Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-996: QP: mixed inclusive/exclusive endpoints for ranges 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1026489 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Yonik Seeley 2010-10-22 20:40:08 +00:00
parent abbfc101e3
commit c8c9ee2cb2
12 changed files with 192 additions and 425 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lucene/CHANGES.txt
View File

@ -270,6 +270,11 @@ New features
* LUCENE-2690: MultiTermQuery boolean rewrites per segment.
(Uwe Schindler, Robert Muir, Mike McCandless, Simon Willnauer)
* LUCENE-996: The QueryParser now accepts mixed inclusive and exclusive
bounds for range queries. Example: "{3 TO 5]"
QueryParser subclasses that overrode getRangeQuery will need to be changed
to use the new getRangeQuery method. (Andrew Schurman, Mark Miller, yonik)
Optimizations
* LUCENE-2410: ~20% speedup on exact (slop=0) PhraseQuery matching.

4
lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/analyzing/AnalyzingQueryParser.java
View File

@ -269,7 +269,7 @@ public class AnalyzingQueryParser extends org.apache.lucene.queryParser.QueryPar
* @exception ParseException
*/
@Override
protected Query getRangeQuery(String field, String part1, String part2, boolean inclusive)
protected Query getRangeQuery(String field, String part1, String part2, boolean startInclusive, boolean endInclusive)
throws ParseException {
// get Analyzer from superclass and tokenize the terms
TokenStream source = getAnalyzer().tokenStream(field, new StringReader(part1));
@ -316,7 +316,7 @@ public class AnalyzingQueryParser extends org.apache.lucene.queryParser.QueryPar
throw new ParseException("Cannot build RangeQuery with analyzer " + getAnalyzer().getClass()
+ " - tokens were added to part2");
}
return super.getRangeQuery(field, part1, part2, inclusive);
return super.getRangeQuery(field, part1, part2, startInclusive, endInclusive);
}
}

10
lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/complexPhrase/ComplexPhraseQueryParser.java
View File

@ -161,25 +161,25 @@ public class ComplexPhraseQueryParser extends QueryParser {
@Override
protected Query getRangeQuery(String field, String part1, String part2,
boolean inclusive) throws ParseException {
boolean startInclusive, boolean endInclusive) throws ParseException {
if (isPass2ResolvingPhrases) {
checkPhraseClauseIsForSameField(field);
}
return super.getRangeQuery(field, part1, part2, inclusive);
return super.getRangeQuery(field, part1, part2, startInclusive, endInclusive);
}
@Override
protected Query newRangeQuery(String field, String part1, String part2,
boolean inclusive) {
boolean startInclusive, boolean endInclusive) {
if (isPass2ResolvingPhrases) {
// Must use old-style RangeQuery in order to produce a BooleanQuery
// that can be turned into SpanOr clause
TermRangeQuery rangeQuery = new TermRangeQuery(field, part1, part2, inclusive, inclusive,
TermRangeQuery rangeQuery = new TermRangeQuery(field, part1, part2, startInclusive, endInclusive,
getRangeCollator());
rangeQuery.setRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
return rangeQuery;
}
return super.newRangeQuery(field, part1, part2, inclusive);
return super.newRangeQuery(field, part1, part2, startInclusive, endInclusive);
}
@Override

6
lucene/src/java/org/apache/lucene/queryParser/MultiFieldQueryParser.java
View File

@ -203,16 +203,16 @@ public class MultiFieldQueryParser extends QueryParser
@Override
protected Query getRangeQuery(String field, String part1, String part2, boolean inclusive) throws ParseException {
protected Query getRangeQuery(String field, String part1, String part2, boolean startInclusive, boolean endInclusive) throws ParseException {
if (field == null) {
List<BooleanClause> clauses = new ArrayList<BooleanClause>();
for (int i = 0; i < fields.length; i++) {
clauses.add(new BooleanClause(getRangeQuery(fields[i], part1, part2, inclusive),
clauses.add(new BooleanClause(getRangeQuery(fields[i], part1, part2, startInclusive, endInclusive),
BooleanClause.Occur.SHOULD));
}
return getBooleanQuery(clauses, true);
}
return super.getRangeQuery(field, part1, part2, inclusive);
return super.getRangeQuery(field, part1, part2, startInclusive, endInclusive);
}
/**

