X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/223ff46e4c1f4ed4a9cef3de6961e7220653391b..0c3c1f98eca714602db1c298d010d8068f84dd7f:/src/scan-gram.l diff --git a/src/scan-gram.l b/src/scan-gram.l index 41aefd62..4416730c 100644 --- a/src/scan-gram.l +++ b/src/scan-gram.l @@ -1,5 +1,6 @@ /* Bison Grammar Scanner -*- C -*- - Copyright (C) 2002 Free Software Foundation, Inc. + + Copyright (C) 2002, 2003 Free Software Foundation, Inc. This file is part of Bison, the GNU Compiler Compiler. @@ -19,7 +20,7 @@ 02111-1307 USA */ -%option debug nodefault noyywrap never-interactive +%option debug nodefault nounput noyywrap never-interactive %option prefix="gram_" outfile="lex.yy.c" %{ @@ -42,6 +43,7 @@ scanner_cursor.file = current_file; \ scanner_cursor.line = 1; \ scanner_cursor.column = 1; \ + code_start = scanner_cursor; \ } \ while (0) @@ -96,23 +98,23 @@ scanner_last_string_free (void) Outside of well-formed rules, RULE_LENGTH has an undefined value. */ static int rule_length; -static void handle_dollar (braced_code code_kind, char *cp, location loc); -static void handle_at (braced_code code_kind, char *cp, location loc); +static void handle_dollar (int token_type, char *cp, location loc); +static void handle_at (int token_type, char *cp, location loc); static void handle_syncline (char *args); static int convert_ucn_to_byte (char const *hex_text); -static void unexpected_end_of_file (boundary, char const *); +static void unexpected_eof (boundary, char const *); %} %x SC_COMMENT SC_LINE_COMMENT SC_YACC_COMMENT %x SC_STRING SC_CHARACTER %x SC_AFTER_IDENTIFIER %x SC_ESCAPED_STRING SC_ESCAPED_CHARACTER -%x SC_BRACED_CODE SC_PROLOGUE SC_EPILOGUE +%x SC_PRE_CODE SC_BRACED_CODE SC_PROLOGUE SC_EPILOGUE letter [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_] id {letter}({letter}|[0-9])* directive %{letter}({letter}|[0-9]|-)* -int [0-9]+ +int [0-9]+ /* POSIX says that a tag must be both an id and a C union member, but historically almost any character is allowed in a tag. We disallow @@ -131,15 +133,20 @@ splice (\\[ \f\t\v]*\n)* /* Parent context state, when applicable. */ int context_state IF_LINT (= 0); + /* Token type to return, when applicable. */ + int token_type IF_LINT (= 0); + /* Location of most recent identifier, when applicable. */ - location id_loc IF_LINT (= *loc); + location id_loc IF_LINT (= empty_location); - /* Where containing code started, when applicable. */ - boundary code_start IF_LINT (= loc->start); + /* Where containing code started, when applicable. Its initial + value is relevant only when yylex is invoked in the SC_EPILOGUE + start condition. */ + boundary code_start = scanner_cursor; /* Where containing comment or string or character literal started, when applicable. */ - boundary token_start IF_LINT (= loc->start); + boundary token_start IF_LINT (= scanner_cursor); %} @@ -147,13 +154,18 @@ splice (\\[ \f\t\v]*\n)* | Scanning white space. | `-----------------------*/ - + { [ \f\n\t\v] ; + "," warn_at (*loc, _("stray `,' treated as white space")); /* Comments. */ - "/*" token_start = loc->start; context_state = YY_START; BEGIN SC_YACC_COMMENT; "//".* ; + "/*" { + token_start = loc->start; + context_state = YY_START; + BEGIN SC_YACC_COMMENT; + } /* #line directives are not documented, and may be withdrawn or modified in future versions of Bison. */ @@ -172,7 +184,7 @@ splice (\\[ \f\t\v]*\n)* "%debug" return PERCENT_DEBUG; "%define" return PERCENT_DEFINE; "%defines" return PERCENT_DEFINES; - "%destructor" return PERCENT_DESTRUCTOR; + "%destructor" token_type = PERCENT_DESTRUCTOR; BEGIN SC_PRE_CODE; "%dprec" return PERCENT_DPREC; "%error"[-_]"verbose" return PERCENT_ERROR_VERBOSE; "%expect" return PERCENT_EXPECT; @@ -180,6 +192,7 @@ splice (\\[ \f\t\v]*\n)* "%fixed"[-_]"output"[-_]"files" return PERCENT_YACC; "%glr-parser" return PERCENT_GLR_PARSER; "%left" return PERCENT_LEFT; + "%lex-param" token_type = PERCENT_LEX_PARAM; BEGIN SC_PRE_CODE; "%locations" return PERCENT_LOCATIONS; "%merge" return