RE2JS(1) RE2JS(1) (NAME) re2js - JavaScript (SYNOPSIS) re2js [ OPTIONS ] [ WARNINGS ] INPUT - stdin . (INTRODUCTION) re2js . ( JavaScript ) / . . re2js . JavaScript . : // re2js $INPUT -o $OUTPUT function lex(yyinput) { let yycursor = 0; /*!re2c re2c:yyfill:enable = 0; [1-9][0-9]* { return true; } * { return false; } */ } if (!lex("1234\0")) { throw "error!" } re2js : // Generated by re2js // re2js $INPUT -o $OUTPUT function lex(yyinput) { let yycursor = 0; { let yych = 0 let yystate = 0 yyl: while (true) { switch (yystate) { case 0: yych = yyinput.charCodeAt(yycursor) yycursor += 1; switch (yych) { case 0x31: case 0x32: case 0x33: case 0x34: case 0x35: case 0x36: case 0x37: case 0x38: case 0x39: yystate = 2 continue yyl default: yystate = 1 continue yyl } case 1: { return false; } case 2: yych = yyinput.charCodeAt(yycursor) switch (yych) { case 0x30: case 0x31: case 0x32: case 0x33: case 0x34: case 0x35: case 0x36: case 0x37: case 0x38: case 0x39: yycursor += 1; yystate = 2 continue yyl default: yystate = 3 continue yyl } case 3: { return true; } default: throw "internal lexer error" } } } } if (!lex("1234\0")) { throw "error!" } re2js . : name = regular-expression ; name regular-expression . - . re2js . name . . . . configuration = value ; re2js . re2js . value - . . . regular-expression code regular-expression ( := ). regular-expression code . . . : * $. ( ). . . !action code code ( ). . !directive ; . . . (Blocks) /*!re2c */ %{ %} ( ). 2.2 . : /*!re2c[:] ... */ or %{[:] ... %} . re2js . . . /*!local:re2c[:] ... */ or %{local[:] ... %} ( ). /*!rules:re2c[:] ... */ or %{rules[:] ... %} -- . ( ). 2.2 re2js -r --reusable . /*!use:re2c[:] ... */ or %{use[:] ... %} . re2js . ( ). . 2.2 re2js -r --reusable . /*!max:re2c[:[:...]] ... */ or %{max[:[:...]] ... %} YYMAXFILL . YYMAXFILL ( ). C (#define YYMAXFILL ) Go (var YYMAXFILL int = ) . format @@{max} ( @@) YYMAXFILL . /*!maxnmatch:re2c[:[:...]] ... */ or %{maxnmatch[:[:...]] ... %} YYMAXNMATCH ( -P --posix-captures ). YYMAXNMATCH ( ). C (#define YYMAXNMATCH ) Go (var YYMAXNMATCH int = ) . format @@{max} ( @@) YYMAXNMATCH . /*!stags:re2c[:[:...]] ... */, /*!mtags:re2c[:[:...]] ... */ or %{stags[:[:...]] ... %}, %{mtags[:[:...]] ... %{ s-tag/m-tag re2js . ( ). : format separator. format @@{tag} ( @@) . separator format . /*!svars:re2c[:[:...]] ... */, /*!mvars:re2c[:[:...]] ... */ or %{svars[:[:...]] ... %}, %{mvars[:[:...]] ... %{ s-tag/m-tag ( --tags) re2js ( --captvars --posix-captvars) . ( ). : format separator. format @@{tag} ( @@) . separator format . /*!getstate:re2c[:[:...]] ... */ or %{getstate[:[:...]] ... %} ( --storable-state ). . . . --loop-switch goto . /*!conditions:re2c[:[:...]] ... */, /*!types:re2c... */ or %{conditions[:[:...]] ... %}, %{types... %} ( --conditions ). ( ). YYCONDTYPE . format separator . format @@{cond} ( @@) @@{num} . separator format . /*!include:re2c */ or %{include %} . #include C/C++ . --depfile . /*!header:re2c:on*/ or %{header:on %} . header:off re2js -t --type-header . /*!header:re2c:off*/ or %{header:off %} header:on*/ . /*!ignore:re2c ... */ or %{ignore ... %} . re2js : re2c:api, re2c:input --api. re2c:api:sigil ("sigil") API . @@ . . $ ${name} . . API re2c:YYFILL@len YYFILL. re2c:api:style API . functions ( C) free-form ( Go Rust). functions API . ( YYFILL) C/C++ (closures) Go Rust . free-form API : @@{var} @@ ( ). API re2c:YYFILL:naked YYFILL . re2c:bit-vectors, re2c:flags:bit-vectors, re2c:flags:b --bit-vectors . re2c:captures, re2c:leftmost-captures --leftmost-captures . re2c:captvars, re2c:leftmost-captvars --leftmost-captvars . re2c:case-insensitive, re2c:flags:case-insensitive --case-insensitive . re2c:case-inverted, re2c:flags:case-inverted --case-inverted . re2c:case-ranges, re2c:flags:case-ranges --case-ranges . re2c:computed-gotos, re2c:flags:computed-gotos, re2c:flags:g --computed-gotos . re2c:computed-gotos:relative, re2c:cgoto:relative --computed-gotos-relative . re2c:computed-gotos:threshold, re2c:cgoto:threshold goto if . 9 . re2c:cond:abort . re2c:cond:goto :=> . goto @@; . @@ ( re2c:api:sigil re2c:cond:goto@cond ). re2c:cond:goto@cond re2c:cond:goto . @@ . re2c:api:sigil . re2c:cond:divider . /* *********************************** */ . ( re2c:api;sigil re2c:cond:divider@cond ). re2c:cond:divider@cond re2c:cond:divider . @@ . re2c:api:sigil . re2c:cond:prefix, re2c:condprefix . yyc_ . re2c:cond:enumprefix, re2c:condenumprefix . yyc . re2c:debug-output, re2c:flags:debug-output, re2c:flags:d --debug-output . re2c:empty-class, re2c:flags:empty-class --empty-class . re2c:encoding:ebcdic, re2c:flags:ecb, re2c:flags:e --ebcdic . re2c:encoding:ucs2, re2c:flags:wide-chars, re2c:flags:w --ucs2 . re2c:encoding:utf8, re2c:flags:utf-8, re2c:flags:8 --utf8 . re2c:encoding:utf16, re2c:flags:utf-16, re2c:flags:x --utf16 . re2c:encoding:utf32, re2c:flags:unicode, re2c:flags:u --utf32 . re2c:encoding-policy, re2c:flags:encoding-policy --encoding-policy . re2c:eof (sentinel symbol) $ . -1 ( $ ). . . re2c:header, re2c:flags:type-header, re2c:flags:t . --header . re2c:indent:string . "\t" . . . re2c:indent:top . . . re2c:invert-captures --invert-captures . re2c:label:prefix, re2c:labelprefix DFA . yy . re2c:label:start, re2c:startlabel . . . . ( ). re2c:label:yyFillLabel YYFILL re2c:eof . re2c:label:yyloop --loop-switch . yyloop . re2c:label:yyNext YYGETSTATE ( re2c:state:nextlabel) . yyNext . re2c:lookahead, re2c:flags:lookahead ( --no-lookahead ). re2c:monadic ( Haskell ). re2c:nested-ifs, re2c:flags:nested-ifs, re2c:flags:s --nested-ifs . re2c:posix-captures, re2c:flags:posix-captures, re2c:flags:P --posix-captures . re2c:posix-captvars --posix-captvars . re2c:tags, re2c:flags:tags, re2c:flags:T --tags . re2c:tags:expression . re2js yyt . struct . @@{tag} @@ . re2c:tags:expression = "s.