goller 2004/09/14 06:45:16
Modified: src/java/org/apache/lucene/queryParser
QueryParserTokenManager.java QueryParser.jj
QueryParser.java QueryParserConstants.java
src/java/org/apache/lucene/search FuzzyQuery.java
FuzzyTermEnum.java
Log:
QueryParser can now handle minimumSimilarity parameter
of FuzzyQuery; FuzzyQuery extended to allow for non-fuzzy
prefixes.
Revision Changes Path
1.4 +133 -117
jakarta-lucene/src/java/org/apache/lucene/queryParser/QueryParserTokenManager.java
Index: QueryParserTokenManager.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/queryParser/QueryParserTokenManager.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- QueryParserTokenManager.java 24 Mar 2004 10:12:27 -0000 1.3
+++ QueryParserTokenManager.java 14 Sep 2004 13:45:15 -0000 1.4
@@ -54,13 +54,11 @@
case 58:
return jjStopAtPos(0, 14);
case 91:
- return jjStopAtPos(0, 22);
+ return jjStopAtPos(0, 21);
case 94:
return jjStopAtPos(0, 15);
case 123:
- return jjStopAtPos(0, 23);
- case 126:
- return jjStartNfaWithStates_3(0, 18, 18);
+ return jjStopAtPos(0, 22);
default :
return jjMoveNfa_3(0, 0);
}
@@ -105,7 +103,7 @@
{
int[] nextStates;
int startsAt = 0;
- jjnewStateCnt = 31;
+ jjnewStateCnt = 33;
int i = 1;
jjstateSet[0] = startState;
int j, kind = 0x7fffffff;
@@ -169,56 +167,67 @@
case 18:
if ((0x3ff000000000000L & l) == 0L)
break;
- if (kind > 19)
- kind = 19;
- jjstateSet[jjnewStateCnt++] = 18;
+ if (kind > 18)
+ kind = 18;
+ jjAddStates(7, 8);
break;
case 19:
+ if (curChar == 46)
+ jjCheckNAdd(20);
+ break;
+ case 20:
+ if ((0x3ff000000000000L & l) == 0L)
+ break;
+ if (kind > 18)
+ kind = 18;
+ jjCheckNAdd(20);
+ break;
+ case 21:
if ((0x7bffd0f8ffffd9ffL & l) == 0L)
break;
if (kind > 17)
kind = 17;
jjCheckNAddStates(0, 6);
break;
- case 20:
+ case 22:
if ((0x7bfff8f8ffffd9ffL & l) == 0L)
break;
if (kind > 17)
kind = 17;
- jjCheckNAddTwoStates(20, 21);
+ jjCheckNAddTwoStates(22, 23);
break;
- case 22:
+ case 24:
if ((0x84002f0600000000L & l) == 0L)
break;
if (kind > 17)
kind = 17;
- jjCheckNAddTwoStates(20, 21);
+ jjCheckNAddTwoStates(22, 23);
break;
- case 23:
+ case 25:
if ((0x7bfff8f8ffffd9ffL & l) != 0L)
- jjCheckNAddStates(7, 9);
- break;
- case 24:
- if (curChar == 42 && kind > 20)
- kind = 20;
+ jjCheckNAddStates(9, 11);
break;
case 26:
+ if (curChar == 42 && kind > 19)
+ kind = 19;
+ break;
+ case 28:
if ((0x84002f0600000000L & l) != 0L)
- jjCheckNAddStates(7, 9);
+ jjCheckNAddStates(9, 11);
break;
- case 27:
+ case 29:
if ((0xfbfffcf8ffffd9ffL & l) == 0L)
break;
- if (kind > 21)
- kind = 21;
- jjCheckNAddTwoStates(27, 28);
+ if (kind > 20)
+ kind = 20;
+ jjCheckNAddTwoStates(29, 30);
break;
- case 29:
+ case 31:
if ((0x84002f0600000000L & l) == 0L)
break;
- if (kind > 21)
- kind = 21;
- jjCheckNAddTwoStates(27, 28);
+ if (kind > 20)
+ kind = 20;
+ jjCheckNAddTwoStates(29, 30);
break;
default : break;
}
@@ -239,9 +248,13 @@
jjCheckNAddStates(0, 6);
}
else if (curChar == 126)
+ {
+ if (kind > 18)
+ kind = 18;
jjstateSet[jjnewStateCnt++] = 18;
+ }
if (curChar == 92)
- jjCheckNAddStates(10, 12);
+ jjCheckNAddStates(12, 14);
