1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-20 11:06:07 +02:00
git/ref-filter.c

2761 lines
76 KiB
C
Raw Normal View History

#include "builtin.h"
#include "cache.h"
#include "parse-options.h"
#include "refs.h"
#include "wildmatch.h"
#include "object-store.h"
#include "repository.h"
#include "commit.h"
#include "remote.h"
#include "color.h"
#include "tag.h"
#include "quote.h"
#include "ref-filter.h"
#include "revision.h"
2015-09-11 17:03:07 +02:00
#include "utf8.h"
#include "git-compat-util.h"
#include "version.h"
#include "trailer.h"
#include "wt-status.h"
#include "commit-slab.h"
#include "commit-graph.h"
#include "commit-reach.h"
#include "worktree.h"
#include "hashmap.h"
#include "strvec.h"
static struct ref_msg {
const char *gone;
const char *ahead;
const char *behind;
const char *ahead_behind;
} msgs = {
/* Untranslated plumbing messages: */
"gone",
"ahead %d",
"behind %d",
"ahead %d, behind %d"
};
void setup_ref_filter_porcelain_msg(void)
{
msgs.gone = _("gone");
msgs.ahead = _("ahead %d");
msgs.behind = _("behind %d");
msgs.ahead_behind = _("ahead %d, behind %d");
}
typedef enum { FIELD_STR, FIELD_ULONG, FIELD_TIME } cmp_type;
typedef enum { COMPARE_EQUAL, COMPARE_UNEQUAL, COMPARE_NONE } cmp_status;
typedef enum { SOURCE_NONE = 0, SOURCE_OBJ, SOURCE_OTHER } info_source;
struct align {
align_type position;
unsigned int width;
};
struct if_then_else {
cmp_status cmp_status;
const char *str;
unsigned int then_atom_seen : 1,
else_atom_seen : 1,
condition_satisfied : 1;
};
struct refname_atom {
enum { R_NORMAL, R_SHORT, R_LSTRIP, R_RSTRIP } option;
int lstrip, rstrip;
};
static struct ref_trailer_buf {
struct string_list filter_list;
struct strbuf sepbuf;
struct strbuf kvsepbuf;
} ref_trailer_buf = {STRING_LIST_INIT_NODUP, STRBUF_INIT, STRBUF_INIT};
static struct expand_data {
struct object_id oid;
enum object_type type;
unsigned long size;
off_t disk_size;
struct object_id delta_base_oid;
void *content;
struct object_info info;
} oi, oi_deref;
struct ref_to_worktree_entry {
struct hashmap_entry ent;
struct worktree *wt; /* key is wt->head_ref */
};
static int ref_to_worktree_map_cmpfnc(const void *UNUSED(lookupdata),
const struct hashmap_entry *eptr,
const struct hashmap_entry *kptr,
const void *keydata_aka_refname)
{
const struct ref_to_worktree_entry *e, *k;
e = container_of(eptr, const struct ref_to_worktree_entry, ent);
k = container_of(kptr, const struct ref_to_worktree_entry, ent);
return strcmp(e->wt->head_ref,
keydata_aka_refname ? keydata_aka_refname : k->wt->head_ref);
}
static struct ref_to_worktree_map {
struct hashmap map;
struct worktree **worktrees;
} ref_to_worktree_map;
/*
* The enum atom_type is used as the index of valid_atom array.
* In the atom parsing stage, it will be passed to used_atom.atom_type
* as the identifier of the atom type. We can check the type of used_atom
* entry by `if (used_atom[i].atom_type == ATOM_*)`.
*/
enum atom_type {
ATOM_REFNAME,
ATOM_OBJECTTYPE,
ATOM_OBJECTSIZE,
ATOM_OBJECTNAME,
ATOM_DELTABASE,
ATOM_TREE,
ATOM_PARENT,
ATOM_NUMPARENT,
ATOM_OBJECT,
ATOM_TYPE,
ATOM_TAG,
ATOM_AUTHOR,
ATOM_AUTHORNAME,
ATOM_AUTHOREMAIL,
ATOM_AUTHORDATE,
ATOM_COMMITTER,
ATOM_COMMITTERNAME,
ATOM_COMMITTEREMAIL,
ATOM_COMMITTERDATE,
ATOM_TAGGER,
ATOM_TAGGERNAME,
ATOM_TAGGEREMAIL,
ATOM_TAGGERDATE,
ATOM_CREATOR,
ATOM_CREATORDATE,
ATOM_SUBJECT,
ATOM_BODY,
ATOM_TRAILERS,
ATOM_CONTENTS,
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
ATOM_RAW,
ATOM_UPSTREAM,
ATOM_PUSH,
ATOM_SYMREF,
ATOM_FLAG,
ATOM_HEAD,
ATOM_COLOR,
ATOM_WORKTREEPATH,
ATOM_ALIGN,
ATOM_END,
ATOM_IF,
ATOM_THEN,
ATOM_ELSE,
ATOM_REST,
};
/*
* An atom is a valid field atom listed below, possibly prefixed with
* a "*" to denote deref_tag().
*
* We parse given format string and sort specifiers, and make a list
* of properties that we need to extract out of objects. ref_array_item
* structure will hold an array of values extracted that can be
* indexed with the "atom number", which is an index into this
* array.
*/
static struct used_atom {
enum atom_type atom_type;
const char *name;
cmp_type type;
info_source source;
union {
char color[COLOR_MAXLEN];
struct align align;
struct {
for-each-ref: let upstream/push optionally report the remote name There are times when e.g. scripts want to know not only the name of the upstream branch on the remote repository, but also the name of the remote. This patch offers the new suffix :remotename for the upstream and for the push atoms, allowing to show exactly that. Example: $ cat .git/config ... [remote "origin"] url = https://where.do.we.come/from fetch = refs/heads/*:refs/remote/origin/* [remote "hello-world"] url = https://hello.world/git fetch = refs/heads/*:refs/remote/origin/* pushURL = hello.world:git push = refs/heads/*:refs/heads/* [branch "master"] remote = origin pushRemote = hello-world ... $ git for-each-ref \ --format='%(upstream) %(upstream:remotename) %(push:remotename)' \ refs/heads/master refs/remotes/origin/master origin hello-world The implementation chooses *not* to DWIM the push remote if no explicit push remote was configured; The reason is that it is possible to DWIM this by using %(if)%(push:remotename)%(then) %(push:remotename) %(else) %(upstream:remotename) %(end) while it would be impossible to "un-DWIM" the information in case the caller is really only interested in explicit push remotes. While `:remote` would be shorter, it would also be a bit more ambiguous, and it would also shut the door e.g. for `:remoteref` (which would obviously refer to the corresponding ref in the remote repository). Note: the dashless, non-CamelCased form `:remotename` follows the example of the `:trackshort` example. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-05 14:19:09 +02:00
enum {
RR_REF, RR_TRACK, RR_TRACKSHORT, RR_REMOTE_NAME, RR_REMOTE_REF
for-each-ref: let upstream/push optionally report the remote name There are times when e.g. scripts want to know not only the name of the upstream branch on the remote repository, but also the name of the remote. This patch offers the new suffix :remotename for the upstream and for the push atoms, allowing to show exactly that. Example: $ cat .git/config ... [remote "origin"] url = https://where.do.we.come/from fetch = refs/heads/*:refs/remote/origin/* [remote "hello-world"] url = https://hello.world/git fetch = refs/heads/*:refs/remote/origin/* pushURL = hello.world:git push = refs/heads/*:refs/heads/* [branch "master"] remote = origin pushRemote = hello-world ... $ git for-each-ref \ --format='%(upstream) %(upstream:remotename) %(push:remotename)' \ refs/heads/master refs/remotes/origin/master origin hello-world The implementation chooses *not* to DWIM the push remote if no explicit push remote was configured; The reason is that it is possible to DWIM this by using %(if)%(push:remotename)%(then) %(push:remotename) %(else) %(upstream:remotename) %(end) while it would be impossible to "un-DWIM" the information in case the caller is really only interested in explicit push remotes. While `:remote` would be shorter, it would also be a bit more ambiguous, and it would also shut the door e.g. for `:remoteref` (which would obviously refer to the corresponding ref in the remote repository). Note: the dashless, non-CamelCased form `:remotename` follows the example of the `:trackshort` example. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-05 14:19:09 +02:00
} option;
struct refname_atom refname;
for-each-ref: let upstream/push optionally report the remote name There are times when e.g. scripts want to know not only the name of the upstream branch on the remote repository, but also the name of the remote. This patch offers the new suffix :remotename for the upstream and for the push atoms, allowing to show exactly that. Example: $ cat .git/config ... [remote "origin"] url = https://where.do.we.come/from fetch = refs/heads/*:refs/remote/origin/* [remote "hello-world"] url = https://hello.world/git fetch = refs/heads/*:refs/remote/origin/* pushURL = hello.world:git push = refs/heads/*:refs/heads/* [branch "master"] remote = origin pushRemote = hello-world ... $ git for-each-ref \ --format='%(upstream) %(upstream:remotename) %(push:remotename)' \ refs/heads/master refs/remotes/origin/master origin hello-world The implementation chooses *not* to DWIM the push remote if no explicit push remote was configured; The reason is that it is possible to DWIM this by using %(if)%(push:remotename)%(then) %(push:remotename) %(else) %(upstream:remotename) %(end) while it would be impossible to "un-DWIM" the information in case the caller is really only interested in explicit push remotes. While `:remote` would be shorter, it would also be a bit more ambiguous, and it would also shut the door e.g. for `:remoteref` (which would obviously refer to the corresponding ref in the remote repository). Note: the dashless, non-CamelCased form `:remotename` follows the example of the `:trackshort` example. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-05 14:19:09 +02:00
unsigned int nobracket : 1, push : 1, push_remote : 1;
} remote_ref;
struct {
enum { C_BARE, C_BODY, C_BODY_DEP, C_LENGTH, C_LINES,
C_SIG, C_SUB, C_SUB_SANITIZE, C_TRAILERS } option;
struct process_trailer_options trailer_opts;
unsigned int nlines;
} contents;
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
struct {
enum { RAW_BARE, RAW_LENGTH } option;
} raw_data;
struct {
cmp_status cmp_status;
const char *str;
} if_then_else;
struct {
enum { O_FULL, O_LENGTH, O_SHORT } option;
unsigned int length;
} oid;
struct {
enum { O_SIZE, O_SIZE_DISK } option;
} objectsize;
struct email_option {
enum { EO_RAW, EO_TRIM, EO_LOCALPART } option;
} email_option;
struct refname_atom refname;
char *head;
} u;
} *used_atom;
static int used_atom_cnt, need_tagged, need_symref;
/*
* Expand string, append it to strbuf *sb, then return error code ret.
* Allow to save few lines of code.
*/
__attribute__((format (printf, 3, 4)))
static int strbuf_addf_ret(struct strbuf *sb, int ret, const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
strbuf_vaddf(sb, fmt, ap);
va_end(ap);
return ret;
}
static int color_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *color_value, struct strbuf *err)
{
if (!color_value)
return strbuf_addf_ret(err, -1, _("expected format: %%(color:<color>)"));
if (color_parse(color_value, atom->u.color) < 0)
return strbuf_addf_ret(err, -1, _("unrecognized color: %%(color:%s)"),
color_value);
/*
* We check this after we've parsed the color, which lets us complain
* about syntactically bogus color names even if they won't be used.
*/
if (!want_color(format->use_color))
color_parse("", atom->u.color);
return 0;
}
static int refname_atom_parser_internal(struct refname_atom *atom, const char *arg,
const char *name, struct strbuf *err)
{
if (!arg)
atom->option = R_NORMAL;
else if (!strcmp(arg, "short"))
atom->option = R_SHORT;
else if (skip_prefix(arg, "lstrip=", &arg) ||
skip_prefix(arg, "strip=", &arg)) {
atom->option = R_LSTRIP;
if (strtol_i(arg, 10, &atom->lstrip))
return strbuf_addf_ret(err, -1, _("Integer value expected refname:lstrip=%s"), arg);
} else if (skip_prefix(arg, "rstrip=", &arg)) {
atom->option = R_RSTRIP;
if (strtol_i(arg, 10, &atom->rstrip))
return strbuf_addf_ret(err, -1, _("Integer value expected refname:rstrip=%s"), arg);
} else
return strbuf_addf_ret(err, -1, _("unrecognized %%(%s) argument: %s"), name, arg);
return 0;
}
static int remote_ref_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
struct string_list params = STRING_LIST_INIT_DUP;
int i;
for-each-ref: let upstream/push optionally report the remote name There are times when e.g. scripts want to know not only the name of the upstream branch on the remote repository, but also the name of the remote. This patch offers the new suffix :remotename for the upstream and for the push atoms, allowing to show exactly that. Example: $ cat .git/config ... [remote "origin"] url = https://where.do.we.come/from fetch = refs/heads/*:refs/remote/origin/* [remote "hello-world"] url = https://hello.world/git fetch = refs/heads/*:refs/remote/origin/* pushURL = hello.world:git push = refs/heads/*:refs/heads/* [branch "master"] remote = origin pushRemote = hello-world ... $ git for-each-ref \ --format='%(upstream) %(upstream:remotename) %(push:remotename)' \ refs/heads/master refs/remotes/origin/master origin hello-world The implementation chooses *not* to DWIM the push remote if no explicit push remote was configured; The reason is that it is possible to DWIM this by using %(if)%(push:remotename)%(then) %(push:remotename) %(else) %(upstream:remotename) %(end) while it would be impossible to "un-DWIM" the information in case the caller is really only interested in explicit push remotes. While `:remote` would be shorter, it would also be a bit more ambiguous, and it would also shut the door e.g. for `:remoteref` (which would obviously refer to the corresponding ref in the remote repository). Note: the dashless, non-CamelCased form `:remotename` follows the example of the `:trackshort` example. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-05 14:19:09 +02:00
if (!strcmp(atom->name, "push") || starts_with(atom->name, "push:"))
atom->u.remote_ref.push = 1;
if (!arg) {
atom->u.remote_ref.option = RR_REF;
return refname_atom_parser_internal(&atom->u.remote_ref.refname,
arg, atom->name, err);
}
atom->u.remote_ref.nobracket = 0;
string_list_split(&params, arg, ',', -1);
for (i = 0; i < params.nr; i++) {
const char *s = params.items[i].string;
if (!strcmp(s, "track"))
atom->u.remote_ref.option = RR_TRACK;
else if (!strcmp(s, "trackshort"))
atom->u.remote_ref.option = RR_TRACKSHORT;
else if (!strcmp(s, "nobracket"))
atom->u.remote_ref.nobracket = 1;
for-each-ref: let upstream/push optionally report the remote name There are times when e.g. scripts want to know not only the name of the upstream branch on the remote repository, but also the name of the remote. This patch offers the new suffix :remotename for the upstream and for the push atoms, allowing to show exactly that. Example: $ cat .git/config ... [remote "origin"] url = https://where.do.we.come/from fetch = refs/heads/*:refs/remote/origin/* [remote "hello-world"] url = https://hello.world/git fetch = refs/heads/*:refs/remote/origin/* pushURL = hello.world:git push = refs/heads/*:refs/heads/* [branch "master"] remote = origin pushRemote = hello-world ... $ git for-each-ref \ --format='%(upstream) %(upstream:remotename) %(push:remotename)' \ refs/heads/master refs/remotes/origin/master origin hello-world The implementation chooses *not* to DWIM the push remote if no explicit push remote was configured; The reason is that it is possible to DWIM this by using %(if)%(push:remotename)%(then) %(push:remotename) %(else) %(upstream:remotename) %(end) while it would be impossible to "un-DWIM" the information in case the caller is really only interested in explicit push remotes. While `:remote` would be shorter, it would also be a bit more ambiguous, and it would also shut the door e.g. for `:remoteref` (which would obviously refer to the corresponding ref in the remote repository). Note: the dashless, non-CamelCased form `:remotename` follows the example of the `:trackshort` example. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-05 14:19:09 +02:00
else if (!strcmp(s, "remotename")) {
atom->u.remote_ref.option = RR_REMOTE_NAME;
atom->u.remote_ref.push_remote = 1;
} else if (!strcmp(s, "remoteref")) {
atom->u.remote_ref.option = RR_REMOTE_REF;
atom->u.remote_ref.push_remote = 1;
for-each-ref: let upstream/push optionally report the remote name There are times when e.g. scripts want to know not only the name of the upstream branch on the remote repository, but also the name of the remote. This patch offers the new suffix :remotename for the upstream and for the push atoms, allowing to show exactly that. Example: $ cat .git/config ... [remote "origin"] url = https://where.do.we.come/from fetch = refs/heads/*:refs/remote/origin/* [remote "hello-world"] url = https://hello.world/git fetch = refs/heads/*:refs/remote/origin/* pushURL = hello.world:git push = refs/heads/*:refs/heads/* [branch "master"] remote = origin pushRemote = hello-world ... $ git for-each-ref \ --format='%(upstream) %(upstream:remotename) %(push:remotename)' \ refs/heads/master refs/remotes/origin/master origin hello-world The implementation chooses *not* to DWIM the push remote if no explicit push remote was configured; The reason is that it is possible to DWIM this by using %(if)%(push:remotename)%(then) %(push:remotename) %(else) %(upstream:remotename) %(end) while it would be impossible to "un-DWIM" the information in case the caller is really only interested in explicit push remotes. While `:remote` would be shorter, it would also be a bit more ambiguous, and it would also shut the door e.g. for `:remoteref` (which would obviously refer to the corresponding ref in the remote repository). Note: the dashless, non-CamelCased form `:remotename` follows the example of the `:trackshort` example. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-05 14:19:09 +02:00
} else {
atom->u.remote_ref.option = RR_REF;
if (refname_atom_parser_internal(&atom->u.remote_ref.refname,
arg, atom->name, err)) {
string_list_clear(&params, 0);
return -1;
}
}
}
string_list_clear(&params, 0);
return 0;
}
static int objecttype_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (arg)
return strbuf_addf_ret(err, -1, _("%%(objecttype) does not take arguments"));
if (*atom->name == '*')
oi_deref.info.typep = &oi_deref.type;
else
oi.info.typep = &oi.type;
return 0;
}
static int objectsize_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (!arg) {
atom->u.objectsize.option = O_SIZE;
if (*atom->name == '*')
oi_deref.info.sizep = &oi_deref.size;
else
oi.info.sizep = &oi.size;
} else if (!strcmp(arg, "disk")) {
atom->u.objectsize.option = O_SIZE_DISK;
if (*atom->name == '*')
oi_deref.info.disk_sizep = &oi_deref.disk_size;
else
oi.info.disk_sizep = &oi.disk_size;
} else
return strbuf_addf_ret(err, -1, _("unrecognized %%(%s) argument: %s"), "objectsize", arg);
return 0;
}
static int deltabase_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (arg)
return strbuf_addf_ret(err, -1, _("%%(deltabase) does not take arguments"));
if (*atom->name == '*')
oi_deref.info.delta_base_oid = &oi_deref.delta_base_oid;
else
oi.info.delta_base_oid = &oi.delta_base_oid;
return 0;
}
static int body_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (arg)
return strbuf_addf_ret(err, -1, _("%%(body) does not take arguments"));
atom->u.contents.option = C_BODY_DEP;
return 0;
}
static int subject_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (!arg)
atom->u.contents.option = C_SUB;
else if (!strcmp(arg, "sanitize"))
atom->u.contents.option = C_SUB_SANITIZE;
else
return strbuf_addf_ret(err, -1, _("unrecognized %%(%s) argument: %s"), "subject", arg);
return 0;
}
static int trailers_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
atom->u.contents.trailer_opts.no_divider = 1;
if (arg) {
const char *argbuf = xstrfmt("%s)", arg);
char *invalid_arg = NULL;
if (format_set_trailers_options(&atom->u.contents.trailer_opts,
&ref_trailer_buf.filter_list,
&ref_trailer_buf.sepbuf,
