org.fife.ui.rsyntaxtextarea.modes.JavaScriptTokenMaker.flex Maven / Gradle / Ivy
The newest version!
/* * 02/05/2012 * * JavaScriptTokenMaker.java - Parses a document into JavaScript tokens. * * This library is distributed under a modified BSD license. See the included * RSyntaxTextArea.License.txt file for details. */ package org.fife.ui.rsyntaxtextarea.modes; import java.io.*; import javax.swing.text.Segment; import org.fife.ui.rsyntaxtextarea.*; /** * Scanner for JavaScript files. Its states could be simplified, but are * kept the way they are to keep a degree of similarity (i.e. copy/paste) * between it and HTML/JSP/PHPTokenMaker. This should cause no difference in * performance.file will contain two * definitions of both* * This implementation was created using * JFlex 1.4.1; however, the generated file * was modified for performance. Memory allocation needs to be almost * completely removed to be competitive with the handwritten lexers (subclasses * of
AbstractTokenMaker, so this class has been modified so that * Strings are never allocated (via yytext()), and the scanner never has to * worry about refilling its buffer (needlessly copying chars around). * We can achieve this because RText always scans exactly 1 line of tokens at a * time, and hands the scanner this line as an array of characters (a Segment * really). Since tokens contain pointers to char arrays instead of Strings * holding their contents, there is no need for allocating new memory for * Strings.* * The actual algorithm generated for scanning has, of course, not been * modified.
* * If you wish to regenerate this file yourself, keep in mind the following: *
*
- The generated JavaScriptTokenMaker.java
zzRefillandyyreset. * You should hand-delete the second of each definition (the ones * generated by the lexer), as these generated methods modify the input * buffer, which we'll never have to do. *
yylex() on the generated scanner
* directly; rather, you should use getTokenList as you would
* with any other TokenMaker instance.zzMarkedPos.
*
* @param tokenType The token's type.
*/
private void addEndToken(int tokenType) {
addToken(zzMarkedPos,zzMarkedPos, tokenType);
}
/**
* Adds the token specified to the current linked list of tokens.
*
* @param tokenType The token's type.
* @see #addToken(int, int, int)
*/
private void addHyperlinkToken(int start, int end, int tokenType) {
int so = start + offsetShift;
addToken(zzBuffer, start,end, tokenType, so, true);
}
/**
* Adds the token specified to the current linked list of tokens.
*
* @param tokenType The token's type.
*/
private void addToken(int tokenType) {
addToken(zzStartRead, zzMarkedPos-1, tokenType);
}
/**
* Adds the token specified to the current linked list of tokens.
*
* @param tokenType The token's type.
*/
private void addToken(int start, int end, int tokenType) {
int so = start + offsetShift;
addToken(zzBuffer, start,end, tokenType, so);
}
/**
* Adds the token specified to the current linked list of tokens.
*
* @param array The character array.
* @param start The starting offset in the array.
* @param end The ending offset in the array.
* @param tokenType The token's type.
* @param startOffset The offset in the document at which this token
* occurs.
*/
@Override
public void addToken(char[] array, int start, int end, int tokenType, int startOffset) {
super.addToken(array, start,end, tokenType, startOffset);
zzStartRead = zzMarkedPos;
}
/**
* Returns the closest {@link TokenTypes "standard" token type} for a given
* "internal" token type (e.g. one whose value is < 0).
*/
@Override
public int getClosestStandardTokenTypeForInternalType(int type) {
switch (type) {
case INTERNAL_IN_JS_MLC:
return TokenTypes.COMMENT_MULTILINE;
case INTERNAL_IN_JS_COMMENT_DOCUMENTATION:
return TokenTypes.COMMENT_DOCUMENTATION;
case INTERNAL_IN_JS_STRING_INVALID:
case INTERNAL_IN_JS_STRING_VALID:
case INTERNAL_IN_JS_CHAR_INVALID:
case INTERNAL_IN_JS_CHAR_VALID:
return TokenTypes.LITERAL_STRING_DOUBLE_QUOTE;
}
return type;
}
/**
* Returns the JavaScript version being highlighted.
