You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by yo...@apache.org on 2012/11/23 20:46:01 UTC
svn commit: r1413042 [2/4] - in /lucene/dev/trunk/solr: ./ core/
core/src/java/org/apache/solr/handler/
core/src/java/org/apache/solr/handler/component/
core/src/java/org/apache/solr/parser/
core/src/java/org/apache/solr/request/ core/src/java/org/apac...
Added: lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/QueryParserTokenManager.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/QueryParserTokenManager.java?rev=1413042&view=auto
==============================================================================
--- lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/QueryParserTokenManager.java (added)
+++ lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/QueryParserTokenManager.java Fri Nov 23 19:45:50 2012
@@ -0,0 +1,1261 @@
+/* Generated By:JavaCC: Do not edit this line. QueryParserTokenManager.java */
+package org.apache.solr.parser;
+import java.io.StringReader;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Locale;
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.document.DateTools;
+import org.apache.lucene.search.BooleanClause;
+import org.apache.lucene.search.Query;
+import org.apache.lucene.search.TermRangeQuery;
+import org.apache.lucene.search.TermQuery;
+import org.apache.lucene.util.Version;
+import org.apache.solr.search.SyntaxError;
+import org.apache.solr.search.QParser;
+
+/** Token Manager. */
+public class QueryParserTokenManager implements QueryParserConstants
+{
+
+ /** Debug output. */
+ public java.io.PrintStream debugStream = System.out;
+ /** Set debug output. */
+ public void setDebugStream(java.io.PrintStream ds) { debugStream = ds; }
+private final int jjStopStringLiteralDfa_2(int pos, long active0)
+{
+ switch (pos)
+ {
+ default :
+ return -1;
+ }
+}
+private final int jjStartNfa_2(int pos, long active0)
+{
+ return jjMoveNfa_2(jjStopStringLiteralDfa_2(pos, active0), pos + 1);
+}
+private int jjStopAtPos(int pos, int kind)
+{
+ jjmatchedKind = kind;
+ jjmatchedPos = pos;
+ return pos + 1;
+}
+private int jjMoveStringLiteralDfa0_2()
+{
+ switch(curChar)
+ {
+ case 40:
+ return jjStopAtPos(0, 15);
+ case 41:
+ return jjStopAtPos(0, 16);
+ case 42:
+ return jjStartNfaWithStates_2(0, 18, 66);
+ case 43:
+ return jjStartNfaWithStates_2(0, 12, 15);
+ case 45:
+ return jjStartNfaWithStates_2(0, 13, 15);
+ case 58:
+ return jjStopAtPos(0, 17);
+ case 91:
+ return jjStopAtPos(0, 27);
+ case 94:
+ return jjStopAtPos(0, 19);
+ case 123:
+ return jjStartNfaWithStates_2(0, 28, 40);
+ default :
+ return jjMoveNfa_2(0, 0);
+ }
+}
+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_2(state, pos + 1);
+}
+static final long[] jjbitVec0 = {
+ 0x1L, 0x0L, 0x0L, 0x0L
+};
+static final long[] jjbitVec1 = {
+ 0xfffffffffffffffeL, 0xffffffffffffffffL, 0xffffffffffffffffL, 0xffffffffffffffffL
+};
+static final long[] jjbitVec3 = {
+ 0x0L, 0x0L, 0xffffffffffffffffL, 0xffffffffffffffffL
+};
+static final long[] jjbitVec4 = {
+ 0xfffefffffffffffeL, 0xffffffffffffffffL, 0xffffffffffffffffL, 0xffffffffffffffffL
+};
+private int jjMoveNfa_2(int startState, int curPos)
+{
+ int startsAt = 0;
+ jjnewStateCnt = 66;
+ 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 66:
+ case 32:
+ if ((0xfbfffcf8ffffd9ffL & l) == 0L)
+ break;
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ break;
+ case 0:
+ if ((0xfbff54f8ffffd9ffL & l) != 0L)
+ {
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ }
+ else if ((0x100002600L & l) != 0L)
+ {
+ if (kind > 8)
+ kind = 8;
+ }
+ else if ((0x280200000000L & l) != 0L)
+ jjstateSet[jjnewStateCnt++] = 15;
+ else if (curChar == 47)
+ jjCheckNAddStates(0, 2);
+ else if (curChar == 34)
+ jjCheckNAddStates(3, 5);
+ if ((0x7bff50f8ffffd9ffL & l) != 0L)
+ {
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddStates(6, 10);
+ }
+ else if (curChar == 42)
+ {
+ if (kind > 24)
+ kind = 24;
+ }
+ else if (curChar == 33)
+ {
+ if (kind > 11)
+ kind = 11;
+ }
+ if (curChar == 39)
+ jjCheckNAddStates(11, 13);
+ else if (curChar == 38)
+ jjstateSet[jjnewStateCnt++] = 4;
+ break;
+ case 4:
+ if (curChar == 38 && kind > 9)
+ kind = 9;
+ break;
+ case 5:
+ if (curChar == 38)
+ jjstateSet[jjnewStateCnt++] = 4;
+ break;
+ case 13:
+ if (curChar == 33 && kind > 11)
+ kind = 11;
+ break;
+ case 14:
+ if ((0x280200000000L & l) != 0L)
+ jjstateSet[jjnewStateCnt++] = 15;
+ break;
+ case 15:
+ if ((0x100002600L & l) != 0L && kind > 14)
+ kind = 14;
+ break;
+ case 16:
+ if (curChar == 34)
+ jjCheckNAddStates(3, 5);
+ break;
+ case 17:
+ if ((0xfffffffbffffffffL & l) != 0L)
+ jjCheckNAddStates(3, 5);
+ break;
+ case 19:
+ jjCheckNAddStates(3, 5);
+ break;
+ case 20:
+ if (curChar == 34 && kind > 20)
+ kind = 20;
+ break;
+ case 21:
+ if (curChar == 39)
+ jjCheckNAddStates(11, 13);
+ break;
+ case 22:
+ if ((0xffffff7fffffffffL & l) != 0L)
+ jjCheckNAddStates(11, 13);
+ break;
+ case 24:
+ jjCheckNAddStates(11, 13);
+ break;
+ case 25:
+ if (curChar == 39 && kind > 21)
+ kind = 21;
+ break;
+ case 27:
+ if ((0x3ff000000000000L & l) == 0L)
+ break;
+ if (kind > 23)
+ kind = 23;
+ jjAddStates(14, 15);
+ break;
+ case 28:
+ if (curChar == 46)
+ jjCheckNAdd(29);
+ break;
+ case 29:
+ if ((0x3ff000000000000L & l) == 0L)
+ break;
+ if (kind > 23)
+ kind = 23;
+ jjCheckNAdd(29);
+ break;
+ case 30:
+ if (curChar == 42 && kind > 24)
+ kind = 24;
+ break;
+ case 31:
+ if ((0xfbff54f8ffffd9ffL & l) == 0L)
+ break;
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ break;
+ case 34:
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ break;
+ case 35:
+ case 37:
+ if (curChar == 47)
+ jjCheckNAddStates(0, 2);
+ break;
+ case 36:
+ if ((0xffff7fffffffffffL & l) != 0L)
+ jjCheckNAddStates(0, 2);
+ break;
+ case 39:
+ if (curChar == 47 && kind > 26)
+ kind = 26;
+ break;
+ case 40:
+ if (curChar == 33)
+ jjCheckNAddStates(16, 18);
+ break;
+ case 41:
+ if ((0x100002600L & l) != 0L)
+ jjCheckNAddTwoStates(41, 42);
+ break;
+ case 42:
+ if ((0xdfffffffffffffffL & l) != 0L)
+ jjCheckNAddStates(19, 22);
+ break;
+ case 43:
+ if (curChar == 61)
+ jjCheckNAddStates(23, 28);
+ break;
+ case 44:
+ if (curChar == 34)
+ jjCheckNAddStates(29, 31);
+ break;
+ case 45:
+ if ((0xfffffffbffffffffL & l) != 0L)
+ jjCheckNAddStates(29, 31);
+ break;
+ case 47:
+ jjCheckNAddStates(29, 31);
+ break;
+ case 48:
+ if (curChar == 34)
+ jjCheckNAddStates(16, 18);
+ break;
+ case 51:
+ if ((0xfffffdfefffff9ffL & l) == 0L)
+ break;
+ if (kind > 29)
+ kind = 29;
+ jjstateSet[jjnewStateCnt++] = 51;
+ break;
+ case 52:
+ if (curChar == 39)
+ jjCheckNAddStates(32, 34);
+ break;
+ case 53:
+ if ((0xffffff7fffffffffL & l) != 0L)
+ jjCheckNAddStates(32, 34);
+ break;
+ case 55:
+ jjCheckNAddStates(32, 34);
+ break;
+ case 56:
+ if (curChar == 39)
+ jjCheckNAddStates(16, 18);
+ break;
+ case 57:
+ if ((0xfffffffeffffffffL & l) != 0L)
+ jjCheckNAddStates(35, 38);
+ break;
+ case 58:
+ if ((0x7bff50f8ffffd9ffL & l) == 0L)
+ break;
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddStates(6, 10);
+ break;
+ case 59:
+ if ((0x7bfff8f8ffffd9ffL & l) == 0L)
+ break;
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddTwoStates(59, 60);
+ break;
+ case 61:
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddTwoStates(59, 60);
+ break;
+ case 62:
+ if ((0x7bfff8f8ffffd9ffL & l) != 0L)
+ jjCheckNAddStates(39, 41);
+ break;
+ case 64:
+ jjCheckNAddStates(39, 41);
+ break;
+ default : break;
+ }
+ } while(i != startsAt);
+ }
+ else if (curChar < 128)