else if (curChar == 78)
jjstateSet[jjnewStateCnt++] = 11;
else if (curChar == 124)
@@ -292,70 +305,73 @@
jjstateSet[jjnewStateCnt++] = 11;
break;
case 15:
- jjAddStates(13, 14);
+ jjAddStates(15, 16);
break;
case 17:
- if (curChar == 126)
- jjstateSet[jjnewStateCnt++] = 18;
+ if (curChar != 126)
+ break;
+ if (kind > 18)
+ kind = 18;
+ jjstateSet[jjnewStateCnt++] = 18;
break;
- case 19:
+ case 21:
if ((0x97ffffff97ffffffL & l) == 0L)
break;
if (kind > 17)
kind = 17;
jjCheckNAddStates(0, 6);
break;
- case 20:
+ case 22:
if ((0x97ffffff97ffffffL & l) == 0L)
break;
if (kind > 17)
kind = 17;
- jjCheckNAddTwoStates(20, 21);
+ jjCheckNAddTwoStates(22, 23);
break;
- case 21:
+ case 23:
if (curChar == 92)
- jjCheckNAddTwoStates(22, 22);
+ jjCheckNAddTwoStates(24, 24);
break;
- case 22:
+ case 24:
if ((0x6800000078000000L & l) == 0L)
break;
if (kind > 17)
kind = 17;
- jjCheckNAddTwoStates(20, 21);
+ jjCheckNAddTwoStates(22, 23);
break;
- case 23:
+ case 25:
if ((0x97ffffff97ffffffL & l) != 0L)
- jjCheckNAddStates(7, 9);
+ jjCheckNAddStates(9, 11);
break;
- case 25:
+ case 27:
if (curChar == 92)
- jjCheckNAddTwoStates(26, 26);
+ jjCheckNAddTwoStates(28, 28);
break;
- case 26:
+ case 28:
if ((0x6800000078000000L & l) != 0L)
- jjCheckNAddStates(7, 9);
+ jjCheckNAddStates(9, 11);
break;
- case 27:
+ case 29:
if ((0x97ffffff97ffffffL & l) == 0L)
break;
- if (kind > 21)
- kind = 21;
- jjCheckNAddTwoStates(27, 28);
+ if (kind > 20)
+ kind = 20;
+ jjCheckNAddTwoStates(29, 30);
break;
- case 28:
+ case 30:
if (curChar == 92)
- jjCheckNAddTwoStates(29, 29);
+ jjCheckNAddTwoStates(31, 31);
break;
- case 29:
+ case 31:
if ((0x6800000078000000L & l) == 0L)
break;
- if (kind > 21)
- kind = 21;
- jjCheckNAddTwoStates(27, 28);
+ if (kind > 20)
+ kind = 20;
+ jjCheckNAddTwoStates(29, 30);
break;
- case 30:
+ case 32:
if (curChar == 92)
- jjCheckNAddStates(10, 12);
+ jjCheckNAddStates(12, 14);
break;
default : break;
}
@@ -381,25 +397,25 @@
break;
case 15:
if (jjCanMove_0(hiByte, i1, i2, l1, l2))
- jjAddStates(13, 14);
+ jjAddStates(15, 16);
break;
- case 20:
+ case 22:
if (!jjCanMove_0(hiByte, i1, i2, l1, l2))
break;
if (kind > 17)
kind = 17;
- jjCheckNAddTwoStates(20, 21);
+ jjCheckNAddTwoStates(22, 23);
break;
- case 23:
+ case 25:
if (jjCanMove_0(hiByte, i1, i2, l1, l2))
- jjCheckNAddStates(7, 9);
+ jjCheckNAddStates(9, 11);
break;
- case 27:
+ case 29:
if (!jjCanMove_0(hiByte, i1, i2, l1, l2))
break;
- if (kind > 21)
- kind = 21;
- jjCheckNAddTwoStates(27, 28);
+ if (kind > 20)
+ kind = 20;
+ jjCheckNAddTwoStates(29, 30);
break;
default : break;
}
@@ -412,7 +428,7 @@
kind = 0x7fffffff;
}
++curPos;
- if ((i = jjnewStateCnt) == (startsAt = 31 - (jjnewStateCnt = startsAt)))
+ if ((i = jjnewStateCnt) == (startsAt = 33 - (jjnewStateCnt = startsAt)))
return curPos;
try { curChar = input_stream.readChar(); }
catch(java.io.IOException e) { return curPos; }
@@ -423,9 +439,9 @@
switch (pos)
{
case 0:
- if ((active0 & 0x20000000L) != 0L)
+ if ((active0 & 0x10000000L) != 0L)
{
- jjmatchedKind = 32;
+ jjmatchedKind = 31;
return 4;
}
return -1;