*
* @return Supported JavaScript version.
* @see #isJavaScriptCompatible(String)
*/
public static String getJavaScriptVersion() {
return jsVersion;
}
/**
* {@inheritDoc}
*/
@Override
public String[] getLineCommentStartAndEnd(int languageIndex) {
return new String[] { "//", null };
}
/**
* Returns the first token in the linked list of tokens generated
* from text. This method must be implemented by
* subclasses so they can correctly implement syntax highlighting.
*
* @param text The text from which to get tokens.
* @param initialTokenType The token type we should start with.
* @param startOffset The offset into the document at which
* text starts.
* @return The first Token in a linked list representing
* the syntax highlighted text.
*/
public Token getTokenList(Segment text, int initialTokenType, int startOffset) {
resetTokenList();
this.offsetShift = -text.offset + startOffset;
validJSString = true;
e4x_prevState = YYINITIAL;
e4x_inInternalDtd = false;
int languageIndex = LANG_INDEX_DEFAULT;
// Start off in the proper state.
int state = YYINITIAL;
switch (initialTokenType) {
case INTERNAL_IN_JS_MLC:
state = JS_MLC;
break;
case INTERNAL_IN_JS_COMMENT_DOCUMENTATION:
state = JS_DOCCOMMENT;
start = text.offset;
break;
case INTERNAL_IN_JS_STRING_INVALID:
state = JS_STRING;
validJSString = false;
break;
case INTERNAL_IN_JS_STRING_VALID:
state = JS_STRING;
break;
case INTERNAL_IN_JS_CHAR_INVALID:
state = JS_CHAR;
validJSString = false;
break;
case INTERNAL_IN_JS_CHAR_VALID:
state = JS_CHAR;
break;
case INTERNAL_E4X:
state = E4X;
languageIndex = LANG_INDEX_E4X;
break;
case INTERNAL_E4X_INTAG:
state = E4X_INTAG;
languageIndex = LANG_INDEX_E4X;
break;
case INTERNAL_E4X_MARKUP_PROCESSING_INSTRUCTION:
state = E4X_PI;
languageIndex = LANG_INDEX_E4X;
break;
case INTERNAL_E4X_DTD:
state = E4X_DTD;
languageIndex = LANG_INDEX_E4X;
break;
case INTERNAL_E4X_DTD_INTERNAL:
state = E4X_DTD;
e4x_inInternalDtd = true;
languageIndex = LANG_INDEX_E4X;
break;
case INTERNAL_E4X_ATTR_SINGLE:
state = E4X_INATTR_SINGLE;
languageIndex = LANG_INDEX_E4X;
break;
case INTERNAL_E4X_ATTR_DOUBLE:
state = E4X_INATTR_DOUBLE;
languageIndex = LANG_INDEX_E4X;
break;
case INTERNAL_E4X_MARKUP_CDATA:
state = E4X_CDATA;
languageIndex = LANG_INDEX_E4X;
break;
default:
if (initialTokenType<-1024) { // INTERNAL_IN_E4X_COMMENT - prevState
int main = -(-initialTokenType & 0xffffff00);
switch (main) {
default: // Should never happen
case INTERNAL_IN_E4X_COMMENT:
state = E4X_COMMENT;
break;
}
e4x_prevState = -initialTokenType&0xff;
languageIndex = LANG_INDEX_E4X;
}
else { // Shouldn't happen
state = Token.NULL;
}
}
setLanguageIndex(languageIndex);
start = text.offset;
s = text;
try {
yyreset(zzReader);
yybegin(state);
return yylex();
} catch (IOException ioe) {
ioe.printStackTrace();
return new TokenImpl();
}
}
/**
* Returns whether e4x is being highlighted.