+ {
+ long l = 1L << (curChar & 077);
+ do
+ {
+ switch(jjstateSet[--i])
+ {
+ case 66:
+ if ((0x97ffffff87ffffffL & l) != 0L)
+ {
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ }
+ else if (curChar == 92)
+ jjCheckNAddTwoStates(34, 34);
+ break;
+ case 0:
+ if ((0x97ffffff87ffffffL & l) != 0L)
+ {
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddStates(6, 10);
+ }
+ else if (curChar == 92)
+ jjCheckNAddStates(42, 44);
+ else if (curChar == 123)
+ jjstateSet[jjnewStateCnt++] = 40;
+ else if (curChar == 126)
+ {
+ if (kind > 23)
+ kind = 23;
+ jjstateSet[jjnewStateCnt++] = 27;
+ }
+ if ((0x97ffffff87ffffffL & l) != 0L)
+ {
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ }
+ if (curChar == 78)
+ jjstateSet[jjnewStateCnt++] = 11;
+ else if (curChar == 124)
+ jjstateSet[jjnewStateCnt++] = 8;
+ else if (curChar == 79)
+ jjstateSet[jjnewStateCnt++] = 6;
+ else if (curChar == 65)
+ jjstateSet[jjnewStateCnt++] = 2;
+ break;
+ case 1:
+ if (curChar == 68 && kind > 9)
+ kind = 9;
+ break;
+ case 2:
+ if (curChar == 78)
+ jjstateSet[jjnewStateCnt++] = 1;
+ break;
+ case 3:
+ if (curChar == 65)
+ jjstateSet[jjnewStateCnt++] = 2;
+ break;
+ case 6:
+ if (curChar == 82 && kind > 10)
+ kind = 10;
+ break;
+ case 7:
+ if (curChar == 79)
+ jjstateSet[jjnewStateCnt++] = 6;
+ break;
+ case 8:
+ if (curChar == 124 && kind > 10)
+ kind = 10;
+ break;
+ case 9:
+ if (curChar == 124)
+ jjstateSet[jjnewStateCnt++] = 8;
+ break;
+ case 10:
+ if (curChar == 84 && kind > 11)
+ kind = 11;
+ break;
+ case 11:
+ if (curChar == 79)
+ jjstateSet[jjnewStateCnt++] = 10;
+ break;
+ case 12:
+ if (curChar == 78)
+ jjstateSet[jjnewStateCnt++] = 11;
+ break;
+ case 17:
+ if ((0xffffffffefffffffL & l) != 0L)
+ jjCheckNAddStates(3, 5);
+ break;
+ case 18:
+ if (curChar == 92)
+ jjstateSet[jjnewStateCnt++] = 19;
+ break;
+ case 19:
+ jjCheckNAddStates(3, 5);
+ break;
+ case 22:
+ if ((0xffffffffefffffffL & l) != 0L)
+ jjCheckNAddStates(11, 13);
+ break;
+ case 23:
+ if (curChar == 92)
+ jjstateSet[jjnewStateCnt++] = 24;
+ break;
+ case 24:
+ jjCheckNAddStates(11, 13);
+ break;
+ case 26:
+ if (curChar != 126)
+ break;
+ if (kind > 23)
+ kind = 23;
+ jjstateSet[jjnewStateCnt++] = 27;
+ break;
+ case 31:
+ if ((0x97ffffff87ffffffL & l) == 0L)
+ break;
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ break;
+ case 32:
+ if ((0x97ffffff87ffffffL & l) == 0L)
+ break;
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ break;
+ case 33:
+ if (curChar == 92)
+ jjCheckNAddTwoStates(34, 34);
+ break;
+ case 34:
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ break;
+ case 36:
+ jjAddStates(0, 2);
+ break;
+ case 38:
+ if (curChar == 92)
+ jjstateSet[jjnewStateCnt++] = 37;
+ break;
+ case 42:
+ if ((0xdfffffffffffffffL & l) != 0L)
+ jjCheckNAddStates(19, 22);
+ break;
+ case 45:
+ if ((0xffffffffefffffffL & l) != 0L)
+ jjCheckNAddStates(29, 31);
+ break;
+ case 46:
+ if (curChar == 92)
+ jjstateSet[jjnewStateCnt++] = 47;
+ break;
+ case 47:
+ jjCheckNAddStates(29, 31);
+ break;
+ case 49:
+ if (curChar != 125)
+ break;
+ if (kind > 29)
+ kind = 29;
+ jjCheckNAddTwoStates(50, 51);
+ break;
+ case 50:
+ if (curChar == 123)
+ jjstateSet[jjnewStateCnt++] = 40;
+ break;
+ case 51:
+ if ((0xf7ffffffbfffffffL & l) == 0L)
+ break;
+ if (kind > 29)
+ kind = 29;
+ jjCheckNAdd(51);
+ break;
+ case 53:
+ if ((0xffffffffefffffffL & l) != 0L)
+ jjCheckNAddStates(32, 34);
+ break;
+ case 54:
+ if (curChar == 92)
+ jjstateSet[jjnewStateCnt++] = 55;
+ break;
+ case 55:
+ jjCheckNAddStates(32, 34);
+ break;
+ case 57:
+ if ((0xdfffffffffffffffL & l) != 0L)
+ jjCheckNAddStates(35, 38);
+ break;
+ case 58:
+ if ((0x97ffffff87ffffffL & l) == 0L)
+ break;
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddStates(6, 10);
+ break;
+ case 59:
+ if ((0x97ffffff87ffffffL & l) == 0L)
+ break;
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddTwoStates(59, 60);
+ break;
+ case 60:
+ if (curChar == 92)
+ jjCheckNAddTwoStates(61, 61);
+ break;
+ case 61:
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddTwoStates(59, 60);
+ break;
+ case 62:
+ if ((0x97ffffff87ffffffL & l) != 0L)
+ jjCheckNAddStates(39, 41);
+ break;
+ case 63:
+ if (curChar == 92)
+ jjCheckNAddTwoStates(64, 64);
+ break;
+ case 64:
+ jjCheckNAddStates(39, 41);
+ break;
+ case 65:
+ if (curChar == 92)
+ jjCheckNAddStates(42, 44);
+ 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 66:
+ case 32:
+ if (!jjCanMove_2(hiByte, i1, i2, l1, l2))
+ break;
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ break;
+ case 0:
+ if (jjCanMove_0(hiByte, i1, i2, l1, l2))
+ {
+ if (kind > 8)
+ kind = 8;
+ }
+ if (jjCanMove_2(hiByte, i1, i2, l1, l2))
+ {
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ }
+ if (jjCanMove_2(hiByte, i1, i2, l1, l2))
+ {
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddStates(6, 10);
+ }
+ break;
+ case 15:
+ if (jjCanMove_0(hiByte, i1, i2, l1, l2) && kind > 14)
+ kind = 14;
+ break;
+ case 17:
+ case 19:
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ jjCheckNAddStates(3, 5);
+ break;
+ case 22:
+ case 24:
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ jjCheckNAddStates(11, 13);
+ break;
+ case 31:
+ if (!jjCanMove_2(hiByte, i1, i2, l1, l2))
+ break;
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ break;
+ case 34:
+ if (!jjCanMove_1(hiByte, i1, i2, l1, l2))
+ break;
+ if (kind > 25)
+ kind = 25;
+ jjCheckNAddTwoStates(32, 33);
+ break;
+ case 36:
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ jjAddStates(0, 2);
+ break;
+ case 41:
+ if (jjCanMove_0(hiByte, i1, i2, l1, l2))
+ jjCheckNAddTwoStates(41, 42);
+ break;
+ case 42:
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ jjCheckNAddStates(19, 22);
+ break;
+ case 45:
+ case 47:
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ jjCheckNAddStates(29, 31);
+ break;
+ case 51:
+ if (!jjCanMove_1(hiByte, i1, i2, l1, l2))
+ break;
+ if (kind > 29)
+ kind = 29;
+ jjstateSet[jjnewStateCnt++] = 51;
+ break;
+ case 53:
+ case 55:
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ jjCheckNAddStates(32, 34);
+ break;
+ case 57:
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ jjCheckNAddStates(35, 38);
+ break;
+ case 58:
+ if (!jjCanMove_2(hiByte, i1, i2, l1, l2))
+ break;
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddStates(6, 10);
+ break;
+ case 59:
+ if (!jjCanMove_2(hiByte, i1, i2, l1, l2))
+ break;
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddTwoStates(59, 60);
+ break;
+ case 61:
+ if (!jjCanMove_1(hiByte, i1, i2, l1, l2))
+ break;
+ if (kind > 22)
+ kind = 22;
+ jjCheckNAddTwoStates(59, 60);
+ break;
+ case 62:
+ if (jjCanMove_2(hiByte, i1, i2, l1, l2))
+ jjCheckNAddStates(39, 41);
+ break;
+ case 64:
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ jjCheckNAddStates(39, 41);
+ break;
+ default : break;
+ }
+ } while(i != startsAt);
+ }
+ if (kind != 0x7fffffff)
+ {
+ jjmatchedKind = kind;
+ jjmatchedPos = curPos;
+ kind = 0x7fffffff;
+ }
+ ++curPos;
+ if ((i = jjnewStateCnt) == (startsAt = 66 - (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);
+}
+private int jjMoveNfa_0(int startState, int curPos)
+{
+ int startsAt = 0;
+ jjnewStateCnt = 4;
+ 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 ((0x3ff000000000000L & l) != 0L)
+ {
+ if (kind > 30)
+ kind = 30;
+ jjCheckNAddTwoStates(1, 2);
+ }
+ else if (curChar == 45)
+ jjCheckNAdd(1);
+ break;
+ case 1:
+ if ((0x3ff000000000000L & l) == 0L)
+ break;
+ if (kind > 30)
+ kind = 30;
+ jjCheckNAddTwoStates(1, 2);
