-#include "cache.h"
+#include "builtin.h"
#include "delta.h"
#include "pack.h"
#include "csum-file.h"
#include "exec_cmd.h"
static const char index_pack_usage[] =
- "git index-pack [-v] [-o <index-file>] [
--keep | --keep=<msg> ] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
+ "git index-pack [-v] [-o <index-file>] [
--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
-struct object_entry
-{
+struct object_entry {
struct pack_idx_entry idx;
unsigned long size;
unsigned int hdr_size;
enum object_type type;
enum object_type real_type;
+ unsigned delta_depth;
+ int base_object_no;
};
union delta_base {
#define FLAG_LINK (1u<<20)
#define FLAG_CHECKED (1u<<21)
-struct delta_entry
-{
+struct delta_entry {
union delta_base base;
int obj_no;
};
static unsigned char input_buffer[4096];
static unsigned int input_offset, input_len;
static off_t consumed_bytes;
+ static unsigned deepest_delta;
static git_SHA_CTX input_ctx;
static uint32_t input_crc32;
static int input_fd, output_fd, pack_fd;
static NORETURN void bad_object(unsigned long offset, const char *format,
...) __attribute__((format (printf, 2, 3)));
-static void bad_object(unsigned long offset, const char *format, ...)
+static NORETURN void bad_object(unsigned long offset, const char *format, ...)
{
va_list params;
char buf[1024];
static void *unpack_entry_data(unsigned long offset, unsigned long size)
{
int status;
- z_stream stream;
+ git_zstream stream;
void *buf = xmalloc(size);
memset(&stream, 0, sizeof(stream));
void *data;
obj->idx.offset = consumed_bytes;
- input_crc32 = crc32(0, Z_NULL, 0);
+ input_crc32 = crc32(0, NULL, 0);
p = fill(1);
c = *p;
off_t from = obj[0].idx.offset + obj[0].hdr_size;
unsigned long len = obj[1].idx.offset - from;
unsigned char *data, *inbuf;
- z_stream stream;
+ git_zstream stream;
int status;
data = xmalloc(obj->size);
return data;
}
- static int find_delta(const union delta_base *base)
+ static int compare_delta_bases(const union delta_base *base1,
+ const union delta_base *base2,
+ enum object_type type1,
+ enum object_type type2)
+ {
+ int cmp = type1 - type2;
+ if (cmp)
+ return cmp;
+ return memcmp(base1, base2, UNION_BASE_SZ);
+ }
+
+ static int find_delta(const union delta_base *base, enum object_type type)
{
int first = 0, last = nr_deltas;
struct delta_entry *delta = &deltas[next];
int cmp;
- cmp = memcmp(base, &delta->base, UNION_BASE_SZ);
+ cmp = compare_delta_bases(base, &delta->base,
+ type, objects[delta->obj_no].type);
if (!cmp)
return next;
if (cmp < 0) {
}
static void find_delta_children(const union delta_base *base,
- int *first_index, int *last_index)
+ int *first_index, int *last_index,
+ enum object_type type)
{
- int first = find_delta(base);
+ int first = find_delta(base, type);
int last = first;
int end = nr_deltas - 1;
}
}
+ static int is_delta_type(enum object_type type)
+ {
+ return (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA);
+ }
+
static void *get_base_data(struct base_data *c)
{
if (!c->data) {
struct object_entry *obj = c->obj;
- if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
+ if (is_delta_type(obj->type)) {
void *base = get_base_data(c->base);
void *raw = get_data_from_pack(obj);
c->data = patch_delta(
void *base_data, *delta_data;
delta_obj->real_type = base->obj->real_type;
+ delta_obj->delta_depth = base->obj->delta_depth + 1;
+ if (deepest_delta < delta_obj->delta_depth)
+ deepest_delta = delta_obj->delta_depth;
+ delta_obj->base_object_no = base->obj - objects;
delta_data = get_data_from_pack(delta_obj);
base_data = get_base_data(base);
result->obj = delta_obj;
union delta_base base_spec;
hashcpy(base_spec.sha1, base->obj->idx.sha1);
- find_delta_children(&base_spec, &ref_first, &ref_last);
+ find_delta_children(&base_spec,
+ &ref_first, &ref_last, OBJ_REF_DELTA);
memset(&base_spec, 0, sizeof(base_spec));
base_spec.offset = base->obj->idx.offset;
- find_delta_children(&base_spec, &ofs_first, &ofs_last);
+ find_delta_children(&base_spec,
+ &ofs_first, &ofs_last, OBJ_OFS_DELTA);
}
if (ref_last == -1 && ofs_last == -1) {
for (i = ref_first; i <= ref_last; i++) {
struct object_entry *child = objects + deltas[i].obj_no;
- if (child->real_type == OBJ_REF_DELTA) {
- struct base_data result;
- resolve_delta(child, base, &result);
- if (i == ref_last && ofs_last == -1)
- free_base_data(base);
- find_unresolved_deltas(&result, base);
- }
+ struct base_data result;
+
+ assert(child->real_type == OBJ_REF_DELTA);
+ resolve_delta(child, base, &result);
+ if (i == ref_last && ofs_last == -1)
+ free_base_data(base);
+ find_unresolved_deltas(&result, base);
}
for (i = ofs_first; i <= ofs_last; i++) {
struct object_entry *child = objects + deltas[i].obj_no;
- if (child->real_type == OBJ_OFS_DELTA) {
- struct base_data result;
- resolve_delta(child, base, &result);
- if (i == ofs_last)
- free_base_data(base);
- find_unresolved_deltas(&result, base);
- }
+ struct base_data result;
+
+ assert(child->real_type == OBJ_OFS_DELTA);
+ resolve_delta(child, base, &result);
+ if (i == ofs_last)
+ free_base_data(base);
+ find_unresolved_deltas(&result, base);
}
unlink_base_data(base);
{
const struct delta_entry *delta_a = a;
const struct delta_entry *delta_b = b;
- return memcmp(&delta_a->base, &delta_b->base, UNION_BASE_SZ);
+
+ /* group by type (ref vs ofs) and then by value (sha-1 or offset) */
+ return compare_delta_bases(&delta_a->base, &delta_b->base,
+ objects[delta_a->obj_no].type,
+ objects[delta_b->obj_no].type);
}
/* Parse all objects and return the pack content SHA1 hash */
struct object_entry *obj = &objects[i];
void *data = unpack_raw_entry(obj, &delta->base);
obj->real_type = obj->type;
- if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
+ if (is_delta_type(obj->type)) {
nr_deltas++;
delta->obj_no = i;
delta++;
struct object_entry *obj = &objects[i];
struct base_data base_obj;
- if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
+ if (is_delta_type(obj->type))
continue;
base_obj.obj = obj;
base_obj.data = NULL;
static int write_compressed(struct sha1file *f, void *in, unsigned int size)
{
- z_stream stream;
+ git_zstream stream;
int status;
unsigned char outbuf[4096];
memset(&stream, 0, sizeof(stream));
- deflateInit(&stream, zlib_compression_level);
+ git_deflate_init(&stream, zlib_compression_level);
stream.next_in = in;
stream.avail_in = size;
do {
stream.next_out = outbuf;
stream.avail_out = sizeof(outbuf);
- status = deflate(&stream, Z_FINISH);
+ status = git_deflate(&stream, Z_FINISH);
sha1write(f, outbuf, sizeof(outbuf) - stream.avail_out);
} while (status == Z_OK);
if (status != Z_STREAM_END)
die("unable to deflate appended object (%d)", status);
size = stream.total_out;
- deflateEnd(&stream);
+ git_deflate_end(&stream);
return size;
}
static int git_index_pack_config(const char *k, const char *v, void *cb)
{
+ struct pack_idx_option *opts = cb;
+
if (!strcmp(k, "pack.indexversion")) {
- pack_idx_default_version = git_config_int(k, v);
- if (pack_idx_default_version > 2)
- die("bad pack.indexversion=%"PRIu32,
- pack_idx_default_version);
+ opts->version = git_config_int(k, v);
+ if (opts->version > 2)
+ die("bad pack.indexversion=%"PRIu32, opts->version);
return 0;
}
return git_default_config(k, v, cb);
}
+ static int cmp_uint32(const void *a_, const void *b_)
+ {
+ uint32_t a = *((uint32_t *)a_);
+ uint32_t b = *((uint32_t *)b_);
+
+ return (a < b) ? -1 : (a != b);
+ }
+
+ static void read_v2_anomalous_offsets(struct packed_git *p,
+ struct pack_idx_option *opts)
+ {
+ const uint32_t *idx1, *idx2;
+ uint32_t i;
+
+ /* The address of the 4-byte offset table */
+ idx1 = (((const uint32_t *)p->index_data)
+ + 2 /* 8-byte header */
+ + 256 /* fan out */
+ + 5 * p->num_objects /* 20-byte SHA-1 table */
+ + p->num_objects /* CRC32 table */
+ );
+
+ /* The address of the 8-byte offset table */
+ idx2 = idx1 + p->num_objects;
+
+ for (i = 0; i < p->num_objects; i++) {
+ uint32_t off = ntohl(idx1[i]);
+ if (!(off & 0x80000000))
+ continue;
+ off = off & 0x7fffffff;
+ if (idx2[off * 2])
+ continue;
+ /*
+ * The real offset is ntohl(idx2[off * 2]) in high 4
+ * octets, and ntohl(idx2[off * 2 + 1]) in low 4
+ * octets. But idx2[off * 2] is Zero!!!
