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

[PATCH v3 4/9] tree: handle submodule case for read_tree_at properly

From
HGHeather Lapointe via GitGitGadget <gitgitgadget@gmail.com>
Date
Oct 17, 2022, 02:23 UTC
Message-ID
<d3d1738e670d5dbf1378fc5c3209b2e98234a771.1665973401.git.gitgitgadget@gmail.com>
In-Reply-To
<pull.1359.v3.git.git.1665973401.gitgitgadget@gmail.com>
From: Heather Lapointe <alpha@alphaservcomputing.solutions>

This supports traversal into an actual submodule for read_tree_at. The logic is blocked on pathspec->recurse_submodules now, but previously hadn't been executed due to all fn() cases returning early for submodules.

Signed-off-by: Heather Lapointe <alpha@alphaservcomputing.solutions>
---
 tree.c | 88 ++++++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 61 insertions(+), 27 deletions(-)
diff --git a/tree.c b/tree.c
index 13f9173d45e..2a087c010f9 100644
--- a/tree.c
+++ b/tree.c
@@ -8,6 +8,7 @@
 #include "alloc.h"
 #include "tree-walk.h"
 #include "repository.h"
+#include "pathspec.h"
 
 const char *tree_type = "tree";
 
@@ -47,40 +48,73 @@ int read_tree_at(struct repository *r,
 			return -1;
 		}
 
-		if (S_ISDIR(entry.mode))
+		if (S_ISDIR(entry.mode)) {
 			oidcpy(&oid, &entry.oid);
-		else if (S_ISGITLINK(entry.mode)) {
-			struct commit *commit;
 
-			commit = lookup_commit(r, &entry.oid);
+			len = tree_entry_len(&entry);
+			strbuf_add(base, entry.path, len);
+			strbuf_addch(base, '/');
+			retval = read_tree_at(r, lookup_tree(r, &oid),
+						base, pathspec,
+						fn, context);
+			strbuf_setlen(base, oldlen);
+			if (retval)
+				return -1;
+		} else if (pathspec->recurse_submodules && S_ISGITLINK(entry.mode)) {
+			struct commit *commit;
+			struct repository subrepo;
+			struct repository* subrepo_p = &subrepo;
+			struct tree* submodule_tree;
+			char *submodule_rel_path;
+			int name_base_len = 0;
+
+			len = tree_entry_len(&entry);
+			strbuf_add(base, entry.path, len);
+			submodule_rel_path = base->buf;
+			// repo_submodule_init expects a path relative to submodule_prefix
+			if (r->submodule_prefix) {
+				name_base_len = strlen(r->submodule_prefix);
+				// we should always expect to start with submodule_prefix
+				assert(!strncmp(submodule_rel_path, r->submodule_prefix, name_base_len));
+				// strip the prefix
+				submodule_rel_path += name_base_len;
+				// if submodule_prefix doesn't end with a /, we want to get rid of that too
+				if (is_dir_sep(submodule_rel_path[0])) {
+					submodule_rel_path++;
+				}
+			}
+
+			if (repo_submodule_init(subrepo_p, r, submodule_rel_path, null_oid()))
+				die("couldn't init submodule %s", base->buf);
+
+			if (repo_read_index(subrepo_p) < 0)
+				die("index file corrupt");
+
+			commit = lookup_commit(subrepo_p, &entry.oid);
 			if (!commit)
-				die("Commit %s in submodule path %s%s not found",
+				die("Commit %s in submodule path %s not found",
 				    oid_to_hex(&entry.oid),
-				    base->buf, entry.path);
-
-			// FIXME: This is the wrong repo instance (it refers to the superproject)
-			// it will always fail as is (will fix in later patch)
-			// This current codepath isn't executed by any existing callbacks
-			// so it wouldn't show up as an issue at this time.
-			if (repo_parse_commit(r, commit))
-				die("Invalid commit %s in submodule path %s%s",
+				    base->buf);
+
+			if (repo_parse_commit(subrepo_p, commit))
+				die("Invalid commit %s in submodule path %s",
 				    oid_to_hex(&entry.oid),
-				    base->buf, entry.path);
+				    base->buf);
 
-			oidcpy(&oid, get_commit_tree_oid(commit));
-		}
-		else
-			continue;
+			submodule_tree = repo_get_commit_tree(subrepo_p, commit);
+			oidcpy(&oid, submodule_tree ? &submodule_tree->object.oid : NULL);
 
