[PATCH 12/20] merge-ort: have process_entries operate in a defined order

From: Elijah Newren <newren@gmail.com>
Date: Oct 30, 2020, 03:41 UTC
Message-ID: <20201030034131.1479968-13-newren@gmail.com>
In-Reply-To: <20201030034131.1479968-1-newren@gmail.com>

We want to handle paths below a directory before needing to handle the directory itself. Also, we want to handle the directory immediately after the paths below it, so we can't use simple lexicographic ordering from strcmp (which would insert foo.txt between foo and foo/file.c). Copy string_list_df_name_compare() from merge-recursive.c, and set up a string list of paths sorted by that function so that we can iterate in the desired order.

Signed-off-by: Elijah Newren <newren@gmail.com>
---
 merge-ort.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 47 insertions(+), 2 deletions(-)

diff --git a/merge-ort.c b/merge-ort.c
index f4bf1baf78..31c16edd3d 100644
--- a/merge-ort.c
+++ b/merge-ort.c
@@ -324,6 +324,33 @@ static int detect_and_process_renames(struct merge_options *opt,
 	return clean;
 }
 
+static int string_list_df_name_compare(const char *one, const char *two)
+{
+	int onelen = strlen(one);
+	int twolen = strlen(two);
+	/*
+	 * Here we only care that entries for D/F conflicts are
+	 * adjacent, in particular with the file of the D/F conflict
+	 * appearing before files below the corresponding directory.
+	 * The order of the rest of the list is irrelevant for us.
+	 *
+	 * To achieve this, we sort with df_name_compare and provide
+	 * the mode S_IFDIR so that D/F conflicts will sort correctly.
+	 * We use the mode S_IFDIR for everything else for simplicity,
+	 * since in other cases any changes in their order due to
+	 * sorting cause no problems for us.
+	 */
+	int cmp = df_name_compare(one, onelen, S_IFDIR,
+				  two, twolen, S_IFDIR);
+	/*
+	 * Now that 'foo' and 'foo/bar' compare equal, we have to make sure
+	 * that 'foo' comes before 'foo/bar'.
+	 */
+	if (cmp)
+		return cmp;
+	return onelen - twolen;
+}
+
 /* Per entry merge function */
 static void process_entry(struct merge_options *opt,
 			  const char *path,
@@ -414,23 +441,41 @@ static void process_entries(struct merge_options *opt,
 {
 	struct hashmap_iter iter;
 	struct strmap_entry *e;
+	struct string_list plist = STRING_LIST_INIT_NODUP;
+	struct string_list_item *entry;
 
 	if (strmap_empty(&opt->priv->paths)) {
 		oidcpy(result_oid, opt->repo->hash_algo->empty_tree);
 		return;
 	}
 
+	/* Hack to pre-allocate plist to the desired size */
+	ALLOC_GROW(plist.items, strmap_get_size(&opt->priv->paths), plist.alloc);
+
+	/* Put every entry from paths into plist, then sort */
 	strmap_for_each_entry(&opt->priv->paths, &iter, e) {
+		string_list_append(&plist, e->key)->util = e->value;
+	}
+	plist.cmp = string_list_df_name_compare;
+	string_list_sort(&plist);
+
+	/*
+	 * Iterate over the items in reverse order, so we can handle paths
+	 * below a directory before needing to handle the directory itself.
+	 */
+	for (entry = &plist.items[plist.nr-1]; entry >= plist.items; --entry) {
+		char *path = entry->string;
 		/*
 		 * WARNING: If ci->merged.clean is true, then ci does not
 		 * actually point to a conflict_info but a struct merge_info.
 		 */
-		struct conflict_info *ci = e->value;
+		struct conflict_info *ci = entry->util;
 
 		if (!ci->merged.clean)
-			process_entry(opt, e->key, e->value);
+			process_entry(opt, path, ci);
 	}
 
+	string_list_clear(&plist, 0);
 	die("Tree creation not yet implemented");
 }

-- 
2.29.1.56.ga287c268e6.dirty