Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[3698] trunk/components-ext
|
From: <chr...@us...> - 2012-05-09 15:28:37
|
Revision: 3698
http://dl-learner.svn.sourceforge.net/dl-learner/?rev=3698&view=rev
Author: christinaunger
Date: 2012-05-09 15:28:25 +0000 (Wed, 09 May 2012)
Log Message:
-----------
[tbsl] repaired parser/templator shortcomings (and probably broke something else ;)
Modified Paths:
--------------
trunk/components-ext/pom.xml
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/ltag/parser/Preprocessor.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_Parser.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_Parser.jj
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_ParserConstants.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_ParserTokenManager.java
trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/templator/BasicSlotBuilder.java
trunk/components-ext/src/main/resources/tbsl/lexicon/basic_english.lex
Added Paths:
-----------
trunk/components-ext/src/main/javacc/
trunk/components-ext/src/main/javacc/DRSParser.jj
trunk/components-ext/src/main/javacc/DUDE_Parser.jj
trunk/components-ext/src/main/javacc/LTAG_Parser.jj
Modified: trunk/components-ext/pom.xml
===================================================================
--- trunk/components-ext/pom.xml 2012-05-08 11:53:28 UTC (rev 3697)
+++ trunk/components-ext/pom.xml 2012-05-09 15:28:25 UTC (rev 3698)
@@ -165,7 +165,22 @@
</dependencies>
<build>
<plugins>
+ <!--
<plugin>
+ <groupId>org.codehaus.mojo</groupId>
+ <artifactId>javacc-maven-plugin</artifactId>
+ <version>2.6</version>
+ <executions>
+ <execution>
+ <id>javacc</id>
+ <goals>
+ <goal>javacc</goal>
+ </goals>
+ </execution>
+ </executions>
+ </plugin>
+ -->
+ <plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<configuration>
Modified: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/ltag/parser/Preprocessor.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/ltag/parser/Preprocessor.java 2012-05-08 11:53:28 UTC (rev 3697)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/ltag/parser/Preprocessor.java 2012-05-09 15:28:25 UTC (rev 3698)
@@ -236,7 +236,7 @@
Pattern quotePattern2 = Pattern.compile("(``/``((.*)_)''/'')");
Pattern nnpPattern = Pattern.compile("\\s?((\\w+)/NNP[S]?\\s(\\w+))/NNP[S]?(\\W|$)");
Pattern nnPattern = Pattern.compile("\\s?((\\w+)/NN[S]?\\s(\\w+))/NN[S]?(\\W|$)");
- Pattern nnnnpPattern = Pattern.compile("\\s?((\\w+)/NNP[S]?)\\s(\\w+)/NN[S]?(\\W|$)");
+ Pattern nnnnpPattern = Pattern.compile("\\s?((\\w+)/NNP[S]?\\s(\\w+)/NN[S]?)(\\W|$)");
m = quotePattern1.matcher(flat);
while (m.find()) {
@@ -265,7 +265,7 @@
}
m = nnnnpPattern.matcher(flat);
while (m.find()) {
- flat = flat.replaceFirst(m.group(1),m.group(2) + "/JJ");
+ flat = flat.replaceFirst(m.group(1),m.group(2) + "_" + m.group(3) + "/NNP" + m.group(4));
m = nnnnpPattern.matcher(flat);
}
Modified: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_Parser.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_Parser.java 2012-05-08 11:53:28 UTC (rev 3697)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_Parser.java 2012-05-09 15:28:25 UTC (rev 3698)
@@ -209,7 +209,7 @@
jj_consume_token(2);
referent = dr();
jj_consume_token(2);
- word = jj_consume_token(WORD);
+ word = word();
jj_consume_token(2);
type = Type();
jj_consume_token(8);
@@ -237,7 +237,7 @@
type.setResultType(result);
{if (true) return type;}
} else if (jj_2_15(2)) {
- word = jj_consume_token(WORD);
+ word = word();
ElementaryType type=null;
if (word.toString().equals("e"))
type = new ElementaryType(ElemType.e);
@@ -344,7 +344,7 @@
DRS drs1;
DRS drs2;
if (jj_2_29(2)) {
- predicate = jj_consume_token(WORD);
+ predicate = word();
jj_consume_token(10);
dr_list = DR_List();
jj_consume_token(8);
@@ -476,9 +476,9 @@
Token type;
SlotType slottype = null;
List<String> words = null;
- ref = jj_consume_token(WORD);
+ ref = word();
jj_consume_token(14);
- type = jj_consume_token(WORD);
+ type = word();
jj_consume_token(14);
if (jj_2_35(2)) {
words = Word_List();
@@ -502,7 +502,7 @@
final public List<String> Word_List() throws ParseException {
Token word;
List<String> words = null;
- word = jj_consume_token(WORD);
+ word = word();
if (jj_2_36(2)) {
jj_consume_token(15);
words = Word_List();
@@ -522,19 +522,31 @@
final public Token dr() throws ParseException {
Token t;
if (jj_2_37(2)) {
- t = jj_consume_token(WORD);
+ t = jj_consume_token(A);
} else if (jj_2_38(2)) {
- t = jj_consume_token(DR);
- } else if (jj_2_39(2)) {
- t = jj_consume_token(QUOTED_STRING);
+ t = jj_consume_token(C);
} else {
jj_consume_token(-1);
throw new ParseException();
}
- {if (true) return t;}
+ {if (true) return t;}
throw new Error("Missing return statement in function");
}
+ final public Token word() throws ParseException {
+ Token t;
+ if (jj_2_39(2)) {
+ t = jj_consume_token(A);
+ } else if (jj_2_40(2)) {
+ t = jj_consume_token(B);
+ } else {
+ jj_consume_token(-1);
+ throw new ParseException();
+ }
+ {if (true) return t;}
+ throw new Error("Missing return statement in function");
+ }
+
private boolean jj_2_1(int xla) {
jj_la = xla; jj_lastpos = jj_scanpos = token;
try { return !jj_3_1(); }
@@ -808,6 +820,13 @@
finally { jj_save(38, xla); }
}
+ private boolean jj_2_40(int xla) {
+ jj_la = xla; jj_lastpos = jj_scanpos = token;
+ try { return !jj_3_40(); }
+ catch(LookaheadSuccess ls) { return true; }
+ finally { jj_save(39, xla); }
+ }
+
private boolean jj_3_12() {
if (jj_scan_token(2)) return true;
if (jj_3R_1()) return true;
@@ -815,12 +834,12 @@
}
private boolean jj_3_16() {
- if (jj_3R_7()) return true;
+ if (jj_3R_8()) return true;
return false;
}
- private boolean jj_3R_12() {
- if (jj_scan_token(WORD)) return true;
+ private boolean jj_3R_13() {
+ if (jj_3R_7()) return true;
Token xsp;
xsp = jj_scanpos;
if (jj_3_36()) jj_scanpos = xsp;
@@ -834,7 +853,7 @@
}
private boolean jj_3_32() {
- if (jj_3R_10()) return true;
+ if (jj_3R_11()) return true;
return false;
}
@@ -848,13 +867,8 @@
return false;
}
- private boolean jj_3_39() {
- if (jj_scan_token(QUOTED_STRING)) return true;
- return false;
- }
-
private boolean jj_3R_1() {
- if (jj_3R_10()) return true;
+ if (jj_3R_11()) return true;
return false;
}
@@ -865,38 +879,58 @@
private boolean jj_3_31() {
