X-Git-Url: https://git.saurik.com/cycript.git/blobdiff_plain/1771224f6d1aaac181963198b5d9fe1b1ed5469e..c937f292473ac8c8be2694c7ebf59934d904d751:/Cycript.l.in diff --git a/Cycript.l.in b/Cycript.l.in index 7ee7d60..800ef74 100644 --- a/Cycript.l.in +++ b/Cycript.l.in @@ -1,5 +1,5 @@ /* Cycript - Optimizing JavaScript Compiler/Runtime - * Copyright (C) 2009-2014 Jay Freeman (saurik) + * Copyright (C) 2009-2015 Jay Freeman (saurik) */ /* GNU Affero General Public License, Version 3 {{{ */ @@ -19,17 +19,23 @@ **/ /* }}} */ -/* XXX: supposedly I will be screwed on very very long multi-line comments and need to replace these with a manual lexer. http://websrv.cs.fsu.edu/~engelen/courses/COP5621/Pr2.pdf */ - -%{ - +%top{ #if defined(__clang__) #pragma clang diagnostic push -#pragma clang diagnostic ignored "-Wunknown-pragmas" #pragma clang diagnostic ignored "-Wdeprecated-register" +#pragma clang diagnostic ignored "-Wunused-function" +#pragma clang diagnostic ignored "-Wunused-variable" +#else +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wsign-compare" +#pragma GCC diagnostic ignored "-Wunused-function" +#pragma GCC diagnostic ignored "-Wunused-variable" #endif +} + +%{ -#define YYLTYPE cy::location +#define YYLTYPE CYLocation #include "Cycript.tab.hh" typedef cy::parser::token tk; @@ -37,38 +43,28 @@ typedef cy::parser::token tk; #define YY_EXTRA_TYPE CYDriver * -// do /not/ fold token to the return: this is a macro and the ordering is dependent #define F(value, highlight) do { \ - int token(value); \ -@begin ObjectiveC - yyextra->no_.AtImplementation = false; \ -@end - yyextra->no_.Function = false; \ - yyextra->no_.OpenBrace = false; \ + yyextra->newline_ = yyextra->last_; \ + yyextra->last_ = false; \ + yyextra->next_ = false; \ + BEGIN(yyextra->template_.top() ? DivOrTemplateTail : Div); \ yylval->highlight_ = highlight; \ - return token; \ + return value; \ } while (false) -#define A new($pool) -#define Y $pool.strmemdup(yytext, yyleng) +#define P yyextra->pool_ +#define A new(P) +#define Y P.strmemdup(yytext, yyleng) #define I(type, Type, value, highlight) do { \ - yylval->type ## _ = A CY ## Type; \ + yylval->semantic_.type ## _ = A CY ## Type; \ F(value, highlight); \ } while (false) -#define T yylval->newline_ = yyextra->state_ == CYNewLine; BEGIN(Div); -#define C T yyextra->state_ = CYClear; -#define R T yyextra->state_ = CYRestricted; - #define N \ - if (yyextra->state_ != CYNewLine) { \ - if (yyextra->state_ != CYRestricted) \ - yyextra->state_ = CYNewLine; \ - else { \ - yyextra->state_ = CYClear; \ - F(tk::NewLine, hi::Nothing); \ - } \ + if (yyextra->last_ && yyextra->next_) { \ + yyextra->last_ = false; \ + F(tk::NewLine, hi::Nothing); \ } #define V(more) { \ @@ -80,25 +76,33 @@ typedef cy::parser::token tk; left = yyleng - (nl - yytext) - 1; \ nl = reinterpret_cast(memchr(nl + 1, '\n', left)); \ } while (nl != NULL); \ + yylloc->step(); \ yylloc->end.lines(lines); \ yylloc->end.columns(left); \ - yylloc->step(); \ more \ } else L \ } -#define L { \ - yylloc->step(); \ - yylloc->columns(yyleng); \ -} +#define R yylloc->end.columns(yyleng); +#define L yylloc->step(); R -#define M { \ - if (yyextra->commented_) { \ - I(comment, Comment(Y), tk::Comment, hi::Comment); \ - } \ +#define H(value, highlight) do { \ + if (yyextra->highlight_) \ + F(value, highlight); \ +} while (false) + +#define M \ + H(tk::Comment, hi::Comment); + +#define E(message) { \ + CYDriver::Error error; \ + error.location_ = *yylloc; \ + error.message_ = "syntax error, " message; \ + yyextra->errors_.push_back(error); \ + yyterminate(); \ } -int H(char c) { +int X(char c) { if (c >= '0' && c <= '9') return c - '0'; if (c >= 'a' && c <= 'f') @@ -108,6 +112,70 @@ int H(char c) { return -1; } +template +static void U(Type_ &local, unsigned point) { + if (false) { + } else if (point < 0x000080) { + *local++ = point; + } else if (point < 0x000800) { + *local++ = 0xc0 | point >> 0x06 & 0x1f; + goto one; + } else if (point < 0x010000) { + *local++ = 0xe0 | point >> 0x0c & 0x0f; + goto two; + } else if (point < 0x110000) { + *local++ = 0xf0 | point >> 0x12 & 0x07; + *local++ = 0x80 | point >> 0x0c & 0x3f; + two: + *local++ = 0x80 | point >> 0x06 & 0x3f; + one: + *local++ = 0x80 | point >> 0x00 & 0x3f; + } else _assert(false); +} + +static void U(char *&local, const char *text, yy_size_t &i) { + unsigned point; + + char next(text[++i]); + if (next != '{') { + point = X(text[i + 0]) << 12 | X(text[i + 1]) << 8 | X(text[i + 2]) << 4 | X(text[i + 3]); + i += 3; + } else { + point = 0; + for (;;) { + next = text[++i]; + if (next == '}') + break; + point = (point << 4) | X(next); + } + } + + U(local, point); +} + +#define CYLexBufferPoint(point) do { \ + std::back_insert_iterator > inserter(yyextra->buffer_); \ + U(inserter, point); \ +} while (false) + +#define CYLexBufferUnit(value) do { \ + yyextra->buffer_.push_back(value); \ +} while (false) + +#define CYLexBufferUnits(data, size) do { \ + yyextra->buffer_.insert(yyextra->buffer_.end(), data, data + size); \ +} while (false) + +#define CYLexBufferStart(condition) do { \ + yyextra->buffer_.clear(); \ + yy_push_state(condition, yyscanner); \ +} while (false) + +#define CYLexBufferEnd(type, Type, value, highlight) do { \ + yy_pop_state(yyscanner); \ + I(type, Type(P.strmemdup(yyextra->buffer_.data(), yyextra->buffer_.size()), yyextra->buffer_.size()), value, highlight); \ +} while (false) + #define YY_INPUT(data, value, size) { \ if (yyextra->data_.eof()) \ value = YY_NULL; \ @@ -123,25 +191,59 @@ int H(char c) { %option prefix="cy" %option bison-bridge %option bison-locations +%option nodefault %option noyywrap -%option yylineno +%option noyylineno %option nounput +%option nounistd +%option 8bit +%option backup %option batch %option never-interactive +%option pointer %option reentrant %option stack -Exponent [eE][+-]?[0-9]+ -Escape \\[\\'"bfnrtv]|\\0|\\x[0-9a-fA-F]{2}|\\u[0-9a-fA-F]{4}|\\\n - -IdentifierStart [a-zA-Z$_] -IdentifierPart [a-zA-Z$_0-9] +%option full +%option ecs + +U1 [\x00-\x7f] +U0 [\x80-\xbf] +U2 [\xc2-\xdf] +U3 [\xe0-\xef] +U4 [\xf0-\xf4] +UN [\xc0-\xc1\xf5-\xff] + +HexDigit [0-9a-fA-F] +LineTerminatorSequence \r?\n|\r|\xe2\x80[\xa8\xa9] +WhiteSpace [\x09\x0b\x0c\x20]|\xc2\xa0|\xef\xbb\xbf +UnicodeEscape \\u({HexDigit}{4}|\{{HexDigit}+\}) + +@include NotLineTerminator.l +CommentCharacter [^*/]{-}[\r\n\x80-\xff]|{NotLineTerminator} +SingleCharacter [^'\\]{-}[\r\n\x80-\xff]|{NotLineTerminator} +DoubleCharacter [^"\\]{-}[\r\n\x80-\xff]|{NotLineTerminator} +PlateCharacter [^$`\\]{-}[\r\n\x80-\xff]|{NotLineTerminator} + +@include UnicodeIDStart.l +@include UnicodeIDContinue.l +IdentifierMore [$_] + +UnicodeStart {IdentifierMore}|{UnicodeIDStart} +UnicodePart {IdentifierMore}|\xe2\x80[\x8c\x8d]|{UnicodeIDContinue} +UnicodeFail {U2}|{U3}|{U3}{U0}|{U4}|{U4}{U0}|{U4}{U0}{U0}|{UN}|{U0} +UnicodeScrap {UnicodePart}*{UnicodeFail}? + +IdentifierStart {UnicodeStart}|{UnicodeEscape} +IdentifierPart {UnicodePart}|{UnicodeEscape} +IdentifierFail {UnicodeFail}|\\(u({HexDigit}{0,3}|\{{HexDigit}*))? +IdentifierScrap {IdentifierPart}*{IdentifierFail}? NonTerminator [^\n] BackslashSequence \\{NonTerminator} RegularExpressionFirstChar [^\n*\\/]|{BackslashSequence} RegularExpressionChar [^\n\\/]|{BackslashSequence} -RegularExpressionFlags {IdentifierPart}* +RegularExpressionFlags {UnicodePart}* RegularExpressionChars {RegularExpressionChar}* RegularExpressionBody {RegularExpressionFirstChar}{RegularExpressionChars} @@ -151,8 +253,19 @@ XMLNamePart [a-zA-Z0-9.