X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/fb9c0b3360928887038a296c338025ced68e2d8c..08af01c2fc26eeb77afe3a667dded68c52ea3c37:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index 027a773d..cf7f7793 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -1,6 +1,7 @@ %{/* Bison Grammar Parser -*- C -*- - Copyright (C) 2002, 2003, 2004, 2005 Free Software Foundation, Inc. + Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007 Free Software Foundation, + Inc. This file is part of Bison, the GNU Compiler Compiler. @@ -20,25 +21,28 @@ 02110-1301 USA */ +#include #include "system.h" +#include + #include "complain.h" #include "conflicts.h" #include "files.h" #include "getargs.h" #include "gram.h" #include "muscle_tab.h" -#include "output.h" #include "quotearg.h" #include "reader.h" #include "symlist.h" -#include "strverscmp.h" +#include "scan-gram.h" +#include "scan-code.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); @@ -46,17 +50,30 @@ 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 void add_param (char const *, char *, location); +static char const *char_name (char); + +/** Add a lex-param or a parse-param. + * + * \param type \a lex_param or \a parse_param + * \param decl the formal argument + * \param loc the location in the source. + */ +static void add_param (char const *type, char *decl, location loc); + static symbol_class current_class = unknown_sym; -static uniqstr current_type = 0; -symbol *current_lhs; -location current_lhs_location; -assoc current_assoc; +static uniqstr current_type = NULL; +static symbol *current_lhs; +static location current_lhs_location; static int current_prec = 0; + +#define YYTYPE_INT16 int_fast16_t +#define YYTYPE_INT8 int_fast8_t +#define YYTYPE_UINT16 uint_fast16_t +#define YYTYPE_UINT8 uint_fast8_t %} %debug @@ -67,25 +84,26 @@ static int current_prec = 0; %error-verbose %defines %name-prefix="gram_" +%expect 0 %initial-action { /* 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 (&@$.start, current_file, 1, 1); + boundary_set (&@$.end, current_file, 1, 1); } -/* Only NUMBERS have a value. */ %union { symbol *symbol; symbol_list *list; int integer; - char *chars; + char const *chars; + char *code; assoc assoc; uniqstr uniqstr; + unsigned char character; }; /* Define the tokens together with their human representation. */ @@ -97,10 +115,8 @@ 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" @@ -116,6 +132,7 @@ static int current_prec = 0; `----------------------*/ %token + PERCENT_CODE "%code" PERCENT_DEBUG "%debug" PERCENT_DEFAULT_PREC "%default-prec" PERCENT_DEFINE "%define" @@ -125,18 +142,22 @@ 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_LANGUAGE "%language" + 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_PUSH_PARSER "%push-parser" + PERCENT_PUSH_PULL_PARSER + "%push-pull-parser" + PERCENT_REQUIRE "%require" PERCENT_SKELETON "%skeleton" PERCENT_START "%start" PERCENT_TOKEN_TABLE "%token-table" @@ -144,52 +165,50 @@ 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 "{...}" - - -%type STRING string_content - "%destructor {...}" - "%initial-action {...}" - "%lex-param {...}" - "%parse-param {...}" - "%printer {...}" - "%union {...}" - BRACED_CODE action - PROLOGUE EPILOGUE -%printer { fprintf (stderr, "\"%s\"", $$); } - STRING string_content +%token SEMICOLON ";" +%token TYPE "type" +%token TYPE_TAG_ANY "<*>" +%token TYPE_TAG_NONE "<>" + +%type CHAR +%printer { fputs (char_name ($$), stderr); } CHAR + +/* braceless is not to be used for rule or symbol actions, as it + calls code_props_plain_init. */ +%type STRING "%{...%}" EPILOGUE braceless content content.opt +%type "{...