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
- */
-
- // 1.4 feature
+ /*
+ * 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
+ //flag indicating if processed source contains occurrences of keyword assert
public boolean containsAssertKeyword = false;
public boolean recordLineSeparator;
//diet parsing support - jump over some method body when requested
public boolean diet = false;
- //support for the poor-line-debuggers ....
+ //support for the poor-line-debuggers ....
//remember the position of the cr/lf
public int[] lineEnds = new int[250];
public int linePtr = -1;
static final int TableSize = 30, InternalTableSize = 6;
//30*6 = 180 entries
public static final int OptimizedLength = 6;
- public /*static*/
+ public /* static */
final char[][][][] charArray_length = new char[OptimizedLength][TableSize][InternalTableSize][];
// support for detecting non-externalized string literals
int currentLineNr = -1;
public boolean checkNonExternalizedStringLiterals = true;
public boolean wasNonExternalizedStringLiteral = false;
- /*static*/ {
+ /* static */ {
for (int i = 0; i < 6; i++) {
for (int j = 0; j < TableSize; j++) {
for (int k = 0; k < InternalTableSize; k++) {
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;
-
+
+ // 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 Scanner() {
}
/**
- * 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);
}
public final boolean atEnd() {
- // This code is not relevant if source is
+ // This code is not relevant if source is
// Only a part of the real stream input
return source.length == currentPosition;
/*
* 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.
*/
public final int getLineEnd(int lineNumber) {
}
/**
* 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.
- *
- * e.g. getLineStart(1) --> 0 i.e. first line starts at character 0.
- *
+ *
+ * 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.
+ *
* In case the given line number is inconsistent, answers -1.
*/
public final int getLineStart(int lineNumber) {
//Both previous lines are true if the currentCharacter is == to the testedChar
//On false, no side effect has occured.
- //ALL getNextChar.... ARE OPTIMIZED COPIES
+ //ALL getNextChar.... ARE OPTIMIZED COPIES
int temp = currentPosition;
try {
//Both previous lines are true if the currentCharacter is == to the testedChar1/2
//On false, no side effect has occured.
- //ALL getNextChar.... ARE OPTIMIZED COPIES
+ //ALL getNextChar.... ARE OPTIMIZED COPIES
int temp = currentPosition;
try {
//Both previous lines are true if the currentCharacter is a digit
//On false, no side effect has occured.
- //ALL getNextChar.... ARE OPTIMIZED COPIES
+ //ALL getNextChar.... ARE OPTIMIZED COPIES
int temp = currentPosition;
try {
//Both previous lines are true if the currentCharacter is a digit base on radix
//On false, no side effect has occured.
- //ALL getNextChar.... ARE OPTIMIZED COPIES
+ //ALL getNextChar.... ARE OPTIMIZED COPIES
int temp = currentPosition;
try {
//Both previous lines are true if the currentCharacter is a JavaIdentifierPart
//On false, no side effect has occured.
- //ALL getNextChar.... ARE OPTIMIZED COPIES
+ //ALL getNextChar.... ARE OPTIMIZED COPIES
int temp = currentPosition;
try {
if (test >= 0) {
test = getNextChar('P', 'p');
if (test >= 0) {
- // <?PHP <?php
+ // <?PHP <?php
startPosition = currentPosition;
phpMode = true;
// }
// }
// }
- // // if (getNextChar('\''))
- // // return TokenNameCharacterLiteral;
+ // // if (getNextChar('\''))
+ // // return TokenNameCharacterLiteral;
// // relocate if finding another quote fairly close: thus unicode '/u000D' will be fully consumed
// for (int lookAhead = 0; lookAhead < 20; lookAhead++) {
// if (currentPosition + lookAhead == source.length)
while (currentCharacter != '\'') {
- /**** in PHP \r and \n are valid in string literals ****/
+ /** ** in PHP \r and \n are valid in string literals *** */
// if ((currentCharacter == '\n')
// || (currentCharacter == '\r')) {
// // relocate if finding another quote fairly close: thus unicode '/u000D' will be fully consumed
}
throw e; // rethrow
}
- if (checkNonExternalizedStringLiterals) { // check for presence of NLS tags //$NON-NLS-?$ where ? is an int.
+ if (checkNonExternalizedStringLiterals) { // check for presence of NLS tags //$NON-NLS-?$ where ? is an int.
if (currentLine == null) {
currentLine = new NLSLine();
lines.add(currentLine);
while (currentCharacter != '"') {
- /**** in PHP \r and \n are valid in string literals ****/
+ /** ** in PHP \r and \n are valid in string literals *** */
// if ((currentCharacter == '\n')
// || (currentCharacter == '\r')) {
// // relocate if finding another quote fairly close: thus unicode '/u000D' will be fully consumed
}
throw e; // rethrow
}
- if (checkNonExternalizedStringLiterals) { // check for presence of NLS tags //$NON-NLS-?$ where ? is an int.