+ break;
+ case 2:
+ if (curChar == 46)
+ jjCheckNAdd(3);
+ break;
+ case 3:
+ if ((0x3ff000000000000L & l) == 0L)
+ break;
+ if (kind > 30)
+ kind = 30;
+ jjCheckNAdd(3);
+ break;
+ default : break;
+ }
+ } while(i != startsAt);
+ }
+ else if (curChar < 128)
+ {
+ long l = 1L << (curChar & 077);
+ do
+ {
+ switch(jjstateSet[--i])
+ {
+ 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])
+ {
+ default : break;
+ }
+ } while(i != startsAt);
+ }
+ if (kind != 0x7fffffff)
+ {
+ jjmatchedKind = kind;
+ jjmatchedPos = curPos;
+ kind = 0x7fffffff;
+ }
+ ++curPos;
+ if ((i = jjnewStateCnt) == (startsAt = 4 - (jjnewStateCnt = startsAt)))
+ return curPos;
+ try { curChar = input_stream.readChar(); }
+ 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 = 35;
+ 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 93:
+ return jjStopAtPos(0, 32);
+ case 125:
+ return jjStopAtPos(0, 33);
+ 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 > 35)
+ kind = 35;
+ jjCheckNAdd(6);
+ }
+ if ((0x100002600L & l) != 0L)
+ {
+ if (kind > 8)
+ kind = 8;
+ }
+ else if (curChar == 34)
+ jjCheckNAddTwoStates(2, 4);
+ break;
+ case 1:
+ if (curChar == 34)
+ jjCheckNAddTwoStates(2, 4);
+ break;
+ case 2:
+ if ((0xfffffffbffffffffL & l) != 0L)
+ jjCheckNAddStates(45, 47);
+ break;
+ case 3:
+ if (curChar == 34)
+ jjCheckNAddStates(45, 47);
+ break;
+ case 5:
+ if (curChar == 34 && kind > 34)
+ kind = 34;
+ break;
+ case 6:
+ if ((0xfffffffeffffffffL & l) == 0L)
+ break;
+ if (kind > 35)
+ kind = 35;
+ 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 ((0xdfffffffdfffffffL & l) == 0L)
+ break;
+ if (kind > 35)
+ kind = 35;
+ jjCheckNAdd(6);
+ break;
+ case 2:
+ jjAddStates(45, 47);
+ 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 > 8)
+ kind = 8;
+ }
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ {
+ if (kind > 35)
+ kind = 35;
+ jjCheckNAdd(6);
+ }
+ break;
+ case 2:
+ if (jjCanMove_1(hiByte, i1, i2, l1, l2))
+ jjAddStates(45, 47);
+ break;
+ case 6:
+ if (!jjCanMove_1(hiByte, i1, i2, l1, l2))
+ break;
+ if (kind > 35)
+ kind = 35;
+ 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; }
+ }
+}
+static final int[] jjnextStates = {
+ 36, 38, 39, 17, 18, 20, 59, 62, 30, 63, 60, 22, 23, 25, 27, 28,
+ 41, 42, 49, 41, 42, 43, 49, 41, 42, 44, 52, 57, 49, 45, 46, 48,
+ 53, 54, 56, 41, 42, 57, 49, 62, 30, 63, 61, 64, 34, 2, 4, 5,
+};
+private static final boolean jjCanMove_0(int hiByte, int i1, int i2, long l1, long l2)
+{
+ switch(hiByte)
+ {
+ case 48:
+ return ((jjbitVec0[i2] & l2) != 0L);
+ default :
+ return false;
+ }
+}
+private static final boolean jjCanMove_1(int hiByte, int i1, int i2, long l1, long l2)
+{
+ switch(hiByte)
+ {
+ case 0:
+ return ((jjbitVec3[i2] & l2) != 0L);
+ default :
+ if ((jjbitVec1[i1] & l1) != 0L)
+ return true;
+ return false;
+ }
+}
+private static final boolean jjCanMove_2(int hiByte, int i1, int i2, long l1, long l2)
+{
+ switch(hiByte)
+ {
+ case 0:
+ return ((jjbitVec3[i2] & l2) != 0L);
+ case 48:
+ return ((jjbitVec1[i2] & l2) != 0L);
+ default :
+ if ((jjbitVec4[i1] & l1) != 0L)
+ return true;
+ return false;
+ }
+}
+
+/** Token literal values. */
+public static final String[] jjstrLiteralImages = {
+"", null, null, null, null, null, null, null, null, null, null, null, "\53",
+"\55", null, "\50", "\51", "\72", "\52", "\136", null, null, null, null, null, null,
+null, "\133", "\173", null, null, "\124\117", "\135", "\175", null, null, };
+
+/** Lexer state names. */
+public static final String[] lexStateNames = {
+ "Boost",
+ "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, -1, -1, 0, -1, -1, -1, -1, -1,
+ -1, -1, 1, 1, -1, 2, -1, 2, 2, -1, -1,
+};
+static final long[] jjtoToken = {
+ 0xffffffe01L,
+};
+static final long[] jjtoSkip = {
+ 0x100L,
+};
+protected CharStream input_stream;
+private final int[] jjrounds = new int[66];
+private final int[] jjstateSet = new int[132];
+protected char curChar;
+/** Constructor. */
+public QueryParserTokenManager(CharStream stream){
+ input_stream = stream;
+}
+
+/** Constructor. */
+public QueryParserTokenManager(CharStream stream, int lexState){
+ this(stream);
+ SwitchTo(lexState);
+}
+
+/** Reinitialise parser. */
+public void ReInit(CharStream stream)
+{
+ jjmatchedPos = jjnewStateCnt = 0;
+ curLexState = defaultLexState;
+ input_stream = stream;
+ ReInitRounds();
+}
+private void ReInitRounds()
+{
+ int i;
+ jjround = 0x80000001;
+ for (i = 66; i-- > 0;)
+ jjrounds[i] = 0x80000000;
+}
+
+/** Reinitialise parser. */
+public void ReInit(CharStream stream, int lexState)
+{
+ ReInit(stream);
+ SwitchTo(lexState);
+}
+
+/** Switch to specified lex state. */
+public void SwitchTo(int lexState)
+{
+ if (lexState >= 3 || lexState < 0)
+ throw new TokenMgrError("Error: Ignoring invalid lexical state : " + lexState + ". State unchanged.", TokenMgrError.INVALID_LEXICAL_STATE);
+ else
+ curLexState = lexState;
+}
+
+protected Token jjFillToken()
+{
+ final Token t;
+ final String curTokenImage;
+ final int beginLine;
+ final int endLine;
+ final int beginColumn;
+ final int endColumn;
+ String im = jjstrLiteralImages[jjmatchedKind];
+ curTokenImage = (im == null) ? input_stream.GetImage() : im;
+ beginLine = input_stream.getBeginLine();
+ beginColumn = input_stream.getBeginColumn();
+ endLine = input_stream.getEndLine();
+ endColumn = input_stream.getEndColumn();
+ t = Token.newToken(jjmatchedKind, curTokenImage);
+
+ t.beginLine = beginLine;
+ t.endLine = endLine;
+ t.beginColumn = beginColumn;
+ t.endColumn = endColumn;
+
+ return t;
+}
+
+int curLexState = 2;
+int defaultLexState = 2;
+int jjnewStateCnt;
+int jjround;
+int jjmatchedPos;
+int jjmatchedKind;
+
+/** Get the next Token. */
+public Token getNextToken()
+{
+ Token matchedToken;
+ int curPos = 0;
+
+ EOFLoop :
+ for (;;)
+ {
+ try
+ {
+ curChar = input_stream.BeginToken();
+ }
+ catch(java.io.IOException e)
+ {
+ jjmatchedKind = 0;
+ matchedToken = jjFillToken();
+ return matchedToken;
+ }
+
+ switch(curLexState)
+ {
+ case 0:
+ jjmatchedKind = 0x7fffffff;
+ jjmatchedPos = 0;
+ curPos = jjMoveStringLiteralDfa0_0();
+ break;
+ case 1:
+ jjmatchedKind = 0x7fffffff;
+ jjmatchedPos = 0;
+ curPos = jjMoveStringLiteralDfa0_1();
+ break;
+ case 2:
+ jjmatchedKind = 0x7fffffff;
+ jjmatchedPos = 0;
+ curPos = jjMoveStringLiteralDfa0_2();
+ break;
+ }
+ if (jjmatchedKind != 0x7fffffff)
+ {
+ if (jjmatchedPos + 1 < curPos)
+ input_stream.backup(curPos - jjmatchedPos - 1);
+ if ((jjtoToken[jjmatchedKind >> 6] & (1L << (jjmatchedKind & 077))) != 0L)
+ {
+ matchedToken = jjFillToken();
+ if (jjnewLexState[jjmatchedKind] != -1)
+ curLexState = jjnewLexState[jjmatchedKind];
+ return matchedToken;
+ }
+ else
+ {
+ if (jjnewLexState[jjmatchedKind] != -1)
+ curLexState = jjnewLexState[jjmatchedKind];
+ continue EOFLoop;
+ }
+ }
+ int error_line = input_stream.getEndLine();
+ int error_column = input_stream.getEndColumn();
+ String error_after = null;
+ boolean EOFSeen = false;
+ try { input_stream.readChar(); input_stream.backup(1); }
+ catch (java.io.IOException e1) {
+ EOFSeen = true;
+ error_after = curPos <= 1 ? "" : input_stream.GetImage();
+ if (curChar == '\n' || curChar == '\r') {
+ error_line++;
+ error_column = 0;
+ }
+ else
+ error_column++;
+ }
+ if (!EOFSeen) {
+ input_stream.backup(1);
+ error_after = curPos <= 1 ? "" : input_stream.GetImage();
+ }
+ throw new TokenMgrError(EOFSeen, curLexState, error_line, error_column, error_after, curChar, TokenMgrError.LEXICAL_ERROR);
+ }
+}
+
+private void jjCheckNAdd(int state)
+{