+ */
+ ALLOC_GROW(opts->anomaly, opts->anomaly_nr + 1, opts->anomaly_alloc);
+ opts->anomaly[opts->anomaly_nr++] = ntohl(idx2[off * 2 + 1]);
+ }
+
+ if (1 < opts->anomaly_nr)
+ qsort(opts->anomaly, opts->anomaly_nr, sizeof(uint32_t), cmp_uint32);
+ }
+
+ static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)
+ {
+ struct packed_git *p = add_packed_git(pack_name, strlen(pack_name), 1);
+
+ if (!p)
+ die("Cannot open existing pack file '%s'", pack_name);
+ if (open_pack_index(p))
+ die("Cannot open existing pack idx file for '%s'", pack_name);
+
+ /* Read the attributes from the existing idx file */
+ opts->version = p->index_version;
+
+ if (opts->version == 2)
+ read_v2_anomalous_offsets(p, opts);
+
+ /*
+ * Get rid of the idx file as we do not need it anymore.
+ * NEEDSWORK: extract this bit from free_pack_by_name() in
+ * sha1_file.c, perhaps? It shouldn't matter very much as we
+ * know we haven't installed this pack (hence we never have
+ * read anything from it).
+ */
+ close_pack_index(p);
+ free(p);
+ }
+
+ static void show_pack_info(int stat_only)
+ {
+ int i, baseobjects = nr_objects - nr_deltas;
+ unsigned long *chain_histogram = NULL;
+
+ if (deepest_delta)
+ chain_histogram = xcalloc(deepest_delta, sizeof(unsigned long));
+
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *obj = &objects[i];
+
+ if (is_delta_type(obj->type))
+ chain_histogram[obj->delta_depth - 1]++;
+ if (stat_only)
+ continue;
+ printf("%s %-6s %lu %lu %"PRIuMAX,
+ sha1_to_hex(obj->idx.sha1),
+ typename(obj->real_type), obj->size,
+ (unsigned long)(obj[1].idx.offset - obj->idx.offset),
+ (uintmax_t)obj->idx.offset);
+ if (is_delta_type(obj->type)) {
+ struct object_entry *bobj = &objects[obj->base_object_no];
+ printf(" %u %s", obj->delta_depth, sha1_to_hex(bobj->idx.sha1));
+ }
+ putchar('\n');
+ }
+
+ if (baseobjects)
+ printf("non delta: %d object%s\n",
+ baseobjects, baseobjects > 1 ? "s" : "");
+ for (i = 0; i < deepest_delta; i++) {
+ if (!chain_histogram[i])
+ continue;
+ printf("chain length = %d: %lu object%s\n",
+ i + 1,
+ chain_histogram[i],
+ chain_histogram[i] > 1 ? "s" : "");
+ }
+ }
+
int cmd_index_pack(int argc, const char **argv, const char *prefix)
{
- int i, fix_thin_pack = 0;
+ int i, fix_thin_pack = 0, verify = 0, stat_only = 0, stat = 0;
const char *curr_pack, *curr_index;
const char *index_name = NULL, *pack_name = NULL;
const char *keep_name = NULL, *keep_msg = NULL;
char *index_name_buf = NULL, *keep_name_buf = NULL;
struct pack_idx_entry **idx_objects;
+ struct pack_idx_option opts;
unsigned char pack_sha1[20];
if (argc == 2 && !strcmp(argv[1], "-h"))
read_replace_refs = 0;
- git_config(git_index_pack_config, NULL);
+ reset_pack_idx_option(&opts);
+ git_config(git_index_pack_config, &opts);
if (prefix && chdir(prefix))
die("Cannot come back to cwd");
fix_thin_pack = 1;
} else if (!strcmp(arg, "--strict")) {
strict = 1;
+ } else if (!strcmp(arg, "--verify")) {
+ verify = 1;
+ } else if (!strcmp(arg, "--verify-stat")) {
+ verify = 1;
+ stat = 1;
+ } else if (!strcmp(arg, "--verify-stat-only")) {
+ verify = 1;
+ stat = 1;
+ stat_only = 1;
} else if (!strcmp(arg, "--keep")) {
keep_msg = "";
} else if (!prefixcmp(arg, "--keep=")) {
index_name = argv[++i];
} else if (!prefixcmp(arg, "--index-version=")) {
char *c;
- pack_idx_default_version = strtoul(arg + 16, &c, 10);
- if (pack_idx_default_version > 2)
+ opts.version = strtoul(arg + 16, &c, 10);
+ if (opts.version > 2)
die("bad %s", arg);
if (*c == ',')
- pack_idx_off32_limit = strtoul(c+1, &c, 0);
- if (*c || pack_idx_off32_limit & 0x80000000)
+ opts.off32_limit = strtoul(c+1, &c, 0);
+ if (*c || opts.off32_limit & 0x80000000)
die("bad %s", arg);
} else
usage(index_pack_usage);
strcpy(keep_name_buf + len - 5, ".keep");
keep_name = keep_name_buf;
}
+ if (verify) {
+ if (!index_name)
+ die("--verify with no packfile name given");
+ read_idx_option(&opts, index_name);
+ opts.flags |= WRITE_IDX_VERIFY;
+ }
curr_pack = open_pack_file(pack_name);
parse_pack_header();
- objects = xmalloc((nr_objects + 1) * sizeof(struct object_entry));
- deltas = xmalloc(nr_objects * sizeof(struct delta_entry));
+ objects = xcalloc(nr_objects + 1, sizeof(struct object_entry));
+ deltas = xcalloc(nr_objects, sizeof(struct delta_entry));
parse_pack_objects(pack_sha1);
if (nr_deltas == nr_resolved_deltas) {
stop_progress(&progress);
if (strict)
check_objects();
+ if (stat)
+ show_pack_info(stat_only);
+
idx_objects = xmalloc((nr_objects) * sizeof(struct pack_idx_entry *));
for (i = 0; i < nr_objects; i++)
idx_objects[i] = &objects[i].idx;
- curr_index = write_idx_file(index_name, idx_objects, nr_objects, pack_sha1);
+ curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_sha1);
free(idx_objects);
- final(pack_name, curr_pack,
- index_name, curr_index,
- keep_name, keep_msg,
- pack_sha1);
+ if (!verify)
+ final(pack_name, curr_pack,
+ index_name, curr_index,
+ keep_name, keep_msg,
+ pack_sha1);
+ else
+ close(input_fd);
free(objects);
free(index_name_buf);
free(keep_name_buf);
static int incremental;
static int ignore_packed_keep;
static int allow_ofs_delta;
+ static struct pack_idx_option pack_idx_opts;
static const char *base_name;
static int progress = 1;
static int window = 10;
static unsigned long do_compress(void **pptr, unsigned long size)
{
- z_stream stream;
+ git_zstream stream;
void *in, *out;
unsigned long maxsize;
memset(&stream, 0, sizeof(stream));
- deflateInit(&stream, pack_compression_level);
- maxsize = deflateBound(&stream, size);
+ git_deflate_init(&stream, pack_compression_level);
+ maxsize = git_deflate_bound(&stream, size);
in = *pptr;
out = xmalloc(maxsize);
stream.avail_in = size;
stream.next_out = out;
stream.avail_out = maxsize;
- while (deflate(&stream, Z_FINISH) == Z_OK)
+ while (git_deflate(&stream, Z_FINISH) == Z_OK)
; /* nothing */
- deflateEnd(&stream);
+ git_deflate_end(&stream);
free(in);
return stream.total_out;
off_t len,
unsigned long expect)
{
- z_stream stream;
+ git_zstream stream;
unsigned char fakebuf[4096], *in;
int st;
off_t len)
{
unsigned char *in;
- unsigned int avail;
+ unsigned long avail;
while (len) {
in = use_pack(p, w_curs, offset, &avail);
if (avail > len)
- avail = (unsigned int)len;
+ avail = (unsigned long)len;
sha1write(f, in, avail);
offset += avail;
len -= avail;
const char *idx_tmp_name;
char tmpname[PATH_MAX];
- idx_tmp_name = write_idx_file(NULL, written_list,
- nr_written, sha1);
+ idx_tmp_name = write_idx_file(NULL, written_list, nr_written,
+ &pack_idx_opts, sha1);
snprintf(tmpname, sizeof(tmpname), "%s-%s.pack",
base_name, sha1_to_hex(sha1));
const unsigned char *base_ref = NULL;
struct object_entry *base_entry;
unsigned long used, used_0;
- unsigned int avail;
+ unsigned long avail;
off_t ofs;
unsigned char *buf, c;
sorted_by_offset[i] = objects + i;
qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort);
- for (i = 0; i < nr_objects; i++)
- check_object(sorted_by_offset[i]);
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *entry = sorted_by_offset[i];
+ check_object(entry);
+ if (big_file_threshold <= entry->size)
+ entry->no_try_delta = 1;
+ }
free(sorted_by_offset);
}
return 0;
}
if (!strcmp(k, "pack.indexversion")) {
- pack_idx_default_version = git_config_int(k, v);
- if (pack_idx_default_version > 2)
+ pack_idx_opts.version = git_config_int(k, v);
+ if (pack_idx_opts.version > 2)
die("bad pack.indexversion=%"PRIu32,
- pack_idx_default_version);
+ pack_idx_opts.version);
return 0;
}
if (!strcmp(k, "pack.packsizelimit")) {
rp_av[1] = "--objects"; /* --thin will make it --objects-edge */
rp_ac = 2;
+ reset_pack_idx_option(&pack_idx_opts);
git_config(git_pack_config, NULL);
if (!pack_compression_seen && core_compression_seen)
pack_compression_level = core_compression_level;
}
if (!prefixcmp(arg, "--index-version=")) {
char *c;