-_:] XMLName {XMLNameStart}{XMLNamePart}* @end +%x MultiLine + +%x LegacySingleString +%x LegacyDoubleString + +%x StrictSingleString +%x StrictDoubleString +%x StrictAccentString + %s Div +%s DivOrTemplateTail %s RegExp +%s RegExpOrTemplateTail @begin E4X %x XMLContent @@ -161,17 +274,28 @@ XMLName {XMLNameStart}{XMLNamePart}* %% -\/{RegularExpressionBody}\/{RegularExpressionFlags} L C I(literal, RegEx(Y), tk::RegularExpressionLiteral, hi::Constant); - + /* RegEx {{{ */ +{ + \/{RegularExpressionBody}\/{RegularExpressionFlags} L I(literal, RegEx(Y), tk::RegularExpressionLiteral, hi::Constant); + \/{RegularExpressionBody}\/{RegularExpressionFlags}{UnicodeFail} L E("invalid flags") + \/{RegularExpressionBody}?\\? L E("unterminated regex") +} + /* }}} */ + /* Comment {{{ */ #![^\n]* L M - \/\/[^\n]* L M - /* http://ostermiller.org/findcomment.html */ - /* XXX: unify these two rules using !? */ -\/\*!([^*]|[\r\n]|(\*+([^*/]|[\r\n])))*\*+\/ V() C I(comment, Comment(Y), tk::Comment, hi::Comment); -\/\*([^*]|[\r\n]|(\*+([^*/]|[\r\n])))*\*+\/ V(N) M +\/\* L yy_push_state(MultiLine, yyscanner); +{ + \**\*\/ R yy_pop_state(yyscanner); M N + \**{LineTerminatorSequence} yylloc->end.lines(); yyextra->last_ = true; + \**{CommentCharacter}|\/ R + \**({UnicodeFail}|\*) R E("invalid comment"); + <> R E("invalid comment") +} + /* }}} */ + /* Element {{{ */ @begin E4X "<>" L F(tk::LeftRight, hi::Structure); "" L F(tk::LeftSlashRight, hi::Structure); @@ -193,243 +317,309 @@ XMLName {XMLNameStart}{XMLNamePart}* "<" L F(tk::Left, hi::Structure); "" L C F(tk::EqualRight, hi::Operator); -"!" L C F(tk::Exclamation, hi::Operator); -"!=" L C F(tk::ExclamationEqual, hi::Operator); -"!==" L C F(tk::ExclamationEqualEqual, hi::Operator); -"-" L C F(tk::Hyphen, hi::Operator); -"-=" L C F(tk::HyphenEqual, hi::Operator); -"--" L C F(yylval->newline_ ? tk::HyphenHyphen_ : tk::HyphenHyphen, hi::Operator); -"->" L C F(tk::HyphenRight, hi::Operator); -"<" L C F(tk::Left, hi::Operator); -"<=" L C F(tk::LeftEqual, hi::Operator); -"<<" L C F(tk::LeftLeft, hi::Operator); -"<<=" L C F(tk::LeftLeftEqual, hi::Operator); -"%" L C F(tk::Percent, hi::Operator); -"%=" L C F(tk::PercentEqual, hi::Operator); -"." L C F(tk::Period, hi::Operator); -"|" L C F(tk::Pipe, hi::Operator); -"|=" L C F(tk::PipeEqual, hi::Operator); -"||" L C F(tk::PipePipe, hi::Operator); -"+" L C F(tk::Plus, hi::Operator); -"+=" L C F(tk::PlusEqual, hi::Operator); -"++" L C F(yylval->newline_ ? tk::PlusPlus_ : tk::PlusPlus, hi::Operator); -">" L C F(tk::Right, hi::Operator); -">=" L C F(tk::RightEqual, hi::Operator); -">>" L C F(tk::RightRight, hi::Operator); -">>=" L C F(tk::RightRightEqual, hi::Operator); -">>>" L C F(tk::RightRightRight, hi::Operator); -">>>=" L C F(tk::RightRightRightEqual, hi::Operator); -"*" L C F(tk::Star, hi::Operator); -"*=" L C F(tk::StarEqual, hi::Operator); -"~" L C F(tk::Tilde, hi::Operator); - -
"/" L C F(tk::Slash, hi::Operator); -
"/=" L C F(tk::SlashEqual, hi::Operator); - -":" L C F(tk::Colon, hi::Structure); -"," L C F(tk::Comma, hi::Structure); -"?" L C F(tk::Question, hi::Structure); -";" L C F(tk::SemiColon, hi::Structure); - -"(" L C F(tk::OpenParen, hi::Structure); -")" L C F(tk::CloseParen, hi::Structure); - -"{" L C F(yyextra->no_.OpenBrace ? tk::OpenBrace__ : yylval->newline_ ? tk::OpenBrace_ : tk::OpenBrace, hi::Structure); -"}" L C F(tk::CloseBrace, hi::Structure); - -"[" L C F(tk::OpenBracket, hi::Structure); -"]" L C F(tk::CloseBracket, hi::Structure); - -"@error" L C F(tk::AtError, hi::Error); +"&" L F(tk::Ampersand, hi::Operator); +"&&" L F(tk::AmpersandAmpersand, hi::Operator); +"&=" L F(tk::AmpersandEqual, hi::Operator); +"^" L F(tk::Carrot, hi::Operator); +"^=" L F(tk::CarrotEqual, hi::Operator); +"=" L F(tk::Equal, hi::Operator); +"==" L F(tk::EqualEqual, hi::Operator); +"===" L F(tk::EqualEqualEqual, hi::Operator); +"=>" L F(yyextra->newline_ ? tk::EqualRight_ : tk::EqualRight, hi::Operator); +"!" L F(tk::Exclamation, hi::Operator); +"!