&ref_trailer_buf.kvsepbuf,
&argbuf, &invalid_arg)) {
if (!invalid_arg)
strbuf_addf(err, _("expected %%(trailers:key=<value>)"));
else
strbuf_addf(err, _("unknown %%(trailers) argument: %s"), invalid_arg);
free((char *)invalid_arg);
return -1;
}
}
atom->u.contents.option = C_TRAILERS;
return 0;
}
static int contents_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (!arg)
atom->u.contents.option = C_BARE;
else if (!strcmp(arg, "body"))
atom->u.contents.option = C_BODY;
else if (!strcmp(arg, "size"))
atom->u.contents.option = C_LENGTH;
else if (!strcmp(arg, "signature"))
atom->u.contents.option = C_SIG;
else if (!strcmp(arg, "subject"))
atom->u.contents.option = C_SUB;
else if (!strcmp(arg, "trailers")) {
if (trailers_atom_parser(format, atom, NULL, err))
return -1;
} else if (skip_prefix(arg, "trailers:", &arg)) {
if (trailers_atom_parser(format, atom, arg, err))
return -1;
} else if (skip_prefix(arg, "lines=", &arg)) {
atom->u.contents.option = C_LINES;
if (strtoul_ui(arg, 10, &atom->u.contents.nlines))
return strbuf_addf_ret(err, -1, _("positive value expected contents:lines=%s"), arg);
} else
return strbuf_addf_ret(err, -1, _("unrecognized %%(%s) argument: %s"), "contents", arg);
return 0;
}
static int raw_atom_parser(struct ref_format *format, struct used_atom *atom,
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
const char *arg, struct strbuf *err)
{
if (!arg)
atom->u.raw_data.option = RAW_BARE;
else if (!strcmp(arg, "size"))
atom->u.raw_data.option = RAW_LENGTH;
else
return strbuf_addf_ret(err, -1, _("unrecognized %%(%s) argument: %s"), "raw", arg);
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
return 0;
}
static int oid_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (!arg)
atom->u.oid.option = O_FULL;
else if (!strcmp(arg, "short"))
atom->u.oid.option = O_SHORT;
else if (skip_prefix(arg, "short=", &arg)) {
atom->u.oid.option = O_LENGTH;
if (strtoul_ui(arg, 10, &atom->u.oid.length) ||
atom->u.oid.length == 0)
return strbuf_addf_ret(err, -1, _("positive value expected '%s' in %%(%s)"), arg, atom->name);
if (atom->u.oid.length < MINIMUM_ABBREV)
atom->u.oid.length = MINIMUM_ABBREV;
} else
return strbuf_addf_ret(err, -1, _("unrecognized %%(%s) argument: %s"), atom->name, arg);
return 0;
}
static int person_email_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (!arg)
atom->u.email_option.option = EO_RAW;
else if (!strcmp(arg, "trim"))
atom->u.email_option.option = EO_TRIM;
else if (!strcmp(arg, "localpart"))
atom->u.email_option.option = EO_LOCALPART;
else
return strbuf_addf_ret(err, -1, _("unrecognized email option: %s"), arg);
return 0;
}
static int refname_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
return refname_atom_parser_internal(&atom->u.refname, arg, atom->name, err);
}
static align_type parse_align_position(const char *s)
{
if (!strcmp(s, "right"))
return ALIGN_RIGHT;
else if (!strcmp(s, "middle"))
return ALIGN_MIDDLE;
else if (!strcmp(s, "left"))
return ALIGN_LEFT;
return -1;
}
static int align_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
struct align *align = &atom->u.align;
struct string_list params = STRING_LIST_INIT_DUP;
int i;
unsigned int width = ~0U;
if (!arg)
return strbuf_addf_ret(err, -1, _("expected format: %%(align:<width>,<position>)"));
align->position = ALIGN_LEFT;
string_list_split(&params, arg, ',', -1);
for (i = 0; i < params.nr; i++) {
const char *s = params.items[i].string;
int position;
if (skip_prefix(s, "position=", &s)) {
position = parse_align_position(s);
if (position < 0) {
strbuf_addf(err, _("unrecognized position:%s"), s);
string_list_clear(&params, 0);
return -1;
}
align->position = position;
} else if (skip_prefix(s, "width=", &s)) {
if (strtoul_ui(s, 10, &width)) {
strbuf_addf(err, _("unrecognized width:%s"), s);
string_list_clear(&params, 0);
return -1;
}
} else if (!strtoul_ui(s, 10, &width))
;
else if ((position = parse_align_position(s)) >= 0)
align->position = position;
else {
strbuf_addf(err, _("unrecognized %%(%s) argument: %s"), "align", s);
string_list_clear(&params, 0);
return -1;
}
}
if (width == ~0U) {
string_list_clear(&params, 0);
return strbuf_addf_ret(err, -1, _("positive width expected with the %%(align) atom"));
}
align->width = width;
string_list_clear(&params, 0);
return 0;
}
static int if_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (!arg) {
atom->u.if_then_else.cmp_status = COMPARE_NONE;
return 0;
} else if (skip_prefix(arg, "equals=", &atom->u.if_then_else.str)) {
atom->u.if_then_else.cmp_status = COMPARE_EQUAL;
} else if (skip_prefix(arg, "notequals=", &atom->u.if_then_else.str)) {
atom->u.if_then_else.cmp_status = COMPARE_UNEQUAL;
} else
return strbuf_addf_ret(err, -1, _("unrecognized %%(%s) argument: %s"), "if", arg);
return 0;
}
static int rest_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err)
{
if (arg)
return strbuf_addf_ret(err, -1, _("%%(rest) does not take arguments"));
format->use_rest = 1;
return 0;
}
static int head_atom_parser(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *unused_err)
{
atom->u.head = resolve_refdup("HEAD", RESOLVE_REF_READING, NULL, NULL);
return 0;
}
static struct {
const char *name;
info_source source;
cmp_type cmp_type;
int (*parser)(struct ref_format *format, struct used_atom *atom,
const char *arg, struct strbuf *err);
} valid_atom[] = {
[ATOM_REFNAME] = { "refname", SOURCE_NONE, FIELD_STR, refname_atom_parser },
[ATOM_OBJECTTYPE] = { "objecttype", SOURCE_OTHER, FIELD_STR, objecttype_atom_parser },
[ATOM_OBJECTSIZE] = { "objectsize", SOURCE_OTHER, FIELD_ULONG, objectsize_atom_parser },
[ATOM_OBJECTNAME] = { "objectname", SOURCE_OTHER, FIELD_STR, oid_atom_parser },
[ATOM_DELTABASE] = { "deltabase", SOURCE_OTHER, FIELD_STR, deltabase_atom_parser },
[ATOM_TREE] = { "tree", SOURCE_OBJ, FIELD_STR, oid_atom_parser },
[ATOM_PARENT] = { "parent", SOURCE_OBJ, FIELD_STR, oid_atom_parser },
[ATOM_NUMPARENT] = { "numparent", SOURCE_OBJ, FIELD_ULONG },
[ATOM_OBJECT] = { "object", SOURCE_OBJ },
[ATOM_TYPE] = { "type", SOURCE_OBJ },
[ATOM_TAG] = { "tag", SOURCE_OBJ },
[ATOM_AUTHOR] = { "author", SOURCE_OBJ },
[ATOM_AUTHORNAME] = { "authorname", SOURCE_OBJ },
[ATOM_AUTHOREMAIL] = { "authoremail", SOURCE_OBJ, FIELD_STR, person_email_atom_parser },
[ATOM_AUTHORDATE] = { "authordate", SOURCE_OBJ, FIELD_TIME },
[ATOM_COMMITTER] = { "committer", SOURCE_OBJ },
[ATOM_COMMITTERNAME] = { "committername", SOURCE_OBJ },
[ATOM_COMMITTEREMAIL] = { "committeremail", SOURCE_OBJ, FIELD_STR, person_email_atom_parser },
[ATOM_COMMITTERDATE] = { "committerdate", SOURCE_OBJ, FIELD_TIME },
[ATOM_TAGGER] = { "tagger", SOURCE_OBJ },
[ATOM_TAGGERNAME] = { "taggername", SOURCE_OBJ },
[ATOM_TAGGEREMAIL] = { "taggeremail", SOURCE_OBJ, FIELD_STR, person_email_atom_parser },
[ATOM_TAGGERDATE] = { "taggerdate", SOURCE_OBJ, FIELD_TIME },
[ATOM_CREATOR] = { "creator", SOURCE_OBJ },
[ATOM_CREATORDATE] = { "creatordate", SOURCE_OBJ, FIELD_TIME },
[ATOM_SUBJECT] = { "subject", SOURCE_OBJ, FIELD_STR, subject_atom_parser },
[ATOM_BODY] = { "body", SOURCE_OBJ, FIELD_STR, body_atom_parser },
[ATOM_TRAILERS] = { "trailers", SOURCE_OBJ, FIELD_STR, trailers_atom_parser },
[ATOM_CONTENTS] = { "contents", SOURCE_OBJ, FIELD_STR, contents_atom_parser },
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
[ATOM_RAW] = { "raw", SOURCE_OBJ, FIELD_STR, raw_atom_parser },
[ATOM_UPSTREAM] = { "upstream", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser },
[ATOM_PUSH] = { "push", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser },
[ATOM_SYMREF] = { "symref", SOURCE_NONE, FIELD_STR, refname_atom_parser },
[ATOM_FLAG] = { "flag", SOURCE_NONE },
[ATOM_HEAD] = { "HEAD", SOURCE_NONE, FIELD_STR, head_atom_parser },
[ATOM_COLOR] = { "color", SOURCE_NONE, FIELD_STR, color_atom_parser },
[ATOM_WORKTREEPATH] = { "worktreepath", SOURCE_NONE },
[ATOM_ALIGN] = { "align", SOURCE_NONE, FIELD_STR, align_atom_parser },
[ATOM_END] = { "end", SOURCE_NONE },
[ATOM_IF] = { "if", SOURCE_NONE, FIELD_STR, if_atom_parser },
[ATOM_THEN] = { "then", SOURCE_NONE },
[ATOM_ELSE] = { "else", SOURCE_NONE },
[ATOM_REST] = { "rest", SOURCE_NONE, FIELD_STR, rest_atom_parser },
/*
* Please update $__git_ref_fieldlist in git-completion.bash
* when you add new atoms
*/
};
#define REF_FORMATTING_STATE_INIT { 0 }
struct ref_formatting_stack {
struct ref_formatting_stack *prev;
struct strbuf output;
void (*at_end)(struct ref_formatting_stack **stack);
2015-09-11 17:03:07 +02:00
void *at_end_data;
};
struct ref_formatting_state {
int quote_style;
struct ref_formatting_stack *stack;
};
struct atom_value {
const char *s;
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
ssize_t s_size;
int (*handler)(struct atom_value *atomv, struct ref_formatting_state *state,
struct strbuf *err);
uintmax_t value; /* used for sorting when not FIELD_STR */
struct used_atom *atom;
};
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
#define ATOM_SIZE_UNSPECIFIED (-1)
#define ATOM_VALUE_INIT { \
.s_size = ATOM_SIZE_UNSPECIFIED \
}
/*
* Used to parse format string and sort specifiers
*/
static int parse_ref_filter_atom(struct ref_format *format,
const char *atom, const char *ep,
struct strbuf *err)
{
const char *sp;
const char *arg;
int i, at, atom_len;
sp = atom;
if (*sp == '*' && sp < ep)
sp++; /* deref */
if (ep <= sp)
return strbuf_addf_ret(err, -1, _("malformed field name: %.*s"),
(int)(ep-atom), atom);
/*
* If the atom name has a colon, strip it and everything after
* it off - it specifies the format for this entry, and
* shouldn't be used for checking against the valid_atom
* table.
*/
arg = memchr(sp, ':', ep - sp);
atom_len = (arg ? arg : ep) - sp;
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
/* Do we have the atom already used elsewhere? */
for (i = 0; i < used_atom_cnt; i++) {
int len = strlen(used_atom[i].name);
if (len == ep - atom && !memcmp(used_atom[i].name, atom, len))
return i;
}
/* Is the atom a valid one? */
for (i = 0; i < ARRAY_SIZE(valid_atom); i++) {
int len = strlen(valid_atom[i].name);
if (len == atom_len && !memcmp(valid_atom[i].name, sp, len))
break;
}
if (ARRAY_SIZE(valid_atom) <= i)
return strbuf_addf_ret(err, -1, _("unknown field name: %.*s"),
(int)(ep-atom), atom);
if (valid_atom[i].source != SOURCE_NONE && !have_git_dir())
return strbuf_addf_ret(err, -1,
_("not a git repository, but the field '%.*s' requires access to object data"),
(int)(ep-atom), atom);
/* Add it in, including the deref prefix */
at = used_atom_cnt;
used_atom_cnt++;
REALLOC_ARRAY(used_atom, used_atom_cnt);
used_atom[at].atom_type = i;
used_atom[at].name = xmemdupz(atom, ep - atom);
used_atom[at].type = valid_atom[i].cmp_type;
used_atom[at].source = valid_atom[i].source;
if (used_atom[at].source == SOURCE_OBJ) {
if (*atom == '*')
oi_deref.info.contentp = &oi_deref.content;
else
oi.info.contentp = &oi.content;
}
if (arg) {
arg = used_atom[at].name + (arg - atom) + 1;
if (!*arg) {
/*
* Treat empty sub-arguments list as NULL (i.e.,
* "%(atom:)" is equivalent to "%(atom)").
*/
arg = NULL;
}
}
memset(&used_atom[at].u, 0, sizeof(used_atom[at].u));
if (valid_atom[i].parser && valid_atom[i].parser(format, &used_atom[at], arg, err))
return -1;
if (*atom == '*')
need_tagged = 1;
if (i == ATOM_SYMREF)
need_symref = 1;
return at;
}
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
static void quote_formatting(struct strbuf *s, const char *str, ssize_t len, int quote_style)
{
switch (quote_style) {
case QUOTE_NONE:
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
if (len < 0)
strbuf_addstr(s, str);
else
strbuf_add(s, str, len);
break;
case QUOTE_SHELL:
sq_quote_buf(s, str);
break;
case QUOTE_PERL:
if (len < 0)
perl_quote_buf(s, str);
else
perl_quote_buf_with_len(s, str, len);
break;
case QUOTE_PYTHON:
python_quote_buf(s, str);
break;
case QUOTE_TCL:
tcl_quote_buf(s, str);
break;
}
}
static int append_atom(struct atom_value *v, struct ref_formatting_state *state,
struct strbuf *unused_err)
{
2015-09-11 17:03:07 +02:00
/*
* Quote formatting is only done when the stack has a single
* element. Otherwise quote formatting is done on the
* element's entire output strbuf when the %(end) atom is
* encountered.
*/
if (!state->stack->prev)
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
quote_formatting(&state->stack->output, v->s, v->s_size, state->quote_style);
else if (v->s_size < 0)
2015-09-11 17:03:07 +02:00
strbuf_addstr(&state->stack->output, v->s);
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
else
strbuf_add(&state->stack->output, v->s, v->s_size);
return 0;
}
static void push_stack_element(struct ref_formatting_stack **stack)
{
struct ref_formatting_stack *s = xcalloc(1, sizeof(struct ref_formatting_stack));
strbuf_init(&s->output, 0);
s->prev = *stack;
*stack = s;
}
static void pop_stack_element(struct ref_formatting_stack **stack)
{
struct ref_formatting_stack *current = *stack;
struct ref_formatting_stack *prev = current->prev;
if (prev)
strbuf_addbuf(&prev->output, &current->output);
strbuf_release(&current->output);
free(current);
*stack = prev;
}
static void end_align_handler(struct ref_formatting_stack **stack)
2015-09-11 17:03:07 +02:00
{
struct ref_formatting_stack *cur = *stack;
struct align *align = (struct align *)cur->at_end_data;
2015-09-11 17:03:07 +02:00
struct strbuf s = STRBUF_INIT;
strbuf_utf8_align(&s, align->position, align->width, cur->output.buf);
strbuf_swap(&cur->output, &s);
2015-09-11 17:03:07 +02:00
strbuf_release(&s);
}
static int align_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state,
struct strbuf *unused_err)
2015-09-11 17:03:07 +02:00
{
struct ref_formatting_stack *new_stack;
2015-09-11 17:03:07 +02:00
push_stack_element(&state->stack);
new_stack = state->stack;
new_stack->at_end = end_align_handler;
new_stack->at_end_data = &atomv->atom->u.align;
return 0;
2015-09-11 17:03:07 +02:00
}
static void if_then_else_handler(struct ref_formatting_stack **stack)
{
struct ref_formatting_stack *cur = *stack;
struct ref_formatting_stack *prev = cur->prev;
struct if_then_else *if_then_else = (struct if_then_else *)cur->at_end_data;
if (!if_then_else->then_atom_seen)
die(_("format: %%(%s) atom used without a %%(%s) atom"), "if", "then");
if (if_then_else->else_atom_seen) {
/*
* There is an %(else) atom: we need to drop one state from the
* stack, either the %(else) branch if the condition is satisfied, or
* the %(then) branch if it isn't.
*/
if (if_then_else->condition_satisfied) {
strbuf_reset(&cur->output);
pop_stack_element(&cur);
} else {
strbuf_swap(&cur->output, &prev->output);
strbuf_reset(&cur->output);
pop_stack_element(&cur);
}
} else if (!if_then_else->condition_satisfied) {
/*
* No %(else) atom: just drop the %(then) branch if the
* condition is not satisfied.
*/
strbuf_reset(&cur->output);
}
*stack = cur;
free(if_then_else);
}
static int if_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state,
struct strbuf *unused_err)
{
struct ref_formatting_stack *new_stack;
struct if_then_else *if_then_else = xcalloc(1,
sizeof(struct if_then_else));
if_then_else->str = atomv->atom->u.if_then_else.str;
if_then_else->cmp_status = atomv->atom->u.if_then_else.cmp_status;
push_stack_element(&state->stack);
new_stack = state->stack;
new_stack->at_end = if_then_else_handler;
new_stack->at_end_data = if_then_else;
return 0;
}
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
static int is_empty(struct strbuf *buf)
{
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
const char *cur = buf->buf;
const char *end = buf->buf + buf->len;
while (cur != end && (isspace(*cur)))
cur++;
return cur == end;
}
static int then_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state,
struct strbuf *err)
{
struct ref_formatting_stack *cur = state->stack;
struct if_then_else *if_then_else = NULL;
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
size_t str_len = 0;
if (cur->at_end == if_then_else_handler)
if_then_else = (struct if_then_else *)cur->at_end_data;
if (!if_then_else)
return strbuf_addf_ret(err, -1, _("format: %%(%s) atom used without a %%(%s) atom"), "then", "if");
if (if_then_else->then_atom_seen)
return strbuf_addf_ret(err, -1, _("format: %%(then) atom used more than once"));
if (if_then_else->else_atom_seen)
return strbuf_addf_ret(err, -1, _("format: %%(then) atom used after %%(else)"));
if_then_else->then_atom_seen = 1;
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
if (if_then_else->str)
str_len = strlen(if_then_else->str);
/*
* If the 'equals' or 'notequals' attribute is used then
* perform the required comparison. If not, only non-empty
* strings satisfy the 'if' condition.
*/
if (if_then_else->cmp_status == COMPARE_EQUAL) {
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
if (str_len == cur->output.len &&
!memcmp(if_then_else->str, cur->output.buf, cur->output.len))
if_then_else->condition_satisfied = 1;
} else if (if_then_else->cmp_status == COMPARE_UNEQUAL) {
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
if (str_len != cur->output.len ||
memcmp(if_then_else->str, cur->output.buf, cur->output.len))
if_then_else->condition_satisfied = 1;
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
} else if (cur->output.len && !is_empty(&cur->output))
if_then_else->condition_satisfied = 1;
strbuf_reset(&cur->output);
return 0;
}
static int else_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state,
struct strbuf *err)
{
struct ref_formatting_stack *prev = state->stack;
struct if_then_else *if_then_else = NULL;
if (prev->at_end == if_then_else_handler)
if_then_else = (struct if_then_else *)prev->at_end_data;
if (!if_then_else)
return strbuf_addf_ret(err, -1, _("format: %%(%s) atom used without a %%(%s) atom"), "else", "if");
if (!if_then_else->then_atom_seen)
return strbuf_addf_ret(err, -1, _("format: %%(%s) atom used without a %%(%s) atom"), "else", "then");
if (if_then_else->else_atom_seen)
return strbuf_addf_ret(err, -1, _("format: %%(else) atom used more than once"));
if_then_else->else_atom_seen = 1;
push_stack_element(&state->stack);
state->stack->at_end_data = prev->at_end_data;
state->stack->at_end = prev->at_end;
return 0;
2015-09-11 17:03:07 +02:00
}
static int end_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state,
struct strbuf *err)
2015-09-11 17:03:07 +02:00
{
struct ref_formatting_stack *current = state->stack;
struct strbuf s = STRBUF_INIT;
if (!current->at_end)
return strbuf_addf_ret(err, -1, _("format: %%(end) atom used without corresponding atom"));
current->at_end(&state->stack);
/* Stack may have been popped within at_end(), hence reset the current pointer */
current = state->stack;
2015-09-11 17:03:07 +02:00
/*
* Perform quote formatting when the stack element is that of
* a supporting atom. If nested then perform quote formatting
* only on the topmost supporting atom.
*/
if (!current->prev->prev) {
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
quote_formatting(&s, current->output.buf, current->output.len, state->quote_style);
2015-09-11 17:03:07 +02:00
strbuf_swap(&current->output, &s);
}
strbuf_release(&s);
pop_stack_element(&state->stack);
return 0;
2015-09-11 17:03:07 +02:00
}
/*
* In a format string, find the next occurrence of %(atom).
*/
static const char *find_next(const char *cp)
{
while (*cp) {
if (*cp == '%') {
/*
* %( is the start of an atom;
* %% is a quoted per-cent.