@@ -450,9 +466,9 @@
switch(curChar)
{
case 84:
- return jjMoveStringLiteralDfa1_1(0x20000000L);
+ return jjMoveStringLiteralDfa1_1(0x10000000L);
case 125:
- return jjStopAtPos(0, 30);
+ return jjStopAtPos(0, 29);
default :
return jjMoveNfa_1(0, 0);
}
@@ -467,8 +483,8 @@
switch(curChar)
{
case 79:
- if ((active0 & 0x20000000L) != 0L)
- return jjStartNfaWithStates_1(1, 29, 4);
+ if ((active0 & 0x10000000L) != 0L)
+ return jjStartNfaWithStates_1(1, 28, 4);
break;
default :
break;
@@ -497,8 +513,8 @@
case 0:
if ((0xfffffffeffffffffL & l) != 0L)
{
- if (kind > 32)
- kind = 32;
+ if (kind > 31)
+ kind = 31;
jjCheckNAdd(4);
}
if ((0x100002600L & l) != 0L)
@@ -518,14 +534,14 @@
jjCheckNAddTwoStates(2, 3);
break;
case 3:
- if (curChar == 34 && kind > 31)
- kind = 31;
+ if (curChar == 34 && kind > 30)
+ kind = 30;
break;
case 4:
if ((0xfffffffeffffffffL & l) == 0L)
break;
- if (kind > 32)
- kind = 32;
+ if (kind > 31)
+ kind = 31;
jjCheckNAdd(4);
break;
default : break;
@@ -543,12 +559,12 @@
case 4:
if ((0xdfffffffffffffffL & l) == 0L)
break;
- if (kind > 32)
- kind = 32;
+ if (kind > 31)
+ kind = 31;
jjCheckNAdd(4);
break;
case 2:
- jjAddStates(15, 16);
+ jjAddStates(17, 18);
break;
default : break;
}
@@ -569,13 +585,13 @@
case 4:
if (!jjCanMove_0(hiByte, i1, i2, l1, l2))
break;
- if (kind > 32)
- kind = 32;
+ if (kind > 31)
+ kind = 31;
jjCheckNAdd(4);
break;
case 2:
if (jjCanMove_0(hiByte, i1, i2, l1, l2))
- jjAddStates(15, 16);
+ jjAddStates(17, 18);
break;
default : break;
}
@@ -620,9 +636,9 @@
case 0:
if ((0x3ff000000000000L & l) == 0L)
break;
- if (kind > 24)
- kind = 24;
- jjAddStates(17, 18);
+ if (kind > 23)
+ kind = 23;
+ jjAddStates(19, 20);
break;
case 1:
if (curChar == 46)
@@ -631,8 +647,8 @@
case 2:
if ((0x3ff000000000000L & l) == 0L)
break;
- if (kind > 24)
- kind = 24;
+ if (kind > 23)
+ kind = 23;
jjCheckNAdd(2);
break;
default : break;
@@ -683,9 +699,9 @@
switch (pos)
{
case 0:
- if ((active0 & 0x2000000L) != 0L)
+ if ((active0 & 0x1000000L) != 0L)
{
- jjmatchedKind = 28;
+ jjmatchedKind = 27;
return 4;
}
return -1;
@@ -710,9 +726,9 @@
switch(curChar)
{
case 84:
- return jjMoveStringLiteralDfa1_2(0x2000000L);
+ return jjMoveStringLiteralDfa1_2(0x1000000L);
case 93:
- return jjStopAtPos(0, 26);
+ return jjStopAtPos(0, 25);
default :
return jjMoveNfa_2(0, 0);
}
@@ -727,8 +743,8 @@
switch(curChar)
{
case 79:
- if ((active0 & 0x2000000L) != 0L)
- return jjStartNfaWithStates_2(1, 25, 4);
+ if ((active0 & 0x1000000L) != 0L)
+ return jjStartNfaWithStates_2(1, 24, 4);
break;
default :
break;
@@ -757,8 +773,8 @@
case 0:
if ((0xfffffffeffffffffL & l) != 0L)
{
- if (kind > 28)
- kind = 28;
+ if (kind > 27)
+ kind = 27;
jjCheckNAdd(4);
}
if ((0x100002600L & l) != 0L)
@@ -778,14 +794,14 @@
jjCheckNAddTwoStates(2, 3);
break;
case 3:
- if (curChar == 34 && kind > 27)
- kind = 27;
+ if (curChar == 34 && kind > 26)
+ kind = 26;
break;
case 4:
if ((0xfffffffeffffffffL & l) == 0L)
break;
- if (kind > 28)
- kind = 28;
+ if (kind > 27)
+ kind = 27;
jjCheckNAdd(4);
break;
default : break;
@@ -803,12 +819,12 @@
case 4:
if ((0xffffffffdfffffffL & l) == 0L)
