git-commit-vandalism/archive.c

562 lines
15 KiB
C
Raw Normal View History

#include "cache.h"
#include "config.h"
#include "refs.h"
#include "commit.h"
#include "tree-walk.h"
#include "attr.h"
#include "archive.h"
#include "parse-options.h"
#include "unpack-trees.h"
#include "dir.h"
static char const * const archive_usage[] = {
N_("git archive [<options>] <tree-ish> [<path>...]"),
N_("git archive --list"),
N_("git archive --remote <repo> [--exec <cmd>] [<options>] <tree-ish> [<path>...]"),
N_("git archive --remote <repo> [--exec <cmd>] --list"),
NULL
};
static const struct archiver **archivers;
static int nr_archivers;
static int alloc_archivers;
static int remote_allow_unreachable;
void register_archiver(struct archiver *ar)
{
ALLOC_GROW(archivers, nr_archivers + 1, alloc_archivers);
archivers[nr_archivers++] = ar;
}
static void format_subst(const struct commit *commit,
const char *src, size_t len,
struct strbuf *buf)
{
char *to_free = NULL;
struct strbuf fmt = STRBUF_INIT;
struct pretty_print_context ctx = {0};
convert "enum date_mode" into a struct In preparation for adding date modes that may carry extra information beyond the mode itself, this patch converts the date_mode enum into a struct. Most of the conversion is fairly straightforward; we pass the struct as a pointer and dereference the type field where necessary. Locations that declare a date_mode can use a "{}" constructor. However, the tricky case is where we use the enum labels as constants, like: show_date(t, tz, DATE_NORMAL); Ideally we could say: show_date(t, tz, &{ DATE_NORMAL }); but of course C does not allow that. Likewise, we cannot cast the constant to a struct, because we need to pass an actual address. Our options are basically: 1. Manually add a "struct date_mode d = { DATE_NORMAL }" definition to each caller, and pass "&d". This makes the callers uglier, because they sometimes do not even have their own scope (e.g., they are inside a switch statement). 2. Provide a pre-made global "date_normal" struct that can be passed by address. We'd also need "date_rfc2822", "date_iso8601", and so forth. But at least the ugliness is defined in one place. 3. Provide a wrapper that generates the correct struct on the fly. The big downside is that we end up pointing to a single global, which makes our wrapper non-reentrant. But show_date is already not reentrant, so it does not matter. This patch implements 3, along with a minor macro to keep the size of the callers sane. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-06-25 18:55:02 +02:00
ctx.date_mode.type = DATE_NORMAL;
ctx.abbrev = DEFAULT_ABBREV;
if (src == buf->buf)
to_free = strbuf_detach(buf, NULL);
for (;;) {
const char *b, *c;
b = memmem(src, len, "$Format:", 8);
if (!b)
break;
c = memchr(b + 8, '$', (src + len) - b - 8);
if (!c)
break;
strbuf_reset(&fmt);
strbuf_add(&fmt, b + 8, c - b - 8);
strbuf_add(buf, src, b - src);
format_commit_message(commit, fmt.buf, buf, &ctx);
len -= c + 1 - src;
src = c + 1;
}
strbuf_add(buf, src, len);
strbuf_release(&fmt);
free(to_free);
}
void *object_file_to_archive(const struct archiver_args *args,
const char *path, const struct object_id *oid,
unsigned int mode, enum object_type *type,
unsigned long *sizep)
{
void *buffer;
const struct commit *commit = args->convert ? args->commit : NULL;
path += args->baselen;
buffer = read_object_file(oid, type, sizep);
if (buffer && S_ISREG(mode)) {
struct strbuf buf = STRBUF_INIT;
size_t size = 0;
strbuf_attach(&buf, buffer, *sizep, *sizep + 1);
convert_to_working_tree(path, buf.buf, buf.len, &buf);
if (commit)
format_subst(commit, buf.buf, buf.len, &buf);
buffer = strbuf_detach(&buf, &size);
*sizep = size;
}
return buffer;
}
struct directory {
struct directory *up;
struct object_id oid;
int baselen, len;
unsigned mode;
int stage;
char path[FLEX_ARRAY];
};
struct archiver_context {
struct archiver_args *args;
write_archive_entry_fn_t write_entry;
struct directory *bottom;
};
static const struct attr_check *get_archive_attrs(const char *path)
{
static struct attr_check *check;
if (!check)
check = attr_check_initl("export-ignore", "export-subst", NULL);
return git_check_attr(path, check) ? NULL : check;
}
static int check_attr_export_ignore(const struct attr_check *check)
{
return check && ATTR_TRUE(check->items[0].value);
}
static int check_attr_export_subst(const struct attr_check *check)
{
return check && ATTR_TRUE(check->items[1].value);
}
static int write_archive_entry(const struct object_id *oid, const char *base,
int baselen, const char *filename, unsigned mode, int stage,
void *context)
{
static struct strbuf path = STRBUF_INIT;
struct archiver_context *c = context;
struct archiver_args *args = c->args;
write_archive_entry_fn_t write_entry = c->write_entry;
int err;
