Fix "grep -w"

We used to find the first match of the pattern and then if the
match is not for the entire word, declared that the whole line
does not match.

But that is wrong.  The command "git grep -w -e mmap" should
find that a line "foo_mmap bar mmap baz" matches, by tring the
second instance of pattern "mmap" on the same line.

Problems an earlier round of "fix" had were pointed out by Morten
Welinder, which have been incorporated in the t7002 tests.

Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/builtin-grep.c b/builtin-grep.c
index 69b7c4862af3bfcbc9aea2cb52abaa65b3e8490b..93b7e07b30ced0b4f4bad544d9bd8dbedadf452c 100644 (file)
--- a/builtin-grep.c
+++ b/builtin-grep.c
@@ -410,8 +410,10 @@ static int fixmatch(const char *pattern, char *line, regmatch_t *match)
 static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol)
 {
        int hit = 0;
 static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol)
 {
        int hit = 0;

+       int at_true_bol = 1;

        regmatch_t pmatch[10];
 
        regmatch_t pmatch[10];
 

+ again:

        if (!opt->fixed) {
                regex_t *exp = &p->regexp;
                hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
        if (!opt->fixed) {
                regex_t *exp = &p->regexp;
                hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),


@@ -422,22 +424,35 @@ static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol
        }
 
        if (hit && opt->word_regexp) {
        }
 
        if (hit && opt->word_regexp) {

-               /* Match beginning must be either
-                * beginning of the line, or at word
-                * boundary (i.e. the last char must
-                * not be alnum or underscore).
-                */

                if ((pmatch[0].rm_so < 0) ||
                    (eol - bol) <= pmatch[0].rm_so ||
                    (pmatch[0].rm_eo < 0) ||
                    (eol - bol) < pmatch[0].rm_eo)
                        die("regexp returned nonsense");
                if ((pmatch[0].rm_so < 0) ||
                    (eol - bol) <= pmatch[0].rm_so ||
                    (pmatch[0].rm_eo < 0) ||
                    (eol - bol) < pmatch[0].rm_eo)
                        die("regexp returned nonsense");

-               if (pmatch[0].rm_so != 0 &&
-                   word_char(bol[pmatch[0].rm_so-1]))
-                       hit = 0;
-               if (pmatch[0].rm_eo != (eol-bol) &&
-                   word_char(bol[pmatch[0].rm_eo]))
+
+               /* Match beginning must be either beginning of the
+                * line, or at word boundary (i.e. the last char must
+                * not be a word char).  Similarly, match end must be
+                * either end of the line, or at word boundary
+                * (i.e. the next char must not be a word char).
+                */
+               if ( ((pmatch[0].rm_so == 0 && at_true_bol) ||
+                     !word_char(bol[pmatch[0].rm_so-1])) &&
+                    ((pmatch[0].rm_eo == (eol-bol)) ||
+                     !word_char(bol[pmatch[0].rm_eo])) )
+                       ;
+               else

                        hit = 0;
                        hit = 0;

+
+               if (!hit && pmatch[0].rm_so + bol + 1 < eol) {
+                       /* There could be more than one match on the
+                        * line, and the first match might not be
+                        * strict word match.  But later ones could be!
+                        */
+                       bol = pmatch[0].rm_so + bol + 1;
+                       at_true_bol = 0;
+                       goto again;
+               }

        }
        return hit;
 }
        }
        return hit;
 }

diff --git a/t/t7002-grep.sh b/t/t7002-grep.sh
new file mode 100755 (executable)
index 0000000..00a7d76
--- /dev/null
+++ b/t/t7002-grep.sh
@@ -0,0 +1,85 @@
+#!/bin/sh
+#
+# Copyright (c) 2006 Junio C Hamano
+#
+
+test_description='git grep -w
+'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+       {
+               echo foo mmap bar
+               echo foo_mmap bar
+               echo foo_mmap bar mmap
+               echo foo mmap bar_mmap
+               echo foo_mmap bar mmap baz
+       } >file &&
+       echo x x xx x >x &&
+       echo y yy >y &&
+       echo zzz > z &&
+       git add file x y z &&
+       git commit -m initial
+'
+
+for H in HEAD ''
+do
+       case "$H" in
+       HEAD)   HC='HEAD:' L='HEAD' ;;
+       '')     HC= L='in working tree' ;;
+       esac
+
+       test_expect_success "grep -w $L" '
+               {
+                       echo ${HC}file:1:foo mmap bar
+                       echo ${HC}file:3:foo_mmap bar mmap
+                       echo ${HC}file:4:foo mmap bar_mmap
+                       echo ${HC}file:5:foo_mmap bar mmap baz
+               } >expected &&
+               git grep -n -w -e mmap $H >actual &&
+               diff expected actual
+       '
+
+       test_expect_success "grep -w $L (x)" '
+               {
+                       echo ${HC}x:1:x x xx x
+               } >expected &&
+               git grep -n -w -e "x xx* x" $H >actual &&
+               diff expected actual
+       '
+
+       test_expect_success "grep -w $L (y-1)" '
+               {
+                       echo ${HC}y:1:y yy
+               } >expected &&
+               git grep -n -w -e "^y" $H >actual &&
+               diff expected actual
+       '
+
+       test_expect_success "grep -w $L (y-2)" '
+               : >expected &&
+               if git grep -n -w -e "^y y" $H >actual
+               then
+                       echo should not have matched
+                       cat actual
+                       false
+               else
+                       diff expected actual
+               fi
+       '
+
+       test_expect_success "grep -w $L (z)" '
+               : >expected &&
+               if git grep -n -w -e "^z" $H >actual
+               then
+                       echo should not have matched
+                       cat actual
+                       false
+               else
+                       diff expected actual
+               fi
+       '
+done
+
+test_done