Return non-default lexer state for unmatched backtick

When a document is changed, the editor highlighter restarts the lexer
at the last point where it was in the default state. Previously, if
a matching backtick was deleted and then reinserted, the lexer was
resumed just before the reinsertion point, and as the result the two
backticks were parsed not as two delimiters of a single token but as
two BAD_CHARACTER tokens. With this change, all tokens after the
unmatched backtick will be in a non-default state, so the lexer will
restart at the first backtick and will correctly see the two backticks
as a single token.

 #KT-9091 Fixed
This commit is contained in:
Dmitry Jemerov
2017-05-09 17:32:48 +02:00
parent 66877c138d
commit ec53a6dbe7
3 changed files with 293 additions and 227 deletions
@@ -69,7 +69,7 @@ import org.jetbrains.kotlin.lexer.KtTokens;
%eof}
%xstate STRING RAW_STRING SHORT_TEMPLATE_ENTRY BLOCK_COMMENT DOC_COMMENT
%state LONG_TEMPLATE_ENTRY
%state LONG_TEMPLATE_ENTRY UNMATCHED_BACKTICK
DIGIT=[0-9]
DIGIT_OR_UNDERSCORE = [_0-9]
@@ -119,6 +119,7 @@ REGULAR_STRING_PART=[^\\\"\n\$]+
SHORT_TEMPLATE_ENTRY=\${IDENTIFIER}
LONELY_DOLLAR=\$
LONG_TEMPLATE_ENTRY_START=\$\{
LONELY_BACKTICK=`
%%
@@ -318,6 +319,8 @@ LONG_TEMPLATE_ENTRY_START=\$\{
"#" { return KtTokens.HASH ; }
"@" { return KtTokens.AT ; }
{LONELY_BACKTICK} { pushState(UNMATCHED_BACKTICK); return TokenType.BAD_CHARACTER; }
// error fallback
. { return TokenType.BAD_CHARACTER; }
// error fallback for exclusive states
@@ -27,7 +27,7 @@ import com.intellij.util.containers.Stack;
/**
* This class is a scanner generated by
* <a href="http://www.jflex.de/">JFlex</a> 1.7.0-SNAPSHOT
* from the specification file <tt>/Users/endermz/projects/kotlin/compiler/frontend/src/org/jetbrains/kotlin/lexer/Kotlin.flex</tt>
* from the specification file <tt>/Users/yole/jetbrains/kotlin/compiler/frontend/src/org/jetbrains/kotlin/lexer/Kotlin.flex</tt>
*/
class _JetLexer implements FlexLexer {
@@ -45,6 +45,7 @@ class _JetLexer implements FlexLexer {
public static final int BLOCK_COMMENT = 8;
public static final int DOC_COMMENT = 10;
public static final int LONG_TEMPLATE_ENTRY = 12;
public static final int UNMATCHED_BACKTICK = 14;
/**
* ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l
@@ -53,7 +54,7 @@ class _JetLexer implements FlexLexer {
* l is of the form l = 2*k, k a non negative integer
*/
private static final int ZZ_LEXSTATE[] = {
0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 4, 5, 5
0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 4, 5, 5, 0, 0
};
/**
@@ -183,26 +184,26 @@ class _JetLexer implements FlexLexer {
private static final int [] ZZ_ACTION = zzUnpackAction();
private static final String ZZ_ACTION_PACKED_0 =
"\6\0\1\1\1\2\1\3\1\4\2\1\1\5\1\6"+