if (jj_scan_token(13)) return true;
- if (jj_3R_10()) return true;
+ if (jj_3R_11()) return true;
return false;
}
- private boolean jj_3R_10() {
+ private boolean jj_3R_11() {
if (jj_scan_token(LABEL)) return true;
if (jj_scan_token(11)) return true;
return false;
}
- private boolean jj_3_38() {
- if (jj_scan_token(DR)) return true;
+ private boolean jj_3_40() {
+ if (jj_scan_token(B)) return true;
return false;
}
- private boolean jj_3R_15() {
- if (jj_scan_token(WORD)) return true;
+ private boolean jj_3R_16() {
+ if (jj_3R_7()) return true;
if (jj_scan_token(14)) return true;
return false;
}
+ private boolean jj_3_38() {
+ if (jj_scan_token(C)) return true;
+ return false;
+ }
+
private boolean jj_3_23() {
if (jj_scan_token(MOST)) return true;
return false;
}
+ private boolean jj_3_39() {
+ if (jj_scan_token(A)) return true;
+ return false;
+ }
+
private boolean jj_3_30() {
- if (jj_3R_9()) return true;
+ if (jj_3R_10()) return true;
if (jj_scan_token(6)) return true;
return false;
}
+ private boolean jj_3R_7() {
+ Token xsp;
+ xsp = jj_scanpos;
+ if (jj_3_39()) {
+ jj_scanpos = xsp;
+ if (jj_3_40()) return true;
+ }
+ return false;
+ }
+
private boolean jj_3_34() {
if (jj_scan_token(2)) return true;
if (jj_3R_4()) return true;
@@ -904,29 +938,26 @@
}
private boolean jj_3_37() {
- if (jj_scan_token(WORD)) return true;
+ if (jj_scan_token(A)) return true;
return false;
}
- private boolean jj_3R_9() {
+ private boolean jj_3R_10() {
Token xsp;
xsp = jj_scanpos;
if (jj_3_37()) {
jj_scanpos = xsp;
- if (jj_3_38()) {
- jj_scanpos = xsp;
- if (jj_3_39()) return true;
+ if (jj_3_38()) return true;
}
- }
return false;
}
private boolean jj_3R_3() {
- if (jj_3R_14()) return true;
+ if (jj_3R_15()) return true;
return false;
}
- private boolean jj_3R_16() {
+ private boolean jj_3R_17() {
Token xsp;
xsp = jj_scanpos;
if (jj_3_29()) {
@@ -943,19 +974,19 @@
}
private boolean jj_3_29() {
- if (jj_scan_token(WORD)) return true;
+ if (jj_3R_7()) return true;
if (jj_scan_token(10)) return true;
return false;
}
private boolean jj_3_19() {
if (jj_scan_token(2)) return true;
- if (jj_3R_8()) return true;
+ if (jj_3R_9()) return true;
return false;
}
private boolean jj_3_15() {
- if (jj_scan_token(WORD)) return true;
+ if (jj_3R_7()) return true;
return false;
}
@@ -966,7 +997,7 @@
}
private boolean jj_3R_4() {
- if (jj_3R_15()) return true;
+ if (jj_3R_16()) return true;
return false;
}
@@ -1009,7 +1040,7 @@
private boolean jj_3_33() {
if (jj_scan_token(2)) return true;
- if (jj_3R_11()) return true;
+ if (jj_3R_12()) return true;
return false;
}
@@ -1031,8 +1062,8 @@
return false;
}
- private boolean jj_3R_8() {
- if (jj_3R_16()) return true;
+ private boolean jj_3R_9() {
+ if (jj_3R_17()) return true;
return false;
}
@@ -1051,7 +1082,7 @@
return false;
}
- private boolean jj_3R_13() {
+ private boolean jj_3R_14() {
if (jj_scan_token(10)) return true;
if (jj_scan_token(LABEL)) return true;
return false;
@@ -1063,13 +1094,13 @@
return false;
}
- private boolean jj_3R_11() {
- if (jj_3R_9()) return true;
+ private boolean jj_3R_12() {
+ if (jj_3R_10()) return true;
return false;
}
private boolean jj_3_17() {
- if (jj_3R_8()) return true;
+ if (jj_3R_9()) return true;
return false;
}
@@ -1091,19 +1122,19 @@
}
private boolean jj_3_35() {
- if (jj_3R_12()) return true;
+ if (jj_3R_13()) return true;
return false;
}
private boolean jj_3_36() {
if (jj_scan_token(15)) return true;
- if (jj_3R_12()) return true;
+ if (jj_3R_13()) return true;
return false;
}
private boolean jj_3_18() {
if (jj_scan_token(2)) return true;
- if (jj_3R_7()) return true;
+ if (jj_3R_8()) return true;
return false;
}
@@ -1112,7 +1143,7 @@
return false;
}
- private boolean jj_3R_14() {
+ private boolean jj_3R_15() {
Token xsp;
xsp = jj_scanpos;
if (jj_3_5()) {
@@ -1137,12 +1168,12 @@
}
private boolean jj_3R_2() {
- if (jj_3R_13()) return true;
+ if (jj_3R_14()) return true;
return false;
}
- private boolean jj_3R_7() {
- if (jj_3R_9()) return true;
+ private boolean jj_3R_8() {
+ if (jj_3R_10()) return true;
Token xsp;
xsp = jj_scanpos;
if (jj_3_18()) jj_scanpos = xsp;
@@ -1173,7 +1204,7 @@
private static void jj_la1_init_1() {
jj_la1_1 = new int[] {};
}
- final private JJCalls[] jj_2_rtns = new JJCalls[39];
+ final private JJCalls[] jj_2_rtns = new JJCalls[40];
private boolean jj_rescan = false;
private int jj_gc = 0;
@@ -1357,7 +1388,7 @@
/** Generate ParseException. */
public ParseException generateParseException() {
jj_expentries.clear();
- boolean[] la1tokens = new boolean[33];
+ boolean[] la1tokens = new boolean[34];
if (jj_kind >= 0) {
la1tokens[jj_kind] = true;
jj_kind = -1;
@@ -1374,7 +1405,7 @@
}
}
}
- for (int i = 0; i < 33; i++) {
+ for (int i = 0; i < 34; i++) {
if (la1tokens[i]) {
jj_expentry = new int[1];
jj_expentry[0] = i;
@@ -1401,7 +1432,7 @@
private void jj_rescan_token() {
jj_rescan = true;
- for (int i = 0; i < 39; i++) {
+ for (int i = 0; i < 40; i++) {
try {
JJCalls p = jj_2_rtns[i];
do {
@@ -1447,6 +1478,7 @@
case 36: jj_3_37(); break;
case 37: jj_3_38(); break;
case 38: jj_3_39(); break;
+ case 39: jj_3_40(); break;
}
}
p = p.next;
Modified: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_Parser.jj
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_Parser.jj 2012-05-08 11:53:28 UTC (rev 3697)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_Parser.jj 2012-05-09 15:28:25 UTC (rev 3698)
@@ -206,7 +206,7 @@
Type type;
}
{
- "(" label=<LABEL> "," referent = dr() "," word=<WORD> "," type = Type() ")"
+ "(" label=<LABEL> "," referent = dr() "," word=word() "," type = Type() ")"
{
Argument argument = new Argument();
argument.setLabel(new Label(label.toString()));
@@ -234,7 +234,7 @@
|
- word = <WORD>
+ word = word()
{
ElementaryType type=null;
if (word.toString().equals("e"))
@@ -330,7 +330,7 @@
}
{
- predicate=<WORD> "(" dr_list=DR_List() ")"
+ predicate=word() "(" dr_list=DR_List() ")"
{
Simple_DRS_Condition condition;
@@ -443,7 +443,7 @@
List<String> words = null;
}
{
- ref = <WORD> "/" type = <WORD> "/" (words = Word_List())?
+ ref = word() "/" type = word() "/" (words = Word_List())?
{
if (words == null)
{
@@ -465,7 +465,7 @@
List<String> words = null;
}
{
- word = <WORD> ("^" words = Word_List())?
+ word = word() ("^" words = Word_List())?