*
* @return Whether e4x is being highlighted.
* @see #setE4xSupported(boolean)
*/
public static boolean isE4xSupported() {
return e4xSupported;
}
/**
* Returns whether features for a specific JS version should be honored
* while highlighting.
*
* @param version JavaScript version required
* @return Whether the JavaScript version is the same or greater than
* version required.
*/
public static boolean isJavaScriptCompatible(String version) {
return jsVersion.compareTo(version) >= 0;
}
/**
* Sets whether e4x should be highlighted. A repaint should be forced on
* all RSyntaxTextAreas editing JavaScript if this property
* is changed to see the difference.
*
* @param supported Whether e4x should be highlighted.
* @see #isE4xSupported()
*/
public static void setE4xSupported(boolean supported) {
e4xSupported = supported;
}
/**
* Set the supported JavaScript version because some keywords were
* introduced on or after this version.
*
* @param javaScriptVersion The version of JavaScript to support, such as
* "1.5" or "1.6".
* @see #isJavaScriptCompatible(String)
* @see #getJavaScriptVersion()
*/
public static void setJavaScriptVersion(String javaScriptVersion) {
jsVersion = javaScriptVersion;
}
/**
* Refills the input buffer.
*
* @return true if EOF was reached, otherwise
* false.
*/
private boolean zzRefill() {
return zzCurrentPos>=s.offset+s.count;
}
/**
* Resets the scanner to read from a new input stream.
* Does not close the old reader.
*
* All internal variables are reset, the old input stream
* cannot be reused (internal buffer is discarded and lost).
* Lexical state is set to YY_INITIAL.
*
* @param reader the new input stream
*/
public final void yyreset(java.io.Reader reader) {
// 's' has been updated.
zzBuffer = s.array;
/*
* We replaced the line below with the two below it because zzRefill
* no longer "refills" the buffer (since the way we do it, it's always
* "full" the first time through, since it points to the segment's
* array). So, we assign zzEndRead here.
*/
//zzStartRead = zzEndRead = s.offset;
zzStartRead = s.offset;
zzEndRead = zzStartRead + s.count - 1;
zzCurrentPos = zzMarkedPos = zzPushbackPos = s.offset;
zzLexicalState = YYINITIAL;
zzReader = reader;
zzAtBOL = true;
zzAtEOF = false;
}
%}
Whitespace = ([ \t\f]+)
LineTerminator = ([\n])
Letter = [A-Za-z]
NonzeroDigit = [1-9]
Digit = ("0"|{NonzeroDigit})
HexDigit = ({Digit}|[A-Fa-f])
OctalDigit = ([0-7])
LetterOrDigit = ({Letter}|{Digit})
EscapedSourceCharacter = ("u"{HexDigit}{HexDigit}{HexDigit}{HexDigit})
NonSeparator = ([^\t\f\r\n\ \(\)\{\}\[\]\;\,\.\=\>\<\!\~\?\:\+\-\*\/\&\|\^\%\"\']|"#"|"\\")
IdentifierStart = ({Letter}|"_"|"$")
IdentifierPart = ({IdentifierStart}|{Digit}|("\\"{EscapedSourceCharacter}))
JS_MLCBegin = "/*"
JS_DocCommentBegin = "/**"
JS_MLCEnd = "*/"
JS_LineCommentBegin = "//"
JS_IntegerHelper1 = (({NonzeroDigit}{Digit}*)|"0")
JS_IntegerHelper2 = ("0"(([xX]{HexDigit}+)|({OctalDigit}*)))
JS_IntegerLiteral = ({JS_IntegerHelper1}[lL]?)
JS_HexLiteral = ({JS_IntegerHelper2}[lL]?)
JS_FloatHelper1 = ([fFdD]?)