"\1\7\1\2\1\10\1\11\1\12\1\13\1\14\3\3"+
"\1\15\1\16\14\3\1\17\1\20\1\21\1\22\1\23"+
"\2\1\1\24\1\25\1\26\1\27\1\30\1\31\1\32"+
"\1\33\1\34\1\35\1\36\1\35\1\1\1\37\2\35"+
"\1\40\1\1\1\40\3\41\1\42\1\43\1\2\1\0"+
"\2\44\1\0\1\45\1\0\1\46\1\47\1\50\1\51"+
"\1\0\1\52\1\0\2\2\1\44\1\53\1\54\1\55"+
"\1\56\2\12\1\0\3\3\1\57\1\60\1\61\1\3"+
"\1\62\2\3\1\63\13\3\1\64\1\65\1\66\1\67"+
"\6\0\1\1\1\2\1\3\1\4\1\5\1\1\1\6"+
"\1\7\1\10\1\2\1\11\1\12\1\13\1\14\1\15"+
"\3\3\1\16\1\17\14\3\1\20\1\21\1\22\1\23"+
"\1\24\2\1\1\25\1\26\1\27\1\30\1\31\1\32"+
"\1\33\1\34\1\35\1\36\1\37\1\36\1\1\1\40"+
"\2\36\1\41\1\1\1\41\3\42\1\43\1\44\1\2"+
"\1\0\2\45\1\0\1\46\1\0\1\47\1\50\1\51"+
"\1\52\1\0\1\53\1\0\2\2\1\45\1\54\1\55"+
"\1\56\1\57\2\13\1\0\3\3\1\60\1\61\1\62"+
"\1\3\1\63\2\3\1\64\13\3\1\65\1\66\1\67"+
"\1\70\1\71\1\72\1\73\1\74\1\75\1\76\1\77"+
"\1\100\1\0\1\101\2\102\2\0\1\40\1\103\1\104"+
"\1\0\1\105\1\44\1\3\1\0\1\106\1\107\1\110"+
"\1\111\1\0\1\112\1\113\4\3\1\114\4\3\1\115"+
"\2\3\1\116\1\3\1\117\6\3\1\120\1\121\1\122"+
"\2\0\1\123\2\40\1\45\1\124\1\125\1\126\2\3"+
"\1\127\3\3\1\130\1\131\7\3\1\132\1\100\1\0"+
"\1\133\1\134\3\3\1\135\2\3\1\136\1\137\2\3"+
"\1\140\1\141\1\0\1\3\1\142\2\3\1\143\1\3"+
"\1\144\2\3\1\145\3\3\1\146\1\147\1\150";
"\1\100\1\101\1\0\1\102\2\103\2\0\1\41\1\104"+
"\1\105\1\0\1\106\1\45\1\3\1\0\1\107\1\110"+
"\1\111\1\112\1\0\1\113\1\114\4\3\1\115\4\3"+
"\1\116\2\3\1\117\1\3\1\120\6\3\1\121\1\122"+
"\1\123\2\0\1\124\2\41\1\46\1\125\1\126\1\127"+
"\2\3\1\130\3\3\1\131\1\132\7\3\1\133\1\101"+
"\1\0\1\134\1\135\3\3\1\136\2\3\1\137\1\140"+
"\2\3\1\141\1\142\1\0\1\3\1\143\2\3\1\144"+
"\1\3\1\145\2\3\1\146\3\3\1\147\1\150\1\151";
private static int [] zzUnpackAction() {
int [] result = new int[231];
@@ -646,7 +647,7 @@ class _JetLexer implements FlexLexer {
}
}
private final Stack<State> states = new Stack<>();
private final Stack<State> states = new Stack<State>();
private int lBraceCount;
private int commentStart;
@@ -954,140 +955,144 @@ class _JetLexer implements FlexLexer {
case 1:
{ return TokenType.BAD_CHARACTER;
}
case 105: break;
case 106: break;
case 2:
{ return KtTokens.INTEGER_LITERAL;
}
case 106: break;
case 107: break;
case 3:
{ return KtTokens.IDENTIFIER;
}
case 107: break;
case 108: break;
case 4:
{ return KtTokens.WHITE_SPACE;
}
case 108: break;
case 5:
{ return KtTokens.DIV ;
}
case 109: break;
case 6:
{ return KtTokens.HASH ;
case 5:
{ pushState(UNMATCHED_BACKTICK); return TokenType.BAD_CHARACTER;
}
case 110: break;
case 7:
{ return KtTokens.EXCL ;
case 6:
{ return KtTokens.DIV ;
}
case 111: break;
case 8:
{ return KtTokens.DOT ;
case 7:
{ return KtTokens.HASH ;
}
case 112: break;
case 9:
{ return KtTokens.MINUS ;
case 8:
{ return KtTokens.EXCL ;
}
case 113: break;
case 10:
{ return KtTokens.CHARACTER_LITERAL;
