[PATCH v2 00/12] nd/icase updates

[Nguyễn Thái Ngọc Duy]

v2 fixes Junio's and Jeff's comments (both good). The sharing "!icase
|| ascii_only" is made a separate commit (6/12) because I think it
takes some seconds to realize that the conversion is correct and it's
technically not needed in 5/12 (and it's sort of the opposite of 1/12)

Interdiff

diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
index 0a5f877..55067ca 100644
--- a/diffcore-pickaxe.c
+++ b/diffcore-pickaxe.c
@@ -200,19 +200,30 @@ static void pickaxe(struct diff_queue_struct *q, struct 
diff_options *o,
        *q = outq;
 }
 
+static void regcomp_or_die(regex_t *regex, const char *needle, int cflags)
+{
+       int err = regcomp(regex, needle, cflags);
+       if (err) {
+               /* The POSIX.2 people are surely sick */
+               char errbuf[1024];
+               regerror(err, regex, errbuf, 1024);
+               regfree(regex);
+               die("invalid regex: %s", errbuf);
+       }
+}
+
 void diffcore_pickaxe(struct diff_options *o)
 {
        const char *needle = o->pickaxe;
        int opts = o->pickaxe_opts;
        regex_t regex, *regexp = NULL;
        kwset_t kws = NULL;
-       int err = 0;
 
        if (opts & (DIFF_PICKAXE_REGEX | DIFF_PICKAXE_KIND_G)) {
                int cflags = REG_EXTENDED | REG_NEWLINE;
                if (DIFF_OPT_TST(o, PICKAXE_IGNORE_CASE))
                        cflags |= REG_ICASE;
-               err = regcomp(&regex, needle, cflags);
+               regcomp_or_die(&regex, needle, cflags);
                regexp = &regex;
        } else if (DIFF_OPT_TST(o, PICKAXE_IGNORE_CASE) &&
                   has_non_ascii(needle)) {
@@ -220,7 +231,7 @@ void diffcore_pickaxe(struct diff_options *o)
                int cflags = REG_NEWLINE | REG_ICASE;
 
                basic_regex_quote_buf(&sb, needle);
-               err = regcomp(&regex, sb.buf, cflags);
+               regcomp_or_die(&regex, sb.buf, cflags);
                strbuf_release(&sb);
                regexp = &regex;
        } else {
@@ -229,13 +240,6 @@ void diffcore_pickaxe(struct diff_options *o)
                kwsincr(kws, needle, strlen(needle));
                kwsprep(kws);
        }
-       if (err) {
-               /* The POSIX.2 people are surely sick */
-               char errbuf[1024];
-               regerror(err, &regex, errbuf, 1024);
-               regfree(&regex);
-               die("invalid regex: %s", errbuf);
-       }
 
        /* Might want to warn when both S and G are on; I don't care... */
        pickaxe(&diff_queued_diff, o, regexp, kws,
diff --git a/grep.c b/grep.c
index cb058a5..92587a8 100644
--- a/grep.c
+++ b/grep.c
@@ -432,15 +432,8 @@ static void compile_regexp(struct grep_pat *p, struct 
grep_opt *opt)
        icase          = opt->regflags & REG_ICASE || p->ignore_case;
        ascii_only     = !has_non_ascii(p->pattern);
 
-       if (opt->fixed) {
+       if (opt->fixed || is_fixed(p->pattern, p->patternlen))
                p->fixed = !icase || ascii_only;
-               if (!p->fixed) {
-                       compile_fixed_regexp(p, opt);
-                       return;
-               }
-       } else if ((!icase || ascii_only) &&
-                  is_fixed(p->pattern, p->patternlen))
-               p->fixed = 1;
        else
                p->fixed = 0;
 
@@ -449,6 +442,9 @@ static void compile_regexp(struct grep_pat *p, struct 
grep_opt *opt)
                kwsincr(p->kws, p->pattern, p->patternlen);
                kwsprep(p->kws);
                return;
+       } else if (opt->fixed) {
+               compile_fixed_regexp(p, opt);
+               return;
        }
 
        if (opt->pcre) {

Nguyễn Thái Ngọc Duy (12):
  grep: break down an "if" stmt in preparation for next changes
  test-regex: isolate the bug test code
  test-regex: expose full regcomp() to the command line
  grep/icase: avoid kwsset on literal non-ascii strings
  grep/icase: avoid kwsset when -F is specified
  grep: rewrite an if/else condition to avoid duplicate expression
  grep/pcre: prepare locale-dependent tables for icase matching
  gettext: add is_utf8_locale()
  grep/pcre: support utf-8
  diffcore-pickaxe: Add regcomp_or_die()
  diffcore-pickaxe: support case insensitive match on non-ascii
  grep.c: reuse "icase" variable

 diffcore-pickaxe.c                       | 33 +++++++++++----
 gettext.c                                | 24 ++++++++++-
 gettext.h                                |  1 +
 grep.c                                   | 43 +++++++++++++++----
 grep.h                                   |  1 +
 quote.c                                  | 37 +++++++++++++++++
 quote.h                                  |  1 +
 t/t0070-fundamental.sh                   |  2 +-
 t/t7812-grep-icase-non-ascii.sh (new +x) | 71 ++++++++++++++++++++++++++++++++
 t/t7813-grep-icase-iso.sh (new +x)       | 19 +++++++++
 test-regex.c                             | 59 +++++++++++++++++++++++++-
 11 files changed, 270 insertions(+), 21 deletions(-)
 create mode 100755 t/t7812-grep-icase-non-ascii.sh
 create mode 100755 t/t7813-grep-icase-iso.sh

-- 
2.8.2.526.g02eed6d

--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html