+ if (checkNonExternalizedStringLiterals) { // check for presence of NLS tags //$NON-NLS-?$ where ? is an int.
if (currentLine == null) {
currentLine = new NLSLine();
lines.add(currentLine);
while (currentCharacter != '`') {
- /**** in PHP \r and \n are valid in string literals ****/
+ /** ** in PHP \r and \n are valid in string literals *** */
// if ((currentCharacter == '\n')
// || (currentCharacter == '\r')) {
// // relocate if finding another quote fairly close: thus unicode '/u000D' will be fully consumed
}
throw e; // rethrow
}
- if (checkNonExternalizedStringLiterals) { // check for presence of NLS tags //$NON-NLS-?$ where ? is an int.
+ if (checkNonExternalizedStringLiterals) { // check for presence of NLS tags //$NON-NLS-?$ where ? is an int.
if (currentLine == null) {
currentLine = new NLSLine();
lines.add(currentLine);
{
int test;
if ((currentCharacter == '#') || (test = getNextChar('/', '*')) == 0) {
- //line comment
+ //line comment
int endPositionForLineComment = 0;
- try { //get the next char
+ try { //get the next char
currentCharacter = source[currentPosition++];
// if (((currentCharacter = source[currentPosition++])
// == '\\')
currentLine = null;
}
}
- try { //get the next char
+ try { //get the next char
currentCharacter = source[currentPosition++];
// if (((currentCharacter = source[currentPosition++])
// == '\\')
// //At the end of this method currentCharacter holds the new visited char
// //and currentPosition points right next after it
//
- // //ALL getNextChar.... ARE OPTIMIZED COPIES
+ // //ALL getNextChar.... ARE OPTIMIZED COPIES
//
// int c1 = 0, c2 = 0, c3 = 0, c4 = 0, unicodeSize = 6;
// currentPosition++;
// }
// 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() {
{
int test;
if ((test = getNextChar('/', '*')) == 0) {
- //line comment
+ //line comment
try {
- //get the next char
+ //get the next char
currentCharacter = source[currentPosition++];
// if (((currentCharacter = source[currentPosition++]) == '\\')
// && (source[currentPosition] == 'u')) {
// }
while (currentCharacter != '\r' && currentCharacter != '\n') {
- //get the next char
+ //get the next char
currentCharacter = source[currentPosition++];
// if (((currentCharacter = source[currentPosition++])
// == '\\')
}
if (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n')))
pushLineSeparator();
- try { //get the next char
+ try { //get the next char
currentCharacter = source[currentPosition++];
// if (((currentCharacter = source[currentPosition++]) == '\\')
// && (source[currentPosition] == 'u')) {
// (char) (((c1 * 16 + c2) * 16 + c3) * 16 + c4);
// }
// }
- //loop until end of comment */
+ //loop until end of comment */
while ((currentCharacter != '/') || (!star)) {
if (recordLineSeparator && ((currentCharacter == '\r') || (currentCharacter == '\n')))
pushLineSeparator();
// }
// }
public final int[] getLineEnds() {
- //return a bounded copy of this.lineEnds
+ //return a bounded copy of this.lineEnds
int[] copy;
System.arraycopy(lineEnds, 0, copy = new int[linePtr + 1], 0, linePtr + 1);
// look-ahead for merged cr+lf
try {
if (source[currentPosition] == '\n') {
- //System.out.println("look-ahead LF-" + currentPosition);
+ //System.out.println("look-ahead LF-" + currentPosition);
lineEnds[linePtr] = currentPosition;
currentPosition++;
wasAcr = false;
if (currentCharacter == '\n') {
//must merge eventual cr followed by lf
if (wasAcr && (lineEnds[linePtr] == (currentPosition - 2))) {
- //System.out.println("merge LF-" + (currentPosition - 1));
+ //System.out.println("merge LF-" + (currentPosition - 1));
lineEnds[linePtr] = currentPosition - 1;
} else {
int separatorPos = currentPosition - 1;
if ((linePtr > 0) && (lineEnds[linePtr] >= separatorPos))
return;
- // System.out.println("LF-" + separatorPos);
+ // System.out.println("LF-" + separatorPos);
try {
lineEnds[++linePtr] = separatorPos;
} catch (IndexOutOfBoundsException e) {
}
// look-ahead for merged cr+lf
if (source[currentPosition] == '\n') {
- //System.out.println("look-ahead LF-" + currentPosition);
+ //System.out.println("look-ahead LF-" + currentPosition);
lineEnds[linePtr] = currentPosition;
currentPosition++;
wasAcr = false;
if (currentCharacter == '\n') {
//must merge eventual cr followed by lf
if (wasAcr && (lineEnds[linePtr] == (currentPosition - 7))) {
- //System.out.println("merge LF-" + (currentPosition - 1));
+ //System.out.println("merge LF-" + (currentPosition - 1));
lineEnds[linePtr] = currentPosition - 6;
} else {
int separatorPos = currentPosition - 6;
if ((linePtr > 0) && (lineEnds[linePtr] >= separatorPos))
return;
- // System.out.println("LF-" + separatorPos);
