simple euristic for further free packing improvements

diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
index be1bbcc53f1d489dccd9e8b8ce4ad9c1c39c107b..cfcce315babb0edb7ad7be7f2ab2437aaf41eb9d 100644 (file)
--- a/diffcore-pickaxe.c
+++ b/diffcore-pickaxe.c
@@ -4,52 +4,134 @@
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "delta.h"
 
-static int contains(struct diff_filespec *one,
-                   const char *needle, unsigned long len)
+#include <regex.h>
+
+static unsigned int contains(struct diff_filespec *one,
+                            const char *needle, unsigned long len,
+                            regex_t *regexp)
 {
+       unsigned int cnt;
        unsigned long offset, sz;
        const char *data;
-       if (diff_populate_filespec(one))
+       if (diff_populate_filespec(one, 0))
                return 0;
+
        sz = one->size;
        data = one->data;
-       for (offset = 0; offset + len <= sz; offset++)
-                    if (!strncmp(needle, data + offset, len))
-                            return 1;
-       return 0;
+       cnt = 0;
+
+       if (regexp) {
+               regmatch_t regmatch;
+               int flags = 0;
+
+               while (*data && !regexec(regexp, data, 1, &regmatch, flags)) {
+                       flags |= REG_NOTBOL;
+                       data += regmatch.rm_so;
+                       if (*data) data++;
+                       cnt++;
+               }
+
+       } else { /* Classic exact string match */
+               /* Yes, I've heard of strstr(), but the thing is *data may
+                * not be NUL terminated.  Sue me.
+                */
+               for (offset = 0; offset + len <= sz; offset++) {
+                       /* we count non-overlapping occurrences of needle */
+                       if (!memcmp(needle, data + offset, len)) {
+                               offset += len - 1;
+                               cnt++;
+                       }
+               }
+       }
+       return cnt;
 }
 
-void diffcore_pickaxe(const char *needle)
+void diffcore_pickaxe(const char *needle, int opts)
 {
        struct diff_queue_struct *q = &diff_queued_diff;
        unsigned long len = strlen(needle);
-       int i;
+       int i, has_changes;
+       regex_t regex, *regexp = NULL;
        struct diff_queue_struct outq;
        outq.queue = NULL;
        outq.nr = outq.alloc = 0;
 
-       for (i = 0; i < q->nr; i++) {
-               struct diff_filepair *p = q->queue[i];
-               int onum = outq.nr;
-               if (!DIFF_FILE_VALID(p->one)) {
-                       if (!DIFF_FILE_VALID(p->two))
-                               continue; /* ignore nonsense */
-                       /* created */
-                       if (contains(p->two, needle, len))
-                               diff_q(&outq, p);
+       if (opts & DIFF_PICKAXE_REGEX) {
+               int err;
+               err = regcomp(&regex, needle, REG_EXTENDED | REG_NEWLINE);
+               if (err) {
+                       /* The POSIX.2 people are surely sick */
+                       char errbuf[1024];
+                       regerror(err, &regex, errbuf, 1024);
+                       regfree(&regex);
+                       die("invalid pickaxe regex: %s", errbuf);
                }
-               else if (!DIFF_FILE_VALID(p->two)) {
-                       if (contains(p->one, needle, len))
+               regexp = &regex;
+       }
+
+       if (opts & DIFF_PICKAXE_ALL) {
+               /* Showing the whole changeset if needle exists */
+               for (i = has_changes = 0; !has_changes && i < q->nr; i++) {
+                       struct diff_filepair *p = q->queue[i];
+                       if (!DIFF_FILE_VALID(p->one)) {
+                               if (!DIFF_FILE_VALID(p->two))
+                                       continue; /* ignore unmerged */
+                               /* created */
+                               if (contains(p->two, needle, len, regexp))
+                                       has_changes++;
+                       }
+                       else if (!DIFF_FILE_VALID(p->two)) {
+                               if (contains(p->one, needle, len, regexp))
+                                       has_changes++;
+                       }
+                       else if (!diff_unmodified_pair(p) &&
+                                contains(p->one, needle, len, regexp) !=
+                                contains(p->two, needle, len, regexp))
+                               has_changes++;
+               }
+               if (has_changes)
+                       return; /* not munge the queue */
+
+               /* otherwise we will clear the whole queue
+                * by copying the empty outq at the end of this
+                * function, but first clear the current entries
+                * in the queue.
+                */
+               for (i = 0; i < q->nr; i++)
+                       diff_free_filepair(q->queue[i]);
+       }
+       else 
+               /* Showing only the filepairs that has the needle */
+               for (i = 0; i < q->nr; i++) {
+                       struct diff_filepair *p = q->queue[i];
+                       has_changes = 0;
+                       if (!DIFF_FILE_VALID(p->one)) {
+                               if (!DIFF_FILE_VALID(p->two))
+                                       ; /* ignore unmerged */
+                               /* created */
+                               else if (contains(p->two, needle, len, regexp))
+                                       has_changes = 1;
+                       }
+                       else if (!DIFF_FILE_VALID(p->two)) {
+                               if (contains(p->one, needle, len, regexp))
+                                       has_changes = 1;
+                       }
+                       else if (!diff_unmodified_pair(p) &&
+                                contains(p->one, needle, len, regexp) !=
+                                contains(p->two, needle, len, regexp))
+                               has_changes = 1;
+
+                       if (has_changes)
                                diff_q(&outq, p);
+                       else
+                               diff_free_filepair(p);
                }
-               else if (contains(p->one, needle, len) !=
-                        contains(p->two, needle, len))
-                       diff_q(&outq, p);
-               if (onum == outq.nr)
-                       free(p);
+
+       if (opts & DIFF_PICKAXE_REGEX) {
+               regfree(&regex);
        }
+
        free(q->queue);
        *q = outq;
        return;