*/
if (cp[1] == '(')
return cp;
else if (cp[1] == '%')
cp++; /* skip over two % */
/* otherwise this is a singleton, literal % */
}
cp++;
}
return NULL;
}
static int reject_atom(enum atom_type atom_type)
{
return atom_type == ATOM_REST;
}
/*
* Make sure the format string is well formed, and parse out
* the used atoms.
*/
int verify_ref_format(struct ref_format *format)
{
const char *cp, *sp;
format->need_color_reset_at_eol = 0;
for (cp = format->format; *cp && (sp = find_next(cp)); ) {
struct strbuf err = STRBUF_INIT;
const char *color, *ep = strchr(sp, ')');
int at;
if (!ep)
return error(_("malformed format string %s"), sp);
/* sp points at "%(" and ep points at the closing ")" */
at = parse_ref_filter_atom(format, sp + 2, ep, &err);
if (at < 0)
die("%s", err.buf);
if (reject_atom(used_atom[at].atom_type))
die(_("this command reject atom %%(%.*s)"), (int)(ep - sp - 2), sp + 2);
if ((format->quote_style == QUOTE_PYTHON ||
format->quote_style == QUOTE_SHELL ||
format->quote_style == QUOTE_TCL) &&
used_atom[at].atom_type == ATOM_RAW &&
used_atom[at].u.raw_data.option == RAW_BARE)
die(_("--format=%.*s cannot be used with "
"--python, --shell, --tcl"), (int)(ep - sp - 2), sp + 2);
cp = ep + 1;
if (skip_prefix(used_atom[at].name, "color:", &color))
format->need_color_reset_at_eol = !!strcmp(color, "reset");
strbuf_release(&err);
}
if (format->need_color_reset_at_eol && !want_color(format->use_color))
format->need_color_reset_at_eol = 0;
return 0;
}
static const char *do_grab_oid(const char *field, const struct object_id *oid,
struct used_atom *atom)
{
switch (atom->u.oid.option) {
case O_FULL:
return oid_to_hex(oid);
case O_LENGTH:
return find_unique_abbrev(oid, atom->u.oid.length);
case O_SHORT:
return find_unique_abbrev(oid, DEFAULT_ABBREV);
default:
BUG("unknown %%(%s) option", field);
}
}
static int grab_oid(const char *name, const char *field, const struct object_id *oid,
struct atom_value *v, struct used_atom *atom)
{
if (starts_with(name, field)) {
v->s = xstrdup(do_grab_oid(field, oid, atom));
return 1;
}
return 0;
}
/* See grab_values */
static void grab_common_values(struct atom_value *val, int deref, struct expand_data *oi)
{
int i;
for (i = 0; i < used_atom_cnt; i++) {
const char *name = used_atom[i].name;
enum atom_type atom_type = used_atom[i].atom_type;
struct atom_value *v = &val[i];
if (!!deref != (*name == '*'))
continue;
if (deref)
name++;
if (atom_type == ATOM_OBJECTTYPE)
v->s = xstrdup(type_name(oi->type));
else if (atom_type == ATOM_OBJECTSIZE) {
if (used_atom[i].u.objectsize.option == O_SIZE_DISK) {
v->value = oi->disk_size;
v->s = xstrfmt("%"PRIuMAX, (uintmax_t)oi->disk_size);
} else if (used_atom[i].u.objectsize.option == O_SIZE) {
v->value = oi->size;
v->s = xstrfmt("%"PRIuMAX , (uintmax_t)oi->size);
}
} else if (atom_type == ATOM_DELTABASE)
v->s = xstrdup(oid_to_hex(&oi->delta_base_oid));
else if (atom_type == ATOM_OBJECTNAME && deref)
grab_oid(name, "objectname", &oi->oid, v, &used_atom[i]);
}
}
/* See grab_values */
static void grab_tag_values(struct atom_value *val, int deref, struct object *obj)
{
int i;
struct tag *tag = (struct tag *) obj;
for (i = 0; i < used_atom_cnt; i++) {
const char *name = used_atom[i].name;
enum atom_type atom_type = used_atom[i].atom_type;
struct atom_value *v = &val[i];
if (!!deref != (*name == '*'))
continue;
if (deref)
name++;
if (atom_type == ATOM_TAG)
v->s = xstrdup(tag->tag);
else if (atom_type == ATOM_TYPE && tag->tagged)
v->s = xstrdup(type_name(tag->tagged->type));
else if (atom_type == ATOM_OBJECT && tag->tagged)
v->s = xstrdup(oid_to_hex(&tag->tagged->oid));
}
}
/* See grab_values */
static void grab_commit_values(struct atom_value *val, int deref, struct object *obj)
{
int i;
struct commit *commit = (struct commit *) obj;
for (i = 0; i < used_atom_cnt; i++) {
const char *name = used_atom[i].name;
enum atom_type atom_type = used_atom[i].atom_type;
struct atom_value *v = &val[i];
if (!!deref != (*name == '*'))
continue;
if (deref)
name++;
if (atom_type == ATOM_TREE &&
grab_oid(name, "tree", get_commit_tree_oid(commit), v, &used_atom[i]))
continue;
if (atom_type == ATOM_NUMPARENT) {
v->value = commit_list_count(commit->parents);
v->s = xstrfmt("%lu", (unsigned long)v->value);
}
else if (atom_type == ATOM_PARENT) {
struct commit_list *parents;
struct strbuf s = STRBUF_INIT;
for (parents = commit->parents; parents; parents = parents->next) {
struct object_id *oid = &parents->item->object.oid;
if (parents != commit->parents)
strbuf_addch(&s, ' ');
strbuf_addstr(&s, do_grab_oid("parent", oid, &used_atom[i]));
}
v->s = strbuf_detach(&s, NULL);
}
}
}
static const char *find_wholine(const char *who, int wholen, const char *buf)
{
const char *eol;
while (*buf) {
if (!strncmp(buf, who, wholen) &&
buf[wholen] == ' ')
return buf + wholen + 1;
eol = strchr(buf, '\n');
if (!eol)
return "";
eol++;
if (*eol == '\n')
return ""; /* end of header */
buf = eol;
}
return "";
}
static const char *copy_line(const char *buf)
{
const char *eol = strchrnul(buf, '\n');
return xmemdupz(buf, eol - buf);
}
static const char *copy_name(const char *buf)
{
const char *cp;
for (cp = buf; *cp && *cp != '\n'; cp++) {
if (!strncmp(cp, " <", 2))
return xmemdupz(buf, cp - buf);
}
return xstrdup("");
}
static const char *copy_email(const char *buf, struct used_atom *atom)
{
const char *email = strchr(buf, '<');
const char *eoemail;
if (!email)
return xstrdup("");
switch (atom->u.email_option.option) {
case EO_RAW:
eoemail = strchr(email, '>');
if (eoemail)
eoemail++;
break;
case EO_TRIM:
email++;
eoemail = strchr(email, '>');
break;
case EO_LOCALPART:
email++;
eoemail = strchr(email, '@');
if (!eoemail)
eoemail = strchr(email, '>');
break;
default:
BUG("unknown email option");
}
if (!eoemail)
return xstrdup("");
return xmemdupz(email, eoemail - email);
}
static char *copy_subject(const char *buf, unsigned long len)
{
ref-filter: handle CRLF at end-of-line more gracefully The ref-filter code does not correctly handle commit or tag messages that use CRLF as the line terminator. Such messages can be created with the `--cleanup=verbatim` option of `git commit` and `git tag`, or by using `git commit-tree` directly. The function `find_subpos` in ref-filter.c looks for two consecutive LFs to find the end of the subject line, a sequence which is absent in messages using CRLF. This results in the whole message being parsed as the subject line (`%(contents:subject)`), and the body of the message (`%(contents:body)`) being empty. Moreover, in `copy_subject`, which wants to return the subject as a single line, '\n' is replaced by space, but '\r' is untouched. This impacts the output of `git branch`, `git tag` and `git for-each-ref`. This behaviour is a regression for `git branch --verbose`, which bisects down to 949af0684c (branch: use ref-filter printing APIs, 2017-01-10). Adjust the ref-filter code to be more lenient by hardening the logic in `copy_subject` and `find_subpos` to correctly parse messages containing CRLF. Add a new test script, 't3920-crlf-messages.sh', to test the behaviour of commands using either the ref-filter or the pretty APIs with messages using CRLF line endings. The function `test_crlf_subject_body_and_contents` can be used to test that the `--format` option of `branch`, `tag`, `for-each-ref`, `log` and `show` correctly displays the subject, body and raw content of commit and tag messages using CRLF. Test the output of `branch`, `tag` and `for-each-ref` with such commits. Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-10-29 13:48:28 +01:00
struct strbuf sb = STRBUF_INIT;
int i;
ref-filter: handle CRLF at end-of-line more gracefully The ref-filter code does not correctly handle commit or tag messages that use CRLF as the line terminator. Such messages can be created with the `--cleanup=verbatim` option of `git commit` and `git tag`, or by using `git commit-tree` directly. The function `find_subpos` in ref-filter.c looks for two consecutive LFs to find the end of the subject line, a sequence which is absent in messages using CRLF. This results in the whole message being parsed as the subject line (`%(contents:subject)`), and the body of the message (`%(contents:body)`) being empty. Moreover, in `copy_subject`, which wants to return the subject as a single line, '\n' is replaced by space, but '\r' is untouched. This impacts the output of `git branch`, `git tag` and `git for-each-ref`. This behaviour is a regression for `git branch --verbose`, which bisects down to 949af0684c (branch: use ref-filter printing APIs, 2017-01-10). Adjust the ref-filter code to be more lenient by hardening the logic in `copy_subject` and `find_subpos` to correctly parse messages containing CRLF. Add a new test script, 't3920-crlf-messages.sh', to test the behaviour of commands using either the ref-filter or the pretty APIs with messages using CRLF line endings. The function `test_crlf_subject_body_and_contents` can be used to test that the `--format` option of `branch`, `tag`, `for-each-ref`, `log` and `show` correctly displays the subject, body and raw content of commit and tag messages using CRLF. Test the output of `branch`, `tag` and `for-each-ref` with such commits. Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-10-29 13:48:28 +01:00
for (i = 0; i < len; i++) {
if (buf[i] == '\r' && i + 1 < len && buf[i + 1] == '\n')
continue; /* ignore CR in CRLF */
ref-filter: handle CRLF at end-of-line more gracefully The ref-filter code does not correctly handle commit or tag messages that use CRLF as the line terminator. Such messages can be created with the `--cleanup=verbatim` option of `git commit` and `git tag`, or by using `git commit-tree` directly. The function `find_subpos` in ref-filter.c looks for two consecutive LFs to find the end of the subject line, a sequence which is absent in messages using CRLF. This results in the whole message being parsed as the subject line (`%(contents:subject)`), and the body of the message (`%(contents:body)`) being empty. Moreover, in `copy_subject`, which wants to return the subject as a single line, '\n' is replaced by space, but '\r' is untouched. This impacts the output of `git branch`, `git tag` and `git for-each-ref`. This behaviour is a regression for `git branch --verbose`, which bisects down to 949af0684c (branch: use ref-filter printing APIs, 2017-01-10). Adjust the ref-filter code to be more lenient by hardening the logic in `copy_subject` and `find_subpos` to correctly parse messages containing CRLF. Add a new test script, 't3920-crlf-messages.sh', to test the behaviour of commands using either the ref-filter or the pretty APIs with messages using CRLF line endings. The function `test_crlf_subject_body_and_contents` can be used to test that the `--format` option of `branch`, `tag`, `for-each-ref`, `log` and `show` correctly displays the subject, body and raw content of commit and tag messages using CRLF. Test the output of `branch`, `tag` and `for-each-ref` with such commits. Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-10-29 13:48:28 +01:00
if (buf[i] == '\n')
strbuf_addch(&sb, ' ');
else
strbuf_addch(&sb, buf[i]);
}
return strbuf_detach(&sb, NULL);
}
static void grab_date(const char *buf, struct atom_value *v, const char *atomname)
{
const char *eoemail = strstr(buf, "> ");
char *zone;
timestamp_t timestamp;
long tz;
struct date_mode date_mode = DATE_MODE_INIT;
const char *formatp;
/*
* We got here because atomname ends in "date" or "date<something>";
* it's not possible that <something> is not ":<format>" because
* parse_ref_filter_atom() wouldn't have allowed it, so we can assume that no
* ":" means no format is specified, and use the default.
*/
formatp = strchr(atomname, ':');
if (formatp) {
formatp++;
parse_date_format(formatp, &date_mode);
}
if (!eoemail)
goto bad;
timestamp = parse_timestamp(eoemail + 2, &zone, 10);
if (timestamp == TIME_MAX)
goto bad;
tz = strtol(zone, NULL, 10);
if ((tz == LONG_MIN || tz == LONG_MAX) && errno == ERANGE)
goto bad;
v->s = xstrdup(show_date(timestamp, tz, &date_mode));
v->value = timestamp;
date API: add and use a date_mode_release() Fix a memory leak in the parse_date_format() function by providing a new date_mode_release() companion function. By using this in "t/helper/test-date.c" we can mark the "t0006-date.sh" test as passing when git is compiled with SANITIZE=leak, and whitelist it to run under "GIT_TEST_PASSING_SANITIZE_LEAK=true" by adding "TEST_PASSES_SANITIZE_LEAK=true" to the test itself. The other tests that expose this memory leak (i.e. take the "mode->type == DATE_STRFTIME" branch in parse_date_format()) are "t6300-for-each-ref.sh" and "t7004-tag.sh". The former is due to an easily fixed leak in "ref-filter.c", and brings the failures in "t6300-for-each-ref.sh" down from 51 to 48. Fixing the remaining leaks will have to wait until there's a release_revisions() in "revision.c", as they have to do with leaks via "struct rev_info". There is also a leak in "builtin/blame.c" due to its call to parse_date_format() to parse the "blame.date" configuration. However as it declares a file-level "static struct date_mode blame_date_mode" to track the data, LSAN will not report it as a leak. It's possible to get valgrind(1) to complain about it with e.g.: valgrind --leak-check=full --show-leak-kinds=all ./git -P -c blame.date=format:%Y blame README.md But let's focus on things LSAN complains about, and are thus observable with "TEST_PASSES_SANITIZE_LEAK=true". We should get to fixing memory leaks in "builtin/blame.c", but as doing so would require some re-arrangement of cmd_blame() let's leave it for some other time. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-02-16 09:14:05 +01:00
date_mode_release(&date_mode);
return;
bad:
v->s = xstrdup("");
v->value = 0;
}
/* See grab_values */
static void grab_person(const char *who, struct atom_value *val, int deref, void *buf)
{
int i;
int wholen = strlen(who);
const char *wholine = NULL;
for (i = 0; i < used_atom_cnt; i++) {
const char *name = used_atom[i].name;
struct atom_value *v = &val[i];
if (!!deref != (*name == '*'))
continue;
if (deref)
name++;
if (strncmp(who, name, wholen))
continue;
if (name[wholen] != 0 &&
strcmp(name + wholen, "name") &&
!starts_with(name + wholen, "email") &&
!starts_with(name + wholen, "date"))
continue;
if (!wholine)
wholine = find_wholine(who, wholen, buf);
if (!wholine)
return; /* no point looking for it */
if (name[wholen] == 0)
v->s = copy_line(wholine);
else if (!strcmp(name + wholen, "name"))
v->s = copy_name(wholine);
else if (starts_with(name + wholen, "email"))
v->s = copy_email(wholine, &used_atom[i]);
else if (starts_with(name + wholen, "date"))
grab_date(wholine, v, name);
}
/*
* For a tag or a commit object, if "creator" or "creatordate" is
* requested, do something special.
*/
if (strcmp(who, "tagger") && strcmp(who, "committer"))
return; /* "author" for commit object is not wanted */
if (!wholine)
wholine = find_wholine(who, wholen, buf);
if (!wholine)
return;
for (i = 0; i < used_atom_cnt; i++) {
const char *name = used_atom[i].name;
enum atom_type atom_type = used_atom[i].atom_type;
struct atom_value *v = &val[i];
if (!!deref != (*name == '*'))
continue;
if (deref)
name++;
if (atom_type == ATOM_CREATORDATE)
grab_date(wholine, v, name);
else if (atom_type == ATOM_CREATOR)
v->s = copy_line(wholine);
}
}
static void find_subpos(const char *buf,
const char **sub, size_t *sublen,
const char **body, size_t *bodylen,
size_t *nonsiglen,
const char **sig, size_t *siglen)
{
struct strbuf payload = STRBUF_INIT;
struct strbuf signature = STRBUF_INIT;
const char *eol;
const char *end = buf + strlen(buf);
const char *sigstart;
/* parse signature first; we might not even have a subject line */
parse_signature(buf, end - buf, &payload, &signature);
/* skip past header until we hit empty line */
while (*buf && *buf != '\n') {
eol = strchrnul(buf, '\n');
if (*eol)
eol++;
buf = eol;
}
/* skip any empty lines */
while (*buf == '\n')
buf++;
*sig = strbuf_detach(&signature, siglen);
sigstart = buf + parse_signed_buffer(buf, strlen(buf));
/* subject is first non-empty line */
*sub = buf;
ref-filter: handle CRLF at end-of-line more gracefully The ref-filter code does not correctly handle commit or tag messages that use CRLF as the line terminator. Such messages can be created with the `--cleanup=verbatim` option of `git commit` and `git tag`, or by using `git commit-tree` directly. The function `find_subpos` in ref-filter.c looks for two consecutive LFs to find the end of the subject line, a sequence which is absent in messages using CRLF. This results in the whole message being parsed as the subject line (`%(contents:subject)`), and the body of the message (`%(contents:body)`) being empty. Moreover, in `copy_subject`, which wants to return the subject as a single line, '\n' is replaced by space, but '\r' is untouched. This impacts the output of `git branch`, `git tag` and `git for-each-ref`. This behaviour is a regression for `git branch --verbose`, which bisects down to 949af0684c (branch: use ref-filter printing APIs, 2017-01-10). Adjust the ref-filter code to be more lenient by hardening the logic in `copy_subject` and `find_subpos` to correctly parse messages containing CRLF. Add a new test script, 't3920-crlf-messages.sh', to test the behaviour of commands using either the ref-filter or the pretty APIs with messages using CRLF line endings. The function `test_crlf_subject_body_and_contents` can be used to test that the `--format` option of `branch`, `tag`, `for-each-ref`, `log` and `show` correctly displays the subject, body and raw content of commit and tag messages using CRLF. Test the output of `branch`, `tag` and `for-each-ref` with such commits. Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-10-29 13:48:28 +01:00
/* subject goes to first empty line before signature begins */
if ((eol = strstr(*sub, "\n\n"))) {
eol = eol < sigstart ? eol : sigstart;
ref-filter: handle CRLF at end-of-line more gracefully The ref-filter code does not correctly handle commit or tag messages that use CRLF as the line terminator. Such messages can be created with the `--cleanup=verbatim` option of `git commit` and `git tag`, or by using `git commit-tree` directly. The function `find_subpos` in ref-filter.c looks for two consecutive LFs to find the end of the subject line, a sequence which is absent in messages using CRLF. This results in the whole message being parsed as the subject line (`%(contents:subject)`), and the body of the message (`%(contents:body)`) being empty. Moreover, in `copy_subject`, which wants to return the subject as a single line, '\n' is replaced by space, but '\r' is untouched. This impacts the output of `git branch`, `git tag` and `git for-each-ref`. This behaviour is a regression for `git branch --verbose`, which bisects down to 949af0684c (branch: use ref-filter printing APIs, 2017-01-10). Adjust the ref-filter code to be more lenient by hardening the logic in `copy_subject` and `find_subpos` to correctly parse messages containing CRLF. Add a new test script, 't3920-crlf-messages.sh', to test the behaviour of commands using either the ref-filter or the pretty APIs with messages using CRLF line endings. The function `test_crlf_subject_body_and_contents` can be used to test that the `--format` option of `branch`, `tag`, `for-each-ref`, `log` and `show` correctly displays the subject, body and raw content of commit and tag messages using CRLF. Test the output of `branch`, `tag` and `for-each-ref` with such commits. Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-10-29 13:48:28 +01:00
/* check if message uses CRLF */
} else if (! (eol = strstr(*sub, "\r\n\r\n"))) {
/* treat whole message as subject */
eol = strrchr(*sub, '\0');
}
ref-filter: handle CRLF at end-of-line more gracefully The ref-filter code does not correctly handle commit or tag messages that use CRLF as the line terminator. Such messages can be created with the `--cleanup=verbatim` option of `git commit` and `git tag`, or by using `git commit-tree` directly. The function `find_subpos` in ref-filter.c looks for two consecutive LFs to find the end of the subject line, a sequence which is absent in messages using CRLF. This results in the whole message being parsed as the subject line (`%(contents:subject)`), and the body of the message (`%(contents:body)`) being empty. Moreover, in `copy_subject`, which wants to return the subject as a single line, '\n' is replaced by space, but '\r' is untouched. This impacts the output of `git branch`, `git tag` and `git for-each-ref`. This behaviour is a regression for `git branch --verbose`, which bisects down to 949af0684c (branch: use ref-filter printing APIs, 2017-01-10). Adjust the ref-filter code to be more lenient by hardening the logic in `copy_subject` and `find_subpos` to correctly parse messages containing CRLF. Add a new test script, 't3920-crlf-messages.sh', to test the behaviour of commands using either the ref-filter or the pretty APIs with messages using CRLF line endings. The function `test_crlf_subject_body_and_contents` can be used to test that the `--format` option of `branch`, `tag`, `for-each-ref`, `log` and `show` correctly displays the subject, body and raw content of commit and tag messages using CRLF. Test the output of `branch`, `tag` and `for-each-ref` with such commits. Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-10-29 13:48:28 +01:00
buf = eol;
*sublen = buf - *sub;
/* drop trailing newline, if present */
ref-filter: handle CRLF at end-of-line more gracefully The ref-filter code does not correctly handle commit or tag messages that use CRLF as the line terminator. Such messages can be created with the `--cleanup=verbatim` option of `git commit` and `git tag`, or by using `git commit-tree` directly. The function `find_subpos` in ref-filter.c looks for two consecutive LFs to find the end of the subject line, a sequence which is absent in messages using CRLF. This results in the whole message being parsed as the subject line (`%(contents:subject)`), and the body of the message (`%(contents:body)`) being empty. Moreover, in `copy_subject`, which wants to return the subject as a single line, '\n' is replaced by space, but '\r' is untouched. This impacts the output of `git branch`, `git tag` and `git for-each-ref`. This behaviour is a regression for `git branch --verbose`, which bisects down to 949af0684c (branch: use ref-filter printing APIs, 2017-01-10). Adjust the ref-filter code to be more lenient by hardening the logic in `copy_subject` and `find_subpos` to correctly parse messages containing CRLF. Add a new test script, 't3920-crlf-messages.sh', to test the behaviour of commands using either the ref-filter or the pretty APIs with messages using CRLF line endings. The function `test_crlf_subject_body_and_contents` can be used to test that the `--format` option of `branch`, `tag`, `for-each-ref`, `log` and `show` correctly displays the subject, body and raw content of commit and tag messages using CRLF. Test the output of `branch`, `tag` and `for-each-ref` with such commits. Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-10-29 13:48:28 +01:00
while (*sublen && ((*sub)[*sublen - 1] == '\n' ||
(*sub)[*sublen - 1] == '\r'))
*sublen -= 1;
/* skip any empty lines */
ref-filter: handle CRLF at end-of-line more gracefully The ref-filter code does not correctly handle commit or tag messages that use CRLF as the line terminator. Such messages can be created with the `--cleanup=verbatim` option of `git commit` and `git tag`, or by using `git commit-tree` directly. The function `find_subpos` in ref-filter.c looks for two consecutive LFs to find the end of the subject line, a sequence which is absent in messages using CRLF. This results in the whole message being parsed as the subject line (`%(contents:subject)`), and the body of the message (`%(contents:body)`) being empty. Moreover, in `copy_subject`, which wants to return the subject as a single line, '\n' is replaced by space, but '\r' is untouched. This impacts the output of `git branch`, `git tag` and `git for-each-ref`. This behaviour is a regression for `git branch --verbose`, which bisects down to 949af0684c (branch: use ref-filter printing APIs, 2017-01-10). Adjust the ref-filter code to be more lenient by hardening the logic in `copy_subject` and `find_subpos` to correctly parse messages containing CRLF. Add a new test script, 't3920-crlf-messages.sh', to test the behaviour of commands using either the ref-filter or the pretty APIs with messages using CRLF line endings. The function `test_crlf_subject_body_and_contents` can be used to test that the `--format` option of `branch`, `tag`, `for-each-ref`, `log` and `show` correctly displays the subject, body and raw content of commit and tag messages using CRLF. Test the output of `branch`, `tag` and `for-each-ref` with such commits. Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-10-29 13:48:28 +01:00
while (*buf == '\n' || *buf == '\r')
buf++;
*body = buf;
*bodylen = strlen(buf);
*nonsiglen = sigstart - buf;
}
/*
* If 'lines' is greater than 0, append that many lines from the given
* 'buf' of length 'size' to the given strbuf.