@@"; s.yyt . re2c:api:sigil ..TP re2c:tags:negative ( -1 (null pointer) ). re2c:tags:prefix . yyt . re2c:sentinel (sentinel) ( re2c:yyfill:enable = 0; re2c:eof ). : . -1` ( re2js ). . re2c:state:abort (default case) (state dispatch) (abort) -1 . re2c:state:nextlabel YYGETSTATE yyNext ( ). re2c:label:start getstate YYGETSTATE . re2c:unsafe, re2c:flags:unsafe --no-unsafe . (wrappers) unsafe YYPEEK . ( ). Rust . re2c:YYBACKUP, re2c:define:YYBACKUP API YYBACKUP . re2c:YYBACKUPCTX, re2c:define:YYBACKUPCTX API YYBACKUPCTX . re2c:YYCONDTYPE, re2c:define:YYCONDTYPE API YYCONDTYPE . re2c:YYCTYPE, re2c:define:YYCTYPE API YYCTYPE . re2c:YYCTXMARKER, re2c:define:YYCTXMARKER API YYCTXMARKER . re2c:YYCURSOR, re2c:define:YYCURSOR API YYCURSOR . re2c:YYDEBUG, re2c:define:YYDEBUG API YYDEBUG . re2c:YYFILL, re2c:define:YYFILL API YYFILL . re2c:YYFILL@len, re2c:define:YYFILL@len (sigil) YYFILL . @@ . re2c:api:sigil (override) . re2c:YYFILL:naked, re2c:define:YYFILL:naked re2c:api:style YYFILL (override) . API (free-form) . re2c:YYFN API YYFN . re2c:YYINPUT API YYINPUT . re2c:YYGETCOND, re2c:define:YYGETCONDITION API YYGETCOND . re2c:YYGETCOND:naked, re2c:define:YYGETCONDITION:naked re2c:api:style YYGETCOND (override) . API . re2c:YYGETSTATE, re2c:define:YYGETSTATE API YYGETSTATE . re2c:YYGETSTATE:naked, re2c:define:YYGETSTATE:naked re2c:api:style YYGETSTATE (override) . API . re2c:YYGETACCEPT, re2c:define:YYGETACCEPT API YYGETACCEPT . re2c:YYLESSTHAN, re2c:define:YYLESSTHAN API YYLESSTHAN . re2c:YYLIMIT, re2c:define:YYLIMIT API YYLIMIT . re2c:YYMARKER, re2c:define:YYMARKER API YYMARKER . re2c:YYMTAGN, re2c:define:YYMTAGN API YYMTAGN . re2c:YYMTAGP, re2c:define:YYMTAGP API YYMTAGP . re2c:YYPEEK, re2c:define:YYPEEK API YYPEEK . re2c:YYRESTORE, re2c:define:YYRESTORE API YYRESTORE . re2c:YYRESTORECTX, re2c:define:YYRESTORECTX API YYRESTORECTX . re2c:YYRESTORETAG, re2c:define:YYRESTORETAG API YYRESTORETAG . re2c:YYSETCOND, re2c:define:YYSETCONDITION API YYSETCOND . re2c:YYSETCOND@cond, re2c:define:YYSETCONDITION@cond (sigil) YYSETCOND . @@ . re2c:api:sigil (override) . re2c:YYSETCOND:naked, re2c:define:YYSETCONDITION:naked re2c:api:style YYSETCOND (override) . API . re2c:YYSETSTATE, re2c:define:YYSETSTATE API YYSETSTATE . re2c:YYSETSTATE@state, re2c:define:YYSETSTATE@state (sigil) YYSETSTATE . @@ . re2c:api:sigil (override) . re2c:YYSETSTATE:naked, re2c:define:YYSETSTATE:naked re2c:api:style YYSETSTATE (override) . API . re2c:YYSETACCEPT, re2c:define:YYSETACCEPT API YYSETACCEPT . re2c:YYSKIP, re2c:define:YYSKIP API YYSKIP . re2c:YYSHIFT, re2c:define:YYSHIFT API YYSHIFT . re2c:YYCOPYMTAG, re2c:define:YYCOPYMTAG API YYCOPYMTAG . re2c:YYCOPYSTAG, re2c:define:YYCOPYSTAG API YYCOPYSTAG . re2c:YYSHIFTMTAG, re2c:define:YYSHIFTMTAG API YYSHIFTMTAG . re2c:YYSHIFTSTAG, re2c:define:YYSHIFTSTAG API YYSHIFTSTAG . re2c:YYSTAGN, re2c:define:YYSTAGN API YYSTAGN . re2c:YYSTAGP, re2c:define:YYSTAGP API YYSTAGP . re2c:yyaccept, re2c:variable:yyaccept API yyaccept . re2c:yybm, re2c:variable:yybm API yybm . re2c:yybm:hex, re2c:variable:yybm:hex --bit-vectors . ( ). re2c:yych, re2c:variable:yych API yych . re2c:yych:emit, re2c:variable:yych:emit yych . . re2c:yych:conversion, re2c:variable:yych:conversion re2js yych YYCTYPE . ( ). re2c:yych:literals, re2c:variable:yych:literals yych . : char ( ) hex ( ) char_or_hex ( ). re2c:yyctable, re2c:variable:yyctable API yyctable ..TP re2c:yynmatch, re2c:variable:yynmatch API yynmatch . re2c:yypmatch, re2c:variable:yypmatch API yypmatch . re2c:yytarget, re2c:variable:yytarget API yytarget . re2c:yystable, re2c:variable:yystable . re2c:yystate, re2c:variable:yystate API yystate . re2c:yyfill, re2c:variable:yyfill API yyfill . re2c:yyfill:check YYFILL ( YYLESSTHAN generic API YYLIMIT C pointer API) . ( ). re2c:yyfill:enable YYFILL ( ) . ( ) YYFILL ( ). ( -W) re2c:sentinel . (YYFILL ). re2c:yyfill:parameter YYFILL . . ( ). re2c:YYFILL:naked re2c:api:style . re2c:yyfn:sep YYFN ( ). re2c:yyfn:throw YYFN ( ). (Regular expressions) re2js : "foo" . 'foo' . [a-xyz], [^a-xyz] ( ). . (newline). R \ S R S. R* R. R+ R. R? R . R{n} R n . R{n,} R n . R{n,m} R n m . (R) R . (R) --invert-captures . (!R) (!R) --invert-captures . R S : R S. R | S : R S. R / S (Lookahead): R S S . name name ( "name" Flex). {name} name Flex. @stag s-tag: @stag stag . #mtag m-tag: #mtag mtag . $ . : \a \b \f \n \r \t \v \\ \ooo \xhh \uhhhh \Uhhhhhhhh..SS " (Actions)" re2js : !entry code code . . (lexeme) . !pre_rule code code ( ) . ( ) . !post_rule code code ( ) . (trap statements) . (Directives) re2js : !use:name ; use name . . : . * $ . use use . !include file ; include : file . (Program interface) API . . . re2js ( ) . API . re2js API : Simple API API (backend) . : YYINPUT ( ) YYCURSOR YYMARKER YYCTXMARKER YYLIMIT ( YYINPUT ). Record API Record API . --api record re2c:api = record . API yyrecord ( re2c:yyrecord ) yyinput yycursor yymarker yyctxmarker yylimit ( ). Generic API API . --api generic re2c:api = generic . : YYPEEK YYSKIP YYBACKUP YYBACKUPCTX YYSTAGP YYSTAGN YYMTAGP YYMTAGN YYRESTORE YYRESTORECTX YYRESTORETAG YYSHIFT YYSHIFTSTAG YYSHIFTMTAG YYLESSTHAN YYEND. API . YYCTYPE ( ). ASCII EBCDIC UTF-8 . UTF-16 UCS-2 . UTF-32 . YYCURSOR l-value ( YYINPUT). YYCURSOR . YYCURSOR . YYLIMIT r-value ( YYINPUT). YYLIMIT . . YYCURSOR YYLIMIT . YYMARKER l-value ( YYINPUT). YYCURSOR (rollback) . . YYCTXMARKER l-value (trailing context) ( YYINPUT). . YYCTXMARKER / . YYFILL Generic API len. YYFILL len . re2c:eof len 1 YYFILL . re2c:eof YYFILL . len YYMAXFILL . YYFN --recursive-functions . re2c:fn:sep ( ) . ( void ). : ( ) ( - ). YYINPUT r-value ( ) . YYMAXFILL YYFILL. max . YYLESSTHAN Generic API len. r-value len true . YYEND Generic API . r-value ( [sentinel]) true . YYEND $ . YYLESSTHAN . YYPEEK Generic API . r-value YYCTYPE . YYSKIP Generic API . YYBACKUP Generic API ( YYRESTORE ). YYRESTORE Generic API YYBACKUP . YYBACKUPCTX Generic API ( YYRESTORECTX )..TP YYRESTORECTX API (trailing context) YYBACKUPCTX . YYRESTORETAG API tag tag . YYSTAGP API tag tag YYINPUT ( ). YYSTAGP tag . YYSTAGN API tag tag YYINPUT ( ). YYSTAGN tag . YYMTAGP API tag. YYMTAGP tag ( ). YYMTAGN API tag. YYMTAGN tag ( ). YYSHIFT API shift shift ( ). YYCOPYSTAG API lhs rhs s-tag rhs s-tag lhs . lhs rhs . YYCOPYMTAG API lhs rhs m-tag rhs m-tag lhs . lhs rhs . YYSHIFTSTAG API tag shift tag shift (code unit) ( ). YYSHIFTMTAG API tag shift tag shift ( ). YYMAXNMATCH POSIX . maxnmatch . YYCONDTYPE (enum) . conditions --header . YYGETACCEPT var . var . YYSETACCEPT : var ( l-value ) val ( ). var val . YYGETCOND (r-value) YYCONDTYPE . YYSETCOND cond cond . YYGETSTATE (r-value) . -1 . YYSETSTATE state state . YYDEBUG -d --debug-output . ( YYDEBUG ). YYDEBUG : state ( DFA -1) symbol ( ). yyaccept (l-value) . --storable-state . yybm ( --bitmaps). . . k- n- (true) n- k- . if switch . yych (l-value) YYCTYPE . -f --storable-state . yyctable ( --conditions --computed-gotos). yyfill (l-value) YYFILL ( YYFILL ). yynmatch (l-value) POSIX . -P --posix-captures . yypmatch (l-value) . yynmatch * 2 ( YYMAXNMATCH * 2 ). -P --posix-captures . yystable . yystate (l-value) --loop-switch DFA . yytarget ( ) . . yytarget --computed-gotos . re2c . re2c . re2c . -? --help -h . --api API . simple (lexer) . record (struct class ) . generic API . --bit-vectors -b . --nested-ifs . --captures, --leftmost-captures (leftmost greedy). yybmatch 2 * YYMAXNMATCH yynmatch . --captvars, --leftmost-captvars (leftmost greedy). yytl yytr k- . --case-insensitive (case-insensitive). --case-inverted : . --case-ranges case switch low ... high. C/C++ GCC Clang Tcc . case Tcc . --computed-gotos -g "computed goto" ( ). re2js . cgoto:threshold . cgoto:relative . --bit-vectors . --computed-gotos-relative --computed-gotos ( ). --computed-gotos . --conditions --start-conditions -c "" (conditions) Flex: . re2js goto . --depfile FILE FILE Makefile : [include-file ...]. / include include . --output . --ebcdic --ecb -e EBCDIC . re2js 0 -- 0xFF . --empty-class re2js . match-empty () ( ). match-none . error . --encoding-policy re2js (Unicode surrogates). fail re2js . substitute re2js 0xFFFD . ignore () re2js . . --flex-syntax -F Flex: . . --goto-label "goto/label": DFA goto . goto . --header --type-header -t HEADER HEADER. header:on header:off . enum ( conditions ). -I PATH PATH include . include . re2js FILE include -I . --input --api. default simple ( ). custom generic . --input-encoding re2js. ascii () re2js ASCII : . utf8 re2js UTF8 . --invert-captures . (...) (! ...) . (! ...) (...) . --lang . C D Go Haskell Java JS OCaml Python Rust Swift V Zig ( --syntax ). none . --location-format . gnu 'filename:line:column: ...' . msvc 'filename(line,column) ...' . gnu . --loop-switch "loop/switch": DFA switch case switch . yystate . yystate case . --nested-ifs -s if switch . . --no-debug-info -i . ( diff ). --no-generation-date . --no-version . --no-unsafe unsafe YYPEEK ( Rust ). YYPEEK (bounds-checking) . YYPEEK (release) --no-unsafe unsafe . --output -o OUTPUT OUTPUT. --posix-captures, -P POSIX. yybmatch 2 * YYMAXNMATCH yynmatch . --posix-captvars POSIX. yytl yytr k- . --recursive-functions (co-recursive) DFA . --reusable -r 2.2 ( ). --skeleton -S ("skeleton") . "skeleton" . . C ..TP --storable-state -f . push . YYGETSTATE YYSETSTATE yych yyaccept state . --syntax FILE FILE . FILE ( ) backend ( --lang none ). --tags -T (submatch) . --ucs2 --wide-chars -w UCS2 . re2js 0 -- 0xFFFF . --nested-ifs . --utf8 --utf-8 -8 UTF-8 . re2js 0 -- 0x10FFFF . --utf16 --utf-16 -x UTF16 . re2js 0 -- 0x10FFFF . --nested-ifs . --utf32 --unicode -u UTF32 . re2js 0 -- 0x10FFFF . --nested-ifs . --verbose . --vernum -V MMmmpp ( ). --version -v . --single-pass -1 . ( single pass ). --debug-output -d YYDEBUG . . --dump-adfa : DFA ( dot.). --dump-cfg : ( dot.). --dump-closure-stats : (closure). --dump-dfa-det : DFA ( dot.). --dump-dfa-min : DFA ( dot.). --dump-dfa-tagopt : DFA ( dot.). --dump-dfa-tree : DFA ( dot.). --dump-dfa-raw : DFA ( dot.). --dump-interf : (liveness analysis) . --dump-nfa : NFA ( dot.). --emit-dot -D dot. . Graphviz ( dot -Tpng -odfa.png dfa.dot). --dfa-minimization : DFA re2js. moore ( ). table " " . DFA . --eager-skip : -- . -- . --no-lookahead . TDFA(0) . TDFA(1) TDFA(0) . . TDFA(0) TDFA(1) . --no-optimize-tags : ( ). --posix-closure : POSIX: gor1 () Goldberg-Radzik gtop " " . --posix-prectable : POSIX. complex TNFA . naive TNFA complex . --stadfa . staDFA TDFA . staDFA TDFA . --fixed-tags : (all) (none) (toplevel). all . "" ( "") . . ( ). . . -W . -Werror . . -W warning. -Wno- warning. -Werror- warning ( -W ). -Wno-error- warning . . -Wcondition-order . --header conditions . -Wempty-character-class . : . re2js . --empty-class . -Wmatch-empty-string ( ) . . -Wswapped-range . . -Wundefined-control-flow ( ). . * . -Wunreachable-rules . -Wdeprecated-eof_rule $ . $ . -Wuseless-escape (escaped) . re2js . -Wnondeterministic-tags n- n . -Wsentinel-in-midrule --- . . re2c:sentinel . -Wundefined-syntax-config --syntax . : . . (Syntax files) re2c . -- . re2c re2c: : . ( include/syntax ) re2js . ( --lang none ). : . (Feature lists) (backend) re2js : supported_apis API simple record generic. supported_api_styles API functions free-form. supported_code_models goto-label loop-switch recursive-functions. supported_targets code dot skeleton. supported_features nested-ifs bitmaps computed-gotos case-ranges monadic unsafe tags captures captvars. (Language configurations) re2js : semicolons (semicolon) . backtick_quoted_strings (backtick) . single_quoted_strings . indentation_sensitive . wrap_blocks_in_braces . (Inplace configurations) re2c: . . (Code templates) . : code-template :: name '=' code-exprs ';' | CODE_TEMPLATE ';' | '' ';' code-exprs :: | code-exprs code-expr code-expr :: STRING | VARIABLE | optional | list optional :: '(' CONDITIONAL '?' code-exprs ')' | '(' CONDITIONAL '?' code-exprs ':' code-exprs ')' list :: '[' VARIABLE ':' code-exprs ']' | '[' VARIABLE '{' NUMBER '}' ':' code-exprs ']' | '[' VARIABLE '{' NUMBER ',' NUMBER '}' ':' code-exprs ']' . . : re2js . ( -1 ). . ( ) ( ) . re2js . if-then-else C : code:if_then_else = [branch{0}: topindent "if " cond " {" nl indent [stmt: stmt] dedent] [branch{1:-1}: topindent "} else" (.cond ? " if " cond) " {" nl indent [stmt: stmt] dedent] topindent "}" nl; branch : branch{0} ( else ) branch{1:-1} ( ) . stmt : [stmt: stmt] . topindent indent dedent nl .cond ( ). : if x { // do something } else if y { // do something else } else { // don't do anything } re2js . . . code:var_local . : type ( ) name ( ) init ( ). : .init ( ). code:var_global code:var_local (top-level) . code:const_local . : type ( ) name ( ) init ( ). code:const_global code:const_local (top-level) . code:array_local (). : type ( ) name ( ) size ( ) row ( ) elem ( -- row ). : .const ( ). code:array_global code:array_local (top-level) . code:array_elem (). : array ( ) index ( ). code:enum ( ). type ( ) elem ( ) init ( ). : .init ( ). code:enum_elem ( code:enum). name ( ) type ( ). code:assign . lhs ( ) rhs ( ). code:type_int (signed). code:type_uint (unsigned). code:type_yybm yybm. code:type_yytarget yytarget. code:type_yyctable yyctable. code:cmp_eq <<>> ("equals"). code:cmp_ne <<>> ("not equals"). code:cmp_lt << >> ("less