- pack_idx_default_version = strtoul(arg + 16, &c, 10);
- if (pack_idx_default_version > 2)
+ pack_idx_opts.version = strtoul(arg + 16, &c, 10);
+ if (pack_idx_opts.version > 2)
die("bad %s", arg);
if (*c == ',')
- pack_idx_off32_limit = strtoul(c+1, &c, 0);
- if (*c || pack_idx_off32_limit & 0x80000000)
+ pack_idx_opts.off32_limit = strtoul(c+1, &c, 0);
+ if (*c || pack_idx_opts.off32_limit & 0x80000000)
die("bad %s", arg);
continue;
}
#include "strbuf.h"
#include "hash.h"
#include "advice.h"
+#include "gettext.h"
+#include "convert.h"
#include SHA1_HEADER
#ifndef git_SHA_CTX
#endif
#include <zlib.h>
-#if defined(NO_DEFLATE_BOUND) || ZLIB_VERNUM < 0x1200
-#define deflateBound(c,s) ((s) + (((s) + 7) >> 3) + (((s) + 63) >> 6) + 11)
-#endif
-
-void git_inflate_init(z_streamp strm);
-void git_inflate_end(z_streamp strm);
-int git_inflate(z_streamp strm, int flush);
+typedef struct git_zstream {
+ z_stream z;
+ unsigned long avail_in;
+ unsigned long avail_out;
+ unsigned long total_in;
+ unsigned long total_out;
+ unsigned char *next_in;
+ unsigned char *next_out;
+} git_zstream;
+
+void git_inflate_init(git_zstream *);
+void git_inflate_init_gzip_only(git_zstream *);
+void git_inflate_end(git_zstream *);
+int git_inflate(git_zstream *, int flush);
+
+void git_deflate_init(git_zstream *, int level);
+void git_deflate_init_gzip(git_zstream *, int level);
+void git_deflate_end(git_zstream *);
+int git_deflate_end_gently(git_zstream *);
+int git_deflate(git_zstream *, int flush);
+unsigned long git_deflate_bound(git_zstream *, unsigned long);
#if defined(DT_UNKNOWN) && !defined(NO_D_TYPE_IN_DIRENT)
#define DTYPE(de) ((de)->d_type)
#define INIT_DB_QUIET 0x0001
+extern int set_git_dir_init(const char *git_dir, const char *real_git_dir, int);
extern int init_db(const char *template_dir, unsigned int flags);
#define alloc_nr(x) (((x)+16)*3/2)
struct pathspec {
const char **raw; /* get_pathspec() result, not freed by free_pathspec() */
int nr;
- int has_wildcard:1;
- int recursive:1;
+ unsigned int has_wildcard:1;
+ unsigned int recursive:1;
int max_depth;
struct pathspec_item {
const char *match;
int len;
- int has_wildcard:1;
+ unsigned int use_wildcard:1;
} *items;
};
extern int init_pathspec(struct pathspec *, const char **);
extern void free_pathspec(struct pathspec *);
extern int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec);
-extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, enum object_type type, const char *path, int format_check);
-extern int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object);
+
+#define HASH_WRITE_OBJECT 1
+#define HASH_FORMAT_CHECK 2
+extern int index_fd(unsigned char *sha1, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags);
+extern int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags);
extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st);
#define REFRESH_REALLY 0x0001 /* ignore_valid */
extern int hold_lock_file_for_update(struct lock_file *, const char *path, int);
extern int hold_lock_file_for_append(struct lock_file *, const char *path, int);
extern int commit_lock_file(struct lock_file *);
+extern void update_index_if_able(struct index_state *, struct lock_file *);
extern int hold_locked_index(struct lock_file *, int);
extern int commit_locked_index(struct lock_file *);
extern int trust_ctime;
extern int quote_path_fully;
extern int has_symlinks;
+extern int minimum_abbrev, default_abbrev;
extern int ignore_case;
extern int assume_unchanged;
extern int prefer_symlink_refs;
extern int log_all_ref_updates;
extern int warn_ambiguous_refs;
-extern int unique_abbrev_extra_length;
extern int shared_repository;
extern const char *apply_default_whitespace;
extern const char *apply_default_ignorewhitespace;
extern size_t packed_git_window_size;
extern size_t packed_git_limit;
extern size_t delta_base_cache_limit;
+extern unsigned long big_file_threshold;
extern int read_replace_refs;
extern int fsync_object_files;
extern int core_preload_index;
extern int core_apply_sparse_checkout;
-enum safe_crlf {
- SAFE_CRLF_FALSE = 0,
- SAFE_CRLF_FAIL = 1,
- SAFE_CRLF_WARN = 2
-};
-
-extern enum safe_crlf safe_crlf;
-
-enum auto_crlf {
- AUTO_CRLF_FALSE = 0,
- AUTO_CRLF_TRUE = 1,
- AUTO_CRLF_INPUT = -1,
-};
-
-extern enum auto_crlf auto_crlf;
-
-enum eol {
- EOL_UNSET,
- EOL_CRLF,
- EOL_LF,
-#ifdef NATIVE_CRLF
- EOL_NATIVE = EOL_CRLF
-#else
- EOL_NATIVE = EOL_LF
-#endif
-};
-
-extern enum eol eol;
-
enum branch_track {
BRANCH_TRACK_UNSPECIFIED = -1,
BRANCH_TRACK_NEVER = 0,
extern char *sha1_pack_index_name(const unsigned char *sha1);
extern const char *find_unique_abbrev(const unsigned char *sha1, int);
extern const unsigned char null_sha1[20];
-static inline int is_null_sha1(const unsigned char *sha1)
+
+static inline int hashcmp(const unsigned char *sha1, const unsigned char *sha2)
{
- return !memcmp(sha1, null_sha1, 20);
+ int i;
+
+ for (i = 0; i < 20; i++, sha1++, sha2++) {
+ if (*sha1 != *sha2)
+ return *sha1 - *sha2;
+ }
+
+ return 0;
}
-static inline int hashcmp(const unsigned char *sha1, const unsigned char *sha2)
+
+static inline int is_null_sha1(const unsigned char *sha1)
{
- return memcmp(sha1, sha2, 20);
+ return !hashcmp(sha1, null_sha1);
}
+
static inline void hashcpy(unsigned char *sha_dst, const unsigned char *sha_src)
{
memcpy(sha_dst, sha_src, 20);
#define adjust_shared_perm(path) set_shared_perm((path), 0)
int safe_create_leading_directories(char *path);
int safe_create_leading_directories_const(const char *path);
+int mkdir_in_gitdir(const char *path);
extern char *expand_user_path(const char *path);
char *enter_repo(char *path, int strict);
static inline int is_absolute_path(const char *path)
{
- return path[0] == '/' || has_dos_drive_prefix(path);
+ return is_dir_sep(path[0]) || has_dos_drive_prefix(path);
}
int is_directory(const char *);
-const char *make_absolute_path(const char *path);
-const char *make_nonrelative_path(const char *path);
-const char *make_relative_path(const char *abs, const char *base);
+const char *real_path(const char *path);
+const char *absolute_path(const char *path);
+const char *relative_path(const char *abs, const char *base);
int normalize_path_copy(char *dst, const char *src);
int longest_ancestor_length(const char *path, const char *prefix_list);
char *strip_path_suffix(const char *path, const char *suffix);
int daemon_avoid_alias(const char *path);
int offset_1st_component(const char *path);
-/* Read and unpack a sha1 file into memory, write memory to a sha1 file */
-extern int sha1_object_info(const unsigned char *, unsigned long *);
-extern void *read_sha1_file_repl(const unsigned char *sha1, enum object_type *type, unsigned long *size, const unsigned char **replacement);
+/* object replacement */
+#define READ_SHA1_FILE_REPLACE 1
+extern void *read_sha1_file_extended(const unsigned char *sha1, enum object_type *type, unsigned long *size, unsigned flag);
static inline void *read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size)
{
- return read_sha1_file_repl(sha1, type, size, NULL);
+ return read_sha1_file_extended(sha1, type, size, READ_SHA1_FILE_REPLACE);
+}
+extern const unsigned char *do_lookup_replace_object(const unsigned char *sha1);
+static inline const unsigned char *lookup_replace_object(const unsigned char *sha1)
+{
+ if (!read_replace_refs)
+ return sha1;
+ return do_lookup_replace_object(sha1);
}
+
+/* Read and unpack a sha1 file into memory, write memory to a sha1 file */
+extern int sha1_object_info(const unsigned char *, unsigned long *);
extern int hash_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1);
extern int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *return_sha1);
extern int pretend_sha1_file(void *, unsigned long, enum object_type, unsigned char *);
extern int force_object_loose(const unsigned char *sha1, time_t mtime);