PERCENT_MERGE; "%name"[-_]"prefix" return PERCENT_NAME_PREFIX; @@ -187,19 +200,18 @@ splice (\\[ \f\t\v]*\n)* "%nonassoc" return PERCENT_NONASSOC; "%nterm" return PERCENT_NTERM; "%output" return PERCENT_OUTPUT; - "%parse-param" return PERCENT_PARSE_PARAM; + "%parse-param" token_type = PERCENT_PARSE_PARAM; BEGIN SC_PRE_CODE; "%prec" rule_length--; return PERCENT_PREC; - "%printer" return PERCENT_PRINTER; + "%printer" token_type = PERCENT_PRINTER; BEGIN SC_PRE_CODE; "%pure"[-_]"parser" return PERCENT_PURE_PARSER; "%right" return PERCENT_RIGHT; - "%lex-param" return PERCENT_LEX_PARAM; "%skeleton" return PERCENT_SKELETON; "%start" return PERCENT_START; "%term" return PERCENT_TOKEN; "%token" return PERCENT_TOKEN; "%token"[-_]"table" return PERCENT_TOKEN_TABLE; "%type" return PERCENT_TYPE; - "%union" return PERCENT_UNION; + "%union" token_type = PERCENT_UNION; BEGIN SC_PRE_CODE; "%verbose" return PERCENT_VERBOSE; "%yacc" return PERCENT_YACC; @@ -211,10 +223,6 @@ splice (\\[ \f\t\v]*\n)* "|" rule_length = 0; return PIPE; ";" return SEMICOLON; - "," { - warn_at (*loc, _("stray `,' treated as white space")); - } - {id} { val->symbol = symbol_get (yytext, *loc); id_loc = *loc; @@ -247,6 +255,7 @@ splice (\\[ \f\t\v]*\n)* /* Code in between braces. */ "{" { STRING_GROW; + token_type = BRACED_CODE; braces_level = 0; code_start = loc->start; BEGIN SC_BRACED_CODE; @@ -264,16 +273,18 @@ splice (\\[ \f\t\v]*\n)* "%%" { static int percent_percent_count; if (++percent_percent_count == 2) - { - code_start = loc->start; - BEGIN SC_EPILOGUE; - } + BEGIN SC_EPILOGUE; return PERCENT_PERCENT; } . { complain_at (*loc, _("invalid character: %s"), quote (yytext)); } + + <> { + loc->start = loc->end = scanner_cursor; + yyterminate (); + } } @@ -312,7 +323,7 @@ splice (\\[ \f\t\v]*\n)* { "*/" BEGIN context_state; .|\n ; - <> unexpected_end_of_file (token_start, "*/"); + <> unexpected_eof (token_start, "*/"); BEGIN context_state; } @@ -323,7 +334,7 @@ splice (\\[ \f\t\v]*\n)* { "*"{splice}"/" STRING_GROW; BEGIN context_state; - <> unexpected_end_of_file (token_start, "*/"); + <> unexpected_eof (token_start, "*/"); BEGIN context_state; } @@ -357,7 +368,7 @@ splice (\\[ \f\t\v]*\n)* } .|\n STRING_GROW; - <> unexpected_end_of_file (token_start, "\""); + <> unexpected_eof (token_start, "\""); BEGIN INITIAL; } /*---------------------------------------------------------------. @@ -368,13 +379,14 @@ splice (\\[ \f\t\v]*\n)* { "'" { + unsigned char last_string_1; STRING_GROW; STRING_FINISH; loc->start = token_start; val->symbol = symbol_get (last_string, *loc); symbol_class_set (val->symbol, token_sym, *loc); - symbol_user_token_number_set (val->symbol, - (unsigned char) last_string[1], *loc); + last_string_1 = last_string[1]; + symbol_user_token_number_set (val->symbol, last_string_1, *loc); STRING_FREE; rule_length++; BEGIN INITIAL; @@ -382,7 +394,7 @@ splice (\\[ \f\t\v]*\n)* } .|\n STRING_GROW; - <> unexpected_end_of_file (token_start, "'"); + <> unexpected_eof (token_start, "'"); BEGIN INITIAL; } @@ -444,7 +456,7 @@ splice (\\[ \f\t\v]*\n)* { "'" STRING_GROW; BEGIN context_state; \\{splice}[^$@\[\]] STRING_GROW; - <> unexpected_end_of_file (token_start, "'"); + <> unexpected_eof (token_start, "'"); BEGIN context_state; } @@ -457,7 +469,10 @@ splice (\\[ \f\t\v]*\n)* { "\"" STRING_GROW; BEGIN context_state; \\{splice}[^$@\[\]] STRING_GROW; - <> unexpected_end_of_file (token_start, "\""); + <> { + unexpected_eof (token_start, "\""); + BEGIN context_state; + } } @@ -493,6 +508,41 @@ splice (\\[ \f\t\v]*\n)* } + /*---------------------------------------------------------------. + | Scanning after %union etc., possibly followed by white space. | + | For %union only, allow arbitrary C code to appear before the | + | following brace, as an extension to POSIX. | + `---------------------------------------------------------------*/ + + +{ + . { + bool valid = yytext[0] == '{' || token_type == PERCENT_UNION; + scanner_cursor.column -= mbsnwidth (yytext, yyleng, 