than"). code:cmp_gt << >> ("greater than"). code:cmp_le << >> ("less or equal"). code:cmp_ge << >> ("greater or equal"). code:if_then_else If-then-else . : branch ( ) cond ( ) stmt ( ). : .cond ( ) .many ( ). code:if_then_else_oneline code:if_then_else . code:if_then_else . code:switch switch case. : expr ( switch) case ( case ). code:switch_cases case switch . case ( case ) stmt ( ). code:switch_cases_oneline code:switch_cases . code:switch_cases . code:switch_case_range case switch ( ). : val ( ). : .many ( ) .char_literals ( switch -- ). code:switch_case_default (default) switch. code:loop ( ). : label ( ) stmt ( ). code:continue continue. : label ( ). code:goto goto. : label ( ). code:cgoto goto (computed). : array ( goto ) index ( ) base ( .cgoto.relative ). code:cgoto:data goto . : label ( ) type ( ) base ( - .cgoto.relative ). code:fndecl . : name ( ) type ( ) throw ( re2c:yyfn:throw ) arg ( ) argname ( ) argtype ( ). : .type ( void ). code:fndef code:fndecl stmt . code:fncall . : name ( ) retval ( l-value ) arg ( ). : .args ( ) .retval ( ). code:tailcall (tail call). : name ( ) arg ( ). : .args ( ) .retval ( void ). code:recursive_functions --recursive-functions. : fn ( ) fndecl ( ) fndef ( ). code:fingerprint (fingerprint) . : ver ( re2js ) date ( ). code:line_info (line directives) ( ). : line ( ) file ( ). code:abort (abort) . code:yydebug YYDEBUG API . : YYDEBUG yyrecord yych ( re2c: ) state ( DFA)..TP code:yypeek YYPEEK API . : YYPEEK YYCTYPE YYINPUT YYCURSOR yyrecord yych ( re2c:). : .cast ( re2c:yych:conversion ). code:yyskip YYSKIP API . : YYSKIP YYCURSOR yyrecord ( re2c:). code:yybackup YYBACKUP API . : YYBACKUP YYCURSOR YYMARKER yyrecord ( re2c:). code:yybackupctx YYBACKUPCTX API . : YYBACKUPCTX YYCURSOR YYCTXMARKER yyrecord ( re2c:). code:yyskip_yypeek code:yyskip code:yypeek ( code:yyskip code:yypeek ). code:yypeek_yyskip code:yypeek code:yyskip ( code:yypeek code:yyskip ). code:yyskip_yybackup code:yyskip code:yybackup ( code:yyskip code:yybackup ). code:yybackup_yyskip code:yybackup code:yyskip ( code:yybackup code:yyskip ). code:yybackup_yypeek code:yybackup code:yypeek ( code:yybackup code:yypeek ). code:yyskip_yybackup_yypeek code:yyskip code:yybackup code:yypeek ( ``code:yyskip`` code:yybackup code:yypeek ). code:yybackup_yypeek_yyskip code:yybackup code:yypeek code:yyskip ( ``code:yybackup`` code:yypeek code:yyskip ). code:yyrestore YYRESTORE API . : YYRESTORE YYCURSOR YYMARKER yyrecord ( re2c:). code:yyrestorectx YYRESTORECTX API . : YYRESTORECTX YYCURSOR YYCTXMARKER yyrecord ( re2c:). code:yyrestoretag YYRESTORETAG API . : YYRESTORETAG YYCURSOR yyrecord ( re2c:) tag ( ). code:yyshift YYSHIFT API . : YYSHIFT YYCURSOR yyrecord ( re2c:) offset ( ). code:yyshiftstag YYSHIFTSTAG API . : YYSHIFTSTAG yyrecord negative ( re2c:) tag ( ) offset ( ). : .nested ( -- re2c:tags:negative ). code:yyshiftmtag YYSHIFTMTAG API . : YYSHIFTMTAG ( re2c:) tag ( ) offset ( ). code:yystagp YYSTAGP API . : YYSTAGP YYCURSOR yyrecord ( re2c:) tag ( ). code:yymtagp YYMTAGP API . : YYMTAGP ( re2c:) tag ( ). code:yystagn YYSTAGN API . : YYSTAGN negative yyrecord ( re2c:) tag ( ). code:yymtagn YYMTAGN API . : YYMTAGN ( re2c:) tag ( ). code:yycopystag YYCOPYSTAG API . : YYCOPYSTAG yyrecord ( re2c:) lhs rhs ( ). code:yycopymtag YYCOPYMTAG API . : YYCOPYMTAG yyrecord ( re2c:) lhs rhs ( ). code:yygetaccept YYGETACCEPT API . : YYGETACCEPT yyrecord ( re2c:) var ( re2c:yyaccept). code:yysetaccept YYSETACCEPT API . : YYSETACCEPT yyrecord ( re2c:) var ( re2c:yyaccept) val ( ). code:yygetcond YYGETCOND API . : YYGETCOND yyrecord ( re2c:) var ( re2c:yycond). code:yysetcond YYSETCOND API . : YYSETCOND yyrecord ( re2c:) var ( re2c:yycond) val ( ). code:yygetstate YYGETSTATE API . : YYGETSTATE yyrecord ( re2c:) var ( re2c:yystate). code:yysetstate YYSETSTATE API . : YYSETSTATE yyrecord ( re2c:) var ( re2c:yystate) val ( ). code:yylessthan YYLESSTHAN API . : YYLESSTHAN YYCURSOR YYLIMIT yyrecord ( re2c:) need ( ). : .many ( need ). code:yyend YYEND API . : YYEND YYCURSOR YYLIMIT. code:yybm_filter yych yybm ( --bitmaps ). : yych ( re2c:yych). code:yybm_match yybm ( --bitmaps). : yybm yych ( re2c:) offset ( yybm yych ) mask ( ). code:yytarget_filter yych yytarget ( --computed-gotos ). : yych ( re2c:yych). (syntax files) : nl . indent ..TP dedent . topindent . . : .api.simple (True) API (--api simple re2c:api = simple). .api.generic API (--api generic re2c:api = generic). .api.record API (--api record re2c:api = record). .api_style.functions API (re2c:api-style = functions). .api_style.freeform API (re2c:api-style = free-form). .case_ranges case (--case-ranges re2c:case-ranges = 1). .cgoto.relative goto (--computed-gotos-relative re2c:cgoto:relative = 1). .code_model.goto_label goto/label (--goto-label). .code_model.loop_switch loop/switch (--loop-switch). .code_model.recursive_functions (--recursive-function). .date (fingerprint) . .loop_label re2js (re2c:label:yyloop ). .monadic (monadic) (re2c:monadic = 1). . .start_conditions (--start-conditions). .storable_state (--storable-state). .unsafe re2js "unsafe" (--unsafe re2c:unsafe = 1). "unsafe" . .version re2js . .yyfill.enable YYFILL (re2c:yyfill:enable = 1). .yyfn.throw re2c:yyfn:throw . (HANDLING THE END OF INPUT) (lexer) . : o ( *) o o "" : . : . . re2js . . : o Sentinel ( ). . "" . . : . . YYFILL re2c:yyfill:enable = 0; re2c:eof -1 . o Sentinel (Sentinel with bounds checks). (generic) : . . "" "" . ( ). (bounds check) . . YYFILL ( ). . . re2c:eof ( ). YYFILL . o (Bounds checks with padding). "Sentinel " . DFA (SCC) SCC SCC . (lexemes) . (padding) ( ) . YYMAXFILL max . YYFILL . YYFILL re2c:eof -1 ( ). o (Custom checks). (Generic API) . . Generic API --api custom re2c:api = custom; re2c:yyfill:enable = 0; re2c:yyfill:check = 0; . ..SS (Sentinel) (sentinel) . null . null : (lexeme) ( ). null * ( -Wsentinel-in-midrule re2c:sentinel ). re2c:yyfill:enable = 0; YYFILL . // re2js $INPUT -o $OUTPUT // expects a null-terminated string function lex(yyinput) { let yycursor = 0; let count = 0 loop: while (true) { /*!re2c re2c:yyfill:enable = 0; * { return -1 } [\x00] { return count } [ ]+ { continue loop } [a-z]+ { count += 1; continue loop } */ } } function test(s, n) { if (lex(s) != n) throw "error!"; } test("\0", 0) test("one two three\0", 3) test("f0ur\0", -1) (Sentinel with bounds checks) ( 1.2 ). . null re2c:eof = 0; . sentinel null ( 'aaa\0aa'\0 'aaa\0 ). null . YYLIMIT <= YYCURSOR API YYLESSTHAN(1) . (YYFILL re2c:yyfill:enable = 0; YYFILL YYFILL with sentinel ). : $ ( *) -Wundefined-control-flow . // re2js $INPUT -o $OUTPUT // expects a null-terminated string function lex(yyinput) { let yycursor = 0; let yylimit = yyinput.length - 1 // terminating null not included let count = 0 loop: while (true) { /*!re2c re2c:yyfill:enable = 0; re2c:eof = 0; str = ['] ([^'\\] | [\\][^])* [']; * { return -1 } $ { return count } [ ]+ { continue loop } str { count += 1; continue loop } */ } } function test(s, n) { if (lex(s) != n) throw "error!"; } test("\0", 0) test("'qu\0tes' 'are' 'fine: \\'' \0", 3) test("'unterminated\\'\0", -1) (Bounds checks with padding) (padding) ( ). . YYMAXFILL null YYMAXFILL max . null --- ( ). "stop" (null) ( null ). . (YYLIMIT - YYCURSOR) < n API YYLESSTHAN(n) n ( n ). YYFILL(n) n . YYFILL ( ). YYFILL YYFILL with padding . // re2js $INPUT -o $OUTPUT /*!max:re2c*/ function lex(yyinput) { let yycursor = 0; let yylimit = yyinput.length let count = 0 loop: while (true) { /*!re2c re2c:YYFILL = "return -1"; str = ['] ([^'\\] | [\\][^])* [']; [\x00] { // check that it is the sentinel, not some unexpected null return (yycursor == yylimit - YYMAXFILL + 1) ? count : -1 } str { count += 1; continue loop } [ ]+ { continue loop } * { return -1 } */ } } function test(s, n) { let padded_s = s + "\0".repeat(YYMAXFILL) if (lex(padded_s) != n) throw "error!" } test("", 0) test("'unterminated\\'", -1) test("'qu\0tes' 'are' 'fine: \\'' ", 3) test("'unexpected \0 null", -1) generic API . . sentinel (null-terminated ). sentinel YYPEEK . . YYPEEK sentinel . // re2js $INPUT -o $OUTPUT // expects a string without terminating null function lex(str) { let cur = 0; let lim = str.length let count = 0 loop: while (true) { /*!re2c re2c:api = generic; re2c:YYPEEK = "cur < lim ? str.charCodeAt(cur) : 0"; re2c:YYSKIP = "cur += 1"; re2c:yyfill:enable = 0; * { return -1 } [\x00] { return count } [ ]+ { continue loop } [a-z]+ { count += 1; continue loop } */ } } function test(s, n) { if (lex(s) != n) throw "error!"; } test("", 0) test("one two three", 3) test("f0ur", -1) (BUFFER REFILLING) : ( ) . (chunks) . . (lexer) : o cursor: (YYCURSOR C pointer API YYSKIP/YYPEEK generic API) o limit: (YYLIMIT C pointer API YYLESSTHAN generic API ) o marker: (YYMARKER default API YYBACKUP/YYRESTORE generic API) o token: (lexeme) ( re2js API ) o context marker: (YYCTXMARKER C pointer API YYBACKUPCTX/YYRESTORECTX generic API) o (tag variables): ( stags mtags generic API YYSTAGP/YYSTAGN/YYMTAGP/YYMTAGN) YYFILL . token cursor token token limit . YYFILL ( ). YYFILL EOF : EOF (padding) . -f --storable-state YYFILL ( ). YYFILL (YYFILL with sentinel) EOF YYFILL . YYFILL YYLIMIT <= YYCURSOR C pointer API YYLESSTHAN() generic API . YYFILL . YYFILL . limit limit (sentinel) re2c:eof . YYFILL ( sentinel # ). <-- shift --> >-A------------B---------C-------------D#-----------E-> buffer token marker limit, cursor >-A------------B---------C-------------D------------E#-> buffer, marker cursor limit token <-- shift --> >-A------------B---------C-------------D#--E (EOF) buffer token marker limit, cursor >-A------------B---------C-------------D---E#........ buffer, marker cursor limit token input.txt EOF . // re2js $INPUT -o $OUTPUT const fs = require('fs') const BUFSIZE = 4096 const OK = 0 const EOF = 1 const LONG_LEXEME = 2 function fill(st) { if (st.eof) return EOF // Error: lexeme too long. In real life could reallocate a larger buffer. if (st.token < 1) return LONG_LEXEME // Shift buffer contents (discard everything up to the current token). st.yyinput.copy(st.yyinput, 0, st.token, st.yylimit) st.yycursor -= st.token; st.yymarker -= st.token; st.yylimit -= st.token; st.token = 0; // Read a new chunk of data from file and append it to `yyinput`. let want = BUFSIZE - st.yylimit - 1 // -1 for sentinel let nread = fs.readSync(st.file, st.yyinput, st.yylimit, want) st.eof = nread < want // end of file? st.yylimit += nread st.yyinput.writeUInt8(0, st.yylimit) // sentinel return OK } function lex(yyrecord, count) { loop: while (true) { yyrecord.token = yyrecord.yycursor /*!re2c re2c:api = record; re2c:YYPEEK = "readUInt8"; re2c:YYFILL = "fill(yyrecord) == OK"; re2c:eof = 0; str = ['] ([^'\\] | [\\][^])* [']; * { return -1 } $ { return count } [ ]+ { continue loop } str { count += 1; continue loop } */ } } function main() { let fname = "input" // Create input file. let content = "'qu\0tes' 'are' 'fine: \\'' ".repeat(BUFSIZE) fs.writeFileSync(fname, content, function(err) { if (err) throw err; }) // Init lexer state. let limit = BUFSIZE - 1 // exclude terminating null let st = { file: fs.openSync(fname, 'r'), yyinput: Buffer.alloc(BUFSIZE), yylimit: limit, yycursor: limit, yymarker: limit, token: limit, eof: false } // Run lexer on the prepared file. if (lex(st, 0) != 3 * BUFSIZE) { throw "error :[" } // Cleanup. fs.unlink(fname, function(err){ if (err) throw err; }) } main() ( EOF ) YYFILL . YYFILL (YYLIMIT - YYCURSOR) < n C pointer API YYLESSTHAN(n) generic API . YYFILL . YYFILL (lexer) ( ). YYFILL limit YYMAXFILL ( YYFILL n ). YYFILL ( YYMAXFILL # ). <-- shift --> <-- need --> >-A------------B---------C-----D-------E---F--------G-> buffer token marker cursor limit >-A------------B---------C-----D-------E---F--------G-> buffer, marker cursor limit token <-- shift --> <-- need --> >-A------------B---------C-----D-------E-F (EOF) buffer token marker cursor limit >-A------------B---------C-----D-------E-F############### buffer, marker cursor limit token <- YYMAXFILL -> input.txt 4096 (bounds-checking) . // re2js $INPUT -o $OUTPUT const fs = require('fs') const BUFSIZE = 4096 const OK = 0 const EOF = 1 const LONG_LEXEME = 2 /*!max:re2c*/ function fill(st, need) { if (st.eof) return EOF // Error: lexeme too long. In real life could reallocate a larger buffer. if (st.token < need) return LONG_LEXEME // Shift buffer contents (discard everything up to the current token). st.yyinput.copy(st.yyinput, 0, st.token, st.yylimit) st.yycursor -= st.token; st.yylimit -= st.token; st.token = 0; // Read a new chunk of data from file and append it to `yyinput`. let want = BUFSIZE - st.yylimit - 1 // -1 for sentinel let nread = fs.readSync(st.file, st.yyinput, st.yylimit, want) st.yylimit += nread if (nread < want) { st.eof = true // end of file st.yyinput.write("\0".repeat(YYMAXFILL), st.yylimit) st.yylimit += YYMAXFILL } return OK } function lex(yyrecord, count) { loop: while (true) { yyrecord.token = yyrecord.yycursor /*!re2c re2c:api = record; re2c:YYPEEK = "readUInt8"; re2c:YYFILL = "if (fill(yyrecord, @@) != OK) return -1;"; str = ['] ([^'\\] | [\\][^])* [']; [\x00] { // Check that it is the sentinel, not some unexpected null. return yyrecord.token == yyrecord.yylimit - YYMAXFILL ? count : -1 } str { count += 1; continue loop } [ ]+ { continue loop } * { return -1 } */ } } function main() { let fname = "input" // Create input file. let content = "'qu\0tes' 'are' 'fine: \\'' ".repeat(BUFSIZE) fs.writeFileSync(fname, content, function(err) { if (err) throw err; }) // Init lexer state. let limit = BUFSIZE - 1 // exclude terminating null let st = { file: fs.openSync(fname, 'r'), yyinput: Buffer.alloc(BUFSIZE), yylimit: limit, yycursor: limit, token: limit, eof: false } // Run lexer on the prepared file. if (lex(st, 0) != 3 * BUFSIZE) { throw "error :[" } // Cleanup. fs.unlink(fname, function(err){ if (err) throw err; }) } main() (Multiple blocks) (lexer) ( ). re2js . start conditions . . goto ( C/C++ Go) (label) . goto . goto ( Rust) switch /switch yystate re2js . (binary) (octal) (decimal) (hexadecimal) . . . . // re2js $INPUT -o $OUTPUT /*!re2c // Common re2c definitions shared between all functions. re2c:api = record; re2c:yyrecord = st; re2c:yyfill:enable = 0; */ function parse_u32(str) { let st = { yyinput: str, yycursor: 0, yymarker: 0 } /*!re2c '0b' / [01] { return parse_bin(st) } "0" { return parse_oct(st) } "" / [1-9] { return parse_dec(st) } '0x' / [0-9a-fA-F] { return parse_hex(st) } * { return null } */ } function parse_bin(st) { n = 0 loop: while (true) { /*!re2c [01] { n = n * 2 + (st.yyinput.charCodeAt(st.yycursor - 1) - 48); continue loop } * { return n } */ } } function parse_oct(st) { n = 0 loop: while (true) { /*!re2c [0-7] { n = n * 8 + (st.yyinput.charCodeAt(st.yycursor - 1) - 48); continue loop } * { return n } */ } } function parse_dec(st) { n = 0 loop: while (true) { /*!re2c [0-9] { n = n * 10 + (st.yyinput.charCodeAt(st.yycursor - 1) - 48); continue loop } * { return n } */ } } function parse_hex(st) { n = 0 loop: while (true) { /*!re2c [0-9] { n = n * 16 + (st.yyinput.charCodeAt(st.yycursor - 1) - 48); continue loop } [a-f] { n = n * 16 + (st.yyinput.charCodeAt(st.yycursor - 1) - 87); continue loop } [A-F] { n = n * 16 + (st.yyinput.charCodeAt(st.yycursor - 1) - 55); continue loop } * { return n } */ } } function test(s, n) { if (parse_u32(s) != n) throw "error!" } test("\0", null) test("1234567890\0", 1234567890) test("0b1101\0", 13) test("0x7Fe\0", 2046) test("0644\0", 420) test("9999999999\0", 9999999999) (Start conditions) --start-conditions . (automata) re2js . re2js . : YYGETCOND YYSETCOND . conditions --header re2c:header . re2c:cond:enumprefix . <*> . : < condition-list > regular-expression code condition-list . regular-expression code . < condition-list > regular-expression => condition code condition-list . regular-expression condition code . < condition-list > regular-expression :=> condition condition-list . regular-expression condition ( ). < condition-list > !action code code action condition-list ( actions ). code code condition-list . !pre_rule ( ). < > code "0" code . !entry ( ). < > => condition code condition . < > :=> condition condition . re2js re2js goto/label loop/switch . goto ( C/C++ Go) yyc_ cond ( re2c:cond:prefix ). goto . re2js switch YYGETSTATE . :=> switch ( re2c:cond:goto ). . goto ( Rust) re2js yystate . switch switch DFA . switch . ( YYGETCOND/YYSETCOND ). . . cond conditions . // re2js $INPUT -o $OUTPUT -c /*!conditions:re2c*/ function parse_u32(yyinput) { let yycursor = 0 let yycond = YYC_INIT let n = 0 loop: while (true) { /*!re2c re2c:yyfill:enable = 0; re2c:indent:top = 2; '0b' / [01] :=> BIN "0" :=> OCT "" / [1-9] :=> DEC '0x' / [0-9a-fA-F] :=> HEX * { return null } [01] { n = n * 2 + (yyinput.charCodeAt(yycursor - 1) - 48); continue loop } [0-7] { n = n * 8 + (yyinput.charCodeAt(yycursor - 1) - 48); continue loop } [0-9] { n = n * 10 + (yyinput.charCodeAt(yycursor - 1) - 48); continue loop } [0-9] { n = n * 16 + (yyinput.charCodeAt(yycursor - 1) - 48); continue loop } [a-f] { n = n * 16 + (yyinput.charCodeAt(yycursor - 1) - 87); continue loop } [A-F] { n = n * 16 + (yyinput.charCodeAt(yycursor - 1) - 55); continue loop } * { return n } */ } } function test(s, n) { if (parse_u32(s) != n) throw "error!" } test("\0", null) test("1234567890\0", 1234567890) test("0b1101\0", 13) test("0x7Fe\0", 2046) test("0644\0", 420) test("9999999999\0", 9999999999) --storable-state re2js . re2js "pull" <<>> ( ). ( (parser) ). : "push" . . . "pull" : o YYSETSTATE() YYGETSTATE(state) . o yych yyaccept ( ) state . state -1 . o YYFILL . . o . o getstate YYGETSTATE . goto ( --loop-switch). o re2c:eof sentinel with bounds checks . (padding) : (greedy lexeme) . ( ). "push" . . <<>> . . // re2js $INPUT -o $OUTPUT -f const fs = require('fs') // Use a small buffer to cover the case when a lexeme doesn't fit. // In real world use a larger buffer. const BUFSIZE = 10 const DEBUG = false const END = 0 const READY = 1 const WAITING = 2 const BIG_PACKET = 3 const BAD_PACKET = 4 function log() { if (DEBUG) console.log.apply(console, arguments) } function fill(st) { // Error: lexeme too long. In real life could reallocate a larger buffer. if (st.token < 1) return BIG_PACKET // Shift buffer contents (discard everything up to the current token). st.yyinput.copy(st.yyinput, 0, st.token, st.yylimit) st.yycursor -= st.token; st.yymarker -= st.token; st.yylimit -= st.token; st.token = 0; // Read a new chunk of data from file and append it to `yyinput`. let want = BUFSIZE - st.yylimit - 1 // -1 for sentinel let nread = fs.readSync(st.file, st.yyinput, st.yylimit, want) st.yylimit += nread st.yyinput.writeUInt8(0, st.yylimit) // sentinel return READY } function lex(yyrecord) { loop: while (true) { yyrecord.token = yyrecord.yycursor /*!re2c re2c:api = record; re2c:YYPEEK = "readUInt8"; re2c:YYFILL = "return WAITING"; re2c:eof = 0; packet = [a-z]+[;]; * { return BAD_PACKET } $ { return END } packet { yyrecord.received += 1; continue loop } */ } } function test(packets, expect) { // Emulate