%{ /* * SPEditorTokens.l - created by Jakob on 3/15/09 for Sequel Pro * * This is the lex file used for syntax coloring. * To add new keywords, just add a line where the other * keywords are and replace spaces with {s} * * If you're new to lex and interested what the code below does, I found * "The Lex And Yacc Page" at http://dinosaur.compilertools.net/ to be * very helpful. Keep in mind that Xcode actually uses flex, the GNU * version of lex. There's a very thorough Texinfo manual for flex * available. (type 'info flex' in the Terminal) */ #import "SPEditorTokens.h" int utf8strlen(const char * _s); int yyuoffset, yyuleng; #define YY_NO_UNPUT //keep track of the current utf-8 character (not byte) offset and token length #define YY_USER_ACTION { yyuoffset += yyuleng; yyuleng = utf8strlen(yytext); } %} %option noyywrap %option case-insensitive s [ \t\n]+ alpha [a-z_\.À-ﾟ] numeric ([+-]?(([0-9]+\.[0-9]+)|([0-9]*\.[0-9]+)|([0-9]+))(e[+-]?[0-9]+)?) ops "+"|"-"|"*"|"/" word [a-z_\.0-9À-ﾟ@] nonword [^a-z_0-9À-ﾟ©#\n\t] keyword (R(IGHT|E(GEXP|STRICT|NAME|TURN|P(EAT|LACE)|VOKE|QUIRE|FERENCES|LEASE|A(D(S|_WRITE)?|L))|LIKE|ANGE)|GR(OUP{s}BY|ANT)|XOR|M(I(NUTE_(MICROSECOND|SECOND)|DDLEINT)|OD(IFIES)?|EDIUM(BLOB|TEXT|INT)|A(STER_SSL_VERIFY_SERVER_CERT|TCH))|B(Y|I(GINT|NARY)|OTH|E(TWEEN|FORE)|LOB)|S(MALLINT|SL|HOW|CHEMA(S)?|T(RAIGHT_JOIN|ARTING)|P(ECIFIC|ATIAL)|E(NSITIVE|COND_MICROSECOND|T|PARATOR|LECT)|QL(STATE|_(BIG_RESULT|SMALL_RESULT|CALC_FOUND_ROWS)|EXCEPTION|WARNING)?)|H(IGH_PRIORITY|OUR_(MI(NUTE|CROSECOND)|SECOND)|AVING)|YEAR_MONTH|N(O(_WRITE_TO_BINLOG|T)|U(MERIC|LL)|ATURAL)|C(R(OSS|EATE)|H(ECK|A(R(ACTER)?|NGE))|O(N(STRAINT|TINUE|DITION|VERT)|L(UMN|LATE))|UR(RENT_(TIME(STAMP)?|DATE|USER)|SOR)|A(S(CADE|E)|LL))|T(R(IGGER|UE|AILING)|HEN|INY(BLOB|TEXT|INT)|O|ERMINATED|ABLE)|I(GNORE|S|N(SE(RT|NSITIVE)|NER|T(1|2|8|3|O|4|E(RVAL|GER))?|OUT|DEX|FILE)?|TERATE|F)|ZEROFILL|O(R(DER{s}BY)?|N|UT(ER|FILE)?|PTI(MIZE|ON(ALLY)?))|D(ROP|I(STINCT(ROW)?|V)|OUBLE|UAL|E(SC(RIBE)?|C(IMAL|LARE)?|TERMINISTIC|FAULT|L(ETE|AYED))|A(Y_(MI(NUTE|CROSECOND)|SECOND|HOUR)|TABASE(S)?))|U(S(ING|E|AGE)|N(SIGNED|I(ON|QUE)|DO|LOCK)|TC_(TIME(STAMP)?|DATE)|PDATE)|JOIN|P(R(IMARY|OCEDURE|ECISION)|URGE)|E(X(I(STS|T)|PLAIN)|SCAPED|NCLOSED|LSE(IF)?|ACH)|VA(R(BINARY|YING|CHAR(ACTER)?)|LUES)|K(ILL|EY(S)?)|F(ROM|OR(CE|EIGN)?|ULLTEXT|ETCH|LOAT(8|4)?|ALSE)|W(RITE|H(ILE|E(RE|N))|ITH)|L(I(MIT|NE(S|AR)|KE)|O(NG(BLOB|TEXT)?|C(K|ALTIME(STAMP)?)|OP|W_PRIORITY|AD)|E(FT|A(DING|VE)))|A(S(C|ENSITIVE)?|N(D|ALYZE)|CCESSIBLE|DD|L(TER|L))) /* un-optimized keywords: ADD ACCESSIBLE ADD ALL ALTER ANALYZE AND AS ASC ASENSITIVE BEFORE BETWEEN BIGINT BINARY BLOB BOTH BY CALL CASCADE CASE CHANGE CHAR CHARACTER CHECK COLLATE COLUMN CONDITION CONSTRAINT CONTINUE CONVERT CREATE CROSS CURRENT_DATE CURRENT_TIME CURRENT_TIMESTAMP CURRENT_USER CURSOR DATABASE DATABASES DAY_HOUR DAY_MICROSECOND DAY_MINUTE DAY_SECOND DEC DECIMAL DECLARE DEFAULT DELAYED DELETE DESC DESCRIBE DETERMINISTIC DISTINCT DISTINCTROW DIV DOUBLE DROP DUAL EACH ELSE ELSEIF ENCLOSED ESCAPED EXISTS EXIT EXPLAIN FALSE FETCH FLOAT FLOAT4 FLOAT8 FOR FORCE FOREIGN FROM FULLTEXT GRANT GROUP{s}BY HAVING HIGH_PRIORITY HOUR_MICROSECOND HOUR_MINUTE HOUR_SECOND IF IGNORE IN INDEX INFILE INNER INOUT INSENSITIVE INSERT INT INT1 INT2 INT3 INT4 INT8 INTEGER INTERVAL INTO IS ITERATE JOIN KEY KEYS KILL LEADING LEAVE LEFT LIKE LIMIT LINEAR LINES LOAD LOCALTIME LOCALTIMESTAMP LOCK LONG LONGBLOB LONGTEXT LOOP LOW_PRIORITY