git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Victoria Dye via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: Victoria Dye <vdye@github.com>, Victoria Dye <vdye@github.com>
Subject: [PATCH 11/16] mktree: create tree using an in-core index
Date: Tue, 11 Jun 2024 18:24:43 +0000	[thread overview]
Message-ID: <130413f2404bb27a2ede4fb00041227c90587e8e.1718130288.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.1746.git.1718130288.gitgitgadget@gmail.com>

From: Victoria Dye <vdye@github.com>

Rather than manually write out the contents of a tree object file, construct
an in-memory sparse index from the provided tree entries and create the tree
by writing out its corresponding cache tree.

This patch does not change the behavior of the 'mktree' command. However,
constructing the tree this way will substantially simplify future extensions
to the command's functionality, including handling deeper-than-toplevel tree
entries and applying the provided entries to an existing tree.

Signed-off-by: Victoria Dye <vdye@github.com>
---
 builtin/mktree.c | 74 +++++++++++++++++++++++++++++++++++-------------
 1 file changed, 55 insertions(+), 19 deletions(-)

diff --git a/builtin/mktree.c b/builtin/mktree.c
index e9e2134136f..12f68187221 100644
--- a/builtin/mktree.c
+++ b/builtin/mktree.c
@@ -4,6 +4,7 @@
  * Copyright (c) Junio C Hamano, 2006, 2009
  */
 #include "builtin.h"
+#include "cache-tree.h"
 #include "gettext.h"
 #include "hex.h"
 #include "index-info.h"
@@ -24,6 +25,11 @@ struct tree_entry {
 	char name[FLEX_ARRAY];
 };
 
+static inline size_t df_path_len(size_t pathlen, unsigned int mode)
+{
+	return S_ISDIR(mode) ? pathlen - 1 : pathlen;
+}
+
 struct tree_entry_array {
 	size_t nr, alloc;
 	struct tree_entry **entries;
@@ -57,17 +63,25 @@ static void append_to_tree(unsigned mode, struct object_id *oid, const char *pat
 	if (literally) {
 		FLEX_ALLOC_MEM(ent, name, path, len);
 	} else {
+		size_t len_to_copy = len;
+
 		/* Normalize and validate entry path */
 		if (S_ISDIR(mode)) {
-			while(len > 0 && is_dir_sep(path[len - 1]))
-				len--;
+			while(len_to_copy > 0 && is_dir_sep(path[len_to_copy - 1]))
+				len_to_copy--;
+			len = len_to_copy + 1; /* add space for trailing slash */
 		}
-		FLEX_ALLOC_MEM(ent, name, path, len);
+		ent = xcalloc(1, st_add3(sizeof(struct tree_entry), len, 1));
+		memcpy(ent->name, path, len_to_copy);
 
 		if (!verify_path(ent->name, mode))
 			die(_("invalid path '%s'"), path);
 		if (strchr(ent->name, '/'))
 			die("path %s contains slash", path);
+
+		/* Add trailing slash to dir */
+		if (S_ISDIR(mode))
+			ent->name[len - 1] = '/';
 	}
 
 	ent->mode = mode;
@@ -86,11 +100,14 @@ static int ent_compare(const void *a_, const void *b_, void *ctx)
 	struct tree_entry *b = *(struct tree_entry **)b_;
 	int ignore_mode = *((int *)ctx);
 
-	if (ignore_mode)
-		cmp = name_compare(a->name, a->len, b->name, b->len);
-	else
-		cmp = base_name_compare(a->name, a->len, a->mode,
-					b->name, b->len, b->mode);
+	size_t a_len = a->len, b_len = b->len;
+
+	if (ignore_mode) {
+		a_len = df_path_len(a_len, a->mode);
+		b_len = df_path_len(b_len, b->mode);
+	}
+
+	cmp = name_compare(a->name, a_len, b->name, b_len);
 	return cmp ? cmp : b->order - a->order;
 }
 
