From: axelcl Date: Wed, 10 Nov 2004 20:24:26 +0000 (+0000) Subject: don't split one line PHP statements in CodeFormatter X-Git-Url: http://git.phpeclipse.com don't split one line PHP statements in CodeFormatter --- diff --git a/net.sourceforge.phpeclipse/src/net/sourceforge/phpdt/internal/compiler/parser/Scanner.java b/net.sourceforge.phpeclipse/src/net/sourceforge/phpdt/internal/compiler/parser/Scanner.java index 0997cb7..a8232c2 100644 --- a/net.sourceforge.phpeclipse/src/net/sourceforge/phpdt/internal/compiler/parser/Scanner.java +++ b/net.sourceforge.phpeclipse/src/net/sourceforge/phpdt/internal/compiler/parser/Scanner.java @@ -1,14 +1,12 @@ -/******************************************************************************* - * Copyright (c) 2000, 2001, 2002 International Business Machines Corp. and others. - * All rights reserved. This program and the accompanying materials - * are made available under the terms of the Common Public License v0.5 - * which accompanies this distribution, and is available at - * http://www.eclipse.org/legal/cpl-v05.html +/*********************************************************************************************************************************** + * Copyright (c) 2000, 2001, 2002 International Business Machines Corp. and others. All rights reserved. This program and the + * accompanying materials are made available under the terms of the Common Public License v0.5 which accompanies this distribution, + * and is available at http://www.eclipse.org/legal/cpl-v05.html * - * Contributors: - * IBM Corporation - initial API and implementation - ******************************************************************************/ + * Contributors: IBM Corporation - initial API and implementation + **********************************************************************************************************************************/ package net.sourceforge.phpdt.internal.compiler.parser; + import java.util.ArrayList; import java.util.Iterator; import java.util.List; @@ -20,98 +18,144 @@ import net.sourceforge.phpdt.core.compiler.ITerminalSymbols; import net.sourceforge.phpdt.core.compiler.InvalidInputException; import net.sourceforge.phpeclipse.internal.compiler.ast.StringLiteral; - public class Scanner implements IScanner, ITerminalSymbols { /* - * APIs ares - getNextToken() which return the current type of the token - * (this value is not memorized by the scanner) - getCurrentTokenSource() - * which provides with the token "REAL" source (aka all unicode have been - * transformed into a correct char) - sourceStart gives the position into the - * stream - currentPosition-1 gives the sourceEnd position into the stream + * APIs ares - getNextToken() which return the current type of the token (this value is not memorized by the scanner) - + * getCurrentTokenSource() which provides with the token "REAL" source (aka all unicode have been transformed into a correct char) - + * sourceStart gives the position into the stream - currentPosition-1 gives the sourceEnd position into the stream */ // 1.4 feature private boolean assertMode; + public boolean useAssertAsAnIndentifier = false; + //flag indicating if processed source contains occurrences of keyword assert public boolean containsAssertKeyword = false; + public boolean recordLineSeparator; + + public boolean ignorePHPOneLiner = false; + public boolean phpMode = false; + public Stack encapsedStringStack = null; + public char currentCharacter; + public int startPosition; + public int currentPosition; + public int initialPosition, eofPosition; + // after this position eof are generated instead of real token from the // source public boolean tokenizeComments; + public boolean tokenizeWhiteSpace; + public boolean tokenizeStrings; + //source should be viewed as a window (aka a part) //of a entire very large stream public char source[]; + //unicode support public char[] withoutUnicodeBuffer; + public int withoutUnicodePtr; + //when == 0 ==> no unicode in the current token public boolean unicodeAsBackSlash = false; + public boolean scanningFloatLiteral = false; -//support for /** comments - public int[] commentStops = new int[10]; - public int[] commentStarts = new int[10]; - public int commentPtr = -1; // no comment test with commentPtr value -1 - protected int lastCommentLinePosition = -1; + + //support for /** comments + public int[] commentStops = new int[10]; + + public int[] commentStarts = new int[10]; + + public int commentPtr = -1; // no comment test with commentPtr value -1 + + protected int lastCommentLinePosition = -1; + //diet parsing support - jump over some method body when requested public boolean diet = false; + //support for the poor-line-debuggers .... //remember the position of the cr/lf public int[] lineEnds = new int[250]; + public int linePtr = -1; + public boolean wasAcr = false; + public static final String END_OF_SOURCE = "End_Of_Source"; //$NON-NLS-1$ + public static final String INVALID_HEXA = "Invalid_Hexa_Literal"; //$NON-NLS-1$ + public static final String INVALID_OCTAL = "Invalid_Octal_Literal"; //$NON-NLS-1$ + public static final String INVALID_CHARACTER_CONSTANT = "Invalid_Character_Constant"; //$NON-NLS-1$ + public static final String INVALID_ESCAPE = "Invalid_Escape"; //$NON-NLS-1$ + public static final String INVALID_INPUT = "Invalid_Input"; //$NON-NLS-1$ + public static final String INVALID_UNICODE_ESCAPE = "Invalid_Unicode_Escape"; //$NON-NLS-1$ + public static final String INVALID_FLOAT = "Invalid_Float_Literal"; //$NON-NLS-1$ + public static final String NULL_SOURCE_STRING = "Null_Source_String"; //$NON-NLS-1$ + public static final String UNTERMINATED_STRING = "Unterminated_String"; //$NON-NLS-1$ + public static final String UNTERMINATED_COMMENT = "Unterminated_Comment"; //$NON-NLS-1$ + public static final String INVALID_CHAR_IN_STRING = "Invalid_Char_In_String"; //$NON-NLS-1$ + //----------------optimized identifier managment------------------ - static final char[] charArray_a = new char[]{'a'}, - charArray_b = new char[]{'b'}, charArray_c = new char[]{'c'}, - charArray_d = new char[]{'d'}, charArray_e = new char[]{'e'}, - charArray_f = new char[]{'f'}, charArray_g = new char[]{'g'}, - charArray_h = new char[]{'h'}, charArray_i = new char[]{'i'}, - charArray_j = new char[]{'j'}, charArray_k = new char[]{'k'}, - charArray_l = new char[]{'l'}, charArray_m = new char[]{'m'}, - charArray_n = new char[]{'n'}, charArray_o = new char[]{'o'}, - charArray_p = new char[]{'p'}, charArray_q = new char[]{'q'}, - charArray_r = new char[]{'r'}, charArray_s = new char[]{'s'}, - charArray_t = new char[]{'t'}, charArray_u = new char[]{'u'}, - charArray_v = new char[]{'v'}, charArray_w = new char[]{'w'}, - charArray_x = new char[]{'x'}, charArray_y = new char[]{'y'}, - charArray_z = new char[]{'z'}; - static final char[] initCharArray = new char[]{'\u0000', '\u0000', '\u0000', - '\u0000', '\u0000', '\u0000'}; + static final char[] charArray_a = new char[] { 'a' }, charArray_b = new char[] { 'b' }, charArray_c = new char[] { 'c' }, + charArray_d = new char[] { 'd' }, charArray_e = new char[] { 'e' }, charArray_f = new char[] { 'f' }, + charArray_g = new char[] { 'g' }, charArray_h = new char[] { 'h' }, charArray_i = new char[] { 'i' }, + charArray_j = new char[] { 'j' }, charArray_k = new char[] { 'k' }, charArray_l = new char[] { 'l' }, + charArray_m = new char[] { 'm' }, charArray_n = new char[] { 'n' }, charArray_o = new char[] { 'o' }, + charArray_p = new char[] { 'p' }, charArray_q = new char[] { 'q' }, charArray_r = new char[] { 'r' }, + charArray_s = new char[] { 's' }, charArray_t = new char[] { 't' }, charArray_u = new char[] { 'u' }, + charArray_v = new char[] { 'v' }, charArray_w = new char[] { 'w' }, charArray_x = new char[] { 'x' }, + charArray_y = new char[] { 'y' }, charArray_z = new char[] { 'z' }; + + static final char[] initCharArray = new char[] { '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000' }; + static final int TableSize = 30, InternalTableSize = 6; + //30*6 = 180 entries public static final int OptimizedLength = 6; + public/* static */ final char[][][][] charArray_length = new char[OptimizedLength][TableSize][InternalTableSize][]; + // support for detecting non-externalized string literals int currentLineNr = -1; + int previousLineNr = -1; + NLSLine currentLine = null; + List lines = new ArrayList(); + public static final String TAG_PREFIX = "//$NON-NLS-"; //$NON-NLS-1$ + public static final int TAG_PREFIX_LENGTH = TAG_PREFIX.length(); + public static final String TAG_POSTFIX = "$"; //$NON-NLS-1$ + public static final int TAG_POSTFIX_LENGTH = TAG_POSTFIX.length(); + public StringLiteral[] nonNLSStrings = null; + public boolean checkNonExternalizedStringLiterals = true; + public boolean wasNonExternalizedStringLiteral = false; /* static */{ for (int i = 0; i < 6; i++) { @@ -122,43 +166,56 @@ public class Scanner implements IScanner, ITerminalSymbols { } } } - static int newEntry2 = 0, newEntry3 = 0, newEntry4 = 0, newEntry5 = 0, - newEntry6 = 0; + + static int newEntry2 = 0, newEntry3 = 0, newEntry4 = 0, newEntry5 = 0, newEntry6 = 0; + public static final int RoundBracket = 0; + public static final int SquareBracket = 1; + public static final int CurlyBracket = 2; + public static final int BracketKinds = 3; + // task tag support public char[][] foundTaskTags = null; + public char[][] foundTaskMessages; + public char[][] foundTaskPriorities = null; + public int[][] foundTaskPositions; + public int foundTaskCount = 0; + public char[][] taskTags = null; + public char[][] taskPriorities = null; + public static final boolean DEBUG = false; + public static final boolean TRACE = false; /** - * Determines if the specified character is permissible as the first - * character in a PHP identifier + * Determines if the specified character is permissible as the first character in a PHP identifier */ public static boolean isPHPIdentifierStart(char ch) { return Character.isLetter(ch) || (ch == '_') || (0x7F <= ch && ch <= 0xFF); } + /** - * Determines if the specified character may be part of a PHP identifier as - * other than the first character + * Determines if the specified character may be part of a PHP identifier as other than the first character */ public static boolean isPHPIdentifierPart(char ch) { - return Character.isLetterOrDigit(ch) || (ch == '_') - || (0x7F <= ch && ch <= 0xFF); + return Character.isLetterOrDigit(ch) || (ch == '_') || (0x7F <= ch && ch <= 0xFF); } + public final boolean atEnd() { // This code is not relevant if source is // Only a part of the real stream input return source.length == currentPosition; } + public char[] getCurrentIdentifierSource() { //return the token REAL source (aka unicodes are precomputed) char[] result; @@ -173,28 +230,29 @@ public class Scanner implements IScanner, ITerminalSymbols { // else { int length = currentPosition - startPosition; switch (length) { // see OptimizedLength - case 1 : - return optimizedCurrentTokenSource1(); - case 2 : - return optimizedCurrentTokenSource2(); - case 3 : - return optimizedCurrentTokenSource3(); - case 4 : - return optimizedCurrentTokenSource4(); - case 5 : - return optimizedCurrentTokenSource5(); - case 6 : - return optimizedCurrentTokenSource6(); + case 1: + return optimizedCurrentTokenSource1(); + case 2: + return optimizedCurrentTokenSource2(); + case 3: + return optimizedCurrentTokenSource3(); + case 4: + return optimizedCurrentTokenSource4(); + case 5: + return optimizedCurrentTokenSource5(); + case 6: + return optimizedCurrentTokenSource6(); } //no optimization - System.arraycopy(source, startPosition, result = new char[length], 0, - length); + System.arraycopy(source, startPosition, result = new char[length], 0, length); // } return result; } + public int getCurrentTokenEndPosition() { return this.currentPosition - 1; } + public final char[] getCurrentTokenSource() { // Return the token REAL source (aka unicodes are precomputed) char[] result; @@ -208,11 +266,11 @@ public class Scanner implements IScanner, ITerminalSymbols { // withoutUnicodePtr); // else { int length; - System.arraycopy(source, startPosition, - result = new char[length = currentPosition - startPosition], 0, length); + System.arraycopy(source, startPosition, result = new char[length = currentPosition - startPosition], 0, length); // } return result; } + public final char[] getCurrentTokenSource(int startPos) { // Return the token REAL source (aka unicodes are precomputed) char[] result; @@ -226,46 +284,44 @@ public class Scanner implements IScanner, ITerminalSymbols { // withoutUnicodePtr); // else { int length; - System.arraycopy(source, startPos, - result = new char[length = currentPosition - startPos], 0, length); + System.arraycopy(source, startPos, result = new char[length = currentPosition - startPos], 0, length); // } return result; } + public final char[] getCurrentTokenSourceString() { //return the token REAL source (aka unicodes are precomputed). //REMOVE the two " that are at the beginning and the end. char[] result; if (withoutUnicodePtr != 0) //0 is used as a fast test flag so the real first char is in position 1 - System.arraycopy(withoutUnicodeBuffer, 2, + System.arraycopy(withoutUnicodeBuffer, 2, //2 is 1 (real start) + 1 (to jump over the ") result = new char[withoutUnicodePtr - 2], 0, withoutUnicodePtr - 2); else { int length; - System.arraycopy(source, startPosition + 1, - result = new char[length = currentPosition - startPosition - 2], 0, - length); + System.arraycopy(source, startPosition + 1, result = new char[length = currentPosition - startPosition - 2], 0, length); } return result; } + public int getCurrentTokenStartPosition() { return this.startPosition; } + public final char[] getCurrentStringLiteralSource() { // Return the token REAL source (aka unicodes are precomputed) char[] result; int length; - System.arraycopy(source, startPosition + 1, - result = new char[length = currentPosition - startPosition - 2], 0, - length); + System.arraycopy(source, startPosition + 1, result = new char[length = currentPosition - startPosition - 2], 0, length); // } return result; } + /* * Search the source position corresponding to the end of a given line number * - * Line numbers are 1-based, and relative to the scanner initialPosition. - * Character positions are 0-based. + * Line numbers are 1-based, and relative to the scanner initialPosition. Character positions are 0-based. * * In case the given line number is inconsistent, answers -1. */ @@ -281,12 +337,11 @@ public class Scanner implements IScanner, ITerminalSymbols { return lineEnds[lineNumber - 1]; // next line start one character behind the lineEnd of the previous line } + /** - * Search the source position corresponding to the beginning of a given line - * number + * Search the source position corresponding to the beginning of a given line number * - * Line numbers are 1-based, and relative to the scanner initialPosition. - * Character positions are 0-based. + * Line numbers are 1-based, and relative to the scanner initialPosition. Character positions are 0-based. * * e.g. getLineStart(1) --> 0 i.e. first line starts at character 0. * @@ -304,6 +359,7 @@ public class Scanner implements IScanner, ITerminalSymbols { return lineEnds[lineNumber - 2] + 1; // next line start one character behind the lineEnd of the previous line } + public final boolean getNextChar(char testedChar) { //BOOLEAN //handle the case of unicode. @@ -380,6 +436,7 @@ public class Scanner implements IScanner, ITerminalSymbols { return false; } } + public final int getNextChar(char testedChar1, char testedChar2) { //INT 0 : testChar1 \\\\///\\\\ 1 : testedChar2 \\\\///\\\\ -1 : others //test can be done with (x==0) for the first and (x>0) for the second @@ -462,6 +519,7 @@ public class Scanner implements IScanner, ITerminalSymbols { return -1; } } + public final boolean getNextCharAsDigit() { //BOOLEAN //handle the case of unicode. @@ -533,6 +591,7 @@ public class Scanner implements IScanner, ITerminalSymbols { return false; } } + public final boolean getNextCharAsDigit(int radix) { //BOOLEAN //handle the case of unicode. @@ -605,6 +664,7 @@ public class Scanner implements IScanner, ITerminalSymbols { return false; } } + public boolean getNextCharAsJavaIdentifierPart() { //BOOLEAN //handle the case of unicode. @@ -677,6 +737,7 @@ public class Scanner implements IScanner, ITerminalSymbols { return false; } } + public int getCastOrParen() { int tempPosition = currentPosition; char tempCharacter = currentCharacter; @@ -687,8 +748,7 @@ public class Scanner implements IScanner, ITerminalSymbols { do { currentCharacter = source[currentPosition++]; } while (currentCharacter == ' ' || currentCharacter == '\t'); - while ((currentCharacter >= 'a' && currentCharacter <= 'z') - || (currentCharacter >= 'A' && currentCharacter <= 'Z')) { + while ((currentCharacter >= 'a' && currentCharacter <= 'z') || (currentCharacter >= 'A' && currentCharacter <= 'Z')) { buf.append(currentCharacter); currentCharacter = source[currentPosition++]; } @@ -696,98 +756,85 @@ public class Scanner implements IScanner, ITerminalSymbols { char[] data = buf.toString().toCharArray(); int index = 0; switch (data.length) { - case 3 : - // int - if ((data[index] == 'i') && (data[++index] == 'n') - && (data[++index] == 't')) { - found = true; - tempToken = TokenNameintCAST; - } - break; - case 4 : - // bool real - if ((data[index] == 'b') && (data[++index] == 'o') - && (data[++index] == 'o') && (data[++index] == 'l')) { + case 3: + // int + if ((data[index] == 'i') && (data[++index] == 'n') && (data[++index] == 't')) { + found = true; + tempToken = TokenNameintCAST; + } + break; + case 4: + // bool real + if ((data[index] == 'b') && (data[++index] == 'o') && (data[++index] == 'o') && (data[++index] == 'l')) { + found = true; + tempToken = TokenNameboolCAST; + } else { + index = 0; + if ((data[index] == 'r') && (data[++index] == 'e') && (data[++index] == 'a') && (data[++index] == 'l')) { found = true; - tempToken = TokenNameboolCAST; - } else { - index = 0; - if ((data[index] == 'r') && (data[++index] == 'e') - && (data[++index] == 'a') && (data[++index] == 'l')) { - found = true; - tempToken = TokenNamedoubleCAST; - } + tempToken = TokenNamedoubleCAST; } - break; - case 5 : - // array unset float - if ((data[index] == 'a') && (data[++index] == 'r') - && (data[++index] == 'r') && (data[++index] == 'a') - && (data[++index] == 'y')) { + } + break; + case 5: + // array unset float + if ((data[index] == 'a') && (data[++index] == 'r') && (data[++index] == 'r') && (data[++index] == 'a') + && (data[++index] == 'y')) { + found = true; + tempToken = TokenNamearrayCAST; + } else { + index = 0; + if ((data[index] == 'u') && (data[++index] == 'n') && (data[++index] == 's') && (data[++index] == 'e') + && (data[++index] == 't')) { found = true; - tempToken = TokenNamearrayCAST; + tempToken = TokenNameunsetCAST; } else { index = 0; - if ((data[index] == 'u') && (data[++index] == 'n') - && (data[++index] == 's') && (data[++index] == 'e') + if ((data[index] == 'f') && (data[++index] == 'l') && (data[++index] == 'o') && (data[++index] == 'a') && (data[++index] == 't')) { found = true; - tempToken = TokenNameunsetCAST; - } else { - index = 0; - if ((data[index] == 'f') && (data[++index] == 'l') - && (data[++index] == 'o') && (data[++index] == 'a') - && (data[++index] == 't')) { - found = true; - tempToken = TokenNamedoubleCAST; - } + tempToken = TokenNamedoubleCAST; } } - break; - case 6 : - // object string double - if ((data[index] == 'o') && (data[++index] == 'b') - && (data[++index] == 'j') && (data[++index] == 'e') - && (data[++index] == 'c') && (data[++index] == 't')) { + } + break; + case 6: + // object string double + if ((data[index] == 'o') && (data[++index] == 'b') && (data[++index] == 'j') && (data[++index] == 'e') + && (data[++index] == 'c') && (data[++index] == 't')) { + found = true; + tempToken = TokenNameobjectCAST; + } else { + index = 0; + if ((data[index] == 's') && (data[++index] == 't') && (data[++index] == 'r') && (data[++index] == 'i') + && (data[++index] == 'n') && (data[++index] == 'g')) { found = true; - tempToken = TokenNameobjectCAST; + tempToken = TokenNamestringCAST; } else { index = 0; - if ((data[index] == 's') && (data[++index] == 't') - && (data[++index] == 'r') && (data[++index] == 'i') - && (data[++index] == 'n') && (data[++index] == 'g')) { + if ((data[index] == 'd') && (data[++index] == 'o') && (data[++index] == 'u') && (data[++index] == 'b') + && (data[++index] == 'l') && (data[++index] == 'e')) { found = true; - tempToken = TokenNamestringCAST; - } else { - index = 0; - if ((data[index] == 'd') && (data[++index] == 'o') - && (data[++index] == 'u') && (data[++index] == 'b') - && (data[++index] == 'l') && (data[++index] == 'e')) { - found = true; - tempToken = TokenNamedoubleCAST; - } + tempToken = TokenNamedoubleCAST; } } - break; - case 7 : - // boolean integer - if ((data[index] == 'b') && (data[++index] == 'o') - && (data[++index] == 'o') && (data[++index] == 'l') - && (data[++index] == 'e') && (data[++index] == 'a') - && (data[++index] == 'n')) { + } + break; + case 7: + // boolean integer + if ((data[index] == 'b') && (data[++index] == 'o') && (data[++index] == 'o') && (data[++index] == 'l') + && (data[++index] == 'e') && (data[++index] == 'a') && (data[++index] == 'n')) { + found = true; + tempToken = TokenNameboolCAST; + } else { + index = 0; + if ((data[index] == 'i') && (data[++index] == 'n') && (data[++index] == 't') && (data[++index] == 'e') + && (data[++index] == 'g') && (data[++index] == 'e') && (data[++index] == 'r')) { found = true; - tempToken = TokenNameboolCAST; - } else { - index = 0; - if ((data[index] == 'i') && (data[++index] == 'n') - && (data[++index] == 't') && (data[++index] == 'e') - && (data[++index] == 'g') && (data[++index] == 'e') - && (data[++index] == 'r')) { - found = true; - tempToken = TokenNameintCAST; - } + tempToken = TokenNameintCAST; } - break; + } + break; } if (found) { while (currentCharacter == ' ' || currentCharacter == '\t') { @@ -804,6 +851,7 @@ public class Scanner implements IScanner, ITerminalSymbols { currentPosition = tempPosition; return TokenNameLPAREN; } + public void consumeStringInterpolated() throws InvalidInputException { try { // consume next character @@ -845,15 +893,13 @@ public class Scanner implements IScanner, ITerminalSymbols { escapeSize = currentPosition - escapeSize; if (withoutUnicodePtr == 0) { //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - escapeSize - 1 - - startPosition; - System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, - withoutUnicodePtr); + withoutUnicodePtr = currentPosition - escapeSize - 1 - startPosition; + System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, withoutUnicodePtr); withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } else { //overwrite the / in the buffer withoutUnicodeBuffer[withoutUnicodePtr] = currentCharacter; if (backSlashAsUnicodeInString) { //there are TWO \ in the stream - // where only one is correct + // where only one is correct withoutUnicodePtr--; } } @@ -871,8 +917,8 @@ public class Scanner implements IScanner, ITerminalSymbols { // } } } catch (IndexOutOfBoundsException e) { -// reset end position for error reporting - currentPosition-=2; + // reset end position for error reporting + currentPosition -= 2; throw new InvalidInputException(UNTERMINATED_STRING); } catch (InvalidInputException e) { if (e.getMessage().equals(INVALID_ESCAPE)) { @@ -892,16 +938,16 @@ public class Scanner implements IScanner, ITerminalSymbols { throw e; // rethrow } if (checkNonExternalizedStringLiterals) { // check for presence of NLS tags - // //$NON-NLS-?$ where ? is an - // int. + // //$NON-NLS-?$ where ? is an + // int. if (currentLine == null) { currentLine = new NLSLine(); lines.add(currentLine); } - currentLine.add(new StringLiteral(getCurrentTokenSourceString(), - startPosition, currentPosition - 1)); + currentLine.add(new StringLiteral(getCurrentTokenSourceString(), startPosition, currentPosition - 1)); } } + public void consumeStringConstant() throws InvalidInputException { try { // consume next character @@ -943,15 +989,13 @@ public class Scanner implements IScanner, ITerminalSymbols { escapeSize = currentPosition - escapeSize; if (withoutUnicodePtr == 0) { //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - escapeSize - 1 - - startPosition; - System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, - withoutUnicodePtr); + withoutUnicodePtr = currentPosition - escapeSize - 1 - startPosition; + System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, withoutUnicodePtr); withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } else { //overwrite the / in the buffer withoutUnicodeBuffer[withoutUnicodePtr] = currentCharacter; if (backSlashAsUnicodeInString) { //there are TWO \ in the stream - // where only one is correct + // where only one is correct withoutUnicodePtr--; } } @@ -970,7 +1014,7 @@ public class Scanner implements IScanner, ITerminalSymbols { } } catch (IndexOutOfBoundsException e) { // reset end position for error reporting - currentPosition-=2; + currentPosition -= 2; throw new InvalidInputException(UNTERMINATED_STRING); } catch (InvalidInputException e) { if (e.getMessage().equals(INVALID_ESCAPE)) { @@ -990,16 +1034,16 @@ public class Scanner implements IScanner, ITerminalSymbols { throw e; // rethrow } if (checkNonExternalizedStringLiterals) { // check for presence of NLS tags - // //$NON-NLS-?$ where ? is an - // int. + // //$NON-NLS-?$ where ? is an + // int. if (currentLine == null) { currentLine = new NLSLine(); lines.add(currentLine); } - currentLine.add(new StringLiteral(getCurrentTokenSourceString(), - startPosition, currentPosition - 1)); + currentLine.add(new StringLiteral(getCurrentTokenSourceString(), startPosition, currentPosition - 1)); } } + public void consumeStringLiteral() throws InvalidInputException { try { // consume next character @@ -1041,15 +1085,13 @@ public class Scanner implements IScanner, ITerminalSymbols { escapeSize = currentPosition - escapeSize; if (withoutUnicodePtr == 0) { //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - escapeSize - 1 - - startPosition; - System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, - withoutUnicodePtr); + withoutUnicodePtr = currentPosition - escapeSize - 1 - startPosition; + System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, withoutUnicodePtr); withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } else { //overwrite the / in the buffer withoutUnicodeBuffer[withoutUnicodePtr] = currentCharacter; if (backSlashAsUnicodeInString) { //there are TWO \ in the stream - // where only one is correct + // where only one is correct withoutUnicodePtr--; } } @@ -1067,8 +1109,8 @@ public class Scanner implements IScanner, ITerminalSymbols { // } } } catch (IndexOutOfBoundsException e) { -// reset end position for error reporting - currentPosition-=2; + // reset end position for error reporting + currentPosition -= 2; throw new InvalidInputException(UNTERMINATED_STRING); } catch (InvalidInputException e) { if (e.getMessage().equals(INVALID_ESCAPE)) { @@ -1088,16 +1130,16 @@ public class Scanner implements IScanner, ITerminalSymbols { throw e; // rethrow } if (checkNonExternalizedStringLiterals) { // check for presence of NLS tags - // //$NON-NLS-?$ where ? is an - // int. + // //$NON-NLS-?$ where ? is an + // int. if (currentLine == null) { currentLine = new NLSLine(); lines.add(currentLine); } - currentLine.add(new StringLiteral(getCurrentTokenSourceString(), - startPosition, currentPosition - 1)); + currentLine.add(new StringLiteral(getCurrentTokenSourceString(), startPosition, currentPosition - 1)); } } + public int getNextToken() throws InvalidInputException { if (!phpMode) { return getInlinedHTML(currentPosition); @@ -1121,52 +1163,49 @@ public class Scanner implements IScanner, ITerminalSymbols { currentCharacter = source[currentPosition++]; if (currentCharacter == encapsedChar) { switch (currentCharacter) { - case '`' : - return TokenNameEncapsedString0; - case '\'' : - return TokenNameEncapsedString1; - case '"' : - return TokenNameEncapsedString2; + case '`': + return TokenNameEncapsedString0; + case '\'': + return TokenNameEncapsedString1; + case '"': + return TokenNameEncapsedString2; } } while (currentCharacter != encapsedChar) { /** ** in PHP \r and \n are valid in string literals *** */ switch (currentCharacter) { - case '\\' : - int escapeSize = currentPosition; - boolean backSlashAsUnicodeInString = unicodeAsBackSlash; - //scanEscapeCharacter make a side effect on this value and - // we need the previous value few lines down this one - scanDoubleQuotedEscapeCharacter(); - escapeSize = currentPosition - escapeSize; - if (withoutUnicodePtr == 0) { - //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - escapeSize - 1 - - startPosition; - System.arraycopy(source, startPosition, - withoutUnicodeBuffer, 1, withoutUnicodePtr); - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } else { //overwrite the / in the buffer - withoutUnicodeBuffer[withoutUnicodePtr] = currentCharacter; - if (backSlashAsUnicodeInString) { //there are TWO \ in - withoutUnicodePtr--; - } - } - break; - case '$' : - if (isPHPIdentifierStart(source[currentPosition]) - || source[currentPosition] == '{') { - currentPosition--; - encapsedStringStack.push(new Character('$')); - return TokenNameSTRING; - } - break; - case '{' : - if (source[currentPosition] == '$') { // CURLY_OPEN - currentPosition--; - encapsedStringStack.push(new Character('$')); - return TokenNameSTRING; + case '\\': + int escapeSize = currentPosition; + boolean backSlashAsUnicodeInString = unicodeAsBackSlash; + //scanEscapeCharacter make a side effect on this value and + // we need the previous value few lines down this one + scanDoubleQuotedEscapeCharacter(); + escapeSize = currentPosition - escapeSize; + if (withoutUnicodePtr == 0) { + //buffer all the entries that have been left aside.... + withoutUnicodePtr = currentPosition - escapeSize - 1 - startPosition; + System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, withoutUnicodePtr); + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + } else { //overwrite the / in the buffer + withoutUnicodeBuffer[withoutUnicodePtr] = currentCharacter; + if (backSlashAsUnicodeInString) { //there are TWO \ in + withoutUnicodePtr--; } + } + break; + case '$': + if (isPHPIdentifierStart(source[currentPosition]) || source[currentPosition] == '{') { + currentPosition--; + encapsedStringStack.push(new Character('$')); + return TokenNameSTRING; + } + break; + case '{': + if (source[currentPosition] == '$') { // CURLY_OPEN + currentPosition--; + encapsedStringStack.push(new Character('$')); + return TokenNameSTRING; + } } // consume next character unicodeAsBackSlash = false; @@ -1185,69 +1224,68 @@ public class Scanner implements IScanner, ITerminalSymbols { currentCharacter = source[currentPosition++]; if (encapsedChar == '$') { switch (currentCharacter) { - case '\\' : - currentCharacter = source[currentPosition++]; - return TokenNameSTRING; - case '{' : - if (encapsedChar == '$') { - if (getNextChar('$')) - return TokenNameLBRACE_DOLLAR; - } - return TokenNameLBRACE; - case '}' : - return TokenNameRBRACE; - case '[' : - return TokenNameLBRACKET; - case ']' : - return TokenNameRBRACKET; - case '\'' : - if (tokenizeStrings) { - consumeStringConstant(); - return TokenNameStringSingleQuote; - } - return TokenNameEncapsedString1; - case '"' : - return TokenNameEncapsedString2; - case '`' : - if (tokenizeStrings) { - consumeStringInterpolated(); - return TokenNameStringInterpolated; - } - return TokenNameEncapsedString0; - case '-' : - if (getNextChar('>')) - return TokenNameMINUS_GREATER; - return TokenNameSTRING; - default : - if (currentCharacter == '$') { - int oldPosition = currentPosition; - try { - currentCharacter = source[currentPosition++]; - if (currentCharacter == '{') { - return TokenNameDOLLAR_LBRACE; - } - if (isPHPIdentifierStart(currentCharacter)) { - return scanIdentifierOrKeyword(true); - } else { - currentPosition = oldPosition; - return TokenNameSTRING; - } - } catch (IndexOutOfBoundsException e) { + case '\\': + currentCharacter = source[currentPosition++]; + return TokenNameSTRING; + case '{': + if (encapsedChar == '$') { + if (getNextChar('$')) + return TokenNameLBRACE_DOLLAR; + } + return TokenNameLBRACE; + case '}': + return TokenNameRBRACE; + case '[': + return TokenNameLBRACKET; + case ']': + return TokenNameRBRACKET; + case '\'': + if (tokenizeStrings) { + consumeStringConstant(); + return TokenNameStringSingleQuote; + } + return TokenNameEncapsedString1; + case '"': + return TokenNameEncapsedString2; + case '`': + if (tokenizeStrings) { + consumeStringInterpolated(); + return TokenNameStringInterpolated; + } + return TokenNameEncapsedString0; + case '-': + if (getNextChar('>')) + return TokenNameMINUS_GREATER; + return TokenNameSTRING; + default: + if (currentCharacter == '$') { + int oldPosition = currentPosition; + try { + currentCharacter = source[currentPosition++]; + if (currentCharacter == '{') { + return TokenNameDOLLAR_LBRACE; + } + if (isPHPIdentifierStart(currentCharacter)) { + return scanIdentifierOrKeyword(true); + } else { currentPosition = oldPosition; return TokenNameSTRING; } + } catch (IndexOutOfBoundsException e) { + currentPosition = oldPosition; + return TokenNameSTRING; } - if (isPHPIdentifierStart(currentCharacter)) - return scanIdentifierOrKeyword(false); - if (Character.isDigit(currentCharacter)) - return scanNumber(false); - return TokenNameERROR; + } + if (isPHPIdentifierStart(currentCharacter)) + return scanIdentifierOrKeyword(false); + if (Character.isDigit(currentCharacter)) + return scanNumber(false); + return TokenNameERROR; } } // boolean isWhiteSpace; - - while ((currentCharacter == ' ') - || Character.isWhitespace(currentCharacter)) { + + while ((currentCharacter == ' ') || Character.isWhitespace(currentCharacter)) { startPosition = currentPosition; currentCharacter = source[currentPosition++]; // if (((currentCharacter = source[currentPosition++]) == '\\') @@ -1277,374 +1315,394 @@ public class Scanner implements IScanner, ITerminalSymbols { return TokenNameEOF; // ---------Identify the next token------------- switch (currentCharacter) { - case '(' : - return getCastOrParen(); - case ')' : - return TokenNameRPAREN; - case '{' : - return TokenNameLBRACE; - case '}' : - return TokenNameRBRACE; - case '[' : - return TokenNameLBRACKET; - case ']' : - return TokenNameRBRACKET; - case ';' : - return TokenNameSEMICOLON; - case ',' : - return TokenNameCOMMA; - case '.' : - if (getNextChar('=')) - return TokenNameDOT_EQUAL; - if (getNextCharAsDigit()) - return scanNumber(true); - return TokenNameDOT; - case '+' : - { - int test; - if ((test = getNextChar('+', '=')) == 0) - return TokenNamePLUS_PLUS; - if (test > 0) - return TokenNamePLUS_EQUAL; - return TokenNamePLUS; - } - case '-' : - { - int test; - if ((test = getNextChar('-', '=')) == 0) - return TokenNameMINUS_MINUS; - if (test > 0) - return TokenNameMINUS_EQUAL; - if (getNextChar('>')) - return TokenNameMINUS_GREATER; - return TokenNameMINUS; - } - case '~' : - if (getNextChar('=')) - return TokenNameTWIDDLE_EQUAL; - return TokenNameTWIDDLE; - case '!' : + case '(': + return getCastOrParen(); + case ')': + return TokenNameRPAREN; + case '{': + return TokenNameLBRACE; + case '}': + return TokenNameRBRACE; + case '[': + return TokenNameLBRACKET; + case ']': + return TokenNameRBRACKET; + case ';': + return TokenNameSEMICOLON; + case ',': + return TokenNameCOMMA; + case '.': + if (getNextChar('=')) + return TokenNameDOT_EQUAL; + if (getNextCharAsDigit()) + return scanNumber(true); + return TokenNameDOT; + case '+': { + int test; + if ((test = getNextChar('+', '=')) == 0) + return TokenNamePLUS_PLUS; + if (test > 0) + return TokenNamePLUS_EQUAL; + return TokenNamePLUS; + } + case '-': { + int test; + if ((test = getNextChar('-', '=')) == 0) + return TokenNameMINUS_MINUS; + if (test > 0) + return TokenNameMINUS_EQUAL; + if (getNextChar('>')) + return TokenNameMINUS_GREATER; + return TokenNameMINUS; + } + case '~': + if (getNextChar('=')) + return TokenNameTWIDDLE_EQUAL; + return TokenNameTWIDDLE; + case '!': + if (getNextChar('=')) { if (getNextChar('=')) { - if (getNextChar('=')) { - return TokenNameNOT_EQUAL_EQUAL; - } - return TokenNameNOT_EQUAL; + return TokenNameNOT_EQUAL_EQUAL; } - return TokenNameNOT; - case '*' : - if (getNextChar('=')) - return TokenNameMULTIPLY_EQUAL; - return TokenNameMULTIPLY; - case '%' : + return TokenNameNOT_EQUAL; + } + return TokenNameNOT; + case '*': + if (getNextChar('=')) + return TokenNameMULTIPLY_EQUAL; + return TokenNameMULTIPLY; + case '%': + if (getNextChar('=')) + return TokenNameREMAINDER_EQUAL; + return TokenNameREMAINDER; + case '<': { + int oldPosition = currentPosition; + try { + currentCharacter = source[currentPosition++]; + } catch (IndexOutOfBoundsException e) { + currentPosition = oldPosition; + return TokenNameLESS; + } + switch (currentCharacter) { + case '=': + return TokenNameLESS_EQUAL; + case '>': + return TokenNameNOT_EQUAL; + case '<': if (getNextChar('=')) - return TokenNameREMAINDER_EQUAL; - return TokenNameREMAINDER; - case '<' : - { - int oldPosition = currentPosition; - try { + return TokenNameLEFT_SHIFT_EQUAL; + if (getNextChar('<')) { + currentCharacter = source[currentPosition++]; + while (Character.isWhitespace(currentCharacter)) { currentCharacter = source[currentPosition++]; - } catch (IndexOutOfBoundsException e) { - currentPosition = oldPosition; - return TokenNameLESS; } - switch (currentCharacter) { - case '=' : - return TokenNameLESS_EQUAL; - case '>' : - return TokenNameNOT_EQUAL; - case '<' : - if (getNextChar('=')) - return TokenNameLEFT_SHIFT_EQUAL; - if (getNextChar('<')) { - currentCharacter = source[currentPosition++]; - while (Character.isWhitespace(currentCharacter)) { - currentCharacter = source[currentPosition++]; - } - int heredocStart = currentPosition - 1; - int heredocLength = 0; - if (isPHPIdentifierStart(currentCharacter)) { - currentCharacter = source[currentPosition++]; - } else { - return TokenNameERROR; - } - while (isPHPIdentifierPart(currentCharacter)) { - currentCharacter = source[currentPosition++]; - } - heredocLength = currentPosition - heredocStart - 1; - // heredoc end-tag determination - boolean endTag = true; - char ch; - do { - ch = source[currentPosition++]; - if (ch == '\r' || ch == '\n') { - if (recordLineSeparator) { - pushLineSeparator(); - } else { - currentLine = null; - } - for (int i = 0; i < heredocLength; i++) { - if (source[currentPosition + i] != source[heredocStart - + i]) { - endTag = false; - break; - } - } - if (endTag) { - currentPosition += heredocLength - 1; - currentCharacter = source[currentPosition++]; - break; // do...while loop - } else { - endTag = true; - } - } - } while (true); - return TokenNameHEREDOC; - } - return TokenNameLEFT_SHIFT; + int heredocStart = currentPosition - 1; + int heredocLength = 0; + if (isPHPIdentifierStart(currentCharacter)) { + currentCharacter = source[currentPosition++]; + } else { + return TokenNameERROR; } - currentPosition = oldPosition; - return TokenNameLESS; - } - case '>' : - { - int test; - if ((test = getNextChar('=', '>')) == 0) - return TokenNameGREATER_EQUAL; - if (test > 0) { - if ((test = getNextChar('=', '>')) == 0) - return TokenNameRIGHT_SHIFT_EQUAL; - return TokenNameRIGHT_SHIFT; + while (isPHPIdentifierPart(currentCharacter)) { + currentCharacter = source[currentPosition++]; } - return TokenNameGREATER; + heredocLength = currentPosition - heredocStart - 1; + // heredoc end-tag determination + boolean endTag = true; + char ch; + do { + ch = source[currentPosition++]; + if (ch == '\r' || ch == '\n') { + if (recordLineSeparator) { + pushLineSeparator(); + } else { + currentLine = null; + } + for (int i = 0; i < heredocLength; i++) { + if (source[currentPosition + i] != source[heredocStart + i]) { + endTag = false; + break; + } + } + if (endTag) { + currentPosition += heredocLength - 1; + currentCharacter = source[currentPosition++]; + break; // do...while loop + } else { + endTag = true; + } + } + } while (true); + return TokenNameHEREDOC; } - case '=' : + return TokenNameLEFT_SHIFT; + } + currentPosition = oldPosition; + return TokenNameLESS; + } + case '>': { + int test; + if ((test = getNextChar('=', '>')) == 0) + return TokenNameGREATER_EQUAL; + if (test > 0) { + if ((test = getNextChar('=', '>')) == 0) + return TokenNameRIGHT_SHIFT_EQUAL; + return TokenNameRIGHT_SHIFT; + } + return TokenNameGREATER; + } + case '=': + if (getNextChar('=')) { if (getNextChar('=')) { - if (getNextChar('=')) { - return TokenNameEQUAL_EQUAL_EQUAL; - } - return TokenNameEQUAL_EQUAL; - } - if (getNextChar('>')) - return TokenNameEQUAL_GREATER; - return TokenNameEQUAL; - case '&' : - { - int test; - if ((test = getNextChar('&', '=')) == 0) - return TokenNameAND_AND; - if (test > 0) - return TokenNameAND_EQUAL; - return TokenNameAND; + return TokenNameEQUAL_EQUAL_EQUAL; } - case '|' : - { - int test; - if ((test = getNextChar('|', '=')) == 0) - return TokenNameOR_OR; - if (test > 0) - return TokenNameOR_EQUAL; - return TokenNameOR; + return TokenNameEQUAL_EQUAL; + } + if (getNextChar('>')) + return TokenNameEQUAL_GREATER; + return TokenNameEQUAL; + case '&': { + int test; + if ((test = getNextChar('&', '=')) == 0) + return TokenNameAND_AND; + if (test > 0) + return TokenNameAND_EQUAL; + return TokenNameAND; + } + case '|': { + int test; + if ((test = getNextChar('|', '=')) == 0) + return TokenNameOR_OR; + if (test > 0) + return TokenNameOR_EQUAL; + return TokenNameOR; + } + case '^': + if (getNextChar('=')) + return TokenNameXOR_EQUAL; + return TokenNameXOR; + case '?': + if (getNextChar('>')) { + phpMode = false; + if (currentPosition == source.length) { + phpMode = true; + return TokenNameINLINE_HTML; } - case '^' : - if (getNextChar('=')) - return TokenNameXOR_EQUAL; - return TokenNameXOR; - case '?' : - if (getNextChar('>')) { - phpMode = false; - if (currentPosition == source.length) { - phpMode = true; - return TokenNameINLINE_HTML; + return getInlinedHTML(currentPosition - 2); + } + return TokenNameQUESTION; + case ':': + if (getNextChar(':')) + return TokenNamePAAMAYIM_NEKUDOTAYIM; + return TokenNameCOLON; + case '@': + return TokenNameAT; + case '\'': + consumeStringConstant(); + return TokenNameStringSingleQuote; + case '"': + if (tokenizeStrings) { + consumeStringLiteral(); + return TokenNameStringDoubleQuote; + } + return TokenNameEncapsedString2; + case '`': + if (tokenizeStrings) { + consumeStringInterpolated(); + return TokenNameStringInterpolated; + } + return TokenNameEncapsedString0; + case '#': + case '/': { + char startChar = currentCharacter; + if (getNextChar('=')) { + return TokenNameDIVIDE_EQUAL; + } + int test; + if ((startChar == '#') || (test = getNextChar('/', '*')) == 0) { + //line comment + this.lastCommentLinePosition = this.currentPosition; + int endPositionForLineComment = 0; + try { //get the next char + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) + // == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // } + // if ((c1 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c1 < 0 + // || (c2 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c2 < 0 + // || (c3 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c3 < 0 + // || (c4 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c4 < 0) { + // throw new + // InvalidInputException(INVALID_UNICODE_ESCAPE); + // } else { + // currentCharacter = + // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // } + // } + //handle the \\u case manually into comment + // if (currentCharacter == '\\') { + // if (source[currentPosition] == '\\') + // currentPosition++; + // } //jump over the \\ + boolean isUnicode = false; + while (currentCharacter != '\r' && currentCharacter != '\n') { + this.lastCommentLinePosition = this.currentPosition; + if (currentCharacter == '?') { + if (getNextChar('>')) { + startPosition = currentPosition - 2; + phpMode = false; + return TokenNameINLINE_HTML; + } + } + //get the next char + isUnicode = false; + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) + // == '\\') + // && (source[currentPosition] == 'u')) { + // isUnicode = true; + // //-------------unicode traitement ------------ + // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // } + // if ((c1 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c1 < 0 + // || (c2 = + // Character.getNumericValue( + // source[currentPosition++])) + // > 15 + // || c2 < 0 + // || (c3 = + // Character.getNumericValue( + // source[currentPosition++])) + // > 15 + // || c3 < 0 + // || (c4 = + // Character.getNumericValue( + // source[currentPosition++])) + // > 15 + // || c4 < 0) { + // throw new + // InvalidInputException(INVALID_UNICODE_ESCAPE); + // } else { + // currentCharacter = + // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // } + // } + //handle the \\u case manually into comment + // if (currentCharacter == '\\') { + // if (source[currentPosition] == '\\') + // currentPosition++; + // } //jump over the \\ } - return getInlinedHTML(currentPosition - 2); - } - return TokenNameQUESTION; - case ':' : - if (getNextChar(':')) - return TokenNamePAAMAYIM_NEKUDOTAYIM; - return TokenNameCOLON; - case '@' : - return TokenNameAT; - case '\'' : - consumeStringConstant(); - return TokenNameStringSingleQuote; - case '"' : - if (tokenizeStrings) { - consumeStringLiteral(); - return TokenNameStringDoubleQuote; - } - return TokenNameEncapsedString2; - case '`' : - if (tokenizeStrings) { - consumeStringInterpolated(); - return TokenNameStringInterpolated; - } - return TokenNameEncapsedString0; - case '#' : - case '/' : - { - char startChar = currentCharacter; - if (getNextChar('=')) { - return TokenNameDIVIDE_EQUAL; + if (isUnicode) { + endPositionForLineComment = currentPosition - 6; + } else { + endPositionForLineComment = currentPosition - 1; } - int test; - if ((startChar == '#') || (test = getNextChar('/', '*')) == 0) { - //line comment - this.lastCommentLinePosition = this.currentPosition; - int endPositionForLineComment = 0; - try { //get the next char - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) - // == '\\') - // && (source[currentPosition] == 'u')) { - // //-------------unicode traitement ------------ - // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; - // currentPosition++; - // while (source[currentPosition] == 'u') { - // currentPosition++; - // } - // if ((c1 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c1 < 0 - // || (c2 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c2 < 0 - // || (c3 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c3 < 0 - // || (c4 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c4 < 0) { - // throw new - // InvalidInputException(INVALID_UNICODE_ESCAPE); - // } else { - // currentCharacter = - // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - // } - // } - //handle the \\u case manually into comment - // if (currentCharacter == '\\') { - // if (source[currentPosition] == '\\') - // currentPosition++; - // } //jump over the \\ - boolean isUnicode = false; - while (currentCharacter != '\r' && currentCharacter != '\n') { - this.lastCommentLinePosition = this.currentPosition; - if (currentCharacter == '?') { - if (getNextChar('>')) { - startPosition = currentPosition - 2; - phpMode = false; - return TokenNameINLINE_HTML; - } - } - //get the next char - isUnicode = false; - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) - // == '\\') - // && (source[currentPosition] == 'u')) { - // isUnicode = true; - // //-------------unicode traitement ------------ - // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; - // currentPosition++; - // while (source[currentPosition] == 'u') { - // currentPosition++; - // } - // if ((c1 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c1 < 0 - // || (c2 = - // Character.getNumericValue( - // source[currentPosition++])) - // > 15 - // || c2 < 0 - // || (c3 = - // Character.getNumericValue( - // source[currentPosition++])) - // > 15 - // || c3 < 0 - // || (c4 = - // Character.getNumericValue( - // source[currentPosition++])) - // > 15 - // || c4 < 0) { - // throw new - // InvalidInputException(INVALID_UNICODE_ESCAPE); - // } else { - // currentCharacter = - // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - // } - // } - //handle the \\u case manually into comment - // if (currentCharacter == '\\') { - // if (source[currentPosition] == '\\') - // currentPosition++; - // } //jump over the \\ - } + // recordComment(false); + recordComment(TokenNameCOMMENT_LINE); + if (this.taskTags != null) + checkTaskTag(this.startPosition, this.currentPosition); + if ((currentCharacter == '\r') || (currentCharacter == '\n')) { + checkNonExternalizeString(); + if (recordLineSeparator) { if (isUnicode) { - endPositionForLineComment = currentPosition - 6; + pushUnicodeLineSeparator(); } else { - endPositionForLineComment = currentPosition - 1; - } -// recordComment(false); - recordComment(TokenNameCOMMENT_LINE); - if (this.taskTags != null) checkTaskTag(this.startPosition, this.currentPosition); - if ((currentCharacter == '\r') - || (currentCharacter == '\n')) { - checkNonExternalizeString(); - if (recordLineSeparator) { - if (isUnicode) { - pushUnicodeLineSeparator(); - } else { - pushLineSeparator(); - } - } else { - currentLine = null; - } - } - if (tokenizeComments) { - if (!isUnicode) { - currentPosition = endPositionForLineComment; - // reset one character behind - } - return TokenNameCOMMENT_LINE; - } - } catch (IndexOutOfBoundsException e) { //an eof will them - // be generated - if (tokenizeComments) { - currentPosition--; - // reset one character behind - return TokenNameCOMMENT_LINE; + pushLineSeparator(); } + } else { + currentLine = null; } - break; } - if (test > 0) { - //traditional and annotation comment - boolean isJavadoc = false, star = false; - // consume next character - unicodeAsBackSlash = false; - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) == - // '\\') - // && (source[currentPosition] == 'u')) { - // getNextUnicodeChar(); - // } else { - // if (withoutUnicodePtr != 0) { - // withoutUnicodeBuffer[++withoutUnicodePtr] = - // currentCharacter; - // } - // } - if (currentCharacter == '*') { - isJavadoc = true; - star = true; + if (tokenizeComments) { + if (!isUnicode) { + currentPosition = endPositionForLineComment; + // reset one character behind } + return TokenNameCOMMENT_LINE; + } + } catch (IndexOutOfBoundsException e) { //an eof will them + // be generated + if (tokenizeComments) { + currentPosition--; + // reset one character behind + return TokenNameCOMMENT_LINE; + } + } + break; + } + if (test > 0) { + //traditional and annotation comment + boolean isJavadoc = false, star = false; + // consume next character + unicodeAsBackSlash = false; + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == + // '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = + // currentCharacter; + // } + // } + if (currentCharacter == '*') { + isJavadoc = true; + star = true; + } + if ((currentCharacter == '\r') || (currentCharacter == '\n')) { + checkNonExternalizeString(); + if (recordLineSeparator) { + pushLineSeparator(); + } else { + currentLine = null; + } + } + try { //get the next char + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) + // == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // getNextUnicodeChar(); + // } + //handle the \\u case manually into comment + // if (currentCharacter == '\\') { + // if (source[currentPosition] == '\\') + // currentPosition++; + // //jump over the \\ + // } + // empty comment is not a javadoc /**/ + if (currentCharacter == '/') { + isJavadoc = false; + } + //loop until end of comment */ + while ((currentCharacter != '/') || (!star)) { if ((currentCharacter == '\r') || (currentCharacter == '\n')) { checkNonExternalizeString(); if (recordLineSeparator) { @@ -1653,98 +1711,69 @@ public class Scanner implements IScanner, ITerminalSymbols { currentLine = null; } } - try { //get the next char - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) - // == '\\') - // && (source[currentPosition] == 'u')) { - // //-------------unicode traitement ------------ - // getNextUnicodeChar(); - // } - //handle the \\u case manually into comment - // if (currentCharacter == '\\') { - // if (source[currentPosition] == '\\') - // currentPosition++; - // //jump over the \\ - // } - // empty comment is not a javadoc /**/ - if (currentCharacter == '/') { - isJavadoc = false; - } - //loop until end of comment */ - while ((currentCharacter != '/') || (!star)) { - if ((currentCharacter == '\r') - || (currentCharacter == '\n')) { - checkNonExternalizeString(); - if (recordLineSeparator) { - pushLineSeparator(); - } else { - currentLine = null; - } - } - star = currentCharacter == '*'; - //get next char - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) - // == '\\') - // && (source[currentPosition] == 'u')) { - // //-------------unicode traitement ------------ - // getNextUnicodeChar(); - // } - //handle the \\u case manually into comment - // if (currentCharacter == '\\') { - // if (source[currentPosition] == '\\') - // currentPosition++; - // } //jump over the \\ - } - //recordComment(isJavadoc); - if (isJavadoc) { - recordComment(TokenNameCOMMENT_PHPDOC); - } else { - recordComment(TokenNameCOMMENT_BLOCK); - } - - if (tokenizeComments) { - if (isJavadoc) - return TokenNameCOMMENT_PHPDOC; - return TokenNameCOMMENT_BLOCK; - } - } catch (IndexOutOfBoundsException e) { -// reset end position for error reporting - currentPosition-=2; - throw new InvalidInputException(UNTERMINATED_COMMENT); - } - break; + star = currentCharacter == '*'; + //get next char + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) + // == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // getNextUnicodeChar(); + // } + //handle the \\u case manually into comment + // if (currentCharacter == '\\') { + // if (source[currentPosition] == '\\') + // currentPosition++; + // } //jump over the \\ + } + //recordComment(isJavadoc); + if (isJavadoc) { + recordComment(TokenNameCOMMENT_PHPDOC); + } else { + recordComment(TokenNameCOMMENT_BLOCK); } - return TokenNameDIVIDE; + + if (tokenizeComments) { + if (isJavadoc) + return TokenNameCOMMENT_PHPDOC; + return TokenNameCOMMENT_BLOCK; + } + } catch (IndexOutOfBoundsException e) { + // reset end position for error reporting + currentPosition -= 2; + throw new InvalidInputException(UNTERMINATED_COMMENT); } - case '\u001a' : - if (atEnd()) - return TokenNameEOF; - //the atEnd may not be if - // source is only some part of a real (external) stream - throw new InvalidInputException("Ctrl-Z"); //$NON-NLS-1$ - default : - if (currentCharacter == '$') { - int oldPosition = currentPosition; - try { - currentCharacter = source[currentPosition++]; - if (isPHPIdentifierStart(currentCharacter)) { - return scanIdentifierOrKeyword(true); - } else { - currentPosition = oldPosition; - return TokenNameDOLLAR; - } - } catch (IndexOutOfBoundsException e) { + break; + } + return TokenNameDIVIDE; + } + case '\u001a': + if (atEnd()) + return TokenNameEOF; + //the atEnd may not be if + // source is only some part of a real (external) stream + throw new InvalidInputException("Ctrl-Z"); //$NON-NLS-1$ + default: + if (currentCharacter == '$') { + int oldPosition = currentPosition; + try { + currentCharacter = source[currentPosition++]; + if (isPHPIdentifierStart(currentCharacter)) { + return scanIdentifierOrKeyword(true); + } else { currentPosition = oldPosition; return TokenNameDOLLAR; } + } catch (IndexOutOfBoundsException e) { + currentPosition = oldPosition; + return TokenNameDOLLAR; } - if (isPHPIdentifierStart(currentCharacter)) - return scanIdentifierOrKeyword(false); - if (Character.isDigit(currentCharacter)) - return scanNumber(false); - return TokenNameERROR; + } + if (isPHPIdentifierStart(currentCharacter)) + return scanIdentifierOrKeyword(false); + if (Character.isDigit(currentCharacter)) + return scanNumber(false); + return TokenNameERROR; } } } //-----------------end switch while try-------------------- @@ -1753,42 +1782,43 @@ public class Scanner implements IScanner, ITerminalSymbols { } return TokenNameEOF; } - + private int getInlinedHTML(int start) throws InvalidInputException { - int token = getInlinedHTMLToken(start); - if (token == TokenNameINLINE_HTML) { -// Stack stack = new Stack(); -// // scan html for errors -// Source inlinedHTMLSource = new Source(new String(source, startPosition, currentPosition - startPosition)); -// int lastPHPEndPos=0; -// for (Iterator i=inlinedHTMLSource.getNextTagIterator(0); i.hasNext();) { -// Tag tag=(Tag)i.next(); -// -// if (tag instanceof StartTag) { -// StartTag startTag=(StartTag)tag; -// // System.out.println("startTag: "+tag); -// if (startTag.isServerTag()) { -// // TODO : what to do with a server tag ? -// } else { -// // do whatever with HTML start tag -// // use startTag.getElement() to find the element corresponding -// // to this start tag which may be useful if you implement code -// // folding etc -// stack.push(startTag); -// } -// } else { -// EndTag endTag=(EndTag)tag; -// StartTag stag = (StartTag) stack.peek(); -//// System.out.println("endTag: "+tag); -// // do whatever with HTML end tag. -// } -// } - } - return token; + int token = getInlinedHTMLToken(start); + if (token == TokenNameINLINE_HTML) { + // Stack stack = new Stack(); + // // scan html for errors + // Source inlinedHTMLSource = new Source(new String(source, startPosition, currentPosition - startPosition)); + // int lastPHPEndPos=0; + // for (Iterator i=inlinedHTMLSource.getNextTagIterator(0); i.hasNext();) { + // Tag tag=(Tag)i.next(); + // + // if (tag instanceof StartTag) { + // StartTag startTag=(StartTag)tag; + // // System.out.println("startTag: "+tag); + // if (startTag.isServerTag()) { + // // TODO : what to do with a server tag ? + // } else { + // // do whatever with HTML start tag + // // use startTag.getElement() to find the element corresponding + // // to this start tag which may be useful if you implement code + // // folding etc + // stack.push(startTag); + // } + // } else { + // EndTag endTag=(EndTag)tag; + // StartTag stag = (StartTag) stack.peek(); + //// System.out.println("endTag: "+tag); + // // do whatever with HTML end tag. + // } + // } + } + return token; } + /** - * @return @throws - * InvalidInputException + * @return + * @throws InvalidInputException */ private int getInlinedHTMLToken(int start) throws InvalidInputException { // int htmlPosition = start; @@ -1803,22 +1833,34 @@ public class Scanner implements IScanner, ITerminalSymbols { if (currentCharacter == '<') { if (getNextChar('?')) { currentCharacter = source[currentPosition++]; - if ((currentCharacter == ' ') - || Character.isWhitespace(currentCharacter)) { + if ((currentCharacter == ' ') || Character.isWhitespace(currentCharacter)) { // = 0) { test = getNextChar('P', 'p'); if (test >= 0) { // ': + if (previousCharInLine == '?') { + // update the scanner's current Position in the source + currentPosition = currentPositionInLine; + // use as "dummy" token + return TokenNameEOF; + } + break; + case '\"': + if (doubleQuotedStringActive) { + if (previousCharInLine != '\\') { + doubleQuotedStringActive = false; + } + } else { + if (!singleQuotedStringActive) { + doubleQuotedStringActive = true; + } + } + break; + case '\'': + if (singleQuotedStringActive) { + if (previousCharInLine != '\\') { + singleQuotedStringActive = false; + } + } else { + if (!doubleQuotedStringActive) { + singleQuotedStringActive = true; + } + } + break; + case '\n': + phpMode = true; + return TokenNameINLINE_HTML; + case '#': + if (!singleQuotedStringActive && !doubleQuotedStringActive) { + phpMode = true; + return TokenNameINLINE_HTML; + } + break; + case '/': + if (previousCharInLine == '/' && !singleQuotedStringActive && !doubleQuotedStringActive) { + phpMode = true; + return TokenNameINLINE_HTML; + } + break; + case '*': + if (previousCharInLine == '/' && !singleQuotedStringActive && !doubleQuotedStringActive) { + phpMode = true; + return TokenNameINLINE_HTML; + } + break; + } + } + } catch (IndexOutOfBoundsException e) { + phpMode = true; + currentPosition = currentPositionInLine; + return TokenNameINLINE_HTML; + } + } + // public final void getNextUnicodeChar() // throws IndexOutOfBoundsException, InvalidInputException { // //VOID @@ -1889,8 +2009,7 @@ public class Scanner implements IScanner, ITerminalSymbols { // unicodeAsBackSlash = currentCharacter == '\\'; // } /* - * Tokenize a method body, assuming that curly brackets are properly - * balanced. + * Tokenize a method body, assuming that curly brackets are properly balanced. */ public final void jumpOverMethodBody() { this.wasAcr = false; @@ -1906,306 +2025,303 @@ public class Scanner implements IScanner, ITerminalSymbols { // && (source[currentPosition] == 'u')) { // isWhiteSpace = jumpOverUnicodeWhiteSpace(); // } else { - if (recordLineSeparator - && ((currentCharacter == '\r') || (currentCharacter == '\n'))) + if (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n'))) pushLineSeparator(); isWhiteSpace = Character.isWhitespace(currentCharacter); // } } while (isWhiteSpace); // -------consume token until } is found--------- switch (currentCharacter) { - case '{' : - found++; - break; - case '}' : - found--; - if (found == 0) - return; - break; - case '\'' : - { - boolean test; - test = getNextChar('\\'); - if (test) { + case '{': + found++; + break; + case '}': + found--; + if (found == 0) + return; + break; + case '\'': { + boolean test; + test = getNextChar('\\'); + if (test) { + try { + scanDoubleQuotedEscapeCharacter(); + } catch (InvalidInputException ex) { + } + ; + } else { + // try { // consume next character + unicodeAsBackSlash = false; + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + if (withoutUnicodePtr != 0) { + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + } + // } + // } catch (InvalidInputException ex) { + // }; + } + getNextChar('\''); + break; + } + case '"': + try { + // try { // consume next character + unicodeAsBackSlash = false; + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + if (withoutUnicodePtr != 0) { + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + } + // } + // } catch (InvalidInputException ex) { + // }; + while (currentCharacter != '"') { + if (currentCharacter == '\r') { + if (source[currentPosition] == '\n') + currentPosition++; + break; + // the string cannot go further that the line + } + if (currentCharacter == '\n') { + break; + // the string cannot go further that the line + } + if (currentCharacter == '\\') { try { scanDoubleQuotedEscapeCharacter(); } catch (InvalidInputException ex) { - }; - } else { - // try { // consume next character - unicodeAsBackSlash = false; - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) == '\\') - // && (source[currentPosition] == 'u')) { - // getNextUnicodeChar(); - // } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } - // } - // } catch (InvalidInputException ex) { - // }; + ; } - getNextChar('\''); - break; - } - case '"' : - try { - // try { // consume next character + // try { // consume next character unicodeAsBackSlash = false; currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) == '\\') - // && (source[currentPosition] == 'u')) { - // getNextUnicodeChar(); - // } else { + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { if (withoutUnicodePtr != 0) { withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } - // } - // } catch (InvalidInputException ex) { - // }; - while (currentCharacter != '"') { - if (currentCharacter == '\r') { - if (source[currentPosition] == '\n') - currentPosition++; - break; - // the string cannot go further that the line - } - if (currentCharacter == '\n') { - break; - // the string cannot go further that the line - } - if (currentCharacter == '\\') { - try { - scanDoubleQuotedEscapeCharacter(); - } catch (InvalidInputException ex) { - }; - } - // try { // consume next character - unicodeAsBackSlash = false; + // } + // } catch (InvalidInputException ex) { + // }; + } + } catch (IndexOutOfBoundsException e) { + return; + } + break; + case '/': { + int test; + if ((test = getNextChar('/', '*')) == 0) { + //line comment + try { + //get the next char + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == + // '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // } + // if ((c1 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c1 < 0 + // || (c2 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c2 < 0 + // || (c3 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c3 < 0 + // || (c4 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c4 < 0) { + // //error don't care of the value + // currentCharacter = 'A'; + // } //something different from \n and \r + // else { + // currentCharacter = + // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // } + // } + while (currentCharacter != '\r' && currentCharacter != '\n') { + //get the next char currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) == '\\') - // && (source[currentPosition] == 'u')) { - // getNextUnicodeChar(); - // } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } - // } - // } catch (InvalidInputException ex) { - // }; + // if (((currentCharacter = source[currentPosition++]) + // == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // } + // if ((c1 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c1 < 0 + // || (c2 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c2 < 0 + // || (c3 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c3 < 0 + // || (c4 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c4 < 0) { + // //error don't care of the value + // currentCharacter = 'A'; + // } //something different from \n and \r + // else { + // currentCharacter = + // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // } + // } } + if (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n'))) + pushLineSeparator(); } catch (IndexOutOfBoundsException e) { - return; - } + } //an eof will them be generated break; - case '/' : - { - int test; - if ((test = getNextChar('/', '*')) == 0) { - //line comment - try { - //get the next char - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) == - // '\\') - // && (source[currentPosition] == 'u')) { - // //-------------unicode traitement ------------ - // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; - // currentPosition++; - // while (source[currentPosition] == 'u') { - // currentPosition++; - // } - // if ((c1 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c1 < 0 - // || (c2 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c2 < 0 - // || (c3 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c3 < 0 - // || (c4 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c4 < 0) { - // //error don't care of the value - // currentCharacter = 'A'; - // } //something different from \n and \r - // else { - // currentCharacter = - // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - // } - // } - while (currentCharacter != '\r' && currentCharacter != '\n') { - //get the next char - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) - // == '\\') - // && (source[currentPosition] == 'u')) { - // //-------------unicode traitement ------------ - // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; - // currentPosition++; - // while (source[currentPosition] == 'u') { - // currentPosition++; - // } - // if ((c1 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c1 < 0 - // || (c2 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c2 < 0 - // || (c3 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c3 < 0 - // || (c4 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c4 < 0) { - // //error don't care of the value - // currentCharacter = 'A'; - // } //something different from \n and \r - // else { - // currentCharacter = - // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - // } - // } - } - if (recordLineSeparator - && ((currentCharacter == '\r') || (currentCharacter == '\n'))) - pushLineSeparator(); - } catch (IndexOutOfBoundsException e) { - } //an eof will them be generated - break; - } - if (test > 0) { - //traditional and annotation comment - boolean star = false; - // try { // consume next character - unicodeAsBackSlash = false; - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) == '\\') - // && (source[currentPosition] == 'u')) { - // getNextUnicodeChar(); - // } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } - // }; - // } catch (InvalidInputException ex) { - // }; - if (currentCharacter == '*') { - star = true; - } - if (recordLineSeparator - && ((currentCharacter == '\r') || (currentCharacter == '\n'))) + } + if (test > 0) { + //traditional and annotation comment + boolean star = false; + // try { // consume next character + unicodeAsBackSlash = false; + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + if (withoutUnicodePtr != 0) { + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + } + // }; + // } catch (InvalidInputException ex) { + // }; + if (currentCharacter == '*') { + star = true; + } + if (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n'))) + pushLineSeparator(); + try { //get the next char + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == + // '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // } + // if ((c1 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c1 < 0 + // || (c2 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c2 < 0 + // || (c3 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c3 < 0 + // || (c4 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c4 < 0) { + // //error don't care of the value + // currentCharacter = 'A'; + // } //something different from * and / + // else { + // currentCharacter = + // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // } + // } + //loop until end of comment */ + while ((currentCharacter != '/') || (!star)) { + if (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n'))) pushLineSeparator(); - try { //get the next char - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) == - // '\\') - // && (source[currentPosition] == 'u')) { - // //-------------unicode traitement ------------ - // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; - // currentPosition++; - // while (source[currentPosition] == 'u') { - // currentPosition++; - // } - // if ((c1 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c1 < 0 - // || (c2 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c2 < 0 - // || (c3 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c3 < 0 - // || (c4 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c4 < 0) { - // //error don't care of the value - // currentCharacter = 'A'; - // } //something different from * and / - // else { - // currentCharacter = - // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - // } - // } - //loop until end of comment */ - while ((currentCharacter != '/') || (!star)) { - if (recordLineSeparator - && ((currentCharacter == '\r') || (currentCharacter == '\n'))) - pushLineSeparator(); - star = currentCharacter == '*'; - //get next char - currentCharacter = source[currentPosition++]; - // if (((currentCharacter = source[currentPosition++]) - // == '\\') - // && (source[currentPosition] == 'u')) { - // //-------------unicode traitement ------------ - // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; - // currentPosition++; - // while (source[currentPosition] == 'u') { - // currentPosition++; - // } - // if ((c1 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c1 < 0 - // || (c2 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c2 < 0 - // || (c3 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c3 < 0 - // || (c4 = - // Character.getNumericValue(source[currentPosition++])) - // > 15 - // || c4 < 0) { - // //error don't care of the value - // currentCharacter = 'A'; - // } //something different from * and / - // else { - // currentCharacter = - // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - // } - // } - } - } catch (IndexOutOfBoundsException e) { - return; - } - break; + star = currentCharacter == '*'; + //get next char + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) + // == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1 = 0, c2 = 0, c3 = 0, c4 = 0; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // } + // if ((c1 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c1 < 0 + // || (c2 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c2 < 0 + // || (c3 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c3 < 0 + // || (c4 = + // Character.getNumericValue(source[currentPosition++])) + // > 15 + // || c4 < 0) { + // //error don't care of the value + // currentCharacter = 'A'; + // } //something different from * and / + // else { + // currentCharacter = + // (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // } + // } } - break; + } catch (IndexOutOfBoundsException e) { + return; } - default : - if (isPHPIdentifierStart(currentCharacter) - || currentCharacter == '$') { - try { - scanIdentifierOrKeyword((currentCharacter == '$')); - } catch (InvalidInputException ex) { - }; - break; + break; + } + break; + } + default: + if (isPHPIdentifierStart(currentCharacter) || currentCharacter == '$') { + try { + scanIdentifierOrKeyword((currentCharacter == '$')); + } catch (InvalidInputException ex) { } - if (Character.isDigit(currentCharacter)) { - try { - scanNumber(false); - } catch (InvalidInputException ex) { - }; - break; + ; + break; + } + if (Character.isDigit(currentCharacter)) { + try { + scanNumber(false); + } catch (InvalidInputException ex) { } + ; + break; + } } } //-----------------end switch while try-------------------- @@ -2214,6 +2330,7 @@ public class Scanner implements IScanner, ITerminalSymbols { } return; } + // public final boolean jumpOverUnicodeWhiteSpace() // throws InvalidInputException { // //BOOLEAN @@ -2264,78 +2381,81 @@ public class Scanner implements IScanner, ITerminalSymbols { System.arraycopy(lineEnds, 0, copy = new int[linePtr + 1], 0, linePtr + 1); return copy; } + public char[] getSource() { return this.source; } + public static boolean isIdentifierOrKeyword(int token) { return (token == TokenNameIdentifier) || (token > TokenNameKEYWORD); } + final char[] optimizedCurrentTokenSource1() { //return always the same char[] build only once //optimization at no speed cost of 99.5 % of the singleCharIdentifier char charOne = source[startPosition]; switch (charOne) { - case 'a' : - return charArray_a; - case 'b' : - return charArray_b; - case 'c' : - return charArray_c; - case 'd' : - return charArray_d; - case 'e' : - return charArray_e; - case 'f' : - return charArray_f; - case 'g' : - return charArray_g; - case 'h' : - return charArray_h; - case 'i' : - return charArray_i; - case 'j' : - return charArray_j; - case 'k' : - return charArray_k; - case 'l' : - return charArray_l; - case 'm' : - return charArray_m; - case 'n' : - return charArray_n; - case 'o' : - return charArray_o; - case 'p' : - return charArray_p; - case 'q' : - return charArray_q; - case 'r' : - return charArray_r; - case 's' : - return charArray_s; - case 't' : - return charArray_t; - case 'u' : - return charArray_u; - case 'v' : - return charArray_v; - case 'w' : - return charArray_w; - case 'x' : - return charArray_x; - case 'y' : - return charArray_y; - case 'z' : - return charArray_z; - default : - return new char[]{charOne}; + case 'a': + return charArray_a; + case 'b': + return charArray_b; + case 'c': + return charArray_c; + case 'd': + return charArray_d; + case 'e': + return charArray_e; + case 'f': + return charArray_f; + case 'g': + return charArray_g; + case 'h': + return charArray_h; + case 'i': + return charArray_i; + case 'j': + return charArray_j; + case 'k': + return charArray_k; + case 'l': + return charArray_l; + case 'm': + return charArray_m; + case 'n': + return charArray_n; + case 'o': + return charArray_o; + case 'p': + return charArray_p; + case 'q': + return charArray_q; + case 'r': + return charArray_r; + case 's': + return charArray_s; + case 't': + return charArray_t; + case 'u': + return charArray_u; + case 'v': + return charArray_v; + case 'w': + return charArray_w; + case 'x': + return charArray_x; + case 'y': + return charArray_y; + case 'z': + return charArray_z; + default: + return new char[] { charOne }; } } + final char[] optimizedCurrentTokenSource2() { //try to return the same char[] build only once char c0, c1; - int hash = (((c0 = source[startPosition]) << 6) + (c1 = source[startPosition + 1])) - % TableSize; + int hash = (((c0 = source[startPosition]) << 6) + (c1 = source[startPosition + 1])) % TableSize; char[][] table = charArray_length[0][hash]; int i = newEntry2; while (++i < InternalTableSize) { @@ -2355,15 +2475,15 @@ public class Scanner implements IScanner, ITerminalSymbols { if (++max >= InternalTableSize) max = 0; char[] r; - table[max] = (r = new char[]{c0, c1}); + table[max] = (r = new char[] { c0, c1 }); newEntry2 = max; return r; } + final char[] optimizedCurrentTokenSource3() { //try to return the same char[] build only once char c0, c1, c2; - int hash = (((c0 = source[startPosition]) << 12) - + ((c1 = source[startPosition + 1]) << 6) + (c2 = source[startPosition + 2])) + int hash = (((c0 = source[startPosition]) << 12) + ((c1 = source[startPosition + 1]) << 6) + (c2 = source[startPosition + 2])) % TableSize; char[][] table = charArray_length[1][hash]; int i = newEntry3; @@ -2384,23 +2504,22 @@ public class Scanner implements IScanner, ITerminalSymbols { if (++max >= InternalTableSize) max = 0; char[] r; - table[max] = (r = new char[]{c0, c1, c2}); + table[max] = (r = new char[] { c0, c1, c2 }); newEntry3 = max; return r; } + final char[] optimizedCurrentTokenSource4() { //try to return the same char[] build only once char c0, c1, c2, c3; - long hash = ((((long) (c0 = source[startPosition])) << 18) - + ((c1 = source[startPosition + 1]) << 12) + long hash = ((((long) (c0 = source[startPosition])) << 18) + ((c1 = source[startPosition + 1]) << 12) + ((c2 = source[startPosition + 2]) << 6) + (c3 = source[startPosition + 3])) % TableSize; char[][] table = charArray_length[2][(int) hash]; int i = newEntry4; while (++i < InternalTableSize) { char[] charArray = table[i]; - if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) - && (c3 == charArray[3])) + if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) && (c3 == charArray[3])) return charArray; } //---------other side--------- @@ -2408,32 +2527,29 @@ public class Scanner implements IScanner, ITerminalSymbols { int max = newEntry4; while (++i <= max) { char[] charArray = table[i]; - if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) - && (c3 == charArray[3])) + if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) && (c3 == charArray[3])) return charArray; } //--------add the entry------- if (++max >= InternalTableSize) max = 0; char[] r; - table[max] = (r = new char[]{c0, c1, c2, c3}); + table[max] = (r = new char[] { c0, c1, c2, c3 }); newEntry4 = max; return r; } + final char[] optimizedCurrentTokenSource5() { //try to return the same char[] build only once char c0, c1, c2, c3, c4; - long hash = ((((long) (c0 = source[startPosition])) << 24) - + (((long) (c1 = source[startPosition + 1])) << 18) - + ((c2 = source[startPosition + 2]) << 12) - + ((c3 = source[startPosition + 3]) << 6) + (c4 = source[startPosition + 4])) + long hash = ((((long) (c0 = source[startPosition])) << 24) + (((long) (c1 = source[startPosition + 1])) << 18) + + ((c2 = source[startPosition + 2]) << 12) + ((c3 = source[startPosition + 3]) << 6) + (c4 = source[startPosition + 4])) % TableSize; char[][] table = charArray_length[3][(int) hash]; int i = newEntry5; while (++i < InternalTableSize) { char[] charArray = table[i]; - if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) - && (c3 == charArray[3]) && (c4 == charArray[4])) + if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) && (c3 == charArray[3]) && (c4 == charArray[4])) return charArray; } //---------other side--------- @@ -2441,33 +2557,30 @@ public class Scanner implements IScanner, ITerminalSymbols { int max = newEntry5; while (++i <= max) { char[] charArray = table[i]; - if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) - && (c3 == charArray[3]) && (c4 == charArray[4])) + if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) && (c3 == charArray[3]) && (c4 == charArray[4])) return charArray; } //--------add the entry------- if (++max >= InternalTableSize) max = 0; char[] r; - table[max] = (r = new char[]{c0, c1, c2, c3, c4}); + table[max] = (r = new char[] { c0, c1, c2, c3, c4 }); newEntry5 = max; return r; } + final char[] optimizedCurrentTokenSource6() { //try to return the same char[] build only once char c0, c1, c2, c3, c4, c5; - long hash = ((((long) (c0 = source[startPosition])) << 32) - + (((long) (c1 = source[startPosition + 1])) << 24) - + (((long) (c2 = source[startPosition + 2])) << 18) - + ((c3 = source[startPosition + 3]) << 12) + long hash = ((((long) (c0 = source[startPosition])) << 32) + (((long) (c1 = source[startPosition + 1])) << 24) + + (((long) (c2 = source[startPosition + 2])) << 18) + ((c3 = source[startPosition + 3]) << 12) + ((c4 = source[startPosition + 4]) << 6) + (c5 = source[startPosition + 5])) % TableSize; char[][] table = charArray_length[4][(int) hash]; int i = newEntry6; while (++i < InternalTableSize) { char[] charArray = table[i]; - if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) - && (c3 == charArray[3]) && (c4 == charArray[4]) + if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) && (c3 == charArray[3]) && (c4 == charArray[4]) && (c5 == charArray[5])) return charArray; } @@ -2476,8 +2589,7 @@ public class Scanner implements IScanner, ITerminalSymbols { int max = newEntry6; while (++i <= max) { char[] charArray = table[i]; - if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) - && (c3 == charArray[3]) && (c4 == charArray[4]) + if ((c0 == charArray[0]) && (c1 == charArray[1]) && (c2 == charArray[2]) && (c3 == charArray[3]) && (c4 == charArray[4]) && (c5 == charArray[5])) return charArray; } @@ -2485,10 +2597,11 @@ public class Scanner implements IScanner, ITerminalSymbols { if (++max >= InternalTableSize) max = 0; char[] r; - table[max] = (r = new char[]{c0, c1, c2, c3, c4, c5}); + table[max] = (r = new char[] { c0, c1, c2, c3, c4, c5 }); newEntry6 = max; return r; } + public final void pushLineSeparator() throws InvalidInputException { //see comment on isLineDelimiter(char) for the use of '\n' and '\r' final int INCREMENT = 250; @@ -2553,6 +2666,7 @@ public class Scanner implements IScanner, ITerminalSymbols { } } } + public final void pushUnicodeLineSeparator() { // isUnicode means that the \r or \n has been read as a unicode character //see comment on isLineDelimiter(char) for the use of '\n' and '\r' @@ -2614,48 +2728,50 @@ public class Scanner implements IScanner, ITerminalSymbols { } } } + public void recordComment(int token) { - // compute position - int stopPosition = this.currentPosition; - switch (token) { - case TokenNameCOMMENT_LINE: - stopPosition = -this.lastCommentLinePosition; - break; - case TokenNameCOMMENT_BLOCK: - stopPosition = -this.currentPosition; - break; - } - - // a new comment is recorded - int length = this.commentStops.length; - if (++this.commentPtr >= length) { - System.arraycopy(this.commentStops, 0, this.commentStops = new int[length + 30], 0, length); - //grows the positions buffers too - System.arraycopy(this.commentStarts, 0, this.commentStarts = new int[length + 30], 0, length); - } - this.commentStops[this.commentPtr] = stopPosition; - this.commentStarts[this.commentPtr] = this.startPosition; -} -// public final void recordComment(boolean isJavadoc) { -// // a new annotation comment is recorded -// try { -// commentStops[++commentPtr] = isJavadoc -// ? currentPosition -// : -currentPosition; -// } catch (IndexOutOfBoundsException e) { -// int oldStackLength = commentStops.length; -// int[] oldStack = commentStops; -// commentStops = new int[oldStackLength + 30]; -// System.arraycopy(oldStack, 0, commentStops, 0, oldStackLength); -// commentStops[commentPtr] = isJavadoc ? currentPosition : -currentPosition; -// //grows the positions buffers too -// int[] old = commentStarts; -// commentStarts = new int[oldStackLength + 30]; -// System.arraycopy(old, 0, commentStarts, 0, oldStackLength); -// } -// //the buffer is of a correct size here -// commentStarts[commentPtr] = startPosition; -// } + // compute position + int stopPosition = this.currentPosition; + switch (token) { + case TokenNameCOMMENT_LINE: + stopPosition = -this.lastCommentLinePosition; + break; + case TokenNameCOMMENT_BLOCK: + stopPosition = -this.currentPosition; + break; + } + + // a new comment is recorded + int length = this.commentStops.length; + if (++this.commentPtr >= length) { + System.arraycopy(this.commentStops, 0, this.commentStops = new int[length + 30], 0, length); + //grows the positions buffers too + System.arraycopy(this.commentStarts, 0, this.commentStarts = new int[length + 30], 0, length); + } + this.commentStops[this.commentPtr] = stopPosition; + this.commentStarts[this.commentPtr] = this.startPosition; + } + + // public final void recordComment(boolean isJavadoc) { + // // a new annotation comment is recorded + // try { + // commentStops[++commentPtr] = isJavadoc + // ? currentPosition + // : -currentPosition; + // } catch (IndexOutOfBoundsException e) { + // int oldStackLength = commentStops.length; + // int[] oldStack = commentStops; + // commentStops = new int[oldStackLength + 30]; + // System.arraycopy(oldStack, 0, commentStops, 0, oldStackLength); + // commentStops[commentPtr] = isJavadoc ? currentPosition : -currentPosition; + // //grows the positions buffers too + // int[] old = commentStarts; + // commentStarts = new int[oldStackLength + 30]; + // System.arraycopy(old, 0, commentStarts, 0, oldStackLength); + // } + // //the buffer is of a correct size here + // commentStarts[commentPtr] = startPosition; + // } public void resetTo(int begin, int end) { //reset the scanner to a given position where it may rescan again diet = false; @@ -2663,8 +2779,8 @@ public class Scanner implements IScanner, ITerminalSymbols { eofPosition = end < Integer.MAX_VALUE ? end + 1 : end; commentPtr = -1; // reset comment stack } - public final void scanSingleQuotedEscapeCharacter() - throws InvalidInputException { + + public final void scanSingleQuotedEscapeCharacter() throws InvalidInputException { // the string with "\\u" is a legal string of two chars \ and u //thus we use a direct access to the source (for regular cases). // if (unicodeAsBackSlash) { @@ -2681,19 +2797,19 @@ public class Scanner implements IScanner, ITerminalSymbols { // } else currentCharacter = source[currentPosition++]; switch (currentCharacter) { - case '\'' : - currentCharacter = '\''; - break; - case '\\' : - currentCharacter = '\\'; - break; - default : - currentCharacter = '\\'; - currentPosition--; + case '\'': + currentCharacter = '\''; + break; + case '\\': + currentCharacter = '\\'; + break; + default: + currentCharacter = '\\'; + currentPosition--; } } - public final void scanDoubleQuotedEscapeCharacter() - throws InvalidInputException { + + public final void scanDoubleQuotedEscapeCharacter() throws InvalidInputException { // the string with "\\u" is a legal string of two chars \ and u //thus we use a direct access to the source (for regular cases). // if (unicodeAsBackSlash) { @@ -2710,84 +2826,83 @@ public class Scanner implements IScanner, ITerminalSymbols { // } else currentCharacter = source[currentPosition++]; switch (currentCharacter) { - // case 'b' : - // currentCharacter = '\b'; - // break; - case 't' : - currentCharacter = '\t'; - break; - case 'n' : - currentCharacter = '\n'; - break; - // case 'f' : - // currentCharacter = '\f'; - // break; - case 'r' : - currentCharacter = '\r'; - break; - case '\"' : - currentCharacter = '\"'; - break; - case '\'' : - currentCharacter = '\''; - break; - case '\\' : - currentCharacter = '\\'; - break; - case '$' : - currentCharacter = '$'; - break; - default : - // -----------octal escape-------------- - // OctalDigit - // OctalDigit OctalDigit - // ZeroToThree OctalDigit OctalDigit - int number = Character.getNumericValue(currentCharacter); - if (number >= 0 && number <= 7) { - boolean zeroToThreeNot = number > 3; - if (Character.isDigit(currentCharacter = source[currentPosition++])) { - int digit = Character.getNumericValue(currentCharacter); - if (digit >= 0 && digit <= 7) { - number = (number * 8) + digit; - if (Character - .isDigit(currentCharacter = source[currentPosition++])) { - if (zeroToThreeNot) { // has read \NotZeroToThree OctalDigit - // Digit --> ignore last character + // case 'b' : + // currentCharacter = '\b'; + // break; + case 't': + currentCharacter = '\t'; + break; + case 'n': + currentCharacter = '\n'; + break; + // case 'f' : + // currentCharacter = '\f'; + // break; + case 'r': + currentCharacter = '\r'; + break; + case '\"': + currentCharacter = '\"'; + break; + case '\'': + currentCharacter = '\''; + break; + case '\\': + currentCharacter = '\\'; + break; + case '$': + currentCharacter = '$'; + break; + default: + // -----------octal escape-------------- + // OctalDigit + // OctalDigit OctalDigit + // ZeroToThree OctalDigit OctalDigit + int number = Character.getNumericValue(currentCharacter); + if (number >= 0 && number <= 7) { + boolean zeroToThreeNot = number > 3; + if (Character.isDigit(currentCharacter = source[currentPosition++])) { + int digit = Character.getNumericValue(currentCharacter); + if (digit >= 0 && digit <= 7) { + number = (number * 8) + digit; + if (Character.isDigit(currentCharacter = source[currentPosition++])) { + if (zeroToThreeNot) { // has read \NotZeroToThree OctalDigit + // Digit --> ignore last character + currentPosition--; + } else { + digit = Character.getNumericValue(currentCharacter); + if (digit >= 0 && digit <= 7) { + // has read \ZeroToThree OctalDigit OctalDigit + number = (number * 8) + digit; + } else { // has read \ZeroToThree OctalDigit NonOctalDigit + // --> ignore last character currentPosition--; - } else { - digit = Character.getNumericValue(currentCharacter); - if (digit >= 0 && digit <= 7) { - // has read \ZeroToThree OctalDigit OctalDigit - number = (number * 8) + digit; - } else { // has read \ZeroToThree OctalDigit NonOctalDigit - // --> ignore last character - currentPosition--; - } } - } else { // has read \OctalDigit NonDigit--> ignore last - // character - currentPosition--; } - } else { // has read \OctalDigit NonOctalDigit--> ignore last + } else { // has read \OctalDigit NonDigit--> ignore last // character currentPosition--; } - } else { // has read \OctalDigit --> ignore last character + } else { // has read \OctalDigit NonOctalDigit--> ignore last + // character currentPosition--; } - if (number > 255) - throw new InvalidInputException(INVALID_ESCAPE); - currentCharacter = (char) number; + } else { // has read \OctalDigit --> ignore last character + currentPosition--; } + if (number > 255) + throw new InvalidInputException(INVALID_ESCAPE); + currentCharacter = (char) number; + } //else // throw new InvalidInputException(INVALID_ESCAPE); } } + // public int scanIdentifierOrKeyword() throws InvalidInputException { // return scanIdentifierOrKeyword( false ); // } - public int scanIdentifierOrKeyword(boolean isVariable) - throws InvalidInputException { + public int scanIdentifierOrKeyword(boolean isVariable) throws InvalidInputException { //test keywords //first dispatch on the first char. //then the length. If there are several @@ -2795,7 +2910,8 @@ public class Scanner implements IScanner, ITerminalSymbols { //disptach on the second char :-)...cool....but fast ! useAssertAsAnIndentifier = false; while (getNextCharAsJavaIdentifierPart()) { - }; + } + ; if (isVariable) { // if (new String(getCurrentTokenSource()).equals("$this")) { // return TokenNamethis; @@ -2831,575 +2947,503 @@ public class Scanner implements IScanner, ITerminalSymbols { // } firstLetter = data[index]; switch (firstLetter) { - case '_' : - switch (length) { - case 8 : - //__FILE__ - if ((data[++index] == '_') && (data[++index] == 'f') - && (data[++index] == 'i') && (data[++index] == 'l') - && (data[++index] == 'e') && (data[++index] == '_') - && (data[++index] == '_')) - return TokenNameFILE; - index = 0; //__LINE__ - if ((data[++index] == '_') && (data[++index] == 'l') - && (data[++index] == 'i') && (data[++index] == 'n') - && (data[++index] == 'e') && (data[++index] == '_') - && (data[++index] == '_')) - return TokenNameLINE; - break; - case 9 : - //__CLASS__ - if ((data[++index] == '_') && (data[++index] == 'c') - && (data[++index] == 'l') && (data[++index] == 'a') - && (data[++index] == 's') && (data[++index] == 's') - && (data[++index] == '_') && (data[++index] == '_')) - return TokenNameCLASS_C; - break; - case 11 : - //__METHOD__ - if ((data[++index] == '_') && (data[++index] == 'm') - && (data[++index] == 'e') && (data[++index] == 't') - && (data[++index] == 'h') && (data[++index] == 'o') - && (data[++index] == 'd') && (data[++index] == '_') - && (data[++index] == '_')) - return TokenNameMETHOD_C; - break; - case 12 : - //__FUNCTION__ - if ((data[++index] == '_') && (data[++index] == 'f') - && (data[++index] == 'u') && (data[++index] == 'n') - && (data[++index] == 'c') && (data[++index] == 't') - && (data[++index] == 'i') && (data[++index] == 'o') - && (data[++index] == 'n') && (data[++index] == '_') - && (data[++index] == '_')) - return TokenNameFUNC_C; - break; - } - return TokenNameIdentifier; - case 'a' : - // as and array abstract - switch (length) { - case 2 : - //as - if ((data[++index] == 's')) { - return TokenNameas; - } else { - return TokenNameIdentifier; - } - case 3 : - //and - if ((data[++index] == 'n') && (data[++index] == 'd')) { - return TokenNameand; - } else { - return TokenNameIdentifier; - } - case 5 : - // array - if ((data[++index] == 'r') && (data[++index] == 'r') - && (data[++index] == 'a') && (data[++index] == 'y')) - return TokenNamearray; - else - return TokenNameIdentifier; - case 8 : - if ((data[++index] == 'b') && (data[++index] == 's') - && (data[++index] == 't') && (data[++index] == 'r') - && (data[++index] == 'a') && (data[++index] == 'c') - && (data[++index] == 't')) - return TokenNameabstract; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; - } - case 'b' : - //break - switch (length) { - case 5 : - if ((data[++index] == 'r') && (data[++index] == 'e') - && (data[++index] == 'a') && (data[++index] == 'k')) - return TokenNamebreak; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; - } - case 'c' : - //case catch class clone const continue - switch (length) { - case 4 : - if ((data[++index] == 'a') && (data[++index] == 's') - && (data[++index] == 'e')) - return TokenNamecase; - else - return TokenNameIdentifier; - case 5 : - if ((data[++index] == 'a') && (data[++index] == 't') - && (data[++index] == 'c') && (data[++index] == 'h')) - return TokenNamecatch; - index = 0; - if ((data[++index] == 'l') && (data[++index] == 'a') - && (data[++index] == 's') && (data[++index] == 's')) - return TokenNameclass; - index = 0; - if ((data[++index] == 'l') && (data[++index] == 'o') - && (data[++index] == 'n') && (data[++index] == 'e')) - return TokenNameclone; - index = 0; - if ((data[++index] == 'o') && (data[++index] == 'n') - && (data[++index] == 's') && (data[++index] == 't')) - return TokenNameconst; - else - return TokenNameIdentifier; - case 8 : - if ((data[++index] == 'o') && (data[++index] == 'n') - && (data[++index] == 't') && (data[++index] == 'i') - && (data[++index] == 'n') && (data[++index] == 'u') - && (data[++index] == 'e')) - return TokenNamecontinue; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; - } - case 'd' : - // declare default do die - // TODO delete define ==> no keyword ! - switch (length) { - case 2 : - if ((data[++index] == 'o')) - return TokenNamedo; - else - return TokenNameIdentifier; - // case 6 : - // if ((data[++index] == 'e') - // && (data[++index] == 'f') - // && (data[++index] == 'i') - // && (data[++index] == 'n') - // && (data[++index] == 'e')) - // return TokenNamedefine; - // else - // return TokenNameIdentifier; - case 7 : - if ((data[++index] == 'e') && (data[++index] == 'c') - && (data[++index] == 'l') && (data[++index] == 'a') - && (data[++index] == 'r') && (data[++index] == 'e')) - return TokenNamedeclare; - index = 0; - if ((data[++index] == 'e') && (data[++index] == 'f') - && (data[++index] == 'a') && (data[++index] == 'u') - && (data[++index] == 'l') && (data[++index] == 't')) - return TokenNamedefault; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; - } - case 'e' : - //echo else exit elseif extends eval - switch (length) { - case 4 : - if ((data[++index] == 'c') && (data[++index] == 'h') - && (data[++index] == 'o')) - return TokenNameecho; - else if ((data[index] == 'l') && (data[++index] == 's') - && (data[++index] == 'e')) - return TokenNameelse; - else if ((data[index] == 'x') && (data[++index] == 'i') - && (data[++index] == 't')) - return TokenNameexit; - else if ((data[index] == 'v') && (data[++index] == 'a') - && (data[++index] == 'l')) - return TokenNameeval; - else - return TokenNameIdentifier; - case 5 : - // endif empty - if ((data[++index] == 