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

RegExp: fix redundant escape is not redundant (IDEA-208559)

Browse Source
This commit is contained in:
Bas Leijdekkers
2019-03-25 15:40:38 +01:00
parent 971ba07c24
commit dd10efd36d
3 changed files with 437 additions and 359 deletions
Download Patch File Download Diff File Expand all files Collapse all files
RegExpSupport/gen/org/intellij/lang/regexp/_RegExLexer.java
+379 -335
View File
File diff suppressed because it is too large Load Diff
RegExpSupport/src/org/intellij/lang/regexp/regexp-lexer.flex
+21 -9
View File
@@ -8,6 +8,7 @@ import com.intellij.psi.tree.IElementType;
import com.intellij.util.containers.IntArrayList;
import java.util.EnumSet;
import static java.lang.Boolean.*;
import static org.intellij.lang.regexp.RegExpCapability.*;
@SuppressWarnings("ALL")
@@ -49,8 +50,8 @@ import static org.intellij.lang.regexp.RegExpCapability.*;
_RegExLexer(EnumSet<RegExpCapability> capabilities) {
this((java.io.Reader)null);
this.xmlSchemaMode = capabilities.contains(XML_SCHEMA_MODE);
if (capabilities.contains(DANGLING_METACHARACTERS)) this.allowDanglingMetacharacters = Boolean.TRUE;
if (capabilities.contains(NO_DANGLING_METACHARACTERS)) this.allowDanglingMetacharacters = Boolean.FALSE;
if (capabilities.contains(DANGLING_METACHARACTERS)) this.allowDanglingMetacharacters = TRUE;
if (capabilities.contains(NO_DANGLING_METACHARACTERS)) this.allowDanglingMetacharacters = FALSE;
this.allowOmitNumbersInQuantifiers = capabilities.contains(OMIT_NUMBERS_IN_QUANTIFIERS);
this.allowOmitBothNumbersInQuantifiers = capabilities.contains(OMIT_BOTH_NUMBERS_IN_QUANTIFIERS);
this.allowNestedCharacterClasses = capabilities.contains(NESTED_CHARACTER_CLASSES);
@@ -104,6 +105,7 @@ import static org.intellij.lang.regexp.RegExpCapability.*;
%xstate QUOTED
%xstate EMBRACED
%xstate QUANTIFIER
%xstate NON_QUANTIFIER
%xstate NEGATED_CLASS
%xstate QUOTED_CLASS1
%xstate CLASS1
@@ -243,8 +245,8 @@ HEX_CHAR=[0-9a-fA-F]
{ESCAPE} {LBRACE} / "," [:digit:]+ {RBRACE} { return allowOmitNumbersInQuantifiers ? RegExpTT.ESC_CHARACTER : RegExpTT.REDUNDANT_ESCAPE; }
{ESCAPE} {LBRACE} / "," {RBRACE} { return allowOmitBothNumbersInQuantifiers ? RegExpTT.ESC_CHARACTER : RegExpTT.REDUNDANT_ESCAPE; }
{ESCAPE} {LBRACE} { return (allowDanglingMetacharacters != Boolean.TRUE) ? RegExpTT.ESC_CHARACTER : RegExpTT.REDUNDANT_ESCAPE; }
{ESCAPE} {RBRACE} { return (allowDanglingMetacharacters == Boolean.FALSE) ? RegExpTT.ESC_CHARACTER : RegExpTT.REDUNDANT_ESCAPE; }
{ESCAPE} {LBRACE} { return (allowDanglingMetacharacters != TRUE) ? RegExpTT.ESC_CHARACTER : RegExpTT.REDUNDANT_ESCAPE; }
{ESCAPE} {RBRACE} { return (allowDanglingMetacharacters == FALSE) ? RegExpTT.ESC_CHARACTER : RegExpTT.REDUNDANT_ESCAPE; }
{ESCAPE} {META2} { return RegExpTT.ESC_CHARACTER; }
}
{ESCAPE} {META1} { return RegExpTT.ESC_CHARACTER; }
@@ -287,9 +289,19 @@ HEX_CHAR=[0-9a-fA-F]
/* "}" outside counted quantifier is treated as regular character */
{LBRACE} / [:digit:]+ {RBRACE} { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; }
{LBRACE} / [:digit:]+ "," [:digit:]* {RBRACE} { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; }
{LBRACE} / "," [:digit:]+ {RBRACE} { if (allowOmitNumbersInQuantifiers || allowDanglingMetacharacters != Boolean.TRUE) { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; } else return RegExpTT.CHARACTER; }
{LBRACE} / "," {RBRACE} { if (allowOmitBothNumbersInQuantifiers || allowDanglingMetacharacters != Boolean.TRUE) { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; } else return RegExpTT.CHARACTER; }
{LBRACE} { if (allowDanglingMetacharacters != Boolean.TRUE) { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; } return RegExpTT.CHARACTER; }
{LBRACE} / "," [:digit:]+ {RBRACE} { if (allowOmitNumbersInQuantifiers || allowDanglingMetacharacters != TRUE) { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; } else return RegExpTT.CHARACTER; }