@@ -106,8 +123,8 @@ static void sort_and_dedup_tree_entry_array(struct tree_entry_array *arr)
 	for (size_t i = 0; i < count; i++) {
 		struct tree_entry *curr = arr->entries[i];
 		if (prev &&
-		    !name_compare(prev->name, prev->len,
-				  curr->name, curr->len)) {
+		    !name_compare(prev->name, df_path_len(prev->len, prev->mode),
+				  curr->name, df_path_len(curr->len, curr->mode))) {
 			FREE_AND_NULL(curr);
 		} else {
 			arr->entries[arr->nr++] = curr;
@@ -120,24 +137,43 @@ static void sort_and_dedup_tree_entry_array(struct tree_entry_array *arr)
 	QSORT_S(arr->entries, arr->nr, ent_compare, &ignore_mode);
 }
 
+static int add_tree_entry_to_index(struct index_state *istate,
+				   struct tree_entry *ent)
+{
+	struct cache_entry *ce;
+	struct strbuf ce_name = STRBUF_INIT;
+	strbuf_add(&ce_name, ent->name, ent->len);
+
+	ce = make_cache_entry(istate, ent->mode, &ent->oid, ent->name, 0, 0);
+	if (!ce)
+		return error(_("make_cache_entry failed for path '%s'"), ent->name);
+
+	add_index_entry(istate, ce, ADD_CACHE_JUST_APPEND);
+	strbuf_release(&ce_name);
+	return 0;
+}
+
 static void write_tree(struct tree_entry_array *arr, struct object_id *oid)
 {
-	struct strbuf buf;
-	size_t size = 0;
+	struct index_state istate = INDEX_STATE_INIT(the_repository);
+	istate.sparse_index = 1;
 
 	sort_and_dedup_tree_entry_array(arr);
-	for (size_t i = 0; i < arr->nr; i++)
-		size += 32 + arr->entries[i]->len;
 
-	strbuf_init(&buf, size);
+	/* Construct an in-memory index from the provided entries */
 	for (size_t i = 0; i < arr->nr; i++) {
 		struct tree_entry *ent = arr->entries[i];
-		strbuf_addf(&buf, "%o %s%c", ent->mode, ent->name, '\0');
-		strbuf_add(&buf, ent->oid.hash, the_hash_algo->rawsz);
+
+		if (add_tree_entry_to_index(&istate, ent))
+			die(_("failed to add tree entry '%s'"), ent->name);
 	}
 
-	write_object_file(buf.buf, buf.len, OBJ_TREE, oid);
-	strbuf_release(&buf);
+	/* Write out new tree */
+	if (cache_tree_update(&istate, WRITE_TREE_SILENT | WRITE_TREE_MISSING_OK))
+		die(_("failed to write tree"));
+	oidcpy(oid, &istate.cache_tree->oid);
+
+	release_index(&istate);
 }
 
 static void write_tree_literally(struct tree_entry_array *arr,
-- 
gitgitgadget


  parent reply	other threads:[~2024-06-11 18:25 UTC|newest]

