X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/a737b2163c275761f32589bf7c249016452bb730..31c10e38dbf21a29af558c6f5144acd22dbc956e:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index 668d9db3..956ddd36 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -1,6 +1,6 @@ -/* Bison Grammar Parser -*- C -*- +%{/* Bison Grammar Parser -*- C -*- - Copyright (C) 2002, 2003 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. @@ -16,59 +16,82 @@ You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA - 02111-1307 USA + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + 02110-1301 USA */ - -%debug -%defines -%locations -%pure-parser -// %error-verbose -%defines -%name-prefix="gram_" - -%{ +#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" - -/* Produce verbose syntax errors. */ -#define YYERROR_VERBOSE 1 +#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) + +static void version_check (location const *loc, char const *version); + /* Request detailed syntax error messages, and pass them to GRAM_ERROR. 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 *); -#define YYPRINT(File, Type, Value) \ - print_token_value (File, Type, &Value) -static void print_token_value (FILE *, int, YYSTYPE const *); +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 void add_param (char const *, char *, location); +static symbol_class current_class = unknown_sym; +static uniqstr current_type = NULL; +static symbol *current_lhs; +static location current_lhs_location; +static int current_prec = 0; -symbol_class current_class = unknown_sym; -uniqstr current_type = 0; -symbol *current_lhs; -location current_lhs_location; -assoc current_assoc; -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 +%verbose +%defines +%locations +%pure-parser +%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 (&@$.start, current_file, 1, 1); + boundary_set (&@$.end, current_file, 1, 1); +} /* Only NUMBERS have a value. */ %union @@ -79,6 +102,7 @@ int current_prec = 0; char *chars; assoc assoc; uniqstr uniqstr; + unsigned char character; }; /* Define the tokens together with their human representation. */ @@ -90,10 +114,10 @@ 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_SYMBOL_DEFAULT + "%symbol-default" %token PERCENT_LEFT "%left" %token PERCENT_RIGHT "%right" @@ -109,56 +133,80 @@ int current_prec = 0; `----------------------*/ %token - PERCENT_DEBUG "%debug" - PERCENT_DEFINE "%define" - PERCENT_DEFINES "%defines" - PERCENT_ERROR_VERBOSE "%error-verbose" - PERCENT_EXPECT "%expect" - PERCENT_FILE_PREFIX "%file-prefix" - PERCENT_GLR_PARSER "%glr-parser" - PERCENT_LEX_PARAM "%lex-param {...}" - PERCENT_LOCATIONS "%locations" - PERCENT_NAME_PREFIX "%name-prefix" - PERCENT_NO_LINES "%no-lines" - PERCENT_OUTPUT "%output" - PERCENT_PARSE_PARAM "%parse-param {...}" - PERCENT_PURE_PARSER "%pure-parser" - PERCENT_SKELETON "%skeleton" - PERCENT_START "%start" - PERCENT_TOKEN_TABLE "%token-table" - PERCENT_VERBOSE "%verbose" - PERCENT_YACC "%yacc" + 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" + PERCENT_FILE_PREFIX "%file-prefix" + PERCENT_GLR_PARSER "%glr-parser" + 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" + 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" ; -%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 ($$), stderr); } CHAR +/* braceless is not to be used for rule or symbol actions, as it + calls translate_code. */ +%type STRING "{...}" "%{...%}" EPILOGUE braceless content content.opt +%printer { fputs (quotearg_style (c_quoting_style, $$), stderr); } + STRING +%printer { fprintf (stderr, "{\n%s\n}", $$); } + braceless content content.opt "{...}" "%{...%}" EPILOGUE + +%type TYPE ID ID_COLON +%printer { fprintf (stderr, "<%s>", $$); } TYPE +%printer { fputs ($$, stderr); } ID +%printer { fprintf (stderr, "%s:", $$); } ID_COLON -%type STRING string_content - "%destructor {...}" - "%lex-param {...}" - "%parse-param {...}" - "%printer {...}" - "%union {...