X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/1221b78adb3f243e9afb8096f95218e2b03a4854..1b818f33ad29193a8ccd1deb2bfec3f6d406d41a:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index 1081f536..f45b323c 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -1,6 +1,6 @@ %{/* Bison Grammar Parser -*- C -*- - Copyright (C) 2002, 2003, 2004, 2005 Free Software Foundation, Inc. + Copyright (C) 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc. This file is part of Bison, the GNU Compiler Compiler. @@ -29,17 +29,18 @@ #include "getargs.h" #include "gram.h" #include "muscle_tab.h" -#include "output.h" #include "quotearg.h" #include "reader.h" #include "symlist.h" +#include "scan-gram.h" +#include "scan-code.h" #include "strverscmp.h" #define YYLLOC_DEFAULT(Current, Rhs, N) (Current) = lloc_default (Rhs, N) static YYLTYPE lloc_default (YYLTYPE const *, int); #define YY_LOCATION_PRINT(File, Loc) \ - location_print (File, Loc) + location_print (File, Loc) static void version_check (location const *loc, char const *version); @@ -47,9 +48,11 @@ static void version_check (location const *loc, char const *version); FIXME: depends on the undocumented availability of YYLLOC. */ #undef yyerror #define yyerror(Msg) \ - gram_error (&yylloc, Msg) + gram_error (&yylloc, Msg) static void gram_error (location const *, char const *); +static char const *char_name (char); + static void add_param (char const *, char *, location); static symbol_class current_class = unknown_sym; @@ -57,6 +60,19 @@ static uniqstr current_type = 0; static symbol *current_lhs; static location current_lhs_location; static int current_prec = 0; + +#ifdef UINT_FAST8_MAX +# define YYTYPE_UINT8 uint_fast8_t +#endif +#ifdef INT_FAST8_MAX +# define YYTYPE_INT8 int_fast8_t +#endif +#ifdef UINT_FAST16_MAX +# define YYTYPE_UINT16 uint_fast16_t +#endif +#ifdef INT_FAST16_MAX +# define YYTYPE_INT16 int_fast16_t +#endif %} %debug @@ -72,9 +88,8 @@ static int current_prec = 0; { /* Bison's grammar can initial empty locations, hence a default location is needed. */ - @$.start.file = @$.end.file = current_file; - @$.start.line = @$.end.line = 1; - @$.start.column = @$.end.column = 0; + boundary_set (&@$.start, current_file, 1, 0); + boundary_set (&@$.end, current_file, 1, 0); } /* Only NUMBERS have a value. */ @@ -86,6 +101,7 @@ static int current_prec = 0; char *chars; assoc assoc; uniqstr uniqstr; + unsigned char character; }; /* Define the tokens together with their human representation. */ @@ -97,10 +113,8 @@ static int current_prec = 0; %token PERCENT_NTERM "%nterm" %token PERCENT_TYPE "%type" -%token PERCENT_DESTRUCTOR "%destructor {...}" -%token PERCENT_PRINTER "%printer {...}" - -%token PERCENT_UNION "%union {...}" +%token PERCENT_DESTRUCTOR "%destructor" +%token PERCENT_PRINTER "%printer" %token PERCENT_LEFT "%left" %token PERCENT_RIGHT "%right" @@ -125,18 +139,18 @@ static int current_prec = 0; PERCENT_EXPECT_RR "%expect-rr" PERCENT_FILE_PREFIX "%file-prefix" PERCENT_GLR_PARSER "%glr-parser" - PERCENT_INITIAL_ACTION "%initial-action {...}" - PERCENT_LEX_PARAM "%lex-param {...}" + PERCENT_INITIAL_ACTION "%initial-action" + PERCENT_LEX_PARAM "%lex-param" PERCENT_LOCATIONS "%locations" PERCENT_NAME_PREFIX "%name-prefix" PERCENT_NO_DEFAULT_PREC "%no-default-prec" PERCENT_NO_LINES "%no-lines" PERCENT_NONDETERMINISTIC_PARSER - "%nondeterministic-parser" + "%nondeterministic-parser" PERCENT_OUTPUT "%output" - PERCENT_PARSE_PARAM "%parse-param {...}" + PERCENT_PARSE_PARAM "%parse-param" PERCENT_PURE_PARSER "%pure-parser" - PERCENT_REQUIRE "%require" + PERCENT_REQUIRE "%require" PERCENT_SKELETON "%skeleton" PERCENT_START "%start" PERCENT_TOKEN_TABLE "%token-table" @@ -144,46 +158,38 @@ static int current_prec = 0; PERCENT_YACC "%yacc" ; -%token TYPE "type" +%token BRACED_CODE "{...}" +%token CHAR "char" +%token EPILOGUE "epilogue" %token EQUAL "=" -%token SEMICOLON ";" -%token PIPE "|" %token ID "identifier" %token ID_COLON "identifier:" %token PERCENT_PERCENT "%%" +%token PIPE "|" %token PROLOGUE "%{...%}" -%token EPILOGUE "epilogue" -%token BRACED_CODE "{...}" +%token SEMICOLON ";" +%token TYPE "type" + +%type CHAR +%printer { fputs (char_name ($$), stderr); } CHAR +%type STRING string_content "{...