'n') && (data[++index] == 'd') - && (data[++index] == 'i') && (data[++index] == 'f')) - return TokenNameendif; - if ((data[index] == 'm') && (data[++index] == 'p') - && (data[++index] == 't') && (data[++index] == 'y')) - return TokenNameempty; - else - return TokenNameIdentifier; - case 6 : - // endfor - if ((data[++index] == 'n') && (data[++index] == 'd') - && (data[++index] == 'f') && (data[++index] == 'o') - && (data[++index] == 'r')) - return TokenNameendfor; - else if ((data[index] == 'l') && (data[++index] == 's') - && (data[++index] == 'e') && (data[++index] == 'i') - && (data[++index] == 'f')) - return TokenNameelseif; - else - return TokenNameIdentifier; - case 7 : - if ((data[++index] == 'x') && (data[++index] == 't') - && (data[++index] == 'e') && (data[++index] == 'n') - && (data[++index] == 'd') && (data[++index] == 's')) - return TokenNameextends; - else - return TokenNameIdentifier; - case 8 : - // endwhile - if ((data[++index] == 'n') && (data[++index] == 'd') - && (data[++index] == 'w') && (data[++index] == 'h') - && (data[++index] == 'i') && (data[++index] == 'l') - && (data[++index] == 'e')) - return TokenNameendwhile; - else - return TokenNameIdentifier; - case 9 : - // endswitch - if ((data[++index] == 'n') && (data[++index] == 'd') - && (data[++index] == 's') && (data[++index] == 'w') - && (data[++index] == 'i') && (data[++index] == 't') - && (data[++index] == 'c') && (data[++index] == 'h')) - return TokenNameendswitch; - else - return TokenNameIdentifier; - case 10 : - // enddeclare - if ((data[++index] == 'n') && (data[++index] == 'd') - && (data[++index] == 'd') && (data[++index] == 'e') - && (data[++index] == 'c') && (data[++index] == 'l') - && (data[++index] == 'a') && (data[++index] == 'r') - && (data[++index] == 'e')) - return TokenNameendforeach; - index = 0; - if ((data[++index] == 'n') // endforeach - && (data[++index] == 'd') && (data[++index] == 'f') - && (data[++index] == 'o') && (data[++index] == 'r') - && (data[++index] == 'e') && (data[++index] == 'a') - && (data[++index] == 'c') && (data[++index] == 'h')) - return TokenNameendforeach; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; - } - case 'f' : - //for false final function - switch (length) { - case 3 : - if ((data[++index] == 'o') && (data[++index] == 'r')) - return TokenNamefor; - else - return TokenNameIdentifier; - case 5 : - // if ((data[++index] == 'a') && (data[++index] == 'l') - // && (data[++index] == 's') && (data[++index] == 'e')) - // return TokenNamefalse; - if ((data[++index] == 'i') && (data[++index] == 'n') - && (data[++index] == 'a') && (data[++index] == 'l')) - return TokenNamefinal; - else - return TokenNameIdentifier; - case 7 : - // foreach - if ((data[++index] == 'o') && (data[++index] == 'r') - && (data[++index] == 'e') && (data[++index] == 'a') - && (data[++index] == 'c') && (data[++index] == 'h')) - return TokenNameforeach; - else - return TokenNameIdentifier; - case 8 : - // function - if ((data[++index] == 'u') && (data[++index] == 'n') - && (data[++index] == 'c') && (data[++index] == 't') - && (data[++index] == 'i') && (data[++index] == 'o') - && (data[++index] == 'n')) - return TokenNamefunction; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; + case '_': + switch (length) { + case 8: + //__FILE__ + if ((data[++index] == '_') && (data[++index] == 'f') && (data[++index] == 'i') && (data[++index] == 'l') + && (data[++index] == 'e') && (data[++index] == '_') && (data[++index] == '_')) + return TokenNameFILE; + index = 0; //__LINE__ + if ((data[++index] == '_') && (data[++index] == 'l') && (data[++index] == 'i') && (data[++index] == 'n') + && (data[++index] == 'e') && (data[++index] == '_') && (data[++index] == '_')) + return TokenNameLINE; + break; + case 9: + //__CLASS__ + if ((data[++index] == '_') && (data[++index] == 'c') && (data[++index] == 'l') && (data[++index] == 'a') + && (data[++index] == 's') && (data[++index] == 's') && (data[++index] == '_') && (data[++index] == '_')) + return TokenNameCLASS_C; + break; + case 11: + //__METHOD__ + if ((data[++index] == '_') && (data[++index] == 'm') && (data[++index] == 'e') && (data[++index] == 't') + && (data[++index] == 'h') && (data[++index] == 'o') && (data[++index] == 'd') && (data[++index] == '_') + && (data[++index] == '_')) + return TokenNameMETHOD_C; + break; + case 12: + //__FUNCTION__ + if ((data[++index] == '_') && (data[++index] == 'f') && (data[++index] == 'u') && (data[++index] == 'n') + && (data[++index] == 'c') && (data[++index] == 't') && (data[++index] == 'i') && (data[++index] == 'o') + && (data[++index] == 'n') && (data[++index] == '_') && (data[++index] == '_')) + return TokenNameFUNC_C; + break; + } + return TokenNameIdentifier; + case 'a': + // as and array abstract + switch (length) { + case 2: + //as + if ((data[++index] == 's')) { + return TokenNameas; + } else { + return TokenNameIdentifier; } - case 'g' : - //global - if (length == 6) { - if ((data[++index] == 'l') && (data[++index] == 'o') - && (data[++index] == 'b') && (data[++index] == 'a') - && (data[++index] == 'l')) { - return TokenNameglobal; - } + case 3: + //and + if ((data[++index] == 'n') && (data[++index] == 'd')) { + return TokenNameand; + } else { + return TokenNameIdentifier; } + case 5: + // array + if ((data[++index] == 'r') && (data[++index] == 'r') && (data[++index] == 'a') && (data[++index] == 'y')) + return TokenNamearray; + else + return TokenNameIdentifier; + case 8: + if ((data[++index] == 'b') && (data[++index] == 's') && (data[++index] == 't') && (data[++index] == 'r') + && (data[++index] == 'a') && (data[++index] == 'c') && (data[++index] == 't')) + return TokenNameabstract; + else + return TokenNameIdentifier; + default: return TokenNameIdentifier; - case 'i' : - //if int isset include include_once instanceof interface implements - switch (length) { - case 2 : - if (data[++index] == 'f') - return TokenNameif; - else - return TokenNameIdentifier; - // case 3 : - // if ((data[++index] == 'n') && (data[++index] == 't')) - // return TokenNameint; - // else - // return TokenNameIdentifier; - case 5 : - if ((data[++index] == 's') && (data[++index] == 's') - && (data[++index] == 'e') && (data[++index] == 't')) - return TokenNameisset; - else - return TokenNameIdentifier; - case 7 : - if ((data[++index] == 'n') && (data[++index] == 'c') - && (data[++index] == 'l') && (data[++index] == 'u') - && (data[++index] == 'd') && (data[++index] == 'e')) - return TokenNameinclude; - else - return TokenNameIdentifier; - case 9 : - // interface - if ((data[++index] == 'n') && (data[++index] == 't') - && (data[++index] == 'e') && (data[++index] == 'r') - && (data[++index] == 'f') && (data[++index] == 'a') - && (data[++index] == 'c') && (data[++index] == 'e')) - return TokenNameinterface; - else - return TokenNameIdentifier; - case 10 : - // instanceof - if ((data[++index] == 'n') && (data[++index] == 's') - && (data[++index] == 't') && (data[++index] == 'a') - && (data[++index] == 'n') && (data[++index] == 'c') - && (data[++index] == 'e') && (data[++index] == 'o') - && (data[++index] == 'f')) - return TokenNameinstanceof; - if ((data[index] == 'm') && (data[++index] == 'p') - && (data[++index] == 'l') && (data[++index] == 'e') - && (data[++index] == 'm') && (data[++index] == 'e') - && (data[++index] == 'n') && (data[++index] == 't') - && (data[++index] == 's')) - return TokenNameimplements; - else - return TokenNameIdentifier; - case 12 : - if ((data[++index] == 'n') && (data[++index] == 'c') - && (data[++index] == 'l') && (data[++index] == 'u') - && (data[++index] == 'd') && (data[++index] == 'e') - && (data[++index] == '_') && (data[++index] == 'o') - && (data[++index] == 'n') && (data[++index] == 'c') - && (data[++index] == 'e')) - return TokenNameinclude_once; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; - } - case 'l' : - //list - if (length == 4) { - if ((data[++index] == 'i') && (data[++index] == 's') - && (data[++index] == 't')) { - return TokenNamelist; - } - } + } + case 'b': + //break + switch (length) { + case 5: + if ((data[++index] == 'r') && (data[++index] == 'e') && (data[++index] == 'a') && (data[++index] == 'k')) + return TokenNamebreak; + else + return TokenNameIdentifier; + default: return TokenNameIdentifier; - case 'n' : - // new null - switch (length) { - case 3 : - if ((data[++index] == 'e') && (data[++index] == 'w')) - return TokenNamenew; - else - return TokenNameIdentifier; - // case 4 : - // if ((data[++index] == 'u') && (data[++index] == 'l') - // && (data[++index] == 'l')) - // return TokenNamenull; - // else - // return TokenNameIdentifier; - default : - return TokenNameIdentifier; - } - case 'o' : - // or old_function - if (length == 2) { - if (data[++index] == 'r') { - return TokenNameor; - } + } + case 'c': + //case catch class clone const continue + switch (length) { + case 4: + if ((data[++index] == 'a') && (data[++index] == 's') && (data[++index] == 'e')) + return TokenNamecase; + else + return TokenNameIdentifier; + case 5: + if ((data[++index] == 'a') && (data[++index] == 't') && (data[++index] == 'c') && (data[++index] == 'h')) + return TokenNamecatch; + index = 0; + if ((data[++index] == 'l') && (data[++index] == 'a') && (data[++index] == 's') && (data[++index] == 's')) + return TokenNameclass; + index = 0; + if ((data[++index] == 'l') && (data[++index] == 'o') && (data[++index] == 'n') && (data[++index] == 'e')) + return TokenNameclone; + index = 0; + if ((data[++index] == 'o') && (data[++index] == 'n') && (data[++index] == 's') && (data[++index] == 't')) + return TokenNameconst; + else + return TokenNameIdentifier; + case 8: + if ((data[++index] == 'o') && (data[++index] == 'n') && (data[++index] == 't') && (data[++index] == 'i') + && (data[++index] == 'n') && (data[++index] == 'u') && (data[++index] == 'e')) + return TokenNamecontinue; + else + return TokenNameIdentifier; + default: + return TokenNameIdentifier; + } + case 'd': + // declare default do die + // TODO delete define ==> no keyword ! + switch (length) { + case 2: + if ((data[++index] == 'o')) + return TokenNamedo; + else + return TokenNameIdentifier; + // case 6 : + // if ((data[++index] == 'e') + // && (data[++index] == 'f') + // && (data[++index] == 'i') + // && (data[++index] == 'n') + // && (data[++index] == 'e')) + // return TokenNamedefine; + // else + // return TokenNameIdentifier; + case 7: + if ((data[++index] == 'e') && (data[++index] == 'c') && (data[++index] == 'l') && (data[++index] == 'a') + && (data[++index] == 'r') && (data[++index] == 'e')) + return TokenNamedeclare; + index = 0; + if ((data[++index] == 'e') && (data[++index] == 'f') && (data[++index] == 'a') && (data[++index] == 'u') + && (data[++index] == 'l') && (data[++index] == 't')) + return TokenNamedefault; + else + return TokenNameIdentifier; + default: + return TokenNameIdentifier; + } + case 'e': + //echo else exit elseif extends eval + switch (length) { + case 4: + if ((data[++index] == 'c') && (data[++index] == 'h') && (data[++index] == 'o')) + return TokenNameecho; + else if ((data[index] == 'l') && (data[++index] == 's') && (data[++index] == 'e')) + return TokenNameelse; + else if ((data[index] == 'x') && (data[++index] == 'i') && (data[++index] == 't')) + return TokenNameexit; + else if ((data[index] == 'v') && (data[++index] == 'a') && (data[++index] == 'l')) + return TokenNameeval; + else + return TokenNameIdentifier; + case 5: + // endif empty + if ((data[++index] == 'n') && (data[++index] == 'd') && (data[++index] == 'i') && (data[++index] == 'f')) + return TokenNameendif; + if ((data[index] == 'm') && (data[++index] == 'p') && (data[++index] == 't') && (data[++index] == 'y')) + return TokenNameempty; + else + return TokenNameIdentifier; + case 6: + // endfor + if ((data[++index] == 'n') && (data[++index] == 'd') && (data[++index] == 'f') && (data[++index] == 'o') + && (data[++index] == 'r')) + return TokenNameendfor; + else if ((data[index] == 'l') && (data[++index] == 's') && (data[++index] == 'e') && (data[++index] == 'i') + && (data[++index] == 'f')) + return TokenNameelseif; + else + return TokenNameIdentifier; + case 7: + if ((data[++index] == 'x') && (data[++index] == 't') && (data[++index] == 'e') && (data[++index] == 'n') + && (data[++index] == 'd') && (data[++index] == 's')) + return TokenNameextends; + else + return TokenNameIdentifier; + case 8: + // endwhile + if ((data[++index] == 'n') && (data[++index] == 'd') && (data[++index] == 'w') && (data[++index] == 'h') + && (data[++index] == 'i') && (data[++index] == 'l') && (data[++index] == 'e')) + return TokenNameendwhile; + else + return TokenNameIdentifier; + case 9: + // endswitch + if ((data[++index] == 'n') && (data[++index] == 'd') && (data[++index] == 's') && (data[++index] == 'w') + && (data[++index] == 'i') && (data[++index] == 't') && (data[++index] == 'c') && (data[++index] == 'h')) + return TokenNameendswitch; + else + return TokenNameIdentifier; + case 10: + // enddeclare + if ((data[++index] == 'n') && (data[++index] == 'd') && (data[++index] == 'd') && (data[++index] == 'e') + && (data[++index] == 'c') && (data[++index] == 'l') && (data[++index] == 'a') && (data[++index] == 'r') + && (data[++index] == 'e')) + return TokenNameendforeach; + index = 0; + if ((data[++index] == 'n') // endforeach + && (data[++index] == 'd') && (data[++index] == 'f') && (data[++index] == 'o') && (data[++index] == 'r') + && (data[++index] == 'e') && (data[++index] == 'a') && (data[++index] == 'c') && (data[++index] == 'h')) + return TokenNameendforeach; + else + return TokenNameIdentifier; + default: + return TokenNameIdentifier; + } + case 'f': + //for false final function + switch (length) { + case 3: + if ((data[++index] == 'o') && (data[++index] == 'r')) + return TokenNamefor; + else + return TokenNameIdentifier; + case 5: + // if ((data[++index] == 'a') && (data[++index] == 'l') + // && (data[++index] == 's') && (data[++index] == 'e')) + // return TokenNamefalse; + if ((data[++index] == 'i') && (data[++index] == 'n') && (data[++index] == 'a') && (data[++index] == 'l')) + return TokenNamefinal; + else + return TokenNameIdentifier; + case 7: + // foreach + if ((data[++index] == 'o') && (data[++index] == 'r') && (data[++index] == 'e') && (data[++index] == 'a') + && (data[++index] == 'c') && (data[++index] == 'h')) + return TokenNameforeach; + else + return TokenNameIdentifier; + case 8: + // function + if ((data[++index] == 'u') && (data[++index] == 'n') && (data[++index] == 'c') && (data[++index] == 't') + && (data[++index] == 'i') && (data[++index] == 'o') && (data[++index] == 'n')) + return TokenNamefunction; + else + return TokenNameIdentifier; + default: + return TokenNameIdentifier; + } + case 'g': + //global + if (length == 6) { + if ((data[++index] == 'l') && (data[++index] == 'o') && (data[++index] == 'b') && (data[++index] == 'a') + && (data[++index] == 'l')) { + return TokenNameglobal; } - // if (length == 12) { - // if ((data[++index] == 'l') - // && (data[++index] == 'd') - // && (data[++index] == '_') - // && (data[++index] == 'f') - // && (data[++index] == 'u') - // && (data[++index] == 'n') - // && (data[++index] == 'c') - // && (data[++index] == 't') - // && (data[++index] == 'i') - // && (data[++index] == 'o') - // && (data[++index] == 'n')) { - // return TokenNameold_function; - // } - // } + } + return TokenNameIdentifier; + case 'i': + //if int isset include include_once instanceof interface implements + switch (length) { + case 2: + if (data[++index] == 'f') + return TokenNameif; + else + return TokenNameIdentifier; + // case 3 : + // if ((data[++index] == 'n') && (data[++index] == 't')) + // return TokenNameint; + // else + // return TokenNameIdentifier; + case 5: + if ((data[++index] == 's') && (data[++index] == 's') && (data[++index] == 'e') && (data[++index] == 't')) + return TokenNameisset; + else + return TokenNameIdentifier; + case 7: + if ((data[++index] == 'n') && (data[++index] == 'c') && (data[++index] == 'l') && (data[++index] == 'u') + && (data[++index] == 'd') && (data[++index] == 'e')) + return TokenNameinclude; + else + return TokenNameIdentifier; + case 9: + // interface + if ((data[++index] == 'n') && (data[++index] == 't') && (data[++index] == 'e') && (data[++index] == 'r') + && (data[++index] == 'f') && (data[++index] == 'a') && (data[++index] == 'c') && (data[++index] == 'e')) + return TokenNameinterface; + else + return TokenNameIdentifier; + case 10: + // instanceof + if ((data[++index] == 'n') && (data[++index] == 's') && (data[++index] == 't') && (data[++index] == 'a') + && (data[++index] == 'n') && (data[++index] == 'c') && (data[++index] == 'e') && (data[++index] == 'o') + && (data[++index] == 'f')) + return TokenNameinstanceof; + if ((data[index] == 'm') && (data[++index] == 'p') && (data[++index] == 'l') && (data[++index] == 'e') + && (data[++index] == 'm') && (data[++index] == 'e') && (data[++index] == 'n') && (data[++index] == 't') + && (data[++index] == 's')) + return TokenNameimplements; + else + return TokenNameIdentifier; + case 12: + if ((data[++index] == 'n') && (data[++index] == 'c') && (data[++index] == 'l') && (data[++index] == 'u') + && (data[++index] == 'd') && (data[++index] == 'e') && (data[++index] == '_') && (data[++index] == 'o') + && (data[++index] == 'n') && (data[++index] == 'c') && (data[++index] == 'e')) + return TokenNameinclude_once; + else + return TokenNameIdentifier; + default: return TokenNameIdentifier; - case 'p' : - // print public private protected - switch (length) { - case 5 : - if ((data[++index] == 'r') && (data[++index] == 'i') - && (data[++index] == 'n') && (data[++index] == 't')) { - return TokenNameprint; - } else - return TokenNameIdentifier; - case 6 : - if ((data[++index] == 'u') && (data[++index] == 'b') - && (data[++index] == 'l') && (data[++index] == 'i') - && (data[++index] == 'c')) { - return TokenNamepublic; - } else - return TokenNameIdentifier; - case 7 : - if ((data[++index] == 'r') && (data[++index] == 'i') - && (data[++index] == 'v') && (data[++index] == 'a') - && (data[++index] == 't') && (data[++index] == 'e')) { - return TokenNameprivate; - } else - return TokenNameIdentifier; - case 9 : - if ((data[++index] == 'r') && (data[++index] == 'o') - && (data[++index] == 't') && (data[++index] == 'e') - && (data[++index] == 'c') && (data[++index] == 't') - && (data[++index] == 'e') && (data[++index] == 'd')) { - return TokenNameprotected; - } else - return TokenNameIdentifier; + } + case 'l': + //list + if (length == 4) { + if ((data[++index] == 'i') && (data[++index] == 's') && (data[++index] == 't')) { + return TokenNamelist; } + } + return TokenNameIdentifier; + case 'n': + // new null + switch (length) { + case 3: + if ((data[++index] == 'e') && (data[++index] == 'w')) + return TokenNamenew; + else + return TokenNameIdentifier; + // case 4 : + // if ((data[++index] == 'u') && (data[++index] == 'l') + // && (data[++index] == 'l')) + // return TokenNamenull; + // else + // return TokenNameIdentifier; + default: return TokenNameIdentifier; - case 'r' : - //return require require_once - if (length == 6) { - if ((data[++index] == 'e') && (data[++index] == 't') - && (data[++index] == 'u') && (data[++index] == 'r') - && (data[++index] == 'n')) { - return TokenNamereturn; - } - } else if (length == 7) { - if ((data[++index] == 'e') && (data[++index] == 'q') - && (data[++index] == 'u') && (data[++index] == 'i') - && (data[++index] == 'r') && (data[++index] == 'e')) { - return TokenNamerequire; - } - } else if (length == 12) { - if ((data[++index] == 