/* * 12/23/2010 * * ClojureTokenMaker.java - Scanner for Clojure. * * 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 the Clojure programming language.

* * This was graciously donated by the folks at the * Fiji project. * Its original location was * here. *

* * 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: *

* * */ %% %public %class ClojureTokenMaker %extends AbstractJFlexTokenMaker %unicode %type org.fife.ui.rsyntaxtextarea.Token %{ /** * Constructor. This must be here because JFlex does not generate a * no-parameter constructor. */ public ClojureTokenMaker() { } /** * 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. * @see #addHyperlinkToken(int, int, int) */ private void addToken(int start, int end, int tokenType) { int so = start + offsetShift; addToken(zzBuffer, start,end, tokenType, so, false); } /** * 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. * @param hyperlink Whether this token is a hyperlink. */ public void addToken(char[] array, int start, int end, int tokenType, int startOffset, boolean hyperlink) { super.addToken(array, start,end, tokenType, startOffset, hyperlink); zzStartRead = zzMarkedPos; } /** * Returns the text to place at the beginning and end of a * line to "comment" it in a this programming language. * * @return The start and end strings to add to a line to "comment" * it out. */ public String[] getLineCommentStartAndEnd() { 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; // Start off in the proper state. int state = Token.NULL; switch (initialTokenType) { /*case Token.COMMENT_MULTILINE: state = MLC; start = text.offset; break; case Token.COMMENT_DOCUMENTATION: state = DOCCOMMENT; start = text.offset; break;*/ case Token.LITERAL_STRING_DOUBLE_QUOTE: state = STRING; start = text.offset; break; default: state = Token.NULL; } s = text; try { yyreset(zzReader); yybegin(state); return yylex(); } catch (IOException ioe) { ioe.printStackTrace(); return new DefaultToken(); } } /** * Refills the input buffer. * * @return true if EOF was reached, otherwise * false. * @exception IOException if any I/O-Error occurs. */ private boolean zzRefill() throws java.io.IOException { 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) throws java.io.IOException { // '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 = s.offset; zzLexicalState = YYINITIAL; zzReader = reader; zzAtBOL = true; zzAtEOF = false; } %} LineCommentBegin = (";") Keyword = ([:][a-zA-Z?!\-+*/][a-zA-Z0-9?!\-+*/]*) NonzeroDigit = [1-9] Digit = ("0"|{NonzeroDigit}) HexDigit = ({Digit}|[A-Fa-f]) OctalDigit = ([0-7]) EscapedSourceCharacter = ("u"{HexDigit}{HexDigit}{HexDigit}{HexDigit}) Escape = ("\\"(([btnfr\"'\\])|([0123]{OctalDigit}?{OctalDigit}?)|({OctalDigit}{OctalDigit}?)|{EscapedSourceCharacter})) AnyCharacterButDoubleQuoteOrBackSlash = ([^\\\"\n]) UnclosedStringLiteral = ([\"]([\\].|[^\\\"])*[^\"]?) ErrorStringLiteral = ({UnclosedStringLiteral}[\"]) StringLiteral = ([\"]) CharLiteral = ("\\."|"\\space"|"\\tab"|"\\newline") AnyCharacter = ([.]*) Separator = ([\(\)\{\}\[\]]) NonSeparator = ([^\t\f\r\n\ \(\)\{\}\[\]\;\,\.\=\>\<\!\~\?\:\+\-\*\/\&\|\^\%\"\']) BooleanLiteral =("true"|"false") LineTerminator = (\n) WhiteSpace = ([ \t\f]) 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}+) Nil = ("nil") Quote = (\('\|`\)) Unquote = (\(\~@\|\~\)) DispatchStart = ("#^"|"#^{") Dispatch = ({DispatchStart}[^\s\t\n;\"}]*([ \t\n;\"]|"}")) VarQuote = ("#'"[.]*[ \t\n;(\"]) DefName = (\s*[a-zA-Z0-9?!\-+*\./<>]*) NonAssignmentOperator = ("+"|"-"|"<="|"^"|"<"|"*"|">="|"%"|">"|"/"|"!="|"?"|">>"|"!"|"&"|"=="|":"|">>"|"~"|">>>") AssignmentOperator = ("=") Operator = ({NonAssignmentOperator}|{AssignmentOperator}) Letter = [A-Za-z] LetterOrUnderscore = ({Letter}|[_]) Digit = [0-9] URLGenDelim = ([:\/\?#\[\]@]) URLSubDelim = ([\!\$&'\(\)\*\+,;=]) URLUnreserved = ({LetterOrUnderscore}|{Digit}|[\-\.\~]) URLCharacter = ({URLGenDelim}|{URLSubDelim}|{URLUnreserved}|[%]) URLCharacters = ({URLCharacter}*) URLEndCharacter = ([\/\$]|{Letter}|{Digit}) URL = (((https?