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

support Perl style comments in Ruby regular expressions (RUBY-4221)

Browse Source
This commit is contained in:
Dmitry Jemerov
2009-09-23 18:26:42 +04:00
parent 749515ec89
commit 5e8e93c6d1
4 changed files with 128 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files
RegExpSupport/src/org/intellij/lang/regexp/RegExpLanguageHost.java
+1
View File
@@ -5,4 +5,5 @@ package org.intellij.lang.regexp;
*/
public interface RegExpLanguageHost {
boolean characterNeedsEscaping(char c);
boolean supportsPerl5EmbeddedComments();
}
RegExpSupport/src/org/intellij/lang/regexp/_RegExLexer.java
+102 -89
View File
@@ -1,4 +1,4 @@
/* The following code was generated by JFlex 1.4.1 on 13.03.09 16:25 */
/* The following code was generated by JFlex 1.4.1 on 23.09.09 18:11 */
/* It's an automatically generated code. Do not modify it. */
package org.intellij.lang.regexp;
@@ -14,8 +14,8 @@ import com.intellij.psi.StringEscapesTokenTypes;
/**
* This class is a scanner generated by
* <a href="http://www.jflex.de/">JFlex</a> 1.4.1
* on 13.03.09 16:25 from the specification file
* <tt>C:/work/java/idea-plugins/RegExpSupport/Trunk/src/org/intellij/lang/regexp/regexp-lexer.flex</tt>
* on 23.09.09 18:11 from the specification file
* <tt>C:/JetBrains/IDEA/svnPlugins/RegExpSupport/src/org/intellij/lang/regexp/regexp-lexer.flex</tt>
*/
class _RegExLexer implements FlexLexer {
/** initial size of the lookahead buffer */
@@ -121,12 +121,12 @@ class _RegExLexer implements FlexLexer {
"\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\2\54\1\55\1\11\1\56\1\57\1\60\1\61"+
"\1\62\1\63\1\64\1\65\1\0\1\66\1\67\2\57"+
"\2\60\1\70\1\71\1\66\1\57\1\72\2\60\1\66"+
"\3\60\1\73";
"\1\62\1\63\1\64\1\65\2\0\1\66\1\67\2\57"+
"\2\60\1\70\1\71\1\0\1\66\1\57\1\72\2\60"+
"\1\73\1\66\3\60\1\74";
private static int [] zzUnpackAction() {
int [] result = new int[85];
int [] result = new int[88];
int offset = 0;
offset = zzUnpackAction(ZZ_ACTION_PACKED_0, offset, result);
return result;
@@ -159,12 +159,12 @@ class _RegExLexer implements FlexLexer {
"\0\u0188\0\u0310\0\u0341\0\u0188\0\u0188\0\u0372\0\u0188\0\u0188"+
"\0\u03a3\0\u03d4\0\u0188\0\u0188\0\u0188\0\u0188\0\u0188\0\u0405"+
"\0\u0188\0\u0188\0\u0188\0\u0436\0\u0467\0\u0188\0\u0188\0\u0188"+
"\0\u0188\0\u0188\0\u0498\0\u04c9\0\u0188\0\u04fa\0\u052b\0\u055c"+
"\0\u058d\0\u0188\0\u0188\0\u05be\0\u0188\0\u0188\0\u05ef\0\u0620"+
"\0\u0188\0\u0651\0\u0682\0\u0188\0\u0188";
"\0\u0188\0\u0188\0\u0498\0\u04c9\0\u04fa\0\u0188\0\u052b\0\u055c"+
"\0\u058d\0\u05be\0\u0188\0\u0188\0\u05ef\0\u0620\0\u0188\0\u0188"+
"\0\u0651\0\u0682\0\u0188\0\u0188\0\u06b3\0\u06e4\0\u0188\0\u0188";
private static int [] zzUnpackRowMap() {
int [] result = new int[85];
int [] result = new int[88];
