Index: CHANGES.txt
===================================================================
--- CHANGES.txt (revision 806552)
+++ CHANGES.txt (working copy)
@@ -915,6 +915,9 @@
position are joined with a |. (Andrzej Bialecki via Mike
McCandless)
+ 5. LUCENE-1787: Additionally match ACRONYMS without trailing dot. So now
+ identifies I.B.M as an acronym, previously would only recognise I.B.M.
+
API Changes
1. LUCENE-1084: Changed all IndexWriter constructors to take an
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java (revision 806552)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java (working copy)
@@ -1,4 +1,4 @@
-/* The following code was generated by JFlex 1.4.1 on 9/4/08 6:49 PM */
+/* The following code was generated by JFlex 1.4.3 on 8/21/09 5:10 PM */
package org.apache.lucene.analysis.standard;
@@ -21,11 +21,12 @@
/*
-NOTE: if you change this file and need to regenerate the tokenizer,
- remember to use JRE 1.4 when running jflex (before Lucene 3.0).
- This grammar now uses constructs (eg :digit:) whose meaning can
- vary according to the JRE used to run jflex. See
- https://issues.apache.org/jira/browse/LUCENE-1126 for details
+NOTE: if you change StandardTokenizerImpl.jflex and need to regenerate
+ the tokenizer, remember to use JRE 1.4 to run jflex (before
+ Lucene 3.0). This grammar now uses constructs (eg :digit:,
+ :letter:) whose meaning can vary according to the JRE used to
+ run jflex. See
+ https://issues.apache.org/jira/browse/LUCENE-1126 for details.
*/
@@ -35,9 +36,9 @@
/**
* This class is a scanner generated by
- * JFlex 1.4.1
- * on 9/4/08 6:49 PM from the specification file
- * /tango/mike/src/lucene.standarddigit/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex
+ * JFlex 1.4.3
+ * on 8/21/09 5:10 PM from the specification file
+ * /Users/paul/code/lucenesvn/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex
*/
class StandardTokenizerImpl {
@@ -50,6 +51,16 @@
/** lexical states */
public static final int YYINITIAL = 0;
+ /**
+ * ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l
+ * ZZ_LEXSTATE[l+1] is the state in the DFA for the lexical state l
+ * at the beginning of a line
+ * l is of the form l = 2*k, k a non negative integer
+ */
+ private static final int ZZ_LEXSTATE[] = {
+ 0, 0
+ };
+
/**
* Translates characters to character classes
*/
@@ -57,59 +68,63 @@
"\11\0\1\0\1\15\1\0\1\0\1\14\22\0\1\0\5\0\1\5"+
