git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 06/19] tree-diff: consolidate code for emitting diffs and recursion in one place

From
Kirill Smelkov <kirr@mns.spb.ru>
Date
Feb 24, 2014, 16:21 UTC
Message-ID
<696b8f0956f5d7699911a3bb56d66602301ee36c.1393257006.git.kirr@mns.spb.ru>
In-Reply-To
<cover.1393257006.git.kirr@mns.spb.ru>

Currently both compare_tree_entry() and show_path() invoke opt diff callbacks (opt->add_remove() and opt->change()), and also they both have code which decides whether to recurse into sub-tree, and whether to emit a tree as separate entry if DIFF_OPT_TREE_IN_RECURSIVE is set.

I.e. we have code duplication and logic scattered on two places.

Let's consolidate it - all diff emmiting code and recurion logic moves to show_entry, which is now named as show_path, because it shows diff for a path, based on up to two tree entries, with actual diff emitting code being kept in new helper emit_diff() for clarity.

What we have as the result, is that compare_tree_entry is now free from code with logic for diff generation, and also performance is not affected as timings for

    `git log --raw --no-abbrev --no-renames`

for navy.git and `linux.git v3.10..v3.11`, just like in previous patch, stay the same.

Signed-off-by: Kirill Smelkov <kirr@mns.spb.ru>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
( re-posting without change )
 tree-diff.c | 115 ++++++++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 84 insertions(+), 31 deletions(-)
diff --git a/tree-diff.c b/tree-diff.c
index 2ad7788..a5b9ff9 100644
--- a/tree-diff.c
+++ b/tree-diff.c
@@ -6,8 +6,8 @@
 #include "diffcore.h"
 #include "tree.h"
 
-static void show_entry(struct diff_options *opt, const char *prefix,
-		       struct tree_desc *desc, struct strbuf *base);
+static void show_path(struct strbuf *base, struct diff_options *opt,
+		      struct tree_desc *t1, struct tree_desc *t2);
 
 static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2,
 			      struct strbuf *base, struct diff_options *opt)
@@ -16,7 +16,6 @@ static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2,
 	const char *path1, *path2;
 	const unsigned char *sha1, *sha2;
 	int cmp, pathlen1, pathlen2;
-	int old_baselen = base->len;
 
 	sha1 = tree_entry_extract(t1, &path1, &mode1);
 	sha2 = tree_entry_extract(t2, &path2, &mode2);
@@ -30,51 +29,105 @@ static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2,
 	 */
 	cmp = base_name_compare(path1, pathlen1, mode1, path2, pathlen2, mode2);
 	if (cmp < 0) {
-		show_entry(opt, "-", t1, base);
+		show_path(base, opt, t1, /*t2=*/NULL);
 		return -1;
 	}
 	if (cmp > 0) {
-		show_entry(opt, "+", t2, base);
+		show_path(base, opt, /*t1=*/NULL, t2);
 		return 1;
 	}
 	if (!DIFF_OPT_TST(opt, FIND_COPIES_HARDER) && !hashcmp(sha1, sha2) && mode1 == mode2)
 		return 0;
 
-	strbuf_add(base, path1, pathlen1);
-	if (DIFF_OPT_TST(opt, RECURSIVE) && S_ISDIR(mode1)) {
-		if (DIFF_OPT_TST(opt, TREE_IN_RECURSIVE)) {
-			opt->change(opt, mode1, mode2,
-				    sha1, sha2, 1, 1, base->buf, 0, 0);
-		}
-		strbuf_addch(base, '/');
-		diff_tree_sha1(sha1, sha2, base->buf, opt);
-	} else {
-		opt->change(opt, mode1, mode2, sha1, sha2, 1, 1, base->buf, 0, 0);
-	}
-	strbuf_setlen(base, old_baselen);
+	show_path(base, opt, t1, t2);
 	return 0;
 }
 
