org.fife.ui.rsyntaxtextarea.modes.PerlTokenMaker.flex Maven / Gradle / Ivy
The newest version!
/* * 01/26/2008 * * PerlTokenMaker.java - Scanner for Perl * * 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 Perl.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 PerlTokenMaker.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.
*/
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;
}
/**
* {@inheritDoc}
*/
@Override
public String[] getLineCommentStartAndEnd(int languageIndex) {
return new String[] { "#", null };
}
/**
* {@inheritDoc}
*/
public boolean getMarkOccurrencesOfTokenType(int type) {
return super.getMarkOccurrencesOfTokenType(type) || type==Token.VARIABLE;
}
/**
* 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;
// Start off in the proper state.
int state = Token.NULL;
switch (initialTokenType) {
case Token.LITERAL_STRING_DOUBLE_QUOTE:
state = STRING;
start = text.offset;
break;
case Token.LITERAL_CHAR:
state = CHAR_LITERAL;
start = text.offset;
break;
case Token.LITERAL_BACKQUOTE:
state = BACKTICKS;
start = text.offset;
break;
case INTERNAL_HEREDOC_EOF_UNQUOTED:
state = HEREDOC_EOF_UNQUOTED;
start = text.offset;
break;
case INTERNAL_HEREDOC_EOF_SINGLE_QUOTED:
state = HEREDOC_EOF_SINGLE_QUOTED;
start = text.offset;
break;
case INTERNAL_HEREDOC_EOT_UNQUOTED:
state = HEREDOC_EOT_UNQUOTED;
start = text.offset;
break;
case INTERNAL_HEREDOC_EOT_SINGLE_QUOTED:
state = HEREDOC_EOT_SINGLE_QUOTED;
start = text.offset;
break;
case INTERNAL_POD:
state = POD;
start = text.offset;
break;
default:
state = Token.NULL;
}
s = text;
try {
yyreset(zzReader);
yybegin(state);
return yylex();
} catch (IOException ioe) {
ioe.printStackTrace();
return new TokenImpl();
}
}
/**
* Returns whether a regular expression token can follow the specified
* token.
*
* @param t The token to check, which may be null.
* @return Whether a regular expression token may follow this one.
*/
private static final boolean regexCanFollow(Token t) {
char ch;
// We basically try to mimic Eclipse's JS editor's behavior here.
return t==null ||
//t.isOperator() ||
(t.length()==1 && (
(ch=t.charAt(0))=='=' ||
ch=='(' ||
ch==',' ||
ch=='?' ||
ch==':' ||
ch=='[' ||
ch=='!' ||
ch=='&'
)) ||
/* Operators "==", "===", "!=", "!==", etc. */
(t.getType()==Token.OPERATOR &&
((ch=t.charAt(t.length()-1))=='=' || ch=='~'));
}
/**
* 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;
}
%}
Letter = [A-Za-z]
NonzeroDigit = [1-9]
Digit = ("0"|{NonzeroDigit})
HexDigit = ({Digit}|[A-Fa-f])
OctalDigit = ([0-7])
/*Escape = ("\\"(([btnfr\"'\\])|([0123]{OctalDigit}?{OctalDigit}?)|({OctalDigit}{OctalDigit}?)))*/
NonSeparator = ([^\t\f\r\n\ \(\)\{\}\[\]\;\,\.\=\>\<\!\~\?\:\+\-\*\/\&\|\^\%\"\'\`]|"#"|"\\")
IdentifierStart = ({Letter}|"_")
IdentifierPart = ({IdentifierStart}|{Digit})
LineTerminator = (\n)
WhiteSpace = ([ \t\f])
LineCommentBegin = "#"
IntegerHelper1 = (({NonzeroDigit}{Digit}*)|"0")
IntegerHelper2 = ("0"(([xX]{HexDigit}+)|({OctalDigit}*)))
IntegerLiteral = ({IntegerHelper1}[lL]?)
HexLiteral = ({IntegerHelper2}[lL]?)
FloatHelper1 = ([fFdD]?)
FloatHelper2 = ([eE][+-]?{Digit}+{FloatHelper1})
FloatLiteral1 = ({Digit}+"."({FloatHelper1}|{FloatHelper2}|{Digit}+({FloatHelper1}|{FloatHelper2})))
FloatLiteral2 = ("."{Digit}+({FloatHelper1}|{FloatHelper2}))
FloatLiteral3 = ({Digit}+{FloatHelper2})
FloatLiteral = ({FloatLiteral1}|{FloatLiteral2}|{FloatLiteral3}|({Digit}+[fFdD]))
ErrorNumberFormat = (({IntegerLiteral}|{HexLiteral}|{FloatLiteral}){NonSeparator}+)
Separator = ([\(\)\{\}\[\]])
Separator2 = ([\;:,.])
VariableStart = ([\$\@\%)]"$"?)
BracedVariable = ({VariableStart}\{{Identifier}\})
UnbracedVariable = ({VariableStart}{Identifier})
BracedShellVariable = ([\$]\{[\&\`\'\+\*\.\/\|\,\\\"\;\#\%\=\-\~\^\:\?\!\@\$\<\>\)\(\[\]\)\}])
UnbracedShellVariable = ([\$][\&\`\'\+\*\.\/\|\,\\\"\;\#\%\=\-\~\^\:\?\!\@\$\<\>\)\(\[\]\)])
MatchVariable = ([\$]{Digit})
Variable = ({BracedVariable}|{UnbracedVariable}|{BracedShellVariable}|{UnbracedShellVariable}|{MatchVariable})
Regex = ("/"([^\*\\/]|\\.)([^/\\]|\\.)*"/"[msixpogcadlu]*)
NonAssignmentOperator = ("+"|"-"|"<="|"^"|"++"|"<"|"*"|">="|"%"|"--"|">"|"/"|"!="|"?"|">>"|"!"|"&"|"=="|":"|">>"|"~"|"|"|"&&"|">>>"|"->")
AssignmentOperator = ("="|"-="|"*="|"/="|"|="|"&="|"^="|"+="|"%="|"<<="|">>="|">>>=")
BindingOperator = ("=~"|"!~")
FunnyOperator = (([\*][\'\"])|([\&][\'\"]))
Operator = ({NonAssignmentOperator}|{AssignmentOperator}|{BindingOperator}|{FunnyOperator})
PodCommandsExceptCut = ("="("pod"|"head1"|"head2"|"head3"|"head4"|"over"|"item"|"back"|"begin"|"end"|"for"|"encoding"))
Identifier = ({IdentifierStart}{IdentifierPart}*)
ErrorIdentifier = ({NonSeparator}+)
%state STRING
%state CHAR_LITERAL
%state BACKTICKS
%state HEREDOC_EOF_UNQUOTED
%state HEREDOC_EOF_SINGLE_QUOTED
%state HEREDOC_EOT_UNQUOTED
%state HEREDOC_EOT_SINGLE_QUOTED
%state POD
%%