164
lucene/src/java/org/apache/lucene/queryParser/QueryParser.java
View File

@ -312,6 +312,8 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
boolean wildcard = false;
boolean fuzzy = false;
boolean regexp = false;
boolean startInc=false;
boolean endInc=false;
Query q;
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case STAR:
@ -378,13 +380,14 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
q = handleBareTokenQuery(field, term, fuzzySlop, prefix, wildcard, fuzzy, regexp);
break;
case RANGEIN_START:
jj_consume_token(RANGEIN_START);
case RANGEEX_START:
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case RANGEIN_GOOP:
goop1 = jj_consume_token(RANGEIN_GOOP);
case RANGEIN_START:
jj_consume_token(RANGEIN_START);
startInc=true;
break;
case RANGEIN_QUOTED:
goop1 = jj_consume_token(RANGEIN_QUOTED);
case RANGEEX_START:
jj_consume_token(RANGEEX_START);
break;
default:
jj_la1[12] = jj_gen;
@ -392,51 +395,44 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
throw new ParseException();
}
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case RANGEIN_TO:
jj_consume_token(RANGEIN_TO);
case RANGE_GOOP:
goop1 = jj_consume_token(RANGE_GOOP);
break;
case RANGE_QUOTED:
goop1 = jj_consume_token(RANGE_QUOTED);
break;
default:
jj_la1[13] = jj_gen;
;
}
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case RANGEIN_GOOP:
goop2 = jj_consume_token(RANGEIN_GOOP);
break;
case RANGEIN_QUOTED:
goop2 = jj_consume_token(RANGEIN_QUOTED);
break;
default:
jj_la1[14] = jj_gen;
jj_consume_token(-1);
throw new ParseException();
}
jj_consume_token(RANGEIN_END);
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case CARAT:
jj_consume_token(CARAT);
boost = jj_consume_token(NUMBER);
case RANGE_TO:
jj_consume_token(RANGE_TO);
break;
default:
jj_la1[14] = jj_gen;
;
}
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case RANGE_GOOP:
goop2 = jj_consume_token(RANGE_GOOP);
break;
case RANGE_QUOTED:
goop2 = jj_consume_token(RANGE_QUOTED);
break;
default:
jj_la1[15] = jj_gen;
;
jj_consume_token(-1);
throw new ParseException();
}
if (goop1.kind == RANGEIN_QUOTED) {
goop1.image = goop1.image.substring(1, goop1.image.length()-1);
}
if (goop2.kind == RANGEIN_QUOTED) {
goop2.image = goop2.image.substring(1, goop2.image.length()-1);
}
q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), true);
break;
case RANGEEX_START:
jj_consume_token(RANGEEX_START);
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case RANGEEX_GOOP:
goop1 = jj_consume_token(RANGEEX_GOOP);
case RANGEIN_END:
jj_consume_token(RANGEIN_END);
endInc=true;
break;
case RANGEEX_QUOTED:
goop1 = jj_consume_token(RANGEEX_QUOTED);
case RANGEEX_END:
jj_consume_token(RANGEEX_END);
break;
default:
jj_la1[16] = jj_gen;
@ -444,26 +440,32 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
throw new ParseException();
}
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case RANGEEX_TO:
jj_consume_token(RANGEEX_TO);
case CARAT:
jj_consume_token(CARAT);
boost = jj_consume_token(NUMBER);
break;
default:
jj_la1[17] = jj_gen;
;
}
if (goop1.kind == RANGE_QUOTED) {
goop1.image = goop1.image.substring(1, goop1.image.length()-1);
}
if (goop2.kind == RANGE_QUOTED) {
goop2.image = goop2.image.substring(1, goop2.image.length()-1);
}
q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), startInc, endInc);
break;
case QUOTED:
term = jj_consume_token(QUOTED);
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case RANGEEX_GOOP:
goop2 = jj_consume_token(RANGEEX_GOOP);
break;
case RANGEEX_QUOTED:
goop2 = jj_consume_token(RANGEEX_QUOTED);
case FUZZY_SLOP:
fuzzySlop = jj_consume_token(FUZZY_SLOP);
break;
default:
jj_la1[18] = jj_gen;
jj_consume_token(-1);
throw new ParseException();
;
}
jj_consume_token(RANGEEX_END);
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case CARAT:
jj_consume_token(CARAT);
@ -472,39 +474,11 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
default:
jj_la1[19] = jj_gen;
;
}
if (goop1.kind == RANGEEX_QUOTED) {
goop1.image = goop1.image.substring(1, goop1.image.length()-1);
}
if (goop2.kind == RANGEEX_QUOTED) {
goop2.image = goop2.image.substring(1, goop2.image.length()-1);
}
q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), false);
break;
case QUOTED:
term = jj_consume_token(QUOTED);
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case FUZZY_SLOP:
fuzzySlop = jj_consume_token(FUZZY_SLOP);
break;
default:
jj_la1[20] = jj_gen;
;
}
switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
case CARAT:
jj_consume_token(CARAT);
boost = jj_consume_token(NUMBER);
break;
default:
jj_la1[21] = jj_gen;
;
}
q = handleQuotedTerm(field, term, fuzzySlop);
break;
default:
jj_la1[22] = jj_gen;
jj_la1[20] = jj_gen;
jj_consume_token(-1);
throw new ParseException();
}
@ -519,6 +493,12 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
finally { jj_save(0, xla); }
}
private boolean jj_3R_3() {
if (jj_scan_token(STAR)) return true;
if (jj_scan_token(COLON)) return true;
return false;
}
private boolean jj_3R_2() {
if (jj_scan_token(TERM)) return true;
if (jj_scan_token(COLON)) return true;
@ -535,12 +515,6 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
return false;
}
private boolean jj_3R_3() {
if (jj_scan_token(STAR)) return true;
if (jj_scan_token(COLON)) return true;
return false;
}
/** Generated Token Manager. */
public QueryParserTokenManager token_source;
/** Current token. */
@ -551,18 +525,13 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
private Token jj_scanpos, jj_lastpos;
private int jj_la;
private int jj_gen;
final private int[] jj_la1 = new int[23];
final private int[] jj_la1 = new int[21];
static private int[] jj_la1_0;
static private int[] jj_la1_1;
static {
jj_la1_init_0();
jj_la1_init_1();
}
private static void jj_la1_init_0() {
jj_la1_0 = new int[] {0x300,0x300,0x1c00,0x1c00,0x7ed3f00,0x90000,0x20000,0x7ed2000,0x4e90000,0x100000,0x100000,0x20000,0x60000000,0x8000000,0x60000000,0x20000,0x0,0x80000000,0x0,0x20000,0x100000,0x20000,0x7ed0000,};
}
private static void jj_la1_init_1() {
jj_la1_1 = new int[] {0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x6,0x0,0x6,0x0,0x0,0x0,0x0,};
jj_la1_0 = new int[] {0x300,0x300,0x1c00,0x1c00,0x7ed3f00,0x90000,0x20000,0x7ed2000,0x4e90000,0x100000,0x100000,0x20000,0x3000000,0xc0000000,0x8000000,0xc0000000,0x30000000,0x20000,0x100000,0x20000,0x7ed0000,};
}
final private JJCalls[] jj_2_rtns = new JJCalls[1];
private boolean jj_rescan = false;
@ -574,7 +543,7 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
token = new Token();
jj_ntk = -1;
jj_gen = 0;
for (int i = 0; i < 23; i++) jj_la1[i] = -1;
for (int i = 0; i < 21; i++) jj_la1[i] = -1;
for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
}
@ -584,7 +553,7 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
token = new Token();
jj_ntk = -1;
jj_gen = 0;
for (int i = 0; i < 23; i++) jj_la1[i] = -1;
for (int i = 0; i < 21; i++) jj_la1[i] = -1;
for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
}
@ -594,7 +563,7 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
token = new Token();
jj_ntk = -1;
jj_gen = 0;
for (int i = 0; i < 23; i++) jj_la1[i] = -1;
for (int i = 0; i < 21; i++) jj_la1[i] = -1;
for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
}
@ -604,7 +573,7 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
token = new Token();
jj_ntk = -1;
jj_gen = 0;
for (int i = 0; i < 23; i++) jj_la1[i] = -1;
for (int i = 0; i < 21; i++) jj_la1[i] = -1;
for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
}
@ -716,24 +685,21 @@ public class QueryParser extends QueryParserBase implements QueryParserConstants
/** Generate ParseException. */
public ParseException generateParseException() {
jj_expentries.clear();
boolean[] la1tokens = new boolean[35];
boolean[] la1tokens = new boolean[32];
if (jj_kind >= 0) {
la1tokens[jj_kind] = true;
jj_kind = -1;
}
for (int i = 0; i < 23; i++) {
for (int i = 0; i < 21; i++) {
if (jj_la1[i] == jj_gen) {
for (int j = 0; j < 32; j++) {
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 < 35; i++) {
for (int i = 0; i < 32; i++) {
if (la1tokens[i]) {
jj_expentry = new int[1];
jj_expentry[0] = i;