break;
- if (kind > 28)
- kind = 28;
+ if (kind > 27)
+ kind = 27;
jjCheckNAdd(4);
break;
case 2:
- jjAddStates(15, 16);
+ jjAddStates(17, 18);
break;
default : break;
}
@@ -829,13 +845,13 @@
case 4:
if (!jjCanMove_0(hiByte, i1, i2, l1, l2))
break;
- if (kind > 28)
- kind = 28;
+ if (kind > 27)
+ kind = 27;
jjCheckNAdd(4);
break;
case 2:
if (jjCanMove_0(hiByte, i1, i2, l1, l2))
- jjAddStates(15, 16);
+ jjAddStates(17, 18);
break;
default : break;
}
@@ -855,8 +871,8 @@
}
}
static final int[] jjnextStates = {
- 20, 23, 24, 27, 28, 25, 21, 23, 24, 25, 22, 26, 29, 15, 16, 2,
- 3, 0, 1,
+ 22, 25, 26, 29, 30, 27, 23, 18, 19, 25, 26, 27, 24, 28, 31, 15,
+ 16, 2, 3, 0, 1,
};
private static final boolean jjCanMove_0(int hiByte, int i1, int i2, long l1, long
l2)
{
@@ -872,8 +888,8 @@
}
public static final String[] jjstrLiteralImages = {
"", null, null, null, null, null, null, null, null, null, "\53", "\55", "\50",
-"\51", "\72", "\136", null, null, "\176", null, null, null, "\133", "\173", null,
-"\124\117", "\135", null, null, "\124\117", "\175", null, null, };
+"\51", "\72", "\136", null, null, null, null, null, "\133", "\173", null,
"\124\117",
+"\135", null, null, "\124\117", "\175", null, null, };
public static final String[] lexStateNames = {
"Boost",
"RangeEx",
@@ -881,18 +897,18 @@
"DEFAULT",
};
public static final int[] jjnewLexState = {
- -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, -1, -1, -1, -1,
-1, -1, 2, 1, 3,
- -1, 3, -1, -1, -1, 3, -1, -1,
+ -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, -1, -1, -1, -1,
-1, 2, 1, 3, -1,
+ 3, -1, -1, -1, 3, -1, -1,
};
static final long[] jjtoToken = {
- 0x1ffffff81L,
+ 0xffffff81L,
};
static final long[] jjtoSkip = {
0x40L,
};
protected CharStream input_stream;
-private final int[] jjrounds = new int[31];
-private final int[] jjstateSet = new int[62];
+private final int[] jjrounds = new int[33];
+private final int[] jjstateSet = new int[66];
protected char curChar;
public QueryParserTokenManager(CharStream stream)
{
@@ -914,7 +930,7 @@
{
int i;
jjround = 0x80000001;
- for (i = 31; i-- > 0;)
+ for (i = 33; i-- > 0;)
jjrounds[i] = 0x80000000;
}
public void ReInit(CharStream stream, int lexState)
1.49 +28 -11
jakarta-lucene/src/java/org/apache/lucene/queryParser/QueryParser.jj
Index: QueryParser.jj
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/queryParser/QueryParser.jj,v
retrieving revision 1.48
retrieving revision 1.49
diff -u -r1.48 -r1.49
--- QueryParser.jj 8 Sep 2004 15:06:42 -0000 1.48
+++ QueryParser.jj 14 Sep 2004 13:45:15 -0000 1.49
@@ -96,6 +96,7 @@
Analyzer analyzer;
String field;
int phraseSlop = 0;
+ float fuzzyMinSim = FuzzyQuery.defaultMinSimilarity;
Locale locale = Locale.getDefault();
/** Parses a query string, returning a [EMAIL PROTECTED]
org.apache.lucene.search.Query}.
@@ -151,6 +152,19 @@
public String getField() {
return field;
}
+
+ /**
+ * Get the default minimal similarity for fuzzy queries.
+ */
+ public float getFuzzyMinSim() {
+ return fuzzyMinSim;
+ }
+ /**
+ *Set the default minimum similarity for fuzzy queries.
