Merge branch 'np/delta' into next

diff --git a/builtin-grep.c b/builtin-grep.c
index b8351200dd61868a60d97a5a491960957b002c61..09e3677824595d71d02fc7bfc03eef0428df8b90 100644 (file)
--- a/builtin-grep.c
+++ b/builtin-grep.c
@@ -88,6 +88,8 @@ struct grep_opt {
        unsigned linenum:1;
        unsigned invert:1;
        unsigned name_only:1;
+       unsigned count:1;
+       unsigned word_regexp:1;
        int regflags;
        unsigned pre_context;
        unsigned post_context;
@@ -127,6 +129,11 @@ static char *end_of_line(char *cp, unsigned long *left)
        return cp;
 }
 
+static int word_char(char ch)
+{
+       return isalnum(ch) || ch == '_';
+}
+
 static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
                      const char *name, unsigned lno, char sign)
 {
@@ -149,6 +156,7 @@ static int grep_buffer(struct grep_opt *opt, const char *name,
        unsigned last_hit = 0;
        unsigned last_shown = 0;
        const char *hunk_mark = "";
+       unsigned count = 0;
 
        if (opt->pre_context)
                prev = xcalloc(opt->pre_context, sizeof(*prev));
@@ -169,6 +177,25 @@ static int grep_buffer(struct grep_opt *opt, const char *name,
                        regex_t *exp = &p->regexp;
                        hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
                                       pmatch, 0);
+
+                       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 &&
+                                   word_char(bol[pmatch[0].rm_so-1]))
+                                       continue; /* not a word boundary */
+                               if ((eol-bol) < pmatch[0].rm_eo &&
+                                   word_char(bol[pmatch[0].rm_eo]))
+                                       continue; /* not a word boundary */
+                       }
                        if (hit)
                                break;
                }
@@ -179,12 +206,16 @@ static int grep_buffer(struct grep_opt *opt, const char *name,
                if (opt->invert)
                        hit = !hit;
                if (hit) {
+                       count++;
                        if (opt->name_only) {
                                printf("%s\n", name);
                                return 1;
                        }
                        /* Hit at this line.  If we haven't shown the
                         * pre-context lines, we would need to show them.
+                        * When asked to do "count", this still show
+                        * the context which is nonsense, but the user
+                        * deserves to get that ;-).
                         */
                        if (opt->pre_context) {
                                unsigned from;
@@ -206,7 +237,8 @@ static int grep_buffer(struct grep_opt *opt, const char *name,
                        }
                        if (last_shown && lno != last_shown + 1)
                                printf(hunk_mark);
-                       show_line(opt, bol, eol, name, lno, ':');
+                       if (!opt->count)
+                               show_line(opt, bol, eol, name, lno, ':');
                        last_shown = last_hit = lno;
                }
                else if (last_hit &&
@@ -230,6 +262,13 @@ static int grep_buffer(struct grep_opt *opt, const char *name,
                left--;
                lno++;
        }
+       /* NEEDSWORK:
+        * The real "grep -c foo *.c" gives many "bar.c:0" lines,
+        * which feels mostly useless but sometimes useful.  Maybe
+        * make it another option?  For now suppress them.
+        */
+       if (opt->count && count)
+               printf("%s:%u\n", name, count);
        return !!last_hit;
 }
 
@@ -442,6 +481,16 @@ int cmd_grep(int argc, const char **argv, char **envp)
                        opt.name_only = 1;
                        continue;
                }
+               if (!strcmp("-c", arg) ||
+                   !strcmp("--count", arg)) {
+                       opt.count = 1;
+                       continue;
+               }
+               if (!strcmp("-w", arg) ||
+                   !strcmp("--word-regexp", arg)) {
+                       opt.word_regexp = 1;
+                       continue;
+               }
                if (!strncmp("-A", arg, 2) ||
                    !strncmp("-B", arg, 2) ||
                    !strncmp("-C", arg, 2) ||