diff options
| -rw-r--r-- | Documentation/git-repo.adoc | 30 | ||||
| -rw-r--r-- | builtin/repo.c | 380 | ||||
| -rw-r--r-- | ref-filter.c | 6 | ||||
| -rw-r--r-- | ref-filter.h | 2 | ||||
| -rw-r--r-- | t/meson.build | 1 | ||||
| -rwxr-xr-x | t/t1901-repo-structure.sh | 129 |
6 files changed, 542 insertions, 6 deletions
diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc index 209afd1b61..ce43cb19c8 100644 --- a/Documentation/git-repo.adoc +++ b/Documentation/git-repo.adoc @@ -9,6 +9,7 @@ SYNOPSIS -------- [synopsis] git repo info [--format=(keyvalue|nul)] [-z] [<key>...] +git repo structure [--format=(table|keyvalue|nul)] DESCRIPTION ----------- @@ -43,6 +44,35 @@ supported: + `-z` is an alias for `--format=nul`. +`structure [--format=(table|keyvalue|nul)]`:: + Retrieve statistics about the current repository structure. The + following kinds of information are reported: ++ +* Reference counts categorized by type +* Reachable object counts categorized by type + ++ +The output format can be chosen through the flag `--format`. Three formats are +supported: ++ +`table`::: + Outputs repository stats in a human-friendly table. This format may + change and is not intended for machine parsing. This is the default + format. + +`keyvalue`::: + Each line of output contains a key-value pair for a repository stat. + The '=' character is used to delimit between the key and the value. + Values containing "unusual" characters are quoted as explained for the + configuration variable `core.quotePath` (see linkgit:git-config[1]). + +`nul`::: + Similar to `keyvalue`, but uses a NUL character to delimit between + key-value pairs instead of a newline. Also uses a newline character as + the delimiter between the key and value instead of '='. Unlike the + `keyvalue` format, values containing "unusual" characters are never + quoted. + INFO KEYS --------- In order to obtain a set of values from `git repo info`, you should provide diff --git a/builtin/repo.c b/builtin/repo.c index bbb0966f2d..9d4749f79b 100644 --- a/builtin/repo.c +++ b/builtin/repo.c @@ -3,19 +3,27 @@ #include "builtin.h" #include "environment.h" #include "parse-options.h" +#include "path-walk.h" +#include "progress.h" #include "quote.h" +#include "ref-filter.h" #include "refs.h" +#include "revision.h" #include "strbuf.h" +#include "string-list.h" #include "shallow.h" +#include "utf8.h" static const char *const repo_usage[] = { "git repo info [--format=(keyvalue|nul)] [-z] [<key>...]", + "git repo structure [--format=(table|keyvalue|nul)]", NULL }; typedef int get_value_fn(struct repository *repo, struct strbuf *buf); enum output_format { + FORMAT_TABLE, FORMAT_KEYVALUE, FORMAT_NUL_TERMINATED, }; @@ -130,14 +138,16 @@ static int parse_format_cb(const struct option *opt, *format = FORMAT_NUL_TERMINATED; else if (!strcmp(arg, "keyvalue")) *format = FORMAT_KEYVALUE; + else if (!strcmp(arg, "table")) + *format = FORMAT_TABLE; else die(_("invalid format '%s'"), arg); return 0; } -static int repo_info(int argc, const char **argv, const char *prefix, - struct repository *repo) +static int cmd_repo_info(int argc, const char **argv, const char *prefix, + struct repository *repo) { enum output_format format = FORMAT_KEYVALUE; struct option options[] = { @@ -152,16 +162,380 @@ static int repo_info(int argc, const char **argv, const char *prefix, }; argc = parse_options(argc, argv, prefix, options, repo_usage, 0); + if (format != FORMAT_KEYVALUE && format != FORMAT_NUL_TERMINATED) + die(_("unsupported output format")); return print_fields(argc, argv, repo, format); } +struct ref_stats { + size_t branches; + size_t remotes; + size_t tags; + size_t others; +}; + +struct object_stats { + size_t tags; + size_t commits; + size_t trees; + size_t blobs; +}; + +struct repo_structure { + struct ref_stats refs; + struct object_stats objects; +}; + +struct stats_table { + struct string_list rows; + + int name_col_width; + int value_col_width; +}; + +/* + * Holds column data that gets stored for each row. + */ +struct stats_table_entry { + char *value; +}; + +static void stats_table_vaddf(struct stats_table *table, + struct stats_table_entry *entry, + const char *format, va_list ap) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list_item *item; + char *formatted_name; + int name_width; + + strbuf_vaddf(&buf, format, ap); + formatted_name = strbuf_detach(&buf, NULL); + name_width = utf8_strwidth(formatted_name); + + item = string_list_append_nodup(&table->rows, formatted_name); + item->util = entry; + + if (name_width > table->name_col_width) + table->name_col_width = name_width; + if (entry) { + int value_width = utf8_strwidth(entry->value); + if (value_width > table->value_col_width) + table->value_col_width = value_width; + } +} + +static void stats_table_addf(struct stats_table *table, const char *format, ...) +{ + va_list ap; + + va_start(ap, format); + stats_table_vaddf(table, NULL, format, ap); + va_end(ap); +} + +static void stats_table_count_addf(struct stats_table *table, size_t value, + const char *format, ...) +{ + struct stats_table_entry *entry; + va_list ap; + + CALLOC_ARRAY(entry, 1); + entry->value = xstrfmt("%" PRIuMAX, (uintmax_t)value); + + va_start(ap, format); + stats_table_vaddf(table, entry, format, ap); + va_end(ap); +} + +static inline size_t get_total_reference_count(struct ref_stats *stats) +{ + return stats->branches + stats->remotes + stats->tags + stats->others; +} + +static inline size_t get_total_object_count(struct object_stats *stats) +{ + return stats->tags + stats->commits + stats->trees + stats->blobs; +} + +static void stats_table_setup_structure(struct stats_table *table, + struct repo_structure *stats) +{ + struct object_stats *objects = &stats->objects; + struct ref_stats *refs = &stats->refs; + size_t object_total; + size_t ref_total; + + ref_total = get_total_reference_count(refs); + stats_table_addf(table, "* %s", _("References")); + stats_table_count_addf(table, ref_total, " * %s", _("Count")); + stats_table_count_addf(table, refs->branches, " * %s", _("Branches")); + stats_table_count_addf(table, refs->tags, " * %s", _("Tags")); + stats_table_count_addf(table, refs->remotes, " * %s", _("Remotes")); + stats_table_count_addf(table, refs->others, " * %s", _("Others")); + + object_total = get_total_object_count(objects); + stats_table_addf(table, ""); + stats_table_addf(table, "* %s", _("Reachable objects")); + stats_table_count_addf(table, object_total, " * %s", _("Count")); + stats_table_count_addf(table, objects->commits, " * %s", _("Commits")); + stats_table_count_addf(table, objects->trees, " * %s", _("Trees")); + stats_table_count_addf(table, objects->blobs, " * %s", _("Blobs")); + stats_table_count_addf(table, objects->tags, " * %s", _("Tags")); +} + +static void stats_table_print_structure(const struct stats_table *table) +{ + const char *name_col_title = _("Repository structure"); + const char *value_col_title = _("Value"); + int name_col_width = utf8_strwidth(name_col_title); + int value_col_width = utf8_strwidth(value_col_title); + struct string_list_item *item; + + if (table->name_col_width > name_col_width) + name_col_width = table->name_col_width; + if (table->value_col_width > value_col_width) + value_col_width = table->value_col_width; + + printf("| %-*s | %-*s |\n", name_col_width, name_col_title, + value_col_width, value_col_title); + printf("| "); + for (int i = 0; i < name_col_width; i++) + putchar('-'); + printf(" | "); + for (int i = 0; i < value_col_width; i++) + putchar('-'); + printf(" |\n"); + + for_each_string_list_item(item, &table->rows) { + struct stats_table_entry *entry = item->util; + const char *value = ""; + + if (entry) { + struct stats_table_entry *entry = item->util; + value = entry->value; + } + + printf("| %-*s | %*s |\n", name_col_width, item->string, + value_col_width, value); + } +} + +static void stats_table_clear(struct stats_table *table) +{ + struct stats_table_entry *entry; + struct string_list_item *item; + + for_each_string_list_item(item, &table->rows) { + entry = item->util; + if (entry) + free(entry->value); + } + + string_list_clear(&table->rows, 1); +} + +static void structure_keyvalue_print(struct repo_structure *stats, + char key_delim, char value_delim) +{ + printf("references.branches.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->refs.branches, value_delim); + printf("references.tags.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->refs.tags, value_delim); + printf("references.remotes.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->refs.remotes, value_delim); + printf("references.others.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->refs.others, value_delim); + + printf("objects.commits.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->objects.commits, value_delim); + printf("objects.trees.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->objects.trees, value_delim); + printf("objects.blobs.