+ */
+ public void setFuzzyMinSim(float fuzzyMinSim) {
+ this.fuzzyMinSim = fuzzyMinSim;
+ }
/**
* Sets the default slop for phrases. If zero, then exact phrase matches
@@ -439,10 +453,10 @@
* @return Resulting [EMAIL PROTECTED] Query} built for the term
* @exception ParseException throw in overridden method to disallow
*/
- protected Query getFuzzyQuery(String field, String termStr) throws ParseException
+ protected Query getFuzzyQuery(String field, String termStr, float minSimilarity)
throws ParseException
{
Term t = new Term(field, termStr);
- return new FuzzyQuery(t);
+ return new FuzzyQuery(t, minSimilarity);
}
/**
@@ -531,8 +545,7 @@
| <CARAT: "^" > : Boost
| <QUOTED: "\"" (~["\""])+ "\"">
| <TERM: <_TERM_START_CHAR> (<_TERM_CHAR>)* >
-| <FUZZY: "~" >
-| <SLOP: "~" (<_NUM_CHAR>)+ >
+| <FUZZY_SLOP: "~" ( (<_NUM_CHAR>)+ ( "." (<_NUM_CHAR>)+ )? )? >
| <PREFIXTERM: <_TERM_START_CHAR> (<_TERM_CHAR>)* "*" >
| <WILDTERM: <_TERM_START_CHAR>
(<_TERM_CHAR> | ( [ "*", "?" ] ))* >
@@ -641,7 +654,7 @@
Query Term(String field) : {
- Token term, boost=null, slop=null, goop1, goop2;
+ Token term, boost=null, fuzzySlop=null, goop1, goop2;
boolean prefix = false;
boolean wildcard = false;
boolean fuzzy = false;
@@ -656,8 +669,8 @@
| term=<WILDTERM> { wildcard=true; }
| term=<NUMBER>
)
- [ <FUZZY> { fuzzy=true; } ]
- [ <CARAT> boost=<NUMBER> [ <FUZZY> { fuzzy=true; } ] ]
+ [ fuzzySlop=<FUZZY_SLOP> { fuzzy=true; } ]
+ [ <CARAT> boost=<NUMBER> [ fuzzySlop=<FUZZY_SLOP> { fuzzy=true; } ] ]
{
String termImage=discardEscapeChar(term.image);
if (wildcard) {
@@ -667,7 +680,11 @@
discardEscapeChar(term.image.substring
(0, term.image.length()-1)));
} else if (fuzzy) {
- q = getFuzzyQuery(field, termImage);
+ float fms = fuzzyMinSim;
+ try {
+ fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue();
+ } catch (Exception ignored) { }
+ q = getFuzzyQuery(field, termImage, fms);
} else {
q = getFieldQuery(field, termImage);
}
@@ -708,14 +725,14 @@
q = getRangeQuery(field, goop1.image, goop2.image, false);
}
| term=<QUOTED>
- [ slop=<SLOP> ]
+ [ fuzzySlop=<FUZZY_SLOP> ]
[ <CARAT> boost=<NUMBER> ]
{
int s = phraseSlop;
- if (slop != null) {
+ if (fuzzySlop != null) {
try {
- s = Float.valueOf(slop.image.substring(1)).intValue();
+ s = Float.valueOf(fuzzySlop.image.substring(1)).intValue();
}
catch (Exception ignored) { }
}
1.16 +36 -26
jakarta-lucene/src/java/org/apache/lucene/queryParser/QueryParser.java
Index: QueryParser.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/queryParser/QueryParser.java,v
retrieving revision 1.15
retrieving revision 1.16
diff -u -r1.15 -r1.16
--- QueryParser.java 8 Sep 2004 15:06:42 -0000 1.15
+++ QueryParser.java 14 Sep 2004 13:45:15 -0000 1.16
@@ -73,6 +73,7 @@
Analyzer analyzer;
String field;
int phraseSlop = 0;
+ float fuzzyMinSim = FuzzyQuery.defaultMinSimilarity;
Locale locale = Locale.getDefault();
/** Parses a query string, returning a [EMAIL PROTECTED]
org.apache.lucene.search.Query}.
@@ -129,6 +130,19 @@
return field;
}
+ /**
+ * Get the default minimal similarity for fuzzy queries.
+ */
+ public float getFuzzyMinSim() {
+ return fuzzyMinSim;
+ }
+ /**
+ *Set the default minimum similarity for fuzzy queries.