+extern void *map_sha1_file(const unsigned char *sha1, unsigned long *size);
+extern int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz);
+extern int parse_sha1_header(const char *hdr, unsigned long *sizep);
/* global flag to enable extra checks when accessing packed objects */
extern int do_check_packed_object_crc;
}
/* Convert to/from hex/sha1 representation */
-#define MINIMUM_ABBREV 4
-#define DEFAULT_ABBREV 7
+#define MINIMUM_ABBREV minimum_abbrev
+#define DEFAULT_ABBREV default_abbrev
struct object_context {
unsigned char tree[20];
};
extern int get_sha1(const char *str, unsigned char *sha1);
-extern int get_sha1_with_mode_1(const char *str, unsigned char *sha1, unsigned *mode, int gently, const char *prefix);
+extern int get_sha1_with_mode_1(const char *str, unsigned char *sha1, unsigned *mode, int only_to_die, const char *prefix);
static inline int get_sha1_with_mode(const char *str, unsigned char *sha1, unsigned *mode)
{
- return get_sha1_with_mode_1(str, sha1, mode, 1, NULL);
+ return get_sha1_with_mode_1(str, sha1, mode, 0, NULL);
}
-extern int get_sha1_with_context_1(const char *name, unsigned char *sha1, struct object_context *orc, int gently, const char *prefix);
+extern int get_sha1_with_context_1(const char *name, unsigned char *sha1, struct object_context *orc, int only_to_die, const char *prefix);
static inline int get_sha1_with_context(const char *str, unsigned char *sha1, struct object_context *orc)
{
- return get_sha1_with_context_1(str, sha1, orc, 1, NULL);
+ return get_sha1_with_context_1(str, sha1, orc, 0, NULL);
}
extern int get_sha1_hex(const char *hex, unsigned char *sha1);
extern char *sha1_to_hex(const unsigned char *sha1); /* static buffer result! */
time_t mtime;
int pack_fd;
unsigned pack_local:1,
- pack_keep:1;
+ pack_keep:1,
+ do_not_close:1;
unsigned char sha1[20];
/* something like ".git/objects/pack/xxxxx.pack" */
char pack_name[FLEX_ARRAY]; /* more */
extern char *git_getpass(const char *prompt);
extern struct child_process *git_connect(int fd[2], const char *url, const char *prog, int flags);
extern int finish_connect(struct child_process *conn);
+extern int git_connection_is_socket(struct child_process *conn);
extern int path_match(const char *path, int nr, char **match);
struct extra_have_objects {
int nr, alloc;
extern void pack_report(void);
extern int open_pack_index(struct packed_git *);
extern void close_pack_index(struct packed_git *);
-extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned int *);
+extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *);
extern void close_pack_windows(struct packed_git *);
extern void unuse_pack(struct pack_window **);
extern void free_pack_by_name(const char *);
extern void *unpack_entry(struct packed_git *, off_t, enum object_type *, unsigned long *);
extern unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep);
extern unsigned long get_size_from_delta(struct packed_git *, struct pack_window **, off_t);
- extern int packed_object_info_detail(struct packed_git *, off_t, unsigned long *, unsigned long *, unsigned int *, unsigned char *);
+extern int unpack_object_header(struct packed_git *, struct pack_window **, off_t *, unsigned long *);
+
+struct object_info {
+ /* Request */
+ unsigned long *sizep;
+
+ /* Response */
+ enum {
+ OI_CACHED,
+ OI_LOOSE,
+ OI_PACKED,
+ OI_DBCACHED
+ } whence;
+ union {
+ /*
+ * struct {
+ * ... Nothing to expose in this case
+ * } cached;
+ * struct {
+ * ... Nothing to expose in this case
+ * } loose;
+ */
+ struct {
+ struct packed_git *pack;
+ off_t offset;
+ unsigned int is_delta;
+ } packed;
+ } u;
+};
+extern int sha1_object_info_extended(const unsigned char *, struct object_info *);
/* Dumb servers support */
extern int update_server_info(int);
+/* git_config_parse_key() returns these negated: */
+#define CONFIG_INVALID_KEY 1
+#define CONFIG_NO_SECTION_OR_NAME 2
+/* git_config_set(), git_config_set_multivar() return the above or these: */
+#define CONFIG_NO_LOCK -1
+#define CONFIG_INVALID_FILE 3
+#define CONFIG_NO_WRITE 4
+#define CONFIG_NOTHING_SET 5
+#define CONFIG_INVALID_PATTERN 6
+
typedef int (*config_fn_t)(const char *, const char *, void *);
extern int git_default_config(const char *, const char *, void *);
extern int git_config_from_file(config_fn_t fn, const char *, void *);
extern void git_config_push_parameter(const char *text);
-extern int git_config_parse_parameter(const char *text);
-extern int git_config_parse_environment(void);
extern int git_config_from_parameters(config_fn_t fn, void *data);
extern int git_config(config_fn_t fn, void *);
extern int git_config_early(config_fn_t fn, void *, const char *repo_config);
extern int check_repository_format_version(const char *var, const char *value, void *cb);
extern int git_env_bool(const char *, int);
extern int git_config_system(void);
-extern int git_config_global(void);
extern int config_error_nonbool(const char *);
extern const char *get_log_output_encoding(void);
extern const char *get_commit_output_encoding(void);
+extern int git_config_parse_parameter(const char *, config_fn_t fn, void *data);
+
extern const char *config_exclusive_filename;
#define MAX_GITNAME (1000)
/* trace.c */
__attribute__((format (printf, 1, 2)))
extern void trace_printf(const char *format, ...);
+extern void trace_vprintf(const char *key, const char *format, va_list ap);
__attribute__((format (printf, 2, 3)))
extern void trace_argv_printf(const char **argv, const char *format, ...);
extern void trace_repo_setup(const char *prefix);
+extern int trace_want(const char *key);
+extern void trace_strbuf(const char *key, const struct strbuf *buf);
-/* convert.c */
-/* returns 1 if *dst was used */
-extern int convert_to_git(const char *path, const char *src, size_t len,
- struct strbuf *dst, enum safe_crlf checksafe);
-extern int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst);
-extern int renormalize_buffer(const char *path, const char *src, size_t len, struct strbuf *dst);
+void packet_trace_identity(const char *prog);
/* add */
/*
#include "progress.h"
#include "csum-file.h"
- static void flush(struct sha1file *f, void * buf, unsigned int count)
+ static void flush(struct sha1file *f, void *buf, unsigned int count)
{
+ if (0 <= f->check_fd && count) {
+ unsigned char check_buffer[8192];
+ ssize_t ret = read_in_full(f->check_fd, check_buffer, count);
+
+ if (ret < 0)
+ die_errno("%s: sha1 file read error", f->name);
+ if (ret < count)
+ die("%s: sha1 file truncated", f->name);
+ if (memcmp(buf, check_buffer, count))
+ die("sha1 file '%s' validation error", f->name);
+ }
+
for (;;) {
int ret = xwrite(f->fd, buf, count);
if (ret > 0) {
fd = 0;
} else
fd = f->fd;
+ if (0 <= f->check_fd) {
+ char discard;
+ int cnt = read_in_full(f->check_fd, &discard, 1);
+ if (cnt < 0)
+ die_errno("%s: error when reading the tail of sha1 file",
+ f->name);
+ if (cnt)
+ die("%s: sha1 file has trailing garbage", f->name);
+ if (close(f->check_fd))
+ die_errno("%s: sha1 file error on close", f->name);
+ }
free(f);
return fd;
}
return sha1fd_throughput(fd, name, NULL);
}
+ struct sha1file *sha1fd_check(const char *name)
+ {
+ int sink, check;
+ struct sha1file *f;
+
+ sink = open("/dev/null", O_WRONLY);
+ if (sink < 0)
+ return NULL;
+ check = open(name, O_RDONLY);
+ if (check < 0) {
+ int saved_errno = errno;
+ close(sink);
+ errno = saved_errno;
+ return NULL;
+ }
+ f = sha1fd(sink, name);
+ f->check_fd = check;
+ return f;
+ }
+
struct sha1file *sha1fd_throughput(int fd, const char *name, struct progress *tp)
{
struct sha1file *f = xmalloc(sizeof(*f));
f->fd = fd;
+ f->check_fd = -1;
f->offset = 0;
f->total = 0;
f->tp = tp;
void crc32_begin(struct sha1file *f)
{
- f->crc32 = crc32(0, Z_NULL, 0);
+ f->crc32 = crc32(0, NULL, 0);
f->do_crc = 1;
}
commit_msg
('from' sp committish lf)?