int offset = 0;
offset = zzUnpackRowMap(ZZ_ROWMAP_PACKED_0, offset, result);
return result;
@@ -205,22 +205,23 @@ class _RegExLexer implements FlexLexer {
"\1\34\3\0\1\34\14\0\2\36\17\0\20\36\1\0"+
"\3\36\62\0\1\77\33\0\17\52\2\0\1\52\37\0"+
"\17\53\2\0\1\53\66\0\2\100\1\101\1\102\1\103"+
"\4\0\2\61\36\0\1\61\21\0\1\104\36\0\1\104"+
"\17\0\61\105\1\106\2\107\20\106\2\107\2\106\3\107"+
"\2\106\1\107\1\106\1\107\2\106\1\107\17\106\1\110"+
"\2\111\20\110\2\111\2\110\3\111\2\110\1\111\1\110"+
"\1\111\2\110\1\111\17\110\53\0\1\112\1\113\6\0"+
"\1\114\36\0\1\114\17\0\62\115\2\116\20\115\2\116"+
"\2\115\3\116\2\115\1\116\1\115\1\116\2\115\1\116"+
"\17\115\62\117\2\120\20\117\2\120\2\117\3\120\2\117"+
"\1\120\1\117\1\120\2\117\1\120\17\117\2\0\1\121"+
"\36\0\1\121\17\0\62\122\2\123\20\122\2\123\2\122"+
"\3\123\2\122\1\123\1\122\1\123\2\122\1\123\17\122"+
"\62\124\2\125\20\124\2\125\2\124\3\125\2\124\1\125"+
"\1\124\1\125\2\124\1\125\17\124";
"\1\104\3\0\2\61\36\0\1\61\21\0\1\105\36\0"+
"\1\105\17\0\61\106\1\107\2\110\20\107\2\110\2\107"+
"\3\110\2\107\1\110\1\107\1\110\2\107\1\110\17\107"+
"\1\111\2\112\20\111\2\112\2\111\3\112\2\111\1\112"+
"\1\111\1\112\2\111\1\112\17\111\53\0\1\113\1\114"+
"\4\0\5\115\1\0\53\115\2\0\1\116\36\0\1\116"+
"\17\0\62\117\2\120\20\117\2\120\2\117\3\120\2\117"+
"\1\120\1\117\1\120\2\117\1\120\17\117\62\121\2\122"+
"\20\121\2\122\2\121\3\122\2\121\1\122\1\121\1\122"+
"\2\121\1\122\17\121\5\115\1\123\53\115\2\0\1\124"+
"\36\0\1\124\17\0\62\125\2\126\20\125\2\126\2\125"+
"\3\126\2\125\1\126\1\125\1\126\2\125\1\126\17\125"+
"\62\127\2\130\20\127\2\130\2\127\3\130\2\127\1\130"+
"\1\127\1\130\2\127\1\130\17\127";
private static int [] zzUnpackTrans() {
int [] result = new int[1715];
int [] result = new int[1813];
int offset = 0;
offset = zzUnpackTrans(ZZ_TRANS_PACKED_0, offset, result);
return result;
@@ -264,11 +265,12 @@ class _RegExLexer implements FlexLexer {
"\6\0\2\1\2\11\1\1\2\11\1\3\1\1\12\11"+
"\1\1\1\11\1\1\1\11\1\1\5\11\1\1\2\11"+
"\1\3\2\11\2\1\2\11\1\1\1\15\1\11\2\1"+
"\5\11\1\1\3\11\2\1\5\11\1\0\1\1\1\11"+
"\4\1\2\11\1\1\2\11\2\1\1\11\2\1\2\11";
"\5\11\1\1\3\11\2\1\5\11\2\0\1\1\1\11"+
"\4\1\2\11\1\0\1\1\2\11\2\1\2\11\2\1"+
"\2\11";
private static int [] zzUnpackAttribute() {
int [] result = new int[85];
int [] result = new int[88];
int offset = 0;
offset = zzUnpackAttribute(ZZ_ATTRIBUTE_PACKED_0, offset, result);
return result;
@@ -413,7 +415,14 @@ class _RegExLexer implements FlexLexer {
// For Demetra compatibility
public void reset(CharSequence buffer, int initialState){
reset(buffer, 0, buffer.length(), initialState);
zzBuffer = buffer;
zzBufferArray = null;
zzCurrentPos = zzMarkedPos = zzStartRead = 0;
zzPushbackPos = 0;
zzAtEOF = false;
zzAtBOL = true;
zzEndRead = buffer.length();
yybegin(initialState);