{
if (words == null)
{
@@ -498,14 +498,20 @@
TOKEN: {<LABEL: "l"(["0"-"9"])+>}
-TOKEN: {<WORD: (["a"-"z","A"-"Z","_",".","#",":","0"-"9"])+>}
+//TOKEN: {<WORD: (["a"-"z","A"-"Z","_",".","#",":","0"-"9"])+>}
+//TOKEN: {<DR: (["?","!"])?(["a"-"z","A"-"Z","0"-"9","."])+>}
-TOKEN: {<DR: (["?","!"])?(["a"-"z","A"-"Z","0"-"9","."])+>}
+TOKEN: {<A: (["a"-"z","A"-"Z","0"-"9"])+>}
+TOKEN: {<B: (["a"-"z","A"-"Z","_",".","#","0"-"9"])+":"(["a"-"z","A"-"Z","_",".","#","0"-"9"])+>}
+TOKEN: {<C: ["?","!"](["a"-"z","A"-"Z","0"-"9"])+>}
+Token dr() : { Token t; }{ (t=<A> | t=<C>) { return t; } }
+Token word() : { Token t; }{ (t=<A> | t=<B>) { return t; } }
+
+// Token label() : { Token t; }{ (t=<A> | t=<B> | t=<LABEL>) { return t; } }
+
TOKEN: {<QUOTED_STRING: "\'" (~["\'"])+ "\'" >}
-Token dr() : { Token t; }{ (t=<WORD> | t=<DR> | t=<QUOTED_STRING>) { return t; } }
-
SKIP : { " " | "\t" | "\n" | "\r" }
Modified: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_ParserConstants.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_ParserConstants.java 2012-05-08 11:53:28 UTC (rev 3697)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_ParserConstants.java 2012-05-09 15:28:25 UTC (rev 3698)
@@ -31,11 +31,13 @@
/** RegularExpression Id. */
int LABEL = 25;
/** RegularExpression Id. */
- int WORD = 26;
+ int A = 26;
/** RegularExpression Id. */
- int DR = 27;
+ int B = 27;
/** RegularExpression Id. */
- int QUOTED_STRING = 28;
+ int C = 28;
+ /** RegularExpression Id. */
+ int QUOTED_STRING = 29;
/** Lexical state. */
int DEFAULT = 0;
@@ -68,8 +70,9 @@
"\"NO\"",
"\"HOWMANY\"",
"<LABEL>",
- "<WORD>",
- "<DR>",
+ "<A>",
+ "<B>",
+ "<C>",
"<QUOTED_STRING>",
"\" \"",
"\"\\t\"",
Modified: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_ParserTokenManager.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_ParserTokenManager.java 2012-05-08 11:53:28 UTC (rev 3697)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_ParserTokenManager.java 2012-05-09 15:28:25 UTC (rev 3698)
@@ -23,18 +23,15 @@
switch (pos)
{
case 0:
- if ((active0 & 0x800L) != 0L)
- {
- jjmatchedKind = 26;
- return 2;
- }
if ((active0 & 0x1ff2280L) != 0L)
{
jjmatchedKind = 26;
- return 8;
+ return 4;
}
return -1;
case 1:
+ if ((active0 & 0x802000L) != 0L)
+ return 4;
if ((active0 & 0x17f0280L) != 0L)
{
if (jjmatchedPos != 1)
@@ -42,58 +39,56 @@
jjmatchedKind = 26;
jjmatchedPos = 1;
}
- return 8;
+ return 4;
}
- if ((active0 & 0x802000L) != 0L)
- return 8;
return -1;
case 2:
if ((active0 & 0x17f0280L) != 0L)
{
jjmatchedKind = 26;
jjmatchedPos = 2;
- return 8;
+ return 4;
}
if ((active0 & 0x2000L) != 0L)
- return 8;
+ return 4;
return -1;
case 3:
if ((active0 & 0x1190200L) != 0L)
{
jjmatchedKind = 26;
jjmatchedPos = 3;
- return 8;
+ return 4;
}
if ((active0 & 0x660000L) != 0L)
- return 8;
+ return 4;
return -1;
case 4:
+ if ((active0 & 0x10000L) != 0L)
+ return 4;
if ((active0 & 0x1180200L) != 0L)
{
jjmatchedKind = 26;
jjmatchedPos = 4;
- return 8;
+ return 4;
}
- if ((active0 & 0x10000L) != 0L)
- return 8;
return -1;
case 5:
if ((active0 & 0x1180000L) != 0L)
{
jjmatchedKind = 26;
jjmatchedPos = 5;
- return 8;
+ return 4;
}
return -1;
case 6:
+ if ((active0 & 0x1080000L) != 0L)
+ return 4;
if ((active0 & 0x100000L) != 0L)
{
jjmatchedKind = 26;
jjmatchedPos = 6;
- return 8;
+ return 4;
}
- if ((active0 & 0x1080000L) != 0L)
- return 8;
return -1;
default :
return -1;
@@ -217,7 +212,7 @@
return jjMoveStringLiteralDfa3_0(active0, 0x20000L);
case 84:
if ((active0 & 0x2000L) != 0L)
- return jjStartNfaWithStates_0(2, 13, 8);
+ return jjStartNfaWithStates_0(2, 13, 4);
break;
case 87:
return jjMoveStringLiteralDfa3_0(active0, 0x1000000L);
@@ -247,7 +242,7 @@
break;
case 69:
if ((active0 & 0x40000L) != 0L)
- return jjStartNfaWithStates_0(3, 18, 8);
+ return jjStartNfaWithStates_0(3, 18, 4);
break;
case 76:
return jjMoveStringLiteralDfa4_0(active0, 0x100000L);
@@ -257,15 +252,15 @@
return jjMoveStringLiteralDfa4_0(active0, 0x10000L);
case 84:
if ((active0 & 0x20000L) != 0L)
- return jjStartNfaWithStates_0(3, 17, 8);
+ return jjStartNfaWithStates_0(3, 17, 4);
break;
case 87:
if ((active0 & 0x200000L) != 0L)
- return jjStartNfaWithStates_0(3, 21, 8);
+ return jjStartNfaWithStates_0(3, 21, 4);
break;
case 89:
if ((active0 & 0x400000L) != 0L)
- return jjStartNfaWithStates_0(3, 22, 8);
+ return jjStartNfaWithStates_0(3, 22, 4);
break;
case 112:
return jjMoveStringLiteralDfa4_0(active0, 0x200L);
@@ -293,7 +288,7 @@
return jjMoveStringLiteralDfa5_0(active0, 0x80000L);
case 89:
if ((active0 & 0x10000L) != 0L)
- return jjStartNfaWithStates_0(4, 16, 8);
+ return jjStartNfaWithStates_0(4, 16, 4);
break;
case 101:
return jjMoveStringLiteralDfa5_0(active0, 0x200L);
@@ -343,11 +338,11 @@
return jjMoveStringLiteralDfa7_0(active0, 0x100000L);
case 84:
if ((active0 & 0x80000L) != 0L)
- return jjStartNfaWithStates_0(6, 19, 8);
+ return jjStartNfaWithStates_0(6, 19, 4);
break;
case 89:
if ((active0 & 0x1000000L) != 0L)
- return jjStartNfaWithStates_0(6, 24, 8);
+ return jjStartNfaWithStates_0(6, 24, 4);
break;
default :
break;
@@ -367,7 +362,7 @@
{
case 84:
if ((active0 & 0x100000L) != 0L)
- return jjStartNfaWithStates_0(7, 20, 8);
+ return jjStartNfaWithStates_0(7, 20, 4);
break;
default :
break;
@@ -388,7 +383,7 @@
private int jjMoveNfa_0(int startState, int curPos)
{
int startsAt = 0;
- jjnewStateCnt = 8;
+ jjnewStateCnt = 11;
int i = 1;
jjstateSet[0] = startState;
int kind = 0x7fffffff;
@@ -403,33 +398,27 @@
{
switch(jjstateSet[--i])
{
- case 0:
- if ((0x3ff400000000000L & l) != 0L)
+ case 4:
+ if ((0x3ff400800000000L & l) != 0L)
+ jjCheckNAddTwoStates(3, 4);
+ else if (curChar == 58)
+ jjCheckNAdd(5);
+ if ((0x3ff000000000000L & l) != 0L)
{
- if (kind > 27)
