlue;
 import org.axsl.common.para.ParaLeaf;
-import org.axsl.common.para.ParaNode;
 import org.axsl.common.para.ParaPenalty;
 import org.axsl.orthography.Whitespace;
 
@@ -165,26 +164,6 @@
     }
 
     @Override
-    public int getQtyParaNodeChildren() {
-        return 0;
-    }
-
-    @Override
-    public ParaNode getParaNodeChild(final int index) {
-        return null;
-    }
-
-    @Override
-    public ParaConfig getParaConfig() {
-        return null;
-    }
-
-    @Override
-    public void setParaConfig(final ParaConfig config) {
-        /* Nothing to do here. */
-    }
-
-    @Override
     public int length() {
         return this.content.length();
     }

Deleted: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/Interword4aTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/Interword4aTests.java	2021-11-13 20:37:22 UTC (rev 12057)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/Interword4aTests.java	2021-11-14 14:37:28 UTC (rev 12058)
@@ -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;
-
-import org.junit.Assert;
-import org.junit.Test;
-
-/**
- * Tests of {@link Interword4a}.
- */
-public class Interword4aTests {
-
-
-    /**
-     * Test of {@link Interword4a#findInstance(CharSequence)}.
-     */
-    @Test
-    public void findInstanceTest() {
-        final Interword4a instance = Interword4a.findInstance(" ");
-        Assert.assertEquals(" ", instance.getContent().toString());
-    }
-
-}

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

[FOray-commit] SF.net SVN: foray:[12057] trunk/foray/foray-unicode/src/main/java/org/ foray/unicode/UnicodeParser.java

[<vic...@us...>]

Revision: 12057
          http://sourceforge.net/p/foray/code/12057
Author:   victormote
Date:     2021-11-13 20:37:22 +0000 (Sat, 13 Nov 2021)
Log Message:
-----------
Add codepoint range to class javadocs.

Modified Paths:
--------------
    trunk/foray/foray-unicode/src/main/java/org/foray/unicode/UnicodeParser.java

Modified: trunk/foray/foray-unicode/src/main/java/org/foray/unicode/UnicodeParser.java
===================================================================
--- trunk/foray/foray-unicode/src/main/java/org/foray/unicode/UnicodeParser.java	2021-11-13 18:00:37 UTC (rev 12056)
+++ trunk/foray/foray-unicode/src/main/java/org/foray/unicode/UnicodeParser.java	2021-11-13 20:37:22 UTC (rev 12057)
@@ -43,6 +43,10 @@
 
 /**
  * Parser that reads the raw Unicode files that we care about and generates Java source code files.
+ * Since the Unicode source files are stored as data in this project, the following command-line example may be
+ * helpful:
+ * java -cp ...  UnicodeParser ./src/main/data/Unicode_13_0/UCD_zip "c:/Users/Victor Mote/desktop" "General Punctuation"
+ *
  */
 public class UnicodeParser {
 
@@ -120,7 +124,11 @@
             writer.write(eol);
             writer.write(" * Unicode(r) code points for the \"");
             writer.write(block.getName());
-            writer.write("\" block.");
+            writer.write("\" block (0x");
+            writer.write(Integer.toHexString(block.getStart()));
+            writer.write(" thru 0x");
+            writer.write(Integer.toHexString(block.getEnd()));
+            writer.write(").");
             writer.write(eol);
             writer.write(" * See package documentation for links to the Unicode(r) license and terms of use.");
             writer.write(eol);
@@ -315,6 +323,8 @@
      * <ol>
      *   <li>The directory containing the raw Unicode files.</li>
      *   <li>The directory into which the generated source code should be written.</li>
+     *   <li>Comma-delimited list of the code blocks to be generated. These code blocks must match those listed in
+     *   Blocks.txt in the Unicode distribution.
      * </ol>
      */
     public static void main(final String[] args) {

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

[FOray-commit] SF.net SVN: foray:[12056] trunk/foray/foray-orthography/src/main/java/org/ foray/orthography/SimpleDictionary.java

[<vic...@us...>]

Revision: 12056
          http://sourceforge.net/p/foray/code/12056
Author:   victormote
Date:     2021-11-13 18:00:37 +0000 (Sat, 13 Nov 2021)
Log Message:
-----------
Add simple dictionary implementation, primarily for testing, but perhaps useful  other places.

Added Paths:
-----------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/SimpleDictionary.java