const char *path_without_prefix;
args->convert = 0;
strbuf_reset(&path);
strbuf_grow(&path, PATH_MAX);
strbuf_add(&path, args->base, args->baselen);
strbuf_add(&path, base, baselen);
strbuf_addstr(&path, filename);
if (S_ISDIR(mode) || S_ISGITLINK(mode))
strbuf_addch(&path, '/');
path_without_prefix = path.buf + args->baselen;
archive: don't add empty directories to archives While git doesn't track empty directories, git archive can be tricked into putting some into archives. One way is to construct an empty tree object, as t5004 does. While that is supported by the object database, it can't be represented in the index and thus it's unlikely to occur in the wild. Another way is using the literal name of a directory in an exclude pathspec -- its contents are are excluded, but the directory stub is included. That's inconsistent: exclude pathspecs containing wildcards don't leave empty directories in the archive. Yet another way is have a few levels of nested subdirectories (e.g. d1/d2/d3/file1) and ignoring the entries at the leaves (e.g. file1). The directories with the ignored content are ignored as well (e.g. d3), but their empty parents are included (e.g. d2). As empty directories are not supported by git, they should also not be written into archives. If an empty directory is really needed then it can be tracked and archived by placing an empty .gitignore file in it. There already is a mechanism in place for suppressing empty directories. When read_tree_recursive() encounters a directory excluded by a pathspec then it enters it anyway because it might contain included entries. It calls the callback function before it is able to decide if the directory is actually needed. For that reason git archive adds directories to a queue and writes entries for them only when it encounters the first child item -- but currently only if pathspecs with wildcards are used. Queue *all* directories, no matter if there even are pathspecs present. This prevents git archive from writing entries for empty directories in all cases. Suggested-by: Jeff King <peff@peff.net> Signed-off-by: Rene Scharfe <l.s.r@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-13 00:43:57 +02:00
if (!S_ISDIR(mode)) {
const struct attr_check *check;
check = get_archive_attrs(path_without_prefix);
if (check_attr_export_ignore(check))
return 0;
args->convert = check_attr_export_subst(check);
}
if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
if (args->verbose)
fprintf(stderr, "%.*s\n", (int)path.len, path.buf);
err = write_entry(args, oid, path.buf, path.len, mode);
if (err)
return err;
return (S_ISDIR(mode) ? READ_TREE_RECURSIVE : 0);
}
if (args->verbose)
fprintf(stderr, "%.*s\n", (int)path.len, path.buf);
return write_entry(args, oid, path.buf, path.len, mode);
}
static void queue_directory(const unsigned char *sha1,
struct strbuf *base, const char *filename,
unsigned mode, int stage, struct archiver_context *c)
{
struct directory *d;
size_t len = st_add4(base->len, 1, strlen(filename), 1);
d = xmalloc(st_add(sizeof(*d), len));
d->up = c->bottom;
d->baselen = base->len;
d->mode = mode;
d->stage = stage;
c->bottom = d;
d->len = xsnprintf(d->path, len, "%.*s%s/", (int)base->len, base->buf, filename);
hashcpy(d->oid.hash, sha1);
}
static int write_directory(struct archiver_context *c)
{
struct directory *d = c->bottom;
int ret;
if (!d)
return 0;
c->bottom = d->up;
d->path[d->len - 1] = '\0'; /* no trailing slash */
ret =
write_directory(c) ||
write_archive_entry(&d->oid, d->path, d->baselen,
d->path + d->baselen, d->mode,
d->stage, c) != READ_TREE_RECURSIVE;
free(d);
return ret ? -1 : 0;
}
static int queue_or_write_archive_entry(const struct object_id *oid,
struct strbuf *base, const char *filename,
unsigned mode, int stage, void *context)
{
struct archiver_context *c = context;
while (c->bottom &&
!(base->len >= c->bottom->len &&
!strncmp(base->buf, c->bottom->path, c->bottom->len))) {
struct directory *next = c->bottom->up;
free(c->bottom);
c->bottom = next;
}
if (S_ISDIR(mode)) {
size_t baselen = base->len;
const struct attr_check *check;
/* Borrow base, but restore its original value when done. */
strbuf_addstr(base, filename);
strbuf_addch(base, '/');
check = get_archive_attrs(base->buf);
strbuf_setlen(base, baselen);
if (check_attr_export_ignore(check))
return 0;
queue_directory(oid->hash, base, filename,
mode, stage, c);
return READ_TREE_RECURSIVE;
}
if (write_directory(c))
return -1;
return write_archive_entry(oid, base->buf, base->len, filename, mode,
stage, context);
}
int write_archive_entries(struct archiver_args *args,
write_archive_entry_fn_t write_entry)
{
struct archiver_context context;
struct unpack_trees_options opts;
struct tree_desc t;
int err;
if (args->baselen > 0 && args->base[args->baselen - 1] == '/') {