}" - BRACED_CODE action - PROLOGUE EPILOGUE -%type TYPE %type INT -%type ID ID_COLON symbol string_as_id +%printer { fprintf (stderr, "%d", $$); } INT + +%type id id_colon symbol string_as_id +%printer { fprintf (stderr, "%s", $$->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 ; @@ -166,33 +214,49 @@ 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 = 1; } -| "%define" string_content string_content { muscle_insert ($2, $3); } -| "%defines" { defines_flag = 1; } -| "%error-verbose" { error_verbose = 1; } -| "%expect" INT { expected_conflicts = $2; } -| "%file-prefix" "=" string_content { spec_file_prefix = $3; } -| "%glr-parser" { glr_parser = 1; } -| "%lex-param {...}" { add_param ("lex_param", $1, @1); } -| "%locations" { locations_flag = 1; } -| "%name-prefix" "=" string_content { spec_name_prefix = $3; } -| "%no-lines" { no_lines_flag = 1; } -| "%output" "=" string_content { spec_outfile = $3; } -| "%parse-param {...}" { add_param ("parse_param", $1, @1); } -| "%pure-parser" { pure_parser = 1; } -| "%skeleton" string_content { skeleton = $2; } -| "%token-table" { token_table_flag = 1; } -| "%verbose" { report_flag = report_states; } -| "%yacc" { yacc_flag = 1; } -| ";" +| "%{...%}" { 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; + 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 { 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? */ ";" ; grammar_declaration: @@ -202,28 +266,72 @@ grammar_declaration: { grammar_start_symbol_set ($2, @2); } -| "%union {...}" +| "%destructor" "{...}" generic_symlist { - typed = 1; - MUSCLE_INSERT_INT ("stype_line", @1.start.line); - muscle_insert ("stype", $1); + symbol_list *list; + const char *action = translate_symbol_action ($2, @2); + for (list = $3; list; list = list->next) + symbol_list_destructor_set (list, action, @2); + symbol_list_free ($3); } -| "%destructor {...}" symbols.1 +| "%printer" "{...}" generic_symlist { 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_list_printer_set (list, action, @2); + symbol_list_free ($3); } -| "%printer {...}" symbols.1 +| "%default-prec" { - symbol_list *list; - for (list = $2; list; list = list->next) - symbol_printer_set (list->sym, $1, list->location); - symbol_list_free ($2); + default_prec = true; } +| "%no-default-prec" + { + default_prec = false; + } +; + + +/*----------* + | %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); + } +; + + + + symbol_declaration: "%nterm" { current_class = nterm_sym; } symbol_defs.1 { @@ -237,9 +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); } ; @@ -251,8 +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; @@ -267,14 +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. */ @@ -282,27 +403,28 @@ 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, $3, @$); @@ -329,33 +451,29 @@ grammar: body of the grammar. */ rules_or_grammar_declaration: rules -| grammar_declaration - { - if (yacc_flag) - complain_at (@$, _("POSIX forbids declarations in the grammar")); - } +| grammar_declaration ";" | error ";" { yyerrok; } -| ";" ; 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); } @@ -365,40 +483,79 @@ rhs: { grammar_current_rule_merge_set ($3, @3); } ; -symbol: - ID { $$ = $1; } -| string_as_id { $$ = $1; } + +/*-----------* + | content. | + *-----------*/ + +content: + STRING +| braceless +; + +/* Some content or "1" by default. */ +content.opt: + /* Nothing. */ + { + static char one[] = "1"; + $$ = one; + } +| content ; -action: - BRACED_CODE - { $$ = $1; } + +braceless: + "{...