X-Git-Url: http://secure.phpeclipse.com 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 0dacb72..2206c00 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 @@ -14,7 +14,9 @@ import java.util.ArrayList; import java.util.Iterator; import java.util.List; -import net.sourceforge.phpdt.core.compiler.*; +import net.sourceforge.phpdt.core.compiler.IScanner; +import net.sourceforge.phpdt.core.compiler.ITerminalSymbols; +import net.sourceforge.phpdt.core.compiler.InvalidInputException; import net.sourceforge.phpdt.internal.compiler.ast.StringLiteral; public class Scanner implements IScanner, ITerminalSymbols { @@ -116,14 +118,12 @@ public class Scanner implements IScanner, ITerminalSymbols { 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[] 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][]; + final char[][][][] charArray_length = new char[OptimizedLength][TableSize][InternalTableSize][]; // support for detecting non-externalized string literals int currentLineNr = -1; int previousLineNr = -1; @@ -146,11 +146,7 @@ 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; @@ -158,6 +154,7 @@ public class Scanner implements IScanner, ITerminalSymbols { public static final int BracketKinds = 3; public static final boolean DEBUG = false; + public Scanner() { this(false, false); } @@ -170,7 +167,7 @@ public class Scanner implements IScanner, ITerminalSymbols { * permissible as the first character in a PHP identifier */ public static boolean isPHPIdentifierStart(char ch) { - return Character.isLetter(ch) || (ch == '_'); + return Character.isLetter(ch) || (ch == '_') || (0x7F <= ch && ch <= 0xFF); } /** @@ -178,7 +175,7 @@ public class Scanner implements IScanner, ITerminalSymbols { * other than the first character */ public static boolean isPHPIdentifierPart(char ch) { - return Character.isLetterOrDigit(ch) || (ch == '_'); + return Character.isLetterOrDigit(ch) || (ch == '_') || (0x7F <= ch && ch <= 0xFF); } public final boolean atEnd() { @@ -191,64 +188,55 @@ public class Scanner implements IScanner, ITerminalSymbols { //return the token REAL source (aka unicodes are precomputed) 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, - 1, - result = new char[withoutUnicodePtr], - 0, - withoutUnicodePtr); - 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(); - } - //no optimization - System.arraycopy( - source, - startPosition, - result = new char[length], - 0, - length); + // if (withoutUnicodePtr != 0) + // //0 is used as a fast test flag so the real first char is in position 1 + // System.arraycopy( + // withoutUnicodeBuffer, + // 1, + // result = new char[withoutUnicodePtr], + // 0, + // withoutUnicodePtr); + // 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(); } + //no optimization + 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; - if (withoutUnicodePtr != 0) - // 0 is used as a fast test flag so the real first char is in position 1 - System.arraycopy( - withoutUnicodeBuffer, - 1, - result = new char[withoutUnicodePtr], - 0, - withoutUnicodePtr); - else { - int length; - System.arraycopy( - source, - startPosition, - result = new char[length = currentPosition - startPosition], - 0, - length); - } + // if (withoutUnicodePtr != 0) + // // 0 is used as a fast test flag so the real first char is in position 1 + // System.arraycopy( + // withoutUnicodeBuffer, + // 1, + // result = new char[withoutUnicodePtr], + // 0, + // withoutUnicodePtr); + // else { + int length; + System.arraycopy(source, startPosition, result = new char[length = currentPosition - startPosition], 0, length); + // } return result; } @@ -256,23 +244,18 @@ public class Scanner implements IScanner, ITerminalSymbols { // Return the token REAL source (aka unicodes are precomputed) 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, - 1, - result = new char[withoutUnicodePtr], - 0, - withoutUnicodePtr); - else { - int length; - System.arraycopy( - source, - startPos, - result = new char[length = currentPosition - startPos], - 0, - length); - } + // if (withoutUnicodePtr != 0) + // // 0 is used as a fast test flag so the real first char is in position 1 + // System.arraycopy( + // withoutUnicodeBuffer, + // 1, + // result = new char[withoutUnicodePtr], + // 0, + // withoutUnicodePtr); + // else { + int length; + System.arraycopy(source, startPos, result = new char[length = currentPosition - startPos], 0, length); + // } return result; } @@ -288,18 +271,25 @@ public class Scanner implements IScanner, ITerminalSymbols { 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); + // } + return result; + } + /* * Search the source position corresponding to the end of a given line number * @@ -359,62 +349,63 @@ public class Scanner implements IScanner, ITerminalSymbols { int temp = currentPosition; try { - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - //-------------unicode traitement ------------ - int c1, c2, c3, c4; - int unicodeSize = 6; - currentPosition++; - while (source[currentPosition] == 'u') { - currentPosition++; - unicodeSize++; - } - - 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)) { - currentPosition = temp; - return false; - } - - currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - if (currentCharacter != testedChar) { - currentPosition = temp; - return false; - } - unicodeAsBackSlash = currentCharacter == '\\'; - - //need the unicode buffer - if (withoutUnicodePtr == 0) { - //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - unicodeSize - startPosition; - System.arraycopy( - source, - startPosition, - withoutUnicodeBuffer, - 1, - withoutUnicodePtr); - } - //fill the buffer with the char - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return true; - - } //-------------end unicode traitement-------------- - else { - if (currentCharacter != testedChar) { - currentPosition = temp; - return false; - } - unicodeAsBackSlash = false; - if (withoutUnicodePtr != 0) - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return true; + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1, c2, c3, c4; + // int unicodeSize = 6; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // unicodeSize++; + // } + // + // 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)) { + // currentPosition = temp; + // return false; + // } + // + // currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // if (currentCharacter != testedChar) { + // currentPosition = temp; + // return false; + // } + // unicodeAsBackSlash = currentCharacter == '\\'; + // + // //need the unicode buffer + // if (withoutUnicodePtr == 0) { + // //buffer all the entries that have been left aside.... + // withoutUnicodePtr = currentPosition - unicodeSize - startPosition; + // System.arraycopy( + // source, + // startPosition, + // withoutUnicodeBuffer, + // 1, + // withoutUnicodePtr); + // } + // //fill the buffer with the char + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // return true; + // + // } //-------------end unicode traitement-------------- + // else { + if (currentCharacter != testedChar) { + currentPosition = temp; + return false; } + unicodeAsBackSlash = false; + // if (withoutUnicodePtr != 0) + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + return true; + // } } catch (IndexOutOfBoundsException e) { unicodeAsBackSlash = false; currentPosition = temp; @@ -436,68 +427,69 @@ public class Scanner implements IScanner, ITerminalSymbols { int temp = currentPosition; try { int result; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - //-------------unicode traitement ------------ - int c1, c2, c3, c4; - int unicodeSize = 6; - currentPosition++; - while (source[currentPosition] == 'u') { - currentPosition++; - unicodeSize++; - } - - 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)) { - currentPosition = temp; - return 2; - } - - currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - if (currentCharacter == testedChar1) - result = 0; - else if (currentCharacter == testedChar2) - result = 1; - else { - currentPosition = temp; - return -1; - } - - //need the unicode buffer - if (withoutUnicodePtr == 0) { - //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - unicodeSize - startPosition; - System.arraycopy( - source, - startPosition, - withoutUnicodeBuffer, - 1, - withoutUnicodePtr); - } - //fill the buffer with the char - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return result; - } //-------------end unicode traitement-------------- + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1, c2, c3, c4; + // int unicodeSize = 6; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // unicodeSize++; + // } + // + // 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)) { + // currentPosition = temp; + // return 2; + // } + // + // currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // if (currentCharacter == testedChar1) + // result = 0; + // else if (currentCharacter == testedChar2) + // result = 1; + // else { + // currentPosition = temp; + // return -1; + // } + // + // //need the unicode buffer + // if (withoutUnicodePtr == 0) { + // //buffer all the entries that have been left aside.... + // withoutUnicodePtr = currentPosition - unicodeSize - startPosition; + // System.arraycopy( + // source, + // startPosition, + // withoutUnicodeBuffer, + // 1, + // withoutUnicodePtr); + // } + // //fill the buffer with the char + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // return result; + // } //-------------end unicode traitement-------------- + // else { + if (currentCharacter == testedChar1) + result = 0; + else if (currentCharacter == testedChar2) + result = 1; else { - if (currentCharacter == testedChar1) - result = 0; - else if (currentCharacter == testedChar2) - result = 1; - else { - currentPosition = temp; - return -1; - } - - if (withoutUnicodePtr != 0) - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return result; + currentPosition = temp; + return -1; } + + // if (withoutUnicodePtr != 0) + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + return result; + // } } catch (IndexOutOfBoundsException e) { currentPosition = temp; return -1; @@ -516,59 +508,60 @@ public class Scanner implements IScanner, ITerminalSymbols { int temp = currentPosition; try { - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - //-------------unicode traitement ------------ - int c1, c2, c3, c4; - int unicodeSize = 6; - currentPosition++; - while (source[currentPosition] == 'u') { - currentPosition++; - unicodeSize++; - } - - 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)) { - currentPosition = temp; - return false; - } - - currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - if (!Character.isDigit(currentCharacter)) { - currentPosition = temp; - return false; - } - - //need the unicode buffer - if (withoutUnicodePtr == 0) { - //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - unicodeSize - startPosition; - System.arraycopy( - source, - startPosition, - withoutUnicodeBuffer, - 1, - withoutUnicodePtr); - } - //fill the buffer with the char - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return true; - } //-------------end unicode traitement-------------- - else { - if (!Character.isDigit(currentCharacter)) { - currentPosition = temp; - return false; - } - if (withoutUnicodePtr != 0) - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return true; + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1, c2, c3, c4; + // int unicodeSize = 6; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // unicodeSize++; + // } + // + // 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)) { + // currentPosition = temp; + // return false; + // } + // + // currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // if (!Character.isDigit(currentCharacter)) { + // currentPosition = temp; + // return false; + // } + // + // //need the unicode buffer + // if (withoutUnicodePtr == 0) { + // //buffer all the entries that have been left aside.... + // withoutUnicodePtr = currentPosition - unicodeSize - startPosition; + // System.arraycopy( + // source, + // startPosition, + // withoutUnicodeBuffer, + // 1, + // withoutUnicodePtr); + // } + // //fill the buffer with the char + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // return true; + // } //-------------end unicode traitement-------------- + // else { + if (!Character.isDigit(currentCharacter)) { + currentPosition = temp; + return false; } + // if (withoutUnicodePtr != 0) + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + return true; + // } } catch (IndexOutOfBoundsException e) { currentPosition = temp; return false; @@ -587,59 +580,60 @@ public class Scanner implements IScanner, ITerminalSymbols { int temp = currentPosition; try { - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - //-------------unicode traitement ------------ - int c1, c2, c3, c4; - int unicodeSize = 6; - currentPosition++; - while (source[currentPosition] == 'u') { - currentPosition++; - unicodeSize++; - } - - 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)) { - currentPosition = temp; - return false; - } - - currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - if (Character.digit(currentCharacter, radix) == -1) { - currentPosition = temp; - return false; - } - - //need the unicode buffer - if (withoutUnicodePtr == 0) { - //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - unicodeSize - startPosition; - System.arraycopy( - source, - startPosition, - withoutUnicodeBuffer, - 1, - withoutUnicodePtr); - } - //fill the buffer with the char - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return true; - } //-------------end unicode traitement-------------- - else { - if (Character.digit(currentCharacter, radix) == -1) { - currentPosition = temp; - return false; - } - if (withoutUnicodePtr != 0) - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return true; + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1, c2, c3, c4; + // int unicodeSize = 6; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // unicodeSize++; + // } + // + // 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)) { + // currentPosition = temp; + // return false; + // } + // + // currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // if (Character.digit(currentCharacter, radix) == -1) { + // currentPosition = temp; + // return false; + // } + // + // //need the unicode buffer + // if (withoutUnicodePtr == 0) { + // //buffer all the entries that have been left aside.... + // withoutUnicodePtr = currentPosition - unicodeSize - startPosition; + // System.arraycopy( + // source, + // startPosition, + // withoutUnicodeBuffer, + // 1, + // withoutUnicodePtr); + // } + // //fill the buffer with the char + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // return true; + // } //-------------end unicode traitement-------------- + // else { + if (Character.digit(currentCharacter, radix) == -1) { + currentPosition = temp; + return false; } + // if (withoutUnicodePtr != 0) + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + return true; + // } } catch (IndexOutOfBoundsException e) { currentPosition = temp; return false; @@ -658,60 +652,61 @@ public class Scanner implements IScanner, ITerminalSymbols { int temp = currentPosition; try { - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - //-------------unicode traitement ------------ - int c1, c2, c3, c4; - int unicodeSize = 6; - currentPosition++; - while (source[currentPosition] == 'u') { - currentPosition++; - unicodeSize++; - } - - 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)) { - currentPosition = temp; - return false; - } - - currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - if (!isPHPIdentifierPart(currentCharacter)) { - currentPosition = temp; - return false; - } - - //need the unicode buffer - if (withoutUnicodePtr == 0) { - //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - unicodeSize - startPosition; - System.arraycopy( - source, - startPosition, - withoutUnicodeBuffer, - 1, - withoutUnicodePtr); - } - //fill the buffer with the char - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return true; - } //-------------end unicode traitement-------------- - else { - if (!isPHPIdentifierPart(currentCharacter)) { - currentPosition = temp; - return false; - } - - if (withoutUnicodePtr != 0) - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - return true; + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // //-------------unicode traitement ------------ + // int c1, c2, c3, c4; + // int unicodeSize = 6; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // unicodeSize++; + // } + // + // 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)) { + // currentPosition = temp; + // return false; + // } + // + // currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // if (!isPHPIdentifierPart(currentCharacter)) { + // currentPosition = temp; + // return false; + // } + // + // //need the unicode buffer + // if (withoutUnicodePtr == 0) { + // //buffer all the entries that have been left aside.... + // withoutUnicodePtr = currentPosition - unicodeSize - startPosition; + // System.arraycopy( + // source, + // startPosition, + // withoutUnicodeBuffer, + // 1, + // withoutUnicodePtr); + // } + // //fill the buffer with the char + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // return true; + // } //-------------end unicode traitement-------------- + // else { + if (!isPHPIdentifierPart(currentCharacter)) { + currentPosition = temp; + return false; } + + // if (withoutUnicodePtr != 0) + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + return true; + // } } catch (IndexOutOfBoundsException e) { currentPosition = temp; return false; @@ -726,8 +721,7 @@ public class Scanner implements IScanner, ITerminalSymbols { if (currentCharacter == '<') { if (getNextChar('?')) { currentCharacter = source[currentPosition++]; - if ((currentCharacter == ' ') - || Character.isWhitespace(currentCharacter)) { + if ((currentCharacter == ' ') || Character.isWhitespace(currentCharacter)) { // = 0) { @@ -797,22 +790,21 @@ public class Scanner implements IScanner, ITerminalSymbols { boolean isWhiteSpace; do { startPosition = currentPosition; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - isWhiteSpace = jumpOverUnicodeWhiteSpace(); - } else { - if ((currentCharacter == '\r') || (currentCharacter == '\n')) { - checkNonExternalizeString(); - if (recordLineSeparator) { - pushLineSeparator(); - } else { - currentLine = null; - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // isWhiteSpace = jumpOverUnicodeWhiteSpace(); + // } else { + if ((currentCharacter == '\r') || (currentCharacter == '\n')) { + checkNonExternalizeString(); + if (recordLineSeparator) { + pushLineSeparator(); + } else { + currentLine = null; } - isWhiteSpace = - (currentCharacter == ' ') - || Character.isWhitespace(currentCharacter); } + isWhiteSpace = (currentCharacter == ' ') || Character.isWhitespace(currentCharacter); + // } } while (isWhiteSpace); if (tokenizeWhiteSpace && (whiteStart != currentPosition - 1)) { // reposition scanner in case we are interested by spaces as tokens @@ -874,8 +866,12 @@ public class Scanner implements IScanner, ITerminalSymbols { return TokenNameTWIDDLE_EQUAL; return TokenNameTWIDDLE; case '!' : - if (getNextChar('=')) + if (getNextChar('=')) { + if (getNextChar('=')) { + return TokenNameNOT_EQUAL_EQUAL; + } return TokenNameNOT_EQUAL; + } return TokenNameNOT; case '*' : if (getNextChar('=')) @@ -920,8 +916,7 @@ public class Scanner implements IScanner, ITerminalSymbols { currentLine = null; } for (int i = 0; i < heredocLength; i++) { - if (source[currentPosition + i] - != source[heredocStart + i]) { + if (source[currentPosition + i] != source[heredocStart + i]) { endTag = false; break; } @@ -956,8 +951,12 @@ public class Scanner implements IScanner, ITerminalSymbols { return TokenNameGREATER; } case '=' : - if (getNextChar('=')) + if (getNextChar('=')) { + if (getNextChar('=')) { + return TokenNameEQUAL_EQUAL_EQUAL; + } return TokenNameEQUAL_EQUAL; + } if (getNextChar('>')) return TokenNameEQUAL_GREATER; return TokenNameEQUAL; @@ -1073,15 +1072,16 @@ public class Scanner implements IScanner, ITerminalSymbols { try { // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = + // currentCharacter; + // } + // } while (currentCharacter != '\'') { @@ -1109,19 +1109,11 @@ 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); - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; + withoutUnicodePtr = currentPosition - escapeSize - 1 - startPosition; + System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, withoutUnicodePtr); + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } else { //overwrite the / in the buffer - withoutUnicodeBuffer[withoutUnicodePtr] = - currentCharacter; + withoutUnicodeBuffer[withoutUnicodePtr] = currentCharacter; if (backSlashAsUnicodeInString) { //there are TWO \ in the stream where only one is correct withoutUnicodePtr--; } @@ -1129,15 +1121,15 @@ public class Scanner implements IScanner, ITerminalSymbols { } // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + if (withoutUnicodePtr != 0) { + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } + // } } } catch (IndexOutOfBoundsException e) { @@ -1164,26 +1156,23 @@ public class Scanner implements IScanner, ITerminalSymbols { currentLine = new NLSLine(); lines.add(currentLine); } - currentLine.add( - new StringLiteral( - getCurrentTokenSourceString(), - startPosition, - currentPosition - 1)); + currentLine.add(new StringLiteral(getCurrentTokenSourceString(), startPosition, currentPosition - 1)); } return TokenNameStringConstant; case '"' : try { // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = + // currentCharacter; + // } + // } while (currentCharacter != '"') { @@ -1211,19 +1200,11 @@ 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); - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; + withoutUnicodePtr = currentPosition - escapeSize - 1 - startPosition; + System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, withoutUnicodePtr); + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } else { //overwrite the / in the buffer - withoutUnicodeBuffer[withoutUnicodePtr] = - currentCharacter; + withoutUnicodeBuffer[withoutUnicodePtr] = currentCharacter; if (backSlashAsUnicodeInString) { //there are TWO \ in the stream where only one is correct withoutUnicodePtr--; } @@ -1231,15 +1212,15 @@ public class Scanner implements IScanner, ITerminalSymbols { } // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + if (withoutUnicodePtr != 0) { + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } + // } } } catch (IndexOutOfBoundsException e) { @@ -1266,26 +1247,23 @@ public class Scanner implements IScanner, ITerminalSymbols { currentLine = new NLSLine(); lines.add(currentLine); } - currentLine.add( - new StringLiteral( - getCurrentTokenSourceString(), - startPosition, - currentPosition - 1)); + currentLine.add(new StringLiteral(getCurrentTokenSourceString(), startPosition, currentPosition - 1)); } return TokenNameStringLiteral; case '`' : try { // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = + // currentCharacter; + // } + // } while (currentCharacter != '`') { @@ -1313,19 +1291,11 @@ 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); - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; + withoutUnicodePtr = currentPosition - escapeSize - 1 - startPosition; + System.arraycopy(source, startPosition, withoutUnicodeBuffer, 1, withoutUnicodePtr); + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } else { //overwrite the / in the buffer - withoutUnicodeBuffer[withoutUnicodePtr] = - currentCharacter; + withoutUnicodeBuffer[withoutUnicodePtr] = currentCharacter; if (backSlashAsUnicodeInString) { //there are TWO \ in the stream where only one is correct withoutUnicodePtr--; } @@ -1333,15 +1303,15 @@ public class Scanner implements IScanner, ITerminalSymbols { } // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + if (withoutUnicodePtr != 0) { + withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; } + // } } } catch (IndexOutOfBoundsException e) { @@ -1368,62 +1338,57 @@ public class Scanner implements IScanner, ITerminalSymbols { currentLine = new NLSLine(); lines.add(currentLine); } - currentLine.add( - new StringLiteral( - getCurrentTokenSourceString(), - startPosition, - currentPosition - 1)); + currentLine.add(new StringLiteral(getCurrentTokenSourceString(), startPosition, currentPosition - 1)); } return TokenNameStringInterpolated; case '#' : case '/' : { int test; - if ((currentCharacter == '#') - || (test = getNextChar('/', '*')) == 0) { + if ((currentCharacter == '#') || (test = getNextChar('/', '*')) == 0) { //line comment int endPositionForLineComment = 0; try { //get the next char - 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); - } - } + 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 \\ + // if (currentCharacter == '\\') { + // if (source[currentPosition] == '\\') + // currentPosition++; + // } //jump over the \\ boolean isUnicode = false; - while (currentCharacter != '\r' - && currentCharacter != '\n') { + while (currentCharacter != '\r' && currentCharacter != '\n') { if (currentCharacter == '?') { if (getNextChar('>')) { startPosition = currentPosition - 2; @@ -1434,46 +1399,47 @@ public class Scanner implements IScanner, ITerminalSymbols { //get the next char isUnicode = false; - 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); - } - } + 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 \\ + // if (currentCharacter == '\\') { + // if (source[currentPosition] == '\\') + // currentPosition++; + // } //jump over the \\ } if (isUnicode) { endPositionForLineComment = currentPosition - 6; @@ -1481,8 +1447,7 @@ public class Scanner implements IScanner, ITerminalSymbols { endPositionForLineComment = currentPosition - 1; } recordComment(false); - if ((currentCharacter == '\r') - || (currentCharacter == '\n')) { + if ((currentCharacter == '\r') || (currentCharacter == '\n')) { checkNonExternalizeString(); if (recordLineSeparator) { if (isUnicode) { @@ -1515,22 +1480,22 @@ public class Scanner implements IScanner, ITerminalSymbols { boolean isJavadoc = false, star = false; // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } - } + 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')) { + if ((currentCharacter == '\r') || (currentCharacter == '\n')) { checkNonExternalizeString(); if (recordLineSeparator) { pushLineSeparator(); @@ -1539,26 +1504,26 @@ public class Scanner implements IScanner, ITerminalSymbols { } } try { //get the next char - if (((currentCharacter = source[currentPosition++]) - == '\\') - && (source[currentPosition] == 'u')) { - //-------------unicode traitement ------------ - getNextUnicodeChar(); - } + 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 \\ - } + // 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')) { + if ((currentCharacter == '\r') || (currentCharacter == '\n')) { checkNonExternalizeString(); if (recordLineSeparator) { pushLineSeparator(); @@ -1568,17 +1533,18 @@ public class Scanner implements IScanner, ITerminalSymbols { } star = currentCharacter == '*'; //get next char - if (((currentCharacter = source[currentPosition++]) - == '\\') - && (source[currentPosition] == 'u')) { - //-------------unicode traitement ------------ - getNextUnicodeChar(); - } + 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 \\ + // if (currentCharacter == '\\') { + // if (source[currentPosition] == '\\') + // currentPosition++; + // } //jump over the \\ } recordComment(isJavadoc); if (tokenizeComments) { @@ -1625,50 +1591,50 @@ public class Scanner implements IScanner, ITerminalSymbols { return TokenNameEOF; } - public final void getNextUnicodeChar() - throws IndexOutOfBoundsException, InvalidInputException { - //VOID - //handle the case of unicode. - //when a unicode appears then we must use a buffer that holds char internal values - //At the end of this method currentCharacter holds the new visited char - //and currentPosition points right next after it - - //ALL getNextChar.... ARE OPTIMIZED COPIES - - int c1 = 0, c2 = 0, c3 = 0, c4 = 0, unicodeSize = 6; - currentPosition++; - while (source[currentPosition] == 'u') { - currentPosition++; - unicodeSize++; - } - - 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); - //need the unicode buffer - if (withoutUnicodePtr == 0) { - //buffer all the entries that have been left aside.... - withoutUnicodePtr = currentPosition - unicodeSize - startPosition; - System.arraycopy( - source, - startPosition, - withoutUnicodeBuffer, - 1, - withoutUnicodePtr); - } - //fill the buffer with the char - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } - unicodeAsBackSlash = currentCharacter == '\\'; - } + // public final void getNextUnicodeChar() + // throws IndexOutOfBoundsException, InvalidInputException { + // //VOID + // //handle the case of unicode. + // //when a unicode appears then we must use a buffer that holds char internal values + // //At the end of this method currentCharacter holds the new visited char + // //and currentPosition points right next after it + // + // //ALL getNextChar.... ARE OPTIMIZED COPIES + // + // int c1 = 0, c2 = 0, c3 = 0, c4 = 0, unicodeSize = 6; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // unicodeSize++; + // } + // + // 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); + // //need the unicode buffer + // if (withoutUnicodePtr == 0) { + // //buffer all the entries that have been left aside.... + // withoutUnicodePtr = currentPosition - unicodeSize - startPosition; + // System.arraycopy( + // source, + // startPosition, + // withoutUnicodeBuffer, + // 1, + // withoutUnicodePtr); + // } + // //fill the buffer with the char + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // } + // unicodeAsBackSlash = currentCharacter == '\\'; + // } /* Tokenize a method body, assuming that curly brackets are properly balanced. */ public final void jumpOverMethodBody() { @@ -1681,15 +1647,15 @@ public class Scanner implements IScanner, ITerminalSymbols { boolean isWhiteSpace; do { startPosition = currentPosition; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - isWhiteSpace = jumpOverUnicodeWhiteSpace(); - } else { - if (recordLineSeparator - && ((currentCharacter == '\r') || (currentCharacter == '\n'))) - pushLineSeparator(); - isWhiteSpace = Character.isWhitespace(currentCharacter); - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // isWhiteSpace = jumpOverUnicodeWhiteSpace(); + // } else { + if (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n'))) + pushLineSeparator(); + isWhiteSpace = Character.isWhitespace(currentCharacter); + // } } while (isWhiteSpace); // -------consume token until } is found--------- @@ -1712,38 +1678,38 @@ public class Scanner implements IScanner, ITerminalSymbols { } catch (InvalidInputException ex) { }; } else { - try { // consume next character - unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } - } - } catch (InvalidInputException ex) { - }; + // 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; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } - } - } catch (InvalidInputException ex) { - }; + // 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') @@ -1761,19 +1727,19 @@ public class Scanner implements IScanner, ITerminalSymbols { } catch (InvalidInputException ex) { }; } - try { // consume next character - unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } - } - } catch (InvalidInputException ex) { - }; + // 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) { + // }; } } catch (IndexOutOfBoundsException e) { return; @@ -1786,78 +1752,78 @@ public class Scanner implements IScanner, ITerminalSymbols { //line comment try { //get the next char - 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); - } - } + 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') { + while (currentCharacter != '\r' && currentCharacter != '\n') { //get the next char - 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); - } - } + 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'))) + if (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n'))) pushLineSeparator(); } catch (IndexOutOfBoundsException e) { } //an eof will them be generated @@ -1866,99 +1832,98 @@ public class Scanner implements IScanner, ITerminalSymbols { if (test > 0) { //traditional and annotation comment boolean star = false; - try { // consume next character - unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } - }; - } catch (InvalidInputException ex) { - }; + // 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 (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n'))) pushLineSeparator(); try { //get the next char - 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); - } - } + 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'))) + if (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n'))) pushLineSeparator(); star = currentCharacter == '*'; //get next char - 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); - } - } + 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; @@ -1969,8 +1934,7 @@ public class Scanner implements IScanner, ITerminalSymbols { } default : - if (isPHPIdentifierStart(currentCharacter) - || currentCharacter == '$') { + if (isPHPIdentifierStart(currentCharacter) || currentCharacter == '$') { try { scanIdentifierOrKeyword((currentCharacter == '$')); } catch (InvalidInputException ex) { @@ -1992,50 +1956,50 @@ public class Scanner implements IScanner, ITerminalSymbols { } return; } - public final boolean jumpOverUnicodeWhiteSpace() - throws InvalidInputException { - //BOOLEAN - //handle the case of unicode. Jump over the next whiteSpace - //making startPosition pointing on the next available char - //On false, the currentCharacter is filled up with a potential - //correct char - - try { - this.wasAcr = false; - int c1, c2, c3, c4; - int unicodeSize = 6; - currentPosition++; - while (source[currentPosition] == 'u') { - currentPosition++; - unicodeSize++; - } - - 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); - } - - currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); - if (recordLineSeparator - && ((currentCharacter == '\r') || (currentCharacter == '\n'))) - pushLineSeparator(); - if (Character.isWhitespace(currentCharacter)) - return true; - - //buffer the new char which is not a white space - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - //withoutUnicodePtr == 1 is true here - return false; - } catch (IndexOutOfBoundsException e) { - throw new InvalidInputException(INVALID_UNICODE_ESCAPE); - } - } + // public final boolean jumpOverUnicodeWhiteSpace() + // throws InvalidInputException { + // //BOOLEAN + // //handle the case of unicode. Jump over the next whiteSpace + // //making startPosition pointing on the next available char + // //On false, the currentCharacter is filled up with a potential + // //correct char + // + // try { + // this.wasAcr = false; + // int c1, c2, c3, c4; + // int unicodeSize = 6; + // currentPosition++; + // while (source[currentPosition] == 'u') { + // currentPosition++; + // unicodeSize++; + // } + // + // 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); + // } + // + // currentCharacter = (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4); + // if (recordLineSeparator + // && ((currentCharacter == '\r') || (currentCharacter == '\n'))) + // pushLineSeparator(); + // if (Character.isWhitespace(currentCharacter)) + // return true; + // + // //buffer the new char which is not a white space + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // //withoutUnicodePtr == 1 is true here + // return false; + // } catch (IndexOutOfBoundsException e) { + // throw new InvalidInputException(INVALID_UNICODE_ESCAPE); + // } + // } public final int[] getLineEnds() { //return a bounded copy of this.lineEnds @@ -2114,9 +2078,7 @@ public class Scanner implements IScanner, ITerminalSymbols { //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) { @@ -2146,9 +2108,7 @@ public class Scanner implements IScanner, ITerminalSymbols { char c0, c1, c2; int hash = - (((c0 = source[startPosition]) << 12) - + ((c1 = source[startPosition + 1]) << 6) - + (c2 = source[startPosition + 2])) + (((c0 = source[startPosition]) << 12) + ((c1 = source[startPosition + 1]) << 6) + (c2 = source[startPosition + 2])) % TableSize; char[][] table = charArray_length[1][hash]; int i = newEntry3; @@ -2188,10 +2148,7 @@ public class Scanner implements IScanner, ITerminalSymbols { 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--------- @@ -2199,10 +2156,7 @@ 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------- @@ -2230,11 +2184,7 @@ public class Scanner implements IScanner, ITerminalSymbols { 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--------- @@ -2242,11 +2192,7 @@ 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------- @@ -2440,8 +2386,7 @@ public class Scanner implements IScanner, ITerminalSymbols { // a new annotation comment is recorded try { - commentStops[++commentPtr] = - isJavadoc ? currentPosition : -currentPosition; + commentStops[++commentPtr] = isJavadoc ? currentPosition : -currentPosition; } catch (IndexOutOfBoundsException e) { int oldStackLength = commentStops.length; int[] oldStack = commentStops; @@ -2466,24 +2411,23 @@ public class Scanner implements IScanner, ITerminalSymbols { 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) { - // consume next character - unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } - } - } else - currentCharacter = source[currentPosition++]; + // if (unicodeAsBackSlash) { + // // consume next character + // unicodeAsBackSlash = false; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // } + // } + // } else + currentCharacter = source[currentPosition++]; switch (currentCharacter) { case '\'' : currentCharacter = '\''; @@ -2497,24 +2441,23 @@ public class Scanner implements IScanner, ITerminalSymbols { } } - 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) { - // consume next character - unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } - } - } else - currentCharacter = source[currentPosition++]; + // if (unicodeAsBackSlash) { + // // consume next character + // unicodeAsBackSlash = false; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // } + // } + // } else + currentCharacter = source[currentPosition++]; switch (currentCharacter) { // case 'b' : // currentCharacter = '\b'; @@ -2552,13 +2495,11 @@ public class Scanner implements IScanner, ITerminalSymbols { int number = Character.getNumericValue(currentCharacter); if (number >= 0 && number <= 7) { boolean zeroToThreeNot = number > 3; - if (Character - .isDigit(currentCharacter = source[currentPosition++])) { + 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 (Character.isDigit(currentCharacter = source[currentPosition++])) { if (zeroToThreeNot) { // has read \NotZeroToThree OctalDigit Digit --> ignore last character currentPosition--; } else { @@ -2592,8 +2533,7 @@ public class Scanner implements IScanner, ITerminalSymbols { // 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. @@ -2607,37 +2547,40 @@ public class Scanner implements IScanner, ITerminalSymbols { }; if (isVariable) { + if (new String(getCurrentTokenSource()).equals("$this")) { + return TokenNamethis; + } return TokenNameVariable; } int index, length; char[] data; char firstLetter; - if (withoutUnicodePtr == 0) - - //quick test on length == 1 but not on length > 12 while most identifier - //have a length which is <= 12...but there are lots of identifier with - //only one char.... - - { - if ((length = currentPosition - startPosition) == 1) - return TokenNameIdentifier; - // data = source; - data = new char[length]; - index = startPosition; - for (int i = 0; i < length; i++) { - data[i] = Character.toLowerCase(source[index + i]); - } - index = 0; - } else { - if ((length = withoutUnicodePtr) == 1) - return TokenNameIdentifier; - // data = withoutUnicodeBuffer; - data = new char[withoutUnicodeBuffer.length]; - for (int i = 0; i < withoutUnicodeBuffer.length; i++) { - data[i] = Character.toLowerCase(withoutUnicodeBuffer[i]); - } - index = 1; + // if (withoutUnicodePtr == 0) + + //quick test on length == 1 but not on length > 12 while most identifier + //have a length which is <= 12...but there are lots of identifier with + //only one char.... + + // { + if ((length = currentPosition - startPosition) == 1) + return TokenNameIdentifier; + // data = source; + data = new char[length]; + index = startPosition; + for (int i = 0; i < length; i++) { + data[i] = Character.toLowerCase(source[index + i]); } + index = 0; + // } else { + // if ((length = withoutUnicodePtr) == 1) + // return TokenNameIdentifier; + // // data = withoutUnicodeBuffer; + // data = new char[withoutUnicodeBuffer.length]; + // for (int i = 0; i < withoutUnicodeBuffer.length; i++) { + // data[i] = Character.toLowerCase(withoutUnicodeBuffer[i]); + // } + // index = 1; + // } firstLetter = data[index]; switch (firstLetter) { @@ -2667,10 +2610,7 @@ public class Scanner implements IScanner, ITerminalSymbols { case 'b' : //break switch (length) { case 5 : - if ((data[++index] == 'r') - && (data[++index] == 'e') - && (data[++index] == 'a') - && (data[++index] == 'k')) + if ((data[++index] == 'r') && (data[++index] == 'e') && (data[++index] == 'a') && (data[++index] == 'k')) return TokenNamebreak; else return TokenNameIdentifier; @@ -2681,17 +2621,12 @@ public class Scanner implements IScanner, ITerminalSymbols { case 'c' : //case class continue switch (length) { case 4 : - if ((data[++index] == 'a') - && (data[++index] == 's') - && (data[++index] == 'e')) + if ((data[++index] == 'a') && (data[++index] == 's') && (data[++index] == 'e')) return TokenNamecase; else return TokenNameIdentifier; case 5 : - if ((data[++index] == 'l') - && (data[++index] == 'a') - && (data[++index] == 's') - && (data[++index] == 's')) + if ((data[++index] == 'l') && (data[++index] == 'a') && (data[++index] == 's') && (data[++index] == 's')) return TokenNameclass; else return TokenNameIdentifier; @@ -2742,22 +2677,14 @@ public class Scanner implements IScanner, ITerminalSymbols { case 'e' : //echo else elseif extends switch (length) { case 4 : - if ((data[++index] == 'c') - && (data[++index] == 'h') - && (data[++index] == 'o')) + if ((data[++index] == 'c') && (data[++index] == 'h') && (data[++index] == 'o')) return TokenNameecho; - else if ( - (data[index] == 'l') - && (data[++index] == 's') - && (data[++index] == 'e')) + else if ((data[index] == 'l') && (data[++index] == 's') && (data[++index] == 'e')) return TokenNameelse; else return TokenNameIdentifier; case 5 : // endif - if ((data[++index] == 'n') - && (data[++index] == 'd') - && (data[++index] == 'i') - && (data[++index] == 'f')) + if ((data[++index] == 'n') && (data[++index] == 'd') && (data[++index] == 'i') && (data[++index] == 'f')) return TokenNameendif; else return TokenNameIdentifier; @@ -2836,10 +2763,7 @@ public class Scanner implements IScanner, ITerminalSymbols { else return TokenNameIdentifier; case 5 : - if ((data[++index] == 'a') - && (data[++index] == 'l') - && (data[++index] == 's') - && (data[++index] == 'e')) + if ((data[++index] == 'a') && (data[++index] == 'l') && (data[++index] == 's') && (data[++index] == 'e')) return