*/
static void append_lines(struct strbuf *out, const char *buf, unsigned long size, int lines)
{
int i;
const char *sp, *eol;
size_t len;
sp = buf;
for (i = 0; i < lines && sp < buf + size; i++) {
if (i)
strbuf_addstr(out, "\n ");
eol = memchr(sp, '\n', size - (sp - buf));
len = eol ? eol - sp : size - (sp - buf);
strbuf_add(out, sp, len);
if (!eol)
break;
sp = eol + 1;
}
}
/* See grab_values */
static void grab_sub_body_contents(struct atom_value *val, int deref, struct expand_data *data)
{
int i;
const char *subpos = NULL, *bodypos = NULL, *sigpos = NULL;
size_t sublen = 0, bodylen = 0, nonsiglen = 0, siglen = 0;
void *buf = data->content;
for (i = 0; i < used_atom_cnt; i++) {
struct used_atom *atom = &used_atom[i];
const char *name = atom->name;
struct atom_value *v = &val[i];
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
enum atom_type atom_type = atom->atom_type;
if (!!deref != (*name == '*'))
continue;
if (deref)
name++;
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
if (atom_type == ATOM_RAW) {
unsigned long buf_size = data->size;
if (atom->u.raw_data.option == RAW_BARE) {
v->s = xmemdupz(buf, buf_size);
v->s_size = buf_size;
} else if (atom->u.raw_data.option == RAW_LENGTH) {
v->s = xstrfmt("%"PRIuMAX, (uintmax_t)buf_size);
}
continue;
}
if ((data->type != OBJ_TAG &&
data->type != OBJ_COMMIT) ||
(strcmp(name, "body") &&
!starts_with(name, "subject") &&
!starts_with(name, "trailers") &&
!starts_with(name, "contents")))
continue;
if (!subpos)
find_subpos(buf,
&subpos, &sublen,
&bodypos, &bodylen, &nonsiglen,
&sigpos, &siglen);
if (atom->u.contents.option == C_SUB)
v->s = copy_subject(subpos, sublen);
else if (atom->u.contents.option == C_SUB_SANITIZE) {
struct strbuf sb = STRBUF_INIT;
format_sanitized_subject(&sb, subpos, sublen);
v->s = strbuf_detach(&sb, NULL);
} else if (atom->u.contents.option == C_BODY_DEP)
v->s = xmemdupz(bodypos, bodylen);
else if (atom->u.contents.option == C_LENGTH)
v->s = xstrfmt("%"PRIuMAX, (uintmax_t)strlen(subpos));
else if (atom->u.contents.option == C_BODY)
v->s = xmemdupz(bodypos, nonsiglen);
else if (atom->u.contents.option == C_SIG)
v->s = xmemdupz(sigpos, siglen);
else if (atom->u.contents.option == C_LINES) {
struct strbuf s = STRBUF_INIT;
const char *contents_end = bodypos + nonsiglen;
/* Size is the length of the message after removing the signature */
append_lines(&s, subpos, contents_end - subpos, atom->u.contents.nlines);
v->s = strbuf_detach(&s, NULL);
} else if (atom->u.contents.option == C_TRAILERS) {
struct strbuf s = STRBUF_INIT;
/* Format the trailer info according to the trailer_opts given */
format_trailers_from_commit(&s, subpos, &atom->u.contents.trailer_opts);
v->s = strbuf_detach(&s, NULL);
} else if (atom->u.contents.option == C_BARE)
v->s = xstrdup(subpos);
}
free((void *)sigpos);
}
/*
* We want to have empty print-string for field requests
* that do not apply (e.g. "authordate" for a tag object)
*/
static void fill_missing_values(struct atom_value *val)
{
int i;
for (i = 0; i < used_atom_cnt; i++) {
struct atom_value *v = &val[i];
if (!v->s)
v->s = xstrdup("");
}
}
/*
* val is a list of atom_value to hold returned values. Extract
* the values for atoms in used_atom array out of (obj, buf, sz).
* when deref is false, (obj, buf, sz) is the object that is
* pointed at by the ref itself; otherwise it is the object the
* ref (which is a tag) refers to.
*/
static void grab_values(struct atom_value *val, int deref, struct object *obj, struct expand_data *data)
{
void *buf = data->content;
switch (obj->type) {
case OBJ_TAG:
grab_tag_values(val, deref, obj);
grab_sub_body_contents(val, deref, data);
grab_person("tagger", val, deref, buf);
break;
case OBJ_COMMIT:
grab_commit_values(val, deref, obj);
grab_sub_body_contents(val, deref, data);
grab_person("author", val, deref, buf);
grab_person("committer", val, deref, buf);
break;
case OBJ_TREE:
/* grab_tree_values(val, deref, obj, buf, sz); */
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
grab_sub_body_contents(val, deref, data);
break;
case OBJ_BLOB:
/* grab_blob_values(val, deref, obj, buf, sz); */
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
grab_sub_body_contents(val, deref, data);
break;
default:
die("Eh? Object of type %d?", obj->type);
}
}
static inline char *copy_advance(char *dst, const char *src)
{
while (*src)
*dst++ = *src++;
return dst;
}
static const char *lstrip_ref_components(const char *refname, int len)
tag: do not show ambiguous tag names as "tags/foo" Since b7cc53e9 (tag.c: use 'ref-filter' APIs, 2015-07-11), git-tag has started showing tags with ambiguous names (i.e., when both "heads/foo" and "tags/foo" exists) as "tags/foo" instead of just "foo". This is both: - pointless; the output of "git tag" includes only refs/tags, so we know that "foo" means the one in "refs/tags". and - ambiguous; in the original output, we know that the line "foo" means that "refs/tags/foo" exists. In the new output, it is unclear whether we mean "refs/tags/foo" or "refs/tags/tags/foo". The reason this happens is that commit b7cc53e9 switched git-tag to use ref-filter's "%(refname:short)" output formatting, which was adapted from for-each-ref. This more general code does not know that we care only about tags, and uses shorten_unambiguous_ref to get the short-name. We need to tell it that we care only about "refs/tags/", and it should shorten with respect to that value. In theory, the ref-filter code could figure this out by us passing FILTER_REFS_TAGS. But there are two complications there: 1. The handling of refname:short is deep in formatting code that does not even have our ref_filter struct, let alone the arguments to the filter_ref struct. 2. In git v2.7.0, we expose the formatting language to the user. If we follow this path, it will mean that "%(refname:short)" behaves differently for "tag" versus "for-each-ref" (including "for-each-ref refs/tags/"), which can lead to confusion. Instead, let's add a new modifier to the formatting language, "strip", to remove a specific set of prefix components. This fixes "git tag", and lets users invoke the same behavior from their own custom formats (for "tag" or "for-each-ref") while leaving ":short" with its same consistent meaning in all places. We introduce a test in t7004 for "git tag", which fails without this patch. We also add a similar test in t3203 for "git branch", which does not actually fail. But since it is likely that "branch" will eventually use the same formatting code, the test helps defend against future regressions. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-01-26 04:00:05 +01:00
{
long remaining = len;
const char *start = xstrdup(refname);
const char *to_free = start;
tag: do not show ambiguous tag names as "tags/foo" Since b7cc53e9 (tag.c: use 'ref-filter' APIs, 2015-07-11), git-tag has started showing tags with ambiguous names (i.e., when both "heads/foo" and "tags/foo" exists) as "tags/foo" instead of just "foo". This is both: - pointless; the output of "git tag" includes only refs/tags, so we know that "foo" means the one in "refs/tags". and - ambiguous; in the original output, we know that the line "foo" means that "refs/tags/foo" exists. In the new output, it is unclear whether we mean "refs/tags/foo" or "refs/tags/tags/foo". The reason this happens is that commit b7cc53e9 switched git-tag to use ref-filter's "%(refname:short)" output formatting, which was adapted from for-each-ref. This more general code does not know that we care only about tags, and uses shorten_unambiguous_ref to get the short-name. We need to tell it that we care only about "refs/tags/", and it should shorten with respect to that value. In theory, the ref-filter code could figure this out by us passing FILTER_REFS_TAGS. But there are two complications there: 1. The handling of refname:short is deep in formatting code that does not even have our ref_filter struct, let alone the arguments to the filter_ref struct. 2. In git v2.7.0, we expose the formatting language to the user. If we follow this path, it will mean that "%(refname:short)" behaves differently for "tag" versus "for-each-ref" (including "for-each-ref refs/tags/"), which can lead to confusion. Instead, let's add a new modifier to the formatting language, "strip", to remove a specific set of prefix components. This fixes "git tag", and lets users invoke the same behavior from their own custom formats (for "tag" or "for-each-ref") while leaving ":short" with its same consistent meaning in all places. We introduce a test in t7004 for "git tag", which fails without this patch. We also add a similar test in t3203 for "git branch", which does not actually fail. But since it is likely that "branch" will eventually use the same formatting code, the test helps defend against future regressions. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-01-26 04:00:05 +01:00
if (len < 0) {
int i;
const char *p = refname;
/* Find total no of '/' separated path-components */
for (i = 0; p[i]; p[i] == '/' ? i++ : *p++)
;
/*
* The number of components we need to strip is now
* the total minus the components to be left (Plus one
* because we count the number of '/', but the number
* of components is one more than the no of '/').
*/
remaining = i + len + 1;
}
tag: do not show ambiguous tag names as "tags/foo" Since b7cc53e9 (tag.c: use 'ref-filter' APIs, 2015-07-11), git-tag has started showing tags with ambiguous names (i.e., when both "heads/foo" and "tags/foo" exists) as "tags/foo" instead of just "foo". This is both: - pointless; the output of "git tag" includes only refs/tags, so we know that "foo" means the one in "refs/tags". and - ambiguous; in the original output, we know that the line "foo" means that "refs/tags/foo" exists. In the new output, it is unclear whether we mean "refs/tags/foo" or "refs/tags/tags/foo". The reason this happens is that commit b7cc53e9 switched git-tag to use ref-filter's "%(refname:short)" output formatting, which was adapted from for-each-ref. This more general code does not know that we care only about tags, and uses shorten_unambiguous_ref to get the short-name. We need to tell it that we care only about "refs/tags/", and it should shorten with respect to that value. In theory, the ref-filter code could figure this out by us passing FILTER_REFS_TAGS. But there are two complications there: 1. The handling of refname:short is deep in formatting code that does not even have our ref_filter struct, let alone the arguments to the filter_ref struct. 2. In git v2.7.0, we expose the formatting language to the user. If we follow this path, it will mean that "%(refname:short)" behaves differently for "tag" versus "for-each-ref" (including "for-each-ref refs/tags/"), which can lead to confusion. Instead, let's add a new modifier to the formatting language, "strip", to remove a specific set of prefix components. This fixes "git tag", and lets users invoke the same behavior from their own custom formats (for "tag" or "for-each-ref") while leaving ":short" with its same consistent meaning in all places. We introduce a test in t7004 for "git tag", which fails without this patch. We also add a similar test in t3203 for "git branch", which does not actually fail. But since it is likely that "branch" will eventually use the same formatting code, the test helps defend against future regressions. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-01-26 04:00:05 +01:00
while (remaining > 0) {
tag: do not show ambiguous tag names as "tags/foo" Since b7cc53e9 (tag.c: use 'ref-filter' APIs, 2015-07-11), git-tag has started showing tags with ambiguous names (i.e., when both "heads/foo" and "tags/foo" exists) as "tags/foo" instead of just "foo". This is both: - pointless; the output of "git tag" includes only refs/tags, so we know that "foo" means the one in "refs/tags". and - ambiguous; in the original output, we know that the line "foo" means that "refs/tags/foo" exists. In the new output, it is unclear whether we mean "refs/tags/foo" or "refs/tags/tags/foo". The reason this happens is that commit b7cc53e9 switched git-tag to use ref-filter's "%(refname:short)" output formatting, which was adapted from for-each-ref. This more general code does not know that we care only about tags, and uses shorten_unambiguous_ref to get the short-name. We need to tell it that we care only about "refs/tags/", and it should shorten with respect to that value. In theory, the ref-filter code could figure this out by us passing FILTER_REFS_TAGS. But there are two complications there: 1. The handling of refname:short is deep in formatting code that does not even have our ref_filter struct, let alone the arguments to the filter_ref struct. 2. In git v2.7.0, we expose the formatting language to the user. If we follow this path, it will mean that "%(refname:short)" behaves differently for "tag" versus "for-each-ref" (including "for-each-ref refs/tags/"), which can lead to confusion. Instead, let's add a new modifier to the formatting language, "strip", to remove a specific set of prefix components. This fixes "git tag", and lets users invoke the same behavior from their own custom formats (for "tag" or "for-each-ref") while leaving ":short" with its same consistent meaning in all places. We introduce a test in t7004 for "git tag", which fails without this patch. We also add a similar test in t3203 for "git branch", which does not actually fail. But since it is likely that "branch" will eventually use the same formatting code, the test helps defend against future regressions. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-01-26 04:00:05 +01:00
switch (*start++) {
case '\0':
free((char *)to_free);
return xstrdup("");
tag: do not show ambiguous tag names as "tags/foo" Since b7cc53e9 (tag.c: use 'ref-filter' APIs, 2015-07-11), git-tag has started showing tags with ambiguous names (i.e., when both "heads/foo" and "tags/foo" exists) as "tags/foo" instead of just "foo". This is both: - pointless; the output of "git tag" includes only refs/tags, so we know that "foo" means the one in "refs/tags". and - ambiguous; in the original output, we know that the line "foo" means that "refs/tags/foo" exists. In the new output, it is unclear whether we mean "refs/tags/foo" or "refs/tags/tags/foo". The reason this happens is that commit b7cc53e9 switched git-tag to use ref-filter's "%(refname:short)" output formatting, which was adapted from for-each-ref. This more general code does not know that we care only about tags, and uses shorten_unambiguous_ref to get the short-name. We need to tell it that we care only about "refs/tags/", and it should shorten with respect to that value. In theory, the ref-filter code could figure this out by us passing FILTER_REFS_TAGS. But there are two complications there: 1. The handling of refname:short is deep in formatting code that does not even have our ref_filter struct, let alone the arguments to the filter_ref struct. 2. In git v2.7.0, we expose the formatting language to the user. If we follow this path, it will mean that "%(refname:short)" behaves differently for "tag" versus "for-each-ref" (including "for-each-ref refs/tags/"), which can lead to confusion. Instead, let's add a new modifier to the formatting language, "strip", to remove a specific set of prefix components. This fixes "git tag", and lets users invoke the same behavior from their own custom formats (for "tag" or "for-each-ref") while leaving ":short" with its same consistent meaning in all places. We introduce a test in t7004 for "git tag", which fails without this patch. We also add a similar test in t3203 for "git branch", which does not actually fail. But since it is likely that "branch" will eventually use the same formatting code, the test helps defend against future regressions. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-01-26 04:00:05 +01:00
case '/':
remaining--;
break;
}
}
start = xstrdup(start);
free((char *)to_free);
tag: do not show ambiguous tag names as "tags/foo" Since b7cc53e9 (tag.c: use 'ref-filter' APIs, 2015-07-11), git-tag has started showing tags with ambiguous names (i.e., when both "heads/foo" and "tags/foo" exists) as "tags/foo" instead of just "foo". This is both: - pointless; the output of "git tag" includes only refs/tags, so we know that "foo" means the one in "refs/tags". and - ambiguous; in the original output, we know that the line "foo" means that "refs/tags/foo" exists. In the new output, it is unclear whether we mean "refs/tags/foo" or "refs/tags/tags/foo". The reason this happens is that commit b7cc53e9 switched git-tag to use ref-filter's "%(refname:short)" output formatting, which was adapted from for-each-ref. This more general code does not know that we care only about tags, and uses shorten_unambiguous_ref to get the short-name. We need to tell it that we care only about "refs/tags/", and it should shorten with respect to that value. In theory, the ref-filter code could figure this out by us passing FILTER_REFS_TAGS. But there are two complications there: 1. The handling of refname:short is deep in formatting code that does not even have our ref_filter struct, let alone the arguments to the filter_ref struct. 2. In git v2.7.0, we expose the formatting language to the user. If we follow this path, it will mean that "%(refname:short)" behaves differently for "tag" versus "for-each-ref" (including "for-each-ref refs/tags/"), which can lead to confusion. Instead, let's add a new modifier to the formatting language, "strip", to remove a specific set of prefix components. This fixes "git tag", and lets users invoke the same behavior from their own custom formats (for "tag" or "for-each-ref") while leaving ":short" with its same consistent meaning in all places. We introduce a test in t7004 for "git tag", which fails without this patch. We also add a similar test in t3203 for "git branch", which does not actually fail. But since it is likely that "branch" will eventually use the same formatting code, the test helps defend against future regressions. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-01-26 04:00:05 +01:00
return start;
}
static const char *rstrip_ref_components(const char *refname, int len)
{
long remaining = len;
const char *start = xstrdup(refname);
const char *to_free = start;
if (len < 0) {
int i;
const char *p = refname;
/* Find total no of '/' separated path-components */
for (i = 0; p[i]; p[i] == '/' ? i++ : *p++)
;
/*
* The number of components we need to strip is now
* the total minus the components to be left (Plus one
* because we count the number of '/', but the number
* of components is one more than the no of '/').