+ */
+ public void setFuzzyMinSim(float fuzzyMinSim) {
+ this.fuzzyMinSim = fuzzyMinSim;
+ }
+
/**
* Sets the default slop for phrases. If zero, then exact phrase matches
* are required. Default value is zero.
@@ -416,10 +430,10 @@
* @return Resulting [EMAIL PROTECTED] Query} built for the term
* @exception ParseException throw in overridden method to disallow
*/
- protected Query getFuzzyQuery(String field, String termStr) throws ParseException
+ protected Query getFuzzyQuery(String field, String termStr, float minSimilarity)
throws ParseException
{
Term t = new Term(field, termStr);
- return new FuzzyQuery(t);
+ return new FuzzyQuery(t, minSimilarity);
}
/**
@@ -622,7 +636,7 @@
}
final public Query Term(String field) throws ParseException {
- Token term, boost=null, slop=null, goop1, goop2;
+ Token term, boost=null, fuzzySlop=null, goop1, goop2;
boolean prefix = false;
boolean wildcard = false;
boolean fuzzy = false;
@@ -654,9 +668,9 @@
throw new ParseException();
}
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case FUZZY:
- jj_consume_token(FUZZY);
- fuzzy=true;
+ case FUZZY_SLOP:
+ fuzzySlop = jj_consume_token(FUZZY_SLOP);
+ fuzzy=true;
break;
default:
jj_la1[8] = jj_gen;
@@ -667,9 +681,9 @@
jj_consume_token(CARAT);
boost = jj_consume_token(NUMBER);
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case FUZZY:
- jj_consume_token(FUZZY);
- fuzzy=true;
+ case FUZZY_SLOP:
+ fuzzySlop = jj_consume_token(FUZZY_SLOP);
+ fuzzy=true;
break;
default:
jj_la1[9] = jj_gen;
@@ -688,7 +702,11 @@
discardEscapeChar(term.image.substring
(0, term.image.length()-1)));
} else if (fuzzy) {
- q = getFuzzyQuery(field, termImage);
+ float fms = fuzzyMinSim;
+ try {
+ fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue();
+ } catch (Exception ignored) { }
+ q = getFuzzyQuery(field, termImage, fms);
} else {
q = getFieldQuery(field, termImage);
}
@@ -809,8 +827,8 @@
case QUOTED:
term = jj_consume_token(QUOTED);
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case SLOP:
- slop = jj_consume_token(SLOP);
+ case FUZZY_SLOP:
+ fuzzySlop = jj_consume_token(FUZZY_SLOP);
break;
default:
jj_la1[19] = jj_gen;
@@ -827,9 +845,9 @@
}
int s = phraseSlop;
- if (slop != null) {
+ if (fuzzySlop != null) {
try {
- s = Float.valueOf(slop.image.substring(1)).intValue();
+ s = Float.valueOf(fuzzySlop.image.substring(1)).intValue();
}
catch (Exception ignored) { }
}
@@ -883,16 +901,11 @@
private int jj_gen;
final private int[] jj_la1 = new int[22];
static private int[] jj_la1_0;
- static private int[] jj_la1_1;
static {
jj_la1_0();
- jj_la1_1();
}
private static void jj_la1_0() {
- jj_la1_0 = new int[]
{0x180,0x180,0xe00,0xe00,0x1f31f80,0x8000,0x1f31000,0x1320000,0x40000,0x40000,0x8000,0x18000000,0x2000000,0x18000000,0x8000,0x80000000,0x20000000,0x80000000,0x8000,0x80000,0x8000,0x1f30000,};
- }
- private static void jj_la1_1() {
- jj_la1_1 = new int[]
{0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x1,0x0,0x1,0x0,0x0,0x0,0x0,};
+ jj_la1_0 = new int[]
{0x180,0x180,0xe00,0xe00,0xfb1f80,0x8000,0xfb1000,0x9a0000,0x40000,0x40000,0x8000,0xc000000,0x1000000,0xc000000,0x8000,0xc0000000,0x10000000,0xc0000000,0x8000,0x40000,0x8000,0xfb0000,};
}
final private JJCalls[] jj_2_rtns = new JJCalls[1];
private boolean jj_rescan = false;
@@ -1041,8 +1054,8 @@
public ParseException generateParseException() {
jj_expentries.removeAllElements();
- boolean[] la1tokens = new boolean[33];
- for (int i = 0; i < 33; i++) {
+ boolean[] la1tokens = new boolean[32];
+ for (int i = 0; i < 32; i++) {
la1tokens[i] = false;
}
if (jj_kind >= 0) {
@@ -1055,13 +1068,10 @@
if ((jj_la1_0[i] & (1<<j)) != 0) {
la1tokens[j] = true;
