git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 1/8] ls-files: add --json to dump the index

From
Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Date
Jun 19, 2019, 09:58 UTC
Message-ID
<20190619095858.30124-2-pclouds@gmail.com>
In-Reply-To
<20190619095858.30124-1-pclouds@gmail.com>

So far we don't have a command to basically dump the index file out, with all its glory details. Checking some info, for example, stat time, usually involves either writing new code or firing up "xxd" and decoding values by yourself.

This --json is supposed to help that. It dumps the index in a human readable format but also easy to be processed with tools. And it will print almost enough info to reconstruct the index later.

In this patch we only dump the main part, not extensions. But at the end of the series, the entire index is dumped. The end result could be very verbose even on a small repository such as git.git.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 Documentation/git-ls-files.txt |  5 +++
 builtin/ls-files.c             | 30 +++++++++++---
 cache.h                        |  2 +
 json-writer.c                  | 16 ++++++++
 json-writer.h                  | 21 ++++++++++
 read-cache.c                   | 73 +++++++++++++++++++++++++++++++++-
 6 files changed, 140 insertions(+), 7 deletions(-)
diff --git a/Documentation/git-ls-files.txt b/Documentation/git-ls-files.txt
index 8461c0e83e..54011c8f65 100644
--- a/Documentation/git-ls-files.txt
+++ b/Documentation/git-ls-files.txt
@@ -60,6 +60,11 @@ OPTIONS
 --stage::
 	Show staged contents' mode bits, object name and stage number in the output.
 
+--json::
+	Dump the entire index content in JSON format. This is for
+	debugging purposes and the JSON structure may change from time
+	to time.
+
 --directory::
 	If a whole directory is classified as "other", show just its
 	name (with a trailing slash) and not its whole contents.
diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index 7f83c9a6f2..d00f6d3074 100644
--- a/builtin/ls-files.c
+++ b/builtin/ls-files.c
@@ -8,6 +8,7 @@
 #include "cache.h"
 #include "repository.h"
 #include "config.h"
+#include "json-writer.h"
 #include "quote.h"
 #include "dir.h"
 #include "builtin.h"
@@ -31,6 +32,7 @@ static int show_modified;
 static int show_killed;
 static int show_valid_bit;
 static int show_fsmonitor_bit;
+static int show_json;
 static int line_terminator = '\n';
 static int debug_mode;
 static int show_eol;
@@ -543,6 +545,8 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 			N_("show staged contents' object name in the output")),
 		OPT_BOOL('k', "killed", &show_killed,
 			N_("show files on the filesystem that need to be removed")),
+		OPT_BOOL(0, "json", &show_json,
+			N_("dump index content in json format")),
 		OPT_BIT(0, "directory", &dir.flags,
 			N_("show 'other' directories' names only"),
 			DIR_SHOW_OTHER_DIRECTORIES),
@@ -660,8 +664,12 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 
 	/* With no flags, we default to showing the cached files */
 	if (!(show_stage || show_deleted || show_others || show_unmerged ||
-	      show_killed || show_modified || show_resolve_undo))
+	      show_killed || show_modified || show_resolve_undo || show_json))
 		show_cached = 1;
+	if (show_json && (show_stage || show_deleted || show_others ||
+			  show_unmerged || show_killed || show_modified ||
+			  show_cached || show_resolve_undo || with_tree))
+		die(_("--show-json cannot be used with other --show- options, or --with-tree"));
 
 	if (with_tree) {
 		/*
@@ -673,10 +681,22 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 		overlay_tree_on_index(the_repository->index, with_tree, max_prefix);
 	}
 