"\1\3\4\0\1\11\1\7\1\4\1\11\12\2\6\0\1\6\32\12"+
"\4\0\1\10\1\0\32\12\57\0\1\12\12\0\1\12\4\0\1\12"+
- "\5\0\27\12\1\0\37\12\1\0\u0128\12\2\0\22\12\34\0\136\12"+
- "\2\0\11\12\2\0\7\12\16\0\2\12\16\0\5\12\11\0\1\12"+
- "\213\0\1\12\13\0\1\12\1\0\3\12\1\0\1\12\1\0\24\12"+
- "\1\0\54\12\1\0\10\12\2\0\32\12\14\0\202\12\12\0\71\12"+
- "\2\0\2\12\2\0\2\12\3\0\46\12\2\0\2\12\67\0\46\12"+
- "\2\0\1\12\7\0\47\12\110\0\33\12\5\0\3\12\56\0\32\12"+
- "\5\0\13\12\25\0\12\2\7\0\143\12\1\0\1\12\17\0\2\12"+
- "\11\0\12\2\3\12\23\0\1\12\1\0\33\12\123\0\46\12\u015f\0"+
- "\65\12\3\0\1\12\22\0\1\12\7\0\12\12\4\0\12\2\25\0"+
- "\10\12\2\0\2\12\2\0\26\12\1\0\7\12\1\0\1\12\3\0"+
- "\4\12\42\0\2\12\1\0\3\12\4\0\12\2\2\12\23\0\6\12"+
- "\4\0\2\12\2\0\26\12\1\0\7\12\1\0\2\12\1\0\2\12"+
- "\1\0\2\12\37\0\4\12\1\0\1\12\7\0\12\2\2\0\3\12"+
- "\20\0\7\12\1\0\1\12\1\0\3\12\1\0\26\12\1\0\7\12"+
- "\1\0\2\12\1\0\5\12\3\0\1\12\22\0\1\12\17\0\1\12"+
- "\5\0\12\2\25\0\10\12\2\0\2\12\2\0\26\12\1\0\7\12"+
- "\1\0\2\12\2\0\4\12\3\0\1\12\36\0\2\12\1\0\3\12"+
- "\4\0\12\2\25\0\6\12\3\0\3\12\1\0\4\12\3\0\2\12"+
- "\1\0\1\12\1\0\2\12\3\0\2\12\3\0\3\12\3\0\10\12"+
- "\1\0\3\12\55\0\11\2\25\0\10\12\1\0\3\12\1\0\27\12"+
- "\1\0\12\12\1\0\5\12\46\0\2\12\4\0\12\2\25\0\10\12"+
- "\1\0\3\12\1\0\27\12\1\0\12\12\1\0\5\12\44\0\1\12"+
- "\1\0\2\12\4\0\12\2\25\0\10\12\1\0\3\12\1\0\27\12"+
- "\1\0\20\12\46\0\2\12\4\0\12\2\25\0\22\12\3\0\30\12"+
- "\1\0\11\12\1\0\1\12\2\0\7\12\71\0\1\1\60\12\1\1"+
- "\2\12\14\1\7\12\11\1\12\2\47\0\2\12\1\0\1\12\2\0"+
- "\2\12\1\0\1\12\2\0\1\12\6\0\4\12\1\0\7\12\1\0"+
- "\3\12\1\0\1\12\1\0\1\12\2\0\2\12\1\0\4\12\1\0"+
- "\2\12\11\0\1\12\2\0\5\12\1\0\1\12\11\0\12\2\2\0"+
- "\2\12\42\0\1\12\37\0\12\2\26\0\10\12\1\0\42\12\35\0"+
- "\4\12\164\0\42\12\1\0\5\12\1\0\2\12\25\0\12\2\6\0"+
- "\6\12\112\0\46\12\12\0\47\12\11\0\132\12\5\0\104\12\5\0"+
- "\122\12\6\0\7\12\1\0\77\12\1\0\1\12\1\0\4\12\2\0"+
- "\7\12\1\0\1\12\1\0\4\12\2\0\47\12\1\0\1\12\1\0"+
- "\4\12\2\0\37\12\1\0\1\12\1\0\4\12\2\0\7\12\1\0"+
- "\1\12\1\0\4\12\2\0\7\12\1\0\7\12\1\0\27\12\1\0"+
- "\37\12\1\0\1\12\1\0\4\12\2\0\7\12\1\0\47\12\1\0"+
- "\23\12\16\0\11\2\56\0\125\12\14\0\u026c\12\2\0\10\12\12\0"+
- "\32\12\5\0\113\12\225\0\64\12\54\0\12\2\46\0\12\2\6\0"+
- "\130\12\10\0\51\12\u0557\0\234\12\4\0\132\12\6\0\26\12\2\0"+
- "\6\12\2\0\46\12\2\0\6\12\2\0\10\12\1\0\1\12\1\0"+
- "\1\12\1\0\1\12\1\0\37\12\2\0\65\12\1\0\7\12\1\0"+
- "\1\12\3\0\3\12\1\0\7\12\3\0\4\12\2\0\6\12\4\0"+