Added: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/SimpleDictionary.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/SimpleDictionary.java	                        (rev 0)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/SimpleDictionary.java	2021-11-13 18:00:37 UTC (rev 12056)
@@ -0,0 +1,107 @@
+/*
+ * Copyright 2021 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;
+
+import org.axsl.orthography.Word;
+import org.axsl.orthography.Word.PartOfSpeech;
+import org.axsl.orthography.Word.PosQualifier;
+import org.axsl.orthography.optional.Dictionary;
+
+import java.util.HashMap;
+import java.util.Map;
+import java.util.regex.Pattern;
+
+/**
+ * A simple dictionary implementation, possibly useful only for testing.
+ */
+public class SimpleDictionary implements Dictionary {
+
+    /** Constant needed for serialization. */
+    private static final long serialVersionUID = 1797657088308334420L;
+
+    /** Regex pattern used to break compound words into their components. */
+    private Pattern wordBreaker;
+
+    /** The map of words. */
+    private Map<String, Word> words = new HashMap<String, Word>();
+
+    public SimpleDictionary(final char softHyphenChar) {
+        this.wordBreaker = Pattern.compile(Character.toString(softHyphenChar));
+    }
+
+    /**
+     * Add a word to this dictionary.
+     * @param wordChars The characters in the word, e.g. "running", "apple", etc.
+     * @param word The word.
+     */
+    public void addWord(final CharSequence wordChars, final Word word) {
+        final String wordString = wordChars.toString();
+        if (this.words.containsKey(wordString)) {
+            throw new IllegalArgumentException("Word already exists in dictionary: " + wordString);
+        }
+        this.words.put(wordString, word);
+    }
+
+    /**
+     * Add a word to this dictionary.
+     * @param wordChars The characters in the word, including raw hyphenation points, e.g. "run-ning", "ap-ple", etc.
+     */
+    public void addWord(final CharSequence wordChars) {
+        final char partsOfSpeech = 0;
+        final String[] components = this.wordBreaker.split(wordChars);
+        final StringWord word = new StringWord(partsOfSpeech, components);
+        final String wordString = word.getActualContent().toString();
+        if (this.words.containsKey(wordString)) {
+            throw new IllegalArgumentException("Word already exists in dictionary: " + wordString);
+        }
+        this.words.put(wordString, word);
+    }
+
+    @Override
+    public int qtyAlternatives(final CharSequence wordChars) {
+        if (this.words.containsKey(wordChars.toString())) {
+            return 1;
+        }
+        return 0;
+    }
+
+    @Override
+    public Word getWord(final CharSequence wordChars, final int index) {
+        if (index != 0) {
+            throw new IndexOutOfBoundsException("Index must be zero.");
+        }
+        return this.words.get(wordChars.toString());
+    }
+
+    @Override
+    public boolean supportsQualifiedType(final PartOfSpeech arg0, final PosQualifier arg1) {
+        return false;
+    }
+
+}


Property changes on: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/SimpleDictionary.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:[12055] trunk/foray/foray-linebreak/src/test/java/org/ foray/linebreak

[<vic...@us...>]

Revision: 12055
          http://sourceforge.net/p/foray/code/12055
Author:   victormote
Date:     2021-11-13 17:58:04 +0000 (Sat, 13 Nov 2021)
Log Message:
-----------
Simplify line-break testing by removing dependency on orthography tokenizing.

Modified Paths:
--------------
    trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java

Added Paths:
-----------
    trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/ParaBranch4aTestFixture.java

Added: trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/ParaBranch4aTestFixture.java
===================================================================
--- trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/ParaBranch4aTestFixture.java	                        (rev 0)
+++ trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/ParaBranch4aTestFixture.java	2021-11-13 17:58:04 UTC (rev 12055)
@@ -0,0 +1,83 @@
+/*
+ * Copyright 2021 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.linebreak;
+
+import org.foray.common.para.ParaBranch4a;
+import org.foray.orthography.StringWord;
+import org.foray.orthography.Whitespace4a;
+
+import org.axsl.common.para.ParaConfig;
+import org.axsl.common.para.ParaNode;
+
+import java.util.regex.Pattern;
+
+/**
+ * Adds some methods that simplify and clarify some tests.
+ */
+public class ParaBranch4aTestFixture extends ParaBranch4a {
+
+    /** Regex pattern used to break compound words into their components. */
+    private Pattern wordBreaker;
+
+    /**
+     * Constructor.
+     * @param config The configuration information for this branch.
+     * @param softHyphenChar The character used to mark syllable breaks.
+     */
+    public ParaBranch4aTestFixture(final ParaConfig config, final char softHyphenChar) {
+        super(config);
+        this.wordBreaker = Pattern.compile(Character.toString(softHyphenChar));
+    }
+
+    /**
+     * Add a word and space to this dictionary.
+     * @param wordChars The characters in the word, including raw hyphenation points, e.g. "run-ning", "ap-ple", etc.
+     */
+    public void addWordAndSpace(final CharSequence wordChars) {
+        addWord(wordChars);
+        this.add(Whitespace4a.SPACE);
+    }
+
+    /**
+     * Add a word and space to this dictionary.
+     * @param wordChars The characters in the word, including raw hyphenation points, e.g. "run-ning", "ap-ple", etc.
+     */
+    public void addWord(final CharSequence wordChars) {
+        final char partsOfSpeech = 0;
+        final String[] components = this.wordBreaker.split(wordChars);
+        final StringWord word = new StringWord(partsOfSpeech, components);
+        this.add(word);
+    }
+
+    public void addNodeAndSpace(final ParaNode node) {
+        this.add(node);
+        this.add(Whitespace4a.SPACE);
+    }
+
+}