50
lucene/src/java/org/apache/lucene/queryParser/QueryParser.jj
View File

@ -173,7 +173,7 @@ PARSER_END(QueryParser)
| <#_QUOTED_CHAR: ( ~[ "\"", "\\" ] | <_ESCAPED_CHAR> ) >
}
<DEFAULT, RangeIn, RangeEx> SKIP : {
<DEFAULT, Range> SKIP : {
< <_WHITESPACE>>
}
@ -194,26 +194,20 @@ PARSER_END(QueryParser)
| <PREFIXTERM: ("*") | ( <_TERM_START_CHAR> (<_TERM_CHAR>)* "*" ) >
| <WILDTERM: (<_TERM_START_CHAR> | [ "*", "?" ]) (<_TERM_CHAR> | ( [ "*", "?" ] ))* >
| <REGEXPTERM: "/" (~[ "/" ] | "\\/" )* "/" >
| <RANGEIN_START: "[" > : RangeIn
| <RANGEEX_START: "{" > : RangeEx
| <RANGEIN_START: "[" > : Range
| <RANGEEX_START: "{" > : Range
}
<Boost> TOKEN : {
<NUMBER: (<_NUM_CHAR>)+ ( "." (<_NUM_CHAR>)+ )? > : DEFAULT
}
<RangeIn> TOKEN : {
<RANGEIN_TO: "TO">
<Range> TOKEN : {
<RANGE_TO: "TO">
| <RANGEIN_END: "]"> : DEFAULT
| <RANGEIN_QUOTED: "\"" (~["\""] | "\\\"")+ "\"">
| <RANGEIN_GOOP: (~[ " ", "]" ])+ >
}
<RangeEx> TOKEN : {
<RANGEEX_TO: "TO">
| <RANGEEX_END: "}"> : DEFAULT
| <RANGEEX_QUOTED: "\"" (~["\""] | "\\\"")+ "\"">
| <RANGEEX_GOOP: (~[ " ", "}" ])+ >
| <RANGE_QUOTED: "\"" (~["\""] | "\\\"")+ "\"">
| <RANGE_GOOP: (~[ " ", "]", "}" ])+ >
}
// * Query ::= ( Clause )*
@ -308,6 +302,8 @@ Query Term(String field) : {
boolean wildcard = false;
boolean fuzzy = false;
boolean regexp = false;
boolean startInc=false;
boolean endInc=false;
Query q;
}
{
@ -325,32 +321,20 @@ Query Term(String field) : {
{
q = handleBareTokenQuery(field, term, fuzzySlop, prefix, wildcard, fuzzy, regexp);
}
| ( <RANGEIN_START> ( goop1=<RANGEIN_GOOP>|goop1=<RANGEIN_QUOTED> )
[ <RANGEIN_TO> ] ( goop2=<RANGEIN_GOOP>|goop2=<RANGEIN_QUOTED> )
<RANGEIN_END> )
| ( ( <RANGEIN_START> {startInc=true;} | <RANGEEX_START> )
( goop1=<RANGE_GOOP>|goop1=<RANGE_QUOTED> )
[ <RANGE_TO> ]
( goop2=<RANGE_GOOP>|goop2=<RANGE_QUOTED> )
( <RANGEIN_END> {endInc=true;} | <RANGEEX_END>))
[ <CARAT> boost=<NUMBER> ]
{
if (goop1.kind == RANGEIN_QUOTED) {
if (goop1.kind == RANGE_QUOTED) {
goop1.image = goop1.image.substring(1, goop1.image.length()-1);
}
if (goop2.kind == RANGEIN_QUOTED) {
if (goop2.kind == RANGE_QUOTED) {
goop2.image = goop2.image.substring(1, goop2.image.length()-1);
}
q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), true);
}
| ( <RANGEEX_START> ( goop1=<RANGEEX_GOOP>|goop1=<RANGEEX_QUOTED> )
[ <RANGEEX_TO> ] ( goop2=<RANGEEX_GOOP>|goop2=<RANGEEX_QUOTED> )
<RANGEEX_END> )
[ <CARAT> boost=<NUMBER> ]
{
if (goop1.kind == RANGEEX_QUOTED) {
goop1.image = goop1.image.substring(1, goop1.image.length()-1);
}
if (goop2.kind == RANGEEX_QUOTED) {
goop2.image = goop2.image.substring(1, goop2.image.length()-1);
}
q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), false);
q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), startInc, endInc);
}
| term=<QUOTED>
[ fuzzySlop=<FUZZY_SLOP> ]