=" L F(tk::ExclamationEqual, hi::Operator); +"!==" L F(tk::ExclamationEqualEqual, hi::Operator); +"-" L F(tk::Hyphen, hi::Operator); +"-=" L F(tk::HyphenEqual, hi::Operator); +"--" L F(yyextra->newline_ ? tk::HyphenHyphen_ : tk::HyphenHyphen, hi::Operator); +"->" L F(tk::HyphenRight, hi::Operator); +"<" L F(tk::Left, hi::Operator); +"<=" L F(tk::LeftEqual, hi::Operator); +"<<" L F(tk::LeftLeft, hi::Operator); +"<<=" L F(tk::LeftLeftEqual, hi::Operator); +"%" L F(tk::Percent, hi::Operator); +"%=" L F(tk::PercentEqual, hi::Operator); +"." L F(tk::Period, hi::Operator); +"|" L F(tk::Pipe, hi::Operator); +"|=" L F(tk::PipeEqual, hi::Operator); +"||" L F(tk::PipePipe, hi::Operator); +"+" L F(tk::Plus, hi::Operator); +"+=" L F(tk::PlusEqual, hi::Operator); +"++" L F(yyextra->newline_ ? tk::PlusPlus_ : tk::PlusPlus, hi::Operator); +">" L F(tk::Right, hi::Operator); +">=" L F(tk::RightEqual, hi::Operator); +">>" L F(tk::RightRight, hi::Operator); +">>=" L F(tk::RightRightEqual, hi::Operator); +">>>" L F(tk::RightRightRight, hi::Operator); +">>>=" L F(tk::RightRightRightEqual, hi::Operator); +"*" L F(tk::Star, hi::Operator); +"*=" L F(tk::StarEqual, hi::Operator); +"~" L F(tk::Tilde, hi::Operator); + +"/" L F(tk::Slash, hi::Operator); +"/=" L F(tk::SlashEqual, hi::Operator); + +":" L F(tk::Colon, hi::Structure); +"," L F(tk::Comma, hi::Structure); +"?" L F(tk::Question, hi::Structure); +";" L F(tk::SemiColon, hi::Structure); + +"(" L F(tk::OpenParen, hi::Structure); +")" L F(tk::CloseParen, hi::Structure); + +"{" L yyextra->template_.push(false); F(yyextra->newline_ ? tk::OpenBrace_ : tk::OpenBrace, hi::Structure); +"}" L yyextra->template_.pop(); F(tk::CloseBrace, hi::Structure); + +"[" L F(tk::OpenBracket, hi::Structure); +"]" L F(tk::CloseBracket, hi::Structure); + /* }}} */ + /* Keyword {{{ */ +"@error" L F(tk::At_error_, hi::Error); @begin Java -"@class" L C F(tk::AtClass, hi::Meta); +"@class" L F(tk::At_class_, hi::Meta); @end @begin C -"typedef" L C I(identifier, Identifier("typedef"), tk::Typedef, hi::Meta); -"unsigned" L C I(identifier, Identifier("unsigned"), tk::Unsigned, hi::Type); -"signed" L C I(identifier, Identifier("signed"), tk::Signed, hi::Type); +"@encode" L F(tk::At_encode_, hi::Meta); @end -@begin C -"@encode" L C F(tk::AtEncode, hi::Meta); +@begin ObjectiveC +"@end" L F(tk::At_end_, hi::Meta); +"@false" L F(tk::At_false_, hi::Constant); +"@implementation" L F(tk::At_implementation_, hi::Meta); +"@import" L F(tk::At_import_, hi::Special); +"@NO" L F(tk::At_NO_, hi::Constant); +"@null" L F(tk::At_null_, hi::Constant); +"@selector" L F(tk::At_selector_, hi::Meta); +"@true" L F(tk::At_true_, hi::Constant); +"@YES" L F(tk::At_YES_, hi::Constant); @end +@({UnicodeStart}{UnicodeScrap}|{UnicodeFail}) L E("invalid keyword") + /* }}} */ + /* Highlight {{{ */ +"undefined" L F(tk::_undefined_, hi::Operator); + @begin ObjectiveC -"@end" L C F(tk::AtEnd, hi::Meta); -"@implementation" L C F(yyextra->no_.AtImplementation ? tk::AtImplementation_ : tk::AtImplementation, hi::Meta); -"@import" L C F(tk::AtImport, hi::Special); -"@selector" L C F(tk::AtSelector, hi::Meta); - -"NULL" L C I(identifier, Identifier("NULL"), tk::Identifier_, hi::Constant); -"nil" L C I(identifier, Identifier("nil"), tk::Identifier_, hi::Constant); -"YES" L C I(identifier, Identifier("YES"), tk::Yes, hi::Constant); -"NO" L C I(identifier, Identifier("NO"), tk::No, hi::Constant); - -"bool" L C