size_t len = args->baselen;
while (len > 1 && args->base[len - 2] == '/')
len--;
if (args->verbose)
fprintf(stderr, "%.*s\n", (int)len, args->base);
err = write_entry(args, &args->tree->object.oid, args->base,
len, 040777);
if (err)
return err;
}
memset(&context, 0, sizeof(context));
context.args = args;
context.write_entry = write_entry;
/*
* Setup index and instruct attr to read index only
*/
if (!args->worktree_attributes) {
memset(&opts, 0, sizeof(opts));
opts.index_only = 1;
opts.head_idx = -1;
opts.src_index = &the_index;
opts.dst_index = &the_index;
opts.fn = oneway_merge;
init_tree_desc(&t, args->tree->buffer, args->tree->size);
if (unpack_trees(1, &t, &opts))
return -1;
git_attr_set_direction(GIT_ATTR_INDEX, &the_index);
}
err = read_tree_recursive(args->tree, "", 0, 0, &args->pathspec,
archive: don't add empty directories to archives While git doesn't track empty directories, git archive can be tricked into putting some into archives. One way is to construct an empty tree object, as t5004 does. While that is supported by the object database, it can't be represented in the index and thus it's unlikely to occur in the wild. Another way is using the literal name of a directory in an exclude pathspec -- its contents are are excluded, but the directory stub is included. That's inconsistent: exclude pathspecs containing wildcards don't leave empty directories in the archive. Yet another way is have a few levels of nested subdirectories (e.g. d1/d2/d3/file1) and ignoring the entries at the leaves (e.g. file1). The directories with the ignored content are ignored as well (e.g. d3), but their empty parents are included (e.g. d2). As empty directories are not supported by git, they should also not be written into archives. If an empty directory is really needed then it can be tracked and archived by placing an empty .gitignore file in it. There already is a mechanism in place for suppressing empty directories. When read_tree_recursive() encounters a directory excluded by a pathspec then it enters it anyway because it might contain included entries. It calls the callback function before it is able to decide if the directory is actually needed. For that reason git archive adds directories to a queue and writes entries for them only when it encounters the first child item -- but currently only if pathspecs with wildcards are used. Queue *all* directories, no matter if there even are pathspecs present. This prevents git archive from writing entries for empty directories in all cases. Suggested-by: Jeff King <peff@peff.net> Signed-off-by: Rene Scharfe <l.s.r@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-13 00:43:57 +02:00
queue_or_write_archive_entry,
&context);
if (err == READ_TREE_RECURSIVE)
err = 0;
while (context.bottom) {
struct directory *next = context.bottom->up;
free(context.bottom);
context.bottom = next;
}
return err;
}
static const struct archiver *lookup_archiver(const char *name)
{
int i;
if (!name)
return NULL;
for (i = 0; i < nr_archivers; i++) {
if (!strcmp(name, archivers[i]->name))
return archivers[i];
}
return NULL;
}
static int reject_entry(const struct object_id *oid, struct strbuf *base,
const char *filename, unsigned mode,
int stage, void *context)
{
int ret = -1;
if (S_ISDIR(mode)) {
struct strbuf sb = STRBUF_INIT;
strbuf_addbuf(&sb, base);
strbuf_addstr(&sb, filename);
if (!match_pathspec(context, sb.buf, sb.len, 0, NULL, 1))
ret = READ_TREE_RECURSIVE;
strbuf_release(&sb);
}
return ret;
}
static int path_exists(struct tree *tree, const char *path)
{
const char *paths[] = { path, NULL };
struct pathspec pathspec;
int ret;
parse_pathspec(&pathspec, 0, 0, "", paths);
pathspec.recursive = 1;
ret = read_tree_recursive(tree, "", 0, 0, &pathspec,
reject_entry, &pathspec);
clear_pathspec(&pathspec);
return ret != 0;
}
static void parse_pathspec_arg(const char **pathspec,
struct archiver_args *ar_args)
{
/*
* must be consistent with parse_pathspec in path_exists()
* Also if pathspec patterns are dependent, we're in big
* trouble as we test each one separately
*/
parse_pathspec(&ar_args->pathspec, 0,
PATHSPEC_PREFER_FULL,
"", pathspec);
ar_args->pathspec.recursive = 1;
if (pathspec) {
while (*pathspec) {
if (**pathspec && !path_exists(ar_args->tree, *pathspec))
die(_("pathspec '%s' did not match any files"), *pathspec);
pathspec++;
}
}
}
static void parse_treeish_arg(const char **argv,
struct archiver_args *ar_args, const char *prefix,
int remote)
{
const char *name = argv[0];
const unsigned char *commit_sha1;
time_t archive_time;
struct tree *tree;
const struct commit *commit;
struct object_id oid;
/* Remotes are only allowed to fetch actual refs */
if (remote && !remote_allow_unreachable) {
char *ref = NULL;
const char *colon = strchrnul(name, ':');