('merge' sp committish lf)*
- file_change*
+ (file_change | ls)*
lf?;
commit_msg ::= data;
+ ls ::= 'ls' sp '"' quoted(path) '"' lf;
+
file_change ::= file_clr
| file_del
| file_rnm
ts ::= # time since the epoch in seconds, ascii base10 notation;
tz ::= # GIT style timezone;
- # note: comments and cat requests may appear anywhere
+ # note: comments, ls and cat requests may appear anywhere
# in the input, except within a data command. Any form
# of the data command always escapes the related input
# from comment processing.
# must be the first character on that line (an lf
# preceded it).
#
+
cat_blob ::= 'cat-blob' sp (hexsha1 | idnum) lf;
+ ls_tree ::= 'ls' sp (hexsha1 | idnum) sp path_str lf;
comment ::= '#' not_lf* lf;
not_lf ::= # Any byte that is not ASCII newline (LF);
#define DEPTH_BITS 13
#define MAX_DEPTH ((1<<DEPTH_BITS)-1)
-struct object_entry
-{
+struct object_entry {
struct pack_idx_entry idx;
struct object_entry *next;
uint32_t type : TYPE_BITS,
depth : DEPTH_BITS;
};
-struct object_entry_pool
-{
+struct object_entry_pool {
struct object_entry_pool *next_pool;
struct object_entry *next_free;
struct object_entry *end;
struct object_entry entries[FLEX_ARRAY]; /* more */
};
-struct mark_set
-{
+struct mark_set {
union {
struct object_entry *marked[1024];
struct mark_set *sets[1024];
unsigned int shift;
};
-struct last_object
-{
+struct last_object {
struct strbuf data;
off_t offset;
unsigned int depth;
unsigned no_swap : 1;
};
-struct mem_pool
-{
+struct mem_pool {
struct mem_pool *next_pool;
char *next_free;
char *end;
uintmax_t space[FLEX_ARRAY]; /* more */
};
-struct atom_str
-{
+struct atom_str {
struct atom_str *next_atom;
unsigned short str_len;
char str_dat[FLEX_ARRAY]; /* more */
};
struct tree_content;
-struct tree_entry
-{
+struct tree_entry {
struct tree_content *tree;
struct atom_str *name;
- struct tree_entry_ms
- {
+ struct tree_entry_ms {
uint16_t mode;
unsigned char sha1[20];
} versions[2];
};
-struct tree_content
-{
+struct tree_content {
unsigned int entry_capacity; /* must match avail_tree_content */
unsigned int entry_count;
unsigned int delta_depth;
struct tree_entry *entries[FLEX_ARRAY]; /* more */
};
-struct avail_tree_content
-{
+struct avail_tree_content {
unsigned int entry_capacity; /* must match tree_content */
struct avail_tree_content *next_avail;
};
-struct branch
-{
+struct branch {
struct branch *table_next_branch;
struct branch *active_next_branch;
const char *name;
unsigned char sha1[20];
};
-struct tag
-{
+struct tag {
struct tag *next_tag;
const char *name;
unsigned int pack_id;
unsigned char sha1[20];
};
-struct hash_list
-{
+struct hash_list {
struct hash_list *next;
unsigned char sha1[20];
};
WHENSPEC_NOW
} whenspec_type;
-struct recent_command
-{
+struct recent_command {
struct recent_command *prev;
struct recent_command *next;
char *buf;
/* Configured limits on output */
static unsigned long max_depth = 10;
static off_t max_packsize;
-static uintmax_t big_file_threshold = 512 * 1024 * 1024;
static int force_update;
static int pack_compression_level = Z_DEFAULT_COMPRESSION;
static int pack_compression_seen;
static struct atom_str **atom_table;
/* The .pack file being generated */
+ static struct pack_idx_option pack_idx_opts;
static unsigned int pack_id;
static struct sha1file *pack_file;
static struct packed_git *pack_data;
static void parse_argv(void);
static void parse_cat_blob(void);
+static void parse_ls(struct branch *b);
static void write_branch_report(FILE *rpt, struct branch *b)
{
p = xcalloc(1, sizeof(*p) + strlen(tmpfile) + 2);
strcpy(p->pack_name, tmpfile);
p->pack_fd = pack_fd;
+ p->do_not_close = 1;
pack_file = sha1fd(pack_fd, p->pack_name);
hdr.hdr_signature = htonl(PACK_SIGNATURE);
if (c != last)
die("internal consistency error creating the index");
- tmpfile = write_idx_file(NULL, idx, object_count, pack_data->sha1);
+ tmpfile = write_idx_file(NULL, idx, object_count, &pack_idx_opts, pack_data->sha1);
free(idx);
return tmpfile;
}
unsigned char sha1[20];
unsigned long hdrlen, deltalen;
git_SHA_CTX c;
- z_stream s;
+ git_zstream s;
hdrlen = sprintf((char *)hdr,"%s %lu", typename(type),
(unsigned long)dat->len) + 1;
delta = NULL;
memset(&s, 0, sizeof(s));
- deflateInit(&s, pack_compression_level);
+ git_deflate_init(&s, pack_compression_level);
if (delta) {
s.next_in = delta;
s.avail_in = deltalen;
s.next_in = (void *)dat->buf;
s.avail_in = dat->len;
}
- s.avail_out = deflateBound(&s, s.avail_in);
+ s.avail_out = git_deflate_bound(&s, s.avail_in);
s.next_out = out = xmalloc(s.avail_out);
- while (deflate(&s, Z_FINISH) == Z_OK)
- /* nothing */;
- deflateEnd(&s);
+ while (git_deflate(&s, Z_FINISH) == Z_OK)
+ ; /* nothing */
+ git_deflate_end(&s);
/* Determine if we should auto-checkpoint. */
if ((max_packsize && (pack_size + 60 + s.total_out) > max_packsize)
delta = NULL;
memset(&s, 0, sizeof(s));
- deflateInit(&s, pack_compression_level);
+ git_deflate_init(&s, pack_compression_level);
s.next_in = (void *)dat->buf;
s.avail_in = dat->len;
- s.avail_out = deflateBound(&s, s.avail_in);
+ s.avail_out = git_deflate_bound(&s, s.avail_in);
s.next_out = out = xrealloc(out, s.avail_out);
- while (deflate(&s, Z_FINISH) == Z_OK)
- /* nothing */;
- deflateEnd(&s);
+ while (git_deflate(&s, Z_FINISH) == Z_OK)
+ ; /* nothing */
+ git_deflate_end(&s);
}
}
off_t offset;
git_SHA_CTX c;
git_SHA_CTX pack_file_ctx;
- z_stream s;
+ git_zstream s;
int status = Z_OK;
/* Determine if we should auto-checkpoint. */
crc32_begin(pack_file);
memset(&s, 0, sizeof(s));
- deflateInit(&s, pack_compression_level);
+ git_deflate_init(&s, pack_compression_level);
hdrlen = encode_in_pack_object_header(OBJ_BLOB, len, out_buf);
if (out_sz <= hdrlen)
len -= n;
}
- status = deflate(&s, len ? 0 : Z_FINISH);
+ status = git_deflate(&s, len ? 0 : Z_FINISH);
if (!s.avail_out || status == Z_STREAM_END) {
size_t n = s.next_out - out_buf;
die("unexpected deflate failure: %d", status);
}
}
- deflateEnd(&s);
+ git_deflate_end(&s);
git_SHA1_Final(sha1, &c);
if (sha1out)
note_change_n(b, prev_fanout);
else if (!strcmp("deleteall", command_buf.buf))
file_change_deleteall(b);
+ else if (!prefixcmp(command_buf.buf, "ls "))
+ parse_ls(b);
else {
unread_command_buf = 1;
break;
cat_blob(oe, sha1);
}
+static struct object_entry *dereference(struct object_entry *oe,
+ unsigned char sha1[20])
+{
+ unsigned long size;
+ char *buf = NULL;
+ if (!oe) {
+ enum object_type type = sha1_object_info(sha1, NULL);
+ if (type < 0)
+ die("object not found: %s", sha1_to_hex(sha1));
+ /* cache it! */
+ oe = insert_object(sha1);
+ oe->type = type;
+ oe->pack_id = MAX_PACK_ID;
+ oe->idx.offset = 1;
+ }
+ switch (oe->type) {
+ case OBJ_TREE: /* easy case. */
+ return oe;
+ case OBJ_COMMIT:
+ case OBJ_TAG:
