MDS/openide
1
0
Fork 0
mirror of https://gitflic.ru/project/openide/openide.git synced 2026-09-27 10:03:11 +07:00
Code Issues Packages Projects Releases Wiki Activity

fix parsing of character classes so that it's actually correct (PY-1929)

Browse Source
This commit is contained in:
Dmitry Jemerov
2011-02-21 19:09:48 +01:00
parent de3f634507
commit 4b57ede2e1
3 changed files with 382 additions and 378 deletions
Download Patch File Download Diff File Expand all files Collapse all files
RegExpSupport/src/org/intellij/lang/regexp/RegExpLexer.java
+2 -2
View File
@@ -21,9 +21,9 @@ public class RegExpLexer extends FlexAdapter {
private static final int COMMENT_MODE = 1 << 14;
public RegExpLexer(boolean xmlSchemaMode, boolean allowDanglingMetacharacters, boolean allowRBracketInCharacterClass,
public RegExpLexer(boolean xmlSchemaMode, boolean allowDanglingMetacharacters, boolean allowNestedCharacterClasses,
boolean allowOctalNoLeadingZero) {
super(new _RegExLexer(xmlSchemaMode, allowDanglingMetacharacters, allowRBracketInCharacterClass, allowOctalNoLeadingZero));
super(new _RegExLexer(xmlSchemaMode, allowDanglingMetacharacters, allowNestedCharacterClasses, allowOctalNoLeadingZero));
}
public void start(CharSequence buffer, int startOffset, int endOffset, int initialState) {
RegExpSupport/src/org/intellij/lang/regexp/_RegExLexer.java
+357 -347
View File
@@ -1,4 +1,4 @@
/* The following code was generated by JFlex 1.4.3 on 21.02.11 18:30 */
/* The following code was generated by JFlex 1.4.3 on 21.02.11 19:08 */
/* It's an automatically generated code. Do not modify it. */
package org.intellij.lang.regexp;
@@ -14,7 +14,7 @@ import com.intellij.psi.StringEscapesTokenTypes;
/**
* This class is a scanner generated by
* <a href="http://www.jflex.de/">JFlex</a> 1.4.3
* on 21.02.11 18:30 from the specification file
* on 21.02.11 19:08 from the specification file
* <tt>C:/JetBrains/IDEA/tools/lexer/../../community/RegExpSupport/src/org/intellij/lang/regexp/regexp-lexer.flex</tt>
*/
class _RegExLexer implements FlexLexer {
@@ -23,18 +23,17 @@ class _RegExLexer implements FlexLexer {
/** lexical states */
public static final int EMBRACED = 4;
public static final int PY_NAMED_GROUP_REF = 22;
public static final int PY_NAMED_GROUP_REF = 20;
public static final int QUOTED = 2;
public static final int CLASS2PY = 10;
public static final int OPTIONS = 14;
public static final int PY_COND_REF = 24;
public static final int OPTIONS = 12;
public static final int PY_COND_REF = 22;
public static final int YYINITIAL = 0;
public static final int NAMED_GROUP = 18;
public static final int NAMED_GROUP = 16;
public static final int CLASS2 = 8;
public static final int CLASS1 = 6;
public static final int COMMENT = 16;
public static final int QUOTED_NAMED_GROUP = 20;
public static final int PROP = 12;
public static final int COMMENT = 14;
public static final int QUOTED_NAMED_GROUP = 18;
public static final int PROP = 10;
/**
* ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l
@@ -44,7 +43,7 @@ class _RegExLexer implements FlexLexer {
*/
private static final int ZZ_LEXSTATE[] = {
0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
8, 8, 9, 9, 10, 10, 11, 11, 12, 12
8, 8, 9, 9, 10, 10, 11, 11
};
/**
@@ -130,21 +129,21 @@ class _RegExLexer implements FlexLexer {
private static final int [] ZZ_ACTION = zzUnpackAction();
