git/ref-filter.h
Taylor Blau 8255dd8a3d builtin/for-each-ref.c: add --exclude option
When using `for-each-ref`, it is sometimes convenient for the caller to
be able to exclude certain parts of the references.

For example, if there are many `refs/__hidden__/*` references, the
caller may want to emit all references *except* the hidden ones.
Currently, the only way to do this is to post-process the output, like:

    $ git for-each-ref --format='%(refname)' | grep -v '^refs/hidden/'

Which is do-able, but requires processing a potentially large quantity
of references.

Teach `git for-each-ref` a new `--exclude=<pattern>` option, which
excludes references from the results if they match one or more excluded
patterns.

This patch provides a naive implementation where the `ref_filter` still
sees all references (including ones that it will discard) and is left to
check whether each reference matches any excluded pattern(s) before
emitting them.

By culling out references we know the caller doesn't care about, we can
avoid allocating memory for their storage, as well as spending time
sorting the output (among other things). Even the naive implementation
provides a significant speed-up on a modified copy of linux.git (that
has a hidden ref pointing at each commit):

    $ hyperfine \
      'git.compile for-each-ref --format="%(objectname) %(refname)" | grep -vE "[0-9a-f]{40} refs/pull/"' \
      'git.compile for-each-ref --format="%(objectname) %(refname)" --exclude refs/pull/'
    Benchmark 1: git.compile for-each-ref --format="%(objectname) %(refname)" | grep -vE "[0-9a-f]{40} refs/pull/"
      Time (mean ± σ):     820.1 ms ±   2.0 ms    [User: 703.7 ms, System: 152.0 ms]
      Range (min … max):   817.7 ms … 823.3 ms    10 runs

    Benchmark 2: git.compile for-each-ref --format="%(objectname) %(refname)" --exclude refs/pull/
      Time (mean ± σ):     106.6 ms ±   1.1 ms    [User: 99.4 ms, System: 7.1 ms]
      Range (min … max):   104.7 ms … 109.1 ms    27 runs

    Summary
      'git.compile for-each-ref --format="%(objectname) %(refname)" --exclude refs/pull/' ran
        7.69 ± 0.08 times faster than 'git.compile for-each-ref --format="%(objectname) %(refname)" | grep -vE "[0-9a-f]{40} refs/pull/"'

Subsequent patches will improve on this by avoiding visiting excluded
sections of the `packed-refs` file in certain cases.

Co-authored-by: Jeff King <peff@peff.net>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-07-10 14:48:55 -07:00

