From 94ed3e615b89d7f94e3f05aa957523a884dd4ec1 Mon Sep 17 00:00:00 2001 From: Norihiro Tanaka Date: Sun, 13 Jan 2019 07:53:32 +0900 Subject: [PATCH] grep: speed up multiple word matching grep uses its KWset matcher for multiple word matching, but that is very slow when most of the parts matched to a pattern are not words. So, if the first match to a pattern is not a word, use the grep matcher to match for its line. Note that when START_PTR is set, the grep matcher uses the regex matcher which is very slow to match words. Therefore, we use the grep matcher when only START_PTR is NULL. * src/kwsearch.c (Fexecute): If an initial match is incomplete because not on a word boundary, use the grep matcher to find a matching line. --- src/kwsearch.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/src/kwsearch.c b/src/kwsearch.c index f121816..7644350 100644 --- a/src/kwsearch.c +++ b/src/kwsearch.c @@ -250,6 +250,23 @@ Fexecute (void *vcp, char const *buf, size_t size, size_t *match_size, else goto success; } + if (!start_ptr && !localeinfo.multibyte) + { + if (! kwsearch->re) + { + fgrep_to_grep_pattern (&kwsearch->pattern, &kwsearch->size); + kwsearch->re = GEAcompile (kwsearch->pattern, + kwsearch->size, + RE_SYNTAX_GREP); + } + end = memchr (beg + len, eol, (buf + size) - (beg + len)); + end = end ? end + 1 : buf + size; + if (EGexecute (kwsearch->re, beg, end - beg, match_size, NULL) + != (size_t) -1) + goto success_match_words; + beg = end - 1; + break; + } if (!len) break; offset = kwsexec (kwset, beg, --len, &kwsmatch, true); @@ -270,6 +287,7 @@ Fexecute (void *vcp, char const *buf, size_t size, size_t *match_size, success: end = memchr (beg + len, eol, (buf + size) - (beg + len)); end = end ? end + 1 : buf + size; + success_match_words: beg = memrchr (buf, eol, beg - buf); beg = beg ? beg + 1 : buf; len = end - beg; -- 2.24.0.390.g083378cc35