X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/07c0db18b4a795a3a35a4d98b3d001bfc7d4e1c1..235892350f6547e5c6a350b85561eda14409a0b5:/src/scan-gram.l diff --git a/src/scan-gram.l b/src/scan-gram.l index 73eb3e80..5e78cb9b 100644 --- a/src/scan-gram.l +++ b/src/scan-gram.l @@ -1,7 +1,6 @@ /* Bison Grammar Scanner -*- C -*- - Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 Free - Software Foundation, Inc. + Copyright (C) 2002-2012 Free Software Foundation, Inc. This file is part of Bison, the GNU Compiler Compiler. @@ -37,6 +36,7 @@ #include "reader.h" #include "uniqstr.h" +#include #include #include @@ -88,11 +88,11 @@ static void unexpected_newline (boundary, char const *); /* Strings and characters in directives/rules. */ %x SC_ESCAPED_STRING SC_ESCAPED_CHARACTER /* A identifier was just read in directives/rules. Special state - to capture the sequence `identifier :'. */ + to capture the sequence 'identifier :'. */ %x SC_AFTER_IDENTIFIER /* Three types of user code: - - prologue (code between `%{' `%}' in the first section, before %%); + - prologue (code between '%{' '%}' in the first section, before %%); - actions, printers, union, etc, (between braced in the middle section); - epilogue (everything after the second %%). */ %x SC_PROLOGUE SC_BRACED_CODE SC_EPILOGUE @@ -103,9 +103,9 @@ static void unexpected_newline (boundary, char const *); /* Bracketed identifiers support. */ %x SC_BRACKETED_ID SC_RETURN_BRACKETED_ID -letter [-.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_] -id {letter}({letter}|[0-9])* -directive %{id} +letter [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_] +notletter [^.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]{-}[%\{] +id {letter}({letter}|[-0-9])* int [0-9]+ /* POSIX says that a tag must be both an id and a C union member, but @@ -120,13 +120,13 @@ splice (\\[ \f\t\v]*\n)* %% %{ /* Nesting level of the current code in braces. */ - int braces_level IF_LINT (= 0); + int braces_level PACIFY_CC (= 0); /* Parent context state, when applicable. */ - int context_state IF_LINT (= 0); + int context_state PACIFY_CC (= 0); /* Location of most recent identifier, when applicable. */ - location id_loc IF_LINT (= empty_location); + location id_loc PACIFY_CC (= empty_location); /* Where containing code started, when applicable. Its initial value is relevant only when yylex is invoked in the SC_EPILOGUE @@ -135,7 +135,7 @@ splice (\\[ \f\t\v]*\n)* /* Where containing comment or string or character literal started, when applicable. */ - boundary token_start IF_LINT (= scanner_cursor); + boundary token_start PACIFY_CC (= scanner_cursor); %} @@ -146,9 +146,9 @@ splice (\\[ \f\t\v]*\n)* { /* Comments and white space. */ - "," warn_at (*loc, _("stray `,' treated as white space")); + "," warn_at (*loc, _("stray ',' treated as white space")); [ \f\n\t\v] | - "//".* ; + "//".* continue; "/*" { token_start = loc->start; context_state = YY_START; @@ -157,7 +157,7 @@ splice (\\[ \f\t\v]*\n)* /* #line directives are not documented, and may be withdrawn or modified in future versions of Bison. */ - ^"#line "{int}" \"".*"\"\n" { + ^"#line "{int}(" \"".*"\"")?"\n" { handle_syncline (yytext + sizeof "#line " - 1, *loc); } } @@ -218,7 +218,7 @@ splice (\\[ \f\t\v]*\n)* "%verbose" return PERCENT_VERBOSE; "%yacc" return PERCENT_YACC; - {directive} { + "%"{id}|"%"{notletter}([[:graph:]])+ { complain_at (*loc, _("invalid directive: %s"), quote (yytext)); } @@ -290,8 +290,10 @@ splice (\\[ \f\t\v]*\n)* BEGIN SC_BRACKETED_ID; } - . { - complain_at (*loc, _("invalid character: %s"), quote (yytext)); + [^\[%A-Za-z0-9_<>{}\"\'*;|=/, \f\n\t\v]+|. { + complain_at (*loc, "%s: %s", + ngettext ("invalid character", "invalid characters", yyleng), + quote_mem (yytext, yyleng)); } <> { @@ -373,10 +375,14 @@ splice (\\[ \f\t\v]*\n)* else complain_at (*loc, _("an identifier expected")); } - . { - complain_at (*loc, _("invalid character in bracketed name: %s"), - quote (yytext)); + + [^\].A-Za-z0-9_/ \f\n\t\v]+|. { + complain_at (*loc, "%s: %s", + ngettext ("invalid character in bracketed name", + "invalid characters in bracketed name", yyleng), + quote_mem (yytext, yyleng)); } + <> { BEGIN bracketed_id_context_state; unexpected_eof (bracketed_id_start, "]"); @@ -397,19 +403,19 @@ splice (\\[ \f\t\v]*\n)* /*---------------------------------------------------------------. - | Scanning a Yacc comment. The initial `/ *' is already eaten. | + | Scanning a Yacc comment. The initial '/ *' is already eaten. | `---------------------------------------------------------------*/ { "*/" BEGIN context_state; - .|\n ; + .