- "\15\12\5\0\3\12\1\0\7\12\202\0\1\12\202\0\1\12\4\0"+
- "\1\12\2\0\12\12\1\0\1\12\3\0\5\12\6\0\1\12\1\0"+
- "\1\12\1\0\1\12\1\0\4\12\1\0\3\12\1\0\7\12\u0ecb\0"+
- "\2\12\52\0\5\12\12\0\1\13\124\13\10\13\2\13\2\13\132\13"+
- "\1\13\3\13\6\13\50\13\3\13\1\0\136\12\21\0\30\12\70\0"+
+ "\5\0\27\12\1\0\37\12\1\0\u013f\12\31\0\162\12\4\0\14\12"+
+ "\16\0\5\12\11\0\1\12\213\0\1\12\13\0\1\12\1\0\3\12"+
+ "\1\0\1\12\1\0\24\12\1\0\54\12\1\0\46\12\1\0\5\12"+
+ "\4\0\202\12\10\0\105\12\1\0\46\12\2\0\2\12\6\0\20\12"+
+ "\41\0\46\12\2\0\1\12\7\0\47\12\110\0\33\12\5\0\3\12"+
+ "\56\0\32\12\5\0\13\12\25\0\12\2\4\0\2\12\1\0\143\12"+
+ "\1\0\1\12\17\0\2\12\7\0\2\12\12\2\3\12\2\0\1\12"+
+ "\20\0\1\12\1\0\36\12\35\0\3\12\60\0\46\12\13\0\1\12"+
+ "\u0152\0\66\12\3\0\1\12\22\0\1\12\7\0\12\12\4\0\12\2"+
+ "\25\0\10\12\2\0\2\12\2\0\26\12\1\0\7\12\1\0\1\12"+
+ "\3\0\4\12\3\0\1\12\36\0\2\12\1\0\3\12\4\0\12\2"+
+ "\2\12\23\0\6\12\4\0\2\12\2\0\26\12\1\0\7\12\1\0"+
+ "\2\12\1\0\2\12\1\0\2\12\37\0\4\12\1\0\1\12\7\0"+
+ "\12\2\2\0\3\12\20\0\11\12\1\0\3\12\1\0\26\12\1\0"+
+ "\7\12\1\0\2\12\1\0\5\12\3\0\1\12\22\0\1\12\17\0"+
+ "\2\12\4\0\12\2\25\0\10\12\2\0\2\12\2\0\26\12\1\0"+
+ "\7\12\1\0\2\12\1\0\5\12\3\0\1\12\36\0\2\12\1\0"+
+ "\3\12\4\0\12\2\1\0\1\12\21\0\1\12\1\0\6\12\3\0"+
+ "\3\12\1\0\4\12\3\0\2\12\1\0\1\12\1\0\2\12\3\0"+
+ "\2\12\3\0\3\12\3\0\10\12\1\0\3\12\55\0\11\2\25\0"+
+ "\10\12\1\0\3\12\1\0\27\12\1\0\12\12\1\0\5\12\46\0"+
+ "\2\12\4\0\12\2\25\0\10\12\1\0\3\12\1\0\27\12\1\0"+
+ "\12\12\1\0\5\12\3\0\1\12\40\0\1\12\1\0\2\12\4\0"+
+ "\12\2\25\0\10\12\1\0\3\12\1\0\27\12\1\0\20\12\46\0"+
+ "\2\12\4\0\12\2\25\0\22\12\3\0\30\12\1\0\11\12\1\0"+
+ "\1\12\2\0\7\12\71\0\1\1\60\12\1\1\2\12\14\1\7\12"+
+ "\11\1\12\2\47\0\2\12\1\0\1\12\2\0\2\12\1\0\1\12"+
+ "\2\0\1\12\6\0\4\12\1\0\7\12\1\0\3\12\1\0\1\12"+
+ "\1\0\1\12\2\0\2\12\1\0\4\12\1\0\2\12\11\0\1\12"+
+ "\2\0\5\12\1\0\1\12\11\0\12\2\2\0\2\12\42\0\1\12"+
+ "\37\0\12\2\26\0\10\12\1\0\42\12\35\0\4\12\164\0\42\12"+
+ "\1\0\5\12\1\0\2\12\25\0\12\2\6\0\6\12\112\0\46\12"+
+ "\12\0\51\12\7\0\132\12\5\0\104\12\5\0\122\12\6\0\7\12"+
+ "\1\0\77\12\1\0\1\12\1\0\4\12\2\0\7\12\1\0\1\12"+
+ "\1\0\4\12\2\0\47\12\1\0\1\12\1\0\4\12\2\0\37\12"+
+ "\1\0\1\12\1\0\4\12\2\0\7\12\1\0\1\12\1\0\4\12"+
+ "\2\0\7\12\1\0\7\12\1\0\27\12\1\0\37\12\1\0\1\12"+
+ "\1\0\4\12\2\0\7\12\1\0\47\12\1\0\23\12\16\0\11\2"+
+ "\56\0\125\12\14\0\u026c\12\2\0\10\12\12\0\32\12\5\0\113\12"+