a "pipe" by opening the same file for reading and writing. let fname = "input" let fw = fs.openSync(fname, 'w'); let fr = fs.openSync(fname, 'r'); // Init lexer state. let limit = BUFSIZE - 1 // exclude terminating null let st = { file: fr, yyinput: Buffer.alloc(BUFSIZE), yylimit: limit, yycursor: limit, yymarker: limit, token: limit, yystate: -1, received: 0 } // Main loop. The buffer contains incomplete data which appears packet by // packet. When the lexer needs more input it saves its internal state and // returns to the caller which should provide more input and resume lexing. let send = 0 let status loop: while (true) { status = lex(st) if (status == END) { log("done: got", st.received, "packets") break loop } else if (status == WAITING) { log("waiting..."); if (send < packets.length) { log("sent packet", send, packets[send]) fs.writeFileSync(fw, packets[send]) send += 1 } status = fill(st) log("queue:", st.yyinput.toString()) if (status == BIG_PACKET) { log("error: packet too big") break loop } if (status != READY) throw "expected READY" } else { if (status != BAD_PACKET) throw "expected BAD_PACKET" log("error: ill-formed packet") break loop } } // Check results. if (status != expect) throw "unexpected status" if (status == END && st.received != send) "unexpected packet count" // Cleanup. fs.unlinkSync(fname, function(err){ if (err) throw err; }) } function main() { test([], END) test(["zero;", "one;", "two;", "three;", "four;"], END) test(["zer0;"], BAD_PACKET) test(["goooooooooogle;"], BIG_PACKET) } main() /*!rules:re2c[:] ... */ %{rules[:] ... %} re2js . . rules use . rules . use /*!use:re2c[:] ... */ %{use[:] ... %} . : rules ( ). use . use : rules ( ). !use:; re2js . . : . * $ ( ) . use re2js ( ). use 2.2 re2js . ( ). 2.2 -r --reusable . 1.2 . !use // re2js $INPUT -o $OUTPUT // This example shows how to combine reusable re2c blocks: two blocks // ('colors' and 'fish') are merged into one. The 'salmon' rule occurs // in both blocks; the 'fish' block takes priority because it is used // earlier. Default rule * occurs in all three blocks; the local (not // inherited) definition takes priority. const COLOR = 1 const FISH = 2 const DUNNO = 3 /*!rules:re2c:colors * { throw "ah" } "red" | "salmon" | "magenta" { return COLOR } */ /*!rules:re2c:fish * { throw "oh" } "haddock" | "salmon" | "eel" { return FISH } */ function lex(yyinput) { let yycursor = 0 /*!re2c re2c:yyfill:enable = 0; !use:fish; !use:colors; * { return DUNNO } // overrides inherited '*' rules */ } function test(s, n) { if (lex(s) != n) throw "error!"; } test("salmon", FISH) test("what?", DUNNO) /*!use:re2c ... */ // re2js $INPUT -o $OUTPUT --input-encoding utf8 // This example supports multiple input encodings: UTF-8 and UTF-32. // Both lexers are generated from the same rules block, and the use // blocks add only encoding-specific configurations. /*!rules:re2c re2c:yyfill:enable = 0; re2c:YYPEEK = "at"; "x y" { return yycursor } * { return null } */ function lex_utf8(yyinput) { let yycursor = 0 /*!use:re2c re2c:encoding:utf8 = 1; */ } function lex_utf32(yyinput) { let yycursor = 0 /*!use:re2c re2c:encoding:utf32 = 1; */ } function test(f, s) { if (f(s) != s.length) throw "error!" } test(lex_utf8, [0xe2, 0x88, 0x80, 0x78, 0x20, 0xe2, 0x88, 0x83, 0x79]) test(lex_utf32, [0x2200, 0x78, 0x20, 0x2203, 0x79]) re2js . Tags tag @stag #mtag stag mtag . -T --tags re2c:tags = 1 . : ( ) . S-tag m-tag ( ). svars mvars . (leftmost greedy) . Captures (capturing groups) . --captures re2c:captures = 1 . --leftmost-captures () --posix-captures POSIX . : (! ... ). --invert-captures re2c:invert-captures = 1 . yynmatch ( ) yypmatch . yynmatch yypmatch yypmatch [yynmatch * 2] . maxnmatch YYMAXNMATCH yynmatch . Captvars --captvars re2c:captvars = 1 . --captures : yynmatch yypmatch re2js yytl yytr k- ( svars ). : --leftmost-captvars re2c:leftmost-captvars = 1 () --posix-captvars re2c:posix-captvars POSIX. Tagged Deterministic Finite Automata with Lookahead ( TDFA) . TDFA (overhead) . TDFA DFA . . TDFA : . . stags mtags . (lexer state) . YYFILL . S-tag : o s-tag: t = YYCURSOR API C YYSTAGP(t) API o s-tag: t = NULL API C YYSTAGN(t) API o s-tag : t1 = t2 M-tag : o m-tag: YYMTAGP(t) API o m-tag: YYMTAGN(t) API o m-tag : t1 = t2 S-tag ( ) . M-tag . m-tag ( ) m-tag (prefix-tree) (v, p) v p . s-tag (semantic versions) : major minor patch ( ). YYFILL . // re2js $INPUT -o $OUTPUT const assert = require('assert'); function parse(yyinput) { let yycursor = 0 // Final tag variables available in semantic action. /*!svars:re2c format = "let @@\n"; */ // Intermediate tag variables used by the lexer (must be autogenerated). /*!stags:re2c format = "let @@\n"; */ /*!re2c re2c:yyfill:enable = 0; re2c:tags = 1; num = [0-9]+; @t1 num @t2 "." @t3 num @t4 ("." @t5 num)? [\x00] { return { major: Number(yyinput.substring(t1, t2)), minor: Number(yyinput.substring(t3, t4)), patch: t5 == -1 ? 0 : Number(yyinput.substring(t5, yycursor - 1)) } } * { return null } */ } assert.deepEqual(parse("23.34\0"), {major: 23, minor: 34, patch: 0}) assert.deepEqual(parse("1.2.99999\0"), {major: 1, minor: 2, patch: 99999}) assert.deepEqual(parse("1.a\0"), null) s-tag YYFILL . YYFILL . s-tag . ( m-tag ) . // re2js $INPUT -o $OUTPUT const assert = require('assert'); const fs = require('fs') const BUFSIZE = 4096 const OK = 0 const EOF = 1 const LONG_LEXEME = 2 function fill(st) { if (st.eof) return EOF // Error: lexeme too long. In real life could reallocate a larger buffer. if (st.token < 1) return LONG_LEXEME // Shift buffer contents (discard everything up to the current token). st.yyinput.copy(st.yyinput, 0, st.token, st.yylimit) st.yycursor -= st.token; st.yymarker -= st.token; st.yylimit -= st.token; /*!stags:re2c format = "if (st.@@ != -1) st.@@ -= st.token\n"; */ st.token = 0; // Read a new chunk of data from file and append it to `yyinput`. let want = BUFSIZE - st.yylimit - 1 // -1 for sentinel let nread = fs.readSync(st.file, st.yyinput, st.yylimit, want) st.eof = nread < want // end of file? st.yylimit += nread st.yyinput.writeUInt8(0, st.yylimit) // sentinel return OK } function lex(st) { let vers = [] loop: while (true) { st.token = st.yycursor // Final tag variables available in semantic action. /*!svars:re2c format = "let @@\n"; */ /*!re2c re2c:api = record; re2c:yyrecord = st; re2c:YYPEEK = "readUInt8"; re2c:YYFILL = "fill(st) == OK"; re2c:eof = 0; re2c:tags = 1; num = [0-9]+; num @t1 "." @t2 num @t3 ("." @t4 num)? [\n] { vers.push({ major: Number(st.yyinput.subarray(st.token, t1)), minor: Number(st.yyinput.subarray(t2, t3)), patch: t4 == -1 ? 