Property changes on: trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/ParaBranch4aTestFixture.java
___________________________________________________________________
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Rev
\ No newline at end of property
Modified: trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java
===================================================================
--- trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java	2021-11-13 17:50:31 UTC (rev 12054)
+++ trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java	2021-11-13 17:58:04 UTC (rev 12055)
@@ -32,10 +32,7 @@
 import org.foray.common.i18n.WritingSystem4a;
 import org.foray.common.para.ParaBranch4a;
 import org.foray.common.para.ParaConfig4a;
-import org.foray.orthography.Orthography4a;
-import org.foray.orthography.OrthographyServer4a;
-import org.foray.orthography.OrthographyServerConfig;
-import org.foray.orthography.StringWord;
+import org.foray.orthography.Punctuation4a;
 
 import org.axsl.common.para.DiscretionaryHyphen;
 import org.axsl.common.para.ParaConfig;
@@ -44,14 +41,11 @@
 import org.axsl.font.FontUse;
 import org.axsl.linebreak.LineBreakControl;
 import org.axsl.linebreak.OutputLine;
-import org.axsl.orthography.OrthographyException;
 
 import org.junit.Assert;
-import org.junit.Before;
 import org.junit.Test;
 import org.mockito.Mockito;
 
-import java.io.IOException;
 import java.util.ArrayList;
 import java.util.List;
 
@@ -66,32 +60,167 @@
     public static final String TEST_STRING_01 =
             "In olden times when wishing still helped one, there lived a king " +
             "whose daughters were all beautiful; and the youngest was so beautiful that the sun itself, which has " +
-            "seen so much, was astonished whenever it shone in her face. Close by the king\u2019s castle lay a great " +
+            "seen so much, was astonished whenever it shone in her face. Close by the king’s castle lay a great " +
             "dark forest, and under an old lime-tree in the forest was a well, and when the day was very warm, the " +
-            "king\u2019s child went out into the forest and sat down by the side of the cool fountain; and when she " +
+            "king’s child went out into the forest and sat down by the side of the cool fountain; and when she " +
             "was bored she took a golden ball, and threw it up on high and caught it; and this ball was her favorite " +
             "plaything.";
 
-    /** The orthography server doing the basic parsing. */
-    private OrthographyServer4a orthographyServer;
-
-    /** The paragraph configuration to be used for these tests. */
-    private ParaConfig paraConfig;
-
     /**
-     * Setup the test.
-     * @throws IOException For errors creating the URLs to the various resources.
-     * @throws OrthographyException For errors creating a hyphenation server.
+     * Creates the tokenized content of {@link #TEST_STRING_01}.
+     * We could use the orthography system to build this, but the line-breaking logic is independent of that, so we
+     * manually build it in this method.
+     * @return The tokenized content of {@link #TEST_STRING_01}.
      */
-    @Before
-    public void setup() throws IOException, OrthographyException {
-        final OrthographyServerConfig config = LbTestUtilities.createHyphenationServerConfig();
-        this.orthographyServer = new OrthographyServer4a(config);
+    private ParaBranch4a createPara() {
+        final ParaBranch4aTestFixture para = new ParaBranch4aTestFixture(null, '-');
+        para.addWordAndSpace("In");
+        para.addWordAndSpace("olden");
+        para.addWordAndSpace("times");
+        para.addWordAndSpace("when");
+        para.addWordAndSpace("wish-ing");               // 2 segments
+        para.addWordAndSpace("still");
+        para.addWordAndSpace("helped");
+        para.addWord("one");
+        para.addNodeAndSpace(Punctuation4a.COMMA);
+        para.addWordAndSpace("there");
+        para.addWordAndSpace("lived");
+        para.addWordAndSpace("a");
+        para.addWordAndSpace("king");
+        para.addWordAndSpace("whose");
+        para.addWordAndSpace("daugh-ters");             // 2 segments
+        para.addWordAndSpace("were");
+        para.addWordAndSpace("all");
+        para.addWord("beau-ti-ful");                    // 3 segments
+        para.addNodeAndSpace(Punctuation4a.SEMICOLON);
+        para.addWordAndSpace("and");
+        para.addWordAndSpace("the");
+        para.addWordAndSpace("young-est");              // 2 segments
+        para.addWordAndSpace("was");
+        para.addWordAndSpace("so");
+        para.addWordAndSpace("beau-ti-ful");            // 3 segments
+        para.addWordAndSpace("that");
+        para.addWordAndSpace("the");
+        para.addWordAndSpace("sun");
+        para.addWord("it-self");                        // 2 segments
+        para.addNodeAndSpace(Punctuation4a.COMMA);
+        para.addWordAndSpace("which");
+        para.addWordAndSpace("has");
+        para.addWordAndSpace("seen");
+        para.addWordAndSpace("so");
+        para.addWord("much");
+        para.addNodeAndSpace(Punctuation4a.COMMA);
+        para.addWordAndSpace("was");
+        para.addWordAndSpace("aston-ished");            // 2 segments
+        para.addWordAndSpace("when-ever");
+        para.addWordAndSpace("it");
+        para.addWordAndSpace("shone");
+        para.addWordAndSpace("in");
+        para.addWordAndSpace("her");
+        para.addWord("face");
+        para.addNodeAndSpace(Punctuation4a.PERIOD);
+        para.addWordAndSpace("Close");
+        para.addWordAndSpace("by");
+        para.addWordAndSpace("the");
+        para.addWordAndSpace("king’s");
+        para.addWordAndSpace("castle");
+        para.addWordAndSpace("lay");
+        para.addWordAndSpace("a");
+        para.addWordAndSpace("great");
+        para.addWordAndSpace("dark");
+        para.addWord("for-est");                        // 2 segments
+        para.addNodeAndSpace(Punctuation4a.COMMA);
+        para.addWordAndSpace("and");
+        para.addWordAndSpace("un-der");                 // 2 segments
+        para.addWordAndSpace("an");
+        para.addWordAndSpace("old");
+        para.addWord("lime");
+        para.add(Punctuation4a.MANDATORY_HYPHEN);
+        para.addWordAndSpace("tree");
+        para.addWordAndSpace("in");
+        para.addWordAndSpace("the");
+        para.addWordAndSpace("for-est");                // 2 segments
+        para.addWordAndSpace("was");
+        para.addWordAndSpace("a");
+        para.addWord("well");
+        para.addNodeAndSpace(Punctuation4a.COMMA);
+        para.addWordAndSpace("and");
+        para.addWordAndSpace("when");
+        para.addWordAndSpace("the");
+        para.addWordAndSpace("day");
+        para.addWordAndSpace("was");
+        para.addWordAndSpace("very");
+        para.addWord("warm");
+        para.addNodeAndSpace(Punctuation4a.COMMA);
+        para.addWordAndSpace("the");
+        para.addWordAndSpace("king’s");
+        para.addWordAndSpace("child");
+        para.addWordAndSpace("went");
+        para.addWordAndSpace("out");
+        para.addWordAndSpace("into");
+        para.addWordAndSpace("the");
+        para.addWordAndSpace("for-est");                // 2 segments
+        para.addWordAndSpace("and");
+        para.addWordAndSpace("sat");
+        para.addWordAndSpace("down");
+        para.addWordAndSpace("by");
+        para.addWordAndSpace("the");
+        para.addWordAndSpace("side");
+        para.addWordAndSpace("of");
+        para.addWordAndSpace("the");
+        para.addWordAndSpace("cool");
+        para.addWord("foun-tain");                      // 2 segments
+        para.addNodeAndSpace(Punctuation4a.SEMICOLON);
+        para.addWordAndSpace("and");
+        para.addWordAndSpace("when");
+        para.addWordAndSpace("she");
+        para.addWordAndSpace("was");
+        para.addWordAndSpace("bored");
+        para.addWordAndSpace("she");
+        para.addWordAndSpace("took");
+        para.addWordAndSpace("a");
+        para.addWordAndSpace("golden");
+        para.addWord("ball");
+        para.addNodeAndSpace(Punctuation4a.COMMA);
+        para.addWordAndSpace("and");
+        para.addWordAndSpace("threw");
+        para.addWordAndSpace("it");
+        para.addWordAndSpace("up");
+        para.addWordAndSpace("on");
+        para.addWordAndSpace("high");
+        para.addWordAndSpace("and");
+        para.addWordAndSpace("caught");
+        para.addWord("it;");
+        para.addNodeAndSpace(Punctuation4a.SEMICOLON);
+        para.addWordAndSpace("and");
+        para.addWordAndSpace("this");
+        para.addWordAndSpace("ball");
+        para.addWordAndSpace("was");
+        para.addWordAndSpace("her");
+        para.addWordAndSpace("favor-ite");              // 2 segments
+        para.addWordAndSpace("play-thing");             // 2 segments
+        para.add(Punctuation4a.PERIOD);
 