-		len = tree_entry_len(&entry);
-		strbuf_add(base, entry.path, len);
-		strbuf_addch(base, '/');
-		retval = read_tree_at(r, lookup_tree(r, &oid),
-				      base, pathspec,
-				      fn, context);
-		strbuf_setlen(base, oldlen);
-		if (retval)
-			return -1;
+			strbuf_addch(base, '/');
+
+			retval = read_tree_at(subrepo_p, lookup_tree(subrepo_p, &oid),
+						base, pathspec,
+						fn, context);
+			if (retval)
+			    die("failed to read tree for %s", base->buf);
+			strbuf_setlen(base, oldlen);
+			repo_clear(subrepo_p);
+		}
+		// else, this is a file (or a submodule, but no pathspec->recurse_submodules)
 	}
 	return 0;
 }
-- 
gitgitgadget
Previous: Jonathan TanNext: Phillip Wood
Message 21 of 48 in “archive: add --recurse-submodules to git-archive command”
  1. archive: add --recurse-submodules to git-archive commandHeather Lapointe via GitGitGadget, Oct 12, 2022
  2. 0/2 archive: Add --recurse-submodules to git-archive commandHeather Lapointe via GitGitGadget, Oct 13, 2022
  3. 2/2 archive: fix a case of submodule in submodule traversalAlphadelta14 via GitGitGadget, Oct 13, 2022
  4. 1/2 archive: add --recurse-submodules to git-archive commandAlphadelta14 via GitGitGadget, Oct 13, 2022
  5. René ScharfeOct 13, 2022
  6. Heather LapointeOct 13, 2022
  7. René ScharfeOct 13, 2022
  8. Heather LapointeOct 13, 2022
  9. René ScharfeOct 14, 2022
  10. 0/9 archive: Add --recurse-submodules to git-archive commandHeather Lapointe via GitGitGadget, Oct 17, 2022
  11. 1/9 tree: do not use the_repository for tree traversal methods.Alphadelta14 via GitGitGadget, Oct 17, 2022
  12. Junio C HamanoOct 17, 2022
  13. Glen ChooOct 26, 2022
  14. Jonathan TanOct 27, 2022
  15. Junio C HamanoOct 27, 2022
  16. 2/9 tree: update cases to use repo_ tree methodsHeather Lapointe via GitGitGadget, Oct 17, 2022
  17. 3/9 tree: increase test coverage for tree.cHeather Lapointe via GitGitGadget, Oct 17, 2022
  18. Phillip WoodOct 17, 2022
  19. Junio C HamanoOct 17, 2022
  20. Jonathan TanOct 27, 2022
  21. 4/9 tree: handle submodule case for read_tree_at properlyHeather Lapointe via GitGitGadget, Oct 17, 2022
  22. Phillip WoodOct 17, 2022
  23. Junio C HamanoOct 17, 2022
  24. Glen ChooOct 26, 2022
  25. Jonathan TanOct 27, 2022
  26. 5/9 tree: add repository parameter to read_tree_fn_tHeather Lapointe via GitGitGadget, Oct 17, 2022
  27. 6/9 archive: pass repo objects to write_archive handlersHeather Lapointe via GitGitGadget, Oct 17, 2022
  28. Phillip WoodOct 17, 2022
  29. 7/9 archive: remove global repository from archive_argsHeather Lapointe via GitGitGadget, Oct 17, 2022
  30. 9/9 archive: add tests for git archive --recurse-submodulesHeather Lapointe via GitGitGadget, Oct 17, 2022
  31. Jonathan TanOct 27, 2022
  32. Glen ChooOct 27, 2022
  33. Ævar Arnfjörð BjarmasonOct 28, 2022
  34. 8/9 archive: add --recurse-submodules to git-archive commandHeather Lapointe via GitGitGadget, Oct 17, 2022
  35. Glen ChooOct 26, 2022
  36. René ScharfeOct 27, 2022
  37. Glen ChooOct 27, 2022
  38. Glen ChooOct 27, 2022
  39. Glen ChooOct 27, 2022
  40. Phillip WoodOct 17, 2022
  41. Junio C HamanoOct 18, 2022
  42. Heather LapointeOct 18, 2022
  43. Junio C HamanoOct 19, 2022
  44. Junio C HamanoOct 19, 2022
  45. Junio C HamanoOct 20, 2022
  46. Junio C HamanoOct 21, 2022
  47. Glen ChooOct 26, 2022
  48. Heather LapointeOct 28, 2022

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.