*/
remaining = i + len + 1;
}
while (remaining-- > 0) {
char *p = strrchr(start, '/');
if (!p) {
free((char *)to_free);
return xstrdup("");
} else
p[0] = '\0';
}
return start;
}
static const char *show_ref(struct refname_atom *atom, const char *refname)
{
if (atom->option == R_SHORT)
return shorten_unambiguous_ref(refname, warn_ambiguous_refs);
else if (atom->option == R_LSTRIP)
return lstrip_ref_components(refname, atom->lstrip);
else if (atom->option == R_RSTRIP)
return rstrip_ref_components(refname, atom->rstrip);
else
return xstrdup(refname);
}
static void fill_remote_ref_details(struct used_atom *atom, const char *refname,
struct branch *branch, const char **s)
{
int num_ours, num_theirs;
if (atom->u.remote_ref.option == RR_REF)
*s = show_ref(&atom->u.remote_ref.refname, refname);
else if (atom->u.remote_ref.option == RR_TRACK) {
if (stat_tracking_info(branch, &num_ours, &num_theirs,
NULL, atom->u.remote_ref.push,
AHEAD_BEHIND_FULL) < 0) {
*s = xstrdup(msgs.gone);
} else if (!num_ours && !num_theirs)
*s = xstrdup("");
else if (!num_ours)
*s = xstrfmt(msgs.behind, num_theirs);
else if (!num_theirs)
*s = xstrfmt(msgs.ahead, num_ours);
else
*s = xstrfmt(msgs.ahead_behind,
num_ours, num_theirs);
if (!atom->u.remote_ref.nobracket && *s[0]) {
const char *to_free = *s;
*s = xstrfmt("[%s]", *s);
free((void *)to_free);
}
} else if (atom->u.remote_ref.option == RR_TRACKSHORT) {
if (stat_tracking_info(branch, &num_ours, &num_theirs,
NULL, atom->u.remote_ref.push,
AHEAD_BEHIND_FULL) < 0) {
*s = xstrdup("");
return;
}
if (!num_ours && !num_theirs)
*s = xstrdup("=");
else if (!num_ours)
*s = xstrdup("<");
else if (!num_theirs)
*s = xstrdup(">");
else
*s = xstrdup("<>");
for-each-ref: let upstream/push optionally report the remote name There are times when e.g. scripts want to know not only the name of the upstream branch on the remote repository, but also the name of the remote. This patch offers the new suffix :remotename for the upstream and for the push atoms, allowing to show exactly that. Example: $ cat .git/config ... [remote "origin"] url = https://where.do.we.come/from fetch = refs/heads/*:refs/remote/origin/* [remote "hello-world"] url = https://hello.world/git fetch = refs/heads/*:refs/remote/origin/* pushURL = hello.world:git push = refs/heads/*:refs/heads/* [branch "master"] remote = origin pushRemote = hello-world ... $ git for-each-ref \ --format='%(upstream) %(upstream:remotename) %(push:remotename)' \ refs/heads/master refs/remotes/origin/master origin hello-world The implementation chooses *not* to DWIM the push remote if no explicit push remote was configured; The reason is that it is possible to DWIM this by using %(if)%(push:remotename)%(then) %(push:remotename) %(else) %(upstream:remotename) %(end) while it would be impossible to "un-DWIM" the information in case the caller is really only interested in explicit push remotes. While `:remote` would be shorter, it would also be a bit more ambiguous, and it would also shut the door e.g. for `:remoteref` (which would obviously refer to the corresponding ref in the remote repository). Note: the dashless, non-CamelCased form `:remotename` follows the example of the `:trackshort` example. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-05 14:19:09 +02:00
} else if (atom->u.remote_ref.option == RR_REMOTE_NAME) {
int explicit;
const char *remote = atom->u.remote_ref.push ?
pushremote_for_branch(branch, &explicit) :
remote_for_branch(branch, &explicit);
*s = xstrdup(explicit ? remote : "");
} else if (atom->u.remote_ref.option == RR_REMOTE_REF) {
const char *merge;
merge = remote_ref_for_branch(branch, atom->u.remote_ref.push);
*s = xstrdup(merge ? merge : "");
} else
BUG("unhandled RR_* enum");
}
char *get_head_description(void)
{
struct strbuf desc = STRBUF_INIT;
struct wt_status_state state;
memset(&state, 0, sizeof(state));
wt_status_get_state(the_repository, &state, 1);
if (state.rebase_in_progress ||
state.rebase_interactive_in_progress) {
if (state.branch)
branch: sort detached HEAD based on a flag Change the ref-filter sorting of detached HEAD to check the FILTER_REFS_DETACHED_HEAD flag, instead of relying on the ref description filled-in by get_head_description() to start with "(", which in turn we expect to ASCII-sort before any other reference. For context, we'd like the detached line to appear first at the start of "git branch -l", e.g.: $ git branch -l * (HEAD detached at <hash>) master This doesn't change that, but improves on a fix made in 28438e84e04 (ref-filter: sort detached HEAD lines firstly, 2019-06-18) and gives the Chinese translation the ability to use its preferred punctuation marks again. In Chinese the fullwidth versions of punctuation like "()" are typically written as (U+FF08 fullwidth left parenthesis), (U+FF09 fullwidth right parenthesis) instead[1]. This form is used in both po/zh_{CN,TW}.po in most cases where "()" is translated in a string. Aside from that improvement to the Chinese translation, it also just makes for cleaner code that we mark any special cases in the ref_array we're sorting with flags and make the sort function aware of them, instead of piggy-backing on the general-case of strcmp() doing the right thing. As seen in the amended tests this made reverse sorting a bit more consistent. Before this we'd sometimes sort this message in the middle, now it's consistently at the beginning or end, depending on whether we're doing a normal or reverse sort. Having it at the end doesn't make much sense either, but at least it behaves consistently now. A follow-up commit will make this behavior under reverse sorting even better. I'm removing the "TRANSLATORS" comments that were in the old code while I'm at it. Those were added in d4919bb288e (ref-filter: move get_head_description() from branch.c, 2017-01-10). I think it's obvious from context, string and translation memory in typical translation tools that these are the same or similar string. 1. https://en.wikipedia.org/wiki/Chinese_punctuation#Marks_similar_to_European_punctuation Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-07 10:51:52 +01:00
strbuf_addf(&desc, _("(no branch, rebasing %s)"),
state.branch);
else
branch: sort detached HEAD based on a flag Change the ref-filter sorting of detached HEAD to check the FILTER_REFS_DETACHED_HEAD flag, instead of relying on the ref description filled-in by get_head_description() to start with "(", which in turn we expect to ASCII-sort before any other reference. For context, we'd like the detached line to appear first at the start of "git branch -l", e.g.: $ git branch -l * (HEAD detached at <hash>) master This doesn't change that, but improves on a fix made in 28438e84e04 (ref-filter: sort detached HEAD lines firstly, 2019-06-18) and gives the Chinese translation the ability to use its preferred punctuation marks again. In Chinese the fullwidth versions of punctuation like "()" are typically written as (U+FF08 fullwidth left parenthesis), (U+FF09 fullwidth right parenthesis) instead[1]. This form is used in both po/zh_{CN,TW}.po in most cases where "()" is translated in a string. Aside from that improvement to the Chinese translation, it also just makes for cleaner code that we mark any special cases in the ref_array we're sorting with flags and make the sort function aware of them, instead of piggy-backing on the general-case of strcmp() doing the right thing. As seen in the amended tests this made reverse sorting a bit more consistent. Before this we'd sometimes sort this message in the middle, now it's consistently at the beginning or end, depending on whether we're doing a normal or reverse sort. Having it at the end doesn't make much sense either, but at least it behaves consistently now. A follow-up commit will make this behavior under reverse sorting even better. I'm removing the "TRANSLATORS" comments that were in the old code while I'm at it. Those were added in d4919bb288e (ref-filter: move get_head_description() from branch.c, 2017-01-10). I think it's obvious from context, string and translation memory in typical translation tools that these are the same or similar string. 1. https://en.wikipedia.org/wiki/Chinese_punctuation#Marks_similar_to_European_punctuation Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-07 10:51:52 +01:00
strbuf_addf(&desc, _("(no branch, rebasing detached HEAD %s)"),
state.detached_from);
} else if (state.bisect_in_progress)
branch: sort detached HEAD based on a flag Change the ref-filter sorting of detached HEAD to check the FILTER_REFS_DETACHED_HEAD flag, instead of relying on the ref description filled-in by get_head_description() to start with "(", which in turn we expect to ASCII-sort before any other reference. For context, we'd like the detached line to appear first at the start of "git branch -l", e.g.: $ git branch -l * (HEAD detached at <hash>) master This doesn't change that, but improves on a fix made in 28438e84e04 (ref-filter: sort detached HEAD lines firstly, 2019-06-18) and gives the Chinese translation the ability to use its preferred punctuation marks again. In Chinese the fullwidth versions of punctuation like "()" are typically written as (U+FF08 fullwidth left parenthesis), (U+FF09 fullwidth right parenthesis) instead[1]. This form is used in both po/zh_{CN,TW}.po in most cases where "()" is translated in a string. Aside from that improvement to the Chinese translation, it also just makes for cleaner code that we mark any special cases in the ref_array we're sorting with flags and make the sort function aware of them, instead of piggy-backing on the general-case of strcmp() doing the right thing. As seen in the amended tests this made reverse sorting a bit more consistent. Before this we'd sometimes sort this message in the middle, now it's consistently at the beginning or end, depending on whether we're doing a normal or reverse sort. Having it at the end doesn't make much sense either, but at least it behaves consistently now. A follow-up commit will make this behavior under reverse sorting even better. I'm removing the "TRANSLATORS" comments that were in the old code while I'm at it. Those were added in d4919bb288e (ref-filter: move get_head_description() from branch.c, 2017-01-10). I think it's obvious from context, string and translation memory in typical translation tools that these are the same or similar string. 1. https://en.wikipedia.org/wiki/Chinese_punctuation#Marks_similar_to_European_punctuation Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-07 10:51:52 +01:00
strbuf_addf(&desc, _("(no branch, bisect started on %s)"),
state.branch);
else if (state.detached_from) {
if (state.detached_at)
branch: sort detached HEAD based on a flag Change the ref-filter sorting of detached HEAD to check the FILTER_REFS_DETACHED_HEAD flag, instead of relying on the ref description filled-in by get_head_description() to start with "(", which in turn we expect to ASCII-sort before any other reference. For context, we'd like the detached line to appear first at the start of "git branch -l", e.g.: $ git branch -l * (HEAD detached at <hash>) master This doesn't change that, but improves on a fix made in 28438e84e04 (ref-filter: sort detached HEAD lines firstly, 2019-06-18) and gives the Chinese translation the ability to use its preferred punctuation marks again. In Chinese the fullwidth versions of punctuation like "()" are typically written as (U+FF08 fullwidth left parenthesis), (U+FF09 fullwidth right parenthesis) instead[1]. This form is used in both po/zh_{CN,TW}.po in most cases where "()" is translated in a string. Aside from that improvement to the Chinese translation, it also just makes for cleaner code that we mark any special cases in the ref_array we're sorting with flags and make the sort function aware of them, instead of piggy-backing on the general-case of strcmp() doing the right thing. As seen in the amended tests this made reverse sorting a bit more consistent. Before this we'd sometimes sort this message in the middle, now it's consistently at the beginning or end, depending on whether we're doing a normal or reverse sort. Having it at the end doesn't make much sense either, but at least it behaves consistently now. A follow-up commit will make this behavior under reverse sorting even better. I'm removing the "TRANSLATORS" comments that were in the old code while I'm at it. Those were added in d4919bb288e (ref-filter: move get_head_description() from branch.c, 2017-01-10). I think it's obvious from context, string and translation memory in typical translation tools that these are the same or similar string. 1. https://en.wikipedia.org/wiki/Chinese_punctuation#Marks_similar_to_European_punctuation Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-07 10:51:52 +01:00
strbuf_addf(&desc, _("(HEAD detached at %s)"),
state.detached_from);
else
branch: sort detached HEAD based on a flag Change the ref-filter sorting of detached HEAD to check the FILTER_REFS_DETACHED_HEAD flag, instead of relying on the ref description filled-in by get_head_description() to start with "(", which in turn we expect to ASCII-sort before any other reference. For context, we'd like the detached line to appear first at the start of "git branch -l", e.g.: $ git branch -l * (HEAD detached at <hash>) master This doesn't change that, but improves on a fix made in 28438e84e04 (ref-filter: sort detached HEAD lines firstly, 2019-06-18) and gives the Chinese translation the ability to use its preferred punctuation marks again. In Chinese the fullwidth versions of punctuation like "()" are typically written as (U+FF08 fullwidth left parenthesis), (U+FF09 fullwidth right parenthesis) instead[1]. This form is used in both po/zh_{CN,TW}.po in most cases where "()" is translated in a string. Aside from that improvement to the Chinese translation, it also just makes for cleaner code that we mark any special cases in the ref_array we're sorting with flags and make the sort function aware of them, instead of piggy-backing on the general-case of strcmp() doing the right thing. As seen in the amended tests this made reverse sorting a bit more consistent. Before this we'd sometimes sort this message in the middle, now it's consistently at the beginning or end, depending on whether we're doing a normal or reverse sort. Having it at the end doesn't make much sense either, but at least it behaves consistently now. A follow-up commit will make this behavior under reverse sorting even better. I'm removing the "TRANSLATORS" comments that were in the old code while I'm at it. Those were added in d4919bb288e (ref-filter: move get_head_description() from branch.c, 2017-01-10). I think it's obvious from context, string and translation memory in typical translation tools that these are the same or similar string. 1. https://en.wikipedia.org/wiki/Chinese_punctuation#Marks_similar_to_European_punctuation Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-07 10:51:52 +01:00
strbuf_addf(&desc, _("(HEAD detached from %s)"),
state.detached_from);
} else
strbuf_addstr(&desc, _("(no branch)"));
return strbuf_detach(&desc, NULL);
}
static const char *get_symref(struct used_atom *atom, struct ref_array_item *ref)
{
if (!ref->symref)
return xstrdup("");
else
return show_ref(&atom->u.refname, ref->symref);
}
static const char *get_refname(struct used_atom *atom, struct ref_array_item *ref)
{
if (ref->kind & FILTER_REFS_DETACHED_HEAD)
return get_head_description();
return show_ref(&atom->u.refname, ref->refname);
}
static int get_object(struct ref_array_item *ref, int deref, struct object **obj,
struct expand_data *oi, struct strbuf *err)
{
/* parse_object_buffer() will set eaten to 0 if free() will be needed */
int eaten = 1;
if (oi->info.contentp) {
/* We need to know that to use parse_object_buffer properly */
oi->info.sizep = &oi->size;
oi->info.typep = &oi->type;
}
if (oid_object_info_extended(the_repository, &oi->oid, &oi->info,
OBJECT_INFO_LOOKUP_REPLACE))
return strbuf_addf_ret(err, -1, _("missing object %s for %s"),
oid_to_hex(&oi->oid), ref->refname);
if (oi->info.disk_sizep && oi->disk_size < 0)
BUG("Object size is less than zero.");
if (oi->info.contentp) {
*obj = parse_object_buffer(the_repository, &oi->oid, oi->type, oi->size, oi->content, &eaten);
if (!*obj) {
if (!eaten)
free(oi->content);
return strbuf_addf_ret(err, -1, _("parse_object_buffer failed on %s for %s"),
oid_to_hex(&oi->oid), ref->refname);
}
grab_values(ref->value, deref, *obj, oi);
}
grab_common_values(ref->value, deref, oi);
if (!eaten)
free(oi->content);
return 0;
}
static void populate_worktree_map(struct hashmap *map, struct worktree **worktrees)
{
int i;
for (i = 0; worktrees[i]; i++) {
if (worktrees[i]->head_ref) {
struct ref_to_worktree_entry *entry;
entry = xmalloc(sizeof(*entry));
entry->wt = worktrees[i];
hashmap_entry_init(&entry->ent,
strhash(worktrees[i]->head_ref));
hashmap_add(map, &entry->ent);
}
}
}
static void lazy_init_worktree_map(void)
{
if (ref_to_worktree_map.worktrees)
return;
ref_to_worktree_map.worktrees = get_worktrees();
hashmap_init(&(ref_to_worktree_map.map), ref_to_worktree_map_cmpfnc, NULL, 0);
populate_worktree_map(&(ref_to_worktree_map.map), ref_to_worktree_map.worktrees);
}
static char *get_worktree_path(const struct used_atom *atom, const struct ref_array_item *ref)
{
struct hashmap_entry entry, *e;
struct ref_to_worktree_entry *lookup_result;
lazy_init_worktree_map();
hashmap_entry_init(&entry, strhash(ref->refname));
e = hashmap_get(&(ref_to_worktree_map.map), &entry, ref->refname);
if (!e)
return xstrdup("");
lookup_result = container_of(e, struct ref_to_worktree_entry, ent);
return xstrdup(lookup_result->wt->path);
}
/*
* Parse the object referred by ref, and grab needed value.
*/
static int populate_value(struct ref_array_item *ref, struct strbuf *err)
{
struct object *obj;
int i;
struct object_info empty = OBJECT_INFO_INIT;
CALLOC_ARRAY(ref->value, used_atom_cnt);
if (need_symref && (ref->flag & REF_ISSYMREF) && !ref->symref) {
ref->symref = resolve_refdup(ref->refname, RESOLVE_REF_READING,
NULL, NULL);
if (!ref->symref)
ref->symref = xstrdup("");
}
/* Fill in specials first */
for (i = 0; i < used_atom_cnt; i++) {
struct used_atom *atom = &used_atom[i];
enum atom_type atom_type = atom->atom_type;
const char *name = used_atom[i].name;
struct atom_value *v = &ref->value[i];
int deref = 0;
const char *refname;
struct branch *branch = NULL;
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
v->s_size = ATOM_SIZE_UNSPECIFIED;
v->handler = append_atom;
v->atom = atom;
if (*name == '*') {
deref = 1;
name++;
}
if (atom_type == ATOM_REFNAME)
refname = get_refname(atom, ref);
else if (atom_type == ATOM_WORKTREEPATH) {
if (ref->kind == FILTER_REFS_BRANCHES)
v->s = get_worktree_path(atom, ref);
else
v->s = xstrdup("");
continue;
}
else if (atom_type == ATOM_SYMREF)
refname = get_symref(atom, ref);
else if (atom_type == ATOM_UPSTREAM) {
const char *branch_name;
/* only local branches may have an upstream */
if (!skip_prefix(ref->refname, "refs/heads/",
&branch_name)) {
v->s = xstrdup("");
continue;
}
branch = branch_get(branch_name);
refname = branch_get_upstream(branch, NULL);
if (refname)
fill_remote_ref_details(atom, refname, branch, &v->s);
else
v->s = xstrdup("");
continue;
} else if (atom_type == ATOM_PUSH && atom->u.remote_ref.push) {
const char *branch_name;
v->s = xstrdup("");
if (!skip_prefix(ref->refname, "refs/heads/",
&branch_name))
continue;
branch = branch_get(branch_name);
for-each-ref: let upstream/push optionally report the remote name There are times when e.g. scripts want to know not only the name of the upstream branch on the remote repository, but also the name of the remote. This patch offers the new suffix :remotename for the upstream and for the push atoms, allowing to show exactly that. Example: $ cat .git/config ... [remote "origin"] url = https://where.do.we.come/from fetch = refs/heads/*:refs/remote/origin/* [remote "hello-world"] url = https://hello.world/git fetch = refs/heads/*:refs/remote/origin/* pushURL = hello.world:git push = refs/heads/*:refs/heads/* [branch "master"] remote = origin pushRemote = hello-world ... $ git for-each-ref \ --format='%(upstream) %(upstream:remotename) %(push:remotename)' \ refs/heads/master refs/remotes/origin/master origin hello-world The implementation chooses *not* to DWIM the push remote if no explicit push remote was configured; The reason is that it is possible to DWIM this by using %(if)%(push:remotename)%(then) %(push:remotename) %(else) %(upstream:remotename) %(end) while it would be impossible to "un-DWIM" the information in case the caller is really only interested in explicit push remotes. While `:remote` would be shorter, it would also be a bit more ambiguous, and it would also shut the door e.g. for `:remoteref` (which would obviously refer to the corresponding ref in the remote repository). Note: the dashless, non-CamelCased form `:remotename` follows the example of the `:trackshort` example. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-05 14:19:09 +02:00
if (atom->u.remote_ref.push_remote)
refname = NULL;
else {
refname = branch_get_push(branch, NULL);
if (!refname)
continue;
}
/* We will definitely re-init v->s on the next line. */
free((char *)v->s);
fill_remote_ref_details(atom, refname, branch, &v->s);
continue;
} else if (atom_type == ATOM_COLOR) {
v->s = xstrdup(atom->u.color);
continue;
} else if (atom_type == ATOM_FLAG) {
char buf[256], *cp = buf;
if (ref->flag & REF_ISSYMREF)
cp = copy_advance(cp, ",symref");
if (ref->flag & REF_ISPACKED)
cp = copy_advance(cp, ",packed");
if (cp == buf)
v->s = xstrdup("");
else {
*cp = '\0';
v->s = xstrdup(buf + 1);
}
continue;
} else if (!deref && atom_type == ATOM_OBJECTNAME &&
grab_oid(name, "objectname", &ref->objectname, v, atom)) {
continue;
} else if (atom_type == ATOM_HEAD) {
if (atom->u.head && !strcmp(ref->refname, atom->u.head))
v->s = xstrdup("*");
else
v->s = xstrdup(" ");
continue;
} else if (atom_type == ATOM_ALIGN) {
2015-09-11 17:03:07 +02:00
v->handler = align_atom_handler;
v->s = xstrdup("");
2015-09-11 17:03:07 +02:00
continue;
} else if (atom_type == ATOM_END) {
2015-09-11 17:03:07 +02:00
v->handler = end_atom_handler;
v->s = xstrdup("");
2015-09-11 17:03:07 +02:00
continue;
} else if (atom_type == ATOM_IF) {
const char *s;
if (skip_prefix(name, "if:", &s))
v->s = xstrdup(s);
else
v->s = xstrdup("");
v->handler = if_atom_handler;
continue;
} else if (atom_type == ATOM_THEN) {
v->handler = then_atom_handler;
v->s = xstrdup("");
continue;
} else if (atom_type == ATOM_ELSE) {
v->handler = else_atom_handler;
v->s = xstrdup("");
continue;
} else if (atom_type == ATOM_REST) {
if (ref->rest)
v->s = xstrdup(ref->rest);
else
v->s = xstrdup("");
continue;
} else
continue;
if (!deref)
v->s = xstrdup(refname);
else
v->s = xstrfmt("%s^{}", refname);
free((char *)refname);
}
for (i = 0; i < used_atom_cnt; i++) {
struct atom_value *v = &ref->value[i];
if (v->s == NULL && used_atom[i].source == SOURCE_NONE)
return strbuf_addf_ret(err, -1, _("missing object %s for %s"),
oid_to_hex(&ref->objectname), ref->refname);
}
if (need_tagged)
oi.info.contentp = &oi.content;
if (!memcmp(&oi.info, &empty, sizeof(empty)) &&
!memcmp(&oi_deref.info, &empty, sizeof(empty)))
return 0;
oi.oid = ref->objectname;
if (get_object(ref, 0, &obj, &oi, err))
return -1;
/*
* If there is no atom that wants to know about tagged
* object, we are done.