}" +%printer { fputs (quotearg_style (c_quoting_style, $$), stderr); } + STRING %printer { fprintf (stderr, "{\n%s\n}", $$); } - "%destructor {...}" - "%initial-action {...}" - "%lex-param {...}" - "%parse-param {...}" - "%printer {...}" - "%union {...}" - BRACED_CODE action - PROLOGUE EPILOGUE -%type TYPE + braceless content content.opt "{...}" "%{...%}" EPILOGUE + +%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 { fputs ($$->tag, stderr); } ID symbol string_as_id -%type ID_COLON -%printer { fprintf (stderr, "%s:", $$->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 +%type symbols.1 generic_symlist generic_symlist_item %% input: - declarations "%%" grammar epilogue.opt + prologue_declarations "%%" grammar epilogue.opt ; @@ -197,44 +216,67 @@ input: | Declarations: before the first %%. | `------------------------------------*/ -declarations: +prologue_declarations: /* Nothing */ -| declarations declaration +| prologue_declarations prologue_declaration ; -declaration: +prologue_declaration: grammar_declaration -| PROLOGUE { prologue_augment ($1, @1); } -| "%debug" { debug_flag = true; } -| "%define" string_content { muscle_insert ($2, "1"); } -| "%define" string_content string_content { muscle_insert ($2, $3); } -| "%defines" { defines_flag = true; } -| "%error-verbose" { error_verbose = true; } -| "%expect" INT { expected_sr_conflicts = $2; } -| "%expect-rr" INT { expected_rr_conflicts = $2; } -| "%file-prefix" "=" string_content { spec_file_prefix = $3; } +| "%{...%}" + { + code_props plain_code; + code_props_plain_init (&plain_code, $1, @1); + code_props_translate_code (&plain_code); + gram_scanner_last_string_free (); + prologue_augment (plain_code.code, @1, union_seen); + code_scanner_last_string_free (); + } +| "%debug" { debug_flag = true; } +| "%define" STRING content.opt { muscle_insert ($2, $3); } +| "%defines" { defines_flag = true; } +| "%defines" STRING + { + defines_flag = true; + spec_defines_file = xstrdup ($2); + } +| "%error-verbose" { error_verbose = true; } +| "%expect" INT { expected_sr_conflicts = $2; } +| "%expect-rr" INT { expected_rr_conflicts = $2; } +| "%file-prefix" STRING { spec_file_prefix = $2; } +| "%file-prefix" "=" STRING { spec_file_prefix = $3; } /* deprecated */ | "%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); } -| "%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); } -| "%pure-parser" { pure_parser = true; } -| "%require" string_content { version_check (&@2, $2); } -| "%skeleton" string_content { skeleton = $2; } -| "%token-table" { token_table_flag = true; } -| "%verbose" { report_flag = report_states; } -| "%yacc" { yacc_flag = true; } + { + nondeterministic_parser = true; + glr_parser = true; + } +| "%initial-action" "{...}" + { + code_props action; + code_props_symbol_action_init (&action, $2, @2); + code_props_translate_code (&action); + gram_scanner_last_string_free (); + muscle_code_grow ("initial_action", action.code, @2); + code_scanner_last_string_free (); + } +| "%language" STRING { language_argmatch ($2, 1, &@1); } +| "%lex-param" "{...}" { add_param ("lex_param", $2, @2); } +| "%locations" { locations_flag = true; } +| "%name-prefix" STRING { spec_name_prefix = $2; } +| "%name-prefix" "=" STRING { spec_name_prefix = $3; } /* deprecated */ +| "%no-lines" { no_lines_flag = true; } +| "%nondeterministic-parser" { nondeterministic_parser = true; } +| "%output" STRING { spec_outfile = $2; } +| "%output" "=" STRING { spec_outfile = $3; } /* deprecated */ +| "%parse-param" "{...