         final Font font = LbTestUtilities.createMonotypeFont();
         final FontUse fontUse = Mockito.mock(FontUse.class);
         Mockito.when(fontUse.getFont()).thenReturn(font);
-        this.paraConfig = new ParaConfig4a(fontUse, 10, WritingSystem4a.USA, 0, 0);
+        final ParaConfig paraConfig = new ParaConfig4a(fontUse, 10, WritingSystem4a.USA, 0, 0);
+        para.setParaConfig(paraConfig);
+
+        /* The tokenized text treated "’s" as part of the attached word.
+         * The compound word "lime-tree" was treated as two words divided by punctuation.
+         * There are 126 lines of code creating the para.
+         *                             Count     Nodes
+         *   addWord                      12        12
+         *   addNodeAndSpace              11        22
+         *   add                           2         2
+         *   addWordAndSpace (forced)    101       202
+         *                             -----     -----
+         *   totals                      126       238
+         *                             =====     =====  */
+
+        Assert.assertEquals(238, para.getQtyParaNodeChildren());
+        return para;
     }
 
     /**
@@ -100,24 +229,8 @@
     @Test
     public void bestFitTest1() {
         /* TODO: THE CLASS BEING TESTED IS VERY INCOMPLETE, AND SO IS THIS TEST !!!!!! */
-        final Orthography4a orthography = this.orthographyServer.getOrthography(WritingSystem4a.USA);
 