case 9:
{ return KtTokens.DOT ;
}
case 114: break;
case 11:
{ pushState(STRING); return KtTokens.OPEN_QUOTE;
case 10:
{ return KtTokens.MINUS ;
}
case 115: break;
case 12:
{ return KtTokens.LBRACE ;
case 11:
{ return KtTokens.CHARACTER_LITERAL;
}
case 116: break;
case 13:
{ return KtTokens.RBRACE ;
case 12:
{ pushState(STRING); return KtTokens.OPEN_QUOTE;
}
case 117: break;
case 14:
{ return KtTokens.MUL ;
case 13:
{ return KtTokens.LBRACE ;
}
case 118: break;
case 15:
{ return KtTokens.EQ ;
case 14:
{ return KtTokens.RBRACE ;
}
case 119: break;
case 16:
{ return KtTokens.QUEST ;
case 15:
{ return KtTokens.MUL ;
}
case 120: break;
case 17:
{ return KtTokens.PLUS ;
case 16:
{ return KtTokens.EQ ;
}
case 121: break;
case 18:
{ return KtTokens.LT ;
case 17:
{ return KtTokens.QUEST ;
}
case 122: break;
case 19:
{ return KtTokens.GT ;
case 18:
{ return KtTokens.PLUS ;
}
case 123: break;
case 20:
{ return KtTokens.PERC ;
case 19:
{ return KtTokens.LT ;
}
case 124: break;
case 21:
{ return KtTokens.COLON ;
case 20:
{ return KtTokens.GT ;
}
case 125: break;
case 22:
{ return KtTokens.LBRACKET ;
case 21:
{ return KtTokens.PERC ;
}
case 126: break;
case 23:
{ return KtTokens.RBRACKET ;
case 22:
{ return KtTokens.COLON ;
}
case 127: break;
case 24:
{ return KtTokens.LPAR ;
case 23:
{ return KtTokens.LBRACKET ;
}
case 128: break;
case 25:
{ return KtTokens.RPAR ;
case 24:
{ return KtTokens.RBRACKET ;
}
case 129: break;
case 26:
{ return KtTokens.SEMICOLON ;
case 25:
{ return KtTokens.LPAR ;
}
case 130: break;
case 27:
{ return KtTokens.COMMA ;
case 26:
{ return KtTokens.RPAR ;
}
case 131: break;
case 28:
{ return KtTokens.AT ;
case 27:
{ return KtTokens.SEMICOLON ;
}
case 132: break;
case 29:
{ return KtTokens.REGULAR_STRING_PART;
case 28:
{ return KtTokens.COMMA ;
}
case 133: break;
case 30:
{ popState(); yypushback(1); return KtTokens.DANGLING_NEWLINE;
case 29:
{ return KtTokens.AT ;
}
case 134: break;
case 31:
{ popState(); return KtTokens.CLOSING_QUOTE;
case 30:
{ return KtTokens.REGULAR_STRING_PART;
}
case 135: break;
case 32:
{ popState(); return KtTokens.IDENTIFIER;
case 31:
{ popState(); yypushback(1); return KtTokens.DANGLING_NEWLINE;
}
case 136: break;
case 33:
{
case 32:
{ popState(); return KtTokens.CLOSING_QUOTE;
}
case 137: break;
case 34:
{ lBraceCount++; return KtTokens.LBRACE;
case 33:
{ popState(); return KtTokens.IDENTIFIER;
}
case 138: break;
case 34:
{
}
case 139: break;
case 35:
{ lBraceCount++; return KtTokens.LBRACE;
}
case 140: break;
case 36:
{ if (lBraceCount == 0) {
popState();
return KtTokens.LONG_TEMPLATE_ENTRY_END;
@@ -1095,30 +1100,30 @@ class _JetLexer implements FlexLexer {
lBraceCount--;
return KtTokens.RBRACE;
}
case 139: break;
case 36:
case 141: break;
case 37:
{ return KtTokens.FLOAT_LITERAL;