int refnamelen = colon - name;
if (!dwim_ref(name, refnamelen, &oid, &ref))
die("no such ref: %.*s", refnamelen, name);
free(ref);
}
sha1_name: convert get_sha1* to get_oid* Now that all the callers of get_sha1 directly or indirectly use struct object_id, rename the functions starting with get_sha1 to start with get_oid. Convert the internals in sha1_name.c to use struct object_id as well, and eliminate explicit length checks where possible. Convert a use of 40 in get_oid_basic to GIT_SHA1_HEXSZ. Outside of sha1_name.c and cache.h, this transition was made with the following semantic patch: @@ expression E1, E2; @@ - get_sha1(E1, E2.hash) + get_oid(E1, &E2) @@ expression E1, E2; @@ - get_sha1(E1, E2->hash) + get_oid(E1, E2) @@ expression E1, E2; @@ - get_sha1_committish(E1, E2.hash) + get_oid_committish(E1, &E2) @@ expression E1, E2; @@ - get_sha1_committish(E1, E2->hash) + get_oid_committish(E1, E2) @@ expression E1, E2; @@ - get_sha1_treeish(E1, E2.hash) + get_oid_treeish(E1, &E2) @@ expression E1, E2; @@ - get_sha1_treeish(E1, E2->hash) + get_oid_treeish(E1, E2) @@ expression E1, E2; @@ - get_sha1_commit(E1, E2.hash) + get_oid_commit(E1, &E2) @@ expression E1, E2; @@ - get_sha1_commit(E1, E2->hash) + get_oid_commit(E1, E2) @@ expression E1, E2; @@ - get_sha1_tree(E1, E2.hash) + get_oid_tree(E1, &E2) @@ expression E1, E2; @@ - get_sha1_tree(E1, E2->hash) + get_oid_tree(E1, E2) @@ expression E1, E2; @@ - get_sha1_blob(E1, E2.hash) + get_oid_blob(E1, &E2) @@ expression E1, E2; @@ - get_sha1_blob(E1, E2->hash) + get_oid_blob(E1, E2) @@ expression E1, E2, E3, E4; @@ - get_sha1_with_context(E1, E2, E3.hash, E4) + get_oid_with_context(E1, E2, &E3, E4) @@ expression E1, E2, E3, E4; @@ - get_sha1_with_context(E1, E2, E3->hash, E4) + get_oid_with_context(E1, E2, E3, E4) Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-07-14 01:49:28 +02:00
if (get_oid(name, &oid))
die("Not a valid object name");
Convert lookup_commit* to struct object_id Convert lookup_commit, lookup_commit_or_die, lookup_commit_reference, and lookup_commit_reference_gently to take struct object_id arguments. Introduce a temporary in parse_object buffer in order to convert this function. This is required since in order to convert parse_object and parse_object_buffer, lookup_commit_reference_gently and lookup_commit_or_die would need to be converted. Not introducing a temporary would therefore require that lookup_commit_or_die take a struct object_id *, but lookup_commit would take unsigned char *, leaving a confusing and hard-to-use interface. parse_object_buffer will lose this temporary in a later patch. This commit was created with manual changes to commit.c, commit.h, and object.c, plus the following semantic patch: @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1.hash, E2) + lookup_commit_reference_gently(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1->hash, E2) + lookup_commit_reference_gently(E1, E2) @@ expression E1; @@ - lookup_commit_reference(E1.hash) + lookup_commit_reference(&E1) @@ expression E1; @@ - lookup_commit_reference(E1->hash) + lookup_commit_reference(E1) @@ expression E1; @@ - lookup_commit(E1.hash) + lookup_commit(&E1) @@ expression E1; @@ - lookup_commit(E1->hash) + lookup_commit(E1) @@ expression E1, E2; @@ - lookup_commit_or_die(E1.hash, E2) + lookup_commit_or_die(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_or_die(E1->hash, E2) + lookup_commit_or_die(E1, E2) Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-07 00:10:10 +02:00
commit = lookup_commit_reference_gently(&oid, 1);
if (commit) {
commit_sha1 = commit->object.oid.hash;
archive_time = commit->date;
} else {
commit_sha1 = NULL;
archive_time = time(NULL);
}
tree = parse_tree_indirect(&oid);
if (tree == NULL)
die("not a tree object");
if (prefix) {
struct object_id tree_oid;
unsigned int mode;
int err;
err = get_tree_entry(&tree->object.oid, prefix, &tree_oid,
&mode);
if (err || !S_ISDIR(mode))
die("current working directory is untracked");
tree = parse_tree_indirect(&tree_oid);
}
ar_args->tree = tree;
ar_args->commit_sha1 = commit_sha1;
ar_args->commit = commit;
ar_args->time = archive_time;
}
#define OPT__COMPR(s, v, h, p) \
OPT_SET_INT_F(s, NULL, v, h, p, PARSE_OPT_NONEG)
#define OPT__COMPR_HIDDEN(s, v, p) \
OPT_SET_INT_F(s, NULL, v, "", p, PARSE_OPT_NONEG | PARSE_OPT_HIDDEN)
static int parse_archive_args(int argc, const char **argv,
