Git Source Code Mirror - This is a publish-only repository and all pull requests are ignored. Please follow Documentation/SubmittingPatches procedure for any of your improvements. https://git-scm.com/
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
git/ref-filter.c

2761 lines
76 KiB

#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"
7 years ago
#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 *lookupdata UNUSED,
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>
1 year ago
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>
5 years ago
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>
5 years ago
} 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>
5 years ago
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>
1 year ago
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>
5 years ago
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>
5 years ago
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>
5 years ago
} 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>
1 year ago
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>
1 year ago
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)
{