git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "Elijah Newren via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: Derrick Stolee <dstolee@microsoft.com>,
	Jonathan Tan <jonathantanmy@google.com>,
	Taylor Blau <me@ttaylorr.com>, Elijah Newren <newren@gmail.com>,
	Derrick Stolee <stolee@gmail.com>,
	Elijah Newren <newren@gmail.com>,
	Elijah Newren <newren@gmail.com>
Subject: [PATCH v2 07/13] merge-ort: populate caches of rename detection results
Date: Tue, 04 May 2021 02:12:13 +0000	[thread overview]
Message-ID: <02d517f052a35a952c726e7e941650ce424abb85.1620094339.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.859.v2.git.1620094339.gitgitgadget@gmail.com>

From: Elijah Newren <newren@gmail.com>

Fill in cache_pairs, cached_target_names, and cached_irrelevant based on
rename detection results.  Future commits will make use of these values.

Signed-off-by: Elijah Newren <newren@gmail.com>
---
 merge-ort.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 70 insertions(+), 2 deletions(-)

diff --git a/merge-ort.c b/merge-ort.c
index 8602f88a960c..5523fc9e86b3 100644
--- a/merge-ort.c
+++ b/merge-ort.c
@@ -2333,6 +2333,65 @@ static void resolve_diffpair_statuses(struct diff_queue_struct *q)
 	}
 }
 
+static void possibly_cache_new_pair(struct rename_info *renames,
+				    struct diff_filepair *p,
+				    unsigned side,
+				    char *new_path)
+{
+	char *old_value;
+	int dir_renamed_side = 0;
+
+	if (new_path) {
+		/*
+		 * Directory renames happen on the other side of history from
+		 * the side that adds new files to the old directory.
+		 */
+		dir_renamed_side = 3 - side;
+	} else {
+		int val = strintmap_get(&renames->relevant_sources[side],
+					p->one->path);
+		if (val == RELEVANT_NO_MORE) {
+			assert(p->status == 'D');
+			strset_add(&renames->cached_irrelevant[side],
+				   p->one->path);
+		}
+		if (val <= 0)
+			return;
+	}
+
+	if (p->status == 'D') {
+		/*
+		 * If we already had this delete, we'll just set it's value
+		 * to NULL again, so no harm.
+		 */
+		strmap_put(&renames->cached_pairs[side], p->one->path, NULL);
+	} else if (p->status == 'R') {
+		if (new_path) {
+			new_path = xstrdup(new_path);
+			old_value = strmap_put(&renames->cached_pairs[dir_renamed_side],
+					       p->two->path, new_path);
+			strset_add(&renames->cached_target_names[dir_renamed_side],
+				   new_path);
+			assert(!old_value);
+		}
+		if (!new_path)
+			new_path = p->two->path;
+		new_path = xstrdup(new_path);
+		old_value = strmap_put(&renames->cached_pairs[side],
+				       p->one->path, new_path);
+		strset_add(&renames->cached_target_names[side],
+			   new_path);
+		free(old_value);
+	} else if (p->status == 'A' && new_path) {
+		new_path = xstrdup(new_path);
+		old_value = strmap_put(&renames->cached_pairs[dir_renamed_side],
+				       p->two->path, new_path);
+		strset_add(&renames->cached_target_names[dir_renamed_side],
+			   new_path);
+		assert(!old_value);
+	}
+}
+
 static int compare_pairs(const void *a_, const void *b_)
 {
 	const struct diff_filepair *a = *((const struct diff_filepair **)a_);
@@ -2415,6 +2474,7 @@ static int collect_renames(struct merge_options *opt,
 		char *new_path; /* non-NULL only with directory renames */
 
 		if (p->status != 'A' && p->status != 'R') {
+			possibly_cache_new_pair(renames, p, side_index, NULL);
 			diff_free_filepair(p);
 			continue;
 		}
@@ -2426,11 +2486,11 @@ static int collect_renames(struct merge_options *opt,
 						      &collisions,
 						      &clean);
 
+		possibly_cache_new_pair(renames, p, side_index, new_path);
 		if (p->status != 'R' && !new_path) {
 			diff_free_filepair(p);
 			continue;
 		}
-
 		if (new_path)
 			apply_directory_rename_modifications(opt, p, new_path);
 
@@ -3701,8 +3761,16 @@ static void merge_start(struct merge_options *opt, struct merge_result *result)
 					 NULL, 1);
 		strmap_init_with_options(&renames->dir_renames[i],
 					 NULL, 0);
+		/*
+		 * relevant_sources uses -1 for the default, because we need
+		 * to be able to distinguish not-in-strintmap from valid
+		 * relevant_source values from enum file_rename_relevance.
+		 * In particular, possibly_cache_new_pair() expects a negative
+		 * value for not-found entries.
+		 */
 		strintmap_init_with_options(&renames->relevant_sources[i],
-					    0, NULL, 0);
+					    -1 /* explicitly invalid */,
+					    NULL, 0);
 		strmap_init_with_options(&renames->cached_pairs[i],
 					 NULL, 1);
 		strset_init_with_options(&renames->cached_irrelevant[i],
-- 
gitgitgadget