}" { add_param ("parse_param", $2, @2); } +| "%pure-parser" { pure_parser = true; } +| "%push-parser" { push_parser = true; pull_parser = false; } +| "%push-pull-parser" { push_parser = true; pull_parser = true; } +| "%require" STRING { version_check (&@2, $2); } +| "%skeleton" STRING { skeleton_arg ($2, 1, &@1); } +| "%token-table" { token_table_flag = true; } +| "%verbose" { report_flag = report_states; } +| "%yacc" { yacc_flag = true; } | /*FIXME: Err? What is this horror doing here? */ ";" ; @@ -245,25 +287,19 @@ grammar_declaration: { grammar_start_symbol_set ($2, @2); } -| "%union {...}" - { - typed = true; - MUSCLE_INSERT_INT ("stype_line", @1.start.line); - muscle_insert ("stype", $1); - } -| "%destructor {...}" symbols.1 +| "%destructor" "{...}" generic_symlist { symbol_list *list; - for (list = $2; list; list = list->next) - symbol_destructor_set (list->sym, $1, @1); - symbol_list_free ($2); + for (list = $3; list; list = list->next) + symbol_list_destructor_set (list, $2, @2); + symbol_list_free ($3); } -| "%printer {...}" symbols.1 +| "%printer" "{...}" generic_symlist { symbol_list *list; - for (list = $2; list; list = list->next) - symbol_printer_set (list->sym, $1, list->location); - symbol_list_free ($2); + for (list = $3; list; list = list->next) + symbol_list_printer_set (list, $2, @2); + symbol_list_free ($3); } | "%default-prec" { @@ -273,8 +309,65 @@ grammar_declaration: { default_prec = false; } +| "%code" braceless + { + muscle_code_grow ("percent_code", $2, @2); + code_scanner_last_string_free (); + } +| "%code" STRING braceless + { + char const name_prefix[] = "percent_code_"; + char *name = xmalloc (sizeof name_prefix + strlen ($2)); + strcpy (name, name_prefix); + strcpy (name + sizeof name_prefix - 1, $2); + muscle_code_grow (uniqstr_new (name), $3, @3); + free (name); + code_scanner_last_string_free (); + muscle_grow ("used_percent_code_qualifiers", $2, ","); + } ; + +/*----------* + | %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; + + /* Concatenate the %union bodies. If this is the first %union, make sure + the synchronization line appears after the opening '{' so as not to + confuse Doxygen. Otherwise, turn the previous %union's trailing '}' + into '\n', and omit the new %union's leading '{'. */ + if (!union_seen) + { + muscle_grow ("stype", "{", ""); + } + else + { + char *code = muscle_find ("stype"); + code[strlen (code) - 1] = '\n'; + } + body++; + + union_seen = true; + muscle_code_grow ("stype", body, @3); + gram_scanner_last_string_free (); + } +; + + + + symbol_declaration: "%nterm" { current_class = nterm_sym; } symbol_defs.1 { @@ -289,8 +382,9 @@ symbol_declaration: | "%type" TYPE symbols.1 { symbol_list *list; + tag_seen = true; for (list = $3; list; list = list->next) - symbol_type_set (list->sym, $2, @2); + symbol_type_set (list->content.sym, $2, @2); symbol_list_free ($3); } ; @@ -302,8 +396,8 @@ precedence_declaration: ++current_prec; for (list = $3; list; list = list->next) { - symbol_type_set (list->sym, current_type, @2); - symbol_precedence_set (list->sym, current_prec, $1, @1); + symbol_type_set (list->content.sym, current_type, @2); + symbol_precedence_set (list->content.sym, current_prec, $1, @1); } symbol_list_free ($3); current_type = NULL; @@ -318,14 +412,27 @@ precedence_declarator: type.opt: /* Nothing. */ { current_type = NULL; } -| TYPE { current_type = $1; } +| TYPE { current_type = $1; tag_seen = true; } ; -/* One or more nonterminals to be %typed. */ - +/* One or more symbols to be %typed. */ symbols.1: - symbol { $$ = symbol_list_new ($1, @1); } -| symbols.1 symbol { $$ = symbol_list_prepend ($1, $2, @2); } + symbol + { $$ = symbol_list_sym_new ($1, @1); } +| symbols.1 symbol + { $$ = symbol_list_prepend ($1, symbol_list_sym_new ($2, @2)); } +; + +generic_symlist: + generic_symlist_item { $$ = $1; } +| generic_symlist generic_symlist_item { $$ = symbol_list_prepend ($1, $2); } +; + +generic_symlist_item: + symbol { $$ = symbol_list_sym_new ($1, @1); } +| TYPE { $$ = symbol_list_type_new ($1, @1); } +| "<*>" { $$ = symbol_list_default_tagged_new (@1); } +| "<>" { $$ = symbol_list_default_tagless_new (@1); } ; /* One token definition. */ @@ -333,27 +440,28 @@ symbol_def: TYPE { current_type = $1; + tag_seen = true; } -| 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, $3, @$); @@ -381,10 +489,6 @@ grammar: rules_or_grammar_declaration: rules | grammar_declaration ";" - { - if (yacc_flag) - complain_at (@$, _("POSIX forbids declarations in the grammar")); - } | error ";" { yyerrok; @@ -392,21 +496,21 @@ 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: - rhs { grammar_rule_end (@1); } -| rhses.1 "|" rhs { grammar_rule_end (@3); } + rhs { grammar_current_rule_end (@1); } +| rhses.1 "|" rhs { grammar_current_rule_end (@3); } | rhses.1 ";" ; rhs: /* Nothing. */ - { grammar_rule_begin (current_lhs, current_lhs_location); } + { grammar_current_rule_begin (current_lhs, current_lhs_location); } | rhs symbol { grammar_current_rule_symbol_append ($2, @2); } -| rhs action +| rhs "{...}" { grammar_current_rule_action_append ($2, @2); } | rhs "%prec" symbol { grammar_current_rule_prec_set ($3, @3); } @@ -416,14 +520,66 @@ rhs: { grammar_current_rule_merge_set ($3, @3); } ; -symbol: - ID { $$ = $1; } -| string_as_id { $$ = $1; } + +/*-----------* + | content. | + *-----------*/ + +content: + STRING +| braceless ; -action: - BRACED_CODE - { $$ = $1; } +/* Some content or "1" by default. */ +content.opt: + /* Nothing. */ + { + static char one[] = "1"; + $$ = one; + } +| content +; + + +braceless: + "{...}" + { + code_props plain_code; + $1[strlen ($1) - 1] = '\n'; + code_props_plain_init (&plain_code, $1+1, @1); + code_props_translate_code (&plain_code); + gram_scanner_last_string_free (); + $$ = plain_code.code; + } +; + + +/*---------------* + | Identifiers. | + *---------------*/ + +/* Identifiers are returned as uniqstr values by the scanner. + Depending on their use, we may need to make them genuine symbols. */ + +id: + ID + { $$ = symbol_from_uniqstr ($1, @1); } +| CHAR + { + $$ = symbol_get (char_name ($1), @1); + symbol_class_set ($$, token_sym, @1, false); + symbol_user_token_number_set ($$, $1, @1); + } +; + +id_colon: + ID_COLON { $$ = symbol_from_uniqstr ($1, @1); } +; + + +symbol: + id +| string_as_id ; /* A string used as an ID: quote it. */ @@ -431,23 +587,20 @@ string_as_id: STRING { $$ = symbol_get (quotearg_style (c_quoting_style, $1), @1); - symbol_class_set ($$, token_sym, @1); + symbol_class_set ($$, token_sym, @1, false); } ; -/* A string used for its contents. Don't quote it. */ -string_content: - STRING - { $$ = $1; } -; - - epilogue.opt: /* Nothing. */ | "%%" EPILOGUE { - muscle_code_grow ("epilogue", $2, @2); - scanner_last_string_free (); + code_props plain_code; + code_props_plain_init (&plain_code, $2, @2); + code_props_translate_code (&plain_code); + gram_scanner_last_string_free (); + muscle_code_grow ("epilogue", plain_code.code, @2); + code_scanner_last_string_free (); } ; @@ -532,15 +685,19 @@ add_param (char const *type, char *decl, location loc) free (name); } - scanner_last_string_free (); + gram_scanner_last_string_free (); } + static void version_check (location const *loc, char const *version) { if (strverscmp (version, PACKAGE_VERSION) > 0) - complain_at (*loc, "require bison %s, but have %s", - version, PACKAGE_VERSION); + { + complain_at (*loc, "require bison %s, but have %s", + version, PACKAGE_VERSION); + exit (63); + } } static void @@ -554,3 +711,16 @@ 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); + } +}