+ // System.out.println("LF-" + separatorPos);
try {
lineEnds[++linePtr] = separatorPos;
} catch (IndexOutOfBoundsException e) {
} else { // has read \OctalDigit NonDigit--> ignore last character
currentPosition--;
}
- } else { // has read \OctalDigit NonOctalDigit--> ignore last character
+ } else { // has read \OctalDigit NonOctalDigit--> ignore last character
currentPosition--;
}
} else { // has read \OctalDigit --> ignore last character
firstLetter = data[index];
switch (firstLetter) {
- case 'a' : // as and array
+ case 'a' : // as and array abstract
switch (length) {
case 2 : //as
if ((data[++index] == 's')) {
} else {
return TokenNameIdentifier;
}
- // case 5 :
- // if ((data[++index] == 'r') && (data[++index] == 'r') && (data[++index] == 'a') && (data[++index] == 'y'))
- // return TokenNamearray;
- // 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;
}
return TokenNameIdentifier;
}
- case 'c' : //case class continue
+ case 'c' : //case catch class const continue
switch (length) {
case 4 :
if ((data[++index] == 'a') && (data[++index] == 's') && (data[++index] == 'e'))
else
return TokenNameIdentifier;
case 5 :
- if ((data[++index] == 'l') && (data[++index] == 'a') && (data[++index] == 's') && (data[++index] == 's'))
+ if ((data[++index] == 'a') && (data[++index] == 't') && (data[++index] == 'c') && (data[++index] == 'h'))
+ return TokenNamecatch;
+ if ((data[index] == 'l') && (data[++index] == 'a') && (data[++index] == 's') && (data[++index] == 's'))
return TokenNameclass;
+ if ((data[index] == 'o') && (data[++index] == 'n') && (data[++index] == 's') && (data[++index] == 't'))
+ return TokenNameconst;
else
return TokenNameIdentifier;
case 8 :
return TokenNameIdentifier;
}
- case 'd' : //define default do
+ case 'd' : //define declare default do die
switch (length) {
case 2 :
if ((data[++index] == 'o'))
return TokenNamedo;
else
return TokenNameIdentifier;
+ case 3 :
+ if ((data[++index] == 'i') && (data[++index] == 'e'))
+ return TokenNamedie;
+ else
+ return TokenNameIdentifier;
case 6 :
if ((data[++index] == 'e')
&& (data[++index] == 'f')
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')
default :
return TokenNameIdentifier;
}
- case 'e' : //echo else elseif extends
+ 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
+ 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
return TokenNameendswitch;
else
return TokenNameIdentifier;
- case 10 : // endforeach
+ 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')
return TokenNameIdentifier;
}
- case 'f' : //for false function
+ case 'f' : //for false final function
switch (length) {
case 3 :
if ((data[++index] == 'o') && (data[++index] == 'r'))
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 : // function
+ case 7 : // foreach
if ((data[++index] == 'o')
&& (data[++index] == 'r')
&& (data[++index] == 'e')
}
return TokenNameIdentifier;
- case 'i' : //if int
+ case 'i' : //if int isset include include_once instanceof interface implements
switch (length) {
case 2 :
if (data[++index] == 'f')
// 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')
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')
// }
return TokenNameIdentifier;
- case 'p' : // print
- if (length == 5) {
- if ((data[++index] == 'r') && (data[++index] == 'i') && (data[++index] == 'n') && (data[++index] == 't')) {
- return TokenNameprint;
- }
+ 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;
}
return TokenNameIdentifier;
case 'r' : //return require require_once
} else
return TokenNameIdentifier;
- case 's' : //static switch
+ case 's' : //static switch
switch (length) {
case 6 :
if (data[++index] == 't')
return TokenNameIdentifier;
}
- case 't' : // true
+ 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;
- // if ((data[++index] == 'h') && (data[++index] == 'i') && (data[++index] == 's'))
- // return TokenNamethis;
+ case 5 :
+ if ((data[++index] == 'h') && (data[++index] == 'r') && (data[++index] == 'o') && (data[++index] == 'w'))
+ return TokenNamethrow;
+ else
+ return TokenNameIdentifier;
default :
return TokenNameIdentifier;
}
-
- case 'v' : //var
+ 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 TokenNameIdentifier;
}
- case 'w' : //while
+ 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'))
+ //case 6:if ( (data[++index] =='i') && (data[++index]=='d') && (data[++index]=='e') && (data[++index]=='f')&&
+ // (data[++index]=='p'))
//return TokenNamewidefp ;
//else
//return TokenNameIdentifier;
}
/**
* Search the line number corresponding to a specific position
- *
+ *
*/
public final int getLineNumber(int position) {
}
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).