'e') && (data[++index] == 'q') - && (data[++index] == 'u') && (data[++index] == 'i') - && (data[++index] == 'r') && (data[++index] == 'e') - && (data[++index] == '_') && (data[++index] == 'o') - && (data[++index] == 'n') && (data[++index] == 'c') - && (data[++index] == 'e')) { - return TokenNamerequire_once; - } + } + case 'o': + // or old_function + if (length == 2) { + if (data[++index] == 'r') { + return TokenNameor; + } + } + // if (length == 12) { + // if ((data[++index] == 'l') + // && (data[++index] == 'd') + // && (data[++index] == '_') + // && (data[++index] == 'f') + // && (data[++index] == 'u') + // && (data[++index] == 'n') + // && (data[++index] == 'c') + // && (data[++index] == 't') + // && (data[++index] == 'i') + // && (data[++index] == 'o') + // && (data[++index] == 'n')) { + // return TokenNameold_function; + // } + // } + return TokenNameIdentifier; + case 'p': + // print public private protected + switch (length) { + case 5: + if ((data[++index] == 'r') && (data[++index] == 'i') && (data[++index] == 'n') && (data[++index] == 't')) { + return TokenNameprint; } else return TokenNameIdentifier; - case 's' : - //static switch - switch (length) { - case 6 : - if (data[++index] == 't') - if ((data[++index] == 'a') && (data[++index] == 't') - && (data[++index] == 'i') && (data[++index] == 'c')) { - return TokenNamestatic; - } else - return TokenNameIdentifier; - else if ((data[index] == 'w') && (data[++index] == 'i') - && (data[++index] == 't') && (data[++index] == 'c') - && (data[++index] == 'h')) - return TokenNameswitch; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; - } - case 't' : - // try true throw - switch (length) { - case 3 : - if ((data[++index] == 'r') && (data[++index] == 'y')) - return TokenNametry; - else - return TokenNameIdentifier; - // case 4 : - // if ((data[++index] == 'r') && (data[++index] == 'u') - // && (data[++index] == 'e')) - // return TokenNametrue; - // else - // return TokenNameIdentifier; - case 5 : - if ((data[++index] == 'h') && (data[++index] == 'r') - && (data[++index] == 'o') && (data[++index] == 'w')) - return TokenNamethrow; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; - } - case 'u' : - //use unset - switch (length) { - case 3 : - if ((data[++index] == 's') && (data[++index] == 'e')) - return TokenNameuse; - else - return TokenNameIdentifier; - case 5 : - if ((data[++index] == 'n') && (data[++index] == 's') - && (data[++index] == 'e') && (data[++index] == 't')) - return TokenNameunset; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; + case 6: + if ((data[++index] == 'u') && (data[++index] == 'b') && (data[++index] == 'l') && (data[++index] == 'i') + && (data[++index] == 'c')) { + return TokenNamepublic; + } else + return TokenNameIdentifier; + case 7: + if ((data[++index] == 'r') && (data[++index] == 'i') && (data[++index] == 'v') && (data[++index] == 'a') + && (data[++index] == 't') && (data[++index] == 'e')) { + return TokenNameprivate; + } else + return TokenNameIdentifier; + case 9: + if ((data[++index] == 'r') && (data[++index] == 'o') && (data[++index] == 't') && (data[++index] == 'e') + && (data[++index] == 'c') && (data[++index] == 't') && (data[++index] == 'e') && (data[++index] == 'd')) { + return TokenNameprotected; + } else + return TokenNameIdentifier; + } + return TokenNameIdentifier; + case 'r': + //return require require_once + if (length == 6) { + if ((data[++index] == 'e') && (data[++index] == 't') && (data[++index] == 'u') && (data[++index] == 'r') + && (data[++index] == 'n')) { + return TokenNamereturn; } - case 'v' : - //var - switch (length) { - case 3 : - if ((data[++index] == 'a') && (data[++index] == 'r')) - return TokenNamevar; - else - return TokenNameIdentifier; - default : - return TokenNameIdentifier; + } else if (length == 7) { + if ((data[++index] == 'e') && (data[++index] == 'q') && (data[++index] == 'u') && (data[++index] == 'i') + && (data[++index] == 'r') && (data[++index] == 'e')) { + return TokenNamerequire; } - case 'w' : - //while - switch (length) { - case 5 : - if ((data[++index] == 'h') && (data[++index] == 'i') - && (data[++index] == 'l') && (data[++index] == 'e')) - return TokenNamewhile; - else - return TokenNameIdentifier; - //case 6:if ( (data[++index] =='i') && (data[++index]=='d') && - // (data[++index]=='e') && (data[++index]=='f')&& - // (data[++index]=='p')) - //return TokenNamewidefp ; - //else - //return TokenNameIdentifier; - default : - return TokenNameIdentifier; + } else if (length == 12) { + if ((data[++index] == 'e') && (data[++index] == 'q') && (data[++index] == 'u') && (data[++index] == 'i') + && (data[++index] == 'r') && (data[++index] == 'e') && (data[++index] == '_') && (data[++index] == 'o') + && (data[++index] == 'n') && (data[++index] == 'c') && (data[++index] == 'e')) { + return TokenNamerequire_once; } - case 'x' : - //xor - switch (length) { - case 3 : - if ((data[++index] == 'o') && (data[++index] == 'r')) - return TokenNamexor; - else - return TokenNameIdentifier; - default : + } else + return TokenNameIdentifier; + case 's': + //static switch + switch (length) { + case 6: + if (data[++index] == 't') + if ((data[++index] == 'a') && (data[++index] == 't') && (data[++index] == 'i') && (data[++index] == 'c')) { + return TokenNamestatic; + } else return TokenNameIdentifier; - } - default : + else if ((data[index] == 'w') && (data[++index] == 'i') && (data[++index] == 't') && (data[++index] == 'c') + && (data[++index] == 'h')) + return TokenNameswitch; + else + return TokenNameIdentifier; + default: + return TokenNameIdentifier; + } + case 't': + // try true throw + switch (length) { + case 3: + if ((data[++index] == 'r') && (data[++index] == 'y')) + return TokenNametry; + else + return TokenNameIdentifier; + // case 4 : + // if ((data[++index] == 'r') && (data[++index] == 'u') + // && (data[++index] == 'e')) + // return TokenNametrue; + // else + // return TokenNameIdentifier; + case 5: + if ((data[++index] == 'h') && (data[++index] == 'r') && (data[++index] == 'o') && (data[++index] == 'w')) + return TokenNamethrow; + else + return TokenNameIdentifier; + default: + return TokenNameIdentifier; + } + case 'u': + //use unset + switch (length) { + case 3: + if ((data[++index] == 's') && (data[++index] == 'e')) + return TokenNameuse; + else + return TokenNameIdentifier; + case 5: + if ((data[++index] == 'n') && (data[++index] == 's') && (data[++index] == 'e') && (data[++index] == 't')) + return TokenNameunset; + else + return TokenNameIdentifier; + default: + return TokenNameIdentifier; + } + case 'v': + //var + switch (length) { + case 3: + if ((data[++index] == 'a') && (data[++index] == 'r')) + return TokenNamevar; + else + return TokenNameIdentifier; + default: + return TokenNameIdentifier; + } + case 'w': + //while + switch (length) { + case 5: + if ((data[++index] == 'h') && (data[++index] == 'i') && (data[++index] == 'l') && (data[++index] == 'e')) + return TokenNamewhile; + else + return TokenNameIdentifier; + //case 6:if ( (data[++index] =='i') && (data[++index]=='d') && + // (data[++index]=='e') && (data[++index]=='f')&& + // (data[++index]=='p')) + //return TokenNamewidefp ; + //else + //return TokenNameIdentifier; + default: return TokenNameIdentifier; + } + case 'x': + //xor + switch (length) { + case 3: + if ((data[++index] == 'o') && (data[++index] == 'r')) + return TokenNamexor; + else + return TokenNameIdentifier; + default: + return TokenNameIdentifier; + } + default: + return TokenNameIdentifier; } } + public int scanNumber(boolean dotPrefix) throws InvalidInputException { //when entering this method the currentCharacter is the firt //digit of the number , i.e. it may be preceeded by a . when @@ -3423,7 +3467,8 @@ public class Scanner implements IScanner, ITerminalSymbols { throw new InvalidInputException(INVALID_HEXA); //---end forcing-- while (getNextCharAsDigit(16)) { - }; + } + ; // if (getNextChar('l', 'L') >= 0) // return TokenNameLongLiteral; // else @@ -3435,7 +3480,8 @@ public class Scanner implements IScanner, ITerminalSymbols { if (getNextCharAsDigit()) { //-------------potential octal----------------- while (getNextCharAsDigit()) { - }; + } + ; // if (getNextChar('l', 'L') >= 0) { // return TokenNameLongLiteral; // } @@ -3448,7 +3494,8 @@ public class Scanner implements IScanner, ITerminalSymbols { } else { //make the distinction between octal and float .... if (getNextChar('.')) { //bingo ! .... while (getNextCharAsDigit()) { - }; + } + ; if (getNextChar('e', 'E') >= 0) { // consume next character unicodeAsBackSlash = false; @@ -3478,7 +3525,8 @@ public class Scanner implements IScanner, ITerminalSymbols { if (!Character.isDigit(currentCharacter)) throw new InvalidInputException(INVALID_FLOAT); while (getNextCharAsDigit()) { - }; + } + ; } // if (getNextChar('f', 'F') >= 0) // return TokenNameFloatingPointLiteral; @@ -3493,12 +3541,14 @@ public class Scanner implements IScanner, ITerminalSymbols { } } while (getNextCharAsDigit()) { - }; + } + ; // if ((!dotPrefix) && (getNextChar('l', 'L') >= 0)) // return TokenNameLongLiteral; if ((!dotPrefix) && (getNextChar('.'))) { //decimal part that can be empty while (getNextCharAsDigit()) { - }; + } + ; floating = true; } //if floating is true both exponant and suffix may be optional @@ -3532,7 +3582,8 @@ public class Scanner implements IScanner, ITerminalSymbols { if (!Character.isDigit(currentCharacter)) throw new InvalidInputException(INVALID_FLOAT); while (getNextCharAsDigit()) { - }; + } + ; } if (getNextChar('d', 'D') >= 0) return TokenNameDoubleLiteral; @@ -3541,6 +3592,7 @@ public class Scanner implements IScanner, ITerminalSymbols { //the long flag has been tested before return floating ? TokenNameDoubleLiteral : TokenNameIntegerLiteral; } + /** * Search the line number corresponding to a specific position * @@ -3568,9 +3620,11 @@ public class Scanner implements IScanner, ITerminalSymbols { } return m + 2; } + public void setPHPMode(boolean mode) { phpMode = mode; } + public final void setSource(char[] source) { //the source-buffer is set to sourceString if (source == null) { @@ -3584,6 +3638,7 @@ public class Scanner implements IScanner, ITerminalSymbols { withoutUnicodeBuffer = new char[this.source.length]; encapsedStringStack = new Stack(); } + public String toString() { if (startPosition == source.length) return "EOF\n\n" + new String(source); //$NON-NLS-1$ @@ -3600,328 +3655,322 @@ public class Scanner implements IScanner, ITerminalSymbols { middle = new char[0]; } char end[] = new char[source.length - (currentPosition - 1)]; - System.arraycopy(source, (currentPosition - 1) + 1, end, 0, source.length - - (currentPosition - 1) - 1); - return new String(front) - + "\n===============================\nStarts here -->" //$NON-NLS-1$ - + new String(middle) - + "<-- Ends here\n===============================\n" //$NON-NLS-1$ + System.arraycopy(source, (currentPosition - 1) + 1, end, 0, source.length - (currentPosition - 1) - 1); + return new String(front) + "\n===============================\nStarts here -->" //$NON-NLS-1$ + + new String(middle) + "<-- Ends here\n===============================\n" //$NON-NLS-1$ + new String(end); } + public final String toStringAction(int act) { switch (act) { - case TokenNameERROR : - return "ScannerError"; // + new String(getCurrentTokenSource()) + ")"; - // //$NON-NLS-1$ - case TokenNameINLINE_HTML : - return "Inline-HTML(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ - case TokenNameIdentifier : - return "Identifier(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ - case TokenNameVariable : - return "Variable(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ - case TokenNameabstract : - return "abstract"; //$NON-NLS-1$ - case TokenNameand : - return "AND"; //$NON-NLS-1$ - case TokenNamearray : - return "array"; //$NON-NLS-1$ - case TokenNameas : - return "as"; //$NON-NLS-1$ - case TokenNamebreak : - return "break"; //$NON-NLS-1$ - case TokenNamecase : - return "case"; //$NON-NLS-1$ - case TokenNameclass : - return "class"; //$NON-NLS-1$ - case TokenNamecatch : - return "catch"; //$NON-NLS-1$ - case TokenNameclone : - //$NON-NLS-1$ - return "clone"; - case TokenNameconst : - //$NON-NLS-1$ - return "const"; - case TokenNamecontinue : - return "continue"; //$NON-NLS-1$ - case TokenNamedefault : - return "default"; //$NON-NLS-1$ - // case TokenNamedefine : - // return "define"; //$NON-NLS-1$ - case TokenNamedo : - return "do"; //$NON-NLS-1$ - case TokenNameecho : - return "echo"; //$NON-NLS-1$ - case TokenNameelse : - return "else"; //$NON-NLS-1$ - case TokenNameelseif : - return "elseif"; //$NON-NLS-1$ - case TokenNameendfor : - return "endfor"; //$NON-NLS-1$ - case TokenNameendforeach : - return "endforeach"; //$NON-NLS-1$ - case TokenNameendif : - return "endif"; //$NON-NLS-1$ - case TokenNameendswitch : - return "endswitch"; //$NON-NLS-1$ - case TokenNameendwhile : - return "endwhile"; //$NON-NLS-1$ - case TokenNameexit: - return "exit"; - case TokenNameextends : - return "extends"; //$NON-NLS-1$ - // case TokenNamefalse : - // return "false"; //$NON-NLS-1$ - case TokenNamefinal : - return "final"; //$NON-NLS-1$ - case TokenNamefor : - return "for"; //$NON-NLS-1$ - case TokenNameforeach : - return "foreach"; //$NON-NLS-1$ - case TokenNamefunction : - return "function"; //$NON-NLS-1$ - case TokenNameglobal : - return "global"; //$NON-NLS-1$ - case TokenNameif : - return "if"; //$NON-NLS-1$ - case TokenNameimplements : - return "implements"; //$NON-NLS-1$ - case TokenNameinclude : - return "include"; //$NON-NLS-1$ - case TokenNameinclude_once : - return "include_once"; //$NON-NLS-1$ - case TokenNameinstanceof : - return "instanceof"; //$NON-NLS-1$ - case TokenNameinterface : - return "interface"; //$NON-NLS-1$ - case TokenNameisset : - return "isset"; //$NON-NLS-1$ - case TokenNamelist : - return "list"; //$NON-NLS-1$ - case TokenNamenew : - return "new"; //$NON-NLS-1$ - // case TokenNamenull : - // return "null"; //$NON-NLS-1$ - case TokenNameor : - return "OR"; //$NON-NLS-1$ - case TokenNameprint : - return "print"; //$NON-NLS-1$ - case TokenNameprivate : - return "private"; //$NON-NLS-1$ - case TokenNameprotected : - return "protected"; //$NON-NLS-1$ - case TokenNamepublic : - return "public"; //$NON-NLS-1$ - case TokenNamerequire : - return "require"; //$NON-NLS-1$ - case TokenNamerequire_once : - return "require_once"; //$NON-NLS-1$ - case TokenNamereturn : - return "return"; //$NON-NLS-1$ - case TokenNamestatic : - return "static"; //$NON-NLS-1$ - case TokenNameswitch : - return "switch"; //$NON-NLS-1$ - // case TokenNametrue : - // return "true"; //$NON-NLS-1$ - case TokenNameunset : - return "unset"; //$NON-NLS-1$ - case TokenNamevar : - return "var"; //$NON-NLS-1$ - case TokenNamewhile : - return "while"; //$NON-NLS-1$ - case TokenNamexor : - return "XOR"; //$NON-NLS-1$ - // case TokenNamethis : - // return "$this"; //$NON-NLS-1$ - case TokenNameIntegerLiteral : - return "Integer(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ - case TokenNameDoubleLiteral : - return "Double(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ - case TokenNameStringDoubleQuote : - return "StringLiteral(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ - case TokenNameStringSingleQuote : - return "StringConstant(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ - case TokenNameStringInterpolated : - return "StringInterpolated(" + new String(getCurrentTokenSource()) - + ")"; //$NON-NLS-1$ //$NON-NLS-2$ - case TokenNameEncapsedString0 : - return "`"; //$NON-NLS-1$ - case TokenNameEncapsedString1 : - return "\'"; //$NON-NLS-1$ - case TokenNameEncapsedString2 : - return "\""; //$NON-NLS-1$ - case TokenNameSTRING : - return "STRING(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ - case TokenNameHEREDOC : - return "HEREDOC(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ - case TokenNamePLUS_PLUS : - return "++"; //$NON-NLS-1$ - case TokenNameMINUS_MINUS : - return "--"; //$NON-NLS-1$ - case TokenNameEQUAL_EQUAL : - return "=="; //$NON-NLS-1$ - case TokenNameEQUAL_EQUAL_EQUAL : - return "==="; //$NON-NLS-1$ - case TokenNameEQUAL_GREATER : - return "=>"; //$NON-NLS-1$ - case TokenNameLESS_EQUAL : - return "<="; //$NON-NLS-1$ - case TokenNameGREATER_EQUAL : - return ">="; //$NON-NLS-1$ - case TokenNameNOT_EQUAL : - return "!="; //$NON-NLS-1$ - case TokenNameNOT_EQUAL_EQUAL : - return "!=="; //$NON-NLS-1$ - case TokenNameLEFT_SHIFT : - return "<<"; //$NON-NLS-1$ - case TokenNameRIGHT_SHIFT : - return ">>"; //$NON-NLS-1$ - case TokenNamePLUS_EQUAL : - return "+="; //$NON-NLS-1$ - case TokenNameMINUS_EQUAL : - return "-="; //$NON-NLS-1$ - case TokenNameMULTIPLY_EQUAL : - return "*="; //$NON-NLS-1$ - case TokenNameDIVIDE_EQUAL : - return "/="; //$NON-NLS-1$ - case TokenNameAND_EQUAL : - return "&="; //$NON-NLS-1$ - case TokenNameOR_EQUAL : - return "|="; //$NON-NLS-1$ - case TokenNameXOR_EQUAL : - return "^="; //$NON-NLS-1$ - case TokenNameREMAINDER_EQUAL : - return "%="; //$NON-NLS-1$ - case TokenNameDOT_EQUAL : - return ".