From: Elijah Newren <newren@gmail.com>
To: git@vger.kernel.org
Cc: sbeller@google.com, szeder.dev@gmail.com, j6t@kdbg.org,
jrnieder@gmail.com, peff@peff.net, git@matthieu-moy.fr,
Elijah Newren <newren@gmail.com>
Subject: [PATCHv6 19/31] merge-recursive: add get_directory_renames()
Date: Fri, 5 Jan 2018 12:26:59 -0800 [thread overview]
Message-ID: <20180105202711.24311-20-newren@gmail.com> (raw)
In-Reply-To: <20180105202711.24311-1-newren@gmail.com>
This populates a list of directory renames for us. The list of
directory renames is not yet used, but will be in subsequent commits.
Signed-off-by: Elijah Newren <newren@gmail.com>
---
merge-recursive.c | 155 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 152 insertions(+), 3 deletions(-)
diff --git a/merge-recursive.c b/merge-recursive.c
index c5932d5c5..6aef357e7 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -1384,6 +1384,138 @@ static struct diff_queue_struct *get_diffpairs(struct merge_options *o,
return ret;
}
+static void get_renamed_dir_portion(const char *old_path, const char *new_path,
+ char **old_dir, char **new_dir)
+{
+ char *end_of_old, *end_of_new;
+ int old_len, new_len;
+
+ *old_dir = NULL;
+ *new_dir = NULL;
+
+ /* For
+ * "a/b/c/d/foo.c" -> "a/b/something-else/d/foo.c"
+ * the "d/foo.c" part is the same, we just want to know that
+ * "a/b/c" was renamed to "a/b/something-else"
+ * so, for this example, this function returns "a/b/c" in
+ * *old_dir and "a/b/something-else" in *new_dir.
+ *
+ * Also, if the basename of the file changed, we don't care. We
+ * want to know which portion of the directory, if any, changed.
+ */
+ end_of_old = strrchr(old_path, '/');
+ end_of_new = strrchr(new_path, '/');
+
+ if (end_of_old == NULL || end_of_new == NULL)
+ return;
+ while (*--end_of_new == *--end_of_old &&
+ end_of_old != old_path &&
+ end_of_new != new_path)
+ ; /* Do nothing; all in the while loop */
+ /*
+ * We've found the first non-matching character in the directory
+ * paths. That means the current directory we were comparing
+ * represents the rename. Move end_of_old and end_of_new back
+ * to the full directory name.
+ */
+ if (*end_of_old == '/')
+ end_of_old++;
+ if (*end_of_old != '/')
+ end_of_new++;
+ end_of_old = strchr(end_of_old, '/');
+ end_of_new = strchr(end_of_new, '/');
+
+ /*
+ * It may have been the case that old_path and new_path were the same
+ * directory all along. Don't claim a rename if they're the same.
+ */
+ old_len = end_of_old - old_path;
+ new_len = end_of_new - new_path;
+
+ if (old_len != new_len || strncmp(old_path, new_path, old_len)) {
+ *old_dir = xstrndup(old_path, old_len);
+ *new_dir = xstrndup(new_path, new_len);
+ }
+}
+
+static struct hashmap *get_directory_renames(struct diff_queue_struct *pairs,
+ struct tree *tree)
+{
+ struct hashmap *dir_renames;
+ struct hashmap_iter iter;
+ struct dir_rename_entry *entry;
+ int i;
+
+ dir_renames = malloc(sizeof(struct hashmap));
+ dir_rename_init(dir_renames);
+ for (i = 0; i < pairs->nr; ++i) {
+ struct string_list_item *item;
+ int *count;
+ struct diff_filepair *pair = pairs->queue[i];
+ char *old_dir, *new_dir;
+