Thread overview: 65+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-11 18:24 [PATCH 00/16] mktree: support more flexible usage Victoria Dye via GitGitGadget
2024-06-11 18:24 ` [PATCH 01/16] mktree: use OPT_BOOL Victoria Dye via GitGitGadget
2024-06-11 18:24 ` [PATCH 02/16] mktree: rename treeent to tree_entry Victoria Dye via GitGitGadget
2024-06-12  9:40   ` Patrick Steinhardt
2024-06-11 18:24 ` [PATCH 03/16] mktree: use non-static tree_entry array Victoria Dye via GitGitGadget
2024-06-11 18:45   ` Eric Sunshine
2024-06-12  9:40   ` Patrick Steinhardt
2024-06-11 18:24 ` [PATCH 04/16] update-index: generalize 'read_index_info' Victoria Dye via GitGitGadget
2024-06-11 22:45   ` Junio C Hamano
2024-06-11 18:24 ` [PATCH 05/16] index-info.c: identify empty input lines in read_index_info Victoria Dye via GitGitGadget
2024-06-11 22:52   ` Junio C Hamano
2024-06-18 17:33     ` Victoria Dye
2024-06-11 18:24 ` [PATCH 06/16] index-info.c: parse object type in provided " Victoria Dye via GitGitGadget
2024-06-12  1:54   ` Junio C Hamano
2024-06-11 18:24 ` [PATCH 07/16] mktree: use read_index_info to read stdin lines Victoria Dye via GitGitGadget
2024-06-12  2:11   ` Junio C Hamano
2024-06-12  9:40   ` Patrick Steinhardt
2024-06-12 18:35     ` Junio C Hamano
2024-06-11 18:24 ` [PATCH 08/16] mktree: add a --literally option Victoria Dye via GitGitGadget
2024-06-12  2:18   ` Junio C Hamano
2024-06-11 18:24 ` [PATCH 09/16] mktree: validate paths more carefully Victoria Dye via GitGitGadget
2024-06-12  2:26   ` Junio C Hamano
2024-06-12 19:01     ` Victoria Dye
2024-06-12 19:45       ` Junio C Hamano
2024-06-11 18:24 ` [PATCH 10/16] mktree: overwrite duplicate entries Victoria Dye via GitGitGadget
2024-06-12  9:40   ` Patrick Steinhardt
2024-06-12 18:48     ` Victoria Dye
2024-06-11 18:24 ` Victoria Dye via GitGitGadget [this message]
2024-06-12  9:40   ` [PATCH 11/16] mktree: create tree using an in-core index Patrick Steinhardt
2024-06-11 18:24 ` [PATCH 12/16] mktree: use iterator struct to add tree entries to index Victoria Dye via GitGitGadget
2024-06-12  9:40   ` Patrick Steinhardt
2024-06-13 18:38     ` Victoria Dye
2024-06-11 18:24 ` [PATCH 13/16] mktree: add directory-file conflict hashmap Victoria Dye via GitGitGadget
2024-06-11 18:24 ` [PATCH 14/16] mktree: optionally add to an existing tree Victoria Dye via GitGitGadget
2024-06-12  9:40   ` Patrick Steinhardt
2024-06-12 19:50     ` Junio C Hamano
2024-06-17 19:23     ` Victoria Dye
2024-06-11 18:24 ` [PATCH 15/16] mktree: allow deeper paths in input Victoria Dye via GitGitGadget
2024-06-11 18:24 ` [PATCH 16/16] mktree: remove entries when mode is 0 Victoria Dye via GitGitGadget
2024-06-19 21:57 ` [PATCH v2 00/17] mktree: support more flexible usage Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 01/17] mktree: use OPT_BOOL Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 02/17] mktree: rename treeent to tree_entry Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 03/17] mktree: use non-static tree_entry array Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 04/17] update-index: generalize 'read_index_info' Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 05/17] index-info.c: return unrecognized lines to caller Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 06/17] index-info.c: parse object type in provided in read_index_info Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 07/17] mktree: use read_index_info to read stdin lines Victoria Dye via GitGitGadget
2024-06-20 20:18     ` Junio C Hamano
2024-06-19 21:57   ` [PATCH v2 08/17] mktree.c: do not fail on mismatched submodule type Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 09/17] mktree: add a --literally option Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 10/17] mktree: validate paths more carefully Victoria Dye via GitGitGadget
2024-06-19 21:57   ` [PATCH v2 11/17] mktree: overwrite duplicate entries Victoria Dye via GitGitGadget
2024-06-20 22:05     ` Junio C Hamano
2024-06-19 21:58   ` [PATCH v2 12/17] mktree: create tree using an in-core index Victoria Dye via GitGitGadget
2024-06-20 22:26     ` Junio C Hamano
2024-06-19 21:58   ` [PATCH v2 13/17] mktree: use iterator struct to add tree entries to index Victoria Dye via GitGitGadget
2024-06-26 21:10     ` Junio C Hamano
2024-06-19 21:58   ` [PATCH v2 14/17] mktree: add directory-file conflict hashmap Victoria Dye via GitGitGadget
2024-06-19 21:58   ` [PATCH v2 15/17] mktree: optionally add to an existing tree Victoria Dye via GitGitGadget
2024-06-26 21:23     ` Junio C Hamano
2024-06-19 21:58   ` [PATCH v2 16/17] mktree: allow deeper paths in input Victoria Dye via GitGitGadget
2024-06-27 19:29     ` Junio C Hamano
2024-06-19 21:58   ` [PATCH v2 17/17] mktree: remove entries when mode is 0 Victoria Dye via GitGitGadget
2024-06-25 23:26   ` [PATCH v2 00/17] mktree: support more flexible usage Junio C Hamano
2024-07-10 21:40     ` Junio C Hamano

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=130413f2404bb27a2ede4fb00041227c90587e8e.1718130288.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=vdye@github.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 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 NNTP newsgroup(s).