25
lucene/src/java/org/apache/lucene/queryParser/QueryParserBase.java
View File

@ -42,6 +42,9 @@ import java.util.*;
*/
public abstract class QueryParserBase {
/** Do not catch this exception in your code, it means you are using methods that you should no longer use. */
public static class MethodRemovedUseAnother extends Throwable {}
static final int CONJ_NONE = 0;
static final int CONJ_AND = 1;
static final int CONJ_OR = 2;
@ -694,13 +697,18 @@ public abstract class QueryParserBase {
}
@Deprecated
protected final Query getRangeQuery(String field, String part1, String part2, boolean inclusive) throws MethodRemovedUseAnother {return null;}
/**
* @exception org.apache.lucene.queryParser.ParseException throw in overridden method to disallow
*/
protected Query getRangeQuery(String field,
String part1,
String part2,
boolean inclusive) throws ParseException
boolean startInclusive,
boolean endInclusive) throws ParseException
{
if (lowercaseExpandedTerms) {
part1 = part1.toLowerCase();
@ -711,7 +719,7 @@ public abstract class QueryParserBase {
df.setLenient(true);
Date d1 = df.parse(part1);
Date d2 = df.parse(part2);
if (inclusive) {
if (endInclusive) {
// The user can only specify the date, not the time, so make sure
// the time is set to the latest possible time of that date to really
// include all documents:
@ -737,7 +745,7 @@ public abstract class QueryParserBase {
}
catch (Exception e) { }
return newRangeQuery(field, part1, part2, inclusive);
return newRangeQuery(field, part1, part2, startInclusive, endInclusive);
}
/**
@ -818,16 +826,21 @@ public abstract class QueryParserBase {
return new FuzzyQuery(term,minimumSimilarity,prefixLength);
}
@Deprecated
protected final Query newRangeQuery(String field, String part1, String part2, boolean inclusive) throws MethodRemovedUseAnother {return null;}
/**
* Builds a new TermRangeQuery instance
* @param field Field
* @param part1 min
* @param part2 max
* @param inclusive true if range is inclusive
* @param startInclusive true if the start of the range is inclusive
* @param endInclusive true if the end of the range is inclusive
* @return new TermRangeQuery instance
*/
protected Query newRangeQuery(String field, String part1, String part2, boolean inclusive) {
final TermRangeQuery query = new TermRangeQuery(field, part1, part2, inclusive, inclusive, rangeCollator);
protected Query newRangeQuery(String field, String part1, String part2, boolean startInclusive, boolean endInclusive) {
final TermRangeQuery query = new TermRangeQuery(field, part1, part2, startInclusive, endInclusive, rangeCollator);
query.setRewriteMethod(multiTermRewriteMethod);
return query;
}

27
lucene/src/java/org/apache/lucene/queryParser/QueryParserConstants.java
View File