+ /* File not part of directory rename if it wasn't renamed */
+ if (pair->status != 'R')
+ continue;
+
+ get_renamed_dir_portion(pair->one->path, pair->two->path,
+ &old_dir, &new_dir);
+ if (!old_dir)
+ /* Directory didn't change at all; ignore this one. */
+ continue;
+
+ entry = dir_rename_find_entry(dir_renames, old_dir);
+ if (!entry) {
+ entry = xmalloc(sizeof(struct dir_rename_entry));
+ dir_rename_entry_init(entry, old_dir);
+ hashmap_put(dir_renames, entry);
+ } else {
+ free(old_dir);
+ }
+ item = string_list_lookup(&entry->possible_new_dirs, new_dir);
+ if (!item) {
+ item = string_list_insert(&entry->possible_new_dirs,
+ new_dir);
+ item->util = xcalloc(1, sizeof(int));
+ } else {
+ free(new_dir);
+ }
+ count = item->util;
+ *count += 1;
+ }
+
+ hashmap_iter_init(dir_renames, &iter);
+ while ((entry = hashmap_iter_next(&iter))) {
+ int max = 0;
+ int bad_max = 0;
+ char *best = NULL;
+
+ for (i = 0; i < entry->possible_new_dirs.nr; i++) {
+ int *count = entry->possible_new_dirs.items[i].util;
+
+ if (*count == max)
+ bad_max = max;
+ else if (*count > max) {
+ max = *count;
+ best = entry->possible_new_dirs.items[i].string;
+ }
+ }
+ if (bad_max == max)
+ entry->non_unique_new_dir = 1;
+ else {
+ assert(entry->new_dir.len == 0);
+ strbuf_addstr(&entry->new_dir, best);
+ }
+ /* Strings were xstrndup'ed before inserting into string-list,
+ * so ask string_list to remove the entries for us.
+ */
+ entry->possible_new_dirs.strdup_strings = 1;
+ string_list_clear(&entry->possible_new_dirs, 1);
+ }
+
+ return dir_renames;
+}
+
/*
* Get information of all renames which occurred in 'pairs', making use of
* any implicit directory renames inferred from the other side of history.
@@ -1695,8 +1827,21 @@ struct rename_info {
struct string_list *merge_renames;
};
-static void initial_cleanup_rename(struct diff_queue_struct *pairs)
+static void initial_cleanup_rename(struct diff_queue_struct *pairs,
+ struct hashmap *dir_renames)
{
+ struct hashmap_iter iter;
+ struct dir_rename_entry *e;
+
+ hashmap_iter_init(dir_renames, &iter);
+ while ((e = hashmap_iter_next(&iter))) {
+ free(e->dir);
+ strbuf_release(&e->new_dir);
+ /* possible_new_dirs already cleared in get_directory_renames */
+ }
+ hashmap_free(dir_renames, 1);
+ free(dir_renames);
+
free(pairs->queue);
free(pairs);
}
@@ -1709,6 +1854,7 @@ static int handle_renames(struct merge_options *o,
struct rename_info *ri)
{
struct diff_queue_struct *head_pairs, *merge_pairs;
+ struct hashmap *dir_re_head, *dir_re_merge;
int clean;
ri->head_renames = NULL;
@@ -1720,6 +1866,9 @@ static int handle_renames(struct merge_options *o,
head_pairs = get_diffpairs(o, common, head);
merge_pairs = get_diffpairs(o, common, merge);
+ dir_re_head = get_directory_renames(head_pairs, head);
+ dir_re_merge = get_directory_renames(merge_pairs, merge);
+
ri->head_renames = get_renames(o, head_pairs, head,
common, head, merge, entries);
ri->merge_renames = get_renames(o, merge_pairs, merge,
@@ -1731,8 +1880,8 @@ static int handle_renames(struct merge_options *o,
* data structures are still needed and referenced in
* process_entry(). But there are a few things we can free now.