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->objects.blobs, value_delim); + printf("objects.tags.count%c%" PRIuMAX "%c", key_delim, + (uintmax_t)stats->objects.tags, value_delim); + + fflush(stdout); +} + +struct count_references_data { + struct ref_stats *stats; + struct rev_info *revs; + struct progress *progress; +}; + +static int count_references(const char *refname, + const char *referent UNUSED, + const struct object_id *oid, + int flags UNUSED, void *cb_data) +{ + struct count_references_data *data = cb_data; + struct ref_stats *stats = data->stats; + size_t ref_count; + + switch (ref_kind_from_refname(refname)) { + case FILTER_REFS_BRANCHES: + stats->branches++; + break; + case FILTER_REFS_REMOTES: + stats->remotes++; + break; + case FILTER_REFS_TAGS: + stats->tags++; + break; + case FILTER_REFS_OTHERS: + stats->others++; + break; + default: + BUG("unexpected reference type"); + } + + /* + * While iterating through references for counting, also add OIDs in + * preparation for the path walk. + */ + add_pending_oid(data->revs, NULL, oid, 0); + + ref_count = get_total_reference_count(stats); + display_progress(data->progress, ref_count); + + return 0; +} + +static void structure_count_references(struct ref_stats *stats, + struct rev_info *revs, + struct repository *repo, + int show_progress) +{ + struct count_references_data data = { + .stats = stats, + .revs = revs, + }; + + if (show_progress) + data.progress = start_delayed_progress(repo, + _("Counting references"), 0); + + refs_for_each_ref(get_main_ref_store(repo), count_references, &data); + stop_progress(&data.progress); +} + +struct count_objects_data { + struct object_stats *stats; + struct progress *progress; +}; + +static int count_objects(const char *path UNUSED, struct oid_array *oids, + enum object_type type, void *cb_data) +{ + struct count_objects_data *data = cb_data; + struct object_stats *stats = data->stats; + size_t object_count; + + switch (type) { + case OBJ_TAG: + stats->tags += oids->nr; + break; + case OBJ_COMMIT: + stats->commits += oids->nr; + break; + case OBJ_TREE: + stats->trees += oids->nr; + break; + case OBJ_BLOB: + stats->blobs += oids->nr; + break; + default: + BUG("invalid object type"); + } + + object_count = get_total_object_count(stats); + display_progress(data->progress, object_count); + + return 0; +} + +static void structure_count_objects(struct object_stats *stats, + struct rev_info *revs, + struct repository *repo, int show_progress) +{ + struct path_walk_info info = PATH_WALK_INFO_INIT; + struct count_objects_data data = { + .stats = stats, + }; + + info.revs = revs; + info.path_fn = count_objects; + info.path_fn_data = &data; + + if (show_progress) + data.progress = start_delayed_progress(repo, _("Counting objects"), 0); + + walk_objects_by_path(&info); + path_walk_info_clear(&info); + stop_progress(&data.progress); +} + +static int cmd_repo_structure(int argc, const char **argv, const char *prefix, + struct repository *repo) +{ + struct stats_table table = { + .rows = STRING_LIST_INIT_DUP, + }; + enum output_format format = FORMAT_TABLE; + struct repo_structure stats = { 0 }; + struct rev_info revs; + int show_progress = -1; + struct option options[] = { + OPT_CALLBACK_F(0, "format", &format, N_("format"), + N_("output format"), + PARSE_OPT_NONEG, parse_format_cb), + OPT_BOOL(0, "progress", &show_progress, N_("show progress")), + OPT_END() + }; + + argc = parse_options(argc, argv, prefix, options, repo_usage, 0); + if (argc) + usage(_("too many arguments")); + + repo_init_revisions(repo, &revs, prefix); + + if (show_progress < 0) + show_progress = isatty(2); + + structure_count_references(&stats.refs, &revs, repo, show_progress); + structure_count_objects(&stats.objects, &revs, repo, show_progress); + + switch (format) { + case FORMAT_TABLE: + stats_table_setup_structure(&table, &stats); + stats_table_print_structure(&table); + break; + case FORMAT_KEYVALUE: + structure_keyvalue_print(&stats, '=', '\n'); + break; + case FORMAT_NUL_TERMINATED: + structure_keyvalue_print(&stats, '\n', '\0'); + break; + default: + BUG("invalid output format"); + } + + stats_table_clear(&table); + release_revisions(&revs); + + return 0; +} + int cmd_repo(int argc, const char **argv, const char *prefix, struct repository *repo) { parse_opt_subcommand_fn *fn = NULL; struct option options[] = { - OPT_SUBCOMMAND("info", &fn, repo_info), + OPT_SUBCOMMAND("info", &fn, cmd_repo_info), + OPT_SUBCOMMAND("structure", &fn, cmd_repo_structure), OPT_END() }; diff --git a/ref-filter.c b/ref-filter.c index 520d2539c9..30cc488d8a 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -2664,7 +2664,7 @@ static int match_name_as_path(const char **pattern, const char *refname, /* Return 1 if the refname matches one of the patterns, otherwise 0. */ static int filter_pattern_match(struct ref_filter *filter, const char *refname) { - if (!