From fa34bb08f50f4611d08865d00e00d46e63b77e06 Mon Sep 17 00:00:00 2001 From: Reuben Thomas Date: Mon, 13 Sep 2010 20:13:47 +0200 Subject: [PATCH 10/10] Add RE_PLAIN flag to match plain text patterns. --- lib/regcomp.c | 139 +++++++++++++++++++++++++++++---------------------------- lib/regex.h | 4 ++ 2 files changed, 75 insertions(+), 68 deletions(-) diff --git a/lib/regcomp.c b/lib/regcomp.c index 7eff569..d15c179 100644 --- a/lib/regcomp.c +++ b/lib/regcomp.c @@ -1793,7 +1793,7 @@ peek_token (re_token_t *token, re_string_t *input, reg_syntax_t syntax) return 1; } #endif - if (c == '\\') + if (!(syntax & RE_PLAIN) && c == '\\') { unsigned char c2; if (re_string_cur_idx (input) + 1 >= re_string_length (input)) @@ -1929,76 +1929,79 @@ peek_token (re_token_t *token, re_string_t *input, reg_syntax_t syntax) #endif token->word_char = IS_WORD_CHAR (token->opr.c); - switch (c) + if (!(syntax & RE_PLAIN)) { - case '\n': - if (syntax & RE_NEWLINE_ALT) - token->type = OP_ALT; - break; - case '|': - if (!(syntax & RE_LIMITED_OPS) && (syntax & RE_NO_BK_VBAR)) - token->type = OP_ALT; - break; - case '*': - token->type = OP_DUP_ASTERISK; - break; - case '+': - if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_BK_PLUS_QM)) - token->type = OP_DUP_PLUS; - break; - case '?': - if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_BK_PLUS_QM)) - token->type = OP_DUP_QUESTION; - break; - case '{': - if ((syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES)) - token->type = OP_OPEN_DUP_NUM; - break; - case '}': - if ((syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES)) - token->type = OP_CLOSE_DUP_NUM; - break; - case '(': - if (syntax & RE_NO_BK_PARENS) - token->type = OP_OPEN_SUBEXP; - break; - case ')': - if (syntax & RE_NO_BK_PARENS) - token->type = OP_CLOSE_SUBEXP; - break; - case '[': - token->type = OP_OPEN_BRACKET; - break; - case '.': - token->type = OP_PERIOD; - break; - case '^': - if (!(syntax & (RE_CONTEXT_INDEP_ANCHORS | RE_CARET_ANCHORS_HERE)) && - re_string_cur_idx (input) != 0) + switch (c) { - char prev = re_string_peek_byte (input, -1); - if (!(syntax & RE_NEWLINE_ALT) || prev != '\n') - break; - } - token->type = ANCHOR; - token->opr.ctx_type = LINE_FIRST; - break; - case '$': - if (!(syntax & RE_CONTEXT_INDEP_ANCHORS) && - re_string_cur_idx (input) + 1 != re_string_length (input)) - { - re_token_t next; - re_string_skip_bytes (input, 1); - peek_token (&next, input, syntax); - re_string_skip_bytes (input, -1); - if (next.type != OP_ALT && next.type != OP_CLOSE_SUBEXP) - break; + case '\n': + if (syntax & RE_NEWLINE_ALT) + token->type = OP_ALT; + break; + case '|': + if (!(syntax & RE_LIMITED_OPS) && (syntax & RE_NO_BK_VBAR)) + token->type = OP_ALT; + break; + case '*': + token->type = OP_DUP_ASTERISK; + break; + case '+': + if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_BK_PLUS_QM)) + token->type = OP_DUP_PLUS; + break; + case '?': + if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_BK_PLUS_QM)) + token->type = OP_DUP_QUESTION; + break; + case '{': + if ((syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES)) + token->type = OP_OPEN_DUP_NUM; + break; + case '}': + if ((syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES)) + token->type = OP_CLOSE_DUP_NUM; + break; + case '(': + if (syntax & RE_NO_BK_PARENS) + token->type = OP_OPEN_SUBEXP; + break; + case ')': + if (syntax & RE_NO_BK_PARENS) + token->type = OP_CLOSE_SUBEXP; + break; + case '[': + token->type = OP_OPEN_BRACKET; + break; + case '.': + token->type = OP_PERIOD; + break; + case '^': + if (!(syntax & (RE_CONTEXT_INDEP_ANCHORS | RE_CARET_ANCHORS_HERE)) && + re_string_cur_idx (input) != 0) + { + char prev = re_string_peek_byte (input, -1); + if (!(syntax & RE_NEWLINE_ALT) || prev != '\n') + break; + } + token->type = ANCHOR; + token->opr.ctx_type = LINE_FIRST; + break; + case '$': + if (!(syntax & RE_CONTEXT_INDEP_ANCHORS) && + re_string_cur_idx (input) + 1 != re_string_length (input)) + { + re_token_t next; + re_string_skip_bytes (input, 1); + peek_token (&next, input, syntax); + re_string_skip_bytes (input, -1); + if (next.type != OP_ALT && next.type != OP_CLOSE_SUBEXP) + break; + } + token->type = ANCHOR; + token->opr.ctx_type = LINE_LAST; + break; + default: + break; } - token->type = ANCHOR; - token->opr.ctx_type = LINE_LAST; - break; - default: - break; } return 1; } diff --git a/lib/regex.h b/lib/regex.h index 89a8143..8fab9f6 100644 --- a/lib/regex.h +++ b/lib/regex.h @@ -227,6 +227,10 @@ typedef unsigned long int reg_syntax_t; re_compile_pattern. */ # define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1) +/* If this bit is set, then all special characters are ignored + by re_compile_pattern. */ +# define RE_PLAIN (RE_NO_SUB << 1) + #endif /* defined __USE_GNU_REGEX */ /* This global variable defines the particular regexp syntax to use (for -- 1.7.0.4