[1/3] diffcore-rename: compute basenames of all source and dest candidates

Commit Message

Elijah Newren Feb. 6, 2021, 10:52 p.m. UTC

From: Elijah Newren <[e-mail]>

We want to make use of unique basenames to help inform rename detection,
so that more likely pairings can be checked first.  Add a new function,
not yet used, which creates a map of the unique basenames within
rename_src and another within rename_dst, together with the indices
within rename_src/rename_dst where those basenames show up.  Non-unique
basenames still show up in the map, but have an invalid index (-1).

Signed-off-by: Elijah Newren <[e-mail]>
---
 diffcore-rename.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

Patch

diff --git a/diffcore-rename.c b/diffcore-rename.c
index 74930716e70d..1c52077b04e5 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -367,6 +367,59 @@  static int find_exact_renames(struct diff_options *options)
 	return renames;
 }
 
+MAYBE_UNUSED
+static int find_basename_matches(struct diff_options *options,
+				 int minimum_score,
+				 int num_src)
+{
+	int i;
+	struct strintmap sources;
+	struct strintmap dests;
+
+	/* Create maps of basename -> fullname(s) for sources and dests */
+	strintmap_init_with_options(&sources, -1, NULL, 0);
+	strintmap_init_with_options(&dests, -1, NULL, 0);
+	for (i = 0; i < num_src; ++i) {
+		char *filename = rename_src[i].p->one->path;
+		char *base;
+
+		/* exact renames removed in remove_unneeded_paths_from_src() */
+		assert(!rename_src[i].p->one->rename_used);
+
+		base = strrchr(filename, '/');
+		base = (base ? base+1 : filename);
+
+		/* Record index within rename_src (i) if basename is unique */
+		if (strintmap_contains(&sources, base))
+			strintmap_set(&sources, base, -1);
+		else
+			strintmap_set(&sources, base, i);
+	}
+	for (i = 0; i < rename_dst_nr; ++i) {
+		char *filename = rename_dst[i].p->two->path;
+		char *base;
+
+		if (rename_dst[i].is_rename)
+			continue; /* involved in exact match already. */
+
+		base = strrchr(filename, '/');
+		base = (base ? base+1 : filename);
+
+		/* Record index within rename_dst (i) if basename is unique */
+		if (strintmap_contains(&dests, base))
+			strintmap_set(&dests, base, -1);
+		else
+			strintmap_set(&dests, base, i);
+	}
+
+	/* TODO: Make use of basenames source and destination basenames */
+
+	strintmap_clear(&sources);
+	strintmap_clear(&dests);
+
+	return 0;
+}
+
 #define NUM_CANDIDATE_PER_DST 4
 static void record_if_better(struct diff_score m[], struct diff_score *o)
 {