archive: move file extension format-guessing lower The process for guessing an archive output format based on the filename is something like this: a. parse --output in cmd_archive; check the filename against a static set of mapping heuristics (right now it just matches ".zip" for zip files). b. if found, stick a fake "--format=zip" at the beginning of the arguments list (if the user did specify a --format manually, the later option will override our fake one) c. if it's a remote call, ship the arguments to the remote (including the fake), which will call write_archive on their end d. if it's local, ship the arguments to write_archive locally There are two problems: 1. The set of mappings is static and at too high a level. The write_archive level is going to check config for user-defined formats, some of which will specify extensions. We need to delay lookup until those are parsed, so we can match against them. 2. For a remote archive call, our set of mappings (or formats) may not match the remote side's. This is OK in practice right now, because all versions of git understand "zip" and "tar". But as new formats are added, there is going to be a mismatch between what the client can do and what the remote server can do. To fix (1), this patch refactors the location guessing to happen at the write_archive level, instead of the cmd_archive level. So instead of sticking a fake --format field in the argv list, we actually pass a "name hint" down the callchain; this hint is used at the appropriate time to guess the format (if one hasn't been given already). This patch leaves (2) unfixed. The name_hint is converted to a "--format" option as before, and passed to the remote. This means the local side's idea of how extensions map to formats will take precedence. Another option would be to pass the name hint to the remote side and let the remote choose. This isn't a good idea for two reasons: 1. There's no room in the protocol for passing that information. We can pass a new argument, but older versions of git on the server will choke on it. 2. Letting the remote side decide creates a silent inconsistency in user experience. Consider the case that the locally installed git knows about the "tar.gz" format, but a remote server doesn't. Running "git archive -o foo.tar.gz" will use the tar.gz format. If we use --remote, and the local side chooses the format, then we send "--format=tar.gz" to the remote, which will complain about the unknown format. But if we let the remote side choose the format, then it will realize that it doesn't know about "tar.gz" and output uncompressed tar without even issuing a warning. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-22 03:24:48 +02:00
const struct archiver **ar, struct archiver_args *args,
const char *name_hint, int is_remote)
{
archive: move file extension format-guessing lower The process for guessing an archive output format based on the filename is something like this: a. parse --output in cmd_archive; check the filename against a static set of mapping heuristics (right now it just matches ".zip" for zip files). b. if found, stick a fake "--format=zip" at the beginning of the arguments list (if the user did specify a --format manually, the later option will override our fake one) c. if it's a remote call, ship the arguments to the remote (including the fake), which will call write_archive on their end d. if it's local, ship the arguments to write_archive locally There are two problems: 1. The set of mappings is static and at too high a level. The write_archive level is going to check config for user-defined formats, some of which will specify extensions. We need to delay lookup until those are parsed, so we can match against them. 2. For a remote archive call, our set of mappings (or formats) may not match the remote side's. This is OK in practice right now, because all versions of git understand "zip" and "tar". But as new formats are added, there is going to be a mismatch between what the client can do and what the remote server can do. To fix (1), this patch refactors the location guessing to happen at the write_archive level, instead of the cmd_archive level. So instead of sticking a fake --format field in the argv list, we actually pass a "name hint" down the callchain; this hint is used at the appropriate time to guess the format (if one hasn't been given already). This patch leaves (2) unfixed. The name_hint is converted to a "--format" option as before, and passed to the remote. This means the local side's idea of how extensions map to formats will take precedence. Another option would be to pass the name hint to the remote side and let the remote choose. This isn't a good idea for two reasons: 1. There's no room in the protocol for passing that information. We can pass a new argument, but older versions of git on the server will choke on it. 2. Letting the remote side decide creates a silent inconsistency in user experience. Consider the case that the locally installed git knows about the "tar.gz" format, but a remote server doesn't. Running "git archive -o foo.tar.gz" will use the tar.gz format. If we use --remote, and the local side chooses the format, then we send "--format=tar.gz" to the remote, which will complain about the unknown format. But if we let the remote side choose the format, then it will realize that it doesn't know about "tar.gz" and output uncompressed tar without even issuing a warning. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-22 03:24:48 +02:00