*filter->name_patterns) + if (!filter->name_patterns || !*filter->name_patterns) return 1; /* No pattern always matches */ if (filter->match_as_path) return match_name_as_path(filter->name_patterns, refname, @@ -2751,7 +2751,7 @@ static int for_each_fullref_in_pattern(struct ref_filter *filter, return for_each_fullref_with_seek(filter, cb, cb_data, 0); } - if (!filter->name_patterns[0]) { + if (!filter->name_patterns || !filter->name_patterns[0]) { /* no patterns; we have to look at everything */ return for_each_fullref_with_seek(filter, cb, cb_data, 0); } @@ -2833,7 +2833,7 @@ struct ref_array_item *ref_array_push(struct ref_array *array, return ref; } -static int ref_kind_from_refname(const char *refname) +int ref_kind_from_refname(const char *refname) { unsigned int i; diff --git a/ref-filter.h b/ref-filter.h index 81f2c229a9..235c60f79c 100644 --- a/ref-filter.h +++ b/ref-filter.h @@ -135,6 +135,8 @@ struct ref_format { OPT_STRVEC(0, "exclude", &(var)->exclude, \ N_("pattern"), N_("exclude refs which match pattern")) +/* Get the reference kind from the provided reference name. */ +int ref_kind_from_refname(const char *refname); /* * API for filtering a set of refs. Based on the type of refs the user * has requested, we iterate through those refs and apply filters diff --git a/t/meson.build b/t/meson.build index c9ddd89889..a5531df415 100644 --- a/t/meson.build +++ b/t/meson.build @@ -238,6 +238,7 @@ integration_tests = [ 't1701-racy-split-index.sh', 't1800-hook.sh', 't1900-repo.sh', + 't1901-repo-structure.sh', 't2000-conflict-when-checking-files-out.sh', 't2002-checkout-cache-u.sh', 't2003-checkout-cache-mkdir.sh', diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh new file mode 100755 index 0000000000..36a71a144e --- /dev/null +++ b/t/t1901-repo-structure.sh @@ -0,0 +1,129 @@ +#!/bin/sh + +test_description='test git repo structure' + +. ./test-lib.sh + +test_expect_success 'empty repository' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + cat >expect <<-\EOF && + | Repository structure | Value | + | -------------------- | ----- | + | * References | | + | * Count | 0 | + | * Branches | 0 | + | * Tags | 0 | + | * Remotes | 0 | + | * Others | 0 | + | | | + | * Reachable objects | | + | * Count | 0 | + | * Commits | 0 | + | * Trees | 0 | + | * Blobs | 0 | + | * Tags | 0 | + EOF + + git repo structure >out 2>err && + + test_cmp expect out && + test_line_count = 0 err + ) +' + +test_expect_success 'repository with references and objects' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit_bulk 42 && + git tag -a foo -m bar && + + oid="$(git rev-parse HEAD)" && + git update-ref refs/remotes/origin/foo "$oid" && + + # Also creates a commit, tree, and blob. + git notes add -m foo && + + cat >expect <<-\EOF && + | Repository structure | Value | + | -------------------- | ----- | + | * References | | + | * Count | 4 | + | * Branches | 1 | + | * Tags | 1 | + | * Remotes | 1 | + | * Others | 1 | + | | | + | * Reachable objects | | + | * Count | 130 | + | * Commits | 43 | + | * Trees | 43 | + | * Blobs | 43 | + | * Tags | 1 | + EOF + + git repo structure >out 2>err && + + test_cmp expect out && + test_line_count = 0 err + ) +' + +test_expect_success 'keyvalue and nul format' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit_bulk 42 && + git tag -a foo -m bar && + + cat >expect <<-\EOF && + references.branches.count=1 + references.tags.count=1 + references.remotes.count=0 + references.others.count=0 + objects.commits.count=42 + objects.trees.count=42 + objects.blobs.count=42 + objects.tags.count=1 + EOF + + git repo structure --format=keyvalue >out 2>err && + + test_cmp expect out && + test_line_count = 0 err && + + # Replace key and value delimiters for nul format. + tr "\n=" "\0\n" <expect >expect_nul && + git repo structure --format=nul >out 2>err && + + test_cmp expect_nul out && + test_line_count = 0 err + ) +' + +test_expect_success 'progress meter option' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit foo && + + GIT_PROGRESS_DELAY=0 git repo structure --progress >out 2>err && + + test_file_not_empty out && + test_grep "Counting references: 2, done." err && + test_grep "Counting objects: 3, done." err && + + GIT_PROGRESS_DELAY=0 git repo structure --no-progress >out 2>err && + + test_file_not_empty out && + test_line_count = 0 err + ) +' + +test_done |