+ if (jjrounds[state] != jjround)
+ {
+ jjstateSet[jjnewStateCnt++] = state;
+ jjrounds[state] = jjround;
+ }
+}
+private void jjAddStates(int start, int end)
+{
+ do {
+ jjstateSet[jjnewStateCnt++] = jjnextStates[start];
+ } while (start++ != end);
+}
+private void jjCheckNAddTwoStates(int state1, int state2)
+{
+ jjCheckNAdd(state1);
+ jjCheckNAdd(state2);
+}
+
+private void jjCheckNAddStates(int start, int end)
+{
+ do {
+ jjCheckNAdd(jjnextStates[start]);
+ } while (start++ != end);
+}
+
+}
Added: lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/SolrQueryParserBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/SolrQueryParserBase.java?rev=1413042&view=auto
==============================================================================
--- lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/SolrQueryParserBase.java (added)
+++ lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/SolrQueryParserBase.java Fri Nov 23 19:45:50 2012
@@ -0,0 +1,1033 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.solr.parser;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.CachingTokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.analysis.tokenattributes.TermToBytesRefAttribute;
+import org.apache.lucene.analysis.util.TokenFilterFactory;
+import org.apache.lucene.index.Term;
+import org.apache.lucene.search.AutomatonQuery;
+import org.apache.lucene.search.BooleanClause;
+import org.apache.lucene.search.BooleanQuery;
+import org.apache.lucene.search.FuzzyQuery;
+import org.apache.lucene.search.MatchAllDocsQuery;
+import org.apache.lucene.search.MultiPhraseQuery;
+import org.apache.lucene.search.MultiTermQuery;
+import org.apache.lucene.search.PhraseQuery;
+import org.apache.lucene.search.PrefixQuery;
+import org.apache.lucene.search.Query;
+import org.apache.lucene.search.RegexpQuery;
+import org.apache.lucene.search.TermQuery;
+import org.apache.lucene.search.WildcardQuery;
+import org.apache.lucene.util.BytesRef;
+import org.apache.lucene.util.ToStringUtils;
+import org.apache.lucene.util.Version;
+import org.apache.lucene.util.automaton.Automaton;
+import org.apache.lucene.util.automaton.BasicAutomata;
+import org.apache.lucene.util.automaton.BasicOperations;
+import org.apache.lucene.util.automaton.SpecialOperations;
+import org.apache.solr.analysis.ReversedWildcardFilterFactory;
+import org.apache.solr.analysis.TokenizerChain;
+import org.apache.solr.common.SolrException;
+import org.apache.solr.parser.QueryParser.Operator;
+import org.apache.solr.schema.FieldType;
+import org.apache.solr.schema.IndexSchema;
+import org.apache.solr.schema.SchemaField;
+import org.apache.solr.schema.TextField;
+import org.apache.solr.search.QParser;
+import org.apache.solr.search.SyntaxError;
+
+import java.io.IOException;
+import java.io.StringReader;
+import java.util.ArrayList;
+import java.util.EnumSet;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+/** This class is overridden by QueryParser in QueryParser.jj
+ * and acts to separate the majority of the Java code from the .jj grammar file.
+ */
+public abstract class SolrQueryParserBase {
+
+
+ static final int CONJ_NONE = 0;
+ static final int CONJ_AND = 1;
+ static final int CONJ_OR = 2;
+
+ static final int MOD_NONE = 0;
+ static final int MOD_NOT = 10;
+ static final int MOD_REQ = 11;
+
+ // make it possible to call setDefaultOperator() without accessing
+ // the nested class:
+ /** Alternative form of QueryParser.Operator.AND */
+ public static final Operator AND_OPERATOR = Operator.AND;
+ /** Alternative form of QueryParser.Operator.OR */
+ public static final Operator OR_OPERATOR = Operator.OR;
+
+ /** The default operator that parser uses to combine query terms */
+ Operator operator = OR_OPERATOR;
+
+ MultiTermQuery.RewriteMethod multiTermRewriteMethod = MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT;
+ boolean allowLeadingWildcard = true;
+ boolean enablePositionIncrements = true;
+
+ String defaultField;
+ int phraseSlop = 0; // default slop for phrase queries
+ float fuzzyMinSim = FuzzyQuery.defaultMinSimilarity;
+ int fuzzyPrefixLength = FuzzyQuery.defaultPrefixLength;
+
+ boolean autoGeneratePhraseQueries = false;
+
+
+ protected IndexSchema schema;
+ protected QParser parser;
+ protected Analyzer analyzer;
+
+ // implementation detail - caching ReversedWildcardFilterFactory based on type
+ private Map<FieldType, ReversedWildcardFilterFactory> leadingWildcards;
+
+ /**
+ * Identifies the list of all known "magic fields" that trigger
+ * special parsing behavior
+ */
+ public static enum MagicFieldName {
+ VAL("_val_", "func"), QUERY("_query_", null);
+
+ public final String field;
+ public final String subParser;
+ MagicFieldName(final String field, final String subParser) {
+ this.field = field;
+ this.subParser = subParser;
+ }
+ public String toString() {
+ return field;
+ }
+ private final static Map<String,MagicFieldName> lookup
+ = new HashMap<String,MagicFieldName>();
+ static {
+ for(MagicFieldName s : EnumSet.allOf(MagicFieldName.class))
+ lookup.put(s.toString(), s);
+ }
+ public static MagicFieldName get(final String field) {
+ return lookup.get(field);
+ }
+ }
+
+
+ // So the generated QueryParser(CharStream) won't error out
+ protected SolrQueryParserBase() {
+ }
+ // the generated parser will create these in QueryParser
+ public abstract void ReInit(CharStream stream);
+ public abstract Query TopLevelQuery(String field) throws ParseException, SyntaxError;
+
+
+ public void init(Version matchVersion, String defaultField, QParser parser) {
+ this.schema = parser.getReq().getSchema();
+ this.parser = parser;
+ this.defaultField = defaultField;
+ this.analyzer = schema.getQueryAnalyzer();
+ }
+
+ /** Parses a query string, returning a {@link org.apache.lucene.search.Query}.
+ * @param query the query string to be parsed.
+ */
+ public Query parse(String query) throws SyntaxError {
+ ReInit(new FastCharStream(new StringReader(query)));
+ try {
+ // TopLevelQuery is a Query followed by the end-of-input (EOF)
+ Query res = TopLevelQuery(null); // pass null so we can tell later if an explicit field was provided or not
+ return res!=null ? res : newBooleanQuery(false);
+ }
+ catch (ParseException tme) {
+ throw new SyntaxError("Cannot parse '" +query+ "': " + tme.getMessage(), tme);
+ }
+ catch (TokenMgrError tme) {
+ throw new SyntaxError("Cannot parse '" +query+ "': " + tme.getMessage(), tme);
+ }
+ catch (BooleanQuery.TooManyClauses tmc) {
+ throw new SyntaxError("Cannot parse '" +query+ "': too many boolean clauses", tmc);
+ }
+ }
+
+
+ /**
+ * @return Returns the default field.
+ */
+ public String getDefaultField() {
+ return this.defaultField;
+ }
+
+ /** Handles the default field if null is passed */
+ public String getField(String fieldName) {
+ return fieldName != null ? fieldName : this.defaultField;
+ }
+
+ /**
+ * @see #setAutoGeneratePhraseQueries(boolean)
+ */
+ public final boolean getAutoGeneratePhraseQueries() {
+ return autoGeneratePhraseQueries;
+ }
+
+ /**
+ * Set to true if phrase queries will be automatically generated
+ * when the analyzer returns more than one term from whitespace
+ * delimited text.
+ * NOTE: this behavior may not be suitable for all languages.
+ * <p>
+ * Set to false if phrase queries should only be generated when
+ * surrounded by double quotes.
+ */
+ public final void setAutoGeneratePhraseQueries(boolean value) {
+ this.autoGeneratePhraseQueries = value;
+ }
+
+ /**
+ * Get the minimal similarity for fuzzy queries.