const char *format = NULL;
const char *base = NULL;
const char *remote = NULL;
const char *exec = NULL;
const char *output = NULL;
int compression_level = -1;
int verbose = 0;
int i;
int list = 0;
int worktree_attributes = 0;
struct option opts[] = {
OPT_GROUP(""),
OPT_STRING(0, "format", &format, N_("fmt"), N_("archive format")),
OPT_STRING(0, "prefix", &base, N_("prefix"),
N_("prepend prefix to each pathname in the archive")),
OPT_STRING('o', "output", &output, N_("file"),
N_("write the archive to this file")),
OPT_BOOL(0, "worktree-attributes", &worktree_attributes,
N_("read .gitattributes in working directory")),
OPT__VERBOSE(&verbose, N_("report archived files on stderr")),
OPT__COMPR('0', &compression_level, N_("store only"), 0),
OPT__COMPR('1', &compression_level, N_("compress faster"), 1),
OPT__COMPR_HIDDEN('2', &compression_level, 2),
OPT__COMPR_HIDDEN('3', &compression_level, 3),
OPT__COMPR_HIDDEN('4', &compression_level, 4),
OPT__COMPR_HIDDEN('5', &compression_level, 5),
OPT__COMPR_HIDDEN('6', &compression_level, 6),
OPT__COMPR_HIDDEN('7', &compression_level, 7),
OPT__COMPR_HIDDEN('8', &compression_level, 8),
OPT__COMPR('9', &compression_level, N_("compress better"), 9),
OPT_GROUP(""),
OPT_BOOL('l', "list", &list,
N_("list supported archive formats")),
OPT_GROUP(""),
OPT_STRING(0, "remote", &remote, N_("repo"),
N_("retrieve the archive from remote repository <repo>")),
OPT_STRING(0, "exec", &exec, N_("command"),
N_("path to the remote git-upload-archive command")),
OPT_END()
};
argc = parse_options(argc, argv, NULL, opts, archive_usage, 0);
if (remote)
die(_("Unexpected option --remote"));
if (exec)
die(_("Option --exec can only be used together with --remote"));
if (output)
die(_("Unexpected option --output"));
if (!base)
base = "";
if (list) {
for (i = 0; i < nr_archivers; i++)
if (!is_remote || archivers[i]->flags & ARCHIVER_REMOTE)
printf("%s\n", archivers[i]->name);
exit(0);
}
archive: move file extension format-guessing lower The process for guessing an archive output format based on the filename is something like this: a. parse --output in cmd_archive; check the filename against a static set of mapping heuristics (right now it just matches ".zip" for zip files). b. if found, stick a fake "--format=zip" at the beginning of the arguments list (if the user did specify a --format manually, the later option will override our fake one) c. if it's a remote call, ship the arguments to the remote (including the fake), which will call write_archive on their end d. if it's local, ship the arguments to write_archive locally There are two problems: 1. The set of mappings is static and at too high a level. The write_archive level is going to check config for user-defined formats, some of which will specify extensions. We need to delay lookup until those are parsed, so we can match against them. 2. For a remote archive call, our set of mappings (or formats) may not match the remote side's. This is OK in practice right now, because all versions of git understand "zip" and "tar". But as new formats are added, there is going to be a mismatch between what the client can do and what the remote server can do. To fix (1), this patch refactors the location guessing to happen at the write_archive level, instead of the cmd_archive level. So instead of sticking a fake --format field in the argv list, we actually pass a "name hint" down the callchain; this hint is used at the appropriate time to guess the format (if one hasn't been given already). This patch leaves (2) unfixed. The name_hint is converted to a "--format" option as before, and passed to the remote. This means the local side's idea of how extensions map to formats will take precedence. Another option would be to pass the name hint to the remote side and let the remote choose. This isn't a good idea for two reasons: 1. There's no room in the protocol for passing that information. We can pass a new argument, but older versions of git on the server will choke on it. 2. Letting the remote side decide creates a silent inconsistency in user experience. Consider the case that the locally installed git knows about the "tar.gz" format, but a remote server doesn't. Running "git archive -o foo.tar.gz" will use the tar.gz format. If we use --remote, and the local side chooses the format, then we send "--format=tar.gz" to the remote, which will complain about the unknown format. But if we let the remote side choose the format, then it will realize that it doesn't know about "tar.gz" and output uncompressed tar without even issuing a warning. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-22 03:24:48 +02:00