*/
- initial_cleanup_rename(head_pairs);
- initial_cleanup_rename(merge_pairs);
+ initial_cleanup_rename(head_pairs, dir_re_head);
+ initial_cleanup_rename(merge_pairs, dir_re_merge);
return clean;
}
--
2.14.2
next prev parent reply other threads:[~2018-01-05 20:28 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-05 20:26 [PATCHv6 00/31] Add directory rename detection to git Elijah Newren
2018-01-05 20:26 ` [PATCHv6 01/31] directory rename detection: basic testcases Elijah Newren
2018-01-05 20:26 ` [PATCHv6 02/31] directory rename detection: directory splitting testcases Elijah Newren
2018-01-05 20:26 ` [PATCHv6 03/31] directory rename detection: testcases to avoid taking detection too far Elijah Newren
2018-01-26 11:37 ` SZEDER Gábor
2018-01-26 16:55 ` Elijah Newren
2018-01-05 20:26 ` [PATCHv6 04/31] directory rename detection: partially renamed directory testcase/discussion Elijah Newren
2018-01-05 20:26 ` [PATCHv6 05/31] directory rename detection: files/directories in the way of some renames Elijah Newren
2018-01-05 20:26 ` [PATCHv6 06/31] directory rename detection: testcases checking which side did the rename Elijah Newren
2018-01-05 20:26 ` [PATCHv6 07/31] directory rename detection: more involved edge/corner testcases Elijah Newren
2018-01-05 20:26 ` [PATCHv6 08/31] directory rename detection: testcases exploring possibly suboptimal merges Elijah Newren
2018-01-05 20:26 ` [PATCHv6 09/31] directory rename detection: miscellaneous testcases to complete coverage Elijah Newren
2018-01-05 20:26 ` [PATCHv6 10/31] directory rename detection: tests for handling overwriting untracked files Elijah Newren
2018-01-05 20:26 ` [PATCHv6 11/31] directory rename detection: tests for handling overwriting dirty files Elijah Newren
2018-01-05 20:26 ` [PATCHv6 12/31] merge-recursive: move the get_renames() function Elijah Newren
2018-01-05 20:26 ` [PATCHv6 13/31] merge-recursive: introduce new functions to handle rename logic Elijah Newren
2018-01-05 20:26 ` [PATCHv6 14/31] merge-recursive: fix leaks of allocated renames and diff_filepairs Elijah Newren
2018-01-05 20:26 ` [PATCHv6 15/31] merge-recursive: make !o->detect_rename codepath more obvious Elijah Newren
2018-01-05 20:26 ` [PATCHv6 16/31] merge-recursive: split out code for determining diff_filepairs Elijah Newren
2018-01-05 20:26 ` [PATCHv6 17/31] merge-recursive: add a new hashmap for storing directory renames Elijah Newren
2018-01-05 20:26 ` [PATCHv6 18/31] merge-recursive: make a helper function for cleanup for handle_renames Elijah Newren
2018-01-05 20:26 ` Elijah Newren [this message]
2018-01-05 20:27 ` [PATCHv6 20/31] merge-recursive: check for directory level conflicts Elijah Newren
2018-01-05 20:27 ` [PATCHv6 21/31] merge-recursive: add a new hashmap for storing file collisions Elijah Newren
2018-01-05 20:27 ` [PATCHv6 22/31] merge-recursive: add computation of collisions due to dir rename & merging Elijah Newren
2018-01-05 20:27 ` [PATCHv6 23/31] merge-recursive: check for file level conflicts then get new name Elijah Newren
2018-01-05 20:27 ` [PATCHv6 24/31] merge-recursive: when comparing files, don't include trees Elijah Newren
2018-01-05 20:27 ` [PATCHv6 25/31] merge-recursive: apply necessary modifications for directory renames Elijah Newren
2018-01-05 20:27 ` [PATCHv6 26/31] merge-recursive: avoid clobbering untracked files with " Elijah Newren
2018-01-05 20:27 ` [PATCHv6 27/31] merge-recursive: fix overwriting dirty files involved in renames Elijah Newren
2018-01-05 20:27 ` [PATCHv6 28/31] merge-recursive: fix remaining directory rename + dirty overwrite cases Elijah Newren
2018-01-05 20:27 ` [PATCHv6 29/31] directory rename detection: new testcases showcasing a pair of bugs Elijah Newren
2018-01-05 20:27 ` [PATCHv6 30/31] merge-recursive: avoid spurious rename/rename conflict from dir renames Elijah Newren
2018-01-05 20:27 ` [PATCHv6 31/31] merge-recursive: ensure we write updates for directory-renamed file Elijah Newren
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180105202711.24311-20-newren@gmail.com \
--to=newren@gmail.com \
--cc=git@matthieu-moy.fr \
--cc=git@vger.kernel.org \
--cc=j6t@kdbg.org \
--cc=jrnieder@gmail.com \
--cc=peff@peff.net \
--cc=sbeller@google.com \
--cc=szeder.dev@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.