*/
if (!need_tagged || (obj->type != OBJ_TAG))
return 0;
/*
* If it is a tag object, see if we use a value that derefs
* the object, and if we do grab the object it refers to.
*/
oi_deref.oid = *get_tagged_oid((struct tag *)obj);
/*
* NEEDSWORK: This derefs tag only once, which
* is good to deal with chains of trust, but
* is not consistent with what deref_tag() does
* which peels the onion to the core.
*/
return get_object(ref, 1, &obj, &oi_deref, err);
}
/*
* Given a ref, return the value for the atom. This lazily gets value
* out of the object by calling populate value.
*/
static int get_ref_atom_value(struct ref_array_item *ref, int atom,
struct atom_value **v, struct strbuf *err)
{
if (!ref->value) {
if (populate_value(ref, err))
return -1;
fill_missing_values(ref->value);
}
*v = &ref->value[atom];
return 0;
}
/*
* Return 1 if the refname matches one of the patterns, otherwise 0.
* A pattern can be a literal prefix (e.g. a refname "refs/heads/master"
* matches a pattern "refs/heads/mas") or a wildcard (e.g. the same ref
* matches "refs/heads/mas*", too).
*/
static int match_pattern(const struct ref_filter *filter, const char *refname)
{
const char **patterns = filter->name_patterns;
unsigned flags = 0;
if (filter->ignore_case)
flags |= WM_CASEFOLD;
/*
* When no '--format' option is given we need to skip the prefix
* for matching refs of tags and branches.
*/
(void)(skip_prefix(refname, "refs/tags/", &refname) ||
skip_prefix(refname, "refs/heads/", &refname) ||
skip_prefix(refname, "refs/remotes/", &refname) ||
skip_prefix(refname, "refs/", &refname));
for (; *patterns; patterns++) {
if (!wildmatch(*patterns, refname, flags))
return 1;
}
return 0;
}
/*
* Return 1 if the refname matches one of the patterns, otherwise 0.
* A pattern can be path prefix (e.g. a refname "refs/heads/master"
* matches a pattern "refs/heads/" but not "refs/heads/m") or a
* wildcard (e.g. the same ref matches "refs/heads/m*", too).
*/
static int match_name_as_path(const struct ref_filter *filter, const char *refname)
{
const char **pattern = filter->name_patterns;
int namelen = strlen(refname);
unsigned flags = WM_PATHNAME;
if (filter->ignore_case)
flags |= WM_CASEFOLD;
for (; *pattern; pattern++) {
const char *p = *pattern;
int plen = strlen(p);
if ((plen <= namelen) &&
!strncmp(refname, p, plen) &&
(refname[plen] == '\0' ||
refname[plen] == '/' ||
p[plen-1] == '/'))
return 1;
if (!wildmatch(p, refname, flags))
return 1;
}
return 0;
}
/* 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)
return 1; /* No pattern always matches */
if (filter->match_as_path)
return match_name_as_path(filter, refname);
return match_pattern(filter, refname);
}
/*
* This is the same as for_each_fullref_in(), but it tries to iterate
* only over the patterns we'll care about. Note that it _doesn't_ do a full
* pattern match, so the callback still has to match each ref individually.
*/
static int for_each_fullref_in_pattern(struct ref_filter *filter,
each_ref_fn cb,
void *cb_data)
{
if (!filter->match_as_path) {
/*
* in this case, the patterns are applied after
* prefixes like "refs/heads/" etc. are stripped off,
* so we have to look at everything:
*/
return for_each_fullref_in("", cb, cb_data);
}
if (filter->ignore_case) {
/*
* we can't handle case-insensitive comparisons,
* so just return everything and let the caller
* sort it out.
*/
return for_each_fullref_in("", cb, cb_data);
}
if (!filter->name_patterns[0]) {
/* no patterns; we have to look at everything */
return for_each_fullref_in("", cb, cb_data);
}
return for_each_fullref_in_prefixes(NULL, filter->name_patterns,
cb, cb_data);
}
/*
* Given a ref (oid, refname), check if the ref belongs to the array
* of oids. If the given ref is a tag, check if the given tag points
* at one of the oids in the given oid array.
* NEEDSWORK:
* 1. Only a single level of indirection is obtained, we might want to
* change this to account for multiple levels (e.g. annotated tags
* pointing to annotated tags pointing to a commit.)
* 2. As the refs are cached we might know what refname peels to without
* the need to parse the object via parse_object(). peel_ref() might be a
* more efficient alternative to obtain the pointee.
*/
static const struct object_id *match_points_at(struct oid_array *points_at,
const struct object_id *oid,
const char *refname)
{
const struct object_id *tagged_oid = NULL;
struct object *obj;
if (oid_array_lookup(points_at, oid) >= 0)
return oid;
obj = parse_object(the_repository, oid);
if (!obj)
die(_("malformed object at '%s'"), refname);
if (obj->type == OBJ_TAG)
tagged_oid = get_tagged_oid((struct tag *)obj);
if (tagged_oid && oid_array_lookup(points_at, tagged_oid) >= 0)
return tagged_oid;
return NULL;
}
/*
* Allocate space for a new ref_array_item and copy the name and oid to it.
*
* Callers can then fill in other struct members at their leisure.
*/
static struct ref_array_item *new_ref_array_item(const char *refname,
const struct object_id *oid)
{
struct ref_array_item *ref;
FLEX_ALLOC_STR(ref, refname, refname);
oidcpy(&ref->objectname, oid);
ref->rest = NULL;
return ref;
}
struct ref_array_item *ref_array_push(struct ref_array *array,
const char *refname,
const struct object_id *oid)
{
struct ref_array_item *ref = new_ref_array_item(refname, oid);
ALLOC_GROW(array->items, array->nr + 1, array->alloc);
array->items[array->nr++] = ref;
return ref;
}
static int ref_kind_from_refname(const char *refname)
{
unsigned int i;
static struct {
const char *prefix;
unsigned int kind;
} ref_kind[] = {
{ "refs/heads/" , FILTER_REFS_BRANCHES },
{ "refs/remotes/" , FILTER_REFS_REMOTES },
{ "refs/tags/", FILTER_REFS_TAGS}
};
if (!strcmp(refname, "HEAD"))
return FILTER_REFS_DETACHED_HEAD;
for (i = 0; i < ARRAY_SIZE(ref_kind); i++) {
if (starts_with(refname, ref_kind[i].prefix))
return ref_kind[i].kind;
}
return FILTER_REFS_OTHERS;
}
static int filter_ref_kind(struct ref_filter *filter, const char *refname)
{
if (filter->kind == FILTER_REFS_BRANCHES ||
filter->kind == FILTER_REFS_REMOTES ||
filter->kind == FILTER_REFS_TAGS)
return filter->kind;
return ref_kind_from_refname(refname);
}
struct ref_filter_cbdata {
struct ref_array *array;
struct ref_filter *filter;
struct contains_cache contains_cache;
struct contains_cache no_contains_cache;
};
/*
* A call-back given to for_each_ref(). Filter refs and keep them for
* later object processing.
*/
static int ref_filter_handler(const char *refname, const struct object_id *oid, int flag, void *cb_data)
{
struct ref_filter_cbdata *ref_cbdata = cb_data;
struct ref_filter *filter = ref_cbdata->filter;
struct ref_array_item *ref;
struct commit *commit = NULL;
unsigned int kind;
if (flag & REF_BAD_NAME) {
warning(_("ignoring ref with broken name %s"), refname);
return 0;
}
if (flag & REF_ISBROKEN) {
warning(_("ignoring broken ref %s"), refname);
return 0;
}
/* Obtain the current ref kind from filter_ref_kind() and ignore unwanted refs. */
kind = filter_ref_kind(filter, refname);
if (!(kind & filter->kind))
return 0;
if (!filter_pattern_match(filter, refname))
return 0;
if (filter->points_at.nr && !match_points_at(&filter->points_at, oid, refname))
return 0;
/*
* A merge filter is applied on refs pointing to commits. Hence
* obtain the commit using the 'oid' available and discard all
* non-commits early. The actual filtering is done later.
*/
if (filter->reachable_from || filter->unreachable_from ||
filter->with_commit || filter->no_commit || filter->verbose) {
commit = lookup_commit_reference_gently(the_repository, oid, 1);
if (!commit)
return 0;
ref-filter: add --no-contains option to tag/branch/for-each-ref Change the tag, branch & for-each-ref commands to have a --no-contains option in addition to their longstanding --contains options. This allows for finding the last-good rollout tag given a known-bad <commit>. Given a hypothetically bad commit cf5c7253e0, the git version to revert to can be found with this hacky two-liner: (git tag -l 'v[0-9]*'; git tag -l --contains cf5c7253e0 'v[0-9]*') | sort | uniq -c | grep -E '^ *1 ' | awk '{print $2}' | tail -n 10 With this new --no-contains option the same can be achieved with: git tag -l --no-contains cf5c7253e0 'v[0-9]*' | sort | tail -n 10 As the filtering machinery is shared between the tag, branch & for-each-ref commands, implement this for those commands too. A practical use for this with "branch" is e.g. finding branches which were branched off between v2.8.0 and v2.10.0: git branch --contains v2.8.0 --no-contains v2.10.0 The "describe" command also has a --contains option, but its semantics are unrelated to what tag/branch/for-each-ref use --contains for. A --no-contains option for "describe" wouldn't make any sense, other than being exactly equivalent to not supplying --contains at all, which would be confusing at best. Add a --without option to "tag" as an alias for --no-contains, for consistency with --with and --contains. The --with option is undocumented, and possibly the only user of it is Junio (<xmqqefy71iej.fsf@gitster.mtv.corp.google.com>). But it's trivial to support, so let's do that. The additions to the the test suite are inverse copies of the corresponding --contains tests. With this change --no-contains for tag, branch & for-each-ref is just as well tested as the existing --contains option. In addition to those tests, add a test for "tag" which asserts that --no-contains won't find tree/blob tags, which is slightly unintuitive, but consistent with how --contains works & is documented. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-24 19:40:57 +01:00
/* We perform the filtering for the '--contains' option... */
if (filter->with_commit &&
ref-filter: add --no-contains option to tag/branch/for-each-ref Change the tag, branch & for-each-ref commands to have a --no-contains option in addition to their longstanding --contains options. This allows for finding the last-good rollout tag given a known-bad <commit>. Given a hypothetically bad commit cf5c7253e0, the git version to revert to can be found with this hacky two-liner: (git tag -l 'v[0-9]*'; git tag -l --contains cf5c7253e0 'v[0-9]*') | sort | uniq -c | grep -E '^ *1 ' | awk '{print $2}' | tail -n 10 With this new --no-contains option the same can be achieved with: git tag -l --no-contains cf5c7253e0 'v[0-9]*' | sort | tail -n 10 As the filtering machinery is shared between the tag, branch & for-each-ref commands, implement this for those commands too. A practical use for this with "branch" is e.g. finding branches which were branched off between v2.8.0 and v2.10.0: git branch --contains v2.8.0 --no-contains v2.10.0 The "describe" command also has a --contains option, but its semantics are unrelated to what tag/branch/for-each-ref use --contains for. A --no-contains option for "describe" wouldn't make any sense, other than being exactly equivalent to not supplying --contains at all, which would be confusing at best. Add a --without option to "tag" as an alias for --no-contains, for consistency with --with and --contains. The --with option is undocumented, and possibly the only user of it is Junio (<xmqqefy71iej.fsf@gitster.mtv.corp.google.com>). But it's trivial to support, so let's do that. The additions to the the test suite are inverse copies of the corresponding --contains tests. With this change --no-contains for tag, branch & for-each-ref is just as well tested as the existing --contains option. In addition to those tests, add a test for "tag" which asserts that --no-contains won't find tree/blob tags, which is slightly unintuitive, but consistent with how --contains works & is documented. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-24 19:40:57 +01:00
!commit_contains(filter, commit, filter->with_commit, &ref_cbdata->contains_cache))
return 0;
/* ...or for the `--no-contains' option */
if (filter->no_commit &&
commit_contains(filter, commit, filter->no_commit, &ref_cbdata->no_contains_cache))
return 0;
}
/*
* We do not open the object yet; sort may only need refname
* to do its job and the resulting list may yet to be pruned
* by maxcount logic.
*/
ref = ref_array_push(ref_cbdata->array, refname, oid);
ref->commit = commit;
ref->flag = flag;
ref->kind = kind;
return 0;
}
/* Free memory allocated for a ref_array_item */
static void free_array_item(struct ref_array_item *item)
{
free((char *)item->symref);
if (item->value) {
int i;
for (i = 0; i < used_atom_cnt; i++)
free((char *)item->value[i].s);
free(item->value);
}
free(item);
}
/* Free all memory allocated for ref_array */
void ref_array_clear(struct ref_array *array)
{
int i;
for (i = 0; i < array->nr; i++)
free_array_item(array->items[i]);
FREE_AND_NULL(array->items);
array->nr = array->alloc = 0;
for (i = 0; i < used_atom_cnt; i++) {
struct used_atom *atom = &used_atom[i];
if (atom->atom_type == ATOM_HEAD)
free(atom->u.head);
free((char *)atom->name);
}
FREE_AND_NULL(used_atom);
used_atom_cnt = 0;
if (ref_to_worktree_map.worktrees) {
hashmap_clear_and_free(&(ref_to_worktree_map.map),
struct ref_to_worktree_entry, ent);
free_worktrees(ref_to_worktree_map.worktrees);
ref_to_worktree_map.worktrees = NULL;
}
}
#define EXCLUDE_REACHED 0
#define INCLUDE_REACHED 1
static void reach_filter(struct ref_array *array,
struct commit_list *check_reachable,
int include_reached)
{
struct rev_info revs;
int i, old_nr;
struct commit **to_clear;
struct commit_list *cr;
if (!check_reachable)
return;
CALLOC_ARRAY(to_clear, array->nr);
repo_init_revisions(the_repository, &revs, NULL);
for (i = 0; i < array->nr; i++) {
struct ref_array_item *item = array->items[i];
add_pending_object(&revs, &item->commit->object, item->refname);
to_clear[i] = item->commit;
}
for (cr = check_reachable; cr; cr = cr->next) {
struct commit *merge_commit = cr->item;
merge_commit->object.flags |= UNINTERESTING;
add_pending_object(&revs, &merge_commit->object, "");
}
revs.limited = 1;
if (prepare_revision_walk(&revs))
die(_("revision walk setup failed"));
old_nr = array->nr;
array->nr = 0;
for (i = 0; i < old_nr; i++) {
struct ref_array_item *item = array->items[i];
struct commit *commit = item->commit;
int is_merged = !!(commit->object.flags & UNINTERESTING);
if (is_merged == include_reached)
array->items[array->nr++] = array->items[i];
else
free_array_item(item);
}
clear_commit_marks_many(old_nr, to_clear, ALL_REV_FLAGS);
while (check_reachable) {
struct commit *merge_commit = pop_commit(&check_reachable);
clear_commit_marks(merge_commit, ALL_REV_FLAGS);
}
release_revisions(&revs);
free(to_clear);
}
/*
* 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)
{
struct ref_filter_cbdata ref_cbdata;
ref-filter: disable save_commit_buffer while traversing Various ref-filter options like "--contains" or "--merged" may cause us to traverse large segments of the history graph. It's counter-productive to have save_commit_buffer turned on, as that will instruct the commit code to cache in-memory the object contents for each commit we traverse. This increases the amount of heap memory used while providing little or no benefit, since we're not actually planning to display those commits (which is the usual reason that tools like git-log want to keep them around). We can easily disable this feature while ref-filter is running. This lowers peak heap (as measured by massif) for running: git tag --contains 1da177e4c3 in linux.git from ~100MB to ~20MB. It also seems to improve runtime by 4-5% (600ms vs 630ms). A few points to note: - it should be safe to temporarily disable save_commit_buffer like this. The saved buffers are accessed through get_commit_buffer(), which treats the saved ones like a cache, and loads on-demand from the object database on a cache miss. So any code that was using this would not be wrong, it might just incur an extra object lookup for some objects. But... - I don't think any ref-filter related code is using the cache. While it's true that an option like "--format=%(*contents:subject)" or "--sort=*authordate" will need to look at the commit contents, ref-filter doesn't use get_commit_buffer() to do so! It always reads the objects directly via read_object_file(), though it does avoid re-reading objects if the format can be satisfied without them. Timing "git tag --format=%(*authordate)" shows that we're the same before and after, as expected. - Note that all of this assumes you don't have a commit-graph file. if you do, then the heap usage is even lower, and the runtime is 10x faster. So in that sense this is not urgent, as there's a much better solution. But since it's such an obvious and easy win for fallback cases (including commits which aren't yet in the graph file), there's no reason not to. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-07-11 16:48:06 +02:00
int save_commit_buffer_orig;
int ret = 0;
ref_cbdata.array = array;
ref_cbdata.filter = filter;
filter->kind = type & FILTER_REFS_KIND_MASK;
ref-filter: disable save_commit_buffer while traversing Various ref-filter options like "--contains" or "--merged" may cause us to traverse large segments of the history graph. It's counter-productive to have save_commit_buffer turned on, as that will instruct the commit code to cache in-memory the object contents for each commit we traverse. This increases the amount of heap memory used while providing little or no benefit, since we're not actually planning to display those commits (which is the usual reason that tools like git-log want to keep them around). We can easily disable this feature while ref-filter is running. This lowers peak heap (as measured by massif) for running: git tag --contains 1da177e4c3 in linux.git from ~100MB to ~20MB. It also seems to improve runtime by 4-5% (600ms vs 630ms). A few points to note: - it should be safe to temporarily disable save_commit_buffer like this. The saved buffers are accessed through get_commit_buffer(), which treats the saved ones like a cache, and loads on-demand from the object database on a cache miss. So any code that was using this would not be wrong, it might just incur an extra object lookup for some objects. But... - I don't think any ref-filter related code is using the cache. While it's true that an option like "--format=%(*contents:subject)" or "--sort=*authordate" will need to look at the commit contents, ref-filter doesn't use get_commit_buffer() to do so! It always reads the objects directly via read_object_file(), though it does avoid re-reading objects if the format can be satisfied without them. Timing "git tag --format=%(*authordate)" shows that we're the same before and after, as expected. - Note that all of this assumes you don't have a commit-graph file. if you do, then the heap usage is even lower, and the runtime is 10x faster. So in that sense this is not urgent, as there's a much better solution. But since it's such an obvious and easy win for fallback cases (including commits which aren't yet in the graph file), there's no reason not to. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-07-11 16:48:06 +02:00
save_commit_buffer_orig = save_commit_buffer;
save_commit_buffer = 0;
init_contains_cache(&ref_cbdata.contains_cache);
ref-filter: add --no-contains option to tag/branch/for-each-ref Change the tag, branch & for-each-ref commands to have a --no-contains option in addition to their longstanding --contains options. This allows for finding the last-good rollout tag given a known-bad <commit>. Given a hypothetically bad commit cf5c7253e0, the git version to revert to can be found with this hacky two-liner: (git tag -l 'v[0-9]*'; git tag -l --contains cf5c7253e0 'v[0-9]*') | sort | uniq -c | grep -E '^ *1 ' | awk '{print $2}' | tail -n 10 With this new --no-contains option the same can be achieved with: git tag -l --no-contains cf5c7253e0 'v[0-9]*' | sort | tail -n 10 As the filtering machinery is shared between the tag, branch & for-each-ref commands, implement this for those commands too. A practical use for this with "branch" is e.g. finding branches which were branched off between v2.8.0 and v2.10.0: git branch --contains v2.8.0 --no-contains v2.10.0 The "describe" command also has a --contains option, but its semantics are unrelated to what tag/branch/for-each-ref use --contains for. A --no-contains option for "describe" wouldn't make any sense, other than being exactly equivalent to not supplying --contains at all, which would be confusing at best. Add a --without option to "tag" as an alias for --no-contains, for consistency with --with and --contains. The --with option is undocumented, and possibly the only user of it is Junio (<xmqqefy71iej.fsf@gitster.mtv.corp.google.com>). But it's trivial to support, so let's do that. The additions to the the test suite are inverse copies of the corresponding --contains tests. With this change --no-contains for tag, branch & for-each-ref is just as well tested as the existing --contains option. In addition to those tests, add a test for "tag" which asserts that --no-contains won't find tree/blob tags, which is slightly unintuitive, but consistent with how --contains works & is documented. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-24 19:40:57 +01:00
init_contains_cache(&ref_cbdata.no_contains_cache);
/* Simple per-ref filtering */
if (!filter->kind)
die("filter_refs: invalid type");
else {
/*
* For common cases where we need only branches or remotes or tags,
* we only iterate through those refs. If a mix of refs is needed,
* we iterate over all refs and filter out required refs with the help
* of filter_ref_kind().