JS_FloatHelper2 = ([eE][+-]?{Digit}+{JS_FloatHelper1})
JS_FloatLiteral1 = ({Digit}+"."({JS_FloatHelper1}|{JS_FloatHelper2}|{Digit}+({JS_FloatHelper1}|{JS_FloatHelper2})))
JS_FloatLiteral2 = ("."{Digit}+({JS_FloatHelper1}|{JS_FloatHelper2}))
JS_FloatLiteral3 = ({Digit}+{JS_FloatHelper2})
JS_FloatLiteral = ({JS_FloatLiteral1}|{JS_FloatLiteral2}|{JS_FloatLiteral3}|({Digit}+[fFdD]))
JS_ErrorNumberFormat = (({JS_IntegerLiteral}|{JS_HexLiteral}|{JS_FloatLiteral}){NonSeparator}+)
JS_Separator = ([\(\)\{\}\[\]\]])
JS_Separator2 = ([\;,.])
JS_NonAssignmentOperator = ("+"|"-"|"<="|"^"|"++"|"<"|"*"|">="|"%"|"--"|">"|"/"|"!="|"?"|">>"|"!"|"&"|"=="|":"|">>"|"~"|"||"|"&&"|">>>")
JS_AssignmentOperator = ("="|"-="|"*="|"/="|"|="|"&="|"^="|"+="|"%="|"<<="|">>="|">>>=")
JS_Operator = ({JS_NonAssignmentOperator}|{JS_AssignmentOperator})
JS_Identifier = ({IdentifierStart}{IdentifierPart}*)
JS_ErrorIdentifier = ({NonSeparator}+)
JS_Regex = ("/"([^\*\\/]|\\.)([^/\\]|\\.)*"/"[gim]*)
JS_E4xAttribute = ("@"{Letter}{LetterOrDigit}*)
JS_BlockTag = ("abstract"|"access"|"alias"|"augments"|"author"|"borrows"|
"callback"|"classdesc"|"constant"|"constructor"|"constructs"|
"copyright"|"default"|"deprecated"|"desc"|"enum"|"event"|
"example"|"exports"|"external"|"file"|"fires"|"global"|
"ignore"|"inner"|"instance"|"kind"|"lends"|"license"|
"link"|"member"|"memberof"|"method"|"mixes"|"mixin"|"module"|
"name"|"namespace"|"param"|"private"|"property"|"protected"|
"public"|"readonly"|"requires"|"return"|"returns"|"see"|"since"|
"static"|"summary"|"this"|"throws"|"todo"|
"type"|"typedef"|"variation"|"version")
JS_InlineTag = ("link"|"linkplain"|"linkcode"|"tutorial")
e4x_NameStartChar = ([\:A-Z_a-z])
e4x_NameChar = ({e4x_NameStartChar}|[\-\.0-9])
e4x_TagName = ({e4x_NameStartChar}{e4x_NameChar}*)
e4x_Identifier = ([^ \t\n<&;]+)
e4x_EndXml = ([;])
e4x_EntityReference = ([&][^; \t]*[;]?)
e4x_InTagIdentifier = ([^ \t\n\"\'=\/>]+)
e4x_CDataBegin = ("")
URLGenDelim = ([:\/\?#\[\]@])
URLSubDelim = ([\!\$&'\(\)\*\+,;=])
URLUnreserved = ({LetterOrDigit}|"_"|[\-\.\~])
URLCharacter = ({URLGenDelim}|{URLSubDelim}|{URLUnreserved}|[%])
URLCharacters = ({URLCharacter}*)
URLEndCharacter = ([\/\$]|{LetterOrDigit})
URL = (((https?|f(tp|ile))"://"|"www.")({URLCharacters}{URLEndCharacter})?)
%state JS_STRING
%state JS_CHAR
%state JS_MLC
%state JS_DOCCOMMENT
%state JS_EOL_COMMENT
%state E4X
%state E4X_COMMENT
%state E4X_PI
%state E4X_DTD
%state E4X_INTAG
%state E4X_INATTR_DOUBLE
%state E4X_INATTR_SINGLE
%state E4X_CDATA
%%