}" PROLOGUE EPILOGUE +%printer { fputs (quotearg_style (c_quoting_style, $$), stderr); } + STRING string_content +%printer { fprintf (stderr, "{\n%s\n}", $$); } "{...}" PROLOGUE EPILOGUE -%type STRING string_content - "%destructor {...}" - "%initial-action {...}" - "%lex-param {...}" - "%parse-param {...}" - "%printer {...}" - "%union {...}" - BRACED_CODE action - PROLOGUE EPILOGUE -%printer { fprintf (stderr, "\"%s\"", $$); } - STRING string_content -%printer { fprintf (stderr, "{\n%s\n}", $$); } - "%destructor {...}" - "%initial-action {...}" - "%lex-param {...}" - "%parse-param {...}" - "%printer {...}" - "%union {...}" - BRACED_CODE action - PROLOGUE EPILOGUE -%type TYPE +%type TYPE ID ID_COLON %printer { fprintf (stderr, "<%s>", $$); } TYPE +%printer { fputs ($$, stderr); } ID +%printer { fprintf (stderr, "%s:", $$); } ID_COLON + %type INT %printer { fprintf (stderr, "%d", $$); } INT -%type ID symbol string_as_id -%printer { fprintf (stderr, "%s", $$->tag); } ID symbol string_as_id -%type ID_COLON -%printer { fprintf (stderr, "%s:", $$->tag); } ID_COLON + +%type id id_colon symbol string_as_id +%printer { fprintf (stderr, "%s", $$->tag); } id symbol string_as_id +%printer { fprintf (stderr, "%s:", $$->tag); } id_colon + %type precedence_declarator %type symbols.1 %% @@ -204,9 +210,14 @@ declarations: declaration: grammar_declaration -| PROLOGUE { prologue_augment ($1, @1); } +| PROLOGUE { prologue_augment (translate_code ($1, @1), + @1); } | "%debug" { debug_flag = true; } -| "%define" string_content { muscle_insert ($2, "1"); } +| "%define" string_content + { + static char one[] = "1"; + muscle_insert ($2, one); + } | "%define" string_content string_content { muscle_insert ($2, $3); } | "%defines" { defines_flag = true; } | "%error-verbose" { error_verbose = true; } @@ -214,21 +225,21 @@ declaration: | "%expect-rr" INT { expected_rr_conflicts = $2; } | "%file-prefix" "=" string_content { spec_file_prefix = $3; } | "%glr-parser" - { - nondeterministic_parser = true; - glr_parser = true; - } -| "%initial-action {...}" - { - muscle_code_grow ("initial_action", $1, @1); - } -| "%lex-param {...}" { add_param ("lex_param", $1, @1); } + { + nondeterministic_parser = true; + glr_parser = true; + } +| "%initial-action" "{...}" + { + muscle_code_grow ("initial_action", translate_symbol_action ($2, @2), @2); + } +| "%lex-param" "{...}" { add_param ("lex_param", $2, @2); } | "%locations" { locations_flag = true; } | "%name-prefix" "=" string_content { spec_name_prefix = $3; } | "%no-lines" { no_lines_flag = true; } | "%nondeterministic-parser" { nondeterministic_parser = true; } | "%output" "=" string_content { spec_outfile = $3; } -| "%parse-param {...}" { add_param ("parse_param", $1, @1); } +| "%parse-param" "{...}" { add_param ("parse_param", $2, @2); } | "%pure-parser" { pure_parser = true; } | "%require" string_content { version_check (&@2, $2); } | "%skeleton" string_content { skeleton = $2; } @@ -245,35 +256,21 @@ grammar_declaration: { grammar_start_symbol_set ($2, @2); } -| "%union {...}" - { - char const *body = $1; - - if (typed) - { - /* Concatenate the union bodies, turning the first one's - trailing '}' into '\n', and omitting the second one's '{'. */ - char *code = muscle_find ("stype"); - code[strlen (code) - 1] = '\n'; - body++; - } - - typed = true; - muscle_code_grow ("stype", body, @1); - } -| "%destructor {...}" symbols.1 +| "%destructor" "{...}" symbols.1 { symbol_list *list; - for (list = $2; list; list = list->next) - symbol_destructor_set (list->sym, $1, @1); - symbol_list_free ($2); + const char *action = translate_symbol_action ($2, @2); + for (list = $3; list; list = list->next) + symbol_destructor_set (list->sym, action, @2); + symbol_list_free ($3); } -| "%printer {...}" symbols.1 +| "%printer" "{...}" symbols.1 { symbol_list *list; - for (list = $2; list; list = list->next) - symbol_printer_set (list->sym, $1, list->location); - symbol_list_free ($2); + const char *action = translate_symbol_action ($2, @2); + for (list = $3; list; list = list->next) + symbol_printer_set (list->sym, action, @2); + symbol_list_free ($3); } | "%default-prec" { @@ -285,6 +282,40 @@ grammar_declaration: } ; + +/*----------* + | %union. | + *----------*/ + +%token PERCENT_UNION "%union"; + +union_name: + /* Nothing. */ {} +| ID { muscle_code_grow ("union_name", $1, @1); } +; + +grammar_declaration: + "%union" union_name "{...