private static final String ZZ_ACTION_PACKED_0 =
"\7\0\1\1\1\2\4\0\1\3\1\4\1\5\1\6"+
"\6\0\1\1\1\2\4\0\1\3\1\4\1\5\1\6"+
"\1\7\1\10\1\11\1\12\1\13\1\14\1\15\1\16"+
"\1\17\1\20\1\21\1\22\1\23\1\3\1\24\1\25"+
"\1\26\1\27\1\30\1\31\1\32\1\33\1\34\2\3"+
"\1\11\1\35\1\36\1\35\1\37\1\40\1\1\1\41"+
"\1\42\1\2\1\43\1\44\1\45\1\46\1\47\1\50"+
"\1\51\1\52\1\53\1\54\1\55\1\56\2\57\1\60"+
"\1\11\1\61\1\62\1\63\1\50\1\64\1\65\1\66"+
"\1\0\1\67\1\70\1\71\1\72\1\0\1\73\1\74"+
"\1\75\2\62\2\63\1\50\1\76\1\77\1\100\1\101"+
"\1\0\1\74\1\62\1\102\2\63\1\103\1\104\1\74"+
"\3\63\1\105";
"\1\26\1\27\1\30\1\31\1\32\1\33\1\34\1\11"+
"\1\35\1\3\1\36\1\37\1\36\1\40\1\41\1\1"+
"\1\42\1\43\1\2\1\44\1\45\1\46\1\47\1\50"+
"\1\51\1\52\1\53\1\54\1\55\1\56\1\57\2\60"+
"\1\61\1\11\1\62\1\63\1\64\1\51\1\65\1\66"+
"\1\67\1\70\1\71\1\0\1\72\1\73\1\74\1\75"+
"\1\0\1\76\1\77\1\100\2\63\2\64\1\51\1\101"+
"\1\102\1\103\1\104\1\0\1\77\1\63\1\105\2\64"+
"\1\106\1\107\1\77\3\64\1\110";
private static int [] zzUnpackAction() {
int [] result = new int[106];
int [] result = new int[107];
int offset = 0;
offset = zzUnpackAction(ZZ_ACTION_PACKED_0, offset, result);
return result;
@@ -170,22 +169,22 @@ class _RegExLexer implements FlexLexer {
private static final String ZZ_ROWMAP_PACKED_0 =
"\0\0\0\63\0\146\0\231\0\314\0\377\0\u0132\0\u0165"+
"\0\u0198\0\u01cb\0\u01fe\0\u0231\0\u0264\0\u0297\0\u0297\0\u02ca"+
"\0\u0297\0\u0297\0\u02fd\0\u0330\0\u0297\0\u0297\0\u0297\0\u0297"+
"\0\u0297\0\u0297\0\u0297\0\u0297\0\u0297\0\u0297\0\u0363\0\u0297"+
"\0\u0396\0\u0297\0\u03c9\0\u0297\0\u0297\0\u0297\0\u0297\0\u0297"+
"\0\u03fc\0\u02fd\0\u042f\0\u0297\0\u0297\0\u02fd\0\u0297\0\u0297"+
"\0\u0462\0\u0495\0\u0297\0\u0297\0\u0297\0\u0297\0\u04c8\0\u0297"+
"\0\u0297\0\u04fb\0\u052e\0\u0297\0\u0297\0\u0297\0\u0297\0\u0297"+
"\0\u0297\0\u0561\0\u0297\0\u0297\0\u0297\0\u0594\0\u05c7\0\u05fa"+
"\0\u0297\0\u0297\0\u0297\0\u062d\0\u0297\0\u0297\0\u0297\0\u0660"+
"\0\u0693\0\u0297\0\u06c6\0\u0297\0\u06f9\0\u072c\0\u075f\0\u0792"+
"\0\u07c5\0\u0297\0\u0297\0\u0297\0\u0297\0\u07f8\0\u082b\0\u0297"+
"\0\u0297\0\u085e\0\u0891\0\u04fb\0\u0297\0\u0297\0\u08c4\0\u08f7"+
"\0\u0297\0\u0297";
"\0\u0198\0\u01cb\0\u01fe\0\u0231\0\u0264\0\u0264\0\u0297\0\u0264"+
"\0\u0264\0\u02ca\0\u02fd\0\u0264\0\u0264\0\u0264\0\u0264\0\u0264"+
"\0\u0264\0\u0264\0\u0264\0\u0264\0\u0264\0\u0330\0\u0264\0\u0363"+
"\0\u0264\0\u0396\0\u0264\0\u0264\0\u0264\0\u03c9\0\u0264\0\u03fc"+
"\0\u0264\0\u042f\0\u0264\0\u0264\0\u02ca\0\u0264\0\u0264\0\u0462"+
"\0\u0495\0\u0264\0\u0264\0\u0264\0\u0264\0\u04c8\0\u0264\0\u0264"+
"\0\u04fb\0\u052e\0\u0264\0\u0264\0\u0264\0\u0264\0\u0264\0\u0264"+
"\0\u0561\0\u0264\0\u0264\0\u0264\0\u0594\0\u05c7\0\u05fa\0\u0264"+
"\0\u0264\0\u0264\0\u0264\0\u0264\0\u062d\0\u0264\0\u0264\0\u0264"+
"\0\u0660\0\u0693\0\u0264\0\u06c6\0\u0264\0\u06f9\0\u072c\0\u075f"+
"\0\u0792\0\u07c5\0\u0264\0\u0264\0\u0264\0\u0264\0\u07f8\0\u082b"+
"\0\u0264\0\u0264\0\u085e\0\u0891\0\u04fb\0\u0264\0\u0264\0\u08c4"+
"\0\u08f7\0\u0264\0\u0264";
private static int [] zzUnpackRowMap() {
int [] result = new int[106];
int [] result = new int[107];
int offset = 0;
offset = zzUnpackRowMap(ZZ_ROWMAP_PACKED_0, offset, result);
return result;
@@ -208,51 +207,49 @@ class _RegExLexer implements FlexLexer {
private static final int [] ZZ_TRANS = zzUnpackTrans();