0); + yyless (0); + + if (valid) + { + braces_level = -1; + code_start = loc->start; + BEGIN SC_BRACED_CODE; + } + else + { + complain_at (*loc, _("missing `{' in `%s'"), + token_name (token_type)); + obstack_sgrow (&obstack_for_string, "{}"); + STRING_FINISH; + val->chars = last_string; + BEGIN INITIAL; + return token_type; + } + } + + <> unexpected_eof (scanner_cursor, "{}"); BEGIN INITIAL; +} + + /*---------------------------------------------------------------. | Scanning some code in braces (%union and actions). The initial | | "{" is already eaten. | @@ -503,16 +553,35 @@ splice (\\[ \f\t\v]*\n)* "{"|"<"{splice}"%" STRING_GROW; braces_level++; "%"{splice}">" STRING_GROW; braces_level--; "}" { - STRING_GROW; - braces_level--; - if (braces_level < 0) + bool outer_brace = --braces_level < 0; + + /* As an undocumented Bison extension, append `;' before the last + brace in braced code, so that the user code can omit trailing + `;'. But do not append `;' if emulating Yacc, since Yacc does + not append one. + + FIXME: Bison should warn if a semicolon seems to be necessary + here, and should omit the semicolon if it seems unnecessary + (e.g., after ';', '{', or '}', each followed by comments or + white space). Such a warning shouldn't depend on --yacc; it + should depend on a new --pedantic option, which would cause + Bison to warn if it detects an extension to POSIX. --pedantic + should also diagnose other Bison extensions like %yacc. + Perhaps there should also be a GCC-style --pedantic-errors + option, so that such warnings are diagnosed as errors. */ + if (outer_brace && token_type == BRACED_CODE && ! yacc_flag) + obstack_1grow (&obstack_for_string, ';'); + + obstack_1grow (&obstack_for_string, '}'); + + if (outer_brace) { STRING_FINISH; + rule_length++; loc->start = code_start; val->chars = last_string; - rule_length++; BEGIN INITIAL; - return BRACED_CODE; + return token_type; } } @@ -520,12 +589,10 @@ splice (\\[ \f\t\v]*\n)* (as `<' `<%'). */ "<"{splice}"<" STRING_GROW; - "$"("<"{tag}">")?(-?[0-9]+|"$") { handle_dollar (current_braced_code, - yytext, *loc); } - "@"(-?[0-9]+|"$") { handle_at (current_braced_code, - yytext, *loc); } + "$"("<"{tag}">")?(-?[0-9]+|"$") handle_dollar (token_type, yytext, *loc); + "@"(-?[0-9]+|"$") handle_at (token_type, yytext, *loc); - <> unexpected_end_of_file (code_start, "}"); + <> unexpected_eof (code_start, "}"); BEGIN INITIAL; } @@ -543,7 +610,7 @@ splice (\\[ \f\t\v]*\n)* return PROLOGUE; } - <> unexpected_end_of_file (code_start, "%}"); + <> unexpected_eof (code_start, "%}"); BEGIN INITIAL; } @@ -625,14 +692,14 @@ adjust_location (location *loc, char const *token, size_t size) static size_t no_cr_read (FILE *fp, char *buf, size_t size) { - size_t s = fread (buf, 1, size, fp); - if (s) + size_t bytes_read = fread (buf, 1, size, fp); + if (bytes_read) { - char *w = memchr (buf, '\r', s); + char *w = memchr (buf, '\r', bytes_read); if (w) { char const *r = ++w; - char const *lim = buf + s; + char const *lim = buf + bytes_read; for (;;) { @@ -661,7 +728,7 @@ no_cr_read (FILE *fp, char *buf, size_t size) } } - return s; + return bytes_read; } @@ -673,12 +740,15 @@ no_cr_read (FILE *fp, char *buf, size_t size) | Output to OBSTACK_FOR_STRING a reference to this semantic value. | `------------------------------------------------------------------*/ -static inline void +static inline bool handle_action_dollar (char *text, location loc) { const char *type_name = NULL; char *cp = text + 1; + if (! current_rule) + return false; + /* Get the type name if explicit. */ if (*cp == '<') { @@ -724,44 +794,40 @@ handle_action_dollar (char *text, location loc) else complain_at (loc, _("integer out of range: %s"), quote (text)); } -} - - -/*---------------------------------------------------------------. -| TEXT is expected to be $$ in some code associated to a symbol: | -| destructor or printer. | -`---------------------------------------------------------------*/ -static inline void -handle_symbol_code_dollar (char *text, location loc) -{ - char *cp = text + 1; - if (*cp == '$') - obstack_sgrow (&obstack_for_string, "]b4_dollar_dollar["); - else - complain_at (loc, _("invalid value: %s"), quote (text)); + return true; } /*-----------------------------------------------------------------. | Dispatch onto handle_action_dollar, or handle_destructor_dollar, | -| depending upon CODE_KIND. | +| depending upon TOKEN_TYPE. | `-----------------------------------------------------------------*/ static void -handle_dollar (braced_code braced_code_kind, char *text, location loc) +handle_dollar (int token_type, char *text, location loc) { - switch (braced_code_kind) + switch (token_type) { - case action_braced_code: - handle_action_dollar (text, loc); + case BRACED_CODE: + if (handle_action_dollar (text, loc)) + return; break; - case destructor_braced_code: - case printer_braced_code: - handle_symbol_code_dollar (text, loc); + case PERCENT_DESTRUCTOR: + case PERCENT_PRINTER: + if (text[1] == '$') + { + obstack_sgrow (&obstack_for_string, "]b4_dollar_dollar["); + return; + } + break; + + default: break; } + + complain_at (loc, _("invalid value: %s"), quote (text)); } @@ -770,16 +836,17 @@ handle_dollar (braced_code braced_code_kind, char *text, location loc) | OBSTACK_FOR_STRING a reference to this location. | `------------------------------------------------------*/ -static inline void +static inline bool handle_action_at (char *text, location loc) { char *cp = text + 1; locations_flag = 1; + if (! current_rule) + return false; + if (*cp == '$') - { - obstack_sgrow (&obstack_for_string, "]b4_lhs_location["); - } + obstack_sgrow (&obstack_for_string, "]b4_lhs_location["); else { long num; @@ -795,22 +862,8 @@ handle_action_at (char *text, location loc) else complain_at (loc, _("integer out of range: %s"), quote (text)); } -} - -/*---------------------------------------------------------------. -| TEXT is expected to be @$ in some code associated to a symbol: | -| destructor or printer. | -`---------------------------------------------------------------*/ - -static inline void -handle_symbol_code_at (char *text, location loc) -{ - char *cp = text + 1; - if (*cp == '$') - obstack_sgrow (&obstack_for_string, "]b4_at_dollar["); - else - complain_at (loc, _("invalid value: %s"), quote (text)); + return true; } @@ -820,19 +873,28 @@ handle_symbol_code_at (char *text, location loc) `-------------------------------------------------------------------*/ static void -handle_at (braced_code braced_code_kind, char *text, location loc) +handle_at (int token_type, char *text, location loc) { - switch (braced_code_kind) + switch (token_type) { - case action_braced_code: + case BRACED_CODE: handle_action_at (text, loc); + return; + + case PERCENT_DESTRUCTOR: + case PERCENT_PRINTER: + if (text[1] == '$') + { + obstack_sgrow (&obstack_for_string, "]b4_at_dollar["); + return; + } break; - case destructor_braced_code: - case printer_braced_code: - handle_symbol_code_at (text, loc); + default: break; } + + complain_at (loc, _("invalid value: %s"), quote (text)); } @@ -912,25 +974,15 @@ handle_syncline (char *args) /*------------------------------------------------------------------------. | Report an unexpected EOF in a token or comment starting at START. | | An end of file was encountered and the expected TOKEN_END was missing. | -| After reporting the problem, pretend that TOKEN_END was found. | `------------------------------------------------------------------------*/ static void -unexpected_end_of_file (boundary start, char const *token_end) +unexpected_eof (boundary start, char const *token_end) { - size_t i = strlen (token_end); - location loc; loc.start = start; loc.end = scanner_cursor; complain_at (loc, _("missing `%s' at end of file"), token_end); - - /* Adjust scanner cursor so that any later message does not count - the characters about to be inserted. */ - scanner_cursor.column -= i; - - while (i != 0) - unput (token_end[--i]); }