MASTER_SSL_VERIFY_SERVER_CERT MATCH MEDIUMBLOB MEDIUMINT MEDIUMTEXT MIDDLEINT MINUTE_MICROSECOND MINUTE_SECOND MOD MODIFIES NATURAL NOT NO_WRITE_TO_BINLOG NULL NUMERIC ON OPTIMIZE OPTION OPTIONALLY OR ORDER{s}BY OUT OUTER OUTFILE PRECISION PRIMARY PROCEDURE PURGE RANGE READ READS READ_WRITE REAL REFERENCES REGEXP RELEASE RENAME REPEAT REPLACE REQUIRE RESTRICT RETURN REVOKE RIGHT RLIKE SCHEMA SCHEMAS SECOND_MICROSECOND SELECT SENSITIVE SEPARATOR SET SHOW SMALLINT SPATIAL SPECIFIC SQL SQLEXCEPTION SQLSTATE SQLWARNING SQL_BIG_RESULT SQL_CALC_FOUND_ROWS SQL_SMALL_RESULT SSL STARTING STRAIGHT_JOIN TABLE TERMINATED THEN TINYBLOB TINYINT TINYTEXT TO TRAILING TRIGGER TRUE UNDO UNION UNIQUE UNLOCK UNSIGNED UPDATE USAGE USE USING UTC_DATE UTC_TIME UTC_TIMESTAMP VALUES VARBINARY VARCHAR VARCHARACTER VARYING WHEN WHERE WHILE WITH WRITE XOR YEAR_MONTH ZEROFILL */ %x comment %x equation %% \"([^"\\]|\\(.|\n))*\"? { return SPT_DOUBLE_QUOTED_TEXT; } /* double quoted strings */ '([^'\\]|\\(.|\n))*'? { return SPT_SINGLE_QUOTED_TEXT; } /* single quoted strings */ `[^`]*`? { return SPT_BACKTICK_QUOTED_TEXT; } /* identifier quoting */ "/*" { BEGIN(comment); return SPT_COMMENT; } /* beginning of a c style comment */ [^*]* { return SPT_COMMENT; } /* anything except * in a c cmnt */ "*"+ { return SPT_COMMENT; } /* a range of * */ "*"+"/" { BEGIN(INITIAL); return SPT_COMMENT; } /* a range of * with trailing / Thanks to John Dickinson for publishing this method of parsing C comments on http://www.stillhq.com/pdfdb/000561/data.pdf */ #[^\n]*\n? | /* # Comments */ --[ \t][^\n]*\n? { return SPT_COMMENT; } /* -- Comments */ {numeric}/{ops} { BEGIN(equation); return SPT_NUMERIC; } /* numeric before operator */ {ops} { BEGIN(INITIAL); return SPT_OTHER; } /* set operator after a numeric */ {numeric}/{alpha} { return SPT_WORD; } /* catch numeric followed by char */ {s}+ { return SPT_WHITESPACE; } /* ignore spaces */ {keyword} { return SPT_RESERVED_WORD; } /* all the mysql reserved words */ {numeric} { return SPT_NUMERIC; } /* single numeric value */ {word}+ { return SPT_WORD; } /* return any word */ {nonword} { return SPT_OTHER; } /* return anything else */ <> { BEGIN(INITIAL); /* make sure we return to initial state when finished! */ yy_delete_buffer(YY_CURRENT_BUFFER); return 0; } %% #define ONEMASK ((size_t)(-1) / 0xFF) // adapted from http://www.daemonology.net/blog/2008-06-05-faster-utf8-strlen.html int utf8strlen(const char * _s) { const char * s; size_t count = 0; size_t u; unsigned char b; /* Handle any initial misaligned bytes. */ for (s = _s; (uintptr_t)(s) & (sizeof(size_t) - 1); s++) { b = *s; /* Exit if we hit a zero byte. */ if (b == '\0') goto done; /* Is this byte NOT the first byte of a character? */ count += (b >> 7) & ((~b) >> 6); } /* Handle complete blocks. */ for (; ; s += sizeof(size_t)) { /* Prefetch 256 bytes ahead. */ __builtin_prefetch(&s[256], 0, 0); /* Grab 4 or 8 bytes of UTF-8 data. */ u = *(size_t *)(s); /* Exit the loop if there are any zero bytes. */ if ((u - ONEMASK) & (~u) & (ONEMASK * 0x80)) break; /* Count bytes which are NOT the first byte of a character. */ u = ((u & (ONEMASK * 0x80)) >> 7) & ((~u) >> 6); count += (u * ONEMASK) >> ((sizeof(size_t) - 1) * 8); } /* Take care of any left-over bytes. */ for (; ; s++) { b = *s; /* Exit if we hit a zero byte. */ if (b == '\0') break; /* Is this byte NOT the first byte of a character? */ count += (b >> 7) & ((~b) >> 6); } done: return ((s - _s) - count); }