+ break;
+ default:
+ die("Not a treeish: %s", command_buf.buf);
+ }
+
+ if (oe->pack_id != MAX_PACK_ID) { /* in a pack being written */
+ buf = gfi_unpack_entry(oe, &size);
+ } else {
+ enum object_type unused;
+ buf = read_sha1_file(sha1, &unused, &size);
+ }
+ if (!buf)
+ die("Can't load object %s", sha1_to_hex(sha1));
+
+ /* Peel one layer. */
+ switch (oe->type) {
+ case OBJ_TAG:
+ if (size < 40 + strlen("object ") ||
+ get_sha1_hex(buf + strlen("object "), sha1))
+ die("Invalid SHA1 in tag: %s", command_buf.buf);
+ break;
+ case OBJ_COMMIT:
+ if (size < 40 + strlen("tree ") ||
+ get_sha1_hex(buf + strlen("tree "), sha1))
+ die("Invalid SHA1 in commit: %s", command_buf.buf);
+ }
+
+ free(buf);
+ return find_object(sha1);
+}
+
+static struct object_entry *parse_treeish_dataref(const char **p)
+{
+ unsigned char sha1[20];
+ struct object_entry *e;
+
+ if (**p == ':') { /* <mark> */
+ char *endptr;
+ e = find_mark(strtoumax(*p + 1, &endptr, 10));
+ if (endptr == *p + 1)
+ die("Invalid mark: %s", command_buf.buf);
+ if (!e)
+ die("Unknown mark: %s", command_buf.buf);
+ *p = endptr;
+ hashcpy(sha1, e->idx.sha1);
+ } else { /* <sha1> */
+ if (get_sha1_hex(*p, sha1))
+ die("Invalid SHA1: %s", command_buf.buf);
+ e = find_object(sha1);
+ *p += 40;
+ }
+
+ while (!e || e->type != OBJ_TREE)
+ e = dereference(e, sha1);
+ return e;
+}
+
+static void print_ls(int mode, const unsigned char *sha1, const char *path)
+{
+ static struct strbuf line = STRBUF_INIT;
+
+ /* See show_tree(). */
+ const char *type =
+ S_ISGITLINK(mode) ? commit_type :
+ S_ISDIR(mode) ? tree_type :
+ blob_type;
+
+ if (!mode) {
+ /* missing SP path LF */
+ strbuf_reset(&line);
+ strbuf_addstr(&line, "missing ");
+ quote_c_style(path, &line, NULL, 0);
+ strbuf_addch(&line, '\n');
+ } else {
+ /* mode SP type SP object_name TAB path LF */
+ strbuf_reset(&line);
+ strbuf_addf(&line, "%06o %s %s\t",
+ mode, type, sha1_to_hex(sha1));
+ quote_c_style(path, &line, NULL, 0);
+ strbuf_addch(&line, '\n');
+ }
+ cat_blob_write(line.buf, line.len);
+}
+
+static void parse_ls(struct branch *b)
+{
+ const char *p;
+ struct tree_entry *root = NULL;
+ struct tree_entry leaf = {NULL};
+
+ /* ls SP (<treeish> SP)? <path> */
+ p = command_buf.buf + strlen("ls ");
+ if (*p == '"') {
+ if (!b)
+ die("Not in a commit: %s", command_buf.buf);
+ root = &b->branch_tree;
+ } else {
+ struct object_entry *e = parse_treeish_dataref(&p);
+ root = new_tree_entry();
+ hashcpy(root->versions[1].sha1, e->idx.sha1);
+ load_tree(root);
+ if (*p++ != ' ')
+ die("Missing space after tree-ish: %s", command_buf.buf);
+ }
+ if (*p == '"') {
+ static struct strbuf uq = STRBUF_INIT;
+ const char *endp;
+ strbuf_reset(&uq);
+ if (unquote_c_style(&uq, p, &endp))
+ die("Invalid path: %s", command_buf.buf);
+ if (*endp)
+ die("Garbage after path in: %s", command_buf.buf);
+ p = uq.buf;
+ }
+ tree_content_get(root, p, &leaf);
+ /*
+ * A directory in preparation would have a sha1 of zero
+ * until it is saved. Save, for simplicity.
+ */
+ if (S_ISDIR(leaf.versions[1].mode))
+ store_tree(&leaf);
+
+ print_ls(leaf.versions[1].mode, leaf.versions[1].sha1, p);
+ if (!b || root != &b->branch_tree)
+ release_tree_entry(root);
+}
+
static void checkpoint(void)
{
checkpoint_requested = 0;
option_export_marks(feature + 13);
} else if (!strcmp(feature, "cat-blob")) {
; /* Don't die - this feature is supported */
- } else if (!prefixcmp(feature, "relative-marks")) {
+ } else if (!strcmp(feature, "relative-marks")) {
relative_marks_paths = 1;
- } else if (!prefixcmp(feature, "no-relative-marks")) {
+ } else if (!strcmp(feature, "no-relative-marks")) {
relative_marks_paths = 0;
- } else if (!prefixcmp(feature, "force")) {
+ } else if (!strcmp(feature, "force")) {
force_update = 1;
- } else if (!strcmp(feature, "notes")) {
+ } else if (!strcmp(feature, "notes") || !strcmp(feature, "ls")) {
; /* do nothing; we have the feature */
} else {
return 0;
return 0;
}
if (!strcmp(k, "pack.indexversion")) {
- pack_idx_default_version = git_config_int(k, v);
- if (pack_idx_default_version > 2)
+ pack_idx_opts.version = git_config_int(k, v);
+ if (pack_idx_opts.version > 2)
die("bad pack.indexversion=%"PRIu32,
- pack_idx_default_version);
+ pack_idx_opts.version);
return 0;
}
if (!strcmp(k, "pack.packsizelimit")) {
max_packsize = git_config_ulong(k, v);
return 0;
}
- if (!strcmp(k, "core.bigfilethreshold")) {
- long n = git_config_int(k, v);
- big_file_threshold = 0 < n ? n : 0;
- }
return git_default_config(k, v, cb);
}
usage(fast_import_usage);
setup_git_directory();
+ reset_pack_idx_option(&pack_idx_opts);
git_config(git_pack_config, NULL);
if (!pack_compression_seen && core_compression_seen)
pack_compression_level = core_compression_level;
while (read_next_command() != EOF) {
if (!strcmp("blob", command_buf.buf))
parse_new_blob();
+ else if (!prefixcmp(command_buf.buf, "ls "))
+ parse_ls(NULL);
else if (!prefixcmp(command_buf.buf, "commit "))
parse_new_commit();
else if (!prefixcmp(command_buf.buf, "tag "))
#include "pack.h"
#include "blob.h"
#include "commit.h"
+#include "run-command.h"
#include "tag.h"
#include "tree.h"
#include "tree-walk.h"
#endif
#endif
-#ifdef NO_C99_FORMAT
-#define SZ_FMT "lu"
-static unsigned long sz_fmt(size_t s) { return (unsigned long)s; }
-#else
-#define SZ_FMT "zu"
-static size_t sz_fmt(size_t s) { return s; }
-#endif
+#define SZ_FMT PRIuMAX
+static inline uintmax_t sz_fmt(size_t s) { return s; }
const unsigned char null_sha1[20];
-static int git_open_noatime(const char *name, struct packed_git *p);
-
/*
* This is meant to hold a *small* number of objects that you would
* want read_sha1_file() to be able to return, but yet you do not want
return NULL;
}
+int mkdir_in_gitdir(const char *path)
+{
+ if (mkdir(path, 0777)) {
+ int saved_errno = errno;
+ struct stat st;
+ struct strbuf sb = STRBUF_INIT;
+
+ if (errno != EEXIST)
+ return -1;
+ /*
+ * Are we looking at a path in a symlinked worktree
+ * whose original repository does not yet have it?
+ * e.g. .git/rr-cache pointing at its original
+ * repository in which the user hasn't performed any
+ * conflict resolution yet?
+ */
+ if (lstat(path, &st) || !S_ISLNK(st.st_mode) ||
+ strbuf_readlink(&sb, path, st.st_size) ||
+ !is_absolute_path(sb.buf) ||
+ mkdir(sb.buf, 0777)) {
+ strbuf_release(&sb);
+ errno = saved_errno;
+ return -1;
+ }
+ strbuf_release(&sb);
+ }
+ return adjust_shared_perm(path);
+}
+
int safe_create_leading_directories(char *path)
{
char *pos = path + offset_1st_component(path);
static struct alternate_object_database **alt_odb_tail;
static void read_info_alternates(const char * alternates, int depth);
+static int git_open_noatime(const char *name);
/*
* Prepare alternate object database registry.