- kind = 27;
- jjCheckNAdd(4);
- }
- else if (curChar == 39)
- jjCheckNAdd(6);
- else if ((0x8000000200000000L & l) != 0L)
- jjCheckNAdd(4);
- if ((0x400400800000000L & l) != 0L)
- {
if (kind > 26)
kind = 26;
jjCheckNAdd(2);
}
break;
- case 8:
- if ((0x3ff400000000000L & l) != 0L)
+ case 0:
+ if ((0x3ff400800000000L & l) != 0L)
+ jjCheckNAddTwoStates(3, 4);
+ else if (curChar == 39)
+ jjCheckNAdd(9);
+ else if ((0x8000000200000000L & l) != 0L)
+ jjCheckNAdd(7);
+ if ((0x3ff000000000000L & l) != 0L)
{
- if (kind > 27)
- kind = 27;
- jjCheckNAdd(4);
- }
- if ((0x400400800000000L & l) != 0L)
- {
if (kind > 26)
kind = 26;
jjCheckNAdd(2);
@@ -443,35 +432,46 @@
jjstateSet[jjnewStateCnt++] = 1;
break;
case 2:
- if ((0x400400800000000L & l) == 0L)
+ if ((0x3ff000000000000L & l) == 0L)
break;
if (kind > 26)
kind = 26;
jjCheckNAdd(2);
break;
case 3:
- if ((0x8000000200000000L & l) != 0L)
- jjCheckNAdd(4);
+ if ((0x3ff400800000000L & l) != 0L)
+ jjCheckNAddTwoStates(3, 4);
break;
- case 4:
- if ((0x3ff400000000000L & l) == 0L)
+ case 5:
+ if ((0x3ff400800000000L & l) == 0L)
break;
if (kind > 27)
kind = 27;
- jjCheckNAdd(4);
+ jjCheckNAdd(5);
break;
- case 5:
- if (curChar == 39)
- jjCheckNAdd(6);
- break;
case 6:
- if ((0xffffff7fffffffffL & l) != 0L)
- jjCheckNAddTwoStates(6, 7);
+ if ((0x8000000200000000L & l) != 0L)
+ jjCheckNAdd(7);
break;
case 7:
- if (curChar == 39 && kind > 28)
+ if ((0x3ff000000000000L & l) == 0L)
+ break;
+ if (kind > 28)
kind = 28;
+ jjCheckNAdd(7);
break;
+ case 8:
+ if (curChar == 39)
+ jjCheckNAdd(9);
+ break;
+ case 9:
+ if ((0xffffff7fffffffffL & l) != 0L)
+ jjCheckNAddTwoStates(9, 10);
+ break;
+ case 10:
+ if (curChar == 39 && kind > 29)
+ kind = 29;
+ break;
default : break;
}
} while(i != startsAt);
@@ -483,51 +483,54 @@
{
switch(jjstateSet[--i])
{
- case 0:
+ case 4:
if ((0x7fffffe87fffffeL & l) != 0L)
+ jjCheckNAddTwoStates(3, 4);
+ if ((0x7fffffe07fffffeL & l) != 0L)
{
if (kind > 26)
kind = 26;
jjCheckNAdd(2);
}
- if ((0x7fffffe07fffffeL & l) != 0L)
- {
- if (kind > 27)
- kind = 27;
- jjCheckNAdd(4);
- }
- if (curChar == 108)
- jjstateSet[jjnewStateCnt++] = 1;
break;
- case 8:
+ case 0:
if ((0x7fffffe87fffffeL & l) != 0L)
+ jjCheckNAddTwoStates(3, 4);
+ if ((0x7fffffe07fffffeL & l) != 0L)
{
if (kind > 26)
kind = 26;
jjCheckNAdd(2);
}
- if ((0x7fffffe07fffffeL & l) != 0L)
- {
- if (kind > 27)
- kind = 27;
- jjCheckNAdd(4);
- }
+ if (curChar == 108)
+ jjstateSet[jjnewStateCnt++] = 1;
break;
case 2:
- if ((0x7fffffe87fffffeL & l) == 0L)
+ if ((0x7fffffe07fffffeL & l) == 0L)
break;
if (kind > 26)
kind = 26;
jjCheckNAdd(2);
break;
- case 4:
- if ((0x7fffffe07fffffeL & l) == 0L)
+ case 3:
+ if ((0x7fffffe87fffffeL & l) != 0L)
+ jjCheckNAddTwoStates(3, 4);
+ break;
+ case 5:
+ if ((0x7fffffe87fffffeL & l) == 0L)
break;
if (kind > 27)
kind = 27;
- jjCheckNAdd(4);
+ jjstateSet[jjnewStateCnt++] = 5;
break;
- case 6:
+ case 7:
+ if ((0x7fffffe07fffffeL & l) == 0L)
+ break;
+ if (kind > 28)
+ kind = 28;
+ jjstateSet[jjnewStateCnt++] = 7;
+ break;
+ case 9:
jjAddStates(0, 1);
break;
default : break;
@@ -542,7 +545,7 @@
{
switch(jjstateSet[--i])
{
- case 6:
+ case 9:
if ((jjbitVec0[i2] & l2) != 0L)
jjAddStates(0, 1);
break;
@@ -557,14 +560,14 @@
kind = 0x7fffffff;
}
++curPos;
- if ((i = jjnewStateCnt) == (startsAt = 8 - (jjnewStateCnt = startsAt)))
+ if ((i = jjnewStateCnt) == (startsAt = 11 - (jjnewStateCnt = startsAt)))
return curPos;
try { curChar = input_stream.readChar(); }
catch(java.io.IOException e) { return curPos; }
}
}
static final int[] jjnextStates = {
- 6, 7,
+ 9, 10,
};
/** Token literal values. */
@@ -573,21 +576,21 @@
"\163\143\157\160\145\50", "\50", "\72\133", "\174", "\116\117\124", "\57", "\136",
"\105\126\105\122\131", "\115\117\123\124", "\123\117\115\105", "\124\110\105\115\117\123\124",
"\124\110\105\114\105\101\123\124", "\101\106\105\127", "\115\101\116\131", "\116\117",
-"\110\117\127\115\101\116\131", null, null, null, null, null, null, null, null, };
+"\110\117\127\115\101\116\131", null, null, null, null, null, null, null, null, null, };
/** Lexer state names. */
public static final String[] lexStateNames = {
"DEFAULT",
};
static final long[] jjtoToken = {
- 0x1fffffffL,
+ 0x3fffffffL,
};
static final long[] jjtoSkip = {
- 0x1e0000000L,
+ 0x3c0000000L,
};
protected SimpleCharStream input_stream;
-private final int[] jjrounds = new int[8];
-private final int[] jjstateSet = new int[16];
+private final int[] jjrounds = new int[11];
+private final int[] jjstateSet = new int[22];
protected char curChar;
/** Constructor. */
public DUDE_ParserTokenManager(SimpleCharStream stream){
@@ -614,7 +617,7 @@
{
int i;
jjround = 0x80000001;
- for (i = 8; i-- > 0;)
+ for (i = 11; i-- > 0;)
jjrounds[i] = 0x80000000;
}
Modified: trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/templator/BasicSlotBuilder.java
===================================================================
--- trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/templator/BasicSlotBuilder.java 2012-05-08 11:53:28 UTC (rev 3697)
+++ trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/templator/BasicSlotBuilder.java 2012-05-09 15:28:25 UTC (rev 3698)
@@ -35,6 +35,14 @@
String type = "UNSPEC";
String slot;
+ /* PRONOUN HACK */
+ if (pos.equals("PRP") || pos.equals("PRP$")) {
+ String[] pronEntry = {token,
+ "(DET DET:'" + token.toLowerCase() + "')",
+ "<x,l1,e,[ l1:[ x | ] ],[],[],[]>"};
+ result.add(pronEntry);
+ }
+
/* NOUNS */
if (equalsOneOf(pos,noun)) {
@@ -329,12 +337,12 @@
slot = "SLOT_" + token + "/PROPERTY/";
String[] npAdjunct = {token,
"(NP NP* (PP P:'" + token.toLowerCase() + "' DP[pobj]))",
- // "<x,l1,<e,t>,[ l1:[ | SLOT_" + token + "(p), p(x,y) ] ],[(l2,y,pobj,<<e,t>,t>)],[l2=l1],["+slot+"]>" +