-	show_files(the_repository, &dir);
-
-	if (show_resolve_undo)
-		show_ru_info(the_repository->index);
+	if (!show_json) {
+		show_files(the_repository, &dir);
+
+		if (show_resolve_undo)
+			show_ru_info(the_repository->index);
+	} else {
+		struct json_writer jw = JSON_WRITER_INIT;
+
+		discard_index(the_repository->index);
+		the_repository->index->jw = &jw;
+		if (repo_read_index(the_repository) < 0)
+			die("index file corrupt");
+		puts(jw.json.buf);
+		the_repository->index->jw = NULL;
+		jw_release(&jw);
+	}
 
 	if (ps_matched) {
 		int bad;
diff --git a/cache.h b/cache.h
index bf20337ef4..84d0aeed20 100644
--- a/cache.h
+++ b/cache.h
@@ -326,6 +326,7 @@ static inline unsigned int canon_mode(unsigned int mode)
 #define UNTRACKED_CHANGED	(1 << 7)
 #define FSMONITOR_CHANGED	(1 << 8)
 
+struct json_writer;
 struct split_index;
 struct untracked_cache;
 
@@ -350,6 +351,7 @@ struct index_state {
 	uint64_t fsmonitor_last_update;
 	struct ewah_bitmap *fsmonitor_dirty;
 	struct mem_pool *ce_mem_pool;
+	struct json_writer *jw;
 };
 
 /* Name hashing */
diff --git a/json-writer.c b/json-writer.c
index aadb9dbddc..281bc50b39 100644
--- a/json-writer.c
+++ b/json-writer.c
@@ -202,6 +202,22 @@ void jw_object_null(struct json_writer *jw, const char *key)
 	strbuf_addstr(&jw->json, "null");
 }
 
+void jw_object_stat_data(struct json_writer *jw, const char *name,
+			 const struct stat_data *sd)
+{
+	jw_object_inline_begin_object(jw, name);
+	jw_object_intmax(jw, "st_ctime.sec", sd->sd_ctime.sec);
+	jw_object_intmax(jw, "st_ctime.nsec", sd->sd_ctime.nsec);
+	jw_object_intmax(jw, "st_mtime.sec", sd->sd_mtime.sec);
+	jw_object_intmax(jw, "st_mtime.nsec", sd->sd_mtime.nsec);
+	jw_object_intmax(jw, "st_dev", sd->sd_dev);
+	jw_object_intmax(jw, "st_ino", sd->sd_ino);
+	jw_object_intmax(jw, "st_uid", sd->sd_uid);
+	jw_object_intmax(jw, "st_gid", sd->sd_gid);
+	jw_object_intmax(jw, "st_size", sd->sd_size);
+	jw_end(jw);
+}
+
 static void increase_indent(struct strbuf *sb,
 			    const struct json_writer *jw,
 			    int indent)
diff --git a/json-writer.h b/json-writer.h
index 83906b09c1..38f9c9bf68 100644
--- a/json-writer.h
+++ b/json-writer.h
@@ -44,6 +44,8 @@
 
 #include "strbuf.h"
 
+struct stat_data;
+
 struct json_writer
 {
 	/*
@@ -81,6 +83,8 @@ void jw_object_true(struct json_writer *jw, const char *key);
 void jw_object_false(struct json_writer *jw, const char *key);
 void jw_object_bool(struct json_writer *jw, const char *key, int value);
 void jw_object_null(struct json_writer *jw, const char *key);
+void jw_object_stat_data(struct json_writer *jw, const char *key,
+			 const struct stat_data *sd);
 void jw_object_sub_jw(struct json_writer *jw, const char *key,
 		      const struct json_writer *value);
 
@@ -104,4 +108,21 @@ void jw_array_inline_begin_array(struct json_writer *jw);
 int jw_is_terminated(const struct json_writer *jw);
 void jw_end(struct json_writer *jw);
 
+/*
+ * These _gently versions accept NULL json_writer to reduce too much
+ * branching at the call site.
+ */
+static inline void jw_object_inline_begin_array_gently(struct json_writer *jw,
+						       const char *name)
+{
+	if (jw)
+		jw_object_inline_begin_array(jw, name);
+}
+
+static inline void jw_end_gently(struct json_writer *jw)
+{
+	if (jw)
+		jw_end(jw);
+}
+
 #endif /* JSON_WRITER_H */
diff --git a/read-cache.c b/read-cache.c
index 4dd22f4f6e..eec030b3bb 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -25,6 +25,7 @@
 #include "fsmonitor.h"
 #include "thread-utils.h"
 #include "progress.h"
+#include "json-writer.h"
 