I(identifier, Identifier("bool"), tk::Identifier_, hi::Type); -"BOOL" L C I(identifier, Identifier("BOOL"), tk::Identifier_, hi::Type); -"id" L C I(identifier, Identifier("id"), tk::Identifier_, hi::Type); -"SEL" L C I(identifier, Identifier("SEL"), tk::Identifier_, hi::Type); +"bool" L F(tk::_bool_, hi::Type); +"BOOL" L F(tk::_BOOL_, hi::Type); +"id" L F(tk::_id_, hi::Type); +"nil" L F(tk::_nil_, hi::Constant); +"NULL" L F(tk::_NULL_, hi::Constant); +"SEL" L F(tk::_SEL_, hi::Type); @end + /* }}} */ + /* Reserved {{{ */ +"abstract" L /*FII*/ F(tk::_abstract_, hi::Meta); +"await" L /*II?*/ F(tk::_await_, hi::Meta); +"boolean" L /*FII*/ F(tk::_boolean_, hi::Type); +"break" L /*KKK*/ F(tk::_break_, hi::Control); +"byte" L /*FII*/ F(tk::_byte_, hi::Type); +"case" L /*KKK*/ F(tk::_case_, hi::Control); +"catch" L /*KKK*/ F(tk::_catch_, hi::Control); +"char" L /*FII*/ F(tk::_char_, hi::Type); +"class" L /*FFK*/ F(tk::_class_, hi::Meta); +"const" L /*FFK*/ F(tk::_const_, hi::Meta); +"continue" L /*KKK*/ F(tk::_continue_, hi::Control); +"debugger" L /*FKK*/ F(tk::_debugger_, hi::Meta); +"default" L /*KKK*/ F(tk::_default_, hi::Control); +"delete" L /*KKK*/ F(tk::_delete_, hi::Operator); +"do" L /*KKK*/ F(tk::_do_, hi::Control); +"double" L /*FII*/ F(tk::_double_, hi::Type); +"else" L /*KKK*/ F(tk::_else_, hi::Control); +"enum" L /*FFF*/ F(tk::_enum_, hi::Meta); +"export" L /*FFK*/ F(tk::_export_, hi::Meta); +"extends" L /*FFK*/ F(tk::_extends_, hi::Meta); +"false" L /*LLL*/ F(tk::_false_, hi::Constant); +"final" L /*FII*/ F(tk::_final_, hi::Meta); +"finally" L /*KKK*/ F(tk::_finally_, hi::Control); +"float" L /*FII*/ F(tk::_float_, hi::Type); +"for" L /*KKK*/ F(tk::_for_, hi::Control); +"function" L /*KKK*/ F(tk::_function_, hi::Meta); +"goto" L /*FII*/ F(tk::_goto_, hi::Control); +"if" L /*KKK*/ F(tk::_if_, hi::Control); +"implements" L /*FSS*/ F(tk::_implements_, hi::Meta); +"import" L /*FFK*/ F(tk::_import_, hi::Meta); +"in" L /*KKK*/ F(yyextra->in_.top() ? tk::_in__ : tk::_in_, hi::Operator); +"instanceof" L /*KKK*/ F(tk::_instanceof_, hi::Operator); +"int" L /*FII*/ F(tk::_int_, hi::Type); +"interface" L /*FSS*/ F(tk::_interface_, hi::Meta); +"let" L /*IS?*/ F(tk::_let_, hi::Meta); +"long" L /*FII*/ F(tk::_long_, hi::Type); +"native" L /*FII*/ F(tk::_native_, hi::Meta); +"new" L /*KKK*/ F(tk::_new_, hi::Operator); +"null" L /*LLL*/ F(tk::_null_, hi::Constant); +"package" L /*FSS*/ F(tk::_package_, hi::Meta); +"private" L /*FSS*/ F(tk::_private_, hi::Meta); +"protected" L /*FSS*/ F(tk::_protected_, hi::Meta); +"public" L /*FSS*/ F(tk::_public_, hi::Meta); +"return" L /*KKK*/ F(tk::_return_, hi::Control); +"short" L /*FII*/ F(tk::_short_, hi::Type); +"static" L /*FS?*/ F(tk::_static_, hi::Meta); +"super" L /*FFK*/ F(tk::_super_, hi::Constant); +"switch" L /*KKK*/ F(tk::_switch_, hi::Control); +"synchronized" L /*FII*/ F(tk::_synchronized_, hi::Meta); +"this" L /*KKK*/ F(tk::_this_, hi::Constant); +"throw" L /*KKK*/ F(tk::_throw_, hi::Control); +"throws" L /*FII*/ F(tk::_throws_, hi::Meta); +"transient" L /*FII*/ F(tk::_transient_, hi::Meta); +"true" L /*LLL*/ F(tk::_true_, hi::Constant); +"try" L /*KKK*/ F(tk::_try_, hi::Control); +"typeof" L /*KKK*/ F(tk::_typeof_, hi::Operator); +"var" L /*KKK*/ F(tk::_var_, hi::Meta); +"void" L /*KKK*/ F(tk::_void_, hi::Operator); +"volatile" L /*FII*/ F(tk::_volatile_, hi::Meta); +"while" L /*KKK*/ F(tk::_while_, hi::Control); +"with" L /*KKK*/ F(tk::_with_, hi::Control); +"yield" L /*IS?