*/
if (filter->kind == FILTER_REFS_BRANCHES)
ret = for_each_fullref_in("refs/heads/", ref_filter_handler, &ref_cbdata);
else if (filter->kind == FILTER_REFS_REMOTES)
ret = for_each_fullref_in("refs/remotes/", ref_filter_handler, &ref_cbdata);
else if (filter->kind == FILTER_REFS_TAGS)
ret = for_each_fullref_in("refs/tags/", ref_filter_handler, &ref_cbdata);
else if (filter->kind & FILTER_REFS_ALL)
ret = for_each_fullref_in_pattern(filter, ref_filter_handler, &ref_cbdata);
if (!ret && (filter->kind & FILTER_REFS_DETACHED_HEAD))
head_ref(ref_filter_handler, &ref_cbdata);
}
clear_contains_cache(&ref_cbdata.contains_cache);
ref-filter: add --no-contains option to tag/branch/for-each-ref Change the tag, branch & for-each-ref commands to have a --no-contains option in addition to their longstanding --contains options. This allows for finding the last-good rollout tag given a known-bad <commit>. Given a hypothetically bad commit cf5c7253e0, the git version to revert to can be found with this hacky two-liner: (git tag -l 'v[0-9]*'; git tag -l --contains cf5c7253e0 'v[0-9]*') | sort | uniq -c | grep -E '^ *1 ' | awk '{print $2}' | tail -n 10 With this new --no-contains option the same can be achieved with: git tag -l --no-contains cf5c7253e0 'v[0-9]*' | sort | tail -n 10 As the filtering machinery is shared between the tag, branch & for-each-ref commands, implement this for those commands too. A practical use for this with "branch" is e.g. finding branches which were branched off between v2.8.0 and v2.10.0: git branch --contains v2.8.0 --no-contains v2.10.0 The "describe" command also has a --contains option, but its semantics are unrelated to what tag/branch/for-each-ref use --contains for. A --no-contains option for "describe" wouldn't make any sense, other than being exactly equivalent to not supplying --contains at all, which would be confusing at best. Add a --without option to "tag" as an alias for --no-contains, for consistency with --with and --contains. The --with option is undocumented, and possibly the only user of it is Junio (<xmqqefy71iej.fsf@gitster.mtv.corp.google.com>). But it's trivial to support, so let's do that. The additions to the the test suite are inverse copies of the corresponding --contains tests. With this change --no-contains for tag, branch & for-each-ref is just as well tested as the existing --contains option. In addition to those tests, add a test for "tag" which asserts that --no-contains won't find tree/blob tags, which is slightly unintuitive, but consistent with how --contains works & is documented. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-24 19:40:57 +01:00
clear_contains_cache(&ref_cbdata.no_contains_cache);
/* Filters that need revision walking */
reach_filter(array, filter->reachable_from, INCLUDE_REACHED);
reach_filter(array, filter->unreachable_from, EXCLUDE_REACHED);
ref-filter: disable save_commit_buffer while traversing Various ref-filter options like "--contains" or "--merged" may cause us to traverse large segments of the history graph. It's counter-productive to have save_commit_buffer turned on, as that will instruct the commit code to cache in-memory the object contents for each commit we traverse. This increases the amount of heap memory used while providing little or no benefit, since we're not actually planning to display those commits (which is the usual reason that tools like git-log want to keep them around). We can easily disable this feature while ref-filter is running. This lowers peak heap (as measured by massif) for running: git tag --contains 1da177e4c3 in linux.git from ~100MB to ~20MB. It also seems to improve runtime by 4-5% (600ms vs 630ms). A few points to note: - it should be safe to temporarily disable save_commit_buffer like this. The saved buffers are accessed through get_commit_buffer(), which treats the saved ones like a cache, and loads on-demand from the object database on a cache miss. So any code that was using this would not be wrong, it might just incur an extra object lookup for some objects. But... - I don't think any ref-filter related code is using the cache. While it's true that an option like "--format=%(*contents:subject)" or "--sort=*authordate" will need to look at the commit contents, ref-filter doesn't use get_commit_buffer() to do so! It always reads the objects directly via read_object_file(), though it does avoid re-reading objects if the format can be satisfied without them. Timing "git tag --format=%(*authordate)" shows that we're the same before and after, as expected. - Note that all of this assumes you don't have a commit-graph file. if you do, then the heap usage is even lower, and the runtime is 10x faster. So in that sense this is not urgent, as there's a much better solution. But since it's such an obvious and easy win for fallback cases (including commits which aren't yet in the graph file), there's no reason not to. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-07-11 16:48:06 +02:00
save_commit_buffer = save_commit_buffer_orig;
return ret;
}
branch: sort detached HEAD based on a flag Change the ref-filter sorting of detached HEAD to check the FILTER_REFS_DETACHED_HEAD flag, instead of relying on the ref description filled-in by get_head_description() to start with "(", which in turn we expect to ASCII-sort before any other reference. For context, we'd like the detached line to appear first at the start of "git branch -l", e.g.: $ git branch -l * (HEAD detached at <hash>) master This doesn't change that, but improves on a fix made in 28438e84e04 (ref-filter: sort detached HEAD lines firstly, 2019-06-18) and gives the Chinese translation the ability to use its preferred punctuation marks again. In Chinese the fullwidth versions of punctuation like "()" are typically written as (U+FF08 fullwidth left parenthesis), (U+FF09 fullwidth right parenthesis) instead[1]. This form is used in both po/zh_{CN,TW}.po in most cases where "()" is translated in a string. Aside from that improvement to the Chinese translation, it also just makes for cleaner code that we mark any special cases in the ref_array we're sorting with flags and make the sort function aware of them, instead of piggy-backing on the general-case of strcmp() doing the right thing. As seen in the amended tests this made reverse sorting a bit more consistent. Before this we'd sometimes sort this message in the middle, now it's consistently at the beginning or end, depending on whether we're doing a normal or reverse sort. Having it at the end doesn't make much sense either, but at least it behaves consistently now. A follow-up commit will make this behavior under reverse sorting even better. I'm removing the "TRANSLATORS" comments that were in the old code while I'm at it. Those were added in d4919bb288e (ref-filter: move get_head_description() from branch.c, 2017-01-10). I think it's obvious from context, string and translation memory in typical translation tools that these are the same or similar string. 1. https://en.wikipedia.org/wiki/Chinese_punctuation#Marks_similar_to_European_punctuation Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-07 10:51:52 +01:00
static int compare_detached_head(struct ref_array_item *a, struct ref_array_item *b)
{
if (!(a->kind ^ b->kind))
BUG("ref_kind_from_refname() should only mark one ref as HEAD");
if (a->kind & FILTER_REFS_DETACHED_HEAD)
return -1;
else if (b->kind & FILTER_REFS_DETACHED_HEAD)
return 1;
BUG("should have died in the xor check above");
return 0;
}
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
static int memcasecmp(const void *vs1, const void *vs2, size_t n)
{
const char *s1 = vs1, *s2 = vs2;
const char *end = s1 + n;
for (; s1 < end; s1++, s2++) {
int diff = tolower(*s1) - tolower(*s2);
if (diff)
return diff;
}
return 0;
}
for-each-ref: delay parsing of --sort=<atom> options The for-each-ref family of commands invoke parsers immediately when it sees each --sort=<atom> option, and die before even seeing the other options on the command line when the <atom> is unrecognised. Instead, accumulate them in a string list, and have them parsed into a ref_sorting structure after the command line parsing is done. As a consequence, "git branch --sort=bogus -h" used to fail to give the brief help, which arguably may have been a feature, now does so, which is more consistent with how other options work. The patch is smaller than the actual extent of the "damage" to the codebase, thanks to the fact that the original code consistently used OPT_REF_SORT() macro to handle command line options. We only needed to replace the variable used for the list, and implementation of the callback function used in the macro. The old rule was for the users of the API to: - Declare ref_sorting and ref_sorting_tail variables; - OPT_REF_SORT() macro will instantiate ref_sorting instance (which may barf and die) and append it to the tail; - Append to the tail each ref_sorting read from the configuration by parsing in the config callback (which may barf and die); - See if ref_sorting is null and use ref_sorting_default() instead. Now the rule is not all that different but is simpler: - Declare ref_sorting_options string list. - OPT_REF_SORT() macro will append it to the string list; - Append to the string list the sort key read from the configuration; - call ref_sorting_options() to turn the string list to ref_sorting structure (which also deals with the default value). As side effects, this change also cleans up a few issues: - 95be717c (parse_opt_ref_sorting: always use with NONEG flag, 2019-03-20) muses that "git for-each-ref --no-sort" should simply clear the sort keys accumulated so far; it now does. - The implementation detail of "struct ref_sorting" and the helper function parse_ref_sorting() can now be private to the ref-filter API implementation. - If you set branch.sort to a bogus value, the any "git branch" invocation, not only the listing mode, would abort with the original code; now it doesn't Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-10-20 21:23:53 +02:00
struct ref_sorting {
struct ref_sorting *next;
int atom; /* index into used_atom array (internal) */
enum ref_sorting_order sort_flags;
};
static int cmp_ref_sorting(struct ref_sorting *s, struct ref_array_item *a, struct ref_array_item *b)
{
struct atom_value *va, *vb;
int cmp;
int cmp_detached_head = 0;
cmp_type cmp_type = used_atom[s->atom].type;
struct strbuf err = STRBUF_INIT;
if (get_ref_atom_value(a, s->atom, &va, &err))
die("%s", err.buf);
if (get_ref_atom_value(b, s->atom, &vb, &err))
die("%s", err.buf);
strbuf_release(&err);
branch: sort detached HEAD based on a flag Change the ref-filter sorting of detached HEAD to check the FILTER_REFS_DETACHED_HEAD flag, instead of relying on the ref description filled-in by get_head_description() to start with "(", which in turn we expect to ASCII-sort before any other reference. For context, we'd like the detached line to appear first at the start of "git branch -l", e.g.: $ git branch -l * (HEAD detached at <hash>) master This doesn't change that, but improves on a fix made in 28438e84e04 (ref-filter: sort detached HEAD lines firstly, 2019-06-18) and gives the Chinese translation the ability to use its preferred punctuation marks again. In Chinese the fullwidth versions of punctuation like "()" are typically written as (U+FF08 fullwidth left parenthesis), (U+FF09 fullwidth right parenthesis) instead[1]. This form is used in both po/zh_{CN,TW}.po in most cases where "()" is translated in a string. Aside from that improvement to the Chinese translation, it also just makes for cleaner code that we mark any special cases in the ref_array we're sorting with flags and make the sort function aware of them, instead of piggy-backing on the general-case of strcmp() doing the right thing. As seen in the amended tests this made reverse sorting a bit more consistent. Before this we'd sometimes sort this message in the middle, now it's consistently at the beginning or end, depending on whether we're doing a normal or reverse sort. Having it at the end doesn't make much sense either, but at least it behaves consistently now. A follow-up commit will make this behavior under reverse sorting even better. I'm removing the "TRANSLATORS" comments that were in the old code while I'm at it. Those were added in d4919bb288e (ref-filter: move get_head_description() from branch.c, 2017-01-10). I think it's obvious from context, string and translation memory in typical translation tools that these are the same or similar string. 1. https://en.wikipedia.org/wiki/Chinese_punctuation#Marks_similar_to_European_punctuation Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-07 10:51:52 +01:00
if (s->sort_flags & REF_SORTING_DETACHED_HEAD_FIRST &&
((a->kind | b->kind) & FILTER_REFS_DETACHED_HEAD)) {
cmp = compare_detached_head(a, b);
cmp_detached_head = 1;
branch: sort detached HEAD based on a flag Change the ref-filter sorting of detached HEAD to check the FILTER_REFS_DETACHED_HEAD flag, instead of relying on the ref description filled-in by get_head_description() to start with "(", which in turn we expect to ASCII-sort before any other reference. For context, we'd like the detached line to appear first at the start of "git branch -l", e.g.: $ git branch -l * (HEAD detached at <hash>) master This doesn't change that, but improves on a fix made in 28438e84e04 (ref-filter: sort detached HEAD lines firstly, 2019-06-18) and gives the Chinese translation the ability to use its preferred punctuation marks again. In Chinese the fullwidth versions of punctuation like "()" are typically written as (U+FF08 fullwidth left parenthesis), (U+FF09 fullwidth right parenthesis) instead[1]. This form is used in both po/zh_{CN,TW}.po in most cases where "()" is translated in a string. Aside from that improvement to the Chinese translation, it also just makes for cleaner code that we mark any special cases in the ref_array we're sorting with flags and make the sort function aware of them, instead of piggy-backing on the general-case of strcmp() doing the right thing. As seen in the amended tests this made reverse sorting a bit more consistent. Before this we'd sometimes sort this message in the middle, now it's consistently at the beginning or end, depending on whether we're doing a normal or reverse sort. Having it at the end doesn't make much sense either, but at least it behaves consistently now. A follow-up commit will make this behavior under reverse sorting even better. I'm removing the "TRANSLATORS" comments that were in the old code while I'm at it. Those were added in d4919bb288e (ref-filter: move get_head_description() from branch.c, 2017-01-10). I think it's obvious from context, string and translation memory in typical translation tools that these are the same or similar string. 1. https://en.wikipedia.org/wiki/Chinese_punctuation#Marks_similar_to_European_punctuation Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-07 10:51:52 +01:00
} else if (s->sort_flags & REF_SORTING_VERSION) {
cmp = versioncmp(va->s, vb->s);
} else if (cmp_type == FIELD_STR) {
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
if (va->s_size < 0 && vb->s_size < 0) {
int (*cmp_fn)(const char *, const char *);
cmp_fn = s->sort_flags & REF_SORTING_ICASE
? strcasecmp : strcmp;
cmp = cmp_fn(va->s, vb->s);
} else {
size_t a_size = va->s_size < 0 ?
strlen(va->s) : va->s_size;
size_t b_size = vb->s_size < 0 ?
strlen(vb->s) : vb->s_size;
int (*cmp_fn)(const void *, const void *, size_t);
cmp_fn = s->sort_flags & REF_SORTING_ICASE
? memcasecmp : memcmp;
cmp = cmp_fn(va->s, vb->s, b_size > a_size ?
a_size : b_size);
if (!cmp) {
if (a_size > b_size)
cmp = 1;
else if (a_size < b_size)
cmp = -1;
}
}
} else {
if (va->value < vb->value)
cmp = -1;
else if (va->value == vb->value)
ref-filter: apply fallback refname sort only after all user sorts Commit 9e468334b4 (ref-filter: fallback on alphabetical comparison, 2015-10-30) taught ref-filter's sort to fallback to comparing refnames. But it did it at the wrong level, overriding the comparison result for a single "--sort" key from the user, rather than after all sort keys have been exhausted. This worked correctly for a single "--sort" option, but not for multiple ones. We'd break any ties in the first key with the refname and never evaluate the second key at all. To make matters even more interesting, we only applied this fallback sometimes! For a field like "taggeremail" which requires a string comparison, we'd truly return the result of strcmp(), even if it was 0. But for numerical "value" fields like "taggerdate", we did apply the fallback. And that's why our multiple-sort test missed this: it uses taggeremail as the main comparison. So let's start by adding a much more rigorous test. We'll have a set of commits expressing every combination of two tagger emails, dates, and refnames. Then we can confirm that our sort is applied with the correct precedence, and we'll be hitting both the string and value comparators. That does show the bug, and the fix is simple: moving the fallback to the outer compare_refs() function, after all ref_sorting keys have been exhausted. Note that in the outer function we don't have an "ignore_case" flag, as it's part of each individual ref_sorting element. It's debatable what such a fallback should do, since we didn't use the user's keys to match. But until now we have been trying to respect that flag, so the least-invasive thing is to try to continue to do so. Since all callers in the current code either set the flag for all keys or for none, we can just pull the flag from the first key. In a hypothetical world where the user really can flip the case-insensitivity of keys separately, we may want to extend the code to distinguish that case from a blanket "--ignore-case". Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-05-03 11:13:09 +02:00
cmp = 0;
else
cmp = 1;
}
return (s->sort_flags & REF_SORTING_REVERSE && !cmp_detached_head)
? -cmp : cmp;
}
static int compare_refs(const void *a_, const void *b_, void *ref_sorting)
{
struct ref_array_item *a = *((struct ref_array_item **)a_);
struct ref_array_item *b = *((struct ref_array_item **)b_);
struct ref_sorting *s;
for (s = ref_sorting; s; s = s->next) {
int cmp = cmp_ref_sorting(s, a, b);
if (cmp)
return cmp;
}
ref-filter: apply fallback refname sort only after all user sorts Commit 9e468334b4 (ref-filter: fallback on alphabetical comparison, 2015-10-30) taught ref-filter's sort to fallback to comparing refnames. But it did it at the wrong level, overriding the comparison result for a single "--sort" key from the user, rather than after all sort keys have been exhausted. This worked correctly for a single "--sort" option, but not for multiple ones. We'd break any ties in the first key with the refname and never evaluate the second key at all. To make matters even more interesting, we only applied this fallback sometimes! For a field like "taggeremail" which requires a string comparison, we'd truly return the result of strcmp(), even if it was 0. But for numerical "value" fields like "taggerdate", we did apply the fallback. And that's why our multiple-sort test missed this: it uses taggeremail as the main comparison. So let's start by adding a much more rigorous test. We'll have a set of commits expressing every combination of two tagger emails, dates, and refnames. Then we can confirm that our sort is applied with the correct precedence, and we'll be hitting both the string and value comparators. That does show the bug, and the fix is simple: moving the fallback to the outer compare_refs() function, after all ref_sorting keys have been exhausted. Note that in the outer function we don't have an "ignore_case" flag, as it's part of each individual ref_sorting element. It's debatable what such a fallback should do, since we didn't use the user's keys to match. But until now we have been trying to respect that flag, so the least-invasive thing is to try to continue to do so. Since all callers in the current code either set the flag for all keys or for none, we can just pull the flag from the first key. In a hypothetical world where the user really can flip the case-insensitivity of keys separately, we may want to extend the code to distinguish that case from a blanket "--ignore-case". Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-05-03 11:13:09 +02:00
s = ref_sorting;
return s && s->sort_flags & REF_SORTING_ICASE ?
