X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=lily%2Flexer.ll;h=708825279384502b81c47e8b56f092a820762692;hb=ff4a77f00d352158e487637b0a537281fd63db1a;hp=9cb2cac0c667baae3b1f24a893ab34acaaf3032b;hpb=4767df468545da224698ec3e807b7adf278aad57;p=lilypond.git diff --git a/lily/lexer.ll b/lily/lexer.ll index 9cb2cac0c6..7088252793 100644 --- a/lily/lexer.ll +++ b/lily/lexer.ll @@ -1,13 +1,23 @@ %{ // -*-Fundamental-*- /* - lexer.ll -- implement the Flex lexer + This file is part of LilyPond, the GNU music typesetter. - source file of the LilyPond music typesetter + Copyright (C) 1996--2011 Han-Wen Nienhuys + Jan Nieuwenhuizen - (c) 1996--2006 Han-Wen Nienhuys - Jan Nieuwenhuizen -*/ + LilyPond is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + LilyPond is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + You should have received a copy of the GNU General Public License + along with LilyPond. If not, see . +*/ /* backup rules @@ -36,17 +46,20 @@ using namespace std; #include "context-def.hh" +#include "duration.hh" #include "identifier-smob.hh" #include "international.hh" #include "interval.hh" #include "lily-guile.hh" #include "lily-lexer.hh" +#include "lily-parser.hh" #include "lilypond-version.hh" #include "main.hh" #include "music.hh" #include "music-function.hh" #include "parse-scm.hh" #include "parser.hh" +#include "pitch.hh" #include "source-file.hh" #include "std-string.hh" #include "string-convert.hh" @@ -62,6 +75,7 @@ void strip_trailing_white (string&); void strip_leading_white (string&); string lyric_fudge (string s); SCM lookup_markup_command (string s); +SCM lookup_markup_list_command (string s); bool is_valid_version (string s); @@ -74,10 +88,10 @@ bool is_valid_version (string s); yylval.string = new string #define yylval \ - (*(YYSTYPE*)lexval) + (*(YYSTYPE*)lexval_) #define yylloc \ - (*(YYLTYPE*)lexloc) + (*(YYLTYPE*)lexloc_) #define YY_USER_ACTION add_lexed_char (YYLeng ()); @@ -121,7 +135,6 @@ PUNCT [?!:'`] ACCENT \\[`'"^] NATIONAL [\001-\006\021-\027\031\036] TEX {AA}|-|{PUNCT}|{ACCENT}|{NATIONAL} -WORD {A}{AN}* DASHED_WORD {A}({AN}|-)* DASHED_KEY_WORD \\{DASHED_WORD} @@ -134,7 +147,6 @@ E_UNSIGNED \\{N}+ FRACTION {N}+\/{N}+ INT -?{UNSIGNED} REAL ({INT}\.{N}*)|(-?\.{N}+) -KEYWORD \\{WORD} WHITE [ \n\t\f\r] HORIZONTALWHITE [ \t] BLACK [^ \n\t\f\r] @@ -151,7 +163,7 @@ BOM_UTF8 \357\273\277 <*>\r { - // windows-suck-suck-suck + // swallow and ignore carriage returns } {ANY_CHAR} { @@ -170,27 +182,40 @@ BOM_UTF8 \357\273\277 return type; } -{BOM_UTF8} { - if (this->lexloc->line_number () != 1 || this->lexloc->column_number () != 0) +<> { + /* Generate a token without swallowing anything */ + + /* produce requested token */ + int type = extra_token_types_.back (); + extra_token_types_.pop_back (); + if (extra_token_types_.empty ()) + yy_pop_state (); + + return type; +} + + /* Use the trailing context feature. Otherwise, the BOM will not be + found if the file starts with an identifier definition. */ +{BOM_UTF8}/.* { + if (this->lexloc_->line_number () != 1 || this->lexloc_->column_number () != 0) { - LexerError (_ ("stray UTF-8 BOM encountered").c_str ()); - exit (1); + LexerWarning (_ ("stray UTF-8 BOM encountered").c_str ()); + // exit (1); } - if (be_verbose_global) - message (_ ("Skipping UTF-8 BOM")); + debug_output (_ ("Skipping UTF-8 BOM")); } { "%{" { yy_push_state (longcomment); } - %[^{\n\r].