combine-diff: better hunk splitting.

diff --git a/sha1_name.c b/sha1_name.c
index 4e9a052333dcbb538866766f68b4fe18f615fe4d..e18a96d772f4186cfaffe6053a3f1664a9fdad3f 100644 (file)
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -1,5 +1,8 @@
 #include "cache.h"
+#include "tag.h"
 #include "commit.h"
+#include "tree.h"
+#include "blob.h"
 
 static int find_short_object_filename(int len, const char *name, unsigned char *sha1)
 {
@@ -140,7 +143,7 @@ static int find_unique_short_object(int len, char *canonical,
        }
        /* Both have unique ones -- do they match? */
        if (memcmp(packed_sha1, unpacked_sha1, 20))
-               return -2;
+               return SHORT_NAME_AMBIGUOUS;
        memcpy(sha1, packed_sha1, 20);
        return 0;
 }
@@ -185,7 +188,10 @@ const char *find_unique_abbrev(const unsigned char *sha1, int len)
 {
        int status;
        static char hex[41];
+
        memcpy(hex, sha1_to_hex(sha1), 40);
+       if (len == 40)
+               return hex;
        while (len < 40) {
                unsigned char sha1_ret[20];
                status = get_short_sha1(hex, len, sha1_ret, 1);
@@ -200,6 +206,31 @@ const char *find_unique_abbrev(const unsigned char *sha1, int len)
        return NULL;
 }
 
+static int ambiguous_path(const char *path, int len)
+{
+       int slash = 1;
+       int cnt;
+
+       for (cnt = 0; cnt < len; cnt++) {
+               switch (*path++) {
+               case '\0':
+                       break;
+               case '/':
+                       if (slash)
+                               break;
+                       slash = 1;
+                       continue;
+               case '.':
+                       continue;
+               default:
+                       slash = 0;
+                       continue;
+               }
+               break;
+       }
+       return slash;
+}
+
 static int get_sha1_basic(const char *str, int len, unsigned char *sha1)
 {
        static const char *prefix[] = {
@@ -214,12 +245,15 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1)
        if (len == 40 && !get_sha1_hex(str, sha1))
                return 0;
 
+       /* Accept only unambiguous ref paths. */
+       if (ambiguous_path(str, len))
+               return -1;
+
        for (p = prefix; *p; p++) {
                char *pathname = git_path("%s/%.*s", *p, len, str);
                if (!read_ref(pathname, sha1))
                        return 0;
        }
-
        return -1;
 }
 
@@ -274,6 +308,84 @@ static int get_nth_ancestor(const char *name, int len,
        return 0;
 }
 
+static int peel_onion(const char *name, int len, unsigned char *sha1)
+{
+       unsigned char outer[20];
+       const char *sp;
+       const char *type_string = NULL;
+       struct object *o;
+
+       /*
+        * "ref^{type}" dereferences ref repeatedly until you cannot
+        * dereference anymore, or you get an object of given type,
+        * whichever comes first.  "ref^{}" means just dereference
+        * tags until you get a non-tag.  "ref^0" is a shorthand for
+        * "ref^{commit}".  "commit^{tree}" could be used to find the
+        * top-level tree of the given commit.
+        */
+       if (len < 4 || name[len-1] != '}')
+               return -1;
+
+       for (sp = name + len - 1; name <= sp; sp--) {
+               int ch = *sp;
+               if (ch == '{' && name < sp && sp[-1] == '^')
+                       break;
+       }
+       if (sp <= name)
+               return -1;
+
+       sp++; /* beginning of type name, or closing brace for empty */
+       if (!strncmp(commit_type, sp, 6) && sp[6] == '}')
+               type_string = commit_type;
+       else if (!strncmp(tree_type, sp, 4) && sp[4] == '}')
+               type_string = tree_type;
+       else if (!strncmp(blob_type, sp, 4) && sp[4] == '}')
+               type_string = blob_type;
+       else if (sp[0] == '}')
+               type_string = NULL;
+       else
+               return -1;
+
+       if (get_sha1_1(name, sp - name - 2, outer))
+               return -1;
+
+       o = parse_object(outer);
+       if (!o)
+               return -1;
+       if (!type_string) {
+               o = deref_tag(o, name, sp - name - 2);
+               if (!o || (!o->parsed && !parse_object(o->sha1)))
+                       return -1;
+               memcpy(sha1, o->sha1, 20);
+       }
+       else {
+               /* At this point, the syntax look correct, so
+                * if we do not get the needed object, we should
+                * barf.
+                */
+
+               while (1) {
+                       if (!o || (!o->parsed && !parse_object(o->sha1)))
+                               return -1;
+                       if (o->type == type_string) {
+                               memcpy(sha1, o->sha1, 20);
+                               return 0;
+                       }
+                       if (o->type == tag_type)
+                               o = ((struct tag*) o)->tagged;
+                       else if (o->type == commit_type)
+                               o = &(((struct commit *) o)->tree->object);
+                       else
+                               return error("%.*s: expected %s type, but the object dereferences to %s type",
+                                            len, name, type_string,
+                                            o->type);
+                       if (!o->parsed)
+                               parse_object(o->sha1);
+               }
+       }
+       return 0;
+}
+
 static int get_sha1_1(const char *name, int len, unsigned char *sha1)
 {
        int parent, ret;
@@ -315,6 +427,10 @@ static int get_sha1_1(const char *name, int len, unsigned char *sha1)
                return get_nth_ancestor(name, len1, sha1, parent);
        }
 
+       ret = peel_onion(name, len, sha1);
+       if (!ret)
+               return 0;
+
        ret = get_sha1_basic(name, len, sha1);
        if (!ret)
                return 0;