}
/**
@@ -625,239 +634,243 @@ class _RegExLexer implements FlexLexer {
case 7:
{ if (yystate() != CLASS2) yypushstate(EMBRACED); return RegExpTT.LBRACE;
}
case 60: break;
case 61: break;
case 6:
{ return RegExpTT.GROUP_END;
}
case 61: break;
case 62: break;
case 36:
{ yypushstate(CLASS1); return RegExpTT.CLASS_BEGIN;
}
case 62: break;
case 63: break;
case 14:
{ return RegExpTT.STAR;
}
case 63: break;
case 64: break;
case 40:
{ return RegExpTT.ESC_CHARACTER;
}
case 64: break;
case 65: break;
case 28:
{ return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.ESC_CHARACTER;
}
case 65: break;
case 66: break;
case 37:
{ return RegExpTT.REDUNDANT_ESCAPE;
}
case 66: break;
case 67: break;
case 24:
{ return RegExpTT.COMMA;
}
case 67: break;
case 68: break;
case 56:
{ return RegExpTT.POS_LOOKBEHIND;
}
case 68: break;
case 69: break;
case 39:
{ return RegExpTT.BAD_OCT_VALUE;
}
case 69: break;
case 70: break;
case 10:
{ return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.CTRL_CHARACTER;
}
case 70: break;
case 71: break;
case 30:
{ yypopstate(); yypushstate(EMBRACED); return RegExpTT.LBRACE;
}
case 71: break;
case 72: break;
case 48:
{ return StringEscapesTokenTypes.INVALID_UNICODE_ESCAPE_TOKEN;
}
case 72: break;
case 73: break;
case 57:
{ return RegExpTT.NEG_LOOKBEHIND;
}
case 73: break;
case 59:
case 74: break;
case 60:
{ return RegExpTT.UNICODE_CHAR;
}
case 74: break;
case 75: break;
case 55:
{ if (xmlSchemaMode) { yypushback(1); return RegExpTT.CHAR_CLASS; } else return RegExpTT.CTRL;
}
case 75: break;
case 76: break;
case 35:
{ yybegin(OPTIONS); return RegExpTT.SET_OPTIONS;
}
case 76: break;
case 77: break;
case 12:
{ return RegExpTT.DOLLAR;
}
case 77: break;
case 78: break;
case 49:
{ yypopstate(); return RegExpTT.QUOTE_END;
}
case 78: break;
case 79: break;
case 52:
{ return RegExpTT.POS_LOOKAHEAD;
}
case 79: break;
case 80: break;
case 22:
{ yypopstate(); return RegExpTT.RBRACE;
}
case 80: break;
case 81: break;
case 3:
{ return RegExpTT.CHARACTER;
}
case 81: break;
case 82: break;
case 53:
{ return RegExpTT.NEG_LOOKAHEAD;
}
case 82: break;
case 83: break;
case 41:
{ return RegExpTT.ESC_CTRL_CHARACTER;
}
case 83: break;
case 84: break;
case 23:
{ return RegExpTT.NAME;
}
case 84: break;
case 85: break;
case 50:
{ return RegExpTT.ANDAND;
}
case 85: break;
case 86: break;
case 13:
{ return RegExpTT.QUEST;
}
case 86: break;
case 87: break;
case 43:
{ return RegExpTT.CHAR_CLASS;
}
case 87: break;
case 88: break;
case 17:
{ return RegExpTT.MINUS;
}
case 88: break;
case 89: break;
case 59:
{ return RegExpTT.COMMENT;
}
case 90: break;
case 38:
{ return yystate() != CLASS2 ? RegExpTT.BACKREF : RegExpTT.ESC_CHARACTER;
}
case 89: break;
case 91: break;
case 16:
{ return RegExpTT.UNION;
}
case 90: break;
case 92: break;
case 44:
{ if (xmlSchemaMode) return RegExpTT.CHAR_CLASS; else return StringEscapesTokenTypes.INVALID_CHARACTER_ESCAPE_TOKEN;
}
case 91: break;
case 93: break;
case 54:
{ return RegExpTT.OCT_CHAR;
}
case 92: break;
case 94: break;
case 4:
{ return RegExpTT.DOT;
}
case 93: break;
case 95: break;
case 32:
{ yybegin(YYINITIAL); return RegExpTT.GROUP_END;
}
case 94: break;
case 96: break;
case 21:
{ return RegExpTT.NUMBER;
}
case 95: break;
case 97: break;
case 45:
{ yypushstate(PROP); return RegExpTT.PROPERTY;
}
case 96: break;
case 98: break;
case 19:
{ return commentMode ? com.intellij.psi.TokenType.WHITE_SPACE : RegExpTT.CHARACTER;
}
case 97: break;
case 99: break;
case 33:
{ handleOptions(); return RegExpTT.OPTIONS_OFF;
}
case 98: break;
case 100: break;
case 34:
{ yybegin(YYINITIAL); return RegExpTT.COLON;
}
case 99: break;
case 101: break;
case 25:
{ assert false : yytext();
}
case 100: break;
case 102: break;
case 27:
{ yypopstate(); return RegExpTT.CLASS_END;
}
case 101: break;
case 103: break;
case 11:
{ return RegExpTT.CARET;
}
case 102: break;
case 104: break;
case 1:
{ handleOptions(); return RegExpTT.OPTIONS_ON;
}
case 103: break;
case 105: break;
case 29:
{ yypopstate(); yypushback(1);
}
case 104: break;
case 106: break;
case 42:
{ return yystate() != CLASS2 ? RegExpTT.BOUNDARY : RegExpTT.ESC_CHARACTER;
}
case 105: break;
case 107: break;
case 18:
{ if (commentMode) { yypushstate(COMMENT); return RegExpTT.COMMENT; } else return RegExpTT.CHARACTER;
}
case 106: break;
case 108: break;
case 58:
{ return RegExpTT.HEX_CHAR;
}
case 107: break;
case 109: break;
case 20:
{ return RegExpTT.BAD_CHARACTER;
}
case 108: break;
case 110: break;
case 5:
{ return RegExpTT.GROUP_BEGIN;
}
case 109: break;
case 111: break;
case 8:
{ yypushstate(CLASS2); return RegExpTT.CLASS_BEGIN;
}
case 110: break;
case 112: break;
case 51:
{ return RegExpTT.NON_CAPT_GROUP;
}
case 111: break;
case 113: break;
case 9:
{ return StringEscapesTokenTypes.INVALID_CHARACTER_ESCAPE_TOKEN;
}
case 112: break;
case 114: break;
case 47:
{ return RegExpTT.BAD_HEX_VALUE;
}
case 113: break;
case 115: break;
case 2:
{ yypopstate(); return RegExpTT.COMMENT;
}
case 114: break;
case 116: break;
case 46:
{ yypushstate(QUOTED); return RegExpTT.QUOTE_BEGIN;
}
case 115: break;
case 117: break;
case 26:
{ yybegin(CLASS2); return RegExpTT.CHARACTER;
}
case 116: break;
case 118: break;
case 15:
{ return RegExpTT.PLUS;
}
case 117: break;
case 119: break;
case 31:
{ yybegin(YYINITIAL); return RegExpTT.BAD_CHARACTER;
}
case 118: break;
case 120: break;
default:
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
RegExpSupport/src/org/intellij/lang/regexp/regexp-lexer.flex
+1
View File
@@ -195,6 +195,7 @@ HEX_CHAR=[0-9a-fA-F]
"(?!" { return RegExpTT.NEG_LOOKAHEAD; }
"(?<=" { return RegExpTT.POS_LOOKBEHIND; }