- "<x,l1,<e,t>,[ l1:[ | empty(x,y) ] ],[(l2,y,pobj,<<e,t>,t>)],[l2=l1],[]>"};
+ "<x,l1,<e,t>,[ l1:[ | SLOT_" + token + "(p), p(x,y) ] ],[(l2,y,pobj,<<e,t>,t>)],[l2=l1],["+slot+"]>" +
+ " ;; <x,l1,<e,t>,[ l1:[ | empty(x,y) ] ],[(l2,y,pobj,<<e,t>,t>)],[l2=l1],[]>"};
String[] vpAdjunct = {token,
"(VP VP* (PP P:'" + token.toLowerCase() + "' DP[pobj]))",
- // "<x,l1,t,[ l1:[ | SLOT_" + token + "(p), p(x,y) ] ],[(l2,y,pobj,<<e,t>,t>)],[l2=l1],["+slot+"]>" +
- "<x,l1,t,[ l1:[ | empty(x,y) ] ],[(l2,y,pobj,<<e,t>,t>)],[l2=l1],[]>"};
+ "<x,l1,t,[ l1:[ | SLOT_" + token + "(p), p(x,y) ] ],[(l2,y,pobj,<<e,t>,t>)],[l2=l1],["+slot+"]>" +
+ " ;; <x,l1,t,[ l1:[ | empty(x,y) ] ],[(l2,y,pobj,<<e,t>,t>)],[l2=l1],[]>"};
result.add(npAdjunct);
result.add(vpAdjunct);
}
Added: trunk/components-ext/src/main/javacc/DRSParser.jj
===================================================================
--- trunk/components-ext/src/main/javacc/DRSParser.jj (rev 0)
+++ trunk/components-ext/src/main/javacc/DRSParser.jj 2012-05-09 15:28:25 UTC (rev 3698)
@@ -0,0 +1,259 @@
+
+options {
+ LOOKAHEAD = 2;
+ CHOICE_AMBIGUITY_CHECK = 2;
+ OTHER_AMBIGUITY_CHECK = 1;
+ STATIC = false;
+ DEBUG_PARSER = false;
+ DEBUG_LOOKAHEAD = false;
+ DEBUG_TOKEN_MANAGER = false;
+ ERROR_REPORTING = true;
+ JAVA_UNICODE_ESCAPE = false;
+ UNICODE_INPUT = false;
+ IGNORE_CASE = false;
+ USER_TOKEN_MANAGER = false;
+ USER_CHAR_STREAM = false;
+ BUILD_PARSER = true;
+ BUILD_TOKEN_MANAGER = true;
+ SANITY_CHECK = true;
+ FORCE_LA_CHECK = false;
+}
+
+PARSER_BEGIN(DRSParser)
+
+package org.dllearner.algorithm.tbsl.sem.drs.reader;
+
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Set;
+
+import org.dllearner.algorithm.tbsl.sem.drs.*;
+import org.dllearner.algorithm.tbsl.sem.util.Label;
+
+public class DRSParser {
+
+ /** Main entry point. */
+ public static void main(String args[]) throws ParseException {
+ DRSParser parser = new DRSParser(System.in);
+ parser.Input();
+ }
+
+}
+
+PARSER_END(DRSParser)
+
+/** Root production. */
+void Input() :
+{}
+{
+ DRS() <EOF>
+}
+
+/** DRS */
+DRS DRS() :
+{
+ Set<DiscourseReferent> dr_set = null;
+ Set<DRS_Condition> conditions = null;
+ DRS drs;
+ Token label = null;
+
+}
+{
+ (label=<LABEL> ":")? "[" (dr_set=DR_Set())? "|" (conditions=Condition_List())? "]"
+ {
+ if (dr_set == null)
+ {
+ dr_set = new HashSet<DiscourseReferent>();
+ }
+ drs = new DRS();
+ if (label != null)
+ {
+ drs.setLabel(label.toString());
+ }
+ drs.setDiscourseReferents(dr_set);
+ if (conditions != null)
+ {
+ drs.setDRSConditions(conditions);
+ }
+ return drs;
+ }
+}
+
+/** DR_Set*/
+Set<DiscourseReferent> DR_Set() :
+{
+ Token dr;
+ Set<DiscourseReferent> dr_set=null;
+}
+{
+ dr = dr() ("," dr_set=DR_Set())?
+ {
+ if (dr_set == null)
+ {
+ dr_set= new HashSet<DiscourseReferent>();
+ }
+ if (dr.toString().startsWith("?"))
+ {
+ dr_set.add(new DiscourseReferent(dr.toString().substring(1),true,false));
+ }
+ else if (dr.toString().startsWith("!"))
+ {
+ dr_set.add(new DiscourseReferent(dr.toString().substring(1),false,true));
+ }
+ else
+ {
+ dr_set.add(new DiscourseReferent(dr.toString(),false,false));
+ }
+ return dr_set;
+ }
+}
+
+Set<DRS_Condition> Condition_List() :
+{
+ DRS_Condition condition= null;
+ Set<DRS_Condition> conditions = null;
+}
+{
+ condition=Condition() ("," conditions=Condition_List())?
+ {
+ if (conditions == null)
+ {
+ conditions = new HashSet<DRS_Condition>();
+ }
+ conditions.add(condition);
+ return conditions;
+ }
+}
+
+DRS_Condition Condition() :
+{
+ List<DiscourseReferent> dr_list;
+ Token dr1;
+ Token dr2;
+ Token dr;
+ Token predicate;
+ Token quantifier;
+ DRS drs1;
+ DRS drs2;
+}
+{
+
+ predicate=<WORD> "(" dr_list=DR_List() ")"
+ {
+ Simple_DRS_Condition condition;
+
+ condition = new Simple_DRS_Condition();
+ condition.setPredicate(predicate.toString());
+ condition.setArguments(dr_list);
+ return condition;
+ }
+
+ |
+
+ dr1 = dr() "=" dr2 = dr()
+ {
+ Simple_DRS_Condition condition;
+
+ condition = new Simple_DRS_Condition();
+ condition.setPredicate("equal");
+ condition.addArgument(new DiscourseReferent(dr1.toString()));
+ condition.addArgument(new DiscourseReferent(dr2.toString()));
+ return condition;
+ }
+
+ |
+
+ "NOT" drs1=DRS()
+ {
+ Negated_DRS drs = new Negated_DRS();
+ drs.setDRS(drs1);
+ return drs;
+ }
+
+ |
+
+ drs1=DRS() (quantifier=<EVERY> | quantifier=<SOME> | quantifier=<AFEW> | quantifier=<MOST> | quantifier=<THEMOST> | quantifier=<THELEAST> |
+ quantifier=<HOWMANY> | quantifier=<MANY> | quantifier=<NO>) dr=dr() drs2=DRS()
+ {
+ Complex_DRS_Condition drs;
+ drs = new Complex_DRS_Condition();
+ drs.setRestrictor(drs1);
+ drs.setScope(drs2);
+ drs.setReferent(new DiscourseReferent(dr.toString()));
+
+ if (quantifier.toString().equals("EVERY")) {drs.setQuantifier(DRS_Quantifier.EVERY);}
+ if (quantifier.toString().equals("SOME")) {drs.setQuantifier(DRS_Quantifier.SOME);}
+ if (quantifier.toString().equals("MOST")) {drs.setQuantifier(DRS_Quantifier.MOST);}
+ if (quantifier.toString().equals("THEMOST")) {drs.setQuantifier(DRS_Quantifier.THEMOST);}
+ if (quantifier.toString().equals("THELEAST")) {drs.setQuantifier(DRS_Quantifier.THELEAST);}
+ if (quantifier.toString().equals("AFEW")) {drs.setQuantifier(DRS_Quantifier.FEW);}
+ if (quantifier.toString().equals("MANY")) {drs.setQuantifier(DRS_Quantifier.MANY);}
+ if (quantifier.toString().equals("HOWMANY")) {drs.setQuantifier(DRS_Quantifier.HOWMANY);}
+ if (quantifier.toString().equals("NO")) {drs.setQuantifier(DRS_Quantifier.NO);}
+
+ return drs;
+
+ }
+}
+
+/** DR_List*/
+List<DiscourseReferent> DR_List() :
+{
+ Token dr;
+ List<DiscourseReferent> dr_list=null;
+}
+{
+ dr = dr() ("," dr_list=DR_List())?