int fd;
sprintf(path, "%s/%s", relative_base, alt_file_name);
- fd = git_open_noatime(path, NULL);
+ fd = git_open_noatime(path);
if (fd < 0)
return;
if (fstat(fd, &st) || (st.st_size == 0)) {
static unsigned int pack_mmap_calls;
static unsigned int peak_pack_open_windows;
static unsigned int pack_open_windows;
+static unsigned int pack_open_fds;
+static unsigned int pack_max_fds;
static size_t peak_pack_mapped;
static size_t pack_mapped;
struct packed_git *packed_git;
struct pack_idx_header *hdr;
size_t idx_size;
uint32_t version, nr, i, *index;
- int fd = git_open_noatime(path, p);
+ int fd = git_open_noatime(path);
struct stat st;
if (fd < 0)
lru_l->next = lru_w->next;
else {
lru_p->windows = lru_w->next;
- if (!lru_p->windows && lru_p->pack_fd != keep_fd) {
+ if (!lru_p->windows && lru_p->pack_fd != -1
+ && lru_p->pack_fd != keep_fd) {
close(lru_p->pack_fd);
+ pack_open_fds--;
lru_p->pack_fd = -1;
}
}
if (strcmp(pack_name, p->pack_name) == 0) {
clear_delta_base_cache();
close_pack_windows(p);
- if (p->pack_fd != -1)
+ if (p->pack_fd != -1) {
close(p->pack_fd);
+ pack_open_fds--;
+ }
close_pack_index(p);
free(p->bad_object_sha1);
*pp = p->next;
if (!p->index_data && open_pack_index(p))
return error("packfile %s index unavailable", p->pack_name);
- p->pack_fd = git_open_noatime(p->pack_name, p);
+ if (!pack_max_fds) {
+ struct rlimit lim;
+ unsigned int max_fds;
+
+ if (getrlimit(RLIMIT_NOFILE, &lim))
+ die_errno("cannot get RLIMIT_NOFILE");
+
+ max_fds = lim.rlim_cur;
+
+ /* Save 3 for stdin/stdout/stderr, 22 for work */
+ if (25 < max_fds)
+ pack_max_fds = max_fds - 25;
+ else
+ pack_max_fds = 1;
+ }
+
+ while (pack_max_fds <= pack_open_fds && unuse_one_window(NULL, -1))
+ ; /* nothing */
+
+ p->pack_fd = git_open_noatime(p->pack_name);
if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
return -1;
+ pack_open_fds++;
/* If we created the struct before we had the pack we lack size. */
if (!p->pack_size) {
return 0;
if (p->pack_fd != -1) {
close(p->pack_fd);
+ pack_open_fds--;
p->pack_fd = -1;
}
return -1;
unsigned char *use_pack(struct packed_git *p,
struct pack_window **w_cursor,
off_t offset,
- unsigned int *left)
+ unsigned long *left)
{
struct pack_window *win = *w_cursor;
- if (p->pack_fd == -1 && open_packed_git(p))
- die("packfile %s cannot be accessed", p->pack_name);
-
/* Since packfiles end in a hash of their content and it's
* pointless to ask for an offset into the middle of that
* hash, and the in_window function above wouldn't match
* don't allow an offset too close to the end of the file.
*/
+ if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p))
+ die("packfile %s cannot be accessed", p->pack_name);
if (offset > (p->pack_size - 20))
die("offset beyond end of packfile (truncated pack?)");
if (!win) {
size_t window_align = packed_git_window_size / 2;
off_t len;
+
+ if (p->pack_fd == -1 && open_packed_git(p))
+ die("packfile %s cannot be accessed", p->pack_name);
+
win = xcalloc(1, sizeof(*win));
win->offset = (offset / window_align) * window_align;
len = p->pack_size - win->offset;
die("packfile %s cannot be mapped: %s",
p->pack_name,
strerror(errno));
+ if (!win->offset && win->len == p->pack_size
+ && !p->do_not_close) {
+ close(p->pack_fd);
+ pack_open_fds--;
+ p->pack_fd = -1;
+ }
pack_mmap_calls++;
pack_open_windows++;
if (pack_mapped > peak_pack_mapped)
void install_packed_git(struct packed_git *pack)
{
+ if (pack->pack_fd != -1)
+ pack_open_fds++;
+
pack->next = packed_git;
packed_git = pack;
}
sprintf(path, "%s/pack", objdir);
len = strlen(path);
dir = opendir(path);
- while (!dir && errno == EMFILE && unuse_one_window(NULL, -1))
- dir = opendir(path);
if (!dir) {
if (errno != ENOENT)
error("unable to open object pack directory: %s: %s",
return hashcmp(sha1, real_sha1) ? -1 : 0;
}
-static int git_open_noatime(const char *name, struct packed_git *p)
+static int git_open_noatime(const char *name)
{
static int sha1_file_open_flag = O_NOATIME;
if (fd >= 0)
return fd;
- /* Might the failure be insufficient file descriptors? */
- if (errno == EMFILE) {
- if (unuse_one_window(p, -1))
- continue;
- else
- return -1;
- }
-
/* Might the failure be due to O_NOATIME? */
if (errno != ENOENT && sha1_file_open_flag) {
sha1_file_open_flag = 0;
char *name = sha1_file_name(sha1);
struct alternate_object_database *alt;
- fd = git_open_noatime(name, NULL);
+ fd = git_open_noatime(name);
if (fd >= 0)
return fd;
for (alt = alt_odb_list; alt; alt = alt->next) {
name = alt->name;
fill_sha1_path(name, sha1);
- fd = git_open_noatime(alt->base, NULL);
+ fd = git_open_noatime(alt->base);
if (fd >= 0)
return fd;
}
return -1;
}
-static void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
+void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
{
void *map;
int fd;
return map;
}
-static int legacy_loose_object(unsigned char *map)
+/*
+ * There used to be a second loose object header format which
+ * was meant to mimic the in-pack format, allowing for direct
+ * copy of the object data. This format turned up not to be
+ * really worth it and we no longer write loose objects in that
+ * format.
+ */
+static int experimental_loose_object(unsigned char *map)
{
unsigned int word;
/*
* Is it a zlib-compressed buffer? If so, the first byte
* must be 0x78 (15-bit window size, deflated), and the
- * first 16-bit word is evenly divisible by 31
+ * first 16-bit word is evenly divisible by 31. If so,
+ * we are looking at the official format, not the experimental
+ * one.
*/
word = (map[0] << 8) + map[1];
if (map[0] == 0x78 && !(word % 31))
- return 1;
- else
return 0;
+ else
+ return 1;
}
unsigned long unpack_object_header_buffer(const unsigned char *buf,
return used;
}
-static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
+int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
{
unsigned long size, used;
static const char valid_loose_object_type[8] = {
stream->next_out = buffer;
stream->avail_out = bufsiz;
- if (legacy_loose_object(map)) {
- git_inflate_init(stream);
- return git_inflate(stream, 0);
- }
-
+ if (experimental_loose_object(map)) {
+ /*
+ * The old experimental format we no longer produce;
+ * we can still read it.
+ */
+ used = unpack_object_header_buffer(map, mapsize, &type, &size);
+ if (!used || !valid_loose_object_type[type])
+ return -1;
+ map += used;
+ mapsize -= used;
- /*
- * There used to be a second loose object header format which
- * was meant to mimic the in-pack format, allowing for direct
- * copy of the object data. This format turned up not to be
- * really worth it and we don't write it any longer. But we
- * can still read it.
- */
- used = unpack_object_header_buffer(map, mapsize, &type, &size);
- if (!used || !valid_loose_object_type[type])
- return -1;
- map += used;
- mapsize -= used;
+ /* Set up the stream for the rest.. */
+ stream->next_in = map;
+ stream->avail_in = mapsize;
+ git_inflate_init(stream);
- /* Set up the stream for the rest.. */
- stream->next_in = map;
- stream->avail_in = mapsize;
+ /* And generate the fake traditional header */
+ stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
+ typename(type), size);
+ return 0;
+ }
git_inflate_init(stream);
-
- /* And generate the fake traditional header */
- stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
- typename(type), size);
- return 0;
+ return git_inflate(stream, 0);
}
-static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
+static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
{
int bytes = strlen(buffer) + 1;
unsigned char *buf = xmallocz(size);
/*
* The above condition must be (bytes <= size), not
* (bytes < size). In other words, even though we
- * expect no more output and set avail_out to zer0,
+ * expect no more output and set avail_out to zero,
* the input zlib stream may have bytes that express
* "this concludes the stream", and we *do* want to
* eat that input.
* too permissive for what we want to check. So do an anal
* object header parse by hand.
*/
-static int parse_sha1_header(const char *hdr, unsigned long *sizep)
+int parse_sha1_header(const char *hdr, unsigned long *sizep)
{
char type[10];
int i;
static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
{
int ret;
- z_stream stream;
+ git_zstream stream;
char hdr[8192];
ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
{
const unsigned char *data;
unsigned char delta_head[20], *in;
- z_stream stream;
+ git_zstream stream;
int st;
memset(&stream, 0, sizeof(stream));
/* forward declaration for a mutually recursive function */
static int packed_object_info(struct packed_git *p, off_t offset,
- unsigned long *sizep);
+ unsigned long *sizep, int *rtype);
static int packed_delta_info(struct packed_git *p,
struct pack_window **w_curs,
base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
if (!base_offset)
return OBJ_BAD;
- type = packed_object_info(p, base_offset, NULL);
+ type = packed_object_info(p, base_offset, NULL, NULL);
if (type <= OBJ_NONE) {
struct revindex_entry *revidx;
const unsigned char *base_sha1;
return type;
}
-static int unpack_object_header(struct packed_git *p,
- struct pack_window **w_curs,
- off_t *curpos,
- unsigned long *sizep)
+int unpack_object_header(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t *curpos,
+ unsigned long *sizep)
{
unsigned char *base;
- unsigned int left;
+ unsigned long left;
unsigned long used;
enum object_type type;
/* use_pack() assures us we have [base, base + 20) available
- * as a range that we can look at at. (Its actually the hash
+ * as a range that we can look at. (Its actually the hash
* size that is assured.) With our object header encoding
* the maximum deflated object size is 2^137, which is just
* insane, so we know won't exceed what we have been given.