@ -61,30 +61,22 @@ public interface QueryParserConstants {
/** RegularExpression Id. */
int NUMBER = 26;
/** RegularExpression Id. */
int RANGEIN_TO = 27;
int RANGE_TO = 27;
/** RegularExpression Id. */
int RANGEIN_END = 28;
/** RegularExpression Id. */
int RANGEIN_QUOTED = 29;
int RANGEEX_END = 29;
/** RegularExpression Id. */
int RANGEIN_GOOP = 30;
int RANGE_QUOTED = 30;
/** RegularExpression Id. */
int RANGEEX_TO = 31;
/** RegularExpression Id. */
int RANGEEX_END = 32;
/** RegularExpression Id. */
int RANGEEX_QUOTED = 33;
/** RegularExpression Id. */
int RANGEEX_GOOP = 34;
int RANGE_GOOP = 31;
/** Lexical state. */
int Boost = 0;
/** Lexical state. */
int RangeEx = 1;
int Range = 1;
/** Lexical state. */
int RangeIn = 2;
/** Lexical state. */
int DEFAULT = 3;
int DEFAULT = 2;
/** Literal token values. */
String[] tokenImage = {
@ -117,12 +109,9 @@ public interface QueryParserConstants {
"<NUMBER>",
"\"TO\"",
"\"]\"",
"<RANGEIN_QUOTED>",
"<RANGEIN_GOOP>",
"\"TO\"",
"\"}\"",
"<RANGEEX_QUOTED>",
"<RANGEEX_GOOP>",
"<RANGE_QUOTED>",
"<RANGE_GOOP>",
};
}

303
lucene/src/java/org/apache/lucene/queryParser/QueryParserTokenManager.java
View File