}" + { + char const *body = $3; + + if (typed) + { + /* Concatenate the union bodies, turning the first one's + trailing '}' into '\n', and omitting the second one's '{'. */ + char *code = muscle_find ("stype"); + code[strlen (code) - 1] = '\n'; + body++; + } + + typed = true; + muscle_code_grow ("stype", body, @3); + } +; + + + + symbol_declaration: "%nterm" { current_class = nterm_sym; } symbol_defs.1 { @@ -332,7 +363,6 @@ type.opt: ; /* One or more nonterminals to be %typed. */ - symbols.1: symbol { $$ = symbol_list_new ($1, @1); } | symbols.1 symbol { $$ = symbol_list_prepend ($1, $2, @2); } @@ -344,26 +374,26 @@ symbol_def: { current_type = $1; } -| ID +| id { - symbol_class_set ($1, current_class, @1); + symbol_class_set ($1, current_class, @1, true); symbol_type_set ($1, current_type, @1); } -| ID INT +| id INT { - symbol_class_set ($1, current_class, @1); + symbol_class_set ($1, current_class, @1, true); symbol_type_set ($1, current_type, @1); symbol_user_token_number_set ($1, $2, @2); } -| ID string_as_id +| id string_as_id { - symbol_class_set ($1, current_class, @1); + symbol_class_set ($1, current_class, @1, true); symbol_type_set ($1, current_type, @1); symbol_make_alias ($1, $2, @$); } -| ID INT string_as_id +| id INT string_as_id { - symbol_class_set ($1, current_class, @1); + symbol_class_set ($1, current_class, @1, true); symbol_type_set ($1, current_type, @1); symbol_user_token_number_set ($1, $2, @2); symbol_make_alias ($1, $3, @$); @@ -391,10 +421,6 @@ grammar: rules_or_grammar_declaration: rules | grammar_declaration ";" - { - if (yacc_flag) - complain_at (@$, _("POSIX forbids declarations in the grammar")); - } | error ";" { yyerrok; @@ -402,7 +428,7 @@ rules_or_grammar_declaration: ; rules: - ID_COLON { current_lhs = $1; current_lhs_location = @1; } rhses.1 + id_colon { current_lhs = $1; current_lhs_location = @1; } rhses.1 ; rhses.1: @@ -416,8 +442,9 @@ rhs: { grammar_current_rule_begin (current_lhs, current_lhs_location); } | rhs symbol { grammar_current_rule_symbol_append ($2, @2); } -| rhs action - { grammar_current_rule_action_append ($2, @2); } +| rhs "{...}" + { grammar_current_rule_action_append (gram_last_string, + gram_last_braced_code_loc); } | rhs "%prec" symbol { grammar_current_rule_prec_set ($3, @3); } | rhs "%dprec" INT @@ -426,14 +453,33 @@ rhs: { grammar_current_rule_merge_set ($3, @3); } ; -symbol: - ID { $$ = $1; } -| string_as_id { $$ = $1; } + +/*---------------* + | Identifiers. | + *---------------*/ + +/* Identifiers are returned as uniqstr values by the scanner. + Depending on their use, we may need to make them genuine symbols. */ + +id: + ID + { $$ = symbol_get ($1, @1); } +| CHAR + { + $$ = symbol_get (char_name ($1), @1); + symbol_class_set ($$, token_sym, @1, false); + symbol_user_token_number_set ($$, $1, @1); + } ; -action: - BRACED_CODE - { $$ = $1; } +id_colon: + ID_COLON { $$ = symbol_get ($1, @1); } +; + + +symbol: + id +| string_as_id ; /* A string used as an ID: quote it. */ @@ -441,7 +487,7 @@ string_as_id: STRING { $$ = symbol_get (quotearg_style (c_quoting_style, $1), @1); - symbol_class_set ($$, token_sym, @1); + symbol_class_set ($$, token_sym, @1, false); } ; @@ -456,8 +502,8 @@ epilogue.opt: /* Nothing. */ | "%%" EPILOGUE { - muscle_code_grow ("epilogue", $2, @2); - scanner_last_string_free (); + muscle_code_grow ("epilogue", translate_code ($2, @2), @2); + gram_scanner_last_string_free (); } ; @@ -542,7 +588,7 @@ add_param (char const *type, char *decl, location loc) free (name); } - scanner_last_string_free (); + gram_scanner_last_string_free (); } static void @@ -567,3 +613,16 @@ token_name (int type) { return yytname[YYTRANSLATE (type)]; } + +static char const * +char_name (char c) +{ + if (c == '\'') + return "'\\''"; + else + { + char buf[4]; + buf[0] = '\''; buf[1] = c; buf[2] = '\''; buf[3] = '\0'; + return quotearg_style (escape_quoting_style, buf); + } +}