"(?<!" { return RegExpTT.NEG_LOOKBEHIND; }
"(?#" [^)]+ ")" { return RegExpTT.COMMENT; }
"(?" { yybegin(OPTIONS); return RegExpTT.SET_OPTIONS; }
}
RegExpSupport/src/org/intellij/lang/regexp/validation/RegExpAnnotator.java
+24 -3
View File
@@ -22,6 +22,7 @@ import com.intellij.lang.annotation.Annotation;
import com.intellij.lang.annotation.AnnotationHolder;
import com.intellij.lang.annotation.Annotator;
import com.intellij.lang.injection.InjectedLanguageManager;
import com.intellij.psi.PsiComment;
import com.intellij.psi.PsiElement;
import com.intellij.psi.PsiLanguageInjectionHost;
import com.intellij.psi.util.PsiTreeUtil;
@@ -29,6 +30,7 @@ import org.intellij.lang.regexp.RegExpLanguageHost;
import org.intellij.lang.regexp.RegExpTT;
import org.intellij.lang.regexp.psi.*;
import org.intellij.lang.regexp.psi.impl.RegExpPropertyImpl;
import org.jetbrains.annotations.Nullable;
public final class RegExpAnnotator extends RegExpElementVisitor implements Annotator {
private AnnotationHolder myHolder;
@@ -100,10 +102,10 @@ public final class RegExpAnnotator extends RegExpElementVisitor implements Annot
private static boolean isRedundantEscape(RegExpChar ch, String text) {
if (text.length() <= 1) return false;
PsiLanguageInjectionHost host = InjectedLanguageManager.getInstance(ch.getProject()).getInjectionHost(ch);
if (host instanceof RegExpLanguageHost) {
RegExpLanguageHost host = findRegExpHost(ch);
if (host != null) {
final char c = text.charAt(1);
final boolean needsEscaping = ((RegExpLanguageHost)host).characterNeedsEscaping(c);
final boolean needsEscaping = host.characterNeedsEscaping(c);
return !needsEscaping;
}
else {
@@ -111,6 +113,15 @@ public final class RegExpAnnotator extends RegExpElementVisitor implements Annot
}
}
@Nullable
private static RegExpLanguageHost findRegExpHost(PsiElement element) {
PsiLanguageInjectionHost host = InjectedLanguageManager.getInstance(element.getProject()).getInjectionHost(element);
if (host instanceof RegExpLanguageHost) {
return (RegExpLanguageHost) host;
}
return null;
}
public void visitRegExpProperty(RegExpProperty property) {
final ASTNode category = property.getCategoryNode();
if (category != null && !RegExpPropertyImpl.isValidCategory(category.getText())) {
@@ -151,6 +162,16 @@ public final class RegExpAnnotator extends RegExpElementVisitor implements Annot
}
}
@Override
public void visitComment(PsiComment comment) {
if (comment.getText().startsWith("(?#")) {
RegExpLanguageHost host = findRegExpHost(comment);
if (host == null || !host.supportsPerl5EmbeddedComments()) {
myHolder.createErrorAnnotation(comment, "Embedded comments are not supported");
}
}
}
private static boolean isEmpty(RegExpBranch[] branches) {
for (RegExpBranch branch : branches) {
if (branch.getAtoms().length > 0) {