0 : Number(st.yyinput.subarray(t4, st.yycursor - 1)) }) continue loop } $ { return vers } * { return null } */ } } function main() { let fname = "input" // Create input file. let content = "1.22.333\n".repeat(BUFSIZE) fs.writeFileSync(fname, content, function(err) { if (err) throw err; }) // Init lexer state. let limit = BUFSIZE - 1 // exclude terminating null let st = { file: fs.openSync(fname, 'r'), yyinput: Buffer.alloc(BUFSIZE), yylimit: limit, yycursor: limit, yymarker: limit, token: limit, // Intermediate tag variables used by the lexer (must be autogenerated). /*!stags:re2c format = "@@: -1,\n"; */ eof: false } // Run lexer on the prepared file. assert.deepEqual(lex(st), Array(BUFSIZE).fill({major: 1, minor: 22, patch: 333})) // Cleanup. fs.unlink(fname, function(err){ if (err) throw err; }) } main() . // re2js $INPUT -o $OUTPUT const assert = require('assert'); function parse(yyinput) { let yycursor = 0 // Final tag variables available in semantic action. /*!svars:re2c format = "let @@\n"; */ // Intermediate tag variables used by the lexer (must be autogenerated). /*!stags:re2c format = "let @@\n"; */ /*!re2c re2c:yyfill:enable = 0; re2c:captvars = 1; num = [0-9]+; (num) "." (num) ("." num)? [\x00] { return { major: Number(yyinput.substring(yytl1, yytr1)), minor: Number(yyinput.substring(yytl2, yytr2)), patch: yytl3 == -1 ? 0 : Number(yyinput.substring(yytl3 + 1, yytr3)) } } * { return null } */ } assert.deepEqual(parse("23.34\0"), {major: 23, minor: 34, patch: 0}) assert.deepEqual(parse("1.2.99999\0"), {major: 1, minor: 2, patch: 99999}) assert.deepEqual(parse("1.a\0"), null) m-tag . (trie) . // re2js $INPUT -o $OUTPUT const assert = require('assert') function parse(yyinput) { let yycursor = 0 // Final tag variables available in semantic action. /*!svars:re2c format = "let @@\n"; */ /*!mvars:re2c format = "let @@\n"; */ // Intermediate tag variables used by the lexer (must be autogenerated). /*!stags:re2c format = "let @@\n"; */ /*!mtags:re2c format = "let @@ = []\n"; */ /*!re2c re2c:YYMTAGP = "@@.push(yycursor)"; re2c:YYMTAGN = ""; // do nothing re2c:yyfill:enable = 0; re2c:tags = 1; num = [0-9]+; @t1 num @t2 ("." #t3 num #t4)* [\x00] { let vers = [Number(yyinput.substring(t1, t2))] for (let i = 0; i < t3.length; ++i) { vers.push(Number(yyinput.substring(t3[i], t4[i]))) } return vers } * { return null } */ } assert.deepEqual(parse("1\0"), [1]) assert.deepEqual(parse("1.2.3.4.5.6.7\0"), [1, 2, 3, 4, 5, 6, 7]) assert.deepEqual(parse("1.2.\0"), null) code point code unit . code point . code unit . code point code unit . code point code unit . code point code unit . << >> ("any") [^] code point code unit ( code unit * ). code unit : yych code unit YYCTYPE code unit . code point . re2js code point code unit . : code point code unit . : o ASCII ( ). [0-255] code point code unit . o EBCDIC ( --ebcdic re2c:encoding:ebcdic). [0-255] code point code unit . o UCS2 ( --ucs2 re2c:encoding:ucs2). [0-0xFFFF] code point code unit . o UTF8 ( --utf8 re2c:encoding:utf8). . code unit . code point code unit . o UTF16 ( --utf16 re2c:encoding:utf16). . code unit . code point code unit . o UTF32 ( --utf32 re2c:encoding:utf32). [0-0x10FFFF] code point code unit . include/unicode_blocks.re include/unicode_categories.re include/unicode_properties.re re2js . --input-encoding (literal) . --input-encoding utf8 re2js UTF8 ( --utf8 ). --encoding-policy (code point [0xD800-0xDFFF]) re2js . UTF8 . // re2js $INPUT -o $OUTPUT --utf8 -s /*!include:re2c "unicode_categories.re" */ function lex(yyinput) { let yycursor = 0 /*!re2c re2c:yyfill:enable = 0; // Simplified "Unicode Identifier and Pattern Syntax" // (see https://unicode.org/reports/tr31) id_start = L | Nl | [$_]; id_continue = id_start | Mn | Mc | Nd | Pc | [\u200D\u05F3]; identifier = id_start id_continue*; identifier { return true } * { return false } */ } if (!lex("_\0")) throw "error!" (Include files) re2js /*!include:re2c FILE */ %{include FILE %} !include FILE ; FILE . re2js -I . / re2js #include C/C++ : FILE / . . --depfile . re2js include/ . ( ) re2js . . (definitions.js) const INT = 1 const FLOAT = 2 const NAN = 3 /*!re2c number = [1-9][0-9]*; */ // floating-point numbers frac = [0-9]* "." [0-9]+ | [0-9]+ "."; exp = 'e' [+-]? [0-9]+; float = frac exp? | [0-9]+ exp; float { return FLOAT } // re2js $INPUT -o $OUTPUT /*!include:re2c "definitions.js" */ function lex(yyinput) { let yycursor = 0 /*!re2c re2c:yyfill:enable = 0; * { return NAN } number { return INT } !include "extra_rules.re.inc"; */ } function test(s, n) { if (lex(s) != n) throw "error!" } test("123\0", INT) test("123.4567\0", FLOAT) re2js --header re2c:header /*!header:re2c:on*/ /*!header:re2c:off*/ %{header:on%} %{header:off%} .re . . re2js --header re2c:header ( stdout ). re2js (translation units) . (tag variables) ( ). // re2js $INPUT -o $OUTPUT --header lexer/state.js let state = require('./lexer/state.js'); /*!header:re2c:on*/ exports.mk_state = function(str) { return { yyinput: str, /*!stags:re2c format = "@@: 0,\n"; */ yycursor: 0 } } /*!header:re2c:off*/ function lex(yyrecord) { let t /*!re2c re2c:api = record; re2c:tags = 1; re2c:yyfill:enable = 0; re2c:header = "lexer/state.js"; [a]* @t [b]* { return t } */ } if (lex(state.mk_state("ab\0")) != 1) { throw "error!" } // Generated by re2c exports.mk_state = function(str) { return { yyinput: str, yyt1: 0, yycursor: 0 } } -S, --skeleton re2js re2js C . (lexer) . DFA ( ) re2js : .input DFA .keys . .input . : o re2js ( DFA ). o (benchmarking) . o ( ). ( ). re2js DFA . : DFA . ( ASCII UTF-8 EBCDIC) DFA . DFA : re2js DFA . . re2js ( ) . (re2js ). (Visualization and debug) -D, --emit-dot re2js DFA DOT (dump) . Graphviz DFA . DFA . --dump-nfa --dump-dfa-raw ( ). (SEE ALSO) re2c : http://re2c.org. flex(1) lex(1) quex(http://quex.sourceforge.net). (AUTHORS) re2js Peter Bumbulis (peter@csg.uwaterloo.ca) . Marcus Boerger Dan Nuffer . : Brian Young (bayoung@acm.org) Marcus Boerger Dan Nuffer (nuffer@users.sourceforge.net) Ulya Trofimovich (skvadrik@gmail.com) Serghei Iakovlev Sergei Trofimovich Petr Skocik ligfx raekye PolarGoose. RE2JS(1)