+ "\25\0\15\12\1\0\4\12\16\0\22\12\16\0\22\12\16\0\15\12"+
+ "\1\0\3\12\17\0\64\12\43\0\1\12\4\0\1\12\3\0\12\2"+
+ "\46\0\12\2\6\0\130\12\10\0\51\12\127\0\35\12\51\0\12\2"+
+ "\36\12\2\0\5\12\u038b\0\154\12\224\0\234\12\4\0\132\12\6\0"+
+ "\26\12\2\0\6\12\2\0\46\12\2\0\6\12\2\0\10\12\1\0"+
+ "\1\12\1\0\1\12\1\0\1\12\1\0\37\12\2\0\65\12\1\0"+
+ "\7\12\1\0\1\12\3\0\3\12\1\0\7\12\3\0\4\12\2\0"+
+ "\6\12\4\0\15\12\5\0\3\12\1\0\7\12\164\0\1\12\15\0"+
+ "\1\12\202\0\1\12\4\0\1\12\2\0\12\12\1\0\1\12\3\0"+
+ "\5\12\6\0\1\12\1\0\1\12\1\0\1\12\1\0\4\12\1\0"+
+ "\3\12\1\0\7\12\3\0\3\12\5\0\5\12\u0ebb\0\2\12\52\0"+
+ "\5\12\5\0\2\12\3\0\1\13\126\13\6\13\3\13\1\13\132\13"+
+ "\1\13\4\13\5\13\50\13\3\13\1\0\136\12\21\0\30\12\70\0"+
"\20\13\u0100\0\200\13\200\0\u19b6\13\12\13\100\0\u51a6\13\132\13\u048d\12"+
- "\u0773\0\u2ba4\12\u215c\0\u012e\13\322\13\7\12\14\0\5\12\5\0\1\12"+
- "\1\0\12\12\1\0\15\12\1\0\5\12\1\0\1\12\1\0\2\12"+
- "\1\0\2\12\1\0\154\12\41\0\u016b\12\22\0\100\12\2\0\66\12"+
- "\50\0\14\12\164\0\3\12\1\0\1\12\1\0\207\12\23\0\12\2"+
+ "\u0773\0\u2ba4\12\u215c\0\u012e\13\2\13\73\13\225\13\7\12\14\0\5\12"+
+ "\5\0\1\12\1\0\12\12\1\0\15\12\1\0\5\12\1\0\1\12"+
+ "\1\0\2\12\1\0\2\12\1\0\154\12\41\0\u016b\12\22\0\100\12"+
+ "\2\0\66\12\50\0\14\12\164\0\5\12\1\0\207\12\23\0\12\2"+
"\7\0\32\12\6\0\32\12\12\0\1\13\72\13\37\12\3\0\6\12"+
"\2\0\6\12\2\0\6\12\2\0\3\12\43\0";
@@ -125,9 +140,9 @@
private static final String ZZ_ACTION_PACKED_0 =
"\1\0\1\1\3\2\1\3\1\1\13\0\1\2\3\4"+
- "\2\0\1\5\1\0\1\5\3\4\6\5\1\6\1\4"+
- "\2\7\1\10\1\0\1\10\3\0\2\10\1\11\1\12"+
- "\1\4";
+ "\2\0\1\5\1\0\1\5\3\4\6\5\1\6\1\7"+
+ "\2\10\1\11\1\0\1\11\3\0\2\11\1\7\1\12"+
+ "\1\7";
private static int [] zzUnpackAction() {
int [] result = new int[51];
@@ -305,9 +320,6 @@
/** the textposition at the last accepting state */
private int zzMarkedPos;
- /** the textposition at the last state to be included in yytext */
- private int zzPushbackPos;
-
/** the current text position in the buffer */
private int zzCurrentPos;
@@ -338,6 +350,9 @@
/** zzAtEOF == true <=> the scanner is at the EOF */
private boolean zzAtEOF;
+ /** denotes if the user-EOF-code has already been executed */
+ private boolean zzEOFDone;
+
/* user code: */
public static final int ALPHANUM = StandardTokenizer.ALPHANUM;
@@ -377,6 +392,7 @@
}
+
/**
* Creates a new scanner
* There is also a java.io.InputStream version of this constructor.
