X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/87fbb0bffc4335f246c89e4bef56a908227c3446..50a339934c5e471f02a1d28171b14e2875a05cf0:/src/parse-gram.y diff --git a/src/parse-gram.y b/src/parse-gram.y index aa307881..bc012637 100644 --- a/src/parse-gram.y +++ b/src/parse-gram.y @@ -1,5 +1,6 @@ -/* Bison Grammar Parser -*- C -*- - Copyright (C) 2002 Free Software Foundation, Inc. +%{/* Bison Grammar Parser -*- C -*- + + Copyright (C) 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc. This file is part of Bison, the GNU Compiler Compiler. @@ -15,83 +16,92 @@ 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 */ +#include +#include "system.h" -%debug -%defines -%locations -%pure-parser -// %error-verbose -%defines -%name-prefix="gram_" +#include -%{ -#include "system.h" #include "complain.h" -#include "muscle_tab.h" +#include "conflicts.h" #include "files.h" #include "getargs.h" -#include "output.h" -#include "symlist.h" #include "gram.h" +#include "muscle_tab.h" +#include "quotearg.h" #include "reader.h" -#include "conflicts.h" +#include "symlist.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) -/* Produce verbose parse errors. */ -#define YYERROR_VERBOSE 1 -#define YYLLOC_DEFAULT(Current, Rhs, N) \ -do { \ - if (N) \ - { \ - Current.first_column = Rhs[1].first_column; \ - Current.first_line = Rhs[1].first_line; \ - Current.last_column = Rhs[N].last_column; \ - Current.last_line = Rhs[N].last_line; \ - } \ - else \ - { \ - Current = Rhs[0]; \ - } \ -} while (0) - -/* Pass the control structure to YYPARSE and YYLEX. */ -#define YYPARSE_PARAM gram_control -#define YYLEX_PARAM gram_control -/* YYPARSE receives GRAM_CONTROL as a void *. Provide a - correctly typed access to it. */ -#define yycontrol ((gram_control_t *) gram_control) - -/* Request detailed parse error messages, and pass them to GRAM_ERROR. - FIXME: depends on the undocumented availability of YYLLOC.t */ +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) - -#define YYPRINT(File, Type, Value) \ - yyprint (File, Type, &Value) -static void yyprint (FILE *file, int type, const yystype *value); - -symbol_class current_class = unknown_sym; -char *current_type = 0; -symbol_t *current_lhs; -location_t current_lhs_location; -assoc_t current_assoc; -int current_prec = 0; -braced_code_t current_braced_code = action_braced_code; + gram_error (&yylloc, Msg) +static void gram_error (location const *, char 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 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; + +#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_" + +%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 { - symbol_t *symbol; - symbol_list_t *list; + symbol *symbol; + symbol_list *list; int integer; - char *string; - assoc_t assoc; + char *chars; + assoc assoc; + uniqstr uniqstr; + unsigned char character; }; /* Define the tokens together with their human representation. */ @@ -106,8 +116,6 @@ braced_code_t current_braced_code = action_braced_code; %token PERCENT_DESTRUCTOR "%destructor" %token PERCENT_PRINTER "%printer" -%token PERCENT_UNION "%union" - %token PERCENT_LEFT "%left" %token PERCENT_RIGHT "%right" %token PERCENT_NONASSOC "%nonassoc" @@ -122,54 +130,79 @@ braced_code_t current_braced_code = action_braced_code; `----------------------*/ %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_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 COLON ":" -%token COMMA "," -%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 TYPE STRING string_content - BRACED_CODE PROLOGUE EPILOGUE epilogue.opt action %type INT -%type ID 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 %% input: - declarations "%%" grammar epilogue.opt - { - yycontrol->errcode = 0; - epilogue_set ($4, @4); - } + prologue_declarations "%%" grammar epilogue.opt ; @@ -177,34 +210,48 @@ input: | Declarations: before the first %%. | `------------------------------------*/ -declarations: +prologue_declarations: /* Nothing */ -| declarations declaration semi_colon.opt +| 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" string_content "," string_content - { muscle_pair_list_grow ("lex_param", $2, $4); } -| "%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" string_content "," string_content - { muscle_pair_list_grow ("parse_param", $2, $4); } -| "%pure-parser" { pure_parser = 1; } -| "%skeleton" string_content { skeleton = $2; } -| "%token-table" { token_table_flag = 1; } -| "%verbose" { report_flag = 1; } -| "%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; } +| "%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: @@ -214,34 +261,72 @@ grammar_declaration: { grammar_start_symbol_set ($2, @2); } -| "%union" BRACED_CODE +| "%destructor" "{...}" symbols.1 + { + 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_free ($3); + } +| "%printer" "{...}" symbols.1 + { + 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_free ($3); + } +| "%default-prec" { - typed = 1; - MUSCLE_INSERT_INT ("stype_line", @2.first_line); - muscle_insert ("stype", $2); + default_prec = true; } -| "%destructor" - { current_braced_code = destructor_braced_code; } - BRACED_CODE symbols.1 +| "%no-default-prec" { - symbol_list_t *list; - for (list = $4; list; list = list->next) - symbol_destructor_set (list->sym, $3, @3); - symbol_list_free ($4); - current_braced_code = action_braced_code; + default_prec = false; } -| "%printer" - { current_braced_code = printer_braced_code; } - BRACED_CODE symbols.1 +; + + +/*----------* + | %union. | + *----------*/ + +%token PERCENT_UNION "%union"; + +union_name: + /* Nothing. */ {} +| ID { muscle_code_grow ("union_name", $1, @1); } +; + +grammar_declaration: + "%union" union_name "{...}" { - symbol_list_t *list; - for (list = $4; list; list = list->next) - symbol_printer_set (list->sym, $3, list->location); - symbol_list_free ($4); - current_braced_code = action_braced_code; + 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 { @@ -255,7 +340,8 @@ symbol_declaration: } | "%type" TYPE symbols.1 { - symbol_list_t *list; + tag_seen = true; + symbol_list *list; for (list = $3; list; list = list->next) symbol_type_set (list->sym, $2, @2); symbol_list_free ($3); @@ -265,7 +351,7 @@ symbol_declaration: precedence_declaration: precedence_declarator type.opt symbols.1 { - symbol_list_t *list; + symbol_list *list; ++current_prec; for (list = $3; list; list = list->next) { @@ -285,11 +371,10 @@ 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. */ - symbols.1: symbol { $$ = symbol_list_new ($1, @1); } | symbols.1 symbol { $$ = symbol_list_prepend ($1, $2, @2); } @@ -300,27 +385,28 @@ 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, @$); @@ -330,9 +416,7 @@ symbol_def: /* One or more symbol definitions. */ symbol_defs.1: symbol_def - {;} | symbol_defs.1 symbol_def - {;} ; @@ -346,15 +430,10 @@ grammar: ; /* As a Bison extension, one can use the grammar declarations in the - body of the grammar. But to remain LALR(1), they must be ended - with a semi-colon. */ + body of the grammar. */ rules_or_grammar_declaration: rules | grammar_declaration ";" - { - if (yacc_flag) - complain_at (@$, _("POSIX forbids declarations in the grammar")); - } | error ";" { yyerrok; @@ -362,21 +441,21 @@ rules_or_grammar_declaration: ; rules: - ID ":" { 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); } @@ -386,87 +465,199 @@ rhs: { grammar_current_rule_merge_set ($3, @3); } ; -symbol: - ID { $$ = $1; } -| string_as_id { $$ = $1; } -; -action: - BRACED_CODE - { $$ = $1; } -; +/*-----------* + | content. | + *-----------*/ -/* A string used as an ID: we have to keep the quotes. */ -string_as_id: +content: STRING +| braceless +; + +/* Some content or "1" by default. */ +content.opt: + /* Nothing. */ { - $$ = symbol_get ($1, @1); - symbol_class_set ($$, token_sym, @1); + static char one[] = "1"; + $$ = one; } +| content ; -/* A string used for its contents. Strip the quotes. */ -string_content: - STRING + +braceless: + "{...