="; //$NON-NLS-1$ - case TokenNameLEFT_SHIFT_EQUAL : - return "<<="; //$NON-NLS-1$ - case TokenNameRIGHT_SHIFT_EQUAL : - return ">>="; //$NON-NLS-1$ - case TokenNameOR_OR : - return "||"; //$NON-NLS-1$ - case TokenNameAND_AND : - return "&&"; //$NON-NLS-1$ - case TokenNamePLUS : - return "+"; //$NON-NLS-1$ - case TokenNameMINUS : - return "-"; //$NON-NLS-1$ - case TokenNameMINUS_GREATER : - return "->"; - case TokenNameNOT : - return "!"; //$NON-NLS-1$ - case TokenNameREMAINDER : - return "%"; //$NON-NLS-1$ - case TokenNameXOR : - return "^"; //$NON-NLS-1$ - case TokenNameAND : - return "&"; //$NON-NLS-1$ - case TokenNameMULTIPLY : - return "*"; //$NON-NLS-1$ - case TokenNameOR : - return "|"; //$NON-NLS-1$ - case TokenNameTWIDDLE : - return "~"; //$NON-NLS-1$ - case TokenNameTWIDDLE_EQUAL : - return "~="; //$NON-NLS-1$ - case TokenNameDIVIDE : - return "/"; //$NON-NLS-1$ - case TokenNameGREATER : - return ">"; //$NON-NLS-1$ - case TokenNameLESS : - return "<"; //$NON-NLS-1$ - case TokenNameLPAREN : - return "("; //$NON-NLS-1$ - case TokenNameRPAREN : - return ")"; //$NON-NLS-1$ - case TokenNameLBRACE : - return "{"; //$NON-NLS-1$ - case TokenNameRBRACE : - return "}"; //$NON-NLS-1$ - case TokenNameLBRACKET : - return "["; //$NON-NLS-1$ - case TokenNameRBRACKET : - return "]"; //$NON-NLS-1$ - case TokenNameSEMICOLON : - return ";"; //$NON-NLS-1$ - case TokenNameQUESTION : - return "?"; //$NON-NLS-1$ - case TokenNameCOLON : - return ":"; //$NON-NLS-1$ - case TokenNameCOMMA : - return ","; //$NON-NLS-1$ - case TokenNameDOT : - return "."; //$NON-NLS-1$ - case TokenNameEQUAL : - return "="; //$NON-NLS-1$ - case TokenNameAT : - return "@"; - case TokenNameDOLLAR : - return "$"; - case TokenNameDOLLAR_LBRACE : - return "${"; - case TokenNameLBRACE_DOLLAR : - return "{$"; - case TokenNameEOF : - return "EOF"; //$NON-NLS-1$ - case TokenNameWHITESPACE : - return "WHITESPACE(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ - case TokenNameCOMMENT_LINE : - return "COMMENT_LINE(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ - case TokenNameCOMMENT_BLOCK : - return "COMMENT_BLOCK(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ - case TokenNameCOMMENT_PHPDOC : - return "COMMENT_PHPDOC(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ - // case TokenNameHTML : - // return "HTML(" + new String(getCurrentTokenSource()) + ")"; - // //$NON-NLS-1$ - case TokenNameFILE : - return "__FILE__"; //$NON-NLS-1$ - case TokenNameLINE : - return "__LINE__"; //$NON-NLS-1$ - case TokenNameCLASS_C : - return "__CLASS__"; //$NON-NLS-1$ - case TokenNameMETHOD_C : - return "__METHOD__"; //$NON-NLS-1$ - case TokenNameFUNC_C : - return "__FUNCTION__"; //$NON-NLS-1 - case TokenNameboolCAST : - return "( bool )"; //$NON-NLS-1$ - case TokenNameintCAST : - return "( int )"; //$NON-NLS-1$ - case TokenNamedoubleCAST : - return "( double )"; //$NON-NLS-1$ - case TokenNameobjectCAST : - return "( object )"; //$NON-NLS-1$ - case TokenNamestringCAST : - return "( string )"; //$NON-NLS-1$ - default : - return "not-a-token(" + (new Integer(act)) + ") " - + new String(getCurrentTokenSource()); //$NON-NLS-1$ + case TokenNameERROR: + return "ScannerError"; // + new String(getCurrentTokenSource()) + ")"; + // //$NON-NLS-1$ + case TokenNameINLINE_HTML: + return "Inline-HTML(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ + case TokenNameIdentifier: + return "Identifier(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ + case TokenNameVariable: + return "Variable(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ + case TokenNameabstract: + return "abstract"; //$NON-NLS-1$ + case TokenNameand: + return "AND"; //$NON-NLS-1$ + case TokenNamearray: + return "array"; //$NON-NLS-1$ + case TokenNameas: + return "as"; //$NON-NLS-1$ + case TokenNamebreak: + return "break"; //$NON-NLS-1$ + case TokenNamecase: + return "case"; //$NON-NLS-1$ + case TokenNameclass: + return "class"; //$NON-NLS-1$ + case TokenNamecatch: + return "catch"; //$NON-NLS-1$ + case TokenNameclone: + //$NON-NLS-1$ + return "clone"; + case TokenNameconst: + //$NON-NLS-1$ + return "const"; + case TokenNamecontinue: + return "continue"; //$NON-NLS-1$ + case TokenNamedefault: + return "default"; //$NON-NLS-1$ + // case TokenNamedefine : + // return "define"; //$NON-NLS-1$ + case TokenNamedo: + return "do"; //$NON-NLS-1$ + case TokenNameecho: + return "echo"; //$NON-NLS-1$ + case TokenNameelse: + return "else"; //$NON-NLS-1$ + case TokenNameelseif: + return "elseif"; //$NON-NLS-1$ + case TokenNameendfor: + return "endfor"; //$NON-NLS-1$ + case TokenNameendforeach: + return "endforeach"; //$NON-NLS-1$ + case TokenNameendif: + return "endif"; //$NON-NLS-1$ + case TokenNameendswitch: + return "endswitch"; //$NON-NLS-1$ + case TokenNameendwhile: + return "endwhile"; //$NON-NLS-1$ + case TokenNameexit: + return "exit"; + case TokenNameextends: + return "extends"; //$NON-NLS-1$ + // case TokenNamefalse : + // return "false"; //$NON-NLS-1$ + case TokenNamefinal: + return "final"; //$NON-NLS-1$ + case TokenNamefor: + return "for"; //$NON-NLS-1$ + case TokenNameforeach: + return "foreach"; //$NON-NLS-1$ + case TokenNamefunction: + return "function"; //$NON-NLS-1$ + case TokenNameglobal: + return "global"; //$NON-NLS-1$ + case TokenNameif: + return "if"; //$NON-NLS-1$ + case TokenNameimplements: + return "implements"; //$NON-NLS-1$ + case TokenNameinclude: + return "include"; //$NON-NLS-1$ + case TokenNameinclude_once: + return "include_once"; //$NON-NLS-1$ + case TokenNameinstanceof: + return "instanceof"; //$NON-NLS-1$ + case TokenNameinterface: + return "interface"; //$NON-NLS-1$ + case TokenNameisset: + return "isset"; //$NON-NLS-1$ + case TokenNamelist: + return "list"; //$NON-NLS-1$ + case TokenNamenew: + return "new"; //$NON-NLS-1$ + // case TokenNamenull : + // return "null"; //$NON-NLS-1$ + case TokenNameor: + return "OR"; //$NON-NLS-1$ + case TokenNameprint: + return "print"; //$NON-NLS-1$ + case TokenNameprivate: + return "private"; //$NON-NLS-1$ + case TokenNameprotected: + return "protected"; //$NON-NLS-1$ + case TokenNamepublic: + return "public"; //$NON-NLS-1$ + case TokenNamerequire: + return "require"; //$NON-NLS-1$ + case TokenNamerequire_once: + return "require_once"; //$NON-NLS-1$ + case TokenNamereturn: + return "return"; //$NON-NLS-1$ + case TokenNamestatic: + return "static"; //$NON-NLS-1$ + case TokenNameswitch: + return "switch"; //$NON-NLS-1$ + // case TokenNametrue : + // return "true"; //$NON-NLS-1$ + case TokenNameunset: + return "unset"; //$NON-NLS-1$ + case TokenNamevar: + return "var"; //$NON-NLS-1$ + case TokenNamewhile: + return "while"; //$NON-NLS-1$ + case TokenNamexor: + return "XOR"; //$NON-NLS-1$ + // case TokenNamethis : + // return "$this"; //$NON-NLS-1$ + case TokenNameIntegerLiteral: + return "Integer(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ + case TokenNameDoubleLiteral: + return "Double(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ + case TokenNameStringDoubleQuote: + return "StringLiteral(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ + case TokenNameStringSingleQuote: + return "StringConstant(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ + case TokenNameStringInterpolated: + return "StringInterpolated(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ + case TokenNameEncapsedString0: + return "`"; //$NON-NLS-1$ + case TokenNameEncapsedString1: + return "\'"; //$NON-NLS-1$ + case TokenNameEncapsedString2: + return "\""; //$NON-NLS-1$ + case TokenNameSTRING: + return "STRING(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ + case TokenNameHEREDOC: + return "HEREDOC(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ + case TokenNamePLUS_PLUS: + return "++"; //$NON-NLS-1$ + case TokenNameMINUS_MINUS: + return "--"; //$NON-NLS-1$ + case TokenNameEQUAL_EQUAL: + return "=="; //$NON-NLS-1$ + case TokenNameEQUAL_EQUAL_EQUAL: + return "==="; //$NON-NLS-1$ + case TokenNameEQUAL_GREATER: + return "=>"; //$NON-NLS-1$ + case TokenNameLESS_EQUAL: + return "<="; //$NON-NLS-1$ + case TokenNameGREATER_EQUAL: + return ">="; //$NON-NLS-1$ + case TokenNameNOT_EQUAL: + return "!="; //$NON-NLS-1$ + case TokenNameNOT_EQUAL_EQUAL: + return "!=="; //$NON-NLS-1$ + case TokenNameLEFT_SHIFT: + return "<<"; //$NON-NLS-1$ + case TokenNameRIGHT_SHIFT: + return ">>"; //$NON-NLS-1$ + case TokenNamePLUS_EQUAL: + return "+="; //$NON-NLS-1$ + case TokenNameMINUS_EQUAL: + return "-="; //$NON-NLS-1$ + case TokenNameMULTIPLY_EQUAL: + return "*="; //$NON-NLS-1$ + case TokenNameDIVIDE_EQUAL: + return "/="; //$NON-NLS-1$ + case TokenNameAND_EQUAL: + return "&="; //$NON-NLS-1$ + case TokenNameOR_EQUAL: + return "|="; //$NON-NLS-1$ + case TokenNameXOR_EQUAL: + return "^="; //$NON-NLS-1$ + case TokenNameREMAINDER_EQUAL: + return "%="; //$NON-NLS-1$ + case TokenNameDOT_EQUAL: + return ".="; //$NON-NLS-1$ + case TokenNameLEFT_SHIFT_EQUAL: + return "<<="; //$NON-NLS-1$ + case TokenNameRIGHT_SHIFT_EQUAL: + return ">>="; //$NON-NLS-1$ + case TokenNameOR_OR: + return "||"; //$NON-NLS-1$ + case TokenNameAND_AND: + return "&&"; //$NON-NLS-1$ + case TokenNamePLUS: + return "+"; //$NON-NLS-1$ + case TokenNameMINUS: + return "-"; //$NON-NLS-1$ + case TokenNameMINUS_GREATER: + return "->"; + case TokenNameNOT: + return "!"; //$NON-NLS-1$ + case TokenNameREMAINDER: + return "%"; //$NON-NLS-1$ + case TokenNameXOR: + return "^"; //$NON-NLS-1$ + case TokenNameAND: + return "&"; //$NON-NLS-1$ + case TokenNameMULTIPLY: + return "*"; //$NON-NLS-1$ + case TokenNameOR: + return "|"; //$NON-NLS-1$ + case TokenNameTWIDDLE: + return "~"; //$NON-NLS-1$ + case TokenNameTWIDDLE_EQUAL: + return "~="; //$NON-NLS-1$ + case TokenNameDIVIDE: + return "/"; //$NON-NLS-1$ + case TokenNameGREATER: + return ">"; //$NON-NLS-1$ + case TokenNameLESS: + return "<"; //$NON-NLS-1$ + case TokenNameLPAREN: + return "("; //$NON-NLS-1$ + case TokenNameRPAREN: + return ")"; //$NON-NLS-1$ + case TokenNameLBRACE: + return "{"; //$NON-NLS-1$ + case TokenNameRBRACE: + return "}"; //$NON-NLS-1$ + case TokenNameLBRACKET: + return "["; //$NON-NLS-1$ + case TokenNameRBRACKET: + return "]"; //$NON-NLS-1$ + case TokenNameSEMICOLON: + return ";"; //$NON-NLS-1$ + case TokenNameQUESTION: + return "?"; //$NON-NLS-1$ + case TokenNameCOLON: + return ":"; //$NON-NLS-1$ + case TokenNameCOMMA: + return ","; //$NON-NLS-1$ + case TokenNameDOT: + return "."; //$NON-NLS-1$ + case TokenNameEQUAL: + return "="; //$NON-NLS-1$ + case TokenNameAT: + return "@"; + case TokenNameDOLLAR: + return "$"; + case TokenNameDOLLAR_LBRACE: + return "${"; + case TokenNameLBRACE_DOLLAR: + return "{$"; + case TokenNameEOF: + return "EOF"; //$NON-NLS-1$ + case TokenNameWHITESPACE: + return "WHITESPACE(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ + case TokenNameCOMMENT_LINE: + return "COMMENT_LINE(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ + case TokenNameCOMMENT_BLOCK: + return "COMMENT_BLOCK(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ + case TokenNameCOMMENT_PHPDOC: + return "COMMENT_PHPDOC(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ + // case TokenNameHTML : + // return "HTML(" + new String(getCurrentTokenSource()) + ")"; + // //$NON-NLS-1$ + case TokenNameFILE: + return "__FILE__"; //$NON-NLS-1$ + case TokenNameLINE: + return "__LINE__"; //$NON-NLS-1$ + case TokenNameCLASS_C: + return "__CLASS__"; //$NON-NLS-1$ + case TokenNameMETHOD_C: + return "__METHOD__"; //$NON-NLS-1$ + case TokenNameFUNC_C: + return "__FUNCTION__"; //$NON-NLS-1 + case TokenNameboolCAST: + return "( bool )"; //$NON-NLS-1$ + case TokenNameintCAST: + return "( int )"; //$NON-NLS-1$ + case TokenNamedoubleCAST: + return "( double )"; //$NON-NLS-1$ + case TokenNameobjectCAST: + return "( object )"; //$NON-NLS-1$ + case TokenNamestringCAST: + return "( string )"; //$NON-NLS-1$ + default: + return "not-a-token(" + (new Integer(act)) + ") " + new String(getCurrentTokenSource()); //$NON-NLS-1$ } } - + public Scanner() { this(false, false); } + public Scanner(boolean tokenizeComments, boolean tokenizeWhiteSpace) { this(tokenizeComments, tokenizeWhiteSpace, false); } - public Scanner(boolean tokenizeComments, boolean tokenizeWhiteSpace, - boolean checkNonExternalizedStringLiterals) { - this(tokenizeComments, tokenizeWhiteSpace, - checkNonExternalizedStringLiterals, false); + + public Scanner(boolean tokenizeComments, boolean tokenizeWhiteSpace, boolean checkNonExternalizedStringLiterals) { + this(tokenizeComments, tokenizeWhiteSpace, checkNonExternalizedStringLiterals, false); } - public Scanner(boolean tokenizeComments, boolean tokenizeWhiteSpace, - boolean checkNonExternalizedStringLiterals, boolean assertMode) { - this(tokenizeComments, tokenizeWhiteSpace, - checkNonExternalizedStringLiterals, assertMode, false, null, null); + + public Scanner(boolean tokenizeComments, boolean tokenizeWhiteSpace, boolean checkNonExternalizedStringLiterals, + boolean assertMode) { + this(tokenizeComments, tokenizeWhiteSpace, checkNonExternalizedStringLiterals, assertMode, false, null, null); } - public Scanner(boolean tokenizeComments, boolean tokenizeWhiteSpace, - boolean checkNonExternalizedStringLiterals, boolean assertMode, - boolean tokenizeStrings, - char[][] taskTags, - char[][] taskPriorities) { + + public Scanner(boolean tokenizeComments, boolean tokenizeWhiteSpace, boolean checkNonExternalizedStringLiterals, + boolean assertMode, boolean tokenizeStrings, char[][] taskTags, char[][] taskPriorities) { this.eofPosition = Integer.MAX_VALUE; this.tokenizeComments = tokenizeComments; this.tokenizeWhiteSpace = tokenizeWhiteSpace; @@ -3930,13 +3979,15 @@ public class Scanner implements IScanner, ITerminalSymbols { this.assertMode = assertMode; this.encapsedStringStack = null; this.taskTags = taskTags; - this.taskPriorities = taskPriorities; + this.taskPriorities = taskPriorities; } + private void checkNonExternalizeString() throws InvalidInputException { if (currentLine == null) return; parseTags(currentLine); } + private void parseTags(NLSLine line) throws InvalidInputException { String s = new String(getCurrentTokenSource()); int pos = s.indexOf(TAG_PREFIX); @@ -3972,12 +4023,11 @@ public class Scanner implements IScanner, ITerminalSymbols { } this.wasNonExternalizedStringLiteral = true; if (nonNLSCounter != lineLength) { - System.arraycopy(this.nonNLSStrings, 0, - (this.nonNLSStrings = new StringLiteral[nonNLSCounter]), 0, - nonNLSCounter); + System.arraycopy(this.nonNLSStrings, 0, (this.nonNLSStrings = new StringLiteral[nonNLSCounter]), 0, nonNLSCounter); } currentLine = null; } + public final void scanEscapeCharacter() throws InvalidInputException { // the string with "\\u" is a legal string of two chars \ and u //thus we use a direct access to the source (for regular cases). @@ -3995,94 +4045,89 @@ public class Scanner implements IScanner, ITerminalSymbols { } else currentCharacter = source[currentPosition++]; switch (currentCharacter) { - case 'b' : - currentCharacter = '\b'; - break; - case 't' : - currentCharacter = '\t'; - break; - case 'n' : - currentCharacter = '\n'; - break; - case 'f' : - currentCharacter = '\f'; - break; - case 'r' : - currentCharacter = '\r'; - break; - case '\"' : - currentCharacter = '\"'; - break; - case '\'' : - currentCharacter = '\''; - break; - case '\\' : - currentCharacter = '\\'; - break; - default : - // -----------octal escape-------------- - // OctalDigit - // OctalDigit OctalDigit - // ZeroToThree OctalDigit OctalDigit - int number = Character.getNumericValue(currentCharacter); - if (number >= 0 && number <= 7) { - boolean zeroToThreeNot = number > 3; - if (Character.isDigit(currentCharacter = source[currentPosition++])) { - int digit = Character.getNumericValue(currentCharacter); - if (digit >= 0 && digit <= 7) { - number = (number * 8) + digit; - if (Character - .isDigit(currentCharacter = source[currentPosition++])) { - if (zeroToThreeNot) { // has read \NotZeroToThree OctalDigit - // Digit --> ignore last character + case 'b': + currentCharacter = '\b'; + break; + case 't': + currentCharacter = '\t'; + break; + case 'n': + currentCharacter = '\n'; + break; + case 'f': + currentCharacter = '\f'; + break; + case 'r': + currentCharacter = '\r'; + break; + case '\"': + currentCharacter = '\"'; + break; + case '\'': + currentCharacter = '\''; + break; + case '\\': + currentCharacter = '\\'; + break; + default: + // -----------octal escape-------------- + // OctalDigit + // OctalDigit OctalDigit + // ZeroToThree OctalDigit OctalDigit + int number = Character.getNumericValue(currentCharacter); + if (number >= 0 && number <= 7) { + boolean zeroToThreeNot = number > 3; + if (Character.isDigit(currentCharacter = source[currentPosition++])) { + int digit = Character.getNumericValue(currentCharacter); + if (digit >= 0 && digit <= 7) { + number = (number * 8) + digit; + if (Character.isDigit(currentCharacter = source[currentPosition++])) { + if (zeroToThreeNot) { // has read \NotZeroToThree OctalDigit + // Digit --> ignore last character + currentPosition--; + } else { + digit = Character.getNumericValue(currentCharacter); + if (digit >= 0 && digit <= 7) { // has read \ZeroToThree + // OctalDigit OctalDigit + number = (number * 8) + digit; + } else { // has read \ZeroToThree OctalDigit NonOctalDigit + // --> ignore last character currentPosition--; - } else { - digit = Character.getNumericValue(currentCharacter); - if (digit >= 0 && digit <= 7) { // has read \ZeroToThree - // OctalDigit OctalDigit - number = (number * 8) + digit; - } else { // has read \ZeroToThree OctalDigit NonOctalDigit - // --> ignore last character - currentPosition--; - } } - } else { // has read \OctalDigit NonDigit--> ignore last - // character - currentPosition--; } - } else { // has read \OctalDigit NonOctalDigit--> ignore last + } else { // has read \OctalDigit NonDigit--> ignore last // character currentPosition--; } - } else { // has read \OctalDigit --> ignore last character + } else { // has read \OctalDigit NonOctalDigit--> ignore last + // character currentPosition--; } - if (number > 255) - throw new InvalidInputException(INVALID_ESCAPE); - currentCharacter = (char) number; - } else + } else { // has read \OctalDigit --> ignore last character + currentPosition--; + } + if (number > 255) throw new InvalidInputException(INVALID_ESCAPE); + currentCharacter = (char) number; + } else + throw new InvalidInputException(INVALID_ESCAPE); } } + // chech presence of task: tags public void checkTaskTag(int commentStart, int commentEnd) { // only look for newer task: tags - if (this.foundTaskCount > 0 - && this.foundTaskPositions[this.foundTaskCount - 1][0] >= commentStart) { + if (this.foundTaskCount > 0 && this.foundTaskPositions[this.foundTaskCount - 1][0] >= commentStart) { return; } int foundTaskIndex = this.foundTaskCount; - nextChar : for (int i = commentStart; i < commentEnd - && i < this.eofPosition; i++) { + nextChar: for (int i = commentStart; i < commentEnd && i < this.eofPosition; i++) { char[] tag = null; char[] priority = null; // check for tag occurrence - nextTag : for (int itag = 0; itag < this.taskTags.length; itag++) { + nextTag: for (int itag = 0; itag < this.taskTags.length; itag++) { tag = this.taskTags[itag]; - priority = this.taskPriorities != null - && itag < this.taskPriorities.length - ? this.taskPriorities[itag] - : null; + priority = this.taskPriorities != null && itag < this.taskPriorities.length ? this.taskPriorities[itag] : null; int tagLength = tag.length; for (int t = 0; t < tagLength; t++) { if (this.source[i + t] != tag[t]) @@ -4094,23 +4139,17 @@ public class Scanner implements IScanner, ITerminalSymbols { this.foundTaskPriorities = new char[5][]; this.foundTaskPositions = new int[5][]; } else if (this.foundTaskCount == this.foundTaskTags.length) { - System.arraycopy(this.foundTaskTags, 0, - this.foundTaskTags = new char[this.foundTaskCount * 2][], 0, + System.arraycopy(this.foundTaskTags, 0, this.foundTaskTags = new char[this.foundTaskCount * 2][], 0, this.foundTaskCount); + System.arraycopy(this.foundTaskMessages, 0, this.foundTaskMessages = new char[this.foundTaskCount * 2][], 0, this.foundTaskCount); - System.arraycopy(this.foundTaskMessages, 0, - this.foundTaskMessages = new char[this.foundTaskCount * 2][], 0, + System.arraycopy(this.foundTaskPriorities, 0, this.foundTaskPriorities = new char[this.foundTaskCount * 2][], 0, this.foundTaskCount); - System.arraycopy(this.foundTaskPriorities, 0, - this.foundTaskPriorities = new char[this.foundTaskCount * 2][], - 0, this.foundTaskCount); - System.arraycopy(this.foundTaskPositions, 0, - this.foundTaskPositions = new int[this.foundTaskCount * 2][], 0, + System.arraycopy(this.foundTaskPositions, 0, this.foundTaskPositions = new int[this.foundTaskCount * 2][], 0, this.foundTaskCount); } this.foundTaskTags[this.foundTaskCount] = tag; this.foundTaskPriorities[this.foundTaskCount] = priority; - this.foundTaskPositions[this.foundTaskCount] = new int[]{i, - i + tagLength - 1}; + this.foundTaskPositions[this.foundTaskCount] = new int[] { i, i + tagLength - 1 }; this.foundTaskMessages[this.foundTaskCount] = CharOperation.NO_CHAR; this.foundTaskCount++; i += tagLength - 1; // will be incremented when looping @@ -4118,11 +4157,8 @@ public class Scanner implements IScanner, ITerminalSymbols { } for (int i = foundTaskIndex; i < this.foundTaskCount; i++) { // retrieve message start and end positions - int msgStart = this.foundTaskPositions[i][0] - + this.foundTaskTags[i].length; - int max_value = i + 1 < this.foundTaskCount - ? this.foundTaskPositions[i + 1][0] - 1 - : commentEnd - 1; + int msgStart = this.foundTaskPositions[i][0] + this.foundTaskTags[i].length; + int max_value = i + 1 < this.foundTaskCount ? this.foundTaskPositions[i + 1][0] - 1 : commentEnd - 1; // at most beginning of next task if (max_value < msgStart) max_value = msgStart; // would only occur if tag is before EOF. @@ -4160,4 +4196,4 @@ public class Scanner implements IScanner, ITerminalSymbols { this.foundTaskMessages[i] = message; } } -} +} \ No newline at end of file