*/ F(tk::_yield_, hi::Control); + +"auto" L F(tk::_auto_, hi::Meta); +"each" L F(tk::_each_, hi::Control); +"of" L F(tk::_of_, hi::Operator); -"undefined" L C I(identifier, Identifier("undefined"), tk::Identifier_, hi::Operator); - -"false" L C I(false, False(), tk::False, hi::Constant); -"null" L C I(null, Null(), tk::Null, hi::Constant); -"true" L C I(true, True(), tk::True, hi::Constant); - -"auto" L C I(word, Word("auto"), tk::Auto, hi::Meta); -"break" L R I(word, Word("break"), tk::Break, hi::Control); -"case" L C I(word, Word("case"), tk::Case, hi::Control); -"catch" L C I(word, Word("catch"), tk::Catch, hi::Control); -"continue" L R I(word, Word("continue"), tk::Continue, hi::Control); -"default" L C I(word, Word("default"), tk::Default, hi::Control); -"delete" L C I(word, Word("delete"), tk::Delete, hi::Operator); -"do" L C I(word, Word("do"), tk::Do, hi::Control); -"else" L C I(word, Word("else"), tk::Else, hi::Control); -"finally" L C I(word, Word("finally"), tk::Finally, hi::Control); -"for" L C I(word, Word("for"), tk::For, hi::Control); -"function" L C I(word, Word("function"), yyextra->no_.Function ? tk::Function_ : tk::Function, hi::Meta); -"if" L C I(word, Word("if"), tk::If, hi::Control); -"in" L C I(word, Word("in"), yyextra->in_.top() ? tk::In_ : tk::In, hi::Operator); -"instanceof" L C I(word, Word("instanceof"), tk::InstanceOf, hi::Operator); -"new" L C I(word, Word("new"), tk::New, hi::Operator); -"return" L R I(word, Word("return"), tk::Return, hi::Control); -"switch" L C I(word, Word("switch"), tk::Switch, hi::Control); -"this" L C I(this, This(), tk::This, hi::Constant); -"throw" L R I(word, Word("throw"), tk::Throw, hi::Control); -"try" L C I(word, Word("try"), tk::Try, hi::Control); -"typeof" L C I(word, Word("typeof"), tk::TypeOf, hi::Operator); -"var" L C I(word, Word("var"), tk::Var, hi::Meta); -"void" L C I(word, Word("void"), tk::Void, hi::Operator); -"while" L C I(word, Word("while"), tk::While, hi::Control); -"with" L C I(word, Word("with"), tk::With, hi::Control); - -"debugger" L C I(word, Word("debugger"), tk::Debugger, hi::Meta); - -"const" L C I(word, Word("const"), tk::Const, hi::Meta); - -"class" L C I(word, Word("class"), tk::Class, hi::Meta); -"enum" L C I(word, Word("enum"), tk::Enum, hi::Meta); -"export" L C I(word, Word("export"), tk::Export, hi::Meta); -"extends" L C I(word, Word("extends"), tk::Extends, hi::Meta); -"import" L C I(word, Word("import"), tk::Import, hi::Meta); -"super" L C I(word, Word("super"), tk::Super, hi::Constant); - -"implements" L C I(identifier, Identifier("implements"), tk::Implements, hi::Meta); -"interface" L C I(identifier, Identifier("interface"), tk::Interface, hi::Meta); -"package" L C I(identifier, Identifier("package"), tk::Package, hi::Meta); -"private" L C I(identifier, Identifier("private"), tk::Private, hi::Meta); -"protected" L C I(identifier, Identifier("protected"), tk::Protected, hi::Meta); -"public" L C I(identifier, Identifier("public"), tk::Public, hi::Meta); -"static" L C I(identifier, Identifier("static"), tk::Static, hi::Meta); - -"abstract" L C I(identifier, Identifier("abstract"), tk::Abstract, hi::Meta); -"boolean" L C I(identifier, Identifier("boolean"), tk::Boolean, hi::Type); -"byte" L C I(identifier, Identifier("byte"), tk::Byte, hi::Type); -"char" L C I(identifier, Identifier("char"), tk::Char, hi::Type); -"double" L C I(identifier, Identifier("double"), tk::Double, hi::Type); -"final" L C I(identifier, Identifier("final"), tk::Final, hi::Meta); -"float" L C I(identifier, Identifier("float"), tk::Float, hi::Type); -"goto" L C I(identifier, Identifier("goto"), tk::Goto, hi::Control); -"int" L C I(identifier, Identifier("int"), tk::Int, hi::Type); -"long" L C I(identifier, Identifier("long"), tk::Long, hi::Type); -"native" L C I(identifier, Identifier("native"), tk::Native, hi::Meta); -"short" L C I(identifier, Identifier("short"), tk::Short, hi::Type); -"synchronized" L C I(identifier, Identifier("synchronized"), tk::Synchronized, hi::Meta); -"throws" L