}
case 140: break;
case 37:
case 142: break;
case 38:
{ return KtTokens.FIELD_IDENTIFIER;
}
case 141: break;
case 38:
case 143: break;
case 39:
{ return KtTokens.EOL_COMMENT;
}
case 142: break;
case 39:
case 144: break;
case 40:
{ pushState(BLOCK_COMMENT);
commentDepth = 0;
commentStart = getTokenStart();
}
case 143: break;
case 40:
case 145: break;
case 41:
{ return KtTokens.DIVEQ ;
}
case 144: break;
case 41:
case 146: break;
case 42:
{ if (zzCurrentPos == 0) {
return KtTokens.SHEBANG_COMMENT;
}
@@ -1127,114 +1132,114 @@ class _JetLexer implements FlexLexer {
return KtTokens.HASH;
}
}
case 145: break;
case 42:
case 147: break;
case 43:
{ return KtTokens.EXCLEQ ;
}
case 146: break;
case 43:
case 148: break;
case 44:
{ return KtTokens.RANGE ;
}
case 147: break;
case 44:
case 149: break;
case 45:
{ return KtTokens.MINUSMINUS;
}
case 148: break;
case 45:
case 150: break;
case 46:
{ return KtTokens.MINUSEQ ;
}
case 149: break;
case 46:
case 151: break;
case 47:
{ return KtTokens.ARROW ;
}
case 150: break;
case 47:
case 152: break;
case 48:
{ return KtTokens.IS_KEYWORD ;
}
case 151: break;
case 48:
case 153: break;
case 49:
{ return KtTokens.IN_KEYWORD ;
}
case 152: break;
case 49:
case 154: break;
case 50:
{ return KtTokens.IF_KEYWORD ;
}
case 153: break;
case 50:
case 155: break;
case 51:
{ return KtTokens.MULTEQ ;
}
case 154: break;
case 51:
case 156: break;
case 52:
{ return KtTokens.AS_KEYWORD ;
}
case 155: break;
case 52:
case 157: break;
case 53:
{ return KtTokens.DO_KEYWORD ;
}
case 156: break;
case 53:
case 158: break;
case 54:
{ return KtTokens.EQEQ ;
}
case 157: break;
case 54:
case 159: break;
case 55:
{ return KtTokens.DOUBLE_ARROW;
}
case 158: break;
case 55:
case 160: break;
case 56:
{ return KtTokens.PLUSEQ ;
}
case 159: break;
case 56:
case 161: break;
case 57:
{ return KtTokens.PLUSPLUS ;
}
case 160: break;
case 57:
case 162: break;
case 58:
{ return KtTokens.LTEQ ;
}
case 161: break;
case 58:
case 163: break;
case 59:
{ return KtTokens.GTEQ ;
}
case 162: break;
case 59:
case 164: break;
case 60:
{ return KtTokens.ANDAND ;
}
case 163: break;
case 60:
case 165: break;
case 61:
{ return KtTokens.OROR ;
}
case 164: break;
case 61:
case 166: break;
case 62:
{ return KtTokens.PERCEQ ;
}
case 165: break;
case 62:
case 167: break;
case 63:
{ return KtTokens.COLONCOLON;
}
case 166: break;
case 63:
case 168: break;
case 64:
{ return KtTokens.DOUBLE_SEMICOLON;
}
case 167: break;
case 64:
case 169: break;
case 65:
{ pushState(SHORT_TEMPLATE_ENTRY);
yypushback(yylength() - 1);
return KtTokens.SHORT_TEMPLATE_ENTRY_START;
}
case 168: break;
case 65:
case 170: break;
case 66:
{ pushState(LONG_TEMPLATE_ENTRY); return KtTokens.LONG_TEMPLATE_ENTRY_START;
}
case 169: break;
case 66:
case 171: break;
case 67:
{ return KtTokens.ESCAPE_SEQUENCE;
}
case 170: break;
case 67:
case 172: break;
case 68:
{ commentDepth++;
}
case 171: break;
case 68:
case 173: break;
case 69:
{ if (commentDepth > 0) {
commentDepth--;
}
@@ -1245,66 +1250,66 @@ class _JetLexer implements FlexLexer {
return commentStateToTokenType(state);
}
}
case 172: break;
case 69:
case 174: break;
case 70:
{ yypushback(2); return KtTokens.INTEGER_LITERAL;
}
case 173: break;
case 70:
case 175: break;
case 71:
{ pushState(DOC_COMMENT);
commentDepth = 0;
commentStart = getTokenStart();
}
case 174: break;
case 71:
case 176: break;
case 72:
{ return KtTokens.NOT_IS;
}
case 175: break;
case 72:
case 177: break;
case 73:
{ return KtTokens.NOT_IN;
}
case 176: break;
case 73:
case 178: break;
case 74:
{ return KtTokens.EXCLEQEQEQ;
}
case 177: break;
case 74:
case 179: break;
case 75:
{ return KtTokens.RESERVED ;
}
case 178: break;
case 75:
case 180: break;
case 76:
{ pushState(RAW_STRING); return KtTokens.OPEN_QUOTE;
}
case 179: break;
case 76:
case 181: break;
case 77:
{ return KtTokens.TRY_KEYWORD ;
}
case 180: break;
case 77:
case 182: break;
case 78:
{ return KtTokens.AS_SAFE;
}
case 181: break;
case 78:
case 183: break;
case 79:
{ return KtTokens.FUN_KEYWORD ;
}
case 182: break;
case 79:
case 184: break;
case 80:
{ return KtTokens.FOR_KEYWORD ;
}
case 183: break;
case 80:
case 185: break;
case 81:
{ return KtTokens.VAL_KEYWORD ;
}
case 184: break;
case 81:
case 186: break;
case 82:
{ return KtTokens.VAR_KEYWORD ;
}
case 185: break;
case 82:
case 187: break;
case 83:
{ return KtTokens.EQEQEQ ;
}
case 186: break;
case 83:
case 188: break;
case 84:
{ int length = yytext().length();
if (length <= 3) { // closing """
popState();
@@ -1315,91 +1320,91 @@ class _JetLexer implements FlexLexer {
return KtTokens.REGULAR_STRING_PART;
}
}
case 187: break;
case 84:
case 189: break;
case 85:
{ return KtTokens.BLOCK_COMMENT;
}
case 188: break;
case 85:
case 190: break;
case 86:
{ yypushback(3); return KtTokens.EXCL;
}
case 189: break;
case 86:
case 191: break;
case 87:
{ return KtTokens.THIS_KEYWORD ;
}
case 190: break;
case 87:
case 192: break;
case 88:
{ return KtTokens.TRUE_KEYWORD ;
}
case 191: break;
case 88:
case 193: break;
case 89:
{ return KtTokens.ELSE_KEYWORD ;
}
case 192: break;
case 89:
case 194: break;
case 90:
{ return KtTokens.NULL_KEYWORD ;
}
case 193: break;
case 90:
case 195: break;
case 91:
{ return KtTokens.WHEN_KEYWORD ;
}
case 194: break;
case 91:
case 196: break;
case 92:
{ popState(); return KtTokens.THIS_KEYWORD;
}
case 195: break;
case 92:
case 197: break;
case 93:
{ return KtTokens.THROW_KEYWORD ;
}
case 196: break;
case 93:
case 198: break;
case 94:
{ return KtTokens.SUPER_KEYWORD ;
}
case 197: break;
case 94:
case 199: break;
case 95:
{ return KtTokens.FALSE_KEYWORD ;