 /* Mask for the name length in ce_flags in the on-disk index */
 
@@ -1952,6 +1953,50 @@ static void *load_index_extensions(void *_data)
 	return NULL;
 }
 
+static void dump_cache_entry(struct index_state *istate,
+			     int index,
+			     unsigned long offset,
+			     const struct cache_entry *ce)
+{
+	struct strbuf sb = STRBUF_INIT;
+	struct json_writer *jw = istate->jw;
+
+	jw_array_inline_begin_object(jw);
+
+	/*
+	 * this is technically redundant, but it's for easier
+	 * navigation when there hundreds of entries
+	 */
+	jw_object_intmax(jw, "id", index);
+
+	jw_object_string(jw, "name", ce->name);
+
+	strbuf_addf(&sb, "%06o", ce->ce_mode);
+	jw_object_string(jw, "mode", sb.buf);
+	strbuf_release(&sb);
+
+	jw_object_intmax(jw, "flags", ce->ce_flags);
+	/*
+	 * again redundant info, just so you don't have to decode
+	 * flags values manually
+	 */
+	if (ce->ce_flags & CE_VALID)
+		jw_object_true(jw, "assume-unchanged");
+	if (ce->ce_flags & CE_INTENT_TO_ADD)
+		jw_object_true(jw, "intent-to-add");
+	if (ce->ce_flags & CE_SKIP_WORKTREE)
+		jw_object_true(jw, "skip-worktree");
+	if (ce_stage(ce))
+		jw_object_intmax(jw, "stage", ce_stage(ce));
+
+	jw_object_string(jw, "oid", oid_to_hex(&ce->oid));
+
+	jw_object_stat_data(jw, "stat", &ce->ce_stat_data);
+	jw_object_intmax(jw, "file-offset", offset);
+
+	jw_end(jw);
+}
+
 /*
  * A helper function that will load the specified range of cache entries
  * from the memory mapped file and add them to the given index.
@@ -1972,6 +2017,9 @@ static unsigned long load_cache_entry_block(struct index_state *istate,
 		ce = create_from_disk(ce_mem_pool, istate->version, disk_ce, &consumed, previous_ce);
 		set_index_entry(istate, i, ce);
 
+		if (istate->jw)
+			dump_cache_entry(istate, i, src_offset, ce);
+
 		src_offset += consumed;
 		previous_ce = ce;
 	}
@@ -1983,6 +2031,8 @@ static unsigned long load_all_cache_entries(struct index_state *istate,
 {
 	unsigned long consumed;
 
+	jw_object_inline_begin_array_gently(istate->jw, "entries");
+
 	if (istate->version == 4) {
 		mem_pool_init(&istate->ce_mem_pool,
 				estimate_cache_size_from_compressed(istate->cache_nr));
@@ -1993,6 +2043,8 @@ static unsigned long load_all_cache_entries(struct index_state *istate,
 
 	consumed = load_cache_entry_block(istate, istate->ce_mem_pool,
 					0, istate->cache_nr, mmap, src_offset, NULL);
+
+	jw_end_gently(istate->jw);
 	return consumed;
 }
 
@@ -2120,6 +2172,7 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 	size_t extension_offset = 0;
 	int nr_threads, cpus;
 	struct index_entry_offset_table *ieot = NULL;
+	int jw_pretty = 1;
 
 	if (istate->initialized)
 		return istate->cache_nr;
@@ -2154,6 +2207,8 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 	istate->cache_nr = ntohl(hdr->hdr_entries);
 	istate->cache_alloc = alloc_nr(istate->cache_nr);
 	istate->cache = xcalloc(istate->cache_alloc, sizeof(*istate->cache));
+	istate->timestamp.sec = st.st_mtime;
+	istate->timestamp.nsec = ST_MTIME_NSEC(st);
 	istate->initialized = 1;
 
 	p.istate = istate;
@@ -2176,6 +2231,20 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 	if (!HAVE_THREADS)
 		nr_threads = 1;
 