-
- 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';
- 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 { // has read \OctalDigit NonDigit--> ignore last character
- currentPosition--;
- }
- } else { // has read \OctalDigit NonOctalDigit--> ignore last character
- currentPosition--;
- }
- } 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) {
- return;
- }
- int foundTaskIndex = this.foundTaskCount;
- 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++){
- tag = this.taskTags[itag];
- 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]) continue nextTag;
- }
-
- if (this.foundTaskTags == null){
- this.foundTaskTags = new char[5][];
- this.foundTaskMessages = new char[5][];
- 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, this.foundTaskCount);
- System.arraycopy(this.foundTaskMessages, 0, this.foundTaskMessages = 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, this.foundTaskCount);
- }
- this.foundTaskTags[this.foundTaskCount] = tag;
- this.foundTaskPriorities[this.foundTaskCount] = priority;
- 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
- }
- }
-
- 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; // at most beginning of next task
- if (max_value < msgStart) max_value = msgStart; // would only occur if tag is before EOF.
- int end = -1;
- char c;
-
- for (int j = msgStart; j < max_value; j++){
- if ((c = this.source[j]) == '\n' || c == '\r'){
- end = j-1;
- break;
- }
- }
-
- if (end == -1){
- for (int j = max_value; j > msgStart; j--){
- if ((c = this.source[j]) == '*') {
- end = j-1;
- break;
- }
- }
- if (end == -1) end = max_value;
- }
-
- if (msgStart == end) continue; // empty
-
- // trim the message
- while (CharOperation.isWhitespace(source[end]) && msgStart <= end) end--;
- while (CharOperation.isWhitespace(source[msgStart]) && msgStart <= end) msgStart++;
-
- // update the end position of the task
- this.foundTaskPositions[i][1] = end;
-
- // get the message source
- final int messageLength = end-msgStart+1;
- char[] message = new char[messageLength];
-
- System.arraycopy(source, msgStart, message, 0, messageLength);
- this.foundTaskMessages[i] = message;
- }
-}
+
+ 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).
+
+ 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';
+ 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 { // has read \OctalDigit NonDigit--> ignore last character
+ currentPosition--;
+ }
+ } else { // has read \OctalDigit NonOctalDigit--> ignore last character
+ currentPosition--;
+ }
+ } 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) {
+ return;
+ }
+ int foundTaskIndex = this.foundTaskCount;
+ 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++) {
+ tag = this.taskTags[itag];
+ 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])
+ continue nextTag;
+ }
+
+ if (this.foundTaskTags == null) {
+ this.foundTaskTags = new char[5][];
+ this.foundTaskMessages = new char[5][];
+ 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, this.foundTaskCount);
+ System.arraycopy(
+ this.foundTaskMessages,
+ 0,
+ this.foundTaskMessages = 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,
+ this.foundTaskCount);
+ }
+ this.foundTaskTags[this.foundTaskCount] = tag;
+ this.foundTaskPriorities[this.foundTaskCount] = priority;
+ 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
+ }
+ }
+
+ 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;
+ // at most beginning of next task
+ if (max_value < msgStart)
+ max_value = msgStart; // would only occur if tag is before EOF.
+ int end = -1;
+ char c;
+
+ for (int j = msgStart; j < max_value; j++) {
+ if ((c = this.source[j]) == '\n' || c == '\r') {
+ end = j - 1;
+ break;
+ }
+ }
+
+ if (end == -1) {
+ for (int j = max_value; j > msgStart; j--) {
+ if ((c = this.source[j]) == '*') {
+ end = j - 1;
+ break;
+ }
+ }
+ if (end == -1)
+ end = max_value;
+ }
+
+ if (msgStart == end)
+ continue; // empty
+
+ // trim the message
+ while (CharOperation.isWhitespace(source[end]) && msgStart <= end)
+ end--;
+ while (CharOperation.isWhitespace(source[msgStart]) && msgStart <= end)
+ msgStart++;
+
+ // update the end position of the task
+ this.foundTaskPositions[i][1] = end;
+
+ // get the message source
+ final int messageLength = end - msgStart + 1;
+ char[] message = new char[messageLength];
+
+ System.arraycopy(source, msgStart, message, 0, messageLength);
+ this.foundTaskMessages[i] = message;
+ }
+ }
}
git://git.phpeclipse.com / phpeclipse.git / blobdiff