}
case 198: break;
case 95:
case 200: break;
case 96:
{ return KtTokens.CLASS_KEYWORD ;
}
case 199: break;
case 96:
case 201: break;
case 97:
{ return KtTokens.BREAK_KEYWORD ;
}
case 200: break;
case 97:
case 202: break;
case 98:
{ return KtTokens.WHILE_KEYWORD ;
}
case 201: break;
case 98:
case 203: break;
case 99:
{ return KtTokens.TYPEOF_KEYWORD ;
}
case 202: break;
case 99:
case 204: break;
case 100:
{ return KtTokens.RETURN_KEYWORD ;
}
case 203: break;
case 100:
case 205: break;
case 101:
{ return KtTokens.OBJECT_KEYWORD ;
}
case 204: break;
case 101:
case 206: break;
case 102:
{ return KtTokens.PACKAGE_KEYWORD ;
}
case 205: break;
case 102:
case 207: break;
case 103:
{ return KtTokens.CONTINUE_KEYWORD ;
}
case 206: break;
case 103:
case 208: break;
case 104:
{ return KtTokens.TYPE_ALIAS_KEYWORD ;
}
case 207: break;
case 104:
case 209: break;
case 105:
{ return KtTokens.INTERFACE_KEYWORD ;
}
case 208: break;
case 210: break;
default:
zzScanError(ZZ_NO_MATCH);
}
@@ -0,0 +1,58 @@
/*
* Copyright 2010-2017 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.
*/
package org.jetbrains.kotlin.idea.highlighter
import com.intellij.openapi.editor.ex.EditorEx
import com.intellij.openapi.editor.ex.util.LexerEditorHighlighter
import com.intellij.psi.TokenType
import com.intellij.psi.tree.IElementType
import org.jetbrains.kotlin.idea.test.KotlinLightCodeInsightFixtureTestCase
import org.jetbrains.kotlin.idea.test.KotlinLightProjectDescriptor
import org.jetbrains.kotlin.idea.util.application.executeWriteCommand
import org.jetbrains.kotlin.lexer.KtTokens
import kotlin.test.assertEquals
class HighlightingUpdateTest : KotlinLightCodeInsightFixtureTestCase() {
override fun getProjectDescriptor(): KotlinLightProjectDescriptor = KotlinLightProjectDescriptor.INSTANCE
fun testUpdateWithBackticks() {
val editorText = "fun `two words`() { }"
myFixture.configureByText("foo.kt", editorText)
val editorHighlighter = (myFixture.editor as EditorEx).highlighter as LexerEditorHighlighter
val index = editorText.indexOf("`()")
myFixture.project.executeWriteCommand("") {
editorHighlighter.assertHighlighterIteratorTokens(KtTokens.FUN_KEYWORD, KtTokens.WHITE_SPACE, KtTokens.IDENTIFIER)
myFixture.editor.document.deleteString(index, index + 1)
editorHighlighter.assertHighlighterIteratorTokens(KtTokens.FUN_KEYWORD, KtTokens.WHITE_SPACE, TokenType.BAD_CHARACTER)
myFixture.editor.document.insertString(index, "`")
editorHighlighter.assertHighlighterIteratorTokens(KtTokens.FUN_KEYWORD, KtTokens.WHITE_SPACE, KtTokens.IDENTIFIER)
}
}
}
private fun LexerEditorHighlighter.assertHighlighterIteratorTokens(vararg tokens: IElementType) {
val iterator = createIterator(0)
for (token in tokens) {
assertEquals(token, iterator.tokenType)
iterator.advance()
}
}