*[\n\r] { + %[^{\n\r][^\n\r]*[\n\r] { } %[^{\n\r] { // backup rule } %[\n\r] { } - %[^{\n\r].* { + %[^{\n\r][^\n\r]* { } {WHITE}+ { @@ -236,7 +261,7 @@ BOM_UTF8 \357\273\277 progress_indication ("\n"); scm_module_define (scm_car (scopes_), ly_symbol2scm ("input-file-name"), - scm_makfrom0str (s.c_str ())); + ly_string2scm (s)); } @@ -248,15 +273,15 @@ BOM_UTF8 \357\273\277 this->here_input ().get_source_file ()->set_line (here_input ().start (), i); } -. { +{ANY_CHAR} { LexerError (_ ("quoted string expected after \\version").c_str ()); yy_pop_state (); } -. { +{ANY_CHAR} { LexerError (_ ("quoted string expected after \\sourcefilename").c_str ()); yy_pop_state (); } -. { +{ANY_CHAR} { LexerError (_ ("integer expected after \\sourcefileline").c_str ()); yy_pop_state (); } @@ -269,12 +294,6 @@ BOM_UTF8 \357\273\277 "%"+"}" { yy_pop_state (); } - <> { - LexerError (_ ("EOF found inside a comment").c_str ()); - is_main_input_ = false; - if (! close_input ()) - yyterminate (); // can't move this, since it actually rets a YY_NULL - } } @@ -298,7 +317,7 @@ BOM_UTF8 \357\273\277 new_input (s, sources_); yy_pop_state (); } -\\{BLACK}*{WHITE} { /* got the include identifier */ +\\{BLACK}*{WHITE}? { /* got the include identifier */ string s = YYText () + 1; strip_trailing_white (s); if (s.length () && (s[s.length () - 1] == ';')) @@ -317,13 +336,13 @@ BOM_UTF8 \357\273\277 scm_display (sid, err); } } -\"[^"]* { // backup rule +\"[^"]* { // backup rule error (_ ("end quote missing")); exit (1); } {RESTNAME} { char const *s = YYText (); - yylval.scm = scm_makfrom0str (s); + yylval.scm = scm_from_locale_string (s); return RESTNAME; } R { @@ -334,7 +353,7 @@ BOM_UTF8 \357\273\277 Input hi = here_input(); hi.step_forward (); SCM sval = ly_parse_scm (hi.start (), &n, hi, - be_safe_global && is_main_input_); + be_safe_global && is_main_input_, parser_); if (sval == SCM_UNDEFINED) { @@ -353,6 +372,11 @@ BOM_UTF8 \357\273\277 yylval.scm = unpack_identifier(sval); return identifier_type (yylval.scm); } + + for (size_t i = 0; i < pending_string_includes_.size (); i++) + new_input ("", pending_string_includes_[i], + parser_->sources_); + pending_string_includes_.clear (); yylval.scm = sval; return SCM_TOKEN; @@ -399,11 +423,15 @@ BOM_UTF8 \357\273\277 yylval.scm = scan_fraction (YYText ()); return FRACTION; } - {DIGIT} { yylval.i = String_convert::dec2int (string (YYText ())); return DIGIT; } + {UNSIGNED}/\/[^0-9] { // backup rule + yylval.i = String_convert::dec2int (string (YYText ())); + return UNSIGNED; + } + {UNSIGNED}/\/ | // backup rule {UNSIGNED} { yylval.i = String_convert::dec2int (string (YYText ())); return UNSIGNED; @@ -418,7 +446,7 @@ BOM_UTF8 \357\273\277 \\{ESCAPED} { *yylval.string += to_string (escaped_char (YYText ()[1])); } - [^\\"]+ { + [^\\""]+ { *yylval.string += YYText (); } \" { @@ -427,7 +455,7 @@ BOM_UTF8 \357\273\277 /* yylval is union. Must remember STRING before setting SCM*/ string *sp = yylval.string; - yylval.scm = scm_makfrom0str (sp->c_str ()); + yylval.scm = ly_string2scm (*sp); delete sp; return is_lyric_state () ? LYRICS_STRING : STRING; } @@ -444,6 +472,11 @@ BOM_UTF8 \357\273\277 yylval.scm = scan_fraction (YYText ()); return FRACTION; } + {UNSIGNED}/\/[^0-9] { // backup rule + yylval.i = String_convert::dec2int (string (YYText ())); + return UNSIGNED; + } + {UNSIGNED}/\/ | // backup rule {UNSIGNED} { yylval.i = String_convert::dec2int (string (YYText ())); return UNSIGNED; @@ -464,7 +497,7 @@ BOM_UTF8 \357\273\277 if (c == '{' || c == '}') // brace open is for not confusing dumb tools. here_input ().warning ( _ ("Brace found at end of lyric. Did you forget a space?")); - yylval.scm = scm_makfrom0str (s.c_str ()); + yylval.scm = ly_string2scm (s); return LYRICS_STRING; @@ -484,6 +517,11 @@ BOM_UTF8 \357\273\277 yylval.scm = scan_fraction (YYText ()); return FRACTION; } + {UNSIGNED}/\/[^0-9] { // backup rule + yylval.i = String_convert::dec2int (string (YYText ())); + return UNSIGNED; + } + {UNSIGNED}/\/ | // backup rule {UNSIGNED} { yylval.i = String_convert::dec2int (string (YYText ())); return UNSIGNED; @@ -515,36 +553,53 @@ BOM_UTF8 \357\273\277 } {MARKUPCOMMAND} { string str (YYText () + 1); + + int token_type = MARKUP_FUNCTION; SCM s = lookup_markup_command (str); - if (scm_is_pair (s) && scm_is_symbol (scm_cdr (s)) ) { - yylval.scm = scm_car(s); - SCM tag = scm_cdr(s); - if (tag == ly_symbol2scm("markup0")) - return MARKUP_HEAD_MARKUP0; - if (tag == ly_symbol2scm("empty")) - return MARKUP_HEAD_EMPTY; - else if (tag == ly_symbol2scm ("markup0-markup1")) - return MARKUP_HEAD_MARKUP0_MARKUP1; - else if (tag == ly_symbol2scm ("markup-list0")) - return MARKUP_HEAD_LIST0; - else if (tag == ly_symbol2scm ("scheme0")) - return MARKUP_HEAD_SCM0; - else if (tag == ly_symbol2scm ("scheme0-scheme1")) - return MARKUP_HEAD_SCM0_SCM1; - else if (tag == ly_symbol2scm ("scheme0-markup1")) - return MARKUP_HEAD_SCM0_MARKUP1; - else if (tag == ly_symbol2scm ("scheme0-scheme1-markup2")) - return MARKUP_HEAD_SCM0_SCM1_MARKUP2; - else if (tag == ly_symbol2scm ("scheme0-scheme1-scheme2")) - return MARKUP_HEAD_SCM0_SCM1_SCM2; - else { - programming_error ("no parser tag defined for this markup signature"); - ly_display_scm (s); - assert(false); - } - } else - return scan_escaped_word (str); + // lookup-markup-command returns a pair with the car + // being the function to call, and the cdr being the + // call signature specified to define-markup-command, + // a list of predicates. + + if (!scm_is_pair (s)) { + // If lookup-markup-command was not successful, we + // try lookup-markup-list-command instead. + // If this fails as well, we just scan and return + // the escaped word. + s = lookup_markup_list_command (str); + if (scm_is_pair (s)) + token_type = MARKUP_LIST_FUNCTION; + else + return scan_escaped_word (str); + } + + // If the list of predicates is, say, + // (number? number? markup?), then tokens + // EXPECT_MARKUP EXPECT_SCM EXPECT_SCM EXPECT_NO_MORE_ARGS + // will be generated. Note that we have to push them + // in reverse order, so the first token pushed in the + // loop will be EXPECT_NO_MORE_ARGS. + + yylval.scm = scm_car(s); + + // yylval now contains the function to call as token + // value (for token type MARKUP_FUNCTION or + // MARKUP_LIST_FUNCTION). + + push_extra_token(EXPECT_NO_MORE_ARGS); + s = scm_cdr(s); + for (; scm_is_pair(s); s = scm_cdr(s)) { + SCM predicate = scm_car(s); + + if (predicate == ly_lily_module_constant ("markup-list?")) + push_extra_token(EXPECT_MARKUP_LIST); + else if (predicate == ly_lily_module_constant ("markup?")) + push_extra_token(EXPECT_MARKUP); + else + push_extra_token(EXPECT_SCM); + } + return token_type; } [{}] { return YYText ()[0]; @@ -557,7 +612,7 @@ BOM_UTF8 \357\273\277 if (c == '{' || c == '}') here_input ().warning ( _ ("Brace found at end of markup. Did you forget a space?")); - yylval.scm = scm_makfrom0str (s.c_str ()); + yylval.scm = ly_string2scm (s); return STRING; @@ -567,10 +622,20 @@ BOM_UTF8 \357\273\277 } } -<*><> { - if (is_main_input_) +<> { + LexerError (_ ("EOF found inside a comment").c_str ()); + is_main_input_ = false; // should be safe , can't have \include in --safe. + if (!close_input ()) + yyterminate (); // can't move this, since it actually rets a YY_NULL + } + +<> { if (is_main_input_) { - is_main_input_ = false; + /* 2 = init.ly + current file. + > because we're before closing, but is_main_input_ should + reflect after. + */ + is_main_input_ = include_stack_.size () > 2; if (!close_input ()) /* Returns YY_NULL */ yyterminate (); @@ -589,12 +654,7 @@ BOM_UTF8 \357\273\277 } } -{WORD} { - return scan_bare_word (YYText ()); -} -{KEYWORD} { - return scan_escaped_word (YYText () + 1); -} +-{UNSIGNED} | // backup rule {REAL} { Real r; int cnv = sscanf (YYText (), "%lf", &r); @@ -604,6 +664,10 @@ BOM_UTF8 \357\273\277 yylval.scm = scm_from_double (r); return REAL; } +-\. { // backup rule + yylval.scm = scm_from_double (0.0); + return REAL; +} {UNSIGNED} { yylval.i = String_convert::dec2int (string (YYText ())); @@ -677,6 +741,12 @@ Lily_lexer::push_extra_token (int token_type) extra_token_types_.push_back (token_type); } +void +Lily_lexer::push_embedded_token () +{ + push_extra_token (EMBEDDED_LILY); +} + void Lily_lexer::push_chord_state (SCM tab) { @@ -754,11 +824,17 @@ Lily_lexer::scan_escaped_word (string str) push_extra_token (EXPECT_NO_MORE_ARGS); for (; scm_is_pair (s); s = scm_cdr (s)) { - if (scm_car (s) == ly_music_p_proc) + SCM cs = scm_car (s); + + if (cs == ly_music_p_proc) push_extra_token (EXPECT_MUSIC); - else if (scm_car (s) == ly_lily_module_constant ("markup?")) + else if (cs == Pitch_type_p_proc) + push_extra_token (EXPECT_PITCH); + else if (cs == Duration_type_p_proc) + push_extra_token (EXPECT_DURATION); + else if (cs == ly_lily_module_constant ("markup?")) push_extra_token (EXPECT_MARKUP); - else if (ly_is_procedure (scm_car (s))) + else if (ly_is_procedure (cs)) push_extra_token (EXPECT_SCM); else programming_error ("Function parameter without type-checking predicate"); } @@ -774,7 +850,7 @@ Lily_lexer::scan_escaped_word (string str) string msg (_f ("unknown escaped string: `\\%s'", str)); LexerError (msg.c_str ()); - yylval.scm = scm_makfrom0str (str.c_str ()); + yylval.scm = ly_string2scm (str); return STRING; } @@ -795,14 +871,18 @@ Lily_lexer::scan_bare_word (string str) else if (scm_is_symbol (yylval.scm)) return DRUM_PITCH; } - else if ((handle = scm_hashq_get_handle (chordmodifier_tab_, sym))!= SCM_BOOL_F) + else if ((YYSTATE == chords) + && (handle = scm_hashq_get_handle (chordmodifier_tab_, sym))!= SCM_BOOL_F) { yylval.scm = scm_cdr (handle); return CHORD_MODIFIER; } + if ((chord_repetition_.repetition_symbol_ != SCM_EOL) + && to_boolean (scm_equal_p (chord_repetition_.repetition_symbol_, sym))) + return CHORD_REPETITION; } - yylval.scm = scm_makfrom0str (str.c_str ()); + yylval.scm = ly_string2scm (str); return STRING; } @@ -937,7 +1017,14 @@ SCM lookup_markup_command (string s) { SCM proc = ly_lily_module_constant ("lookup-markup-command"); - return scm_call_1 (proc, scm_makfrom0str (s.c_str ())); + return scm_call_1 (proc, ly_string2scm (s)); +} + +SCM +lookup_markup_list_command (string s) +{ + SCM proc = ly_lily_module_constant ("lookup-markup-list-command"); + return scm_call_1 (proc, ly_string2scm (s)); } /* Shut up lexer warnings. */