}
- if ((jj_la1_1[i] & (1<<j)) != 0) {
- la1tokens[32+j] = true;
- }
}
}
}
- for (int i = 0; i < 33; i++) {
+ for (int i = 0; i < 32; i++) {
if (la1tokens[i]) {
jj_expentry = new int[1];
jj_expentry[0] = i;
1.2 +15 -17
jakarta-lucene/src/java/org/apache/lucene/queryParser/QueryParserConstants.java
Index: QueryParserConstants.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/queryParser/QueryParserConstants.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- QueryParserConstants.java 11 Sep 2003 01:51:33 -0000 1.1
+++ QueryParserConstants.java 14 Sep 2004 13:45:15 -0000 1.2
@@ -20,21 +20,20 @@
int CARAT = 15;
int QUOTED = 16;
int TERM = 17;
- int FUZZY = 18;
- int SLOP = 19;
- int PREFIXTERM = 20;
- int WILDTERM = 21;
- int RANGEIN_START = 22;
- int RANGEEX_START = 23;
- int NUMBER = 24;
- int RANGEIN_TO = 25;
- int RANGEIN_END = 26;
- int RANGEIN_QUOTED = 27;
- int RANGEIN_GOOP = 28;
- int RANGEEX_TO = 29;
- int RANGEEX_END = 30;
- int RANGEEX_QUOTED = 31;
- int RANGEEX_GOOP = 32;
+ int FUZZY_SLOP = 18;
+ int PREFIXTERM = 19;
+ int WILDTERM = 20;
+ int RANGEIN_START = 21;
+ int RANGEEX_START = 22;
+ int NUMBER = 23;
+ int RANGEIN_TO = 24;
+ int RANGEIN_END = 25;
+ int RANGEIN_QUOTED = 26;
+ int RANGEIN_GOOP = 27;
+ int RANGEEX_TO = 28;
+ int RANGEEX_END = 29;
+ int RANGEEX_QUOTED = 30;
+ int RANGEEX_GOOP = 31;
int Boost = 0;
int RangeEx = 1;
@@ -60,8 +59,7 @@
"\"^\"",
"<QUOTED>",
"<TERM>",
- "\"~\"",
- "<SLOP>",
+ "<FUZZY_SLOP>",
"<PREFIXTERM>",
"<WILDTERM>",
"\"[\"",
1.6 +25 -5 jakarta-lucene/src/java/org/apache/lucene/search/FuzzyQuery.java
Index: FuzzyQuery.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/search/FuzzyQuery.java,v
retrieving revision 1.5
retrieving revision 1.6
diff -u -r1.5 -r1.6
--- FuzzyQuery.java 13 Aug 2004 18:35:01 -0000 1.5
+++ FuzzyQuery.java 14 Sep 2004 13:45:15 -0000 1.6
@@ -25,11 +25,15 @@
*/
public final class FuzzyQuery extends MultiTermQuery {
+ public final static float defaultMinSimilarity = 0.5f;
private float minimumSimilarity;
+ private int prefixLength;
/**
* Create a new FuzzyQuery that will match terms with a similarity
* of at least <code>minimumSimilarity</code> to <code>term</code>.
+ * If a <code>prefixLength</code> > 0 is specified, a common prefix
+ * of that length is also required.
*
* @param term the term to search for
* @param minimumSimilarity a value between 0 and 1 to set the required similarity
@@ -37,29 +41,45 @@
* <code>minimumSimilarity</code> of <code>0.5</code> a term of the same length
* as the query term is considered similar to the query term if the edit distance
* between both terms is less than <code>length(term)*0.5</code>.
+ * @param prefixLength length of common prefix.
* @throws IllegalArgumentException if minimumSimilarity is > 1 or < 0
+ * or if prefixLength < 0 or > <code>term.text().length()</code>.
*/
- public FuzzyQuery(Term term, float minimumSimilarity) throws
IllegalArgumentException {
+ public FuzzyQuery(Term term, float minimumSimilarity, int prefixLength) throws
IllegalArgumentException {
super(term);
+
if (minimumSimilarity > 1.0f)
throw new IllegalArgumentException("minimumSimilarity > 1");
else if (minimumSimilarity < 0.0f)
throw new IllegalArgumentException("minimumSimilarity < 0");
this.minimumSimilarity = minimumSimilarity;
+
+ if(prefixLength < 0)
+ throw new IllegalArgumentException("prefixLength < 0");
+ else if(prefixLength >= term.text().length())
+ throw new IllegalArgumentException("prefixLength >= term.text().length()");
+ this.prefixLength = prefixLength;
+ }
+
+ /**
+ * Calls [EMAIL PROTECTED] #FuzzyQuery(Term, float) FuzzyQuery(term,
minimumSimilarity, 0)}.