}" { - $$ = $1 + 1; - $$[strlen ($$) - 1] = '\0'; - }; + $1[strlen ($1) - 1] = '\n'; + $$ = translate_code ($1 + 1, @1); + } +; -epilogue.opt: - /* Nothing. */ +/*---------------* + | Identifiers. | + *---------------*/ + +/* Identifiers are returned as uniqstr values by the scanner. + Depending on their use, we may need to make them genuine symbols. */ + +id: + ID + { $$ = symbol_from_uniqstr ($1, @1); } +| CHAR { - $$ = xstrdup (""); + $$ = symbol_get (char_name ($1), @1); + symbol_class_set ($$, token_sym, @1, false); + symbol_user_token_number_set ($$, $1, @1); } -| "%%" EPILOGUE +; + +id_colon: + ID_COLON { $$ = symbol_from_uniqstr ($1, @1); } +; + + +symbol: + id +| string_as_id +; + +/* A string used as an ID: quote it. */ +string_as_id: + STRING { - $$ = $2; + $$ = symbol_get (quotearg_style (c_quoting_style, $1), @1); + symbol_class_set ($$, token_sym, @1, false); } ; -semi_colon.opt: +epilogue.opt: /* Nothing. */ -| ";" +| "%%" EPILOGUE + { + muscle_code_grow ("epilogue", translate_code ($2, @2), @2); + gram_scanner_last_string_free (); + } ; + %% -/*------------------------------------------------------------------. -| When debugging the parser, display tokens' locations and values. | -`------------------------------------------------------------------*/ + + +/* Return the location of the left-hand side of a rule whose + right-hand side is RHS[1] ... RHS[N]. Ignore empty nonterminals in + the right-hand side, and return an empty location equal to the end + boundary of RHS[0] if the right-hand side is empty. */ + +static YYLTYPE +lloc_default (YYLTYPE const *rhs, int n) +{ + int i; + YYLTYPE loc; + + /* 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, + since empty nonterminals have the same end as their predecessors. */ + for (i = 1; i <= n; i++) + if (! equal_boundaries (rhs[i].start, rhs[i].end)) + { + loc.start = rhs[i].start; + break; + } + + return loc; +} + + +/* Add a lex-param or a parse-param (depending on TYPE) with + declaration DECL and location LOC. */ + +static void +add_param (char const *type, char *decl, location loc) +{ + static char const alphanum[26 + 26 + 1 + 10] = + "abcdefghijklmnopqrstuvwxyz" + "ABCDEFGHIJKLMNOPQRSTUVWXYZ" + "_" + "0123456789"; + char const *name_start = NULL; + char *p; + + /* 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 '}', 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")); + else + { + char *name; + size_t name_len; + + for (name_len = 1; + memchr (alphanum, name_start[name_len], sizeof alphanum); + name_len++) + continue; + + name = xmalloc (name_len + 1); + memcpy (name, name_start, name_len); + name[name_len] = '\0'; + muscle_pair_list_grow (type, decl, name); + free (name); + } + + gram_scanner_last_string_free (); +} + static void -yyprint (FILE *file, - int type, const yystype *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->string); - break; - - case TYPE: - fprintf (file, " = <%s>", value->string); - break; - - case BRACED_CODE: - case PROLOGUE: - case EPILOGUE: - fprintf (file, " = {{ %s }}", value->string); - break; + complain_at (*loc, "require bison %s, but have %s", + version, PACKAGE_VERSION); + exit (63); } } -void -gram_error (location_t *yylloc, const char *msg) +static void +gram_error (location const *loc, char const *msg) +{ + complain_at (*loc, "%s", msg); +} + +char const * +token_name (int type) +{ + return yytname[YYTRANSLATE (type)]; +} + +static char const * +char_name (char c) { - complain_at (*yylloc, "%s", msg); + if (c == '\'') + return "'\\''"; + else + { + char buf[4]; + buf[0] = '\''; buf[1] = c; buf[2] = '\''; buf[3] = '\0'; + return quotearg_style (escape_quoting_style, buf); + } }