C I(identifier, Identifier("throws"), tk::Throws, hi::Meta); -"transient" L C I(identifier, Identifier("transient"), tk::Transient, hi::Meta); -"volatile" L C I(identifier, Identifier("volatile"), tk::Volatile, hi::Meta); - -"let" L C I(identifier, Identifier("let"), tk::Let, hi::Meta); -"yield" L C I(identifier, Identifier("yield"), tk::Yield, hi::Control); - -"each" L C I(identifier, Identifier("each"), tk::Each, hi::Control); -"of" L C I(identifier, Identifier("of"), tk::Of, hi::Operator); +@begin C +"extern" L F(tk::_extern_, hi::Type); +"signed" L F(tk::_signed_, hi::Type); +"typedef" L F(tk::_typedef_, hi::Meta); +"unsigned" L F(tk::_unsigned_, hi::Type); +@end + +@begin ObjectiveC +"NO" L F(tk::_NO_, hi::Constant); +"YES" L F(tk::_YES_, hi::Constant); +@end @begin E4X -"namespace" L C I(identifier, Identifier("namespace"), tk::Namespace, hi::Meta); -"xml" L C I(identifier, Identifier("xml"), tk::XML, hi::Meta); +"namespace" L F(tk::_namespace_, hi::Meta); +"xml" L F(tk::_xml_, hi::Meta); @end + /* }}} */ + /* Identifier {{{ */ +{UnicodeStart}{UnicodePart}* L I(identifier, Identifier(Y), tk::Identifier_, hi::Identifier); -{IdentifierStart}{IdentifierPart}* L C I(identifier, Identifier(Y), tk::Identifier_, hi::Identifier); +{IdentifierStart}{IdentifierPart}* L { + char *value(A char[yyleng + 1]); + char *local(value); -(\.[0-9]+|(0|[1-9][0-9]*)(\.[0-9]*)?){Exponent}? L C I(number, Number(strtod(yytext, NULL)), tk::NumericLiteral, hi::Constant); + for (yy_size_t i(0), e(yyleng); i != e; ++i) { + char next(yytext[i]); + if (next != '\\') + *local++ = next; + else + U(local, yytext, ++i); + } -0[xX][0-9a-fA-F]+ L C I(number, Number(strtoull(yytext + 2, NULL, 16)), tk::NumericLiteral, hi::Constant); -0[0-7]+ L C I(number, Number(strtoull(yytext + 1, NULL, 8)), tk::NumericLiteral, hi::Constant); -0[bB][0-1]+ L C I(number, Number(strtoull(yytext + 2, NULL, 2)), tk::NumericLiteral, hi::Constant); + *local = '\0'; + I(identifier, Identifier(value), tk::Identifier_, hi::Identifier); +} -\"([^"\\\n]|{Escape})*\"|'([^'\\\n]|{Escape})*' L C { - char *value(A char[yyleng]); - char *local(value); +({IdentifierStart}{IdentifierPart}*)?{IdentifierFail} L E("invalid identifier") + /* }}} */ + /* Number {{{ */ +0[0-7]+ L I(number, Number(strtoull(yytext + 1, NULL, 8)), tk::NumericLiteral, hi::Constant); +0[0-9]+ L I(number, Number(strtoull(yytext + 1, NULL, 10)), tk::NumericLiteral, hi::Constant); + +0[xX][0-9a-fA-F]+ L I(number, Number(strtoull(yytext + 2, NULL, 16)), tk::NumericLiteral, hi::Constant); +0[oO][0-7]+ L I(number, Number(strtoull(yytext + 2, NULL, 8)), tk::NumericLiteral, hi::Constant); +0[bB][0-1]+ L I(number, Number(strtoull(yytext + 2, NULL, 2)), tk::NumericLiteral, hi::Constant); + +(\.[0-9]+|(0|[1-9][0-9]*)(\.[0-9]*)?)([eE][+-]?[0-9]+)? L I(number, Number(strtod(yytext, NULL)), tk::NumericLiteral, hi::Constant); +(\.[0-9]+|(0|[1-9][0-9]*)(\.[0-9]*)?)[eE][+-]?{IdentifierScrap} L E("invalid exponent") +(\.?[0-9]|(0|[1-9][0-9]*)\.){IdentifierScrap} L E("invalid number") + /* }}} */ + /* String {{{ */ +\' L CYLexBufferStart(LegacySingleString); +{ + \' R CYLexBufferEnd(string, String, tk::StringLiteral, hi::Constant); + {SingleCharacter}+ R CYLexBufferUnits(yytext, yyleng); + {SingleCharacter}*{UnicodeFail} R E("invalid character"); + {LineTerminatorSequence} R E("invalid newline"); +} - for (yy_size_t i(1), e(yyleng - 1); i != e; ++i) { - char next(yytext[i]); +\" L CYLexBufferStart(LegacyDoubleString); +{ + \" R CYLexBufferEnd(string, String, tk::StringLiteral, hi::Constant); + {DoubleCharacter}+ R CYLexBufferUnits(yytext, yyleng); + {DoubleCharacter}*{UnicodeFail} R E("invalid character"); + {LineTerminatorSequence} R E("invalid newline"); +} + /* }}} */ + /* Template {{{ */ +"`" L yyextra->tail_ = false; CYLexBufferStart(StrictAccentString); +"}" L yyextra->tail_ = true; yyextra->template_.pop(); CYLexBufferStart(StrictAccentString); - if (yytext[i] == '\\') - switch (next = yytext[++i]) { - case '\n': continue; - case '\\': next = '\\'; break; - case '\'': next = '\''; break; - case '"': next = '"'; break; - case 'b': next = '\b'; break; - case 'f': next = '\f'; break; - case 'n': next = '\n'; break; - case 'r': next = '\r'; break; - case 't': next = '\t'; break; - case 'v': next = '\v'; break; - case '0': next = '\0'; break; - - case 'x': - next = H(yytext[i + 1]) << 4 | H(yytext[i + 2]); - i += 2; - break; - } +{ + "`" R CYLexBufferEnd(string, String, yyextra->tail_ ? tk::TemplateTail : tk::NoSubstitutionTemplate, hi::Constant); + "${" R yyextra->template_.push(true); CYLexBufferEnd(string, String, yyextra->tail_ ? tk::TemplateMiddle : tk::TemplateHead, hi::Constant); - *local++ = next; - } + "$" R CYLexBufferUnit('$'); - *local = '\0'; - I(string, String(value, local - value), tk::StringLiteral, hi::Constant); + {PlateCharacter}+ R CYLexBufferUnits(yytext, yyleng); + {PlateCharacter}*{UnicodeFail} R E("invalid character"); + {LineTerminatorSequence} R E("invalid newline"); +} + /* }}} */ + /* Escapes {{{ */ +{ + \\[0-3][0-7][0-7] R CYLexBufferPoint(X(yytext[1]) << 6 | X(yytext[2]) << 3 | X(yytext[3])); + \\[0-7][0-7] R CYLexBufferUnit(X(yytext[1]) << 3 | X(yytext[2])); + \\[0-7] R CYLexBufferUnit(X(yytext[1])); } -\r?\n|\r|\xe2\x80[\xa8\xa9] yylloc->end.lines(); yylloc->step(); N +{ + \\0[0-7] R E("legacy escape"); + \\0 R CYLexBufferUnit('\0'); +} -[ \t] L +{ + \\b R CYLexBufferUnit('\b'); + \\f R CYLexBufferUnit('\f'); + \\n R CYLexBufferUnit('\n'); + \\r R CYLexBufferUnit('\r'); + \\t R CYLexBufferUnit('\t'); + \\v R CYLexBufferUnit('\v'); -<> if (yyextra->auto_) { yyextra->auto_ = false; F(tk::AutoComplete, hi::Nothing); } L yyterminate(); + \\x{HexDigit}{2} R CYLexBufferPoint(X(yytext[2]) << 4 | X(yytext[3])); -. L { - CYDriver::Error error; - error.location_ = *yylloc; - error.message_ = "syntax error, unknown token"; - yyextra->errors_.push_back(error); - yyterminate(); + \\u{HexDigit}{4} R CYLexBufferPoint(X(yytext[2]) << 12 | X(yytext[3]) << 8 | X(yytext[4]) << 4 | X(yytext[5])); + + \\u\{{HexDigit}+\} R { + unsigned point(0); + for (yy_size_t i(3); i != yyleng - 1; ++i) + point = point << 4 | X(yytext[i]); + CYLexBufferPoint(point); + } + + \\{LineTerminatorSequence} yylloc->end.lines(); + \\(.|{NotLineTerminator}) R CYLexBufferUnits(yytext + 1, yyleng - 1); + + \\(x{HexDigit}{0,1}|u({HexDigit}{0,3}|\{{HexDigit}*)|{UnicodeFail})? R E("invalid escape"); + <> R E("invalid string"); } + /* }}} */ + +{LineTerminatorSequence} yylloc->step(); yylloc->end.lines(); yyextra->last_ = true; N +{WhiteSpace} L + +<> if (yyextra->auto_) { yyextra->auto_ = false; F(tk::AutoComplete, hi::Nothing); } L yyterminate(); + +. L E("invalid character") %% @@ -442,27 +632,12 @@ void CYDriver::ScannerDestroy() { cylex_destroy(scanner_); } -CYDriver::Condition CYDriver::GetCondition() { - switch (yy_top_state(scanner_)) { - case RegExp: - return RegExpCondition; -@begin E4X - case XMLContent: - return XMLContentCondition; - case XMLTag: - return XMLTagCondition; -@end - default: - _assert(false); - } -} - void CYDriver::SetCondition(Condition condition) { struct yyguts_t *yyg(reinterpret_cast(scanner_)); switch (condition) { case RegExpCondition: - BEGIN(RegExp); + BEGIN(template_.top() ? RegExpOrTemplateTail : RegExp); break; @begin E4X case XMLContentCondition: @@ -501,4 +676,7 @@ void CYDriver::PopCondition() { #if defined(__clang__) #pragma clang diagnostic pop +#else +// must not pop -Wunused-function +//#pragma GCC diagnostic pop #endif