X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/c046698e6e98aefa7f234b8035fe4cf20ce5d05d..ac9b0e954b1d3aed514a3bbd363da1514202af0f:/src/scan-gram.l?ds=sidebyside diff --git a/src/scan-gram.l b/src/scan-gram.l index b37b29b0..0c12cbaa 100644 --- a/src/scan-gram.l +++ b/src/scan-gram.l @@ -55,9 +55,21 @@ static boundary scanner_cursor; static size_t no_cr_read (FILE *, char *, size_t); #define YY_INPUT(buf, result, size) ((result) = no_cr_read (yyin, buf, size)) +#define ROLLBACK_CURRENT_TOKEN \ + do { \ + scanner_cursor.column -= mbsnwidth (yytext, yyleng, 0); \ + yyless (0); \ + } while (0) + /* A string representing the most recently saved token. */ static char *last_string; +/* Bracketed identifier. */ +static uniqstr bracketed_id_str = 0; +static location bracketed_id_loc; +static boundary bracketed_id_start; +static int bracketed_id_context_state = 0; + void gram_scanner_last_string_free (void) { @@ -88,6 +100,8 @@ static void unexpected_newline (boundary, char const *); %x SC_COMMENT SC_LINE_COMMENT /* Strings and characters in code. */ %x SC_STRING SC_CHARACTER + /* Bracketed identifiers support. */ +%x SC_BRACKETED_ID SC_RETURN_BRACKETED_ID letter [-.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_] id {letter}({letter}|[0-9])* @@ -129,7 +143,7 @@ splice (\\[ \f\t\v]*\n)* | Scanning white space. | `-----------------------*/ - + { /* Comments and white space. */ "," warn_at (*loc, _("stray `,' treated as white space")); @@ -161,48 +175,48 @@ splice (\\[ \f\t\v]*\n)* { - "%binary" return PERCENT_NONASSOC; + "%binary" return PERCENT_NONASSOC; "%code" return PERCENT_CODE; - "%debug" return PERCENT_DEBUG; - "%default"[-_]"prec" return PERCENT_DEFAULT_PREC; - "%define" return PERCENT_DEFINE; - "%defines" return PERCENT_DEFINES; - "%destructor" return PERCENT_DESTRUCTOR; - "%dprec" return PERCENT_DPREC; - "%error"[-_]"verbose" return PERCENT_ERROR_VERBOSE; - "%expect" return PERCENT_EXPECT; - "%expect"[-_]"rr" return PERCENT_EXPECT_RR; - "%file-prefix" return PERCENT_FILE_PREFIX; + "%debug" return PERCENT_DEBUG; + "%default"[-_]"prec" return PERCENT_DEFAULT_PREC; + "%define" return PERCENT_DEFINE; + "%defines" return PERCENT_DEFINES; + "%destructor" return PERCENT_DESTRUCTOR; + "%dprec" return PERCENT_DPREC; + "%error"[-_]"verbose" return PERCENT_ERROR_VERBOSE; + "%expect" return PERCENT_EXPECT; + "%expect"[-_]"rr" return PERCENT_EXPECT_RR; + "%file-prefix" return PERCENT_FILE_PREFIX; "%fixed"[-_]"output"[-_]"files" return PERCENT_YACC; - "%initial-action" return PERCENT_INITIAL_ACTION; - "%glr-parser" return PERCENT_GLR_PARSER; - "%language" return PERCENT_LANGUAGE; - "%left" return PERCENT_LEFT; - "%lex-param" return PERCENT_LEX_PARAM; - "%locations" return PERCENT_LOCATIONS; - "%merge" return PERCENT_MERGE; - "%name"[-_]"prefix" return PERCENT_NAME_PREFIX; - "%no"[-_]"default"[-_]"prec" return PERCENT_NO_DEFAULT_PREC; - "%no"[-_]"lines" return PERCENT_NO_LINES; - "%nonassoc" return PERCENT_NONASSOC; - "%nondeterministic-parser" return PERCENT_NONDETERMINISTIC_PARSER; - "%nterm" return PERCENT_NTERM; - "%output" return PERCENT_OUTPUT; - "%parse-param" return PERCENT_PARSE_PARAM; - "%prec" return PERCENT_PREC; - "%printer" return PERCENT_PRINTER; - "%pure"[-_]"parser" return PERCENT_PURE_PARSER; - "%require" return PERCENT_REQUIRE; - "%right" return PERCENT_RIGHT; - "%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; - "%verbose" return PERCENT_VERBOSE; - "%yacc" return PERCENT_YACC; + "%initial-action" return PERCENT_INITIAL_ACTION; + "%glr-parser" return PERCENT_GLR_PARSER; + "%language" return PERCENT_LANGUAGE; + "%left" return PERCENT_LEFT; + "%lex-param" return PERCENT_LEX_PARAM; + "%locations" return PERCENT_LOCATIONS; + "%merge" return PERCENT_MERGE; + "%name"[-_]"prefix" return PERCENT_NAME_PREFIX; + "%no"[-_]"default"[-_]"prec" return PERCENT_NO_DEFAULT_PREC; + "%no"[-_]"lines" return PERCENT_NO_LINES; + "%nonassoc" return PERCENT_NONASSOC; + "%nondeterministic-parser" return PERCENT_NONDETERMINISTIC_PARSER; + "%nterm" return PERCENT_NTERM; + "%output" return PERCENT_OUTPUT; + "%parse-param" return PERCENT_PARSE_PARAM; + "%prec" return PERCENT_PREC; + "%printer" return PERCENT_PRINTER; + "%pure"[-_]"parser" return