-/* An entry went away or appeared */
-static void show_entry(struct diff_options *opt, const char *prefix,
-		       struct tree_desc *desc, struct strbuf *base)
+
+/* convert path, t1/t2 -> opt->diff_*() callbacks */
+static void emit_diff(struct diff_options *opt, struct strbuf *path,
+		      struct tree_desc *t1, struct tree_desc *t2)
+{
+	unsigned int mode1 = t1 ? t1->entry.mode : 0;
+	unsigned int mode2 = t2 ? t2->entry.mode : 0;
+
+	if (mode1 && mode2) {
+		opt->change(opt, mode1, mode2, t1->entry.sha1, t2->entry.sha1,
+			1, 1, path->buf, 0, 0);
+	}
+	else {
+		const unsigned char *sha1;
+		unsigned int mode;
+		int addremove;
+
+		if (mode2) {
+			addremove = '+';
+			sha1 = t2->entry.sha1;
+			mode = mode2;
+		}
+		else {
+			addremove = '-';
+			sha1 = t1->entry.sha1;
+			mode = mode1;
+		}
+
+		opt->add_remove(opt, addremove, mode, sha1, 1, path->buf, 0);
+	}
+}
+
+
+/* new path should be added to diff
+ *
+ * 3 cases on how/when it should be called and behaves:
+ *
+ *	!t1,  t2	-> path added, parent lacks it
+ *	 t1, !t2	-> path removed from parent
+ *	 t1,  t2	-> path modified
+ */
+static void show_path(struct strbuf *base, struct diff_options *opt,
+		      struct tree_desc *t1, struct tree_desc *t2)
 {
 	unsigned mode;
 	const char *path;
-	const unsigned char *sha1 = tree_entry_extract(desc, &path, &mode);
-	int pathlen = tree_entry_len(&desc->entry);
+	int pathlen;
 	int old_baselen = base->len;
+	int isdir, recurse = 0, emitthis = 1;
+
+	/* at least something has to be valid */
+	assert(t1 || t2);
+
+	if (t2) {
+		/* path present in resulting tree */
+		tree_entry_extract(t2, &path, &mode);
+		pathlen = tree_entry_len(&t2->entry);
+		isdir = S_ISDIR(mode);
+	}
+	else {
+		/* a path was removed - take path from parent. Also take
+		 * mode from parent, to decide on recursion.
+		 */
+		tree_entry_extract(t1, &path, &mode);
+		pathlen = tree_entry_len(&t1->entry);
+
+		isdir = S_ISDIR(mode);
+		mode = 0;
+	}
+
+	if (DIFF_OPT_TST(opt, RECURSIVE) && isdir) {
+		recurse = 1;
+		emitthis = DIFF_OPT_TST(opt, TREE_IN_RECURSIVE);
+	}
 
 	strbuf_add(base, path, pathlen);
-	if (DIFF_OPT_TST(opt, RECURSIVE) && S_ISDIR(mode)) {
-		if (DIFF_OPT_TST(opt, TREE_IN_RECURSIVE))
-			opt->add_remove(opt, *prefix, mode, sha1, 1, base->buf, 0);
 
+	if (emitthis)
+		emit_diff(opt, base, t1, t2);
+
+	if (recurse) {
 		strbuf_addch(base, '/');
-		diff_tree_sha1(*prefix == '-' ? sha1 : NULL,
-			       *prefix == '+' ? sha1 : NULL, base->buf, opt);
-	} else
-		opt->add_remove(opt, prefix[0], mode, sha1, 1, base->buf, 0);
+		diff_tree_sha1(t1 ? t1->entry.sha1 : NULL,
+			       t2 ? t2->entry.sha1 : NULL, base->buf, opt);
+	}
 