if (!format && name_hint)
format = archive_format_from_filename(name_hint);
if (!format)
format = "tar";
/* We need at least one parameter -- tree-ish */
if (argc < 1)
usage_with_options(archive_usage, opts);
*ar = lookup_archiver(format);
if (!*ar || (is_remote && !((*ar)->flags & ARCHIVER_REMOTE)))
die(_("Unknown archive format '%s'"), format);
args->compression_level = Z_DEFAULT_COMPRESSION;
if (compression_level != -1) {
if ((*ar)->flags & ARCHIVER_WANT_COMPRESSION_LEVELS)
args->compression_level = compression_level;
else {
die(_("Argument not supported for format '%s': -%d"),
format, compression_level);
}
}
args->verbose = verbose;
args->base = base;
args->baselen = strlen(base);
args->worktree_attributes = worktree_attributes;
return argc;
}
int write_archive(int argc, const char **argv, const char *prefix,
const char *name_hint, int remote)
{
const struct archiver *ar = NULL;
struct archiver_args args;
git_config_get_bool("uploadarchive.allowunreachable", &remote_allow_unreachable);
git_config(git_default_config, NULL);
init_tar_archiver();
init_zip_archiver();
argc = parse_archive_args(argc, argv, &ar, &args, name_hint, remote);
if (!startup_info->have_repository) {
/*
* We know this will die() with an error, so we could just
* die ourselves; but its error message will be more specific
* than what we could write here.
*/
setup_git_directory();
}
parse_treeish_arg(argv, &args, prefix, remote);
parse_pathspec_arg(argv + 1, &args);
return ar->write_archive(ar, &args);
}
archive: move file extension format-guessing lower The process for guessing an archive output format based on the filename is something like this: a. parse --output in cmd_archive; check the filename against a static set of mapping heuristics (right now it just matches ".zip" for zip files). b. if found, stick a fake "--format=zip" at the beginning of the arguments list (if the user did specify a --format manually, the later option will override our fake one) c. if it's a remote call, ship the arguments to the remote (including the fake), which will call write_archive on their end d. if it's local, ship the arguments to write_archive locally There are two problems: 1. The set of mappings is static and at too high a level. The write_archive level is going to check config for user-defined formats, some of which will specify extensions. We need to delay lookup until those are parsed, so we can match against them. 2. For a remote archive call, our set of mappings (or formats) may not match the remote side's. This is OK in practice right now, because all versions of git understand "zip" and "tar". But as new formats are added, there is going to be a mismatch between what the client can do and what the remote server can do. To fix (1), this patch refactors the location guessing to happen at the write_archive level, instead of the cmd_archive level. So instead of sticking a fake --format field in the argv list, we actually pass a "name hint" down the callchain; this hint is used at the appropriate time to guess the format (if one hasn't been given already). This patch leaves (2) unfixed. The name_hint is converted to a "--format" option as before, and passed to the remote. This means the local side's idea of how extensions map to formats will take precedence. Another option would be to pass the name hint to the remote side and let the remote choose. This isn't a good idea for two reasons: 1. There's no room in the protocol for passing that information. We can pass a new argument, but older versions of git on the server will choke on it. 2. Letting the remote side decide creates a silent inconsistency in user experience. Consider the case that the locally installed git knows about the "tar.gz" format, but a remote server doesn't. Running "git archive -o foo.tar.gz" will use the tar.gz format. If we use --remote, and the local side chooses the format, then we send "--format=tar.gz" to the remote, which will complain about the unknown format. But if we let the remote side choose the format, then it will realize that it doesn't know about "tar.gz" and output uncompressed tar without even issuing a warning. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-22 03:24:48 +02:00
static int match_extension(const char *filename, const char *ext)
{
int prefixlen = strlen(filename) - strlen(ext);
/*
* We need 1 character for the '.', and 1 character to ensure that the
* prefix is non-empty (k.e., we don't match .tar.gz with no actual
* filename).
