X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/33ad1a9c2d7b2eb22ebc010c7cdaac48b3f5e8c7..31c10e38dbf21a29af558c6f5144acd22dbc956e:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index f45b323c..956ddd36 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -23,6 +23,8 @@ #include #include "system.h" +#include + #include "complain.h" #include "conflicts.h" #include "files.h" @@ -34,7 +36,6 @@ #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); @@ -53,26 +54,25 @@ static void gram_error (location const *, char const *); static char const *char_name (char); -static void add_param (char const *, char *, location); +/** 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; +static uniqstr current_type = NULL; 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 +#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 @@ -83,13 +83,14 @@ 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. */ - boundary_set (&@$.start, current_file, 1, 0); - boundary_set (&@$.end, current_file, 1, 0); + boundary_set (&@$.start, current_file, 1, 1); + boundary_set (&@$.end, current_file, 1, 1); } /* Only NUMBERS have a value. */ @@ -115,6 +116,8 @@ static int current_prec = 0; %token PERCENT_TYPE "%type" %token PERCENT_DESTRUCTOR "%destructor" %token PERCENT_PRINTER "%printer" +%token PERCENT_SYMBOL_DEFAULT + "%symbol-default" %token PERCENT_LEFT "%left" %token PERCENT_RIGHT "%right" @@ -130,10 +133,13 @@ static int current_prec = 0; `----------------------*/ %token + PERCENT_AFTER_HEADER "%after-header" + PERCENT_BEFORE_HEADER "%before-header" PERCENT_DEBUG "%debug" PERCENT_DEFAULT_PREC "%default-prec" PERCENT_DEFINE "%define" PERCENT_DEFINES "%defines" + PERCENT_END_HEADER "%end-header" PERCENT_ERROR_VERBOSE "%error-verbose" PERCENT_EXPECT "%expect" PERCENT_EXPECT_RR "%expect-rr" @@ -150,9 +156,11 @@ static int current_prec = 0; PERCENT_OUTPUT "%output" PERCENT_PARSE_PARAM "%parse-param" PERCENT_PURE_PARSER "%pure-parser" + PERCENT_PUSH_PARSER "%push-parser" PERCENT_REQUIRE "%require" PERCENT_SKELETON "%skeleton" PERCENT_START "%start" + PERCENT_START_HEADER "%start-header" PERCENT_TOKEN_TABLE "%token-table" PERCENT_VERBOSE "%verbose" PERCENT_YACC "%yacc" @@ -173,10 +181,13 @@ static int current_prec = 0; %type CHAR %printer { fputs (char_name ($$), stderr); } CHAR -%type STRING string_content "{...}" PROLOGUE EPILOGUE +/* braceless is not to be used for rule or symbol actions, as it + calls translate_code. */ +%type STRING "{...}" "%{...%}" EPILOGUE braceless content content.opt %printer { fputs (quotearg_style (c_quoting_style, $$), stderr); } - STRING string_content -%printer { fprintf (stderr, "{\n%s\n}", $$); } "{...}" PROLOGUE EPILOGUE + STRING +%printer { fprintf (stderr, "{\n%s\n}", $$); } + braceless content content.opt "{...}" "%{...%}" EPILOGUE %type TYPE ID ID_COLON %printer { fprintf (stderr, "<%s>", $$); } TYPE @@ -191,11 +202,11 @@ static int current_prec = 0; %printer { fprintf (stderr, "%s:", $$->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 ; @@ -203,27 +214,24 @@ input: | Declarations: before the first %%. | `------------------------------------*/ -declarations: +prologue_declarations: /* Nothing */ -| declarations declaration +| prologue_declarations prologue_declaration ; -declaration: +prologue_declaration: grammar_declaration -| PROLOGUE { prologue_augment (translate_code ($1, @1), - @1); } -| "%debug" { debug_flag = true; } -| "%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; } -| "%expect" INT { expected_sr_conflicts = $2; } -| "%expect-rr" INT { expected_rr_conflicts = $2; } -| "%file-prefix" "=" string_content { spec_file_prefix = $3; } +| "%{...%}" { prologue_augment (translate_code ($1, @1), @1, union_seen); } +| "%after-header" braceless { prologue_augment ($2, @2, true); } +| "%before-header" braceless { prologue_augment ($2, @2, false); } +| "%debug" { debug_flag = true; } +| "%define" STRING content.opt { muscle_insert ($2, $3); } +| "%defines" { defines_flag = true; } +| "%end-header" braceless { muscle_code_grow ("end_header", $2, @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 = $3; } | "%glr-parser" { nondeterministic_parser = true; @@ -233,19 +241,21 @@ declaration: { 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", $2, @2); } -| "%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; } +| "%lex-param" "{...