182 lines
5.4 KiB
C

#ifndef REF_FILTER_H
#define REF_FILTER_H
#include "gettext.h"
#include "oid-array.h"
#include "refs.h"
#include "commit.h"
#include "string-list.h"
#include "strvec.h"
/* Quoting styles */
#define QUOTE_NONE 0
#define QUOTE_SHELL 1
#define QUOTE_PERL 2
#define QUOTE_PYTHON 4
#define QUOTE_TCL 8
#define FILTER_REFS_TAGS 0x0002
#define FILTER_REFS_BRANCHES 0x0004
#define FILTER_REFS_REMOTES 0x0008
#define FILTER_REFS_OTHERS 0x0010
#define FILTER_REFS_ALL (FILTER_REFS_TAGS | FILTER_REFS_BRANCHES | \
FILTER_REFS_REMOTES | FILTER_REFS_OTHERS)
#define FILTER_REFS_DETACHED_HEAD 0x0020
#define FILTER_REFS_KIND_MASK (FILTER_REFS_ALL | FILTER_REFS_DETACHED_HEAD)
struct atom_value;
struct ref_sorting;
struct ahead_behind_count;
struct option;
enum ref_sorting_order {
REF_SORTING_REVERSE = 1<<0,
REF_SORTING_ICASE = 1<<1,
REF_SORTING_VERSION = 1<<2,
REF_SORTING_DETACHED_HEAD_FIRST = 1<<3,
};
struct ref_array_item {
struct object_id objectname;
const char *rest;
int flag;
unsigned int kind;
const char *symref;
struct commit *commit;
struct atom_value *value;
struct ahead_behind_count **counts;
char refname[FLEX_ARRAY];
};
struct ref_array {
int nr, alloc;
struct ref_array_item **items;
struct rev_info *revs;
struct ahead_behind_count *counts;
size_t counts_nr;
};
struct ref_filter {
const char **name_patterns;
struct strvec exclude;
struct oid_array points_at;
struct commit_list *with_commit;
struct commit_list *no_commit;
struct commit_list *reachable_from;
struct commit_list *unreachable_from;
unsigned int with_commit_tag_algo : 1,
match_as_path : 1,
ignore_case : 1,
detached : 1;
unsigned int kind,
lines;
int abbrev,
verbose;
};
struct ref_format {
/*
* Set these to define the format; make sure you call
* verify_ref_format() afterwards to finalize.
*/
const char *format;
const char *rest;
int quote_style;
int use_color;
/* Internal state to ref-filter */
int need_color_reset_at_eol;
/* List of bases for ahead-behind counts. */
struct string_list bases;
};
#define REF_FILTER_INIT { \
.points_at = OID_ARRAY_INIT, \
.exclude = STRVEC_INIT, \
}
#define REF_FORMAT_INIT { \
.use_color = -1, \
.bases = STRING_LIST_INIT_DUP, \
}
/* Macros for checking --merged and --no-merged options */
#define _OPT_MERGED_NO_MERGED(option, filter, h) \
{ OPTION_CALLBACK, 0, option, (filter), N_("commit"), (h), \
PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NONEG, \
parse_opt_merge_filter, (intptr_t) "HEAD" \
}
#define OPT_MERGED(f, h) _OPT_MERGED_NO_MERGED("merged", f, h)
#define OPT_NO_MERGED(f, h) _OPT_MERGED_NO_MERGED("no-merged", f, h)
#define OPT_REF_SORT(var) \
OPT_STRING_LIST(0, "sort", (var), \
N_("key"), N_("field name to sort on"))
#define OPT_REF_FILTER_EXCLUDE(var) \
OPT_STRVEC(0, "exclude", &(var)->exclude, \
N_("pattern"), N_("exclude refs which match pattern"))
/*
* 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
* as per the given ref_filter structure and finally store the
* filtered refs in the ref_array structure.
*/
int filter_refs(struct ref_array *array, struct ref_filter *filter, unsigned int type);
/* Clear all memory allocated to ref_array */
void ref_array_clear(struct ref_array *array);
/* Used to verify if the given format is correct and to parse out the used atoms */
int verify_ref_format(struct ref_format *format);
/* Sort the given ref_array as per the ref_sorting provided */
void ref_array_sort(struct ref_sorting *sort, struct ref_array *array);
/* Set REF_SORTING_* sort_flags for all elements of a sorting list */
void ref_sorting_set_sort_flags_all(struct ref_sorting *sorting, unsigned int mask, int on);
/* Based on the given format and quote_style, fill the strbuf */
int format_ref_array_item(struct ref_array_item *info,
struct ref_format *format,
struct strbuf *final_buf,
struct strbuf *error_buf);
/* Release a "struct ref_sorting" */
void ref_sorting_release(struct ref_sorting *);
/* Convert list of sort options into ref_sorting */
struct ref_sorting *ref_sorting_options(struct string_list *);
/* Function to parse --merged and --no-merged options */
int parse_opt_merge_filter(const struct option *opt, const char *arg, int unset);
/* Get the current HEAD's description */
char *get_head_description(void);
/* Set up translated strings in the output. */
void setup_ref_filter_porcelain_msg(void);
/*
* Print a single ref, outside of any ref-filter. Note that the
* name must be a fully qualified refname.
*/
void pretty_print_ref(const char *name, const struct object_id *oid,
struct ref_format *format);
/*
* Push a single ref onto the array; this can be used to construct your own
* ref_array without using filter_refs().
*/
struct ref_array_item *ref_array_push(struct ref_array *array,
const char *refname,
const struct object_id *oid);
/*
* If the provided format includes ahead-behind atoms, then compute the
* ahead-behind values for the array of filtered references. Must be
* called after filter_refs() but before outputting the formatted refs.
*
* If this is not called, then any ahead-behind atoms will be blank.
*/
void filter_ahead_behind(struct repository *r,
struct ref_format *format,
struct ref_array *array);
void ref_filter_init(struct ref_filter *filter);
void ref_filter_clear(struct ref_filter *filter);
#endif /* REF_FILTER_H */