+ */
+ public float getFuzzyMinSim() {
+ return fuzzyMinSim;
+ }
+
+ /**
+ * Set the minimum similarity for fuzzy queries.
+ * Default is 2f.
+ */
+ public void setFuzzyMinSim(float fuzzyMinSim) {
+ this.fuzzyMinSim = fuzzyMinSim;
+ }
+
+ /**
+ * Get the prefix length for fuzzy queries.
+ * @return Returns the fuzzyPrefixLength.
+ */
+ public int getFuzzyPrefixLength() {
+ return fuzzyPrefixLength;
+ }
+
+ /**
+ * Set the prefix length for fuzzy queries. Default is 0.
+ * @param fuzzyPrefixLength The fuzzyPrefixLength to set.
+ */
+ public void setFuzzyPrefixLength(int fuzzyPrefixLength) {
+ this.fuzzyPrefixLength = fuzzyPrefixLength;
+ }
+
+ /**
+ * Sets the default slop for phrases. If zero, then exact phrase matches
+ * are required. Default value is zero.
+ */
+ public void setPhraseSlop(int phraseSlop) {
+ this.phraseSlop = phraseSlop;
+ }
+
+ /**
+ * Gets the default slop for phrases.
+ */
+ public int getPhraseSlop() {
+ return phraseSlop;
+ }
+
+
+ /**
+ * Set to <code>true</code> to allow leading wildcard characters.
+ * <p>
+ * When set, <code>*</code> or <code>?</code> are allowed as
+ * the first character of a PrefixQuery and WildcardQuery.
+ * Note that this can produce very slow
+ * queries on big indexes.
+ * <p>
+ * Default: false.
+ */
+ public void setAllowLeadingWildcard(boolean allowLeadingWildcard) {
+ this.allowLeadingWildcard = allowLeadingWildcard;
+ }
+
+ /**
+ * @see #setAllowLeadingWildcard(boolean)
+ */
+ public boolean getAllowLeadingWildcard() {
+ return allowLeadingWildcard;
+ }
+
+ /**
+ * Set to <code>true</code> to enable position increments in result query.
+ * <p>
+ * When set, result phrase and multi-phrase queries will
+ * be aware of position increments.
+ * Useful when e.g. a StopFilter increases the position increment of
+ * the token that follows an omitted token.
+ * <p>
+ * Default: true.
+ */
+ public void setEnablePositionIncrements(boolean enable) {
+ this.enablePositionIncrements = enable;
+ }
+
+ /**
+ * @see #setEnablePositionIncrements(boolean)
+ */
+ public boolean getEnablePositionIncrements() {
+ return enablePositionIncrements;
+ }
+
+ /**
+ * Sets the boolean operator of the QueryParser.
+ * In default mode (<code>OR_OPERATOR</code>) terms without any modifiers
+ * are considered optional: for example <code>capital of Hungary</code> is equal to
+ * <code>capital OR of OR Hungary</code>.<br/>
+ * In <code>AND_OPERATOR</code> mode terms are considered to be in conjunction: the
+ * above mentioned query is parsed as <code>capital AND of AND Hungary</code>
+ */
+ public void setDefaultOperator(Operator op) {
+ this.operator = op;
+ }
+
+
+ /**
+ * Gets implicit operator setting, which will be either AND_OPERATOR
+ * or OR_OPERATOR.
+ */
+ public Operator getDefaultOperator() {
+ return operator;
+ }
+
+
+ /**
+ * By default QueryParser uses {@link org.apache.lucene.search.MultiTermQuery#CONSTANT_SCORE_AUTO_REWRITE_DEFAULT}
+ * when creating a PrefixQuery, WildcardQuery or RangeQuery. This implementation is generally preferable because it
+ * a) Runs faster b) Does not have the scarcity of terms unduly influence score
+ * c) avoids any "TooManyBooleanClauses" exception.
+ * However, if your application really needs to use the
+ * old-fashioned BooleanQuery expansion rewriting and the above
+ * points are not relevant then use this to change
+ * the rewrite method.
+ */
+ public void setMultiTermRewriteMethod(MultiTermQuery.RewriteMethod method) {
+ multiTermRewriteMethod = method;
+ }
+
+
+ /**
+ * @see #setMultiTermRewriteMethod
+ */
+ public MultiTermQuery.RewriteMethod getMultiTermRewriteMethod() {
+ return multiTermRewriteMethod;
+ }
+
+
+ protected void addClause(List<BooleanClause> clauses, int conj, int mods, Query q) {
+ boolean required, prohibited;
+
+ // If this term is introduced by AND, make the preceding term required,
+ // unless it's already prohibited
+ if (clauses.size() > 0 && conj == CONJ_AND) {
+ BooleanClause c = clauses.get(clauses.size()-1);
+ if (!c.isProhibited())
+ c.setOccur(BooleanClause.Occur.MUST);
+ }
+
+ if (clauses.size() > 0 && operator == AND_OPERATOR && conj == CONJ_OR) {
+ // If this term is introduced by OR, make the preceding term optional,
+ // unless it's prohibited (that means we leave -a OR b but +a OR b-->a OR b)
+ // notice if the input is a OR b, first term is parsed as required; without
+ // this modification a OR b would parsed as +a OR b
+ BooleanClause c = clauses.get(clauses.size()-1);
+ if (!c.isProhibited())
+ c.setOccur(BooleanClause.Occur.SHOULD);
+ }
+
+ // We might have been passed a null query; the term might have been
+ // filtered away by the analyzer.
+ if (q == null)
+ return;
+
+ if (operator == OR_OPERATOR) {
+ // We set REQUIRED if we're introduced by AND or +; PROHIBITED if
+ // introduced by NOT or -; make sure not to set both.
+ prohibited = (mods == MOD_NOT);
+ required = (mods == MOD_REQ);
+ if (conj == CONJ_AND && !prohibited) {
+ required = true;
+ }
+ } else {
+ // We set PROHIBITED if we're introduced by NOT or -; We set REQUIRED
+ // if not PROHIBITED and not introduced by OR
+ prohibited = (mods == MOD_NOT);
+ required = (!prohibited && conj != CONJ_OR);
+ }
+ if (required && !prohibited)
+ clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST));
+ else if (!required && !prohibited)
+ clauses.add(newBooleanClause(q, BooleanClause.Occur.SHOULD));
+ else if (!required && prohibited)
+ clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST_NOT));
+ else
+ throw new RuntimeException("Clause cannot be both required and prohibited");
+ }
+
+
+
+ protected Query newFieldQuery(Analyzer analyzer, String field, String queryText, boolean quoted) throws SyntaxError {
+ // Use the analyzer to get all the tokens, and then build a TermQuery,
+ // PhraseQuery, or nothing based on the term count
+
+ TokenStream source;
+ try {
+ source = analyzer.tokenStream(field, new StringReader(queryText));
+ source.reset();
+ } catch (IOException e) {
+ throw new SyntaxError("Unable to initialize TokenStream to analyze query text", e);
+ }
+ CachingTokenFilter buffer = new CachingTokenFilter(source);
+ TermToBytesRefAttribute termAtt = null;
+ PositionIncrementAttribute posIncrAtt = null;
+ int numTokens = 0;
+
+ buffer.reset();
+
+ if (buffer.hasAttribute(TermToBytesRefAttribute.class)) {
+ termAtt = buffer.getAttribute(TermToBytesRefAttribute.class);
+ }
+ if (buffer.hasAttribute(PositionIncrementAttribute.class)) {
+ posIncrAtt = buffer.getAttribute(PositionIncrementAttribute.class);
+ }
+
+ int positionCount = 0;
+ boolean severalTokensAtSamePosition = false;
+
+ boolean hasMoreTokens = false;
+ if (termAtt != null) {
+ try {
+ hasMoreTokens = buffer.incrementToken();
+ while (hasMoreTokens) {
+ numTokens++;
+ int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1;
+ if (positionIncrement != 0) {
+ positionCount += positionIncrement;
+ } else {
+ severalTokensAtSamePosition = true;
+ }
+ hasMoreTokens = buffer.incrementToken();
+ }
+ } catch (IOException e) {
+ // ignore
+ }
+ }
+ try {
+ // rewind the buffer stream
+ buffer.reset();
+
+ // close original stream - all tokens buffered
+ source.close();
+ }
+ catch (IOException e) {
+ throw new SyntaxError("Cannot close TokenStream analyzing query text", e);
+ }
+
+ BytesRef bytes = termAtt == null ? null : termAtt.getBytesRef();
+
+ if (numTokens == 0)
+ return null;
+ else if (numTokens == 1) {
+ try {
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ termAtt.fillBytesRef();
+ } catch (IOException e) {
+ // safe to ignore, because we know the number of tokens
+ }
+ return newTermQuery(new Term(field, BytesRef.deepCopyOf(bytes)));
+ } else {
+ if (severalTokensAtSamePosition || (!quoted && !autoGeneratePhraseQueries)) {
+ if (positionCount == 1 || (!quoted && !autoGeneratePhraseQueries)) {
+ // no phrase query:
+ BooleanQuery q = newBooleanQuery(positionCount == 1);
+
+ BooleanClause.Occur occur = positionCount > 1 && operator == AND_OPERATOR ?