}" { add_param ("lex_param", $2, @2); } +| "%locations" { locations_flag = true; } +| "%name-prefix" "=" STRING { spec_name_prefix = $3; } +| "%no-lines" { no_lines_flag = true; } +| "%nondeterministic-parser" { nondeterministic_parser = true; } +| "%output" "=" STRING { spec_outfile = $3; } +| "%parse-param" "{...}" { add_param ("parse_param", $2, @2); } +| "%pure-parser" { pure_parser = true; } +| "%push-parser" { push_parser = true; } +| "%require" STRING { version_check (&@2, $2); } +| "%skeleton" STRING { skeleton = $2; } +| "%start-header" braceless { muscle_code_grow ("start_header", $2, @2); } +| "%token-table" { token_table_flag = true; } +| "%verbose" { report_flag = report_states; } +| "%yacc" { yacc_flag = true; } | /*FIXME: Err? What is this horror doing here? */ ";" ; @@ -256,20 +266,20 @@ grammar_declaration: { grammar_start_symbol_set ($2, @2); } -| "%destructor" "{...}" symbols.1 +| "%destructor" "{...}" generic_symlist { symbol_list *list; const char *action = translate_symbol_action ($2, @2); for (list = $3; list; list = list->next) - symbol_destructor_set (list->sym, action, @2); + symbol_list_destructor_set (list, action, @2); symbol_list_free ($3); } -| "%printer" "{...}" symbols.1 +| "%printer" "{...}" generic_symlist { symbol_list *list; const char *action = translate_symbol_action ($2, @2); for (list = $3; list; list = list->next) - symbol_printer_set (list->sym, action, @2); + symbol_list_printer_set (list, action, @2); symbol_list_free ($3); } | "%default-prec" @@ -299,16 +309,22 @@ grammar_declaration: { char const *body = $3; - if (typed) + /* 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 { - /* 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++; } + body++; - typed = true; + union_seen = true; muscle_code_grow ("stype", body, @3); } ; @@ -329,9 +345,10 @@ symbol_declaration: } | "%type" TYPE symbols.1 { + tag_seen = true; symbol_list *list; 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); } ; @@ -343,8 +360,8 @@ 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; @@ -359,13 +376,26 @@ 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-default" { $$ = symbol_list_default_new (@1); } ; /* One token definition. */ @@ -373,6 +403,7 @@ symbol_def: TYPE { current_type = $1; + tag_seen = true; } | id { @@ -443,8 +474,7 @@ rhs: | rhs symbol { grammar_current_rule_symbol_append ($2, @2); } | rhs "{...}" - { grammar_current_rule_action_append (gram_last_string, - gram_last_braced_code_loc); } + { grammar_current_rule_action_append ($2, @2); } | rhs "%prec" symbol { grammar_current_rule_prec_set ($3, @3); } | rhs "%dprec" INT @@ -454,6 +484,35 @@ rhs: ; +/*-----------* + | content. | + *-----------*/ + +content: + STRING +| braceless +; + +/* Some content or "1" by default. */ +content.opt: + /* Nothing. */ + { + static char one[] = "1"; + $$ = one; + } +| content +; + + +braceless: + "{...}" + { + $1[strlen ($1) - 1] = '\n'; + $$ = translate_code ($1 + 1, @1); + } +; + + /*---------------* | Identifiers. | *---------------*/ @@ -463,7 +522,7 @@ rhs: id: ID - { $$ = symbol_get ($1, @1); } + { $$ = symbol_from_uniqstr ($1, @1); } | CHAR { $$ = symbol_get (char_name ($1), @1); @@ -473,7 +532,7 @@ id: ; id_colon: - ID_COLON { $$ = symbol_get ($1, @1); } + ID_COLON { $$ = symbol_from_uniqstr ($1, @1); } ; @@ -491,13 +550,6 @@ string_as_id: } ; -/* A string used for its contents. Don't quote it. */ -string_content: - STRING - { $$ = $1; } -; - - epilogue.opt: /* Nothing. */ | "%%" EPILOGUE @@ -591,6 +643,7 @@ add_param (char const *type, char *decl, location loc) gram_scanner_last_string_free (); } + static void version_check (location const *loc, char const *version) {