private static final String ZZ_TRANS_PACKED_0 =
"\3\16\1\17\1\20\1\21\1\22\1\16\1\23\1\16"+
"\1\24\1\25\1\26\1\27\1\30\1\31\1\32\1\33"+
"\21\16\1\34\1\16\1\35\4\16\1\25\5\16\1\36"+
"\1\16\1\25\12\16\1\37\1\0\47\16\1\40\2\41"+
"\4\40\1\42\12\40\20\43\1\41\1\40\1\43\2\40"+
"\1\41\1\44\12\40\11\45\1\46\1\45\1\0\47\45"+
"\6\16\1\22\1\16\1\23\1\47\1\24\1\50\1\26"+
"\26\16\1\34\5\16\1\51\1\50\7\16\1\50\6\16"+
"\1\22\1\16\1\52\1\47\1\53\1\50\1\26\26\16"+
"\1\34\6\16\1\50\7\16\1\50\6\54\1\55\1\54"+
"\1\56\1\54\1\24\50\54\5\57\1\60\14\57\20\61"+
"\1\57\1\62\1\61\6\57\1\63\7\57\13\11\1\64"+
"\46\11\1\64\22\57\20\43\2\57\1\43\7\57\1\65"+
"\30\57\20\43\2\57\1\43\14\57\1\66\6\57\1\60"+
"\14\57\20\43\2\57\1\43\17\57\2\41\2\57\1\60"+
"\14\57\20\43\1\41\1\57\1\43\2\57\1\41\13\57"+
"\101\0\1\67\55\0\1\70\51\0\1\71\1\72\1\73"+
"\4\74\1\71\1\74\1\71\1\74\1\75\6\74\2\76"+
"\2\77\2\100\1\101\1\102\1\101\2\103\1\104\1\105"+
"\1\104\1\106\1\107\1\110\1\74\1\104\1\75\4\71"+
"\1\75\7\71\1\75\37\0\1\111\24\0\2\41\37\0"+
"\1\41\4\0\1\41\14\0\2\43\17\0\21\43\1\0"+
"\1\43\1\0\2\43\64\0\1\112\11\0\1\71\1\72"+
"\1\73\4\74\1\71\1\74\1\16\1\74\1\75\6\74"+
"\2\76\2\77\2\100\1\101\1\102\1\101\2\103\1\104"+
"\1\105\1\104\1\106\1\107\1\110\1\74\1\104\1\75"+
"\4\71\1\75\7\71\1\75\22\0\20\61\2\0\1\61"+
"\40\0\20\62\2\0\1\62\22\0\1\113\27\0\1\114"+
"\16\0\2\115\1\116\1\117\1\120\1\121\1\122\2\0"+
"\2\72\37\0\1\72\22\0\1\123\37\0\1\123\20\0"+
"\63\124\1\125\2\126\20\125\2\126\2\125\3\126\3\125"+
"\1\126\1\125\1\126\2\125\1\126\20\125\1\127\2\130"+
"\20\127\2\130\2\127\3\130\3\127\1\130\1\127\1\130"+
"\2\127\1\130\20\127\1\0\1\72\1\131\37\0\1\131"+
"\75\0\1\132\1\0\1\133\60\0\1\134\1\135\4\0"+
"\5\136\1\0\55\136\2\0\1\137\37\0\1\137\20\0"+
"\64\140\2\141\20\140\2\141\2\140\3\141\3\140\1\141"+
"\1\140\1\141\2\140\1\141\20\140\64\142\2\143\20\142"+
"\2\143\2\142\3\143\3\142\1\143\1\142\1\143\2\142"+
"\1\143\20\142\1\0\1\72\1\144\37\0\1\144\20\0"+
"\5\136\1\145\55\136\2\0\1\146\37\0\1\146\20\0"+
"\64\147\2\150\20\147\2\150\2\147\3\150\3\147\1\150"+
"\1\147\1\150\2\147\1\150\20\147\64\151\2\152\20\151"+
"\2\152\2\151\3\152\3\151\1\152\1\151\1\152\2\151"+
"\1\152\20\151";
"\3\15\1\16\1\17\1\20\1\21\1\15\1\22\1\15"+
"\1\23\1\24\1\25\1\26\1\27\1\30\1\31\1\32"+
"\21\15\1\33\1\15\1\34\4\15\1\24\5\15\1\35"+
"\1\15\1\24\12\15\1\36\1\0\47\15\1\37\2\40"+
"\4\37\1\41\12\37\20\42\1\40\1\37\1\42\2\37"+
"\1\40\1\43\12\37\11\44\1\45\1\44\1\0\47\44"+
"\6\15\1\21\1\15\1\46\1\47\1\50\1\51\1\25"+
"\26\15\1\33\5\15\1\52\1\51\7\15\1\51\6\53"+
"\1\54\1\53\1\55\1\53\1\23\50\53\5\56\1\57"+
"\14\56\20\60\1\56\1\61\1\60\6\56\1\62\7\56"+
"\13\10\1\63\46\10\1\63\22\56\20\42\2\56\1\42"+
"\7\56\1\64\30\56\20\42\2\56\1\42\14\56\1\65"+
"\6\56\1\57\14\56\20\42\2\56\1\42\17\56\2\40"+
"\2\56\1\57\14\56\20\42\1\40\1\56\1\42\2\56"+
"\1\40\13\56\101\0\1\66\55\0\1\67\51\0\1\70"+
"\1\71\1\72\4\73\1\70\1\73\1\70\1\73\1\74"+
"\6\73\2\75\2\76\2\77\1\100\1\101\1\100\2\102"+
"\1\103\1\104\1\103\1\105\1\106\1\107\1\73\1\103"+
"\1\74\4\70\1\74\7\70\1\74\37\0\1\110\24\0"+
"\2\40\37\0\1\40\4\0\1\40\14\0\2\42\17\0"+
"\21\42\1\0\1\42\1\0\2\42\24\0\1\111\51\0"+
"\1\70\1\71\1\72\4\73\1\70\1\73\1\112\1\73"+
"\1\74\6\73\2\75\2\76\2\77\1\100\1\101\1\100"+
"\2\102\1\103\1\104\1\103\1\105\1\106\1\107\1\73"+
"\1\103\1\74\4\70\1\74\7\70\1\74\51\0\1\113"+
"\33\0\20\60\2\0\1\60\40\0\20\61\2\0\1\61"+