PERCENT_PURE_PARSER; + "%require" return PERCENT_REQUIRE; + "%right" return PERCENT_RIGHT; + "%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; + "%verbose" return PERCENT_VERBOSE; + "%yacc" return PERCENT_YACC; {directive} { complain_at (*loc, _("invalid directive: %s"), quote (yytext)); @@ -217,6 +231,7 @@ splice (\\[ \f\t\v]*\n)* {id} { val->uniqstr = uniqstr_new (yytext); id_loc = *loc; + bracketed_id_str = NULL; BEGIN SC_AFTER_IDENTIFIER; } @@ -229,7 +244,13 @@ splice (\\[ \f\t\v]*\n)* return INT; } - /* Characters. We don't check there is only one. */ + /* Identifiers may not start with a digit. Yet, don't silently + accept "1FOO" as "1 FOO". */ + {int}{id} { + complain_at (*loc, _("invalid identifier: %s"), quote (yytext)); + } + + /* Characters. */ "'" STRING_GROW; token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER; /* Strings. */ @@ -262,6 +283,13 @@ splice (\\[ \f\t\v]*\n)* return PERCENT_PERCENT; } + "[" { + bracketed_id_str = NULL; + bracketed_id_start = loc->start; + bracketed_id_context_state = YY_START; + BEGIN SC_BRACKETED_ID; + } + . { complain_at (*loc, _("invalid character: %s"), quote (yytext)); } @@ -279,25 +307,94 @@ splice (\\[ \f\t\v]*\n)* { + "[" { + if (bracketed_id_str) + { + ROLLBACK_CURRENT_TOKEN; + BEGIN SC_RETURN_BRACKETED_ID; + *loc = id_loc; + return ID; + } + else + { + bracketed_id_start = loc->start; + bracketed_id_context_state = YY_START; + BEGIN SC_BRACKETED_ID; + } + } ":" { + BEGIN (bracketed_id_str ? SC_RETURN_BRACKETED_ID : INITIAL); *loc = id_loc; - BEGIN INITIAL; return ID_COLON; } . { - scanner_cursor.column -= mbsnwidth (yytext, yyleng, 0); - yyless (0); + ROLLBACK_CURRENT_TOKEN; + BEGIN (bracketed_id_str ? SC_RETURN_BRACKETED_ID : INITIAL); *loc = id_loc; - BEGIN INITIAL; return ID; } <> { + BEGIN (bracketed_id_str ? SC_RETURN_BRACKETED_ID : INITIAL); *loc = id_loc; - BEGIN INITIAL; return ID; } } + /*--------------------------------. + | Scanning bracketed identifiers. | + `--------------------------------*/ + + +{ + {id} { + if (bracketed_id_str) + { + complain_at (*loc, _("unexpected identifier in bracketed name: %s"), + quote (yytext)); + } + else + { + bracketed_id_str = uniqstr_new (yytext); + bracketed_id_loc = *loc; + } + } + "]" { + BEGIN bracketed_id_context_state; + if (bracketed_id_str) + { + if (INITIAL == bracketed_id_context_state) + { + val->uniqstr = bracketed_id_str; + bracketed_id_str = 0; + *loc = bracketed_id_loc; + return BRACKETED_ID; + } + } + else + complain_at (*loc, _("an identifier expected")); + } + . { + complain_at (*loc, _("invalid character in bracketed name: %s"), + quote (yytext)); + } + <> { + BEGIN bracketed_id_context_state; + unexpected_eof (bracketed_id_start, "]"); + } +} + + +{ + . { + ROLLBACK_CURRENT_TOKEN; + val->uniqstr = bracketed_id_str; + bracketed_id_str = 0; + *loc = bracketed_id_loc; + BEGIN INITIAL; + return BRACKETED_ID; + } +} + /*---------------------------------------------------------------. | Scanning a Yacc comment. The initial `/ *' is already eaten. | @@ -368,24 +465,40 @@ splice (\\[ \f\t\v]*\n)* { "'"|"\n" { - if (yytext[0] == '\n') - unexpected_newline (token_start, "'"); STRING_GROW; STRING_FINISH; loc->start = token_start; val->character = last_string[1]; + { + /* FIXME: Eventually, make these errors. */ + size_t length = strlen (last_string); + if (strlen (last_string) < 3) + warn_at (*loc, _("empty character literal")); + else if (strlen (last_string) > 3) + warn_at (*loc, _("extra characters in character literal")); + } + if (yytext[0] == '\n') + unexpected_newline (token_start, "'"); STRING_FREE; BEGIN INITIAL; return CHAR; } <> { - unexpected_eof (token_start, "'"); STRING_FINISH; loc->start = token_start; - if (strlen (last_string) > 1) - val->character = last_string[1]; - else - val->character = last_string[0]; + { + size_t length = strlen (last_string); + /* FIXME: Eventually, make these errors. */ + if (length < 2) + warn_at (*loc, _("empty character literal")); + else if (length > 2) + warn_at (*loc, _("extra characters in character literal")); + if (length > 1) + val->character = last_string[1]; + else + val->character = last_string[0]; + } + unexpected_eof (token_start, "'"); STRING_FREE; BEGIN INITIAL; return CHAR;