 	strbuf_setlen(base, old_baselen);
 }
@@ -117,12 +170,12 @@ int diff_tree(struct tree_desc *t1, struct tree_desc *t2,
 		if (!t1->size) {
 			if (!t2->size)
 				break;
-			show_entry(opt, "+", t2, &base);
+			show_path(&base, opt, /*t1=*/NULL, t2);
 			update_tree_entry(t2);
 			continue;
 		}
 		if (!t2->size) {
-			show_entry(opt, "-", t1, &base);
+			show_path(&base, opt, t1, /*t2=*/NULL);
 			update_tree_entry(t1);
 			continue;
 		}
-- 
1.9.rc1.181.g641f458
Previous: Kirill SmelkovNext: Kirill Smelkov
Message 7 of 64 in “Multiparent diff tree-walker + combine-diff speedup”
  1. 00/19 Multiparent diff tree-walker + combine-diff speedupKirill Smelkov, Feb 24, 2014
  2. 01/19 combine-diff: move show_log_first logic/action out of paths scanningKirill Smelkov, Feb 24, 2014
  3. 02/19 combine-diff: move changed-paths scanning logic into its own functionKirill Smelkov, Feb 24, 2014
  4. 03/19 tree-diff: no need to manually verify that there is no mode change for a pathKirill Smelkov, Feb 24, 2014
  5. 04/19 tree-diff: no need to pass match to skip_uninteresting()Kirill Smelkov, Feb 24, 2014
  6. 05/19 tree-diff: show_tree() is not neededKirill Smelkov, Feb 24, 2014
  7. 06/19 tree-diff: consolidate code for emitting diffs and recursion in one placeKirill Smelkov, Feb 24, 2014
  8. 07/19 tree-diff: don't assume compare_tree_entry() returns -1,0,1Kirill Smelkov, Feb 24, 2014
  9. 08/19 tree-diff: move all action-taking code out of compare_tree_entry()Kirill Smelkov, Feb 24, 2014
  10. 09/19 tree-diff: rename compare_tree_entry -> tree_entry_pathcmpKirill Smelkov, Feb 24, 2014
  11. 10/19 tree-diff: show_path prototype is not needed anymoreKirill Smelkov, Feb 24, 2014
  12. 11/19 tree-diff: simplify tree_entry_pathcmpKirill Smelkov, Feb 24, 2014
  13. Junio C HamanoMar 24, 2014
  14. Kirill SmelkovMar 25, 2014
  15. 12/19 tree-diff: remove special-case diff-emitting code for empty-tree casesKirill Smelkov, Feb 24, 2014
  16. Junio C HamanoMar 24, 2014
  17. Kirill SmelkovMar 25, 2014
  18. Junio C HamanoMar 25, 2014
  19. Junio C HamanoMar 25, 2014
  20. Kirill SmelkovMar 26, 2014
  21. 13/19 tree-diff: diff_tree() should now be staticKirill Smelkov, Feb 24, 2014
  22. 14/19 tree-diff: rework diff_tree interface to be sha1 basedKirill Smelkov, Feb 24, 2014
  23. Junio C HamanoMar 24, 2014
  24. Kirill SmelkovMar 25, 2014
  25. Junio C HamanoMar 25, 2014
  26. Kirill SmelkovMar 26, 2014
  27. Junio C HamanoMar 26, 2014
  28. Kirill SmelkovMar 27, 2014
  29. Junio C HamanoMar 27, 2014
  30. Kirill SmelkovMar 27, 2014
  31. Johannes SixtMar 28, 2014
  32. Junio C HamanoMar 28, 2014
  33. Johannes SixtMar 28, 2014
  34. Junio C HamanoMar 28, 2014
  35. Johannes SixtMar 28, 2014
  36. Junio C HamanoMar 28, 2014
  37. 15/19 tree-diff: no need to call "full" diff_tree_sha1 from show_path()Kirill Smelkov, Feb 24, 2014
  38. Kirill SmelkovMar 27, 2014
  39. 16/19 tree-diff: reuse base str(buf) memory on sub-tree recursionKirill Smelkov, Feb 24, 2014
  40. Junio C HamanoMar 24, 2014
  41. Kirill SmelkovMar 25, 2014
  42. Kirill SmelkovMar 27, 2014
  43. 17/19 Portable alloca for GitKirill Smelkov, Feb 24, 2014
  44. Thomas SchwingeFeb 28, 2014
  45. Erik Faye-LundFeb 28, 2014
  46. Erik Faye-LundFeb 28, 2014
  47. Kirill SmelkovFeb 28, 2014
  48. Erik Faye-LundFeb 28, 2014
  49. Kirill SmelkovMar 5, 2014
  50. Junio C HamanoMar 24, 2014
  51. Kirill SmelkovMar 27, 2014
  52. Kirill SmelkovApr 9, 2014
  53. Erik Faye-LundApr 9, 2014
  54. Junio C HamanoApr 10, 2014
  55. 18/19 tree-diff: rework diff_tree() to generate diffs for multiparent cases as wellKirill Smelkov, Feb 24, 2014
  56. Kirill SmelkovMar 27, 2014
  57. Junio C HamanoApr 4, 2014
  58. Kirill SmelkovApr 6, 2014
  59. Junio C HamanoApr 7, 2014
  60. Junio C HamanoApr 7, 2014
  61. Kirill SmelkovApr 7, 2014
  62. 19/19 combine-diff: speed it up, by using multiparent diff tree-walker directlyKirill Smelkov, Feb 24, 2014
  63. Duy NguyenFeb 24, 2014
  64. Kirill SmelkovFeb 25, 2014

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.