+ BooleanClause.Occur.MUST : BooleanClause.Occur.SHOULD;
+
+ for (int i = 0; i < numTokens; i++) {
+ try {
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ termAtt.fillBytesRef();
+ } catch (IOException e) {
+ // safe to ignore, because we know the number of tokens
+ }
+ Query currentQuery = newTermQuery(
+ new Term(field, BytesRef.deepCopyOf(bytes)));
+ q.add(currentQuery, occur);
+ }
+ return q;
+ }
+ else {
+ // phrase query:
+ MultiPhraseQuery mpq = newMultiPhraseQuery();
+ mpq.setSlop(phraseSlop);
+ List<Term> multiTerms = new ArrayList<Term>();
+ int position = -1;
+ for (int i = 0; i < numTokens; i++) {
+ int positionIncrement = 1;
+ try {
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ termAtt.fillBytesRef();
+ if (posIncrAtt != null) {
+ positionIncrement = posIncrAtt.getPositionIncrement();
+ }
+ } catch (IOException e) {
+ // safe to ignore, because we know the number of tokens
+ }
+
+ if (positionIncrement > 0 && multiTerms.size() > 0) {
+ if (enablePositionIncrements) {
+ mpq.add(multiTerms.toArray(new Term[0]),position);
+ } else {
+ mpq.add(multiTerms.toArray(new Term[0]));
+ }
+ multiTerms.clear();
+ }
+ position += positionIncrement;
+ multiTerms.add(new Term(field, BytesRef.deepCopyOf(bytes)));
+ }
+ if (enablePositionIncrements) {
+ mpq.add(multiTerms.toArray(new Term[0]),position);
+ } else {
+ mpq.add(multiTerms.toArray(new Term[0]));
+ }
+ return mpq;
+ }
+ }
+ else {
+ PhraseQuery pq = newPhraseQuery();
+ pq.setSlop(phraseSlop);
+ int position = -1;
+
+ for (int i = 0; i < numTokens; i++) {
+ int positionIncrement = 1;
+
+ try {
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ termAtt.fillBytesRef();
+ if (posIncrAtt != null) {
+ positionIncrement = posIncrAtt.getPositionIncrement();
+ }
+ } catch (IOException e) {
+ // safe to ignore, because we know the number of tokens
+ }
+
+ if (enablePositionIncrements) {
+ position += positionIncrement;
+ pq.add(new Term(field, BytesRef.deepCopyOf(bytes)),position);
+ } else {
+ pq.add(new Term(field, BytesRef.deepCopyOf(bytes)));
+ }
+ }
+ return pq;
+ }
+ }
+ }
+
+
+
+ /**
+ * Base implementation delegates to {@link #getFieldQuery(String,String,boolean)}.
+ * This method may be overridden, for example, to return
+ * a SpanNearQuery instead of a PhraseQuery.
+ *
+ */
+ protected Query getFieldQuery(String field, String queryText, int slop)
+ throws SyntaxError {
+ Query query = getFieldQuery(field, queryText, true);
+
+ if (query instanceof PhraseQuery) {
+ ((PhraseQuery) query).setSlop(slop);
+ }
+ if (query instanceof MultiPhraseQuery) {
+ ((MultiPhraseQuery) query).setSlop(slop);
+ }
+
+ return query;
+ }
+
+
+ /**
+ * Builds a new BooleanQuery instance
+ * @param disableCoord disable coord
+ * @return new BooleanQuery instance
+ */
+ protected BooleanQuery newBooleanQuery(boolean disableCoord) {
+ return new BooleanQuery(disableCoord);
+ }
+
+ /**
+ * Builds a new BooleanClause instance
+ * @param q sub query
+ * @param occur how this clause should occur when matching documents
+ * @return new BooleanClause instance
+ */
+ protected BooleanClause newBooleanClause(Query q, BooleanClause.Occur occur) {
+ return new BooleanClause(q, occur);
+ }
+
+ /**
+ * Builds a new TermQuery instance
+ * @param term term
+ * @return new TermQuery instance
+ */
+ protected Query newTermQuery(Term term){
+ return new TermQuery(term);
+ }
+
+ /**
+ * Builds a new PhraseQuery instance
+ * @return new PhraseQuery instance
+ */
+ protected PhraseQuery newPhraseQuery(){
+ return new PhraseQuery();
+ }
+
+ /**
+ * Builds a new MultiPhraseQuery instance
+ * @return new MultiPhraseQuery instance
+ */
+ protected MultiPhraseQuery newMultiPhraseQuery(){
+ return new MultiPhraseQuery();
+ }
+
+ /**
+ * Builds a new PrefixQuery instance
+ * @param prefix Prefix term
+ * @return new PrefixQuery instance
+ */
+ protected Query newPrefixQuery(Term prefix){
+ PrefixQuery query = new PrefixQuery(prefix);
+ query.setRewriteMethod(multiTermRewriteMethod);
+ return query;
+ }
+
+ /**
+ * Builds a new RegexpQuery instance
+ * @param regexp Regexp term
+ * @return new RegexpQuery instance
+ */
+ protected Query newRegexpQuery(Term regexp) {
+ RegexpQuery query = new RegexpQuery(regexp);
+ query.setRewriteMethod(multiTermRewriteMethod);
+ return query;
+ }
+
+ /**
+ * Builds a new FuzzyQuery instance
+ * @param term Term
+ * @param minimumSimilarity minimum similarity
+ * @param prefixLength prefix length
+ * @return new FuzzyQuery Instance
+ */
+ protected Query newFuzzyQuery(Term term, float minimumSimilarity, int prefixLength) {
+ // FuzzyQuery doesn't yet allow constant score rewrite
+ String text = term.text();
+ int numEdits = FuzzyQuery.floatToEdits(minimumSimilarity,
+ text.codePointCount(0, text.length()));
+ return new FuzzyQuery(term,numEdits,prefixLength);
+ }
+
+ /**
+ * Builds a new MatchAllDocsQuery instance
+ * @return new MatchAllDocsQuery instance
+ */
+ protected Query newMatchAllDocsQuery() {
+ return new MatchAllDocsQuery();
+ }
+
+ /**
+ * Builds a new WildcardQuery instance
+ * @param t wildcard term
+ * @return new WildcardQuery instance
+ */
+ protected Query newWildcardQuery(Term t) {
+ WildcardQuery query = new WildcardQuery(t);
+ query.setRewriteMethod(multiTermRewriteMethod);
+ return query;
+ }
+
+ /**
+ * Factory method for generating query, given a set of clauses.
+ * By default creates a boolean query composed of clauses passed in.
+ *
+ * Can be overridden by extending classes, to modify query being
+ * returned.
+ *
+ * @param clauses List that contains {@link org.apache.lucene.search.BooleanClause} instances
+ * to join.
+ *
+ * @return Resulting {@link org.apache.lucene.search.Query} object.
+ */
+ protected Query getBooleanQuery(List<BooleanClause> clauses) throws SyntaxError {
+ return getBooleanQuery(clauses, false);
+ }
+
+ /**
+ * Factory method for generating query, given a set of clauses.
+ * By default creates a boolean query composed of clauses passed in.
+ *
+ * Can be overridden by extending classes, to modify query being
+ * returned.
+ *
+ * @param clauses List that contains {@link org.apache.lucene.search.BooleanClause} instances
+ * to join.
+ * @param disableCoord true if coord scoring should be disabled.
+ *
+ * @return Resulting {@link org.apache.lucene.search.Query} object.
+ */
+ protected Query getBooleanQuery(List<BooleanClause> clauses, boolean disableCoord)
+ throws SyntaxError
+ {
+ if (clauses.size()==0) {
+ return null; // all clause words were filtered away by the analyzer.
+ }
+ BooleanQuery query = newBooleanQuery(disableCoord);
+ for(final BooleanClause clause: clauses) {
+ query.add(clause);
+ }
+ return query;
+ }
+
+
+ // called from parser
+ Query handleBareTokenQuery(String qfield, Token term, Token fuzzySlop, boolean prefix, boolean wildcard, boolean fuzzy, boolean regexp) throws SyntaxError {
+ Query q;
+
+ String termImage=discardEscapeChar(term.image);
+ if (wildcard) {
+ q = getWildcardQuery(qfield, term.image);
+ } else if (prefix) {
+ q = getPrefixQuery(qfield,
+ discardEscapeChar(term.image.substring
+ (0, term.image.length()-1)));
+ } else if (regexp) {
+ q = getRegexpQuery(qfield, term.image.substring(1, term.image.length()-1));
+ } else if (fuzzy) {
+ float fms = fuzzyMinSim;
+ try {
+ fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue();
+ } catch (Exception ignored) { }
+ if(fms < 0.0f){
+ throw new SyntaxError("Minimum similarity for a FuzzyQuery has to be between 0.0f and 1.0f !");
+ } else if (fms >= 1.0f && fms != (int) fms) {
+ throw new SyntaxError("Fractional edit distances are not allowed!");
+ }
+ q = getFuzzyQuery(qfield, termImage, fms);
+ } else {
+ q = getFieldQuery(qfield, termImage, false);
+ }
+ return q;
+ }
+
+ // called from parser
+ Query handleQuotedTerm(String qfield, Token term, Token fuzzySlop) throws SyntaxError {
+ int s = phraseSlop; // default
+ if (fuzzySlop != null) {
+ try {
+ s = Float.valueOf(fuzzySlop.image.substring(1)).intValue();
+ }
+ catch (Exception ignored) { }
+ }
+ return getFieldQuery(qfield, discardEscapeChar(term.image.substring(1, term.image.length()-1)), s);
+ }
+
+ // called from parser
+ Query handleBoost(Query q, Token boost) {
+ if (boost != null) {
+ float boostVal = Float.parseFloat(boost.image);
+ // avoid boosting null queries, such as those caused by stop words
+ if (q != null) {
+ q.setBoost(boostVal);
+ }
+ }
+ return q;
+ }
+
+
+
+ /**
+ * Returns a String where the escape char has been
+ * removed, or kept only once if there was a double escape.