TokenNamefalse; else return TokenNameIdentifier; @@ -2922,9 +2846,7 @@ public class Scanner implements IScanner, ITerminalSymbols { case 'l' : //list if (length == 4) { - if ((data[++index] == 'i') - && (data[++index] == 's') - && (data[++index] == 't')) { + if ((data[++index] == 'i') && (data[++index] == 's') && (data[++index] == 't')) { return TokenNamelist; } } @@ -2938,9 +2860,7 @@ public class Scanner implements IScanner, ITerminalSymbols { else return TokenNameIdentifier; case 4 : - if ((data[++index] == 'u') - && (data[++index] == 'l') - && (data[++index] == 'l')) + if ((data[++index] == 'u') && (data[++index] == 'l') && (data[++index] == 'l')) return TokenNamenull; else return TokenNameIdentifier; @@ -2973,10 +2893,7 @@ public class Scanner implements IScanner, ITerminalSymbols { case 'p' : // print if (length == 5) { - if ((data[++index] == 'r') - && (data[++index] == 'i') - && (data[++index] == 'n') - && (data[++index] == 't')) { + if ((data[++index] == 'r') && (data[++index] == 'i') && (data[++index] == 'n') && (data[++index] == 't')) { return TokenNameprint; } } @@ -3020,10 +2937,7 @@ public class Scanner implements IScanner, ITerminalSymbols { switch (length) { case 6 : if (data[++index] == 't') - if ((data[++index] == 'a') - && (data[++index] == 't') - && (data[++index] == 'i') - && (data[++index] == 'c')) { + if ((data[++index] == 'a') && (data[++index] == 't') && (data[++index] == 'i') && (data[++index] == 'c')) { return TokenNamestatic; } else return TokenNameIdentifier; @@ -3044,9 +2958,7 @@ public class Scanner implements IScanner, ITerminalSymbols { switch (length) { case 4 : - if ((data[++index] == 'r') - && (data[++index] == 'u') - && (data[++index] == 'e')) + if ((data[++index] == 'r') && (data[++index] == 'u') && (data[++index] == 'e')) return TokenNametrue; else return TokenNameIdentifier; @@ -3072,10 +2984,7 @@ public class Scanner implements IScanner, ITerminalSymbols { case 'w' : //while switch (length) { case 5 : - if ((data[++index] == 'h') - && (data[++index] == 'i') - && (data[++index] == 'l') - && (data[++index] == 'e')) + if ((data[++index] == 'h') && (data[++index] == 'i') && (data[++index] == 'l') && (data[++index] == 'e')) return TokenNamewhile; else return TokenNameIdentifier; @@ -3114,14 +3023,15 @@ public class Scanner implements IScanner, ITerminalSymbols { //force the first char of the hexa number do exist... // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // } + // } if (Character.digit(currentCharacter, 16) == -1) throw new InvalidInputException(INVALID_HEXA); //---end forcing-- @@ -3157,27 +3067,29 @@ public class Scanner implements IScanner, ITerminalSymbols { if (getNextChar('e', 'E') >= 0) { // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // } + // } if ((currentCharacter == '-') || (currentCharacter == '+')) { // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = - currentCharacter; - } - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = + // currentCharacter; + // } + // } } if (!Character.isDigit(currentCharacter)) throw new InvalidInputException(INVALID_FLOAT); @@ -3215,26 +3127,27 @@ public class Scanner implements IScanner, ITerminalSymbols { floating = true; // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } - } - - if ((currentCharacter == '-') - || (currentCharacter == '+')) { // consume next character + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // } + // } + + if ((currentCharacter == '-') || (currentCharacter == '+')) { // consume next character unicodeAsBackSlash = false; - if (((currentCharacter = source[currentPosition++]) == '\\') - && (source[currentPosition] == 'u')) { - getNextUnicodeChar(); - } else { - if (withoutUnicodePtr != 0) { - withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; - } - } + currentCharacter = source[currentPosition++]; + // if (((currentCharacter = source[currentPosition++]) == '\\') + // && (source[currentPosition] == 'u')) { + // getNextUnicodeChar(); + // } else { + // if (withoutUnicodePtr != 0) { + // withoutUnicodeBuffer[++withoutUnicodePtr] = currentCharacter; + // } + // } } if (!Character.isDigit(currentCharacter)) throw new InvalidInputException(INVALID_FLOAT); @@ -3318,21 +3231,17 @@ public class Scanner implements IScanner, ITerminalSymbols { } char end[] = new char[source.length - (currentPosition - 1)]; - System.arraycopy( - source, - (currentPosition - 1) + 1, - end, - 0, - source.length - (currentPosition - 1) - 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()) + ")"; //$NON-NLS-1$ + return "ScannerError"; // + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ case TokenNameStopPHP : return "StopPHP(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ case TokenNameIdentifier : @@ -3413,6 +3322,8 @@ public class Scanner implements IScanner, ITerminalSymbols { return "var"; //$NON-NLS-1$ case TokenNamewhile : return "while"; //$NON-NLS-1$ + case TokenNamethis : + return "$this"; //$NON-NLS-1$ case TokenNameIntegerLiteral : return "Integer(" + new String(getCurrentTokenSource()) + ")"; //$NON-NLS-1$ //$NON-NLS-2$ case TokenNameDoubleLiteral : @@ -3432,6 +3343,8 @@ public class Scanner implements IScanner, ITerminalSymbols { 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 : @@ -3440,6 +3353,8 @@ public class Scanner implements IScanner, ITerminalSymbols { 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 : @@ -3526,20 +3441,23 @@ public class Scanner implements IScanner, ITerminalSymbols { 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()) + ")"; //$NON-NLS-1$ default : return "not-a-token(" + (new Integer(act)) + ") " + new String(getCurrentTokenSource()); //$NON-NLS-1$ } } - 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( @@ -3550,8 +3468,7 @@ public class Scanner implements IScanner, ITerminalSymbols { this.eofPosition = Integer.MAX_VALUE; this.tokenizeComments = tokenizeComments; this.tokenizeWhiteSpace = tokenizeWhiteSpace; - this.checkNonExternalizedStringLiterals = - checkNonExternalizedStringLiterals; + this.checkNonExternalizedStringLiterals = checkNonExternalizedStringLiterals; this.assertMode = assertMode; } @@ -3597,12 +3514,7 @@ 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; }