}" + { + $1[strlen ($1) - 1] = '\n'; + $$ = translate_code ($1 + 1, @1); + } ; -/* A string used as an ID: we have to keep the quotes. */ -string_as_id: - STRING + +/*---------------* + | Identifiers. | + *---------------*/ + +/* Identifiers are returned as uniqstr values by the scanner. + Depending on their use, we may need to make them genuine symbols. */ + +id: + ID + { $$ = symbol_from_uniqstr ($1, @1); } +| CHAR { - $$ = symbol_get ($1, @1); - symbol_class_set ($$, token_sym, @1); + $$ = symbol_get (char_name ($1), @1); + symbol_class_set ($$, token_sym, @1, false); + symbol_user_token_number_set ($$, $1, @1); } ; -/* A string used for its contents. Strip the quotes. */ -string_content: +id_colon: + ID_COLON { $$ = symbol_from_uniqstr ($1, @1); } +; + + +symbol: + id +| string_as_id +; + +/* A string used as an ID: quote it. */ +string_as_id: STRING { - $$ = $1 + 1; - $$[strlen ($$) - 1] = '\0'; - }; - + $$ = symbol_get (quotearg_style (c_quoting_style, $1), @1); + symbol_class_set ($$, token_sym, @1, false); + } +; epilogue.opt: /* Nothing. */ | "%%" EPILOGUE { - epilogue_augment ($2, @2); - scanner_last_string_free (); + muscle_code_grow ("epilogue", translate_code ($2, @2), @2); + gram_scanner_last_string_free (); } ; @@ -415,7 +572,11 @@ lloc_default (YYLTYPE const *rhs, int n) { int i; YYLTYPE loc; - loc.start = loc.end = rhs[n].end; + + /* SGI MIPSpro 7.4.1m miscompiles "loc.start = loc.end = rhs[n].end;". + The bug is fixed in 7.4.2m, but play it safe for now. */ + loc.start = rhs[n].end; + loc.end = rhs[n].end; /* Ignore empty nonterminals the start of the the right-hand side. Do not bother to ignore them at the end of the right-hand side, @@ -437,22 +598,28 @@ lloc_default (YYLTYPE const *rhs, int n) static void add_param (char const *type, char *decl, location loc) { - static char const alphanum[] = - "0123456789" + static char const alphanum[26 + 26 + 1 + 10] = "abcdefghijklmnopqrstuvwxyz" "ABCDEFGHIJKLMNOPQRSTUVWXYZ" - "_"; - char const *alpha = alphanum + 10; + "_" + "0123456789"; char const *name_start = NULL; char *p; - for (p = decl; *p; p++) - if ((p == decl || ! strchr (alphanum, p[-1])) && strchr (alpha, p[0])) + /* Stop on last actual character. */ + for (p = decl; p[1]; p++) + if ((p == decl + || ! memchr (alphanum, p[-1], sizeof alphanum)) + && memchr (alphanum, p[0], sizeof alphanum - 10)) name_start = p; - /* Strip the surrounding '{' and '}'. */ - decl++; - p[-1] = '\0'; + /* Strip the surrounding '{' and '}', and any blanks just inside + the braces. */ + while (*--p == ' ' || *p == '\t') + continue; + p[1] = '\0'; + while (*++decl == ' ' || *decl == '\t') + continue; if (! name_start) complain_at (loc, _("missing identifier in parameter declaration")); @@ -462,7 +629,7 @@ add_param (char const *type, char *decl, location loc) size_t name_len; for (name_len = 1; - name_start[name_len] && strchr (alphanum, name_start[name_len]); + memchr (alphanum, name_start[name_len], sizeof alphanum); name_len++) continue; @@ -473,49 +640,18 @@ add_param (char const *type, char *decl, location loc) free (name); } - scanner_last_string_free (); + gram_scanner_last_string_free (); } -/*----------------------------------------------------. -| When debugging the parser, display tokens' values. | -`----------------------------------------------------*/ static void -print_token_value (FILE *file, int type, YYSTYPE const *value) +version_check (location const *loc, char const *version) { - fputc (' ', file); - switch (type) + if (strverscmp (version, PACKAGE_VERSION) > 0) { - case ID: - fprintf (file, " = %s", value->symbol->tag); - break; - - case INT: - fprintf (file, " = %d", value->integer); - break; - - case STRING: - fprintf (file, " = \"%s\"", value->chars); - break; - - case TYPE: - fprintf (file, " = <%s>", value->uniqstr); - break; - - case BRACED_CODE: - case PERCENT_DESTRUCTOR: - case PERCENT_LEX_PARAM: - case PERCENT_PARSE_PARAM: - case PERCENT_PRINTER: - case PERCENT_UNION: - case PROLOGUE: - case EPILOGUE: - fprintf (file, " = {{ %s }}", value->chars); - break; - - default: - fprintf (file, "unknown token type"); - break; + complain_at (*loc, "require bison %s, but have %s", + version, PACKAGE_VERSION); + exit (63); } } @@ -528,5 +664,18 @@ gram_error (location const *loc, char const *msg) char const * token_name (int type) { - return yytname[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); + } }