  parent reply	other threads:[~2021-05-04  2:12 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-24 21:32 [PATCH 0/7] Optimization batch 11: avoid repeatedly detecting same renames Elijah Newren via GitGitGadget
2021-03-24 21:32 ` [PATCH 1/7] merge-ort: add data structures for in-memory caching of rename detection Elijah Newren via GitGitGadget
2021-03-24 21:32 ` [PATCH 2/7] merge-ort: populate caches of rename detection results Elijah Newren via GitGitGadget
2021-03-24 21:32 ` [PATCH 3/7] merge-ort: add code to check for whether cached renames can be reused Elijah Newren via GitGitGadget
2021-03-24 21:32 ` [PATCH 4/7] merge-ort: avoid accidental API mis-use Elijah Newren via GitGitGadget
2021-03-24 21:32 ` [PATCH 5/7] merge-ort: preserve cached renames for the appropriate side Elijah Newren via GitGitGadget
2021-03-24 21:32 ` [PATCH 6/7] merge-ort: add helper functions for using cached renames Elijah Newren via GitGitGadget
2021-03-24 21:32 ` [PATCH 7/7] merge-ort, diffcore-rename: employ cached renames when possible Elijah Newren via GitGitGadget
2021-03-24 22:04 ` [PATCH 0/7] Optimization batch 11: avoid repeatedly detecting same renames Junio C Hamano
2021-03-24 23:25   ` Elijah Newren
2021-03-25 18:59     ` Junio C Hamano
2021-03-29 22:34       ` Elijah Newren
2021-03-30 12:07         ` Derrick Stolee
2021-05-04  2:12 ` [PATCH v2 00/13] " Elijah Newren via GitGitGadget
2021-05-04  2:12   ` [PATCH v2 01/13] t6423: rename file within directory that other side renamed Elijah Newren via GitGitGadget
2021-05-04  2:12   ` [PATCH v2 02/13] Documentation/technical: describe remembering renames optimization Elijah Newren via GitGitGadget
2021-05-04  2:12   ` [PATCH v2 03/13] fast-rebase: change assert() to BUG() Elijah Newren via GitGitGadget
2021-05-04  2:12   ` [PATCH v2 04/13] fast-rebase: write conflict state to working tree, index, and HEAD Elijah Newren via GitGitGadget
2021-05-17 13:32     ` Derrick Stolee
2021-05-18  3:42       ` Elijah Newren
2021-05-18 13:54         ` Derrick Stolee
2021-05-04  2:12   ` [PATCH v2 05/13] t6429: testcases for remembering renames Elijah Newren via GitGitGadget
2021-05-04  2:12   ` [PATCH v2 06/13] merge-ort: add data structures for in-memory caching of rename detection Elijah Newren via GitGitGadget
2021-05-17 13:41     ` Derrick Stolee
2021-05-18  3:55       ` Elijah Newren
2021-05-18 13:57         ` Derrick Stolee
2021-05-04  2:12   ` Elijah Newren via GitGitGadget [this message]
2021-05-17 13:51     ` [PATCH v2 07/13] merge-ort: populate caches of rename detection results Derrick Stolee
2021-05-20  0:48       ` Elijah Newren
2021-05-04  2:12   ` [PATCH v2 08/13] merge-ort: add code to check for whether cached renames can be reused Elijah Newren via GitGitGadget
2021-05-17 14:01     ` Derrick Stolee
2021-05-04  2:12   ` [PATCH v2 09/13] merge-ort: avoid accidental API mis-use Elijah Newren via GitGitGadget
2021-05-17 14:10     ` Derrick Stolee
2021-05-04  2:12   ` [PATCH v2 10/13] merge-ort: preserve cached renames for the appropriate side Elijah Newren via GitGitGadget
2021-05-04  2:12   ` [PATCH v2 11/13] merge-ort: add helper functions for using cached renames Elijah Newren via GitGitGadget
2021-05-04  2:12   ` [PATCH v2 12/13] merge-ort: handle interactions of caching and rename/rename(1to1) cases Elijah Newren via GitGitGadget
2021-05-17 14:16     ` Derrick Stolee
2021-05-04  2:12   ` [PATCH v2 13/13] merge-ort, diffcore-rename: employ cached renames when possible Elijah Newren via GitGitGadget
2021-05-17 14:23     ` Derrick Stolee
2021-05-20  0:36       ` Elijah Newren
2021-05-22 11:17         ` Derrick Stolee
2021-05-14 17:37   ` [PATCH v2 00/13] Optimization batch 11: avoid repeatedly detecting same renames Elijah Newren
2021-05-14 21:04     ` Derrick Stolee
2021-05-20  6:09   ` [PATCH v3 " Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 01/13] t6423: rename file within directory that other side renamed Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 02/13] Documentation/technical: describe remembering renames optimization Elijah Newren via GitGitGadget
2021-05-20 11:32       ` Bagas Sanjaya
2021-05-20 15:14         ` Kerry, Richard
2021-05-20 16:34         ` Elijah Newren
2021-05-20  6:09     ` [PATCH v3 03/13] fast-rebase: change assert() to BUG() Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 04/13] fast-rebase: write conflict state to working tree, index, and HEAD Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 05/13] t6429: testcases for remembering renames Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 06/13] merge-ort: add data structures for in-memory caching of rename detection Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 07/13] merge-ort: populate caches of rename detection results Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 08/13] merge-ort: add code to check for whether cached renames can be reused Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 09/13] merge-ort: avoid accidental API mis-use Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 10/13] merge-ort: preserve cached renames for the appropriate side Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 11/13] merge-ort: add helper functions for using cached renames Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 12/13] merge-ort: handle interactions of caching and rename/rename(1to1) cases Elijah Newren via GitGitGadget
2021-05-20  6:09     ` [PATCH v3 13/13] merge-ort, diffcore-rename: employ cached renames when possible Elijah Newren via GitGitGadget
2021-05-22 11:17     ` [PATCH v3 00/13] Optimization batch 11: avoid repeatedly detecting same renames Derrick Stolee

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

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=02d517f052a35a952c726e7e941650ce424abb85.1620094339.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=jonathantanmy@google.com \
    --cc=me@ttaylorr.com \
    --cc=newren@gmail.com \
    --cc=stolee@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.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).