@ -44,7 +44,7 @@ public class QueryParserTokenManager implements QueryParserConstants
public java.io.PrintStream debugStream = System.out;
/** Set debug output. */
public void setDebugStream(java.io.PrintStream ds) { debugStream = ds; }
private final int jjStopStringLiteralDfa_3(int pos, long active0)
private final int jjStopStringLiteralDfa_2(int pos, long active0)
{
switch (pos)
{
@ -52,9 +52,9 @@ private final int jjStopStringLiteralDfa_3(int pos, long active0)
return -1;
}
}
private final int jjStartNfa_3(int pos, long active0)
private final int jjStartNfa_2(int pos, long active0)
{
return jjMoveNfa_3(jjStopStringLiteralDfa_3(pos, active0), pos + 1);
return jjMoveNfa_2(jjStopStringLiteralDfa_2(pos, active0), pos + 1);
}
private int jjStopAtPos(int pos, int kind)
{
@ -62,7 +62,7 @@ private int jjStopAtPos(int pos, int kind)
jjmatchedPos = pos;
return pos + 1;
}
private int jjMoveStringLiteralDfa0_3()
private int jjMoveStringLiteralDfa0_2()
{
switch(curChar)
{
@ -71,7 +71,7 @@ private int jjMoveStringLiteralDfa0_3()
case 41:
return jjStopAtPos(0, 14);
case 42:
return jjStartNfaWithStates_3(0, 16, 41);
return jjStartNfaWithStates_2(0, 16, 41);
case 43:
return jjStopAtPos(0, 11);
case 45:
@ -85,16 +85,16 @@ private int jjMoveStringLiteralDfa0_3()
case 123:
return jjStopAtPos(0, 25);
default :
return jjMoveNfa_3(0, 0);
return jjMoveNfa_2(0, 0);
}
}
private int jjStartNfaWithStates_3(int pos, int kind, int state)
private int jjStartNfaWithStates_2(int pos, int kind, int state)
{
jjmatchedKind = kind;
jjmatchedPos = pos;
try { curChar = input_stream.readChar(); }
catch(java.io.IOException e) { return pos + 1; }
return jjMoveNfa_3(state, pos + 1);
return jjMoveNfa_2(state, pos + 1);
}
static final long[] jjbitVec0 = {
0x1L, 0x0L, 0x0L, 0x0L
@ -108,7 +108,7 @@ static final long[] jjbitVec3 = {
static final long[] jjbitVec4 = {
0xfffefffffffffffeL, 0xffffffffffffffffL, 0xffffffffffffffffL, 0xffffffffffffffffL
};
private int jjMoveNfa_3(int startState, int curPos)
private int jjMoveNfa_2(int startState, int curPos)
{
int startsAt = 0;
jjnewStateCnt = 41;
@ -557,201 +557,6 @@ private int jjMoveNfa_3(int startState, int curPos)
catch(java.io.IOException e) { return curPos; }
}
}
private final int jjStopStringLiteralDfa_1(int pos, long active0)
{
switch (pos)
{
case 0:
if ((active0 & 0x80000000L) != 0L)
{
jjmatchedKind = 34;
return 6;
}
return -1;
default :
return -1;
}
}
private final int jjStartNfa_1(int pos, long active0)
{
return jjMoveNfa_1(jjStopStringLiteralDfa_1(pos, active0), pos + 1);
}
private int jjMoveStringLiteralDfa0_1()
{
switch(curChar)
{
case 84:
return jjMoveStringLiteralDfa1_1(0x80000000L);
case 125:
return jjStopAtPos(0, 32);
default :
return jjMoveNfa_1(0, 0);
}
}
private int jjMoveStringLiteralDfa1_1(long active0)
{
try { curChar = input_stream.readChar(); }
catch(java.io.IOException e) {
jjStopStringLiteralDfa_1(0, active0);
return 1;
}
switch(curChar)
{
case 79:
if ((active0 & 0x80000000L) != 0L)
return jjStartNfaWithStates_1(1, 31, 6);
break;
default :
break;
}
return jjStartNfa_1(0, active0);
}
private int jjStartNfaWithStates_1(int pos, int kind, int state)
{
jjmatchedKind = kind;
jjmatchedPos = pos;
try { curChar = input_stream.readChar(); }
catch(java.io.IOException e) { return pos + 1; }
return jjMoveNfa_1(state, pos + 1);
}
private int jjMoveNfa_1(int startState, int curPos)
{
int startsAt = 0;
jjnewStateCnt = 7;
int i = 1;
jjstateSet[0] = startState;
int kind = 0x7fffffff;
for (;;)
{
if (++jjround == 0x7fffffff)
ReInitRounds();
if (curChar < 64)
{
long l = 1L << curChar;
do
{
switch(jjstateSet[--i])
{
case 0:
if ((0xfffffffeffffffffL & l) != 0L)
{
if (kind > 34)
kind = 34;
jjCheckNAdd(6);
}
if ((0x100002600L & l) != 0L)
{
if (kind > 7)
kind = 7;
}
else if (curChar == 34)
jjCheckNAddTwoStates(2, 4);
break;
case 1:
if (curChar == 34)
jjCheckNAddTwoStates(2, 4);
break;
case 2:
if ((0xfffffffbffffffffL & l) != 0L)
jjCheckNAddStates(19, 21);
break;
case 3:
if (curChar == 34)
jjCheckNAddStates(19, 21);
break;
case 5:
if (curChar == 34 && kind > 33)
kind = 33;
break;
case 6:
if ((0xfffffffeffffffffL & l) == 0L)
break;
if (kind > 34)
kind = 34;
jjCheckNAdd(6);
break;
default : break;
}
} while(i != startsAt);
}
else if (curChar < 128)
{
long l = 1L << (curChar & 077);
do
{
switch(jjstateSet[--i])
{
case 0:
case 6:
if ((0xdfffffffffffffffL & l) == 0L)
break;
if (kind > 34)
kind = 34;
jjCheckNAdd(6);
break;
case 2:
jjAddStates(19, 21);
break;
case 4:
if (curChar == 92)
jjstateSet[jjnewStateCnt++] = 3;
break;
default : break;
}
} while(i != startsAt);
}
else
{
int hiByte = (int)(curChar >> 8);
int i1 = hiByte >> 6;
long l1 = 1L << (hiByte & 077);
int i2 = (curChar & 0xff) >> 6;
long l2 = 1L << (curChar & 077);
do
{
switch(jjstateSet[--i])
{
case 0:
if (jjCanMove_0(hiByte, i1, i2, l1, l2))
{
if (kind > 7)
kind = 7;
}
if (jjCanMove_1(hiByte, i1, i2, l1, l2))
{
if (kind > 34)
kind = 34;
jjCheckNAdd(6);
}
break;
case 2:
if (jjCanMove_1(hiByte, i1, i2, l1, l2))
jjAddStates(19, 21);
break;
case 6:
if (!jjCanMove_1(hiByte, i1, i2, l1, l2))
break;
if (kind > 34)
kind = 34;
jjCheckNAdd(6);
break;
default : break;
}
} while(i != startsAt);
}
if (kind != 0x7fffffff)
{
jjmatchedKind = kind;
jjmatchedPos = curPos;
kind = 0x7fffffff;
}
++curPos;
if ((i = jjnewStateCnt) == (startsAt = 7 - (jjnewStateCnt = startsAt)))
return curPos;
try { curChar = input_stream.readChar(); }
catch(java.io.IOException e) { return curPos; }
}
}
private int jjMoveStringLiteralDfa0_0()
{
return jjMoveNfa_0(0, 0);
@ -779,7 +584,7 @@ private int jjMoveNfa_0(int startState, int curPos)
break;
if (kind > 26)
kind = 26;
jjAddStates(22, 23);
jjAddStates(19, 20);