|\n continue; <> unexpected_eof (token_start, "*/"); BEGIN context_state; } /*------------------------------------------------------------. - | Scanning a C comment. The initial `/ *' is already eaten. | + | Scanning a C comment. The initial '/ *' is already eaten. | `------------------------------------------------------------*/ @@ -420,7 +426,7 @@ splice (\\[ \f\t\v]*\n)* /*--------------------------------------------------------------. - | Scanning a line comment. The initial `//' is already eaten. | + | Scanning a line comment. The initial '//' is already eaten. | `--------------------------------------------------------------*/ @@ -521,10 +527,9 @@ splice (\\[ \f\t\v]*\n)* { \\[0-7]{1,3} { unsigned long int c = strtoul (yytext + 1, NULL, 8); - if (UCHAR_MAX < c) - complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext)); - else if (! c) - complain_at (*loc, _("invalid null character: %s"), quote (yytext)); + if (!c || UCHAR_MAX < c) + complain_at (*loc, _("invalid number after \\-escape: %s"), + yytext+1); else obstack_1grow (&obstack_for_string, c); } @@ -532,10 +537,9 @@ splice (\\[ \f\t\v]*\n)* \\x[0-9abcdefABCDEF]+ { verify (UCHAR_MAX < ULONG_MAX); unsigned long int c = strtoul (yytext + 2, NULL, 16); - if (UCHAR_MAX < c) - complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext)); - else if (! c) - complain_at (*loc, _("invalid null character: %s"), quote (yytext)); + if (!c || UCHAR_MAX < c) + complain_at (*loc, _("invalid number after \\-escape: %s"), + yytext+1); else obstack_1grow (&obstack_for_string, c); } @@ -553,16 +557,20 @@ splice (\\[ \f\t\v]*\n)* \\(u|U[0-9abcdefABCDEF]{4})[0-9abcdefABCDEF]{4} { int c = convert_ucn_to_byte (yytext); - if (c < 0) - complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext)); - else if (! c) - complain_at (*loc, _("invalid null character: %s"), quote (yytext)); + if (c <= 0) + complain_at (*loc, _("invalid number after \\-escape: %s"), + yytext+1); else obstack_1grow (&obstack_for_string, c); } \\(.|\n) { - complain_at (*loc, _("unrecognized escape sequence: %s"), quote (yytext)); - STRING_GROW; + char const *p = yytext + 1; + /* Quote only if escaping won't make the character visible. */ + if (c_isspace ((unsigned char) *p) && c_isprint ((unsigned char) *p)) + p = quote (p); + else + p = quotearg_style_mem (escape_quoting_style, p, 1); + complain_at (*loc, _("invalid character after \\-escape: %s"), p); } } @@ -646,8 +654,8 @@ splice (\\[ \f\t\v]*\n)* } } - /* Tokenize `<<%' correctly (as `<<' `%') rather than incorrrectly - (as `<' `<%'). */ + /* Tokenize '<<%' correctly (as '<<' '%') rather than incorrrectly + (as '<' '<%'). */ "<"{splice}"<" STRING_GROW; <> { @@ -837,23 +845,27 @@ convert_ucn_to_byte (char const *ucn) } -/*----------------------------------------------------------------. -| Handle `#line INT "FILE"'. ARGS has already skipped `#line '. | -`----------------------------------------------------------------*/ +/*---------------------------------------------------------------------. +| Handle '#line INT( "FILE")?\n'. ARGS has already skipped '#line '. | +`---------------------------------------------------------------------*/ static void handle_syncline (char *args, location loc) { - char *after_num; - unsigned long int lineno = strtoul (args, &after_num, 10); - char *file = strchr (after_num, '"') + 1; - *strchr (file, '"') = '\0'; + char *file; + unsigned long int lineno = strtoul (args, &file, 10); if (INT_MAX <= lineno) { warn_at (loc, _("line number overflow")); lineno = INT_MAX; } - current_file = uniqstr_new (file); + + file = mbschr (file, '"'); + if (file) + { + *mbschr (file + 1, '"') = '\0'; + current_file = uniqstr_new (file + 1); + } boundary_set (&scanner_cursor, current_file, lineno, 1); } @@ -870,6 +882,10 @@ unexpected_end (boundary start, char const *msgid, char const *token_end) location loc; loc.start = start; loc.end = scanner_cursor; + token_end = quote (token_end); + // Instead of '\'', display "'". + if (!strcmp (token_end, "'\\''")) + token_end = "\"'\""; complain_at (loc, _(msgid), token_end); } @@ -882,7 +898,7 @@ unexpected_end (boundary start, char const *msgid, char const *token_end) static void unexpected_eof (boundary start, char const *token_end) { - unexpected_end (start, N_("missing `%s' at end of file"), token_end); + unexpected_end (start, N_("missing %s at end of file"), token_end); } @@ -893,7 +909,7 @@ unexpected_eof (boundary start, char const *token_end) static void unexpected_newline (boundary start, char const *token_end) { - unexpected_end (start, N_("missing `%s' at end of line"), token_end); + unexpected_end (start, N_("missing %s at end of line"), token_end); }