[RFC] get_sha1() shorthands for blob/tree objects

From

Linus Torvalds <torvalds@osdl.org>

Date

Apr 18, 2006, 23:45 UTC

Message-ID

<Pine.LNX.4.64.0604181627101.3701@g5.osdl.org>

[ NOTE! The reason I put "RFC" in the subject rather than "PATCH" is that 
  I'm not 100% sure this isn't just a "shiny object" of mine rather than a 
  really useful thing to do. What do people think? Have you ever wanted to 
  access individual files in some random revision? Do you think this is 
  useful? I think it's cool and _may_ be useful, but I'm not going to 
  really push this patch. Consider it a throw-away patch unless somebody 
  else finds it intriguing enough.. ]

With this, you can do something like

	git cat-file blob v1.2.4:Makefile

to get the contents of "Makefile" at revision v1.2.4.

	git diff v0.99.6:git-commit-script..v1.3.0:git-commit.sh

[ IOW, don't get me wrong: the get_sha1() parsing is just the first step, 
  and does _not_ allow that "git diff" syntax to work yet. It parses the 
  object names fine, but git-diff-tree will currently exit with a "fatal: 
  unable to read source tree" error message because the objects aren't 
  tree objects ]

			Linus
---

diff --git a/sha1_name.c b/sha1_name.c
index 4f92e12..0cd1139 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -3,6 +3,7 @@ #include "tag.h"
 #include "commit.h"
 #include "tree.h"
 #include "blob.h"
+#include "diff.h"
 
 static int find_short_object_filename(int len, const char *name, unsigned char *sha1)
 {
@@ -449,12 +450,76 @@ static int get_sha1_1(const char *name, 
 	return get_short_sha1(name, len, sha1, 0);
 }
 
+static int get_tree_entry(const unsigned char *, const char *, unsigned char *);
+
+static int find_tree_entry(struct tree_desc *t, const char *name, unsigned char *result)
+{
+	int namelen = strlen(name);
+	while (t->size) {
+		const char *entry;
+		const unsigned char *sha1;
+		int entrylen, cmp;
+		unsigned mode;
+
+		sha1 = tree_entry_extract(t, &entry, &mode);
+		update_tree_entry(t);
+		entrylen = strlen(entry);
+		if (entrylen > namelen)
+			continue;
+		cmp = memcmp(name, entry, entrylen);
+		if (cmp > 0)
+			continue;
+		if (cmp < 0)
+			break;
+		if (entrylen == namelen) {
+			memcpy(result, sha1, 20);
+			return 0;
+		}
+		if (name[entrylen] != '/')
+			continue;
+		if (!S_ISDIR(mode))
+			break;
+		if (++entrylen == namelen) {
+			memcpy(result, sha1, 20);
+			return 0;
+		}
+		return get_tree_entry(sha1, name + entrylen, result);
+	}
+	return -1;
+}
+
+static int get_tree_entry(const unsigned char *tree_sha1, const char *name, unsigned char *sha1)
+{
+	int retval;
+	void *tree;
+	struct tree_desc t;
+
+	tree = read_object_with_reference(tree_sha1, tree_type, &t.size, NULL);
+	if (!tree)
+		return -1;
+	t.buf = tree;
+	retval = find_tree_entry(&t, name, sha1);
+	free(tree);
+	return retval;
+}
+
 /*
  * This is like "get_sha1_basic()", except it allows "sha1 expressions",
  * notably "xyz^" for "parent of xyz"
  */
 int get_sha1(const char *name, unsigned char *sha1)
 {
+	int ret;
+
 	prepare_alt_odb();
-	return get_sha1_1(name, strlen(name), sha1);
+	ret = get_sha1_1(name, strlen(name), sha1);
+	if (ret < 0) {
+		const char *cp = strchr(name, ':');
+		if (cp) {
+			unsigned char tree_sha1[20];
+			if (!get_sha1_1(name, cp-name, tree_sha1))
+				return get_tree_entry(tree_sha1, cp+1, sha1);
+		}
+	}
+	return ret;
 }