break;
case 1:
if (curChar == 46)
@ -835,14 +640,14 @@ private int jjMoveNfa_0(int startState, int curPos)
catch(java.io.IOException e) { return curPos; }
}
}
private final int jjStopStringLiteralDfa_2(int pos, long active0)
private final int jjStopStringLiteralDfa_1(int pos, long active0)
{
switch (pos)
{
case 0:
if ((active0 & 0x8000000L) != 0L)
{
jjmatchedKind = 30;
jjmatchedKind = 31;
return 6;
}
return -1;
@ -850,49 +655,51 @@ private final int jjStopStringLiteralDfa_2(int pos, long active0)
return -1;
}
}
private final int jjStartNfa_2(int pos, long active0)
private final int jjStartNfa_1(int pos, long active0)
{
return jjMoveNfa_2(jjStopStringLiteralDfa_2(pos, active0), pos + 1);
return jjMoveNfa_1(jjStopStringLiteralDfa_1(pos, active0), pos + 1);
}
private int jjMoveStringLiteralDfa0_2()
private int jjMoveStringLiteralDfa0_1()
{
switch(curChar)
{
case 84:
return jjMoveStringLiteralDfa1_2(0x8000000L);
return jjMoveStringLiteralDfa1_1(0x8000000L);
case 93:
return jjStopAtPos(0, 28);
case 125:
return jjStopAtPos(0, 29);
default :
return jjMoveNfa_2(0, 0);
return jjMoveNfa_1(0, 0);
}
}
private int jjMoveStringLiteralDfa1_2(long active0)
private int jjMoveStringLiteralDfa1_1(long active0)
{
try { curChar = input_stream.readChar(); }
catch(java.io.IOException e) {
jjStopStringLiteralDfa_2(0, active0);
jjStopStringLiteralDfa_1(0, active0);
return 1;
}
switch(curChar)
{
case 79:
if ((active0 & 0x8000000L) != 0L)
return jjStartNfaWithStates_2(1, 27, 6);
return jjStartNfaWithStates_1(1, 27, 6);
break;
default :
break;
}
return jjStartNfa_2(0, active0);
return jjStartNfa_1(0, active0);
}
private int jjStartNfaWithStates_2(int pos, int kind, int state)
private int jjStartNfaWithStates_1(int pos, int kind, int state)
{
jjmatchedKind = kind;
jjmatchedPos = pos;
try { curChar = input_stream.readChar(); }
catch(java.io.IOException e) { return pos + 1; }
return jjMoveNfa_2(state, pos + 1);
return jjMoveNfa_1(state, pos + 1);
}
private int jjMoveNfa_2(int startState, int curPos)
private int jjMoveNfa_1(int startState, int curPos)
{
int startsAt = 0;
jjnewStateCnt = 7;
@ -913,8 +720,8 @@ private int jjMoveNfa_2(int startState, int curPos)
case 0:
if ((0xfffffffeffffffffL & l) != 0L)
{
if (kind > 30)
kind = 30;
if (kind > 31)
kind = 31;
jjCheckNAdd(6);
}
if ((0x100002600L & l) != 0L)
@ -931,21 +738,21 @@ private int jjMoveNfa_2(int startState, int curPos)
break;
case 2:
if ((0xfffffffbffffffffL & l) != 0L)
jjCheckNAddStates(19, 21);
jjCheckNAddStates(21, 23);
break;
case 3:
if (curChar == 34)
jjCheckNAddStates(19, 21);
jjCheckNAddStates(21, 23);
break;
case 5:
if (curChar == 34 && kind > 29)
kind = 29;
if (curChar == 34 && kind > 30)
kind = 30;
break;
case 6:
if ((0xfffffffeffffffffL & l) == 0L)
break;
if (kind > 30)
kind = 30;
if (kind > 31)
kind = 31;
jjCheckNAdd(6);
break;
default : break;
@ -961,14 +768,14 @@ private int jjMoveNfa_2(int startState, int curPos)
{
case 0:
case 6:
if ((0xffffffffdfffffffL & l) == 0L)
if ((0xdfffffffdfffffffL & l) == 0L)
break;
if (kind > 30)
kind = 30;
if (kind > 31)
kind = 31;
jjCheckNAdd(6);
break;
case 2:
jjAddStates(19, 21);
jjAddStates(21, 23);
break;
case 4:
if (curChar == 92)
@ -997,20 +804,20 @@ private int jjMoveNfa_2(int startState, int curPos)
}
if (jjCanMove_1(hiByte, i1, i2, l1, l2))
{
if (kind > 30)
kind = 30;
if (kind > 31)
kind = 31;
jjCheckNAdd(6);
}
break;
case 2:
if (jjCanMove_1(hiByte, i1, i2, l1, l2))
jjAddStates(19, 21);
jjAddStates(21, 23);
break;
case 6:
if (!jjCanMove_1(hiByte, i1, i2, l1, l2))
break;
if (kind > 30)
kind = 30;
if (kind > 31)
kind = 31;
jjCheckNAdd(6);
break;
default : break;
@ -1032,7 +839,7 @@ private int jjMoveNfa_2(int startState, int curPos)
}
static final int[] jjnextStates = {
15, 16, 18, 34, 37, 23, 38, 35, 29, 31, 32, 20, 21, 37, 23, 38,
36, 39, 27, 2, 4, 5, 0, 1,
36, 39, 27, 0, 1, 2, 4, 5,
};
private static final boolean jjCanMove_0(int hiByte, int i1, int i2, long l1, long l2)
{
@ -1075,23 +882,22 @@ private static final boolean jjCanMove_2(int hiByte, int i1, int i2, long l1, lo
public static final String[] jjstrLiteralImages = {
"", null, null, null, null, null, null, null, null, null, null, "\53", "\55",
"\50", "\51", "\72", "\52", "\136", null, null, null, null, null, null, "\133",
"\173", null, "\124\117", "\135", null, null, "\124\117", "\175", null, null, };
"\173", null, "\124\117", "\135", "\175", null, null, };
/** Lexer state names. */
public static final String[] lexStateNames = {
"Boost",
"RangeEx",
"RangeIn",
"Range",
"DEFAULT",
};
/** Lex State array. */
public static final int[] jjnewLexState = {
-1, -1, -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, -1, -1, 0, -1, -1, -1, -1, -1, -1, 1,
1, 2, -1, 2, 2, -1, -1,
};
static final long[] jjtoToken = {
0x7ffffff01L,
0xffffff01L,
};
static final long[] jjtoSkip = {
0x80L,
@ -1137,7 +943,7 @@ public void ReInit(CharStream stream, int lexState)
/** Switch to specified lex state. */
public void SwitchTo(int lexState)
{
if (lexState >= 4 || lexState < 0)
if (lexState >= 3 || lexState < 0)
throw new TokenMgrError("Error: Ignoring invalid lexical state : " + lexState + ". State unchanged.", TokenMgrError.INVALID_LEXICAL_STATE);
else
curLexState = lexState;
@ -1167,8 +973,8 @@ protected Token jjFillToken()
return t;
}
int curLexState = 3;
int defaultLexState = 3;
int curLexState = 2;
int defaultLexState = 2;
int jjnewStateCnt;
int jjround;
int jjmatchedPos;
@ -1211,11 +1017,6 @@ public Token getNextToken()
jjmatchedPos = 0;
curPos = jjMoveStringLiteralDfa0_2();
break;
case 3:
jjmatchedKind = 0x7fffffff;
jjmatchedPos = 0;
curPos = jjMoveStringLiteralDfa0_3();
break;
}
if (jjmatchedKind != 0x7fffffff)
{