|f(tp|ile))"://"|"www.")({URLCharacters}{URLEndCharacter})?) %state STRING %state EOL_COMMENT %% { "fn" | "if" | "cond" | "def" | "defn" | "let" | "new" | "defmacro" | "recur" | "loop" | "thisfn" | "do" | "quote" | "the-var" | "class" | "instance?" | "throw" | "try-finally" | "set!" | "monitor-enter" | "monitor-exit" { addToken(Token.RESERVED_WORD); } "load-file" | "eql-ref?" | "list" | "cons" | "conj" | "vector" | "hash-map" | "sorted-map" | "sorted-map-by" | "meta" | "with-meta" | "when" | "when-not" | "nil?" | "not" | "first" | "rest" | "second" | "ffirst" | "frest" | "rfirst" | "rrest" | "eql?" | "str" | "strcat" | "gensym" | "apply" | "list*" | "delay" | "lazy-cons" | "fnseq" | "concat" | "inc" | "dec" | "pos?" | "neg?" | "zero?" | "quot" | "rem" | "complement" | "constantly" | "identity" | "seq" | "count" | "assoc" | "dissoc" | "find" | "keys" | "vals" | "merge" | "rseq" | "sym" | "name" | "namespace" | "locking" | ".." | "->" | "defmulti" | "defmethod" | "remove-method" | "binding" | "find-var" | "ref" | "deref" | "commute" | "alter" | "set" | "ensure" | "sync" | "agent" | "agent-of" | "agent-errors" | "clear-agent-errors" | "reduce" | "reverse" | "comp" | "appl" | "every" | "not-every" | "any" | "not-any" | "map" | "pmap" | "mapcat" | "filter" | "take" | "take-while" | "drop" | "drop-while" | "zipmap" | "cycle" | "split-at" | "split-with" | "repeat" | "replicate" | "iterate" | "range" | "doseq" | "dotimes" | "into" | "eval" | "import" | "unimport" | "refer" | "unrefer" | "in-namespace" | "unintern" | "into-array" | "array" | "make-proxy" | "implement" | "prn" | "print" | "newline" | "*out*" | "*current-namespace*" | "*print-meta*" "doto" | "memfn" | "read" | "*in*" | "time" | "key" | "val" | "int" | "long" | "float" | "double" | "short" | "byte" | "boolean" | "char" | "aget" | "aset" | "aset-boolean" | "aset-int" | "aset-long" | "aset-float" | "aset-double" | "aset-short" | "aset-byte" | "make-array" | "peek" | "pop" | "nth" | "get" | "and" | "or" { addToken(Token.FUNCTION); } {LineTerminator} { addNullToken(); return firstToken; } {WhiteSpace}+ { addToken(Token.WHITESPACE); } {CharLiteral} { addToken(Token.LITERAL_CHAR); } {StringLiteral} { start = zzMarkedPos-1; yybegin(STRING); } //{UnclosedStringLiteral} { addToken(Token.ERROR_STRING_DOUBLE); addNullToken(); return firstToken; } //{ErrorStringLiteral} { addToken(Token.ERROR_STRING_DOUBLE); } {Nil} { addToken(Token.DATA_TYPE); } {BooleanLiteral} { addToken(Token.LITERAL_BOOLEAN); } {Quote} { addToken(Token.SEPARATOR); } {Unquote} { addToken(Token.SEPARATOR); } {VarQuote} { addToken(Token.SEPARATOR); } {Dispatch} { addToken(Token.DATA_TYPE); } {LineCommentBegin} { start = zzMarkedPos-1; yybegin(EOL_COMMENT); } {Separator} { addToken(Token.SEPARATOR); } {Operator} { addToken(Token.OPERATOR); } {IntegerLiteral} { addToken(Token.LITERAL_NUMBER_DECIMAL_INT); } {HexLiteral} { addToken(Token.LITERAL_NUMBER_HEXADECIMAL); } {FloatLiteral} { addToken(Token.LITERAL_NUMBER_FLOAT); } {ErrorNumberFormat} { addToken(Token.ERROR_NUMBER_FORMAT); } {Keyword} { addToken(Token.PREPROCESSOR); } {DefName} { addToken(Token.IDENTIFIER); } <> { addNullToken(); return firstToken; } . { addToken(Token.ERROR_IDENTIFIER); } } { [^\n\"]+ {} \n { addToken(start,zzStartRead-1, Token.LITERAL_STRING_DOUBLE_QUOTE); return firstToken; } "\"\"" {} "\"" { yybegin(YYINITIAL); addToken(start,zzStartRead, Token.LITERAL_STRING_DOUBLE_QUOTE); } <> { addToken(start,zzStartRead-1, Token.LITERAL_STRING_DOUBLE_QUOTE); return firstToken; } } { [^hwf\n]+ {} {URL} { int temp=zzStartRead; addToken(start,zzStartRead-1, Token.COMMENT_EOL); addHyperlinkToken(temp,zzMarkedPos-1, Token.COMMENT_EOL); start = zzMarkedPos; } [hwf] {} \n { addToken(start,zzStartRead-1, Token.COMMENT_EOL); addNullToken(); return firstToken; } <> { addToken(start,zzStartRead-1, Token.COMMENT_EOL); addNullToken(); return firstToken; } }