+ {
+ if (dr_list == null)
+ {
+ dr_list= new ArrayList<DiscourseReferent>();
+ }
+
+ if (dr.toString().startsWith("?")) {
+ dr_list.add(0,new DiscourseReferent(dr.toString().substring(1),true,false));
+ }
+ else if (dr.toString().startsWith("?")) {
+ dr_list.add(0,new DiscourseReferent(dr.toString().substring(1),false,true));
+ }
+ else {
+ dr_list.add(0,new DiscourseReferent(dr.toString(),false,false));
+ }
+
+ return dr_list;
+ }
+}
+
+
+TOKEN: {<EVERY: "EVERY">}
+
+TOKEN: {<MOST: "MOST">}
+
+TOKEN: {<SOME: "SOME">}
+
+TOKEN: {<THEMOST: "THEMOST">}
+
+TOKEN: {<THELEAST: "THELEAST">}
+
+TOKEN: {<AFEW: "AFEW">}
+
+TOKEN: {<MANY: "MANY">}
+
+TOKEN: {<NO: "NO">}
+
+TOKEN: {<HOWMANY: "HOWMANY">}
+
+TOKEN: {<LABEL: "l"(["0"-"9"])+>}
+
+TOKEN: {<WORD: (["a"-"z","A"-"Z","_",".","#",":"])+>}
+
+TOKEN: {<DR: (["?","!"])?(["a"-"z","A"-"Z","0"-"9","."])+>}
+
+TOKEN: {<QUOTED_STRING: "\'" (~["\'"])+ "\'" >}
+
+Token dr() : { Token t; }{ (t=<WORD> | t=<DR> | t=<QUOTED_STRING>) { return t; } }
+
+SKIP : { " " | "\t" | "\n" | "\r" }
+
+
Property changes on: trunk/components-ext/src/main/javacc/DRSParser.jj
___________________________________________________________________
Added: svn:executable
+ *
Copied: trunk/components-ext/src/main/javacc/DUDE_Parser.jj (from rev 3694, trunk/components-ext/src/main/java/org/dllearner/algorithm/tbsl/sem/dudes/reader/DUDE_Parser.jj)
===================================================================
--- trunk/components-ext/src/main/javacc/DUDE_Parser.jj (rev 0)
+++ trunk/components-ext/src/main/javacc/DUDE_Parser.jj 2012-05-09 15:28:25 UTC (rev 3698)
@@ -0,0 +1,513 @@
+
+options {
+ LOOKAHEAD = 2;
+ CHOICE_AMBIGUITY_CHECK = 2;
+ OTHER_AMBIGUITY_CHECK = 1;
+ STATIC = false;
+ DEBUG_PARSER = false;
+ DEBUG_LOOKAHEAD = false;
+ DEBUG_TOKEN_MANAGER = false;
+ ERROR_REPORTING = true;
+ JAVA_UNICODE_ESCAPE = false;
+ UNICODE_INPUT = false;
+ IGNORE_CASE = false;
+ USER_TOKEN_MANAGER = false;
+ USER_CHAR_STREAM = false;
+ BUILD_PARSER = true;
+ BUILD_TOKEN_MANAGER = true;
+ SANITY_CHECK = true;
+ FORCE_LA_CHECK = false;
+}
+
+PARSER_BEGIN(DUDE_Parser)
+
+package org.dllearner.algorithm.tbsl.sem.dudes.reader;
+
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Set;
+
+import org.dllearner.algorithm.tbsl.sem.drs.*;
+import org.dllearner.algorithm.tbsl.sem.dudes.data.*;
+import org.dllearner.algorithm.tbsl.sem.util.*;
+import org.dllearner.algorithm.tbsl.sparql.Slot;
+import org.dllearner.algorithm.tbsl.sparql.SlotType;
+
+public class DUDE_Parser {
+
+ /** Main entry point. */
+ public static void main(String args[]) throws ParseException {
+ DUDE_Parser parser = new DUDE_Parser(System.in);
+ parser.Input();
+ }
+
+}
+
+PARSER_END(DUDE_Parser)
+
+/** Root production. */
+void Input() :
+{}
+{
+ DUDE() <EOF>
+}
+
+/** DUDE */
+Dude DUDE() :
+{
+ Token referent;
+ Token label;
+ Type type;
+ List<DRS> drs_list = null;
+ List<DominanceConstraint> constraints = null;
+ List<Argument> arg_list = null;
+ List<Slot> slots = null;
+}
+{
+ "<" referent = dr() "," label=<LABEL> "," type=Type() "," "[" (drs_list=DRS_List())? "]" "," "[" (arg_list = Arg_List())? "]"
+ "," "[" (constraints = DC_List())? "]" "," "[" (slots = Slot_List())? "]" ">"
+ {
+ Dude dude = new Dude();
+ dude.setReferent(referent.toString());
+ dude.setType(type);
+ if (drs_list != null) dude.setComponents(drs_list);
+ dude.setLabel(new Label(label.toString()));
+ if (arg_list != null) dude.setArguments(arg_list);
+ if (constraints != null) dude.setDominanceConstraints(constraints);
+ if (slots != null) dude.setSlots(slots);
+ return dude;
+ }
+}
+
+DominanceConstraint DominanceConstraint() :
+{
+ Label label1;
+ Label label2;
+ Token domType;
+ DominanceConstraint dc = null;
+}
+{
+ label1 = Label() "<" label2 = Label()
+ {
+ dc = new DominanceConstraint(label1,label2);
+ return dc;
+ }
+
+ |
+
+ label1 = Label() ">" label2 = Label()
+ {
+ dc = new DominanceConstraint(label2,label1);
+ return dc;
+ }
+
+ |
+
+ label1 = Label() "=" label2 = Label()
+ {
+ dc = new DominanceConstraint(label1,label2);
+ dc.setType(DomType.equal);
+ return dc;
+ }
+}
+
+
+Label Label() :
+{
+ Token label;
+}
+{
+
+ label = <LABEL>
+ {
+ return new Label(label.toString());
+ }
+
+ |
+
+ "res(" label = <LABEL> ")"
+ {
+ return new Label(label.toString(),Position.res);
+ }
+
+ |
+
+ "scope(" label = <LABEL> ")"
+ {
+ return new Label(label.toString(),Position.scope);
+ }
+}
+
+
+List<DominanceConstraint> DC_List() :
+{
+List<DominanceConstraint> dc_list = null;
+DominanceConstraint dc = null;
+}
+{
+ dc = DominanceConstraint() ("," dc_list = DC_List())?
+ {
+ if (dc_list == null)
+ {
+ dc_list = new ArrayList<DominanceConstraint>();
+ }
+
+ dc_list.add(0,dc);
+ return dc_list;
+ }
+
+
+}
+
+
+List<DRS> DRS_List() :
+{
+ DRS drs;
+ List<DRS> drs_list = null;
+}
+{
+ drs = DRS() ("," drs_list = DRS_List())?
+ {
+ if (drs_list == null)
+ {
+ drs_list = new ArrayList<DRS>();
+ }
+
+ drs_list.add(0,drs);
+ return drs_list;
+ }
+}
+
+List<Argument> Arg_List() :
+{
+ Argument argument;
+ List<Argument> arg_list = null;
+}
+{
+ argument = Argument() ("," arg_list = Arg_List())?
+ {
+ if (arg_list == null)
+ {
+ arg_list = new ArrayList<Argument>();
+ }
+
+ arg_list.add(0,argument);
+ return arg_list;
+ }
+
+}
+
+Argument Argument() :
+{
+ Token label;
+ Token word;
+ Token referent;
+ Type type;
+}
+{
+ "(" label=<LABEL> "," referent = dr() "," word=word() "," type = Type() ")"
+ {
+ Argument argument = new Argument();
+ argument.setLabel(new Label(label.toString()));
+ argument.setReferent(referent.toString());
+ argument.setAnchor(word.toString());
+ argument.setType(type);
+ return argument;
+ }
+}
+
+Type Type() :
+{
+ Type argument;
+ Type result;
+ Token word;
+}
+{
+ "<" argument = Type() "," result = Type() ">"
+ {
+ CompositeType type = new CompositeType();
+ type.setArgumentType(argument);
+ type.setResultType(result);
+ return type;
+ }
+
+ |
+
+ word = word()
+ {
+ ElementaryType type=null;
+ if (word.toString().equals("e"))
+ type = new ElementaryType(ElemType.e);
+ if (word.toString().equals("t"))
+ type = new ElementaryType(ElemType.t);
+ return type;
+ }
+}
+
+
+/** DRS */
+DRS DRS() :
+{
+ Set<DiscourseReferent> dr_set = null;
+ Set<DRS_Condition> conditions = null;
+ DRS drs;
+ Token label;
+
+}
+{
+ label=<LABEL> ":[" (dr_set=DR_Set())? "|" (conditions=Condition_List())? "]"
+ {
+ if (dr_set == null)
+ {
+ dr_set = new HashSet<DiscourseReferent>();
+ }
+ drs = new DRS();
+ drs.setLabel(label.toString());
+ drs.setDiscourseReferents(dr_set);
+ if (conditions != null)
+ drs.setDRSConditions(conditions);
+ return drs;
+ }
+}
+
+/** DR_Set*/
+Set<DiscourseReferent> DR_Set() :
+{
+ Token dr;
+ Set<DiscourseReferent> dr_set=null;
+}
+{
+ dr = dr() ("," dr_set=DR_Set())?
+ {
+ if (dr_set == null)
+ {
+ dr_set= new HashSet<DiscourseReferent>();
+ }
+ if (dr.toString().startsWith("?"))
+ {
+ dr_set.add(new DiscourseReferent(dr.toString().substring(1),true,false));
+ }
+ else if (dr.toString().startsWith("!"))