-        final ParaBranch4a paragraph =
-                orthography.tokenizeWordSequence(TEST_STRING_01, 0, TEST_STRING_01.length());
-        paragraph.setParaConfig(paraConfig);
-
-        /* Make manual changes to get the paragraph features identical to our baseline paragraph, as documented
-         * in the Knuth-Plass article. These are all cases where the native hyphenation opportunies violate the
-         * "leave at least 2, and push at least 3" general rule. */
-        paragraph.setParaNodeChild(2, new StringWord(0, "olden"));                 // Native = old-en
-        paragraph.setParaNodeChild(66, new StringWord(0, "aston", "ished"));       // Native = as-ton-ish-ed
-        paragraph.setParaNodeChild(68, new StringWord(0, "when", "ever"));         // Native = when-ev-er
-        paragraph.setParaNodeChild(88, new StringWord(0, "castle"));               // Native = cas-tle
-        paragraph.setParaNodeChild(134,  new StringWord(0, "very"));               // Native = ver-y
-        paragraph.setParaNodeChild(148, new StringWord(0, "into"));                // Native = in-to
-        paragraph.setParaNodeChild(190,  new StringWord(0, "golden"));             // Native = gold-en
-        paragraph.setParaNodeChild(222, new StringWord(0, "favor", "ite"));        // Native = fa-vor-ite
-
+        final ParaBranch4a content = this.createPara();
         final LineBreakControl lbControl = Mockito.mock(LineBreakControl.class);
         final OutputLine lineOutput = Mockito.mock(OutputLine.class);
         /* Page is 8.5 inches wide, 1 inch margin on both ends, leaving 6.5 inches, or 468,000 millipoints. */
@@ -126,19 +239,12 @@
         final ParaControl paraControl = Mockito.mock(ParaControl.class);
         Mockito.when(paraControl.getCost(Mockito.any(DiscretionaryHyphen.Quality.class))).thenReturn(50);
         final TotalFitLb out = new TotalFitLb();
-        final List<OrderedTreePath4a> actual = out.breakIntoLines(paragraph, paraControl, lbControl);
+        final List<OrderedTreePath4a> actual = out.breakIntoLines(content, paraControl, lbControl);
 
-        /* For now, treat "’s" as interword content of an apostrophe, followed by a 1-syllable word. */
-        /* Words: 98 1-syllable, 13 2-syllable, 2 3-syllable, total of 114 words
-         * 98 x 2 = 196, 13 x 4 = 52, 2 x 6 = 12, subtotal of 260 nodes.
-         * Special Interword: 11 normal, 2 "’s", 1 ="-", 1 terminating period (no space after).
-         * 11 x 2 = 22, 2 x 3 = 6, 1 x 1 = 1, 1 x 1 = 1, subtotal of 30 nodes.
-         * Grand total of 290 nodes. */
-//        Assert.assertEquals(290, out.getContentNodes().size());
 
         final List<OrderedTreePath4a> expected = new ArrayList<OrderedTreePath4a>();
-//        final int[] expectedArray = {};
-//        expected.add(new OrderedTreePath4a(new IntArray(expectedArray)));
+////        final int[] expectedArray = {};
+////        expected.add(new OrderedTreePath4a(new IntArray(expectedArray)));
         Assert.assertArrayEquals(expected.toArray(), actual.toArray());
     }
 

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

[FOray-commit] SF.net SVN: foray:[12054] trunk/foray/foray-orthography/src/main/java/org/ foray/orthography

[<vic...@us...>]

Revision: 12054
          http://sourceforge.net/p/foray/code/12054
Author:   victormote
Date:     2021-11-13 17:50:31 +0000 (Sat, 13 Nov 2021)
Log Message:
-----------
Make interword constants public.

Modified Paths:
--------------
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java	2021-11-13 13:41:48 UTC (rev 12053)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java	2021-11-13 17:50:31 UTC (rev 12054)
@@ -51,61 +51,61 @@
 public final class Punctuation4a implements Punctuation, ParaLeaf, ParaBox {
 
     /** Common punctuation item, a comma. */
-    private static final Punctuation4a COMMA = new Punctuation4a(",");
+    public static final Punctuation4a COMMA = new Punctuation4a(",");
 
     /** Common punctuation item, semicolon. */
-    private static final Punctuation4a SEMICOLON = new Punctuation4a(";");
+    public static final Punctuation4a SEMICOLON = new Punctuation4a(";");
 
     /** Common punctuation item, a colon. */
-    private static final Punctuation4a COLON = new Punctuation4a(":");
+    public static final Punctuation4a COLON = new Punctuation4a(":");
 
     /** Common punctuation item, period. */
-    private static final Punctuation4a PERIOD = new Punctuation4a(".");
+    public static final Punctuation4a PERIOD = new Punctuation4a(".");
 
     /** Common punctuation item, a question mark. */
-    private static final Punctuation4a QUESTION = new Punctuation4a("?");
+    public static final Punctuation4a QUESTION = new Punctuation4a("?");
 
     /** Common punctuation item, an exclamation point. */
-    private static final Punctuation4a EXCLAMATION = new Punctuation4a("!");
+    public static final Punctuation4a EXCLAMATION = new Punctuation4a("!");
 
     /** Common punctuation item, a closing single quote or apostrophe. TODO: This needs to be treated differently. */
-    private static final Punctuation4a SINGLE_QUOTE = new Punctuation4a("\'");
+    public static final Punctuation4a SINGLE_QUOTE = new Punctuation4a("\'");
 
     /** Common punctuation item, a closing single quote or apostrophe. TODO: This needs to be treated differently. */
-    private static final Punctuation4a DOUBLE_QUOTE = new Punctuation4a("\"");
+    public static final Punctuation4a DOUBLE_QUOTE = new Punctuation4a("\"");
 
     /** Common punctuation item, an opening typographical single quote or apostrophe. */
-    private static final Punctuation4a OPEN_TYPO_SINGLE_QUOTE = new Punctuation4a("\u2018");
+    public static final Punctuation4a OPEN_TYPO_SINGLE_QUOTE = new Punctuation4a("\u2018");
 