+ *
+ * Supports escaped unicode characters, e. g. translates
+ * <code>\\u0041</code> to <code>A</code>.
+ *
+ */
+ String discardEscapeChar(String input) throws SyntaxError {
+ // Create char array to hold unescaped char sequence
+ char[] output = new char[input.length()];
+
+ // The length of the output can be less than the input
+ // due to discarded escape chars. This variable holds
+ // the actual length of the output
+ int length = 0;
+
+ // We remember whether the last processed character was
+ // an escape character
+ boolean lastCharWasEscapeChar = false;
+
+ // The multiplier the current unicode digit must be multiplied with.
+ // E. g. the first digit must be multiplied with 16^3, the second with 16^2...
+ int codePointMultiplier = 0;
+
+ // Used to calculate the codepoint of the escaped unicode character
+ int codePoint = 0;
+
+ for (int i = 0; i < input.length(); i++) {
+ char curChar = input.charAt(i);
+ if (codePointMultiplier > 0) {
+ codePoint += hexToInt(curChar) * codePointMultiplier;
+ codePointMultiplier >>>= 4;
+ if (codePointMultiplier == 0) {
+ output[length++] = (char)codePoint;
+ codePoint = 0;
+ }
+ } else if (lastCharWasEscapeChar) {
+ if (curChar == 'u') {
+ // found an escaped unicode character
+ codePointMultiplier = 16 * 16 * 16;
+ } else {
+ // this character was escaped
+ output[length] = curChar;
+ length++;
+ }
+ lastCharWasEscapeChar = false;
+ } else {
+ if (curChar == '\\') {
+ lastCharWasEscapeChar = true;
+ } else {
+ output[length] = curChar;
+ length++;
+ }
+ }
+ }
+
+ if (codePointMultiplier > 0) {
+ throw new SyntaxError("Truncated unicode escape sequence.");
+ }
+
+ if (lastCharWasEscapeChar) {
+ throw new SyntaxError("Term can not end with escape character.");
+ }
+
+ return new String(output, 0, length);
+ }
+
+ /** Returns the numeric value of the hexadecimal character */
+ static final int hexToInt(char c) throws SyntaxError {
+ if ('0' <= c && c <= '9') {
+ return c - '0';
+ } else if ('a' <= c && c <= 'f'){
+ return c - 'a' + 10;
+ } else if ('A' <= c && c <= 'F') {
+ return c - 'A' + 10;
+ } else {
+ throw new SyntaxError("Non-hex character in Unicode escape sequence: " + c);
+ }
+ }
+
+ /**
+ * Returns a String where those characters that QueryParser
+ * expects to be escaped are escaped by a preceding <code>\</code>.
+ */
+ public static String escape(String s) {
+ StringBuilder sb = new StringBuilder();
+ for (int i = 0; i < s.length(); i++) {
+ char c = s.charAt(i);
+ // These characters are part of the query syntax and must be escaped
+ if (c == '\\' || c == '+' || c == '-' || c == '!' || c == '(' || c == ')' || c == ':'
+ || c == '^' || c == '[' || c == ']' || c == '\"' || c == '{' || c == '}' || c == '~'
+ || c == '*' || c == '?' || c == '|' || c == '&' || c == '/') {
+ sb.append('\\');
+ }
+ sb.append(c);
+ }
+ return sb.toString();
+ }
+
+
+ protected ReversedWildcardFilterFactory getReversedWildcardFilterFactory(FieldType fieldType) {
+ if (leadingWildcards == null) leadingWildcards = new HashMap<FieldType, ReversedWildcardFilterFactory>();
+ ReversedWildcardFilterFactory fac = leadingWildcards.get(fieldType);
+ if (fac != null || leadingWildcards.containsKey(fac)) {
+ return fac;
+ }
+
+ Analyzer a = fieldType.getAnalyzer();
+ if (a instanceof TokenizerChain) {
+ // examine the indexing analysis chain if it supports leading wildcards
+ TokenizerChain tc = (TokenizerChain)a;
+ TokenFilterFactory[] factories = tc.getTokenFilterFactories();
+ for (TokenFilterFactory factory : factories) {
+ if (factory instanceof ReversedWildcardFilterFactory) {
+ fac = (ReversedWildcardFilterFactory)factory;
+ break;
+ }
+ }
+ }
+
+ leadingWildcards.put(fieldType, fac);
+ return fac;
+ }
+
+
+ private void checkNullField(String field) throws SolrException {
+ if (field == null && defaultField == null) {
+ throw new SolrException
+ (SolrException.ErrorCode.BAD_REQUEST,
+ "no field name specified in query and no default specified via 'df' param");
+ }
+ }
+
+ protected String analyzeIfMultitermTermText(String field, String part, FieldType fieldType) {
+ if (part == null) return part;
+
+ SchemaField sf = schema.getFieldOrNull((field));
+ if (sf == null || ! (fieldType instanceof TextField)) return part;
+ String out = TextField.analyzeMultiTerm(field, part, ((TextField)fieldType).getMultiTermAnalyzer()).utf8ToString();
+ return out;
+ }
+
+
+ // called from parser
+ protected Query getFieldQuery(String field, String queryText, boolean quoted) throws SyntaxError {
+ checkNullField(field);
+ // intercept magic field name of "_" to use as a hook for our
+ // own functions.
+ if (field.charAt(0) == '_' && parser != null) {
+ MagicFieldName magic = MagicFieldName.get(field);
+ if (null != magic) {
+ QParser nested = parser.subQuery(queryText, magic.subParser);
+ return nested.getQuery();
+ }
+ }
+ SchemaField sf = schema.getFieldOrNull(field);
+ if (sf != null) {
+ FieldType ft = sf.getType();
+ // delegate to type for everything except tokenized fields
+ if (ft.isTokenized()) {
+ return newFieldQuery(analyzer, field, queryText, quoted || (ft instanceof TextField && ((TextField)ft).getAutoGeneratePhraseQueries()));
+ } else {
+ return sf.getType().getFieldQuery(parser, sf, queryText);
+ }
+ }
+
+ // default to a normal field query
+ return newFieldQuery(analyzer, field, queryText, quoted);
+ }
+
+
+ // called from parser
+ protected Query getRangeQuery(String field, String part1, String part2, boolean startInclusive, boolean endInclusive) throws SyntaxError {
+ checkNullField(field);
+ SchemaField sf = schema.getField(field);
+ return sf.getType().getRangeQuery(parser, sf, part1, part2, startInclusive, endInclusive);
+ }
+
+ // called from parser
+ protected Query getPrefixQuery(String field, String termStr) throws SyntaxError {
+ checkNullField(field);
+
+ termStr = analyzeIfMultitermTermText(field, termStr, schema.getFieldType(field));
+
+ // Solr has always used constant scoring for prefix queries. This should return constant scoring by default.
+ return newPrefixQuery(new Term(field, termStr));
+ }
+
+ // called from parser
+ protected Query getWildcardQuery(String field, String termStr) throws SyntaxError {
+ checkNullField(field);
+ // *:* -> MatchAllDocsQuery
+ if ("*".equals(field) && "*".equals(termStr)) {
+ return newMatchAllDocsQuery();
+ }
+ FieldType fieldType = schema.getFieldType(field);
+ termStr = analyzeIfMultitermTermText(field, termStr, fieldType);
+ // can we use reversed wildcards in this field?
+ ReversedWildcardFilterFactory factory = getReversedWildcardFilterFactory(fieldType);
+ if (factory != null) {
+ Term term = new Term(field, termStr);
+ // fsa representing the query
+ Automaton automaton = WildcardQuery.toAutomaton(term);
+ // TODO: we should likely use the automaton to calculate shouldReverse, too.
+ if (factory.shouldReverse(termStr)) {
+ automaton = BasicOperations.concatenate(automaton, BasicAutomata.makeChar(factory.getMarkerChar()));
+ SpecialOperations.reverse(automaton);
+ } else {
+ // reverse wildcardfilter is active: remove false positives
+ // fsa representing false positives (markerChar*)
+ Automaton falsePositives = BasicOperations.concatenate(
+ BasicAutomata.makeChar(factory.getMarkerChar()),
+ BasicAutomata.makeAnyString());
+ // subtract these away
+ automaton = BasicOperations.minus(automaton, falsePositives);
+ }
+ return new AutomatonQuery(term, automaton) {
+ // override toString so its completely transparent
+ @Override
+ public String toString(String field) {
+ StringBuilder buffer = new StringBuilder();
+ if (!getField().equals(field)) {
+ buffer.append(getField());
+ buffer.append(":");
+ }
+ buffer.append(term.text());
+ buffer.append(ToStringUtils.boost(getBoost()));
+ return buffer.toString();
+ }
+ };
+ }
+
+ // Solr has always used constant scoring for wildcard queries. This should return constant scoring by default.