"\22\0\1\114\27\0\1\115\16\0\2\116\1\117\1\120"+
"\1\121\1\122\1\123\2\0\2\71\37\0\1\71\22\0"+
"\1\124\37\0\1\124\20\0\63\125\1\126\2\127\20\126"+
"\2\127\2\126\3\127\3\126\1\127\1\126\1\127\2\126"+
"\1\127\20\126\1\130\2\131\20\130\2\131\2\130\3\131"+
"\3\130\1\131\1\130\1\131\2\130\1\131\20\130\1\0"+
"\1\71\1\132\37\0\1\132\75\0\1\133\1\0\1\134"+
"\60\0\1\135\1\136\4\0\5\137\1\0\55\137\2\0"+
"\1\140\37\0\1\140\20\0\64\141\2\142\20\141\2\142"+
"\2\141\3\142\3\141\1\142\1\141\1\142\2\141\1\142"+
"\20\141\64\143\2\144\20\143\2\144\2\143\3\144\3\143"+
"\1\144\1\143\1\144\2\143\1\144\20\143\1\0\1\71"+
"\1\145\37\0\1\145\20\0\5\137\1\146\55\137\2\0"+
"\1\147\37\0\1\147\20\0\64\150\2\151\20\150\2\151"+
"\2\150\3\151\3\150\1\151\1\150\1\151\2\150\1\151"+
"\20\150\64\152\2\153\20\152\2\153\2\152\3\153\3\152"+
"\1\153\1\152\1\153\2\152\1\153\20\152";
private static int [] zzUnpackTrans() {
int [] result = new int[2346];
@@ -296,15 +293,15 @@ class _RegExLexer implements FlexLexer {
private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
private static final String ZZ_ATTRIBUTE_PACKED_0 =
"\7\0\2\1\4\0\2\11\1\1\2\11\2\1\12\11"+
"\1\1\1\11\1\1\1\11\1\1\5\11\3\1\2\11"+
"\1\1\2\11\2\1\4\11\1\1\2\11\2\1\6\11"+
"\1\1\3\11\3\1\3\11\1\0\3\11\1\1\1\0"+
"\1\11\1\1\1\11\5\1\4\11\1\0\1\1\2\11"+
"\3\1\2\11\2\1\2\11";
"\6\0\2\1\4\0\2\11\1\1\2\11\2\1\12\11"+
"\1\1\1\11\1\1\1\11\1\1\3\11\1\1\1\11"+
"\1\1\1\11\1\1\2\11\1\1\2\11\2\1\4\11"+
"\1\1\2\11\2\1\6\11\1\1\3\11\3\1\5\11"+
"\1\0\3\11\1\1\1\0\1\11\1\1\1\11\5\1"+
"\4\11\1\0\1\1\2\11\3\1\2\11\2\1\2\11";
private static int [] zzUnpackAttribute() {
int [] result = new int[106];
int [] result = new int[107];
int offset = 0;
offset = zzUnpackAttribute(ZZ_ATTRIBUTE_PACKED_0, offset, result);
return result;
@@ -371,14 +368,14 @@ class _RegExLexer implements FlexLexer {
private boolean xmlSchemaMode;
private boolean allowDanglingMetacharacters;
private boolean allowRBracketInCharacterClass;
private boolean allowNestedCharacterClasses;
private boolean allowOctalNoLeadingZero;
_RegExLexer(boolean xmlSchemaMode, boolean allowDanglingMetacharacters, boolean allowRBracketInCharacterClass, boolean allowOctalNoLeadingZero) {
_RegExLexer(boolean xmlSchemaMode, boolean allowDanglingMetacharacters, boolean allowNestedCharacterClasses, boolean allowOctalNoLeadingZero) {
this((java.io.Reader)null);
this.xmlSchemaMode = xmlSchemaMode;
this.allowDanglingMetacharacters = allowDanglingMetacharacters;
this.allowRBracketInCharacterClass = allowRBracketInCharacterClass;
this.allowNestedCharacterClasses = allowNestedCharacterClasses;
this.allowOctalNoLeadingZero = allowOctalNoLeadingZero;
}
@@ -649,269 +646,207 @@ class _RegExLexer implements FlexLexer {
zzMarkedPos = zzMarkedPosL;
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
case 72:
{ return RegExpTT.UNICODE_CHAR;
}
case 73: break;
case 7:
{ if (yystate() != CLASS2) yypushstate(EMBRACED); return RegExpTT.LBRACE;
}
case 70: break;
case 6:
{ return RegExpTT.GROUP_END;
}
case 71: break;
case 14:
{ return RegExpTT.STAR;
}
case 72: break;
case 42:
{ return RegExpTT.ESC_CHARACTER;
}
case 73: break;
case 38:
// lookahead expression with fixed base length
zzMarkedPos = zzStartRead + 1;
{ if (allowRBracketInCharacterClass) {
yypushstate(CLASS1);
}
else {
yypushstate(CLASS2PY);
}
return RegExpTT.CLASS_BEGIN;
}