ref-filter: apply fallback refname sort only after all user sorts Commit 9e468334b4 (ref-filter: fallback on alphabetical comparison, 2015-10-30) taught ref-filter's sort to fallback to comparing refnames. But it did it at the wrong level, overriding the comparison result for a single "--sort" key from the user, rather than after all sort keys have been exhausted. This worked correctly for a single "--sort" option, but not for multiple ones. We'd break any ties in the first key with the refname and never evaluate the second key at all. To make matters even more interesting, we only applied this fallback sometimes! For a field like "taggeremail" which requires a string comparison, we'd truly return the result of strcmp(), even if it was 0. But for numerical "value" fields like "taggerdate", we did apply the fallback. And that's why our multiple-sort test missed this: it uses taggeremail as the main comparison. So let's start by adding a much more rigorous test. We'll have a set of commits expressing every combination of two tagger emails, dates, and refnames. Then we can confirm that our sort is applied with the correct precedence, and we'll be hitting both the string and value comparators. That does show the bug, and the fix is simple: moving the fallback to the outer compare_refs() function, after all ref_sorting keys have been exhausted. Note that in the outer function we don't have an "ignore_case" flag, as it's part of each individual ref_sorting element. It's debatable what such a fallback should do, since we didn't use the user's keys to match. But until now we have been trying to respect that flag, so the least-invasive thing is to try to continue to do so. Since all callers in the current code either set the flag for all keys or for none, we can just pull the flag from the first key. In a hypothetical world where the user really can flip the case-insensitivity of keys separately, we may want to extend the code to distinguish that case from a blanket "--ignore-case". Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-05-03 11:13:09 +02:00
strcasecmp(a->refname, b->refname) :
strcmp(a->refname, b->refname);
}
void ref_sorting_set_sort_flags_all(struct ref_sorting *sorting,
unsigned int mask, int on)
{
for (; sorting; sorting = sorting->next) {
if (on)
sorting->sort_flags |= mask;
else
sorting->sort_flags &= ~mask;
}
}
void ref_array_sort(struct ref_sorting *sorting, struct ref_array *array)
{
QSORT_S(array->items, array->nr, compare_refs, sorting);
}
static void append_literal(const char *cp, const char *ep, struct ref_formatting_state *state)
{
struct strbuf *s = &state->stack->output;
while (*cp && (!ep || cp < ep)) {
if (*cp == '%') {
if (cp[1] == '%')
cp++;
else {
int ch = hex2chr(cp + 1);
if (0 <= ch) {
strbuf_addch(s, ch);
cp += 3;
continue;
}
}
}
strbuf_addch(s, *cp);
cp++;
}
}
int format_ref_array_item(struct ref_array_item *info,
struct ref_format *format,
struct strbuf *final_buf,
struct strbuf *error_buf)
{
const char *cp, *sp, *ep;
struct ref_formatting_state state = REF_FORMATTING_STATE_INIT;
state.quote_style = format->quote_style;
push_stack_element(&state.stack);
for (cp = format->format; *cp && (sp = find_next(cp)); cp = ep + 1) {
struct atom_value *atomv;
int pos;
ep = strchr(sp, ')');
if (cp < sp)
append_literal(cp, sp, &state);
pos = parse_ref_filter_atom(format, sp + 2, ep, error_buf);
if (pos < 0 || get_ref_atom_value(info, pos, &atomv, error_buf) ||
atomv->handler(atomv, &state, error_buf)) {
pop_stack_element(&state.stack);
return -1;
}
}
if (*cp) {
sp = cp + strlen(cp);
append_literal(cp, sp, &state);
}
if (format->need_color_reset_at_eol) {
ref-filter: add %(raw) atom Add new formatting option `%(raw)`, which will print the raw object data without any changes. It will help further to migrate all cat-file formatting logic from cat-file to ref-filter. The raw data of blob, tree objects may contain '\0', but most of the logic in `ref-filter` depends on the output of the atom being text (specifically, no embedded NULs in it). E.g. `quote_formatting()` use `strbuf_addstr()` or `*._quote_buf()` add the data to the buffer. The raw data of a tree object is `100644 one\0...`, only the `100644 one` will be added to the buffer, which is incorrect. Therefore, we need to find a way to record the length of the atom_value's member `s`. Although strbuf can already record the string and its length, if we want to replace the type of atom_value's member `s` with strbuf, many places in ref-filter that are filled with dynamically allocated mermory in `v->s` are not easy to replace. At the same time, we need to check if `v->s == NULL` in populate_value(), and strbuf cannot easily distinguish NULL and empty strings, but c-style "const char *" can do it. So add a new member in `struct atom_value`: `s_size`, which can record raw object size, it can help us add raw object data to the buffer or compare two buffers which contain raw object data. Note that `--format=%(raw)` cannot be used with `--python`, `--shell`, `--tcl`, and `--perl` because if the binary raw data is passed to a variable in such languages, these may not support arbitrary binary data in their string variable type. Reviewed-by: Jacob Keller <jacob.keller@gmail.com> Mentored-by: Christian Couder <christian.couder@gmail.com> Mentored-by: Hariom Verma <hariom18599@gmail.com> Helped-by: Bagas Sanjaya <bagasdotme@gmail.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Helped-by: Felipe Contreras <felipe.contreras@gmail.com> Helped-by: Phillip Wood <phillip.wood@dunelm.org.uk> Helped-by: Junio C Hamano <gitster@pobox.com> Based-on-patch-by: Olga Telezhnaya <olyatelezhnaya@gmail.com> Signed-off-by: ZheNing Hu <adlternative@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-26 05:26:47 +02:00
struct atom_value resetv = ATOM_VALUE_INIT;
resetv.s = GIT_COLOR_RESET;
if (append_atom(&resetv, &state, error_buf)) {
pop_stack_element(&state.stack);
return -1;
}
}
if (state.stack->prev) {
pop_stack_element(&state.stack);
return strbuf_addf_ret(error_buf, -1, _("format: %%(end) atom missing"));
}
strbuf_addbuf(final_buf, &state.stack->output);
pop_stack_element(&state.stack);
return 0;
}
void pretty_print_ref(const char *name, const struct object_id *oid,
struct ref_format *format)
{
struct ref_array_item *ref_item;
struct strbuf output = STRBUF_INIT;
struct strbuf err = STRBUF_INIT;
ref_item = new_ref_array_item(name, oid);
ref_item->kind = ref_kind_from_refname(name);
if (format_ref_array_item(ref_item, format, &output, &err))
die("%s", err.buf);
fwrite(output.buf, 1, output.len, stdout);
putchar('\n');
strbuf_release(&err);
strbuf_release(&output);
free_array_item(ref_item);
}
static int parse_sorting_atom(const char *atom)
{
/*
* This parses an atom using a dummy ref_format, since we don't
* actually care about the formatting details.
*/
struct ref_format dummy = REF_FORMAT_INIT;
const char *end = atom + strlen(atom);
struct strbuf err = STRBUF_INIT;
int res = parse_ref_filter_atom(&dummy, atom, end, &err);
if (res < 0)
die("%s", err.buf);
strbuf_release(&err);
return res;
}
/* If no sorting option is given, use refname to sort as default */
for-each-ref: delay parsing of --sort=<atom> options The for-each-ref family of commands invoke parsers immediately when it sees each --sort=<atom> option, and die before even seeing the other options on the command line when the <atom> is unrecognised. Instead, accumulate them in a string list, and have them parsed into a ref_sorting structure after the command line parsing is done. As a consequence, "git branch --sort=bogus -h" used to fail to give the brief help, which arguably may have been a feature, now does so, which is more consistent with how other options work. The patch is smaller than the actual extent of the "damage" to the codebase, thanks to the fact that the original code consistently used OPT_REF_SORT() macro to handle command line options. We only needed to replace the variable used for the list, and implementation of the callback function used in the macro. The old rule was for the users of the API to: - Declare ref_sorting and ref_sorting_tail variables; - OPT_REF_SORT() macro will instantiate ref_sorting instance (which may barf and die) and append it to the tail; - Append to the tail each ref_sorting read from the configuration by parsing in the config callback (which may barf and die); - See if ref_sorting is null and use ref_sorting_default() instead. Now the rule is not all that different but is simpler: - Declare ref_sorting_options string list. - OPT_REF_SORT() macro will append it to the string list; - Append to the string list the sort key read from the configuration; - call ref_sorting_options() to turn the string list to ref_sorting structure (which also deals with the default value). As side effects, this change also cleans up a few issues: - 95be717c (parse_opt_ref_sorting: always use with NONEG flag, 2019-03-20) muses that "git for-each-ref --no-sort" should simply clear the sort keys accumulated so far; it now does. - The implementation detail of "struct ref_sorting" and the helper function parse_ref_sorting() can now be private to the ref-filter API implementation. - If you set branch.sort to a bogus value, the any "git branch" invocation, not only the listing mode, would abort with the original code; now it doesn't Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-10-20 21:23:53 +02:00
static struct ref_sorting *ref_default_sorting(void)
{
static const char cstr_name[] = "refname";
struct ref_sorting *sorting = xcalloc(1, sizeof(*sorting));
sorting->next = NULL;
sorting->atom = parse_sorting_atom(cstr_name);
return sorting;
}
for-each-ref: delay parsing of --sort=<atom> options The for-each-ref family of commands invoke parsers immediately when it sees each --sort=<atom> option, and die before even seeing the other options on the command line when the <atom> is unrecognised. Instead, accumulate them in a string list, and have them parsed into a ref_sorting structure after the command line parsing is done. As a consequence, "git branch --sort=bogus -h" used to fail to give the brief help, which arguably may have been a feature, now does so, which is more consistent with how other options work. The patch is smaller than the actual extent of the "damage" to the codebase, thanks to the fact that the original code consistently used OPT_REF_SORT() macro to handle command line options. We only needed to replace the variable used for the list, and implementation of the callback function used in the macro. The old rule was for the users of the API to: - Declare ref_sorting and ref_sorting_tail variables; - OPT_REF_SORT() macro will instantiate ref_sorting instance (which may barf and die) and append it to the tail; - Append to the tail each ref_sorting read from the configuration by parsing in the config callback (which may barf and die); - See if ref_sorting is null and use ref_sorting_default() instead. Now the rule is not all that different but is simpler: - Declare ref_sorting_options string list. - OPT_REF_SORT() macro will append it to the string list; - Append to the string list the sort key read from the configuration; - call ref_sorting_options() to turn the string list to ref_sorting structure (which also deals with the default value). As side effects, this change also cleans up a few issues: - 95be717c (parse_opt_ref_sorting: always use with NONEG flag, 2019-03-20) muses that "git for-each-ref --no-sort" should simply clear the sort keys accumulated so far; it now does. - The implementation detail of "struct ref_sorting" and the helper function parse_ref_sorting() can now be private to the ref-filter API implementation. - If you set branch.sort to a bogus value, the any "git branch" invocation, not only the listing mode, would abort with the original code; now it doesn't Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-10-20 21:23:53 +02:00
static void parse_ref_sorting(struct ref_sorting **sorting_tail, const char *arg)
{
struct ref_sorting *s;
CALLOC_ARRAY(s, 1);
s->next = *sorting_tail;
*sorting_tail = s;
if (*arg == '-') {
s->sort_flags |= REF_SORTING_REVERSE;
arg++;
}
if (skip_prefix(arg, "version:", &arg) ||
skip_prefix(arg, "v:", &arg))
s->sort_flags |= REF_SORTING_VERSION;
s->atom = parse_sorting_atom(arg);
}
for-each-ref: delay parsing of --sort=<atom> options The for-each-ref family of commands invoke parsers immediately when it sees each --sort=<atom> option, and die before even seeing the other options on the command line when the <atom> is unrecognised. Instead, accumulate them in a string list, and have them parsed into a ref_sorting structure after the command line parsing is done. As a consequence, "git branch --sort=bogus -h" used to fail to give the brief help, which arguably may have been a feature, now does so, which is more consistent with how other options work. The patch is smaller than the actual extent of the "damage" to the codebase, thanks to the fact that the original code consistently used OPT_REF_SORT() macro to handle command line options. We only needed to replace the variable used for the list, and implementation of the callback function used in the macro. The old rule was for the users of the API to: - Declare ref_sorting and ref_sorting_tail variables; - OPT_REF_SORT() macro will instantiate ref_sorting instance (which may barf and die) and append it to the tail; - Append to the tail each ref_sorting read from the configuration by parsing in the config callback (which may barf and die); - See if ref_sorting is null and use ref_sorting_default() instead. Now the rule is not all that different but is simpler: - Declare ref_sorting_options string list. - OPT_REF_SORT() macro will append it to the string list; - Append to the string list the sort key read from the configuration; - call ref_sorting_options() to turn the string list to ref_sorting structure (which also deals with the default value). As side effects, this change also cleans up a few issues: - 95be717c (parse_opt_ref_sorting: always use with NONEG flag, 2019-03-20) muses that "git for-each-ref --no-sort" should simply clear the sort keys accumulated so far; it now does. - The implementation detail of "struct ref_sorting" and the helper function parse_ref_sorting() can now be private to the ref-filter API implementation. - If you set branch.sort to a bogus value, the any "git branch" invocation, not only the listing mode, would abort with the original code; now it doesn't Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-10-20 21:23:53 +02:00
struct ref_sorting *ref_sorting_options(struct string_list *options)
{
for-each-ref: delay parsing of --sort=<atom> options The for-each-ref family of commands invoke parsers immediately when it sees each --sort=<atom> option, and die before even seeing the other options on the command line when the <atom> is unrecognised. Instead, accumulate them in a string list, and have them parsed into a ref_sorting structure after the command line parsing is done. As a consequence, "git branch --sort=bogus -h" used to fail to give the brief help, which arguably may have been a feature, now does so, which is more consistent with how other options work. The patch is smaller than the actual extent of the "damage" to the codebase, thanks to the fact that the original code consistently used OPT_REF_SORT() macro to handle command line options. We only needed to replace the variable used for the list, and implementation of the callback function used in the macro. The old rule was for the users of the API to: - Declare ref_sorting and ref_sorting_tail variables; - OPT_REF_SORT() macro will instantiate ref_sorting instance (which may barf and die) and append it to the tail; - Append to the tail each ref_sorting read from the configuration by parsing in the config callback (which may barf and die); - See if ref_sorting is null and use ref_sorting_default() instead. Now the rule is not all that different but is simpler: - Declare ref_sorting_options string list. - OPT_REF_SORT() macro will append it to the string list; - Append to the string list the sort key read from the configuration; - call ref_sorting_options() to turn the string list to ref_sorting structure (which also deals with the default value). As side effects, this change also cleans up a few issues: - 95be717c (parse_opt_ref_sorting: always use with NONEG flag, 2019-03-20) muses that "git for-each-ref --no-sort" should simply clear the sort keys accumulated so far; it now does. - The implementation detail of "struct ref_sorting" and the helper function parse_ref_sorting() can now be private to the ref-filter API implementation. - If you set branch.sort to a bogus value, the any "git branch" invocation, not only the listing mode, would abort with the original code; now it doesn't Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-10-20 21:23:53 +02:00
struct string_list_item *item;
struct ref_sorting *sorting = NULL, **tail = &sorting;
if (!options->nr) {
sorting = ref_default_sorting();
} else {
for_each_string_list_item(item, options)
parse_ref_sorting(tail, item->string);
}
/*
for-each-ref: delay parsing of --sort=<atom> options The for-each-ref family of commands invoke parsers immediately when it sees each --sort=<atom> option, and die before even seeing the other options on the command line when the <atom> is unrecognised. Instead, accumulate them in a string list, and have them parsed into a ref_sorting structure after the command line parsing is done. As a consequence, "git branch --sort=bogus -h" used to fail to give the brief help, which arguably may have been a feature, now does so, which is more consistent with how other options work. The patch is smaller than the actual extent of the "damage" to the codebase, thanks to the fact that the original code consistently used OPT_REF_SORT() macro to handle command line options. We only needed to replace the variable used for the list, and implementation of the callback function used in the macro. The old rule was for the users of the API to: - Declare ref_sorting and ref_sorting_tail variables; - OPT_REF_SORT() macro will instantiate ref_sorting instance (which may barf and die) and append it to the tail; - Append to the tail each ref_sorting read from the configuration by parsing in the config callback (which may barf and die); - See if ref_sorting is null and use ref_sorting_default() instead. Now the rule is not all that different but is simpler: - Declare ref_sorting_options string list. - OPT_REF_SORT() macro will append it to the string list; - Append to the string list the sort key read from the configuration; - call ref_sorting_options() to turn the string list to ref_sorting structure (which also deals with the default value). As side effects, this change also cleans up a few issues: - 95be717c (parse_opt_ref_sorting: always use with NONEG flag, 2019-03-20) muses that "git for-each-ref --no-sort" should simply clear the sort keys accumulated so far; it now does. - The implementation detail of "struct ref_sorting" and the helper function parse_ref_sorting() can now be private to the ref-filter API implementation. - If you set branch.sort to a bogus value, the any "git branch" invocation, not only the listing mode, would abort with the original code; now it doesn't Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-10-20 21:23:53 +02:00
* From here on, the ref_sorting list should be used to talk
* about the sort order used for the output. The caller
* should not touch the string form anymore.
*/
for-each-ref: delay parsing of --sort=<atom> options The for-each-ref family of commands invoke parsers immediately when it sees each --sort=<atom> option, and die before even seeing the other options on the command line when the <atom> is unrecognised. Instead, accumulate them in a string list, and have them parsed into a ref_sorting structure after the command line parsing is done. As a consequence, "git branch --sort=bogus -h" used to fail to give the brief help, which arguably may have been a feature, now does so, which is more consistent with how other options work. The patch is smaller than the actual extent of the "damage" to the codebase, thanks to the fact that the original code consistently used OPT_REF_SORT() macro to handle command line options. We only needed to replace the variable used for the list, and implementation of the callback function used in the macro. The old rule was for the users of the API to: - Declare ref_sorting and ref_sorting_tail variables; - OPT_REF_SORT() macro will instantiate ref_sorting instance (which may barf and die) and append it to the tail; - Append to the tail each ref_sorting read from the configuration by parsing in the config callback (which may barf and die); - See if ref_sorting is null and use ref_sorting_default() instead. Now the rule is not all that different but is simpler: - Declare ref_sorting_options string list. - OPT_REF_SORT() macro will append it to the string list; - Append to the string list the sort key read from the configuration; - call ref_sorting_options() to turn the string list to ref_sorting structure (which also deals with the default value). As side effects, this change also cleans up a few issues: - 95be717c (parse_opt_ref_sorting: always use with NONEG flag, 2019-03-20) muses that "git for-each-ref --no-sort" should simply clear the sort keys accumulated so far; it now does. - The implementation detail of "struct ref_sorting" and the helper function parse_ref_sorting() can now be private to the ref-filter API implementation. - If you set branch.sort to a bogus value, the any "git branch" invocation, not only the listing mode, would abort with the original code; now it doesn't Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-10-20 21:23:53 +02:00
string_list_clear(options, 0);
return sorting;
}
void ref_sorting_release(struct ref_sorting *sorting)
{
while (sorting) {
struct ref_sorting *next = sorting->next;
free(sorting);
sorting = next;
}
}
int parse_opt_merge_filter(const struct option *opt, const char *arg, int unset)
{
struct ref_filter *rf = opt->value;
struct object_id oid;
struct commit *merge_commit;
assert NOARG/NONEG behavior of parse-options callbacks When we define a parse-options callback, the flags we put in the option struct must match what the callback expects. For example, a callback which does not handle the "unset" parameter should only be used with PARSE_OPT_NONEG. But since the callback and the option struct are not defined next to each other, it's easy to get this wrong (as earlier patches in this series show). Fortunately, the compiler can help us here: compiling with -Wunused-parameters can show us which callbacks ignore their "unset" parameters (and likewise, ones that ignore "arg" expect to be triggered with PARSE_OPT_NOARG). But after we've inspected a callback and determined that all of its callers use the right flags, what do we do next? We'd like to silence the compiler warning, but do so in a way that will catch any wrong calls in the future. We can do that by actually checking those variables and asserting that they match our expectations. Because this is such a common pattern, we'll introduce some helper macros. The resulting messages aren't as descriptive as we could make them, but the file/line information from BUG() is enough to identify the problem (and anyway, the point is that these should never be seen). Each of the annotated callbacks in this patch triggers -Wunused-parameters, and was manually inspected to make sure all callers use the correct options (so none of these BUGs should be triggerable). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-05 07:45:42 +01:00
BUG_ON_OPT_NEG(unset);
if (get_oid(arg, &oid))
die(_("malformed object name %s"), arg);
merge_commit = lookup_commit_reference_gently(the_repository, &oid, 0);
if (!merge_commit)
return error(_("option `%s' must point to a commit"), opt->long_name);
if (starts_with(opt->long_name, "no"))
commit_list_insert(merge_commit, &rf->unreachable_from);
else
commit_list_insert(merge_commit, &rf->reachable_from);
return 0;
}