7
lucene/src/test/org/apache/lucene/queryParser/TestQueryParser.java
View File

@ -541,7 +541,10 @@ public class TestQueryParser extends LuceneTestCase {
public void testRange() throws Exception {
assertQueryEquals("[ a TO z]", null, "[a TO z]");
assertEquals(MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT, ((TermRangeQuery)getQuery("[ a TO z]", null)).getRewriteMethod());
assertQueryEquals("[ a TO z}", null, "[a TO z}");
assertQueryEquals("{ a TO z]", null, "{a TO z]");
assertEquals(MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT, ((TermRangeQuery)getQuery("[ a TO z]", null)).getRewriteMethod());
QueryParser qp = new QueryParser(TEST_VERSION_CURRENT, "field", new MockAnalyzer(MockTokenizer.SIMPLE, true));
qp.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
@ -555,7 +558,7 @@ public class TestQueryParser extends LuceneTestCase {
assertQueryEquals("[ a TO z] AND bar", null, "+[a TO z] +bar");
assertQueryEquals("( bar blar { a TO z}) ", null, "bar blar {a TO z}");
assertQueryEquals("gack ( bar blar { a TO z}) ", null, "gack (bar blar {a TO z})");
}
}
public void testFarsiRangeCollating() throws Exception {
Directory ramDir = newDirectory();

8
solr/src/java/org/apache/solr/search/ExtendedDismaxQParserPlugin.java
View File

@ -866,6 +866,7 @@ class ExtendedDismaxQParser extends QParser {
String val;
String val2;
boolean bool;
boolean bool2;
float flt;
int slop;
@ -904,14 +905,15 @@ class ExtendedDismaxQParser extends QParser {
}
@Override
protected Query getRangeQuery(String field, String a, String b, boolean inclusive) throws ParseException {
protected Query getRangeQuery(String field, String a, String b, boolean startInclusive, boolean endInclusive) throws ParseException {
//System.out.println("getRangeQuery:");
this.type = QType.RANGE;
this.field = field;
this.val = a;
this.val2 = b;
this.bool = inclusive;
this.bool = startInclusive;
this.bool2 = endInclusive;
return getAliasedQuery();
}
@ -1022,7 +1024,7 @@ class ExtendedDismaxQParser extends QParser {
case PREFIX: return super.getPrefixQuery(field, val);
case WILDCARD: return super.getWildcardQuery(field, val);
case FUZZY: return super.getFuzzyQuery(field, val, flt);
case RANGE: return super.getRangeQuery(field, val, val2, bool);
case RANGE: return super.getRangeQuery(field, val, val2, bool, bool2);
}
return null;

8
solr/src/java/org/apache/solr/search/SolrQueryParser.java
View File

@ -130,6 +130,7 @@ public class SolrQueryParser extends QueryParser {
}
}
@Override
protected Query getFieldQuery(String field, String queryText, boolean quoted) throws ParseException {
checkNullField(field);
// intercept magic field name of "_" to use as a hook for our
@ -161,15 +162,17 @@ public class SolrQueryParser extends QueryParser {
return super.getFieldQuery(field, queryText, quoted);
}
protected Query getRangeQuery(String field, String part1, String part2, boolean inclusive) throws ParseException {
@Override
protected Query getRangeQuery(String field, String part1, String part2, boolean startInclusive, boolean endInclusive) throws ParseException {
checkNullField(field);
SchemaField sf = schema.getField(field);
return sf.getType().getRangeQuery(parser, sf,
"*".equals(part1) ? null : part1,
"*".equals(part2) ? null : part2,
inclusive, inclusive);
startInclusive, endInclusive);
}
@Override
protected Query getPrefixQuery(String field, String termStr) throws ParseException {
checkNullField(field);
if (getLowercaseExpandedTerms()) {
@ -191,6 +194,7 @@ public class SolrQueryParser extends QueryParser {
return prefixQuery;
}
@Override
protected Query getWildcardQuery(String field, String termStr) throws ParseException {
// *:* -> MatchAllDocsQuery
if ("*".equals(field) && "*".equals(termStr)) {