case 74: break;
case 28:
{ return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.ESC_CHARACTER;
}
case 75: break;
case 43:
{ return commentMode ? RegExpTT.CHARACTER : RegExpTT.REDUNDANT_ESCAPE;
}
case 76: break;
case 8:
{ if (allowRBracketInCharacterClass) {
yypushstate(CLASS2);
}
else {
yypushstate(CLASS2PY);
}
return RegExpTT.CLASS_BEGIN;
}
case 77: break;
case 39:
{ return RegExpTT.REDUNDANT_ESCAPE;
}
case 78: break;
case 24:
{ return RegExpTT.COMMA;
}
case 79: break;
case 58:
{ yybegin(NAMED_GROUP); return RegExpTT.RUBY_NAMED_GROUP;
}
case 80: break;
case 64:
{ return RegExpTT.POS_LOOKBEHIND;
}
case 81: break;
case 41:
{ return RegExpTT.BAD_OCT_VALUE;
}
case 82: break;
case 10:
{ return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.CTRL_CHARACTER;
}
case 83: break;
case 30:
{ yypopstate(); yypushstate(EMBRACED); return RegExpTT.LBRACE;
}
case 84: break;
case 51:
{ return StringEscapesTokenTypes.INVALID_UNICODE_ESCAPE_TOKEN;
}
case 85: break;
case 65:
{ return RegExpTT.NEG_LOOKBEHIND;
}
case 86: break;
case 69:
{ return RegExpTT.UNICODE_CHAR;
}
case 87: break;
case 61:
{ if (xmlSchemaMode) { yypushback(1); return RegExpTT.CHAR_CLASS; } else return RegExpTT.CTRL;
}
case 88: break;
case 37:
{ yybegin(OPTIONS); return RegExpTT.SET_OPTIONS;
}
case 89: break;
case 12:
{ return RegExpTT.DOLLAR;
}
case 90: break;
case 52:
{ yypopstate(); return RegExpTT.QUOTE_END;
}
case 91: break;
case 56:
case 75: break;
case 59:
{ return RegExpTT.POS_LOOKAHEAD;
}
case 92: break;
case 22:
{ yypopstate(); return RegExpTT.RBRACE;
}
case 93: break;
case 3:
{ return RegExpTT.CHARACTER;
}
case 94: break;
case 57:
{ return RegExpTT.NEG_LOOKAHEAD;
}
case 95: break;
case 67:
{ if (allowOctalNoLeadingZero) return RegExpTT.OCT_CHAR;
return yystate() != CLASS2 ? RegExpTT.BACKREF : RegExpTT.ESC_CHARACTER;
}
case 96: break;
case 44:
{ return RegExpTT.ESC_CTRL_CHARACTER;
}
case 97: break;
case 23:
{ return RegExpTT.NAME;
}
case 98: break;
case 53:
{ return RegExpTT.ANDAND;
}
case 99: break;
case 13:
{ return RegExpTT.QUEST;
}
case 100: break;
case 46:
{ return RegExpTT.CHAR_CLASS;
}
case 101: break;
case 17:
{ return RegExpTT.MINUS;
}
case 102: break;
case 68:
{ return RegExpTT.COMMENT;
}
case 103: break;
case 40:
{ return yystate() != CLASS2 ? RegExpTT.BACKREF : RegExpTT.ESC_CHARACTER;
}
case 104: break;
case 16:
{ return RegExpTT.UNION;
}
case 105: break;
case 47:
{ if (xmlSchemaMode) return RegExpTT.CHAR_CLASS; else return StringEscapesTokenTypes.INVALID_CHARACTER_ESCAPE_TOKEN;
}
case 106: break;
case 60:
{ return RegExpTT.OCT_CHAR;
}
case 107: break;
case 4:
{ return RegExpTT.DOT;
}
case 108: break;
case 32:
{ yybegin(YYINITIAL); return RegExpTT.GROUP_END;
}
case 109: break;
case 21:
{ return RegExpTT.NUMBER;
}
case 110: break;
case 35:
{ yybegin(YYINITIAL); return RegExpTT.GT;
}
case 111: break;
case 59:
{ yybegin(QUOTED_NAMED_GROUP); return RegExpTT.RUBY_QUOTED_NAMED_GROUP;
}
case 112: break;
case 54:
{ yybegin(PY_COND_REF); return RegExpTT.PYTHON_COND_REF;
}
case 113: break;
case 48:
{ yypushstate(PROP); return RegExpTT.PROPERTY;
}
case 114: break;
case 18:
{ return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.CHARACTER;
}
case 115: break;
case 33:
{ handleOptions(); return RegExpTT.OPTIONS_OFF;
}
case 116: break;
case 34:
{ yybegin(YYINITIAL); return RegExpTT.COLON;
}
case 117: break;