+ {
+ dr_set.add(new DiscourseReferent(dr.toString().substring(1),false,true));
+ }
+ else
+ {
+ dr_set.add(new DiscourseReferent(dr.toString(),false,false));
+ }
+ return dr_set;
+ }
+}
+
+Set<DRS_Condition> Condition_List() :
+{
+ DRS_Condition condition= null;
+ Set<DRS_Condition> conditions = null;
+}
+{
+ condition=Condition() ("," conditions=Condition_List())?
+ {
+ if (conditions == null)
+ {
+ conditions = new HashSet<DRS_Condition>();
+ }
+ conditions.add(condition);
+ return conditions;
+ }
+}
+
+DRS_Condition Condition() :
+{
+ List<DiscourseReferent> dr_list;
+ Token dr1;
+ Token dr2;
+ Token dr;
+ Token predicate;
+ Token quantifier;
+ DRS drs1;
+ DRS drs2;
+}
+{
+
+ predicate=word() "(" dr_list=DR_List() ")"
+ {
+ Simple_DRS_Condition condition;
+
+ condition = new Simple_DRS_Condition();
+ condition.setPredicate(predicate.toString());
+ condition.setArguments(dr_list);
+ return condition;
+ }
+
+ |
+
+ dr1 = dr() "=" dr2 = dr()
+ {
+ Simple_DRS_Condition condition;
+
+ condition = new Simple_DRS_Condition();
+ condition.setPredicate("equal");
+ condition.addArgument(new DiscourseReferent(dr1.toString()));
+ condition.addArgument(new DiscourseReferent(dr2.toString()));
+ return condition;
+ }
+
+ |
+
+ "NOT" drs1=DRS()
+ {
+ Negated_DRS drs = new Negated_DRS();
+ drs.setDRS(drs1);
+ return drs;
+ }
+
+ |
+
+ drs1=DRS() (quantifier=<EVERY> | quantifier=<SOME> | quantifier=<AFEW> | quantifier=<MOST> | quantifier=<THEMOST> | quantifier=<THELEAST> |
+ quantifier=<HOWMANY> | quantifier=<MANY> | quantifier=<NO>) dr=dr() drs2=DRS()
+ {
+ Complex_DRS_Condition drs;
+ drs = new Complex_DRS_Condition();
+ drs.setRestrictor(drs1);
+ drs.setScope(drs2);
+ drs.setReferent(new DiscourseReferent(dr.toString()));
+
+ if (quantifier.toString().equals("EVERY")) {drs.setQuantifier(DRS_Quantifier.EVERY);}
+ if (quantifier.toString().equals("SOME")) {drs.setQuantifier(DRS_Quantifier.SOME);}
+ if (quantifier.toString().equals("MOST")) {drs.setQuantifier(DRS_Quantifier.MOST);}
+ if (quantifier.toString().equals("THEMOST")) {drs.setQuantifier(DRS_Quantifier.THEMOST);}
+ if (quantifier.toString().equals("THELEAST")) {drs.setQuantifier(DRS_Quantifier.THELEAST);}
+ if (quantifier.toString().equals("AFEW")) {drs.setQuantifier(DRS_Quantifier.FEW);}
+ if (quantifier.toString().equals("MANY")) {drs.setQuantifier(DRS_Quantifier.MANY);}
+ if (quantifier.toString().equals("HOWMANY")) {drs.setQuantifier(DRS_Quantifier.HOWMANY);}
+ if (quantifier.toString().equals("NO")) {drs.setQuantifier(DRS_Quantifier.NO);}
+
+ return drs;
+
+ }
+}
+
+/** DR_List*/
+List<DiscourseReferent> DR_List() :
+{
+ Token dr;
+ List<DiscourseReferent> dr_list=null;
+}
+{
+ dr = dr() ("," dr_list=DR_List())?
+ {
+ if (dr_list == null)
+ {
+ dr_list= new ArrayList<DiscourseReferent>();
+ }
+
+ if (dr.toString().startsWith("?")) {
+ dr_list.add(0,new DiscourseReferent(dr.toString().substring(1),true,false));
+ }
+ else if (dr.toString().startsWith("?")) {
+ dr_list.add(0,new DiscourseReferent(dr.toString().substring(1),false,true));
+ }
+ else {
+ dr_list.add(0,new DiscourseReferent(dr.toString(),false,false));
+ }
+
+ return dr_list;
+ }
+}
+
+
+List<Slot> Slot_List() :
+{
+ Slot slot;
+ List<Slot> slots = null;
+}
+{
+ slot = Slot() ("," slots = Slot_List())?
+ {
+ if (slots == null)
+ {
+ slots = new ArrayList<Slot>();
+ }
+
+ slots.add(slot);
+ return slots;
+ }
+}
+
+Slot Slot() :
+{
+ Token ref;
+ Token type;
+ SlotType slottype = null;
+ List<String> words = null;
+}
+{
+ ref = word() "/" type = word() "/" (words = Word_List())?
+ {
+ if (words == null)
+ {
+ words = new ArrayList<String>();
+ }
+ if (type.toString().equals("CLASS")) { slottype = SlotType.CLASS; }
+ else if (type.toString().equals("RESOURCE")) { slottype = SlotType.RESOURCE; }
+ else if (type.toString().equals("PROPERTY")) { slottype = SlotType.PROPERTY; }
+ else if (type.toString().equals("SYMPROPERTY")) { slottype = SlotType.SYMPROPERTY; }
+ else { slottype = SlotType.UNSPEC; }
+
+ return new Slot(ref.toString(),slottype,words);
+ }
+}
+
+List<String> Word_List() :
+{
+ Token word;
+ List<String> words = null;
+}
+{
+ word = word() ("^" words = Word_List())?
+ {
+ if (words == null)
+ {
+ words = new ArrayList<String>();
+ }
+
+ words.add(0,word.toString());
+ return words;
+ }
+}
+
+
+TOKEN: {<EVERY: "EVERY">}
+
+TOKEN: {<MOST: "MOST">}
+
+TOKEN: {<SOME: "SOME">}
+
+TOKEN: {<THEMOST: "THEMOST">}
+
+TOKEN: {<THELEAST: "THELEAST">}
+
+TOKEN: {<AFEW: "AFEW">}
+
+TOKEN: {<MANY: "MANY">}
+
+TOKEN: {<NO: "NO">}
+
+TOKEN: {<HOWMANY: "HOWMANY">}
+
+TOKEN: {<LABEL: "l"(["0"-"9"])+>}
+
+TOKEN: {<WORD: (["a"-"z","A"-"Z","_",".","#",":","0"-"9"])+>}
+
+TOKEN: {<DR: (["?","!"])?(["a"-"z","A"-"Z","0"-"9","."])+>}
+
+TOKEN: {<QUOTED_STRING: "\'" (~["\'"])+ "\'" >}
+
+Token dr() : { Token t; }{ (t=<WORD> | t=<DR> | t=<QUOTED_STRING>) { return t; } }
+Token word() : { Token t; }{ (t=<WORD> | t=<DR> | t=<QUOTED_STRING>) { return t; } }
+
+SKIP : { " " | "\t" | "\n" | "\r" }
+
+
+
Added: trunk/components-ext/src/main/javacc/LTAG_Parser.jj
===================================================================
--- trunk/components-ext/src/main/javacc/LTAG_Parser.jj (rev 0)
+++ trunk/components-ext/src/main/javacc/LTAG_Parser.jj 2012-05-09 15:28:25 UTC (rev 3698)
@@ -0,0 +1,212 @@
+
+options {
+ LOOKAHEAD = 5;
+ CHOICE_AMBIGUITY_CHECK = 2;
+ OTHER_AMBIGUITY_CHECK = 1;
+ STATIC = false;
+ DEBUG_PARSER = false;
+ DEBUG_LOOKAHEAD = false;
+ DEBUG_TOKEN_MANAGER = false;
+ ERROR_REPORTING = true;
+ JAVA_UNICODE_ESCAPE = false;
+ UNICODE_INPUT = false;
+ IGNORE_CASE = false;
+ USER_TOKEN_MANAGER = false;
+ USER_CHAR_STREAM = false;
+ BUILD_PARSER = true;
+ BUILD_TOKEN_MANAGER = true;
+ SANITY_CHECK = true;
+ FORCE_LA_CHECK = false;
+}
+
+PARSER_BEGIN(LTAGTreeParser)
+
+package org.dllearner.algorithm.tbsl.ltag.reader;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+import org.dllearner.algorithm.tbsl.ltag.data.*;
+import org.dllearner.algorithm.tbsl.ltag.agreement.*;
+
+public class LTAGTreeParser {
+
+ /** Main entry point. */
+ public static void main(String args[]) throws ParseException {
+ LTAGTreeParser parser = new LTAGTreeParser(System.in);
+ parser.Input();
+ }
+
+}
+
+PARSER_END(LTAGTreeParser)
+
+/** Root production. */
+void Input() :
+{}
+{
+ Tree() <EOF>
+}
+
+/** Tree */
+TreeNode Tree() :
+{
+ Category category;
+ String terminal = "";
+ List<TreeNode> treelist;
+ Token word;
+ Feature feature = null;
+}
+
+{
+ // SubstNode with case constraints (e.g. DP[subj]|nom)
+ category = Cat() "[" word=<WORD> "]" ("{" feature=Feat() "}")?