+ */
+ public FuzzyQuery(Term term, float minimumSimilarity) throws
IllegalArgumentException {
+ this(term, minimumSimilarity, 0);
}
/**
- * Calls [EMAIL PROTECTED] #FuzzyQuery(Term, float) FuzzyQuery(term, 0.5f)}.
+ * Calls [EMAIL PROTECTED] #FuzzyQuery(Term, float) FuzzyQuery(term, 0.5f, 0)}.
*/
public FuzzyQuery(Term term) {
- this(term, 0.5f);
+ this(term, defaultMinSimilarity, 0);
}
protected FilteredTermEnum getEnum(IndexReader reader) throws IOException {
- return new FuzzyTermEnum(reader, getTerm(), minimumSimilarity);
+ return new FuzzyTermEnum(reader, getTerm(), minimumSimilarity, prefixLength);
}
public String toString(String field) {
- return super.toString(field) + '~';
+ return super.toString(field) + '~' + Float.toString(minimumSimilarity);
}
}
1.8 +45 -4
jakarta-lucene/src/java/org/apache/lucene/search/FuzzyTermEnum.java
Index: FuzzyTermEnum.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/search/FuzzyTermEnum.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -u -r1.7 -r1.8
--- FuzzyTermEnum.java 13 Aug 2004 18:35:01 -0000 1.7
+++ FuzzyTermEnum.java 14 Sep 2004 13:45:15 -0000 1.8
@@ -32,15 +32,49 @@
String field = "";
String text = "";
int textlen;
+ String prefix = "";
+ int prefixLength = 0;
float minimumSimilarity;
double scale_factor;
+ /**
+ * Empty prefix and minSimilarity of 0.5f are used.
+ *
+ * @param reader
+ * @param term
+ * @throws IOException
+ * @see #FuzzyTermEnum(IndexReader, Term, float, int)
+ */
public FuzzyTermEnum(IndexReader reader, Term term) throws IOException {
- this(reader, term, 0.5f);
+ this(reader, term, FuzzyQuery.defaultMinSimilarity, 0);
}
+ /**
+ * This is the standard FuzzyTermEnum with an empty prefix.
+ *
+ * @param reader
+ * @param term
+ * @param minSimilarity
+ * @throws IOException
+ * @see #FuzzyTermEnum(IndexReader, Term, float, int)
+ */
public FuzzyTermEnum(IndexReader reader, Term term, float minSimilarity) throws
IOException {
+ this(reader, term, minSimilarity, 0);
+ }
+
+ /**
+ * Constructor for enumeration of all terms from specified <code>reader</code>
which share a prefix of
+ * length <code>prefixLength</code> with <code>term</code> and which have a
fuzzy similarity >
+ * <code>minSimilarity</code>.
+ *
+ * @param reader Delivers terms.
+ * @param term Pattern term.
+ * @param minSimilarity Minimum required similarity for terms from the reader.
Default value is 0.5f.
+ * @param prefixLength Length of required common prefix. Default value is 0.
+ * @throws IOException
+ */
+ public FuzzyTermEnum(IndexReader reader, Term term, float minSimilarity, int
prefixLength) throws IOException {
super();
minimumSimilarity = minSimilarity;
scale_factor = 1.0f / (1.0f - minimumSimilarity);
@@ -48,7 +82,13 @@
field = searchTerm.field();
text = searchTerm.text();
textlen = text.length();
- setEnum(reader.terms(new Term(searchTerm.field(), "")));
+ if(prefixLength > 0 && prefixLength < textlen){
+ this.prefixLength = prefixLength;
+ prefix = text.substring(0, prefixLength);
+ text = text.substring(prefixLength);
+ textlen = text.length();
+ }
+ setEnum(reader.terms(new Term(searchTerm.field(), prefix)));
}
/**
@@ -56,8 +96,9 @@
calculate the distance between the given term and the comparing term.
*/
protected final boolean termCompare(Term term) {
- if (field == term.field()) {
- String target = term.text();
+ String termText = term.text();
+ if (field == term.field() && termText.startsWith(prefix)) {
+ String target = termText.substring(prefixLength);
int targetlen = target.length();
int dist = editDistance(text, target, textlen, targetlen);
distance = 1 - ((double)dist / (double)Math.min(textlen, targetlen));
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