     /** Common punctuation item, a closing typographical single quote. */
-    private static final Punctuation4a CLOSE_TYPO_SINGLE_QUOTE = new Punctuation4a("\u2019");
+    public static final Punctuation4a CLOSE_TYPO_SINGLE_QUOTE = new Punctuation4a("\u2019");
 
     /** Common punctuation item, an opening typographical double quote. */
-    private static final Punctuation4a OPEN_TYPO_DOUBLE_QUOTE = new Punctuation4a("\u201C");
+    public static final Punctuation4a OPEN_TYPO_DOUBLE_QUOTE = new Punctuation4a("\u201C");
 
     /** Common punctuation item, a closing typographical double quote. */
-    private static final Punctuation4a CLOSE_TYPO_DOUBLE_QUOTE = new Punctuation4a("\u201D");
+    public static final Punctuation4a CLOSE_TYPO_DOUBLE_QUOTE = new Punctuation4a("\u201D");
 
     /** Common punctuation item. */
-    private static final Punctuation4a MANDATORY_HYPHEN = new Punctuation4a("-");
+    public static final Punctuation4a MANDATORY_HYPHEN = new Punctuation4a("-");
 
     /** Common punctuation item. */
-    private static final Punctuation4a EN_DASH = new Punctuation4a("\u2013");
+    public static final Punctuation4a EN_DASH = new Punctuation4a("\u2013");
 
     /** Common punctuation item. */
-    private static final Punctuation4a EM_DASH = new Punctuation4a("\u2014");
+    public static final Punctuation4a EM_DASH = new Punctuation4a("\u2014");
 
     /** Common punctuation item. */
-    private static final Punctuation4a OPEN_PAREN = new Punctuation4a("(");
+    public static final Punctuation4a OPEN_PAREN = new Punctuation4a("(");
 
     /** Common punctuation item. */
-    private static final Punctuation4a CLOSE_PAREN = new Punctuation4a(")");
+    public static final Punctuation4a CLOSE_PAREN = new Punctuation4a(")");
 
     /** Common punctuation item. */
-    private static final Punctuation4a OPEN_SQUARE_BRACKET = new Punctuation4a("[");
+    public static final Punctuation4a OPEN_SQUARE_BRACKET = new Punctuation4a("[");
 
     /** Common punctuation item. */
-    private static final Punctuation4a CLOSE_SQUARE_BRACKET = new Punctuation4a("]");
+    public static final Punctuation4a CLOSE_SQUARE_BRACKET = new Punctuation4a("]");
 
 
     /** The list of common interword items. */

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java	2021-11-13 13:41:48 UTC (rev 12053)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java	2021-11-13 17:50:31 UTC (rev 12054)
@@ -51,19 +51,19 @@
 public final class Whitespace4a implements Whitespace, ParaLeaf, ParaGlue {
 
     /** Common whitespace item. */
-    private static final Whitespace4a SPACE = new Whitespace4a(" ");
+    public static final Whitespace4a SPACE = new Whitespace4a(" ");
 
     /** Common whitespace item. */
-    private static final Whitespace4a LINE_FEED = new Whitespace4a("\n");
+    public static final Whitespace4a LINE_FEED = new Whitespace4a("\n");
 
     /** Common whitespace item. */
-    private static final Whitespace4a CARRIAGE_RETURN_AND_LINE_FEED = new Whitespace4a("\r\n");
+    public static final Whitespace4a CARRIAGE_RETURN_AND_LINE_FEED = new Whitespace4a("\r\n");
 
     /** Common whitespace item. */
-    private static final Whitespace4a CARRIAGE_RETURN = new Whitespace4a("\r");
+    public static final Whitespace4a CARRIAGE_RETURN = new Whitespace4a("\r");
 
     /** Common whitespace item. */
-    private static final Whitespace4a TAB = new Whitespace4a("\t");
+    public static final Whitespace4a TAB = new Whitespace4a("\t");
 
     /** The list of common whitespace items. */
     private static final List<Whitespace4a> COMMON_WHITESPACE = new ArrayList<Whitespace4a>(20);

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

[FOray-commit] SF.net SVN: foray:[12053] trunk/foray

[<vic...@us...>]

Revision: 12053
          http://sourceforge.net/p/foray/code/12053
Author:   victormote
Date:     2021-11-13 13:41:48 +0000 (Sat, 13 Nov 2021)
Log Message:
-----------
Conform to aXSL changes: Move management of the paragraph config, a layout issue, out of Orthography.

Modified Paths:
--------------
    trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaBranch4a.java
    trunk/foray/foray-fotree/src/main/java/org/foray/fotree/fo/obj/FoWordSequence.java
    trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Interword4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java
    trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Word4a.java
    trunk/foray/foray-orthography/src/test/java/org/foray/orthography/HyphenationConsumer4aTests.java

Modified: trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaBranch4a.java
===================================================================
--- trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaBranch4a.java	2021-11-13 12:37:41 UTC (rev 12052)
+++ trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaBranch4a.java	2021-11-13 13:41:48 UTC (rev 12053)
@@ -108,4 +108,9 @@
         this.nodes.set(index, newNode);
     }
 
+    @Override
+    public void setParaConfig(final ParaConfig config) {
+        this.config = config;
+    }
+
 }