+ return newWildcardQuery(new Term(field, termStr));
+ }
+
+ // called from parser
+ protected Query getRegexpQuery(String field, String termStr) throws SyntaxError
+ {
+ termStr = analyzeIfMultitermTermText(field, termStr, schema.getFieldType(field));
+ return newRegexpQuery(new Term(field, termStr));
+ }
+
+ // called from parser
+ protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws SyntaxError {
+ termStr = analyzeIfMultitermTermText(field, termStr, schema.getFieldType(field));
+ Term t = new Term(field, termStr);
+ return newFuzzyQuery(t, minSimilarity, getFuzzyPrefixLength());
+ }
+
+ // called from parser
+ protected Query getLocalParams(String qfield, String lparams) throws SyntaxError {
+ QParser nested = parser.subQuery(lparams, null);
+ return nested.getQuery();
+ }
+
+}
Added: lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/Token.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/Token.java?rev=1413042&view=auto
==============================================================================
--- lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/Token.java (added)
+++ lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/Token.java Fri Nov 23 19:45:50 2012
@@ -0,0 +1,131 @@
+/* Generated By:JavaCC: Do not edit this line. Token.java Version 5.0 */
+/* JavaCCOptions:TOKEN_EXTENDS=,KEEP_LINE_COL=null,SUPPORT_CLASS_VISIBILITY_PUBLIC=true */
+package org.apache.solr.parser;
+
+/**
+ * Describes the input token stream.
+ */
+
+public class Token implements java.io.Serializable {
+
+ /**
+ * The version identifier for this Serializable class.
+ * Increment only if the <i>serialized</i> form of the
+ * class changes.
+ */
+ private static final long serialVersionUID = 1L;
+
+ /**
+ * An integer that describes the kind of this token. This numbering
+ * system is determined by JavaCCParser, and a table of these numbers is
+ * stored in the file ...Constants.java.
+ */
+ public int kind;
+
+ /** The line number of the first character of this Token. */
+ public int beginLine;
+ /** The column number of the first character of this Token. */
+ public int beginColumn;
+ /** The line number of the last character of this Token. */
+ public int endLine;
+ /** The column number of the last character of this Token. */
+ public int endColumn;
+
+ /**
+ * The string image of the token.
+ */
+ public String image;
+
+ /**
+ * A reference to the next regular (non-special) token from the input
+ * stream. If this is the last token from the input stream, or if the
+ * token manager has not read tokens beyond this one, this field is
+ * set to null. This is true only if this token is also a regular
+ * token. Otherwise, see below for a description of the contents of
+ * this field.
+ */
+ public Token next;
+
+ /**
+ * This field is used to access special tokens that occur prior to this
+ * token, but after the immediately preceding regular (non-special) token.
+ * If there are no such special tokens, this field is set to null.
+ * When there are more than one such special token, this field refers
+ * to the last of these special tokens, which in turn refers to the next
+ * previous special token through its specialToken field, and so on
+ * until the first special token (whose specialToken field is null).
+ * The next fields of special tokens refer to other special tokens that
+ * immediately follow it (without an intervening regular token). If there
+ * is no such token, this field is null.
+ */
+ public Token specialToken;
+
+ /**
+ * An optional attribute value of the Token.
+ * Tokens which are not used as syntactic sugar will often contain
+ * meaningful values that will be used later on by the compiler or
+ * interpreter. This attribute value is often different from the image.
+ * Any subclass of Token that actually wants to return a non-null value can
+ * override this method as appropriate.
+ */
+ public Object getValue() {
+ return null;
+ }
+
+ /**
+ * No-argument constructor
+ */
+ public Token() {}
+
+ /**
+ * Constructs a new token for the specified Image.
+ */
+ public Token(int kind)
+ {
+ this(kind, null);
+ }
+
+ /**
+ * Constructs a new token for the specified Image and Kind.
+ */
+ public Token(int kind, String image)
+ {
+ this.kind = kind;
+ this.image = image;
+ }
+
+ /**
+ * Returns the image.
+ */
+ public String toString()
+ {
+ return image;
+ }
+
+ /**
+ * Returns a new Token object, by default. However, if you want, you
+ * can create and return subclass objects based on the value of ofKind.
+ * Simply add the cases to the switch for all those special cases.
+ * For example, if you have a subclass of Token called IDToken that
+ * you want to create if ofKind is ID, simply add something like :
+ *
+ * case MyParserConstants.ID : return new IDToken(ofKind, image);
+ *
+ * to the following switch statement. Then you can cast matchedToken
+ * variable to the appropriate type and use sit in your lexical actions.
+ */
+ public static Token newToken(int ofKind, String image)
+ {
+ switch(ofKind)
+ {
+ default : return new Token(ofKind, image);
+ }
+ }
+
+ public static Token newToken(int ofKind)
+ {
+ return newToken(ofKind, null);
+ }
+
+}
+/* JavaCC - OriginalChecksum=f463ad6fd3205ca07166de02ee86b907 (do not edit this line) */
Added: lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/TokenMgrError.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/TokenMgrError.java?rev=1413042&view=auto
==============================================================================
--- lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/TokenMgrError.java (added)
+++ lucene/dev/trunk/solr/core/src/java/org/apache/solr/parser/TokenMgrError.java Fri Nov 23 19:45:50 2012
@@ -0,0 +1,147 @@
+/* Generated By:JavaCC: Do not edit this line. TokenMgrError.java Version 5.0 */
+/* JavaCCOptions: */
+package org.apache.solr.parser;
+
+/** Token Manager Error. */
+public class TokenMgrError extends Error
+{
+
+ /**
+ * The version identifier for this Serializable class.
+ * Increment only if the <i>serialized</i> form of the
+ * class changes.
+ */
+ private static final long serialVersionUID = 1L;
+
+ /*
+ * Ordinals for various reasons why an Error of this type can be thrown.
+ */
+
+ /**
+ * Lexical error occurred.
+ */
+ static final int LEXICAL_ERROR = 0;
+
+ /**
+ * An attempt was made to create a second instance of a static token manager.
+ */
+ static final int STATIC_LEXER_ERROR = 1;
+
+ /**
+ * Tried to change to an invalid lexical state.
+ */
+ static final int INVALID_LEXICAL_STATE = 2;
+
+ /**
+ * Detected (and bailed out of) an infinite loop in the token manager.
+ */
+ static final int LOOP_DETECTED = 3;
+
+ /**
+ * Indicates the reason why the exception is thrown. It will have
+ * one of the above 4 values.
+ */
+ int errorCode;
+
+ /**
+ * Replaces unprintable characters by their escaped (or unicode escaped)
+ * equivalents in the given string
+ */
+ protected static final String addEscapes(String str) {
+ StringBuffer retval = new StringBuffer();
+ char ch;
+ for (int i = 0; i < str.length(); i++) {
+ switch (str.charAt(i))
+ {
+ case 0 :
+ continue;
+ case '\b':
+ retval.append("\\b");
+ continue;
+ case '\t':
+ retval.append("\\t");
+ continue;
+ case '\n':
+ retval.append("\\n");
+ continue;
+ case '\f':
+ retval.append("\\f");
+ continue;
+ case '\r':
+ retval.append("\\r");
+ continue;
+ case '\"':
+ retval.append("\\\"");
+ continue;
+ case '\'':
+ retval.append("\\\'");
+ continue;
+ case '\\':
+ retval.append("\\\\");
+ continue;
+ default:
+ if ((ch = str.charAt(i)) < 0x20 || ch > 0x7e) {
+ String s = "0000" + Integer.toString(ch, 16);
+ retval.append("\\u" + s.substring(s.length() - 4, s.length()));
+ } else {
+ retval.append(ch);
+ }
+ continue;
+ }
+ }
+ return retval.toString();
+ }
+
+ /**
+ * Returns a detailed message for the Error when it is thrown by the
+ * token manager to indicate a lexical error.
+ * Parameters :
+ * EOFSeen : indicates if EOF caused the lexical error
+ * curLexState : lexical state in which this error occurred
+ * errorLine : line number when the error occurred
+ * errorColumn : column number when the error occurred
+ * errorAfter : prefix that was seen before this error occurred
+ * curchar : the offending character
+ * Note: You can customize the lexical error message by modifying this method.
+ */
+ protected static String LexicalError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar) {
+ return("Lexical error at line " +
+ errorLine + ", column " +
+ errorColumn + ". Encountered: " +
+ (EOFSeen ? "<EOF> " : ("\"" + addEscapes(String.valueOf(curChar)) + "\"") + " (" + (int)curChar + "), ") +
+ "after : \"" + addEscapes(errorAfter) + "\"");
+ }
+
+ /**
+ * You can also modify the body of this method to customize your error messages.
+ * For example, cases like LOOP_DETECTED and INVALID_LEXICAL_STATE are not
+ * of end-users concern, so you can return something like :
+ *
+ * "Internal Error : Please file a bug report .... "
+ *
+ * from this method for such cases in the release version of your parser.
+ */
+ public String getMessage() {
+ return super.getMessage();
+ }
+
+ /*
+ * Constructors of various flavors follow.
+ */
+
+ /** No arg constructor. */
+ public TokenMgrError() {
+ }
+
+ /** Constructor with message and reason. */
+ public TokenMgrError(String message, int reason) {
+ super(message);
+ errorCode = reason;
+ }
+
+ /** Full Constructor. */
+ public TokenMgrError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar, int reason) {
+ this(LexicalError(EOFSeen, lexState, errorLine, errorColumn, errorAfter, curChar), reason);
+ }
+}
+/* JavaCC - OriginalChecksum=200a46f65c1a0f71a7f037b35f4e934e (do not edit this line) */