+	if (istate->jw) {
+		jw_object_begin(istate->jw, jw_pretty);
+		jw_object_intmax(istate->jw, "version", istate->version);
+		jw_object_string(istate->jw, "oid", oid_to_hex(&istate->oid));
+		jw_object_intmax(istate->jw, "st_mtime.sec", istate->timestamp.sec);
+		jw_object_intmax(istate->jw, "st_mtime.nsec", istate->timestamp.nsec);
+
+		/*
+		 * Threading may mess up json writing. This is for
+		 * debugging only, so performance is not a concern.
+		 */
+		nr_threads = 1;
+	}
+
 	if (nr_threads > 1) {
 		extension_offset = read_eoie_extension(mmap, mmap_size);
 		if (extension_offset) {
@@ -2204,8 +2273,6 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 		src_offset += load_all_cache_entries(istate, mmap, mmap_size, src_offset);
 	}
 
-	istate->timestamp.sec = st.st_mtime;
-	istate->timestamp.nsec = ST_MTIME_NSEC(st);
 
 	/* if we created a thread, join it otherwise load the extensions on the primary thread */
 	if (extension_offset) {
@@ -2216,6 +2283,8 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 		p.src_offset = src_offset;
 		load_index_extensions(&p);
 	}
+	jw_end_gently(istate->jw);
+
 	munmap((void *)mmap, mmap_size);
 
 	/*

-- 
2.22.0.rc0.322.g2b0371e29a
Previous: Nguyễn Thái Ngọc DuyNext: Ævar Arnfjörð Bjarmason
Message 2 of 36 in “Add 'ls-files --json' to dump the index in json”
  1. 0/8 Add 'ls-files --json' to dump the index in jsonNguyễn Thái Ngọc Duy, Jun 19, 2019
  2. 1/8 ls-files: add --json to dump the indexNguyễn Thái Ngọc Duy, Jun 19, 2019
  3. Ævar Arnfjörð BjarmasonJun 19, 2019
  4. Derrick StoleeJun 19, 2019
  5. Johannes SchindelinJun 21, 2019
  6. Duy NguyenJun 24, 2019
  7. 2/8 split-index.c: dump "link" extension as jsonNguyễn Thái Ngọc Duy, Jun 19, 2019
  8. 3/8 fsmonitor.c: dump "FSMN" extension as jsonNguyễn Thái Ngọc Duy, Jun 19, 2019
  9. 4/8 resolve-undo.c: dump "REUC" extension as jsonNguyễn Thái Ngọc Duy, Jun 19, 2019
  10. Derrick StoleeJun 19, 2019
  11. 5/8 read-cache.c: dump "EOIE" extension as jsonNguyễn Thái Ngọc Duy, Jun 19, 2019
  12. 6/8 read-cache.c: dump "IEOT" extension as jsonNguyễn Thái Ngọc Duy, Jun 19, 2019
  13. Derrick StoleeJun 19, 2019
  14. Duy NguyenJun 19, 2019
  15. Derrick StoleeJun 19, 2019
  16. 7/8 cache-tree.c: dump "TREE" extension as jsonNguyễn Thái Ngọc Duy, Jun 19, 2019
  17. 8/8 dir.c: dump "UNTR" extension as jsonNguyễn Thái Ngọc Duy, Jun 19, 2019
  18. Derrick StoleeJun 19, 2019
  19. Duy NguyenJun 19, 2019
  20. Derrick StoleeJun 19, 2019
  21. Jeff KingJun 19, 2019
  22. Duy NguyenJun 21, 2019
  23. Jeff KingJun 21, 2019
  24. Johannes SchindelinJun 21, 2019
  25. Duy NguyenJun 21, 2019
  26. Junio C HamanoJun 21, 2019
  27. Jeff KingJun 21, 2019
  28. Johannes SchindelinJun 24, 2019
  29. Johannes SchindelinJun 24, 2019
  30. Duy NguyenJun 24, 2019
  31. Jeff KingJun 21, 2019
  32. Johannes SchindelinJun 24, 2019
  33. Junio C HamanoJun 20, 2019
  34. Jeff HostetlerJun 20, 2019
  35. brian m. carlsonJun 21, 2019
  36. Duy NguyenJun 22, 2019

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.