Modified: trunk/foray/foray-fotree/src/main/java/org/foray/fotree/fo/obj/FoWordSequence.java
===================================================================
--- trunk/foray/foray-fotree/src/main/java/org/foray/fotree/fo/obj/FoWordSequence.java	2021-11-13 12:37:41 UTC (rev 12052)
+++ trunk/foray/foray-fotree/src/main/java/org/foray/fotree/fo/obj/FoWordSequence.java	2021-11-13 13:41:48 UTC (rev 12053)
@@ -59,11 +59,12 @@
     public FoWordSequence(final FoObj parent, final CharSequence content) {
         super(parent);
         final OrthographyServer orthographyServer = getOrthographyServer();
+        final Orthography orthography = orthographyServer.getOrthography(getWritingSystem());
+        final ParaBranch wordSequence =
+                orthography.tokenizeWordSequence(content, 0, content.length());
         final ParaConfig4a config = new ParaConfig4a(getPrimaryFont(null), inlineFontSize(), inlineWritingSystem(),
                 parent.traitWordSpacingMax(null), parent.traitWordSpacingMin(null));
-        final Orthography orthography = orthographyServer.getOrthography(getWritingSystem());
-        final ParaBranch wordSequence =
-                orthography.parseWordSequence(content, 0, content.length(), config);
+        wordSequence.setParaConfig(config);
         this.content = new ArrayList<FoWordSequenceContent>(wordSequence.getQtyParaNodeChildren());
         for (int index = 0; index < wordSequence.getQtyParaNodeChildren(); index ++) {
             final ParaNode wordSequenceContent = wordSequence.getParaNodeChild(index);

Modified: trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java
===================================================================
--- trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java	2021-11-13 12:37:41 UTC (rev 12052)
+++ trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java	2021-11-13 13:41:48 UTC (rev 12053)
@@ -60,7 +60,9 @@
  */
 public class TotalFitLbTests {
 
-    /** A string used for testing line-breaking. */
+    /** A string used for testing line-breaking. This example is used in Knuth, "Digital Typography," 1999, Chapter 3,
+     * "Breaking Paragraphs into Lines," p. 74 et seq. Knuth cites his source as "Grimm's Fairy Tales." By using an
+     * example directly from the book, we hope to get some independent expected results. */
     public static final String TEST_STRING_01 =
             "In olden times when wishing still helped one, there lived a king " +
             "whose daughters were all beautiful; and the youngest was so beautiful that the sun itself, which has " +
@@ -101,7 +103,8 @@
         final Orthography4a orthography = this.orthographyServer.getOrthography(WritingSystem4a.USA);
 
         final ParaBranch4a paragraph =
-                orthography.parseWordSequence(TEST_STRING_01, 0, TEST_STRING_01.length(), paraConfig);
+                orthography.tokenizeWordSequence(TEST_STRING_01, 0, TEST_STRING_01.length());
+        paragraph.setParaConfig(paraConfig);
 
         /* Make manual changes to get the paragraph features identical to our baseline paragraph, as documented
          * in the Knuth-Plass article. These are all cases where the native hyphenation opportunies violate the

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Interword4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Interword4a.java	2021-11-13 12:37:41 UTC (rev 12052)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Interword4a.java	2021-11-13 13:41:48 UTC (rev 12053)
@@ -303,6 +303,11 @@
     }
 
     @Override
+    public void setParaConfig(final ParaConfig config) {
+        /* Nothing to do here. */
+    }
+
+    @Override
     public Type getParaNodeType() {
         return ParaNode.Type.BRANCH;
     }

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	2021-11-13 12:37:41 UTC (rev 12052)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Orthography4a.java	2021-11-13 13:41:48 UTC (rev 12053)
@@ -37,7 +37,6 @@
 import org.foray.orthography.wrapper.ExactWord;
 import org.foray.orthography.wrapper.UppercaseWord;
 
-import org.axsl.common.para.ParaConfig;
 import org.axsl.orthography.Orthography;
 import org.axsl.orthography.Word;
 import org.axsl.orthography.optional.Dictionary;
@@ -407,9 +406,8 @@
     }
 
     @Override
-    public ParaBranch4a parseWordSequence(final CharSequence characters, final int startIndex, final int length,
-            final ParaConfig paraConfig) {
-        final ParaBranch4a wordSequence = new ParaBranch4a(paraConfig);
+    public ParaBranch4a tokenizeWordSequence(final CharSequence characters, final int startIndex, final int length) {
+        final ParaBranch4a wordSequence = new ParaBranch4a(null);
         final CharSequence sequence = characters.subSequence(startIndex, startIndex + length);
         final List<CharSequence> chunks = this.lexer.tokenize(sequence);
 

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java	2021-11-13 12:37:41 UTC (rev 12052)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Punctuation4a.java	2021-11-13 13:41:48 UTC (rev 12053)
@@ -234,6 +234,11 @@
     }
 
     @Override
+    public void setParaConfig(final ParaConfig config) {
+        /* Nothing to do here. */
+    }
+
+    @Override
     public int length() {
         return this.content.length();
     }

Modified: trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java
===================================================================
--- trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java	2021-11-13 12:37:41 UTC (rev 12052)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Whitespace4a.java	2021-11-13 13:41:48 UTC (rev 12053)
@@ -180,6 +180,11 @@
     }
 
     @Override
+    public void setParaConfig(final ParaConfig config) {
+        /* Nothing to do here. */
+    }
+
+    @Override
     public int length() {
         return this.content.length();
     }