case 25:
{ assert false : yytext();
}
case 118: break;
case 62:
{ yybegin(PY_NAMED_GROUP_REF); return RegExpTT.PYTHON_NAMED_GROUP_REF;
}
case 119: break;
case 27:
{ yypopstate(); return RegExpTT.CLASS_END;
}
case 120: break;
case 11:
{ return RegExpTT.CARET;
}
case 121: break;
case 1:
{ handleOptions(); return RegExpTT.OPTIONS_ON;
}
case 122: break;
case 29:
{ yypopstate(); yypushback(1);
}
case 123: break;
case 45:
{ return yystate() != CLASS2 ? RegExpTT.BOUNDARY : RegExpTT.ESC_CHARACTER;
}
case 124: break;
case 63:
case 76: break;
case 66:
{ yybegin(NAMED_GROUP); return RegExpTT.PYTHON_NAMED_GROUP;
}
case 125: break;
case 19:
{ if (commentMode) { yypushstate(COMMENT); return RegExpTT.COMMENT; } else return RegExpTT.CHARACTER;
case 77: break;
case 71:
{ return RegExpTT.COMMENT;
}
case 126: break;
case 66:
{ return RegExpTT.HEX_CHAR;
case 78: break;
case 14:
{ return RegExpTT.STAR;
}
case 127: break;
case 79: break;
case 57:
{ yybegin(PY_COND_REF); return RegExpTT.PYTHON_COND_REF;
}
case 80: break;
case 47:
{ return RegExpTT.CHAR_CLASS;
}
case 81: break;
case 34:
{ handleOptions(); return RegExpTT.OPTIONS_OFF;
}
case 82: break;
case 53:
{ yypopstate(); return RegExpTT.QUOTE_END;
}
case 83: break;
case 33:
{ yybegin(YYINITIAL); return RegExpTT.GROUP_END;
}
case 84: break;
case 5:
{ return RegExpTT.GROUP_BEGIN;
}
case 128: break;
case 55:
case 85: break;
case 35:
{ yybegin(YYINITIAL); return RegExpTT.COLON;
}
case 86: break;
case 6:
{ return RegExpTT.GROUP_END;
}
case 87: break;
case 25:
{ assert false : yytext();
}
case 88: break;
case 18:
{ return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.CHARACTER;
}
case 89: break;
case 44:
{ return commentMode ? RegExpTT.CHARACTER : RegExpTT.REDUNDANT_ESCAPE;
}
case 90: break;
case 23:
{ return RegExpTT.NAME;
}
case 91: break;
case 70:
{ if (allowOctalNoLeadingZero) return RegExpTT.OCT_CHAR;
return yystate() != CLASS2 ? RegExpTT.BACKREF : RegExpTT.ESC_CHARACTER;
}
case 92: break;
case 28:
{ yypopstate(); return RegExpTT.CLASS_END;
}
case 93: break;
case 32:
{ yybegin(YYINITIAL); return RegExpTT.BAD_CHARACTER;
}
case 94: break;
case 50:
{ yypushstate(QUOTED); return RegExpTT.QUOTE_BEGIN;
}
case 95: break;
case 21:
{ return RegExpTT.NUMBER;
}
case 96: break;
case 4:
{ return RegExpTT.DOT;
}
case 97: break;
case 68:
{ return RegExpTT.NEG_LOOKBEHIND;
}
case 98: break;
case 39:
// lookahead expression with fixed base length
zzMarkedPos = zzStartRead + 1;
{ yypushstate(CLASS1);
return RegExpTT.CLASS_BEGIN;
}
case 99: break;
case 60:
{ return RegExpTT.NEG_LOOKAHEAD;
}
case 100: break;
case 10:
{ return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.CTRL_CHARACTER;
}
case 101: break;
case 58:
{ return RegExpTT.NON_CAPT_GROUP;
}
case 129: break;
case 9:
{ return StringEscapesTokenTypes.INVALID_CHARACTER_ESCAPE_TOKEN;
case 102: break;
case 62:
{ yybegin(QUOTED_NAMED_GROUP); return RegExpTT.RUBY_QUOTED_NAMED_GROUP;
}
case 130: break;
case 36:
case 103: break;
case 27:
{ if (allowNestedCharacterClasses) {
yypushstate(CLASS2);
return RegExpTT.CLASS_BEGIN;
}
return RegExpTT.CHARACTER;
}
case 104: break;
case 19:
{ if (commentMode) { yypushstate(COMMENT); return RegExpTT.COMMENT; } else return RegExpTT.CHARACTER;
}
case 105: break;
case 49:
{ yypushstate(PROP); return RegExpTT.PROPERTY;
}
case 106: break;
case 8:
{ yypushstate(CLASS2);