*/
if (prefixlen < 2 || filename[prefixlen - 1] != '.')
return 0;
return !strcmp(filename + prefixlen, ext);
}
archive: move file extension format-guessing lower The process for guessing an archive output format based on the filename is something like this: a. parse --output in cmd_archive; check the filename against a static set of mapping heuristics (right now it just matches ".zip" for zip files). b. if found, stick a fake "--format=zip" at the beginning of the arguments list (if the user did specify a --format manually, the later option will override our fake one) c. if it's a remote call, ship the arguments to the remote (including the fake), which will call write_archive on their end d. if it's local, ship the arguments to write_archive locally There are two problems: 1. The set of mappings is static and at too high a level. The write_archive level is going to check config for user-defined formats, some of which will specify extensions. We need to delay lookup until those are parsed, so we can match against them. 2. For a remote archive call, our set of mappings (or formats) may not match the remote side's. This is OK in practice right now, because all versions of git understand "zip" and "tar". But as new formats are added, there is going to be a mismatch between what the client can do and what the remote server can do. To fix (1), this patch refactors the location guessing to happen at the write_archive level, instead of the cmd_archive level. So instead of sticking a fake --format field in the argv list, we actually pass a "name hint" down the callchain; this hint is used at the appropriate time to guess the format (if one hasn't been given already). This patch leaves (2) unfixed. The name_hint is converted to a "--format" option as before, and passed to the remote. This means the local side's idea of how extensions map to formats will take precedence. Another option would be to pass the name hint to the remote side and let the remote choose. This isn't a good idea for two reasons: 1. There's no room in the protocol for passing that information. We can pass a new argument, but older versions of git on the server will choke on it. 2. Letting the remote side decide creates a silent inconsistency in user experience. Consider the case that the locally installed git knows about the "tar.gz" format, but a remote server doesn't. Running "git archive -o foo.tar.gz" will use the tar.gz format. If we use --remote, and the local side chooses the format, then we send "--format=tar.gz" to the remote, which will complain about the unknown format. But if we let the remote side choose the format, then it will realize that it doesn't know about "tar.gz" and output uncompressed tar without even issuing a warning. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-22 03:24:48 +02:00
const char *archive_format_from_filename(const char *filename)
{
int i;
for (i = 0; i < nr_archivers; i++)
if (match_extension(filename, archivers[i]->name))
return archivers[i]->name;
archive: move file extension format-guessing lower The process for guessing an archive output format based on the filename is something like this: a. parse --output in cmd_archive; check the filename against a static set of mapping heuristics (right now it just matches ".zip" for zip files). b. if found, stick a fake "--format=zip" at the beginning of the arguments list (if the user did specify a --format manually, the later option will override our fake one) c. if it's a remote call, ship the arguments to the remote (including the fake), which will call write_archive on their end d. if it's local, ship the arguments to write_archive locally There are two problems: 1. The set of mappings is static and at too high a level. The write_archive level is going to check config for user-defined formats, some of which will specify extensions. We need to delay lookup until those are parsed, so we can match against them. 2. For a remote archive call, our set of mappings (or formats) may not match the remote side's. This is OK in practice right now, because all versions of git understand "zip" and "tar". But as new formats are added, there is going to be a mismatch between what the client can do and what the remote server can do. To fix (1), this patch refactors the location guessing to happen at the write_archive level, instead of the cmd_archive level. So instead of sticking a fake --format field in the argv list, we actually pass a "name hint" down the callchain; this hint is used at the appropriate time to guess the format (if one hasn't been given already). This patch leaves (2) unfixed. The name_hint is converted to a "--format" option as before, and passed to the remote. This means the local side's idea of how extensions map to formats will take precedence. Another option would be to pass the name hint to the remote side and let the remote choose. This isn't a good idea for two reasons: 1. There's no room in the protocol for passing that information. We can pass a new argument, but older versions of git on the server will choke on it. 2. Letting the remote side decide creates a silent inconsistency in user experience. Consider the case that the locally installed git knows about the "tar.gz" format, but a remote server doesn't. Running "git archive -o foo.tar.gz" will use the tar.gz format. If we use --remote, and the local side chooses the format, then we send "--format=tar.gz" to the remote, which will complain about the unknown format. But if we let the remote side choose the format, then it will realize that it doesn't know about "tar.gz" and output uncompressed tar without even issuing a warning. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-06-22 03:24:48 +02:00
return NULL;
}