{LBRACE} / "," [:digit:]+ {ESCAPE} {RBRACE} { if (allowDanglingMetacharacters != TRUE) { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; } else if (allowOmitNumbersInQuantifiers) yypushstate(NON_QUANTIFIER); return RegExpTT.CHARACTER; }
{LBRACE} / "," {RBRACE} { if (allowOmitBothNumbersInQuantifiers || allowDanglingMetacharacters != TRUE) { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; } else return RegExpTT.CHARACTER; }
{LBRACE} / "," {ESCAPE} {RBRACE} { if (allowDanglingMetacharacters == TRUE) { if (allowOmitBothNumbersInQuantifiers) yypushstate(NON_QUANTIFIER); return RegExpTT.CHARACTER; } else { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; }}
{LBRACE} / {ESCAPE} {RBRACE} { return (allowDanglingMetacharacters != TRUE) ? RegExpTT.LBRACE : RegExpTT.CHARACTER; }
{LBRACE} / [:digit:]* ","? [:digit:]* {ESCAPE} {RBRACE} { if (allowDanglingMetacharacters != TRUE) { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; } else { yypushstate(NON_QUANTIFIER); return RegExpTT.CHARACTER; }}
{LBRACE} { if (allowDanglingMetacharacters != TRUE) { yypushstate(QUANTIFIER); return RegExpTT.LBRACE; } return RegExpTT.CHARACTER; }
}
<NON_QUANTIFIER> {
[:digit:] { return RegExpTT.CHARACTER; }
"," { return RegExpTT.CHARACTER; }
{ESCAPE} {RBRACE} { yypopstate(); return RegExpTT.ESC_CHARACTER; }
}
<QUANTIFIER> {
@@ -391,7 +403,7 @@ HEX_CHAR=[0-9a-fA-F]
<YYINITIAL> {
{LPAREN} { capturingGroupCount++; return RegExpTT.GROUP_BEGIN; }
{RPAREN} { return RegExpTT.GROUP_END; }
{RBRACE} { return (allowDanglingMetacharacters != Boolean.FALSE) ? RegExpTT.CHARACTER : RegExpTT.RBRACE; }
{RBRACE} { return (allowDanglingMetacharacters != FALSE) ? RegExpTT.CHARACTER : RegExpTT.RBRACE; }
"|" { return RegExpTT.UNION; }
"?" { return RegExpTT.QUEST; }
@@ -456,7 +468,7 @@ HEX_CHAR=[0-9a-fA-F]
"-" { return RegExpTT.CHARACTER; }
/* "dangling ]" */
<YYINITIAL> {RBRACKET} { return allowDanglingMetacharacters == Boolean.FALSE ? RegExpTT.CLASS_END : RegExpTT.CHARACTER; }
<YYINITIAL> {RBRACKET} { return allowDanglingMetacharacters == FALSE ? RegExpTT.CLASS_END : RegExpTT.CHARACTER; }
"#" { if (commentMode) { yypushstate(COMMENT); } else return RegExpTT.CHARACTER; }
RegExpSupport/test/org/intellij/lang/regexp/RegExpLexerTest.java
+37 -15
View File
@@ -1,18 +1,4 @@
/*
* Copyright 2000-2017 JetBrains s.r.o.
*
* Licensed 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.
*/
// Copyright 2000-2019 JetBrains s.r.o. Use of this source code is governed by the Apache 2.0 license that can be found in the LICENSE file.
package org.intellij.lang.regexp;
import com.intellij.lexer.Lexer;
@@ -490,6 +476,42 @@ public class RegExpLexerTest extends LexerTestCase {
final RegExpLexer lexer = new RegExpLexer(EnumSet.noneOf(RegExpCapability.class));
doTest("\\%\\ä", "REDUNDANT_ESCAPE ('\\%')\n" +
"REDUNDANT_ESCAPE ('\\ä')", lexer);
RegExpLexer lexer2 = new RegExpLexer(EnumSet.of(DANGLING_METACHARACTERS));
doTest("{\\}{33,34\\}{1\\}{1,\\}{,\\}{,2\\}", "CHARACTER ('{')\n" +
"REDUNDANT_ESCAPE ('\\}')\n" +
"CHARACTER ('{')\n" +
"CHARACTER ('3')\n" +
"CHARACTER ('3')\n" +
"CHARACTER (',')\n" +
"CHARACTER ('3')\n" +
"CHARACTER ('4')\n" +
"ESC_CHARACTER ('\\}')\n" +
"CHARACTER ('{')\n" +
"CHARACTER ('1')\n" +
"ESC_CHARACTER ('\\}')\n" +
"CHARACTER ('{')\n" +
"CHARACTER ('1')\n" +
"CHARACTER (',')\n" +
"ESC_CHARACTER ('\\}')\n" +
"CHARACTER ('{')\n" +
"CHARACTER (',')\n" +
"REDUNDANT_ESCAPE ('\\}')\n" +
"CHARACTER ('{')\n" +
"CHARACTER (',')\n" +
"CHARACTER ('2')\n" +
"REDUNDANT_ESCAPE ('\\}')", lexer2);
RegExpLexer lexer3 = new RegExpLexer(EnumSet.of(DANGLING_METACHARACTERS, OMIT_NUMBERS_IN_QUANTIFIERS, OMIT_BOTH_NUMBERS_IN_QUANTIFIERS));
doTest("{\\}{,\\}{,2\\}", "CHARACTER ('{')\n" +
"REDUNDANT_ESCAPE ('\\}')\n" +
"CHARACTER ('{')\n" +
"CHARACTER (',')\n" +
"ESC_CHARACTER ('\\}')\n" +
"CHARACTER ('{')\n" +
"CHARACTER (',')\n" +
"CHARACTER ('2')\n" +
"ESC_CHARACTER ('\\}')", lexer3);
}
public void testEscapesInsideCharClass() {