+ {
+ SubstNode substnode = new SubstNode(word.toString(),category,feature);
+ return substnode;
+ }
+
+ |
+
+ // FootNode (e.g. S*)
+ category = Cat() "*"
+ {
+ FootNode footnode = new FootNode(category);
+ return footnode;
+ }
+
+ |
+
+ // FootNode with no adjunction allowed (e.g. ^S*)
+ "^" category = Cat() "*"
+ {
+ FootNode footnode = new FootNode(category);
+ footnode.setAdjConstraint(true);
+ return footnode;
+ }
+
+ |
+
+ // TreeNode which has case feature marked (e.g. (S|nom ...))
+ "(" category = Cat() ("{" feature=Feat() "}")? treelist=TreeList() ")"
+ {
+ TreeNode tree = new Tree();
+ tree.setCategory(category);
+ tree.setChildren(treelist);
+ tree.setParentForTree();
+ tree.setFeature(feature);
+ return tree;
+ }
+
+ |
+
+ // TreeNode with no case feature an no adjunction allowed (e.g. (^S DP...))
+ "(" "^" category = Cat() treelist=TreeList() ")"
+ {
+ TreeNode tree = new Tree();
+ tree.setCategory(category);
+ tree.setChildren(treelist);
+ tree.setParentForTree();
+ tree.setAdjConstraint(true);
+ return tree;
+ }
+
+ |
+
+ // TerminalNode with case feature (e.g. N|nom:'house')
+ category = Cat() ("{" feature=Feat() "}")? ":" "'" (terminal = Terminal())? "'"
+ {
+ TerminalNode node = new TerminalNode(terminal, category);
+ node.setCategory(category);
+ node.setFeature(feature);
+ return node;
+ }
+
+}
+
+
+String Terminal() :
+{
+ Token word;
+ String terminal=null;
+}
+{
+ word = <WORD> (terminal=Terminal())?
+ {
+ if (terminal != null) return word.toString() + " " + terminal;
+ return word.toString();
+ }
+}
+
+List<TreeNode> TreeList() :
+{
+ List<TreeNode> treelist = null;
+ TreeNode tree;
+}
+{
+
+ tree = Tree() (treelist=TreeList())?
+ {
+ if (treelist == null)
+ {
+ treelist = new ArrayList<TreeNode>();
+ }
+
+ treelist.add(0,tree);
+ return treelist;
+ }
+}
+
+
+Category Cat() :
+{
+ Token cat;
+}
+{
+ cat=<CATEGORY>
+ {
+ if (cat.toString().equals("DP")) return Category.DP;
+ if (cat.toString().equals("NP")) return Category.NP;
+ if (cat.toString().equals("N")) return Category.N;
+ if (cat.toString().equals("S")) return Category.S;
+ if (cat.toString().equals("V")) return Category.V;
+ if (cat.toString().equals("P")) return Category.P;
+ if (cat.toString().equals("VP")) return Category.VP;
+ if (cat.toString().equals("PP")) return Category.PP;
+ if (cat.toString().equals("DET")) return Category.DET;
+ if (cat.toString().equals("WH")) return Category.WH;
+ if (cat.toString().equals("ADV")) return Category.ADV;
+ if (cat.toString().equals("ADJ")) return Category.ADJ;
+ if (cat.toString().equals("ADJCOMP")) return Category.ADJCOMP;
+ if (cat.toString().equals("PART")) return Category.PART;
+ if (cat.toString().equals("PUNCT")) return Category.PUNCT;
+ if (cat.toString().equals("CC")) return Category.CC;
+ if (cat.toString().equals("EX")) return Category.EX;
+ if (cat.toString().equals("NUM")) return Category.NUM;
+ if (cat.toString().equals("C")) return Category.C;
+ if (cat.toString().equals("NEG")) return Category.NEG;
+ }
+
+}
+
+Feature Feat() :
+{
+ Token raw;
+}
+{
+
+ raw=<WORD>
+ {
+
+ return Feature.construct(raw.toString());
+ }
+}
+
+TOKEN: {<WORD: (["a"-"z"]|["0"-"9"]|["?"]|["-"]|["_"]|["!"]|[","]|[";"]|["."]|[":"]|["/"])+>}
+
+TOKEN: {<CATEGORY: (["A"-"Z"])+>}
+
+SKIP : { " " | "\t" | "\n" | "\r" }
+
+
+
Property changes on: trunk/components-ext/src/main/javacc/LTAG_Parser.jj
___________________________________________________________________
Added: svn:executable
+ *
Modified: trunk/components-ext/src/main/resources/tbsl/lexicon/basic_english.lex
===================================================================
--- trunk/components-ext/src/main/resources/tbsl/lexicon/basic_english.lex 2012-05-08 11:53:28 UTC (rev 3697)
+++ trunk/components-ext/src/main/resources/tbsl/lexicon/basic_english.lex 2012-05-09 15:28:25 UTC (rev 3698)
@@ -90,7 +90,7 @@
the least || (DET DET:'the' DET:'least') || <y, l1, e, [ l1:[ | l2:[ y | ] THELEAST y l3:[|] ] ], [], [],[]>
// NECESSARY "CHEAT"
- highest || (NP ADJ:'highest' NP*) || <x, l1, e, [ l1:[ | maximum(x) ] ], [], [],[]> ;; <x, l1, e, [ l1:[ j | SLOT_high(x,j), maximum(j) ] ],[],[],[ SLOT_high/PROPERTY/height ]>
+ highest || (NP ADJ:'highest' NP*) || <x, l1, e, [ l1:[ j | SLOT_high(x,j), maximum(j) ] ],[],[],[ SLOT_high/PROPERTY/height ]> ;; <x, l1, e, [ l1:[ | maximum(x) ] ], [], [],[]>
// COUNT
more than || (DP DET:'more' DET:'than' NUM[num] NP[np]) || <y,l1,<<e,t>,t>,[ l1:[ y,c | count_greater(y,z) ] ],[(l2,y,np,<e,t>),(l3,z,num,e)],[l2=l1,l3=l1],[]> ;; <y,l1,<<e,t>,t>,[ l1:[ y | greater(y,z) ] ],[(l2,y,np,<e,t>),(l3,z,num,e)],[l2=l1,l3=l1],[]>
@@ -125,6 +125,7 @@
what || (DP WH:'what') || <x, l1, <<e,t>,t>, [ l1:[ ?x | ] ], [], [], []>
which || (DP WH:'which') || <x, l1, <<e,t>,t>, [ l1:[ ?x | ] ], [], [], []>
how many || (DP WH:'how' ADJ:'many' NP[noun]) || <y, l1, <<e,t>,t>, [ l1:[ | l2:[ y | ] HOWMANY y l3:[|] ] ], [ (l4,y,noun,<e,t>) ], [ l4=l2 ],[]>
+ how many || (DP WH:'how' ADJ:'many' NP[noun]) || <y, l1, <<e,t>,t>, [ l1:[ ?y | ] ], [ (l4,y,noun,<e,t>) ], [ l4=l1 ],[]>
who || (DP WH:'who') || <x, l1, <<e,t>,t>, [ l1:[ ?x | ] ], [], [], []>
whom || (DP WH:'whom') || <x, l1, <<e,t>,t>, [ l1:[ ?x | ] ], [], [], []>
when || (S WH:'when' S[s]) || <x, l1, t, [ l1:[ ?x | SLOT_p(y,x) ] ], [(l2,y,s,t)], [l2=l1], [ SLOT_p/PROPERTY/date ]>
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