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	2021-11-13 12:37:41 UTC (rev 12052)
+++ trunk/foray/foray-orthography/src/main/java/org/foray/orthography/Word4a.java	2021-11-13 13:41:48 UTC (rev 12053)
@@ -221,6 +221,11 @@
         return null;
     }
 
+    @Override
+    public void setParaConfig(final ParaConfig config) {
+        /* Nothing to do here. */
+    }
+
     /**
      * Returns the index (from a {@link CharSequence} standpoint) to the first character of a given segment.
      * For example, for the word phi-los-o-phy, getSegmentStart(1) should return the index to the second segment

Modified: trunk/foray/foray-orthography/src/test/java/org/foray/orthography/HyphenationConsumer4aTests.java
===================================================================
--- trunk/foray/foray-orthography/src/test/java/org/foray/orthography/HyphenationConsumer4aTests.java	2021-11-13 12:37:41 UTC (rev 12052)
+++ trunk/foray/foray-orthography/src/test/java/org/foray/orthography/HyphenationConsumer4aTests.java	2021-11-13 13:41:48 UTC (rev 12053)
@@ -30,7 +30,6 @@
 
 import org.foray.common.i18n.WritingSystem4a;
 import org.foray.common.para.ParaBranch4a;
-import org.foray.common.para.ParaConfig4a;
 
 import org.axsl.common.para.ParaConfig;
 import org.axsl.orthography.OrthographyException;
@@ -51,9 +50,6 @@
     /** The hyphenation server used in these tests. */
     private static OrthographyServer4a server;
 
-    /** The paragraph configuration that should be used in these tests. */
-    private static ParaConfig paraConfig = new ParaConfig4a(null, 0, WritingSystem4a.USA, 0, 0);
-
     /** The object under test. */
     private Orthography4a consumer;
 
@@ -86,7 +82,7 @@
         /* Spoken by Henry, Henry V, Act III Scene 1. */
         final String testString = "Once more unto the breach, dear friends, once more;";
         final ParaBranch4a wordSequence =
-                this.consumer.parseWordSequence(testString, 0, testString.length(), paraConfig);
+                this.consumer.tokenizeWordSequence(testString, 0, testString.length());
         Assert.assertEquals(20,        wordSequence.getQtyParaNodeChildren());
         Assert.assertEquals("Once",    wordSequence.getParaNodeChild(0).toString());
         Assert.assertEquals(" ",       wordSequence.getParaNodeChild(1).toString());

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

[FOray-commit] SF.net SVN: foray:[12052] trunk/foray

[<vic...@us...>]

Revision: 12052
          http://sourceforge.net/p/foray/code/12052
Author:   victormote
Date:     2021-11-13 12:37:41 +0000 (Sat, 13 Nov 2021)
Log Message:
-----------
Conform to aXSL change: Remove writing system info from ParaConfig. Writing system and orthography issues have all been resolved prior to paragraph layout.

Modified Paths:
--------------
    trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaConfig4a.java
    trunk/foray/foray-fotree/src/main/java/org/foray/fotree/FoObj.java
    trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java

Modified: trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaConfig4a.java
===================================================================
--- trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaConfig4a.java	2021-11-12 18:37:54 UTC (rev 12051)
+++ trunk/foray/foray-common/src/main/java/org/foray/common/para/ParaConfig4a.java	2021-11-13 12:37:41 UTC (rev 12052)
@@ -95,11 +95,6 @@
     }
 
     @Override
-    public WritingSystem getWritingSystem() {
-        return this.orthography;
-    }
-
-    @Override
     public int getHyphenCharacterWidth() {
         return this.fontUse.width(this.hyphenationCharacter, this.fontSize);
     }

Modified: trunk/foray/foray-fotree/src/main/java/org/foray/fotree/FoObj.java
===================================================================
--- trunk/foray/foray-fotree/src/main/java/org/foray/fotree/FoObj.java	2021-11-12 18:37:54 UTC (rev 12051)
+++ trunk/foray/foray-fotree/src/main/java/org/foray/fotree/FoObj.java	2021-11-13 12:37:41 UTC (rev 12052)
@@ -3919,7 +3919,10 @@
         return fontUse.width(hyphenationCodePoint, traitFontSize(null));
     }
 
-    @Override
+    /**
+     * Returns the writing system for this FO.
+     * @return The writing system for this FO.
+     */
     public WritingSystem getWritingSystem() {
         final Language4a language = this.traitLanguage(null);
         final Country4a country = this.traitCountry(null);

Modified: trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java
===================================================================
--- trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java	2021-11-12 18:37:54 UTC (rev 12051)
+++ trunk/foray/foray-linebreak/src/test/java/org/foray/linebreak/TotalFitLbTests.java	2021-11-13 12:37:41 UTC (rev 12052)
@@ -98,7 +98,7 @@
     @Test
     public void bestFitTest1() {
         /* TODO: THE CLASS BEING TESTED IS VERY INCOMPLETE, AND SO IS THIS TEST !!!!!! */
-        final Orthography4a orthography = this.orthographyServer.getOrthography(this.paraConfig.getWritingSystem());
+        final Orthography4a orthography = this.orthographyServer.getOrthography(WritingSystem4a.USA);
 
         final ParaBranch4a paragraph =
                 orthography.parseWordSequence(TEST_STRING_01, 0, TEST_STRING_01.length(), paraConfig);

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