return RegExpTT.CLASS_BEGIN;
}
case 107: break;
case 67:
{ return RegExpTT.POS_LOOKBEHIND;
}
case 108: break;
case 41:
{ return yystate() != CLASS2 ? RegExpTT.BACKREF : RegExpTT.ESC_CHARACTER;
}
case 109: break;
case 69:
{ return RegExpTT.HEX_CHAR;
}
case 110: break;
case 1:
{ handleOptions(); return RegExpTT.OPTIONS_ON;
}
case 111: break;
case 56:
{ return allowNestedCharacterClasses ? RegExpTT.ANDAND : RegExpTT.CHARACTER;
}
case 112: break;
case 2:
{ yypopstate(); return RegExpTT.COMMENT;
}
case 113: break;
case 17:
{ return RegExpTT.MINUS;
}
case 114: break;
case 45:
{ return RegExpTT.ESC_CTRL_CHARACTER;
}
case 115: break;
case 31:
{ yypopstate(); yypushstate(EMBRACED); return RegExpTT.LBRACE;
}
case 116: break;
case 13:
{ return RegExpTT.QUEST;
}
case 117: break;
case 15:
{ return RegExpTT.PLUS;
}
case 118: break;
case 63:
{ return RegExpTT.OCT_CHAR;
}
case 119: break;
case 37:
{ yybegin(YYINITIAL); return RegExpTT.QUOTE;
}
case 131: break;
case 120: break;
case 20:
{ if (allowDanglingMetacharacters) {
yypopstate(); yypushback(1);
@@ -919,31 +854,106 @@ class _RegExLexer implements FlexLexer {
return RegExpTT.BAD_CHARACTER;
}
}
case 132: break;
case 50:
{ return RegExpTT.BAD_HEX_VALUE;
case 121: break;
case 30:
{ yypopstate(); yypushback(1);
}
case 133: break;
case 2:
{ yypopstate(); return RegExpTT.COMMENT;
case 122: break;
case 54:
// lookahead expression with fixed base length
zzMarkedPos = zzStartRead + 1;
{ if (allowNestedCharacterClasses) {
yypushstate(CLASS1);
return RegExpTT.CLASS_BEGIN;
}
return RegExpTT.CHARACTER;
}
case 134: break;
case 49:
{ yypushstate(QUOTED); return RegExpTT.QUOTE_BEGIN;
case 123: break;
case 55:
{ if (!allowNestedCharacterClasses) return RegExpTT.CHARACTER;
return RegExpTT.REDUNDANT_ESCAPE;
}
case 135: break;
case 124: break;
case 36:
{ yybegin(YYINITIAL); return RegExpTT.GT;
}
case 125: break;
case 65:
{ yybegin(PY_NAMED_GROUP_REF); return RegExpTT.PYTHON_NAMED_GROUP_REF;
}
case 126: break;
case 16:
{ return RegExpTT.UNION;
}
case 127: break;
case 3:
{ return RegExpTT.CHARACTER;
}
case 128: break;
case 61:
{ yybegin(NAMED_GROUP); return RegExpTT.RUBY_NAMED_GROUP;
}
case 129: break;
case 38:
{ yybegin(OPTIONS); return RegExpTT.SET_OPTIONS;
}
case 130: break;
case 26:
{ yybegin(CLASS2); return RegExpTT.CHARACTER;
}
case 131: break;
case 64:
{ if (xmlSchemaMode) { yypushback(1); return RegExpTT.CHAR_CLASS; } else return RegExpTT.CTRL;
}
case 132: break;
case 29:
{ return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.ESC_CHARACTER;
}
case 133: break;
case 12:
{ return RegExpTT.DOLLAR;
}
case 134: break;
case 48:
{ if (xmlSchemaMode) return RegExpTT.CHAR_CLASS; else return StringEscapesTokenTypes.INVALID_CHARACTER_ESCAPE_TOKEN;
}
case 135: break;
case 40:
{ return RegExpTT.REDUNDANT_ESCAPE;
}
case 136: break;
case 15:
{ return RegExpTT.PLUS;
case 46:
{ return yystate() != CLASS2 ? RegExpTT.BOUNDARY : RegExpTT.ESC_CHARACTER;
}
case 137: break;
case 31:
{ yybegin(YYINITIAL); return RegExpTT.BAD_CHARACTER;
case 22:
{ yypopstate(); return RegExpTT.RBRACE;
}
case 138: break;
case 52:
{ return StringEscapesTokenTypes.INVALID_UNICODE_ESCAPE_TOKEN;
}
case 139: break;
case 42:
{ return RegExpTT.BAD_OCT_VALUE;
}
case 140: break;
case 51:
{ return RegExpTT.BAD_HEX_VALUE;
}
case 141: break;
case 9:
{ return StringEscapesTokenTypes.INVALID_CHARACTER_ESCAPE_TOKEN;