@@ -407,7 +423,7 @@
char [] map = new char[0x10000];
int i = 0; /* index in packed string */
int j = 0; /* index in unpacked array */
- while (i < 1154) {
+ while (i < 1234) {
int count = packed.charAt(i++);
char value = packed.charAt(i++);
do map[j++] = value; while (--count > 0);
@@ -435,7 +451,6 @@
zzEndRead-= zzStartRead;
zzCurrentPos-= zzStartRead;
zzMarkedPos-= zzStartRead;
- zzPushbackPos-= zzStartRead;
zzStartRead = 0;
}
@@ -451,13 +466,23 @@
int numRead = zzReader.read(zzBuffer, zzEndRead,
zzBuffer.length-zzEndRead);
- if (numRead < 0) {
- return true;
- }
- else {
+ if (numRead > 0) {
zzEndRead+= numRead;
return false;
}
+ // unlikely but not impossible: read 0 characters, but not at end of stream
+ if (numRead == 0) {
+ int c = zzReader.read();
+ if (c == -1) {
+ return true;
+ } else {
+ zzBuffer[zzEndRead++] = (char) c;
+ return false;
+ }
+ }
+
+ // numRead < 0
+ return true;
}
@@ -487,8 +512,9 @@
zzReader = reader;
zzAtBOL = true;
zzAtEOF = false;
+ zzEOFDone = false;
zzEndRead = zzStartRead = 0;
- zzCurrentPos = zzMarkedPos = zzPushbackPos = 0;
+ zzCurrentPos = zzMarkedPos = 0;
yyline = yychar = yycolumn = 0;
zzLexicalState = YYINITIAL;
}
@@ -618,7 +644,7 @@
zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
- zzState = zzLexicalState;
+ zzState = ZZ_LEXSTATE[zzLexicalState];
zzForAction: {
@@ -671,11 +697,11 @@
}
case 11: break;
case 9:
- { return ACRONYM;
+ { return ACRONYM_DEP;
}
case 12: break;
- case 8:
- { return ACRONYM_DEP;
+ case 7:
+ { return ACRONYM;
}
case 13: break;
case 1:
@@ -694,7 +720,7 @@
{ return ALPHANUM;
}
case 17: break;
- case 7:
+ case 8:
{ return COMPANY;
}
case 18: break;
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex (revision 806552)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex (working copy)
@@ -89,9 +89,9 @@
// use a post-filter to remove possesives
APOSTROPHE = {ALPHA} ("'" {ALPHA})+
-// acronyms: U.S.A., I.B.M., etc.
+// acronyms (with or without trailing dot): U.S.A., I.B.M, etc.
// use a post-filter to remove dots
-ACRONYM = {LETTER} "." ({LETTER} ".")+
+ACRONYM = {LETTER} ("." {LETTER})+ (".")?
ACRONYM_DEP = {ALPHANUM} "." ({ALPHANUM} ".")+
Index: src/test/org/apache/lucene/analysis/TestStandardAnalyzer.java
===================================================================
--- src/test/org/apache/lucene/analysis/TestStandardAnalyzer.java (revision 806552)
+++ src/test/org/apache/lucene/analysis/TestStandardAnalyzer.java (working copy)
@@ -187,6 +187,8 @@
public void testAcronyms() throws Exception {
// acronyms have their dots stripped
assertAnalyzesTo(a, "U.S.A.", new String[]{"usa"});
+ assertAnalyzesTo(a, "I.B.M", new String[]{"ibm"});
+
}
public void testCPlusPlusHash() throws Exception {
@@ -261,4 +263,6 @@
// this should be removed once replaceDepAcronym is removed.
assertAnalyzesTo(a, "lucene.apache.org.", new String[]{ "lucene.apache.org" }, new String[] { "" });
}
+
+
}