}
case 142: break;
case 11:
{ return RegExpTT.CARET;
}
case 143: break;
case 43:
{ return RegExpTT.ESC_CHARACTER;
}
case 144: break;
default:
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
RegExpSupport/src/org/intellij/lang/regexp/regexp-lexer.flex
+23 -29
View File
@@ -27,14 +27,14 @@ import com.intellij.psi.StringEscapesTokenTypes;
private boolean xmlSchemaMode;
private boolean allowDanglingMetacharacters;
private boolean allowRBracketInCharacterClass;
private boolean allowNestedCharacterClasses;
private boolean allowOctalNoLeadingZero;
_RegExLexer(boolean xmlSchemaMode, boolean allowDanglingMetacharacters, boolean allowRBracketInCharacterClass, boolean allowOctalNoLeadingZero) {
_RegExLexer(boolean xmlSchemaMode, boolean allowDanglingMetacharacters, boolean allowNestedCharacterClasses, boolean allowOctalNoLeadingZero) {
this((java.io.Reader)null);
this.xmlSchemaMode = xmlSchemaMode;
this.allowDanglingMetacharacters = allowDanglingMetacharacters;
this.allowRBracketInCharacterClass = allowRBracketInCharacterClass;
this.allowNestedCharacterClasses = allowNestedCharacterClasses;
this.allowOctalNoLeadingZero = allowOctalNoLeadingZero;
}
@@ -63,7 +63,6 @@ import com.intellij.psi.StringEscapesTokenTypes;
%xstate EMBRACED
%xstate CLASS1
%state CLASS2
%state CLASS2PY
%state PROP
%xstate OPTIONS
%xstate COMMENT
@@ -155,8 +154,9 @@ HEX_CHAR=[0-9a-fA-F]
{ESCAPE} [:letter:] { return StringEscapesTokenTypes.INVALID_CHARACTER_ESCAPE_TOKEN; }
{ESCAPE} [\n\b\t\r\f ] { return commentMode ? RegExpTT.CHARACTER : RegExpTT.REDUNDANT_ESCAPE; }
<CLASS2PY> {
{ESCAPE} {RBRACKET} { return RegExpTT.CHARACTER; }
<CLASS2> {
{ESCAPE} {RBRACKET} { if (!allowNestedCharacterClasses) return RegExpTT.CHARACTER;
return RegExpTT.REDUNDANT_ESCAPE; }
}
{ESCAPE} {ANY} { return RegExpTT.REDUNDANT_ESCAPE; }
@@ -190,24 +190,26 @@ HEX_CHAR=[0-9a-fA-F]
"-" { return RegExpTT.MINUS; }
"^" { return RegExpTT.CARET; }
<CLASS2PY> {
{LBRACKET} { return RegExpTT.CHARACTER; }
<CLASS2> {
{LBRACKET} { if (allowNestedCharacterClasses) {
yypushstate(CLASS2);
return RegExpTT.CLASS_BEGIN;
}
return RegExpTT.CHARACTER;
}
{LBRACKET} / {RBRACKET} { if (allowNestedCharacterClasses) {
yypushstate(CLASS1);
return RegExpTT.CLASS_BEGIN;
}
return RegExpTT.CHARACTER;
}
}
{LBRACKET} / {RBRACKET} { if (allowRBracketInCharacterClass) {
yypushstate(CLASS1);
}
else {
yypushstate(CLASS2PY);
}
{LBRACKET} / {RBRACKET} { yypushstate(CLASS1);
return RegExpTT.CLASS_BEGIN; }
{LBRACKET} { if (allowRBracketInCharacterClass) {
yypushstate(CLASS2);
}
else {
yypushstate(CLASS2PY);
}
{LBRACKET} { yypushstate(CLASS2);
return RegExpTT.CLASS_BEGIN; }
/* []abc] is legal. The first ] is treated as literal character */
@@ -219,15 +221,7 @@ HEX_CHAR=[0-9a-fA-F]
<CLASS2> {
{RBRACKET} { yypopstate(); return RegExpTT.CLASS_END; }
"&&" { return RegExpTT.ANDAND; }
[\n\b\t\r\f] { return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.ESC_CHARACTER; }
{ANY} { return RegExpTT.CHARACTER; }
}
/* see rules for matching LBRACKET and escaped RBRACKET in CLASS2PY above */
<CLASS2PY> {
{RBRACKET} { yypopstate(); return RegExpTT.CLASS_END; }
"&&" { return allowNestedCharacterClasses ? RegExpTT.ANDAND : RegExpTT.CHARACTER; }
[\n\b\t\r\f] { return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.ESC_CHARACTER; }
{ANY} { return RegExpTT.CHARACTER; }
}