return type;
}
- int packed_object_info_detail(struct packed_git *p,
- off_t obj_offset,
- unsigned long *size,
- unsigned long *store_size,
- unsigned int *delta_chain_length,
- unsigned char *base_sha1)
- {
- struct pack_window *w_curs = NULL;
- off_t curpos;
- unsigned long dummy;
- unsigned char *next_sha1;
- enum object_type type;
- struct revindex_entry *revidx;
-
- *delta_chain_length = 0;
- curpos = obj_offset;
- type = unpack_object_header(p, &w_curs, &curpos, size);
-
- revidx = find_pack_revindex(p, obj_offset);
- *store_size = revidx[1].offset - obj_offset;
-
- for (;;) {
- switch (type) {
- default:
- die("pack %s contains unknown object type %d",
- p->pack_name, type);
- case OBJ_COMMIT:
- case OBJ_TREE:
- case OBJ_BLOB:
- case OBJ_TAG:
- unuse_pack(&w_curs);
- return type;
- case OBJ_OFS_DELTA:
- obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
- if (!obj_offset)
- die("pack %s contains bad delta base reference of type %s",
- p->pack_name, typename(type));
- if (*delta_chain_length == 0) {
- revidx = find_pack_revindex(p, obj_offset);
- hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr));
- }
- break;
- case OBJ_REF_DELTA:
- next_sha1 = use_pack(p, &w_curs, curpos, NULL);
- if (*delta_chain_length == 0)
- hashcpy(base_sha1, next_sha1);
- obj_offset = find_pack_entry_one(next_sha1, p);
- break;
- }
- (*delta_chain_length)++;
- curpos = obj_offset;
- type = unpack_object_header(p, &w_curs, &curpos, &dummy);
- }
- }
-
static int packed_object_info(struct packed_git *p, off_t obj_offset,
- unsigned long *sizep)
+ unsigned long *sizep, int *rtype)
{
struct pack_window *w_curs = NULL;
unsigned long size;
enum object_type type;
type = unpack_object_header(p, &w_curs, &curpos, &size);
+ if (rtype)
+ *rtype = type; /* representation type */
switch (type) {
case OBJ_OFS_DELTA:
unsigned long size)
{
int st;
- z_stream stream;
+ git_zstream stream;
unsigned char *buffer, *in;
buffer = xmallocz(size);
return hash % MAX_DELTA_CACHE;
}
+static int in_delta_base_cache(struct packed_git *p, off_t base_offset)
+{
+ unsigned long hash = pack_entry_hash(p, base_offset);
+ struct delta_base_cache_entry *ent = delta_base_cache + hash;
+ return (ent->data && ent->p == p && ent->base_offset == base_offset);
+}
+
static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
unsigned long *base_size, enum object_type *type, int keep_cache)
{
return 0;
}
+static int is_pack_valid(struct packed_git *p)
+{
+ /* An already open pack is known to be valid. */
+ if (p->pack_fd != -1)
+ return 1;
+
+ /* If the pack has one window completely covering the
+ * file size, the pack is known to be valid even if
+ * the descriptor is not currently open.
+ */
+ if (p->windows) {
+ struct pack_window *w = p->windows;
+
+ if (!w->offset && w->len == p->pack_size)
+ return 1;
+ }
+
+ /* Force the pack to open to prove its valid. */
+ return !open_packed_git(p);
+}
+
static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
{
static struct packed_git *last_found = (void *)1;
* it may have been deleted since the index
* was loaded!
*/
- if (p->pack_fd == -1 && open_packed_git(p)) {
+ if (!is_pack_valid(p)) {
error("packfile %s cannot be accessed", p->pack_name);
goto next;
}
int status;
unsigned long mapsize, size;
void *map;
- z_stream stream;
+ git_zstream stream;
char hdr[32];
map = map_sha1_file(sha1, &mapsize);
return status;
}
-int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+/* returns enum object_type or negative */
+int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi)
{
struct cached_object *co;
struct pack_entry e;
- int status;
+ int status, rtype;
co = find_cached_object(sha1);
if (co) {
- if (sizep)
- *sizep = co->size;
+ if (oi->sizep)
+ *(oi->sizep) = co->size;
+ oi->whence = OI_CACHED;
return co->type;
}
if (!find_pack_entry(sha1, &e)) {
/* Most likely it's a loose object. */
- status = sha1_loose_object_info(sha1, sizep);
- if (status >= 0)
+ status = sha1_loose_object_info(sha1, oi->sizep);
+ if (status >= 0) {
+ oi->whence = OI_LOOSE;
return status;
+ }
/* Not a loose object; someone else may have just packed it. */
reprepare_packed_git();
return status;
}
- status = packed_object_info(e.p, e.offset, sizep);
+ status = packed_object_info(e.p, e.offset, oi->sizep, &rtype);
if (status < 0) {
mark_bad_packed_object(e.p, sha1);
- status = sha1_object_info(sha1, sizep);
+ status = sha1_object_info_extended(sha1, oi);
+ } else if (in_delta_base_cache(e.p, e.offset)) {
+ oi->whence = OI_DBCACHED;
+ } else {
+ oi->whence = OI_PACKED;
+ oi->u.packed.offset = e.offset;
+ oi->u.packed.pack = e.p;
+ oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
+ rtype == OBJ_OFS_DELTA);
}
return status;
}
+int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+{
+ struct object_info oi;
+
+ oi.sizep = sizep;
+ return sha1_object_info_extended(sha1, &oi);
+}
+
static void *read_packed_sha1(const unsigned char *sha1,
enum object_type *type, unsigned long *size)
{
* deal with them should arrange to call read_object() and give error
* messages themselves.
*/
-void *read_sha1_file_repl(const unsigned char *sha1,
- enum object_type *type,
- unsigned long *size,
- const unsigned char **replacement)
+void *read_sha1_file_extended(const unsigned char *sha1,
+ enum object_type *type,
+ unsigned long *size,
+ unsigned flag)
{
- const unsigned char *repl = lookup_replace_object(sha1);
void *data;
char *path;
const struct packed_git *p;
+ const unsigned char *repl = (flag & READ_SHA1_FILE_REPLACE)
+ ? lookup_replace_object(sha1) : sha1;
errno = 0;
data = read_object(repl, type, size);
- if (data) {
- if (replacement)
- *replacement = repl;
+ if (data)
return data;
- }
if (errno && errno != ENOENT)
die_errno("failed to read object %s", sha1_to_hex(sha1));
{
int fd, ret;
unsigned char compressed[4096];
- z_stream stream;
+ git_zstream stream;
git_SHA_CTX c;
unsigned char parano_sha1[20];
char *filename;
filename = sha1_file_name(sha1);
fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
- while (fd < 0 && errno == EMFILE && unuse_one_window(NULL, -1))
- fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
if (fd < 0) {
if (errno == EACCES)
return error("insufficient permission for adding an object to repository database %s\n", get_object_directory());
/* Set it up */
memset(&stream, 0, sizeof(stream));
- deflateInit(&stream, zlib_compression_level);
+ git_deflate_init(&stream, zlib_compression_level);
stream.next_out = compressed;
stream.avail_out = sizeof(compressed);
git_SHA1_Init(&c);
/* First header.. */
stream.next_in = (unsigned char *)hdr;
stream.avail_in = hdrlen;
- while (deflate(&stream, 0) == Z_OK)
- /* nothing */;
+ while (git_deflate(&stream, 0) == Z_OK)
+ ; /* nothing */
git_SHA1_Update(&c, hdr, hdrlen);
/* Then the data itself.. */
stream.avail_in = len;
do {
unsigned char *in0 = stream.next_in;
- ret = deflate(&stream, Z_FINISH);
+ ret = git_deflate(&stream, Z_FINISH);
git_SHA1_Update(&c, in0, stream.next_in - in0);
if (write_buffer(fd, compressed, stream.next_out - compressed) < 0)
die("unable to write sha1 file");
if (ret != Z_STREAM_END)
die("unable to deflate new object %s (%d)", sha1_to_hex(sha1), ret);
- ret = deflateEnd(&stream);
+ ret = git_deflate_end_gently(&stream);
if (ret != Z_OK)
die("deflateEnd on object %s failed (%d)", sha1_to_hex(sha1), ret);
git_SHA1_Final(parano_sha1, &c);
}
static int index_mem(unsigned char *sha1, void *buf, size_t size,
- int write_object, enum object_type type,
- const char *path, int format_check)
+ enum object_type type,
+ const char *path, unsigned flags)
{
int ret, re_allocated = 0;
+ int write_object = flags & HASH_WRITE_OBJECT;
if (!type)
type = OBJ_BLOB;
re_allocated = 1;
}
}
- if (format_check) {
+ if (flags & HASH_FORMAT_CHECK) {
if (type == OBJ_TREE)
check_tree(buf, size);
if (type == OBJ_COMMIT)
return ret;
}
+static int index_pipe(unsigned char *sha1, int fd, enum object_type type,
+ const char *path, unsigned flags)
+{
+ struct strbuf sbuf = STRBUF_INIT;
+ int ret;
+
+ if (strbuf_read(&sbuf, fd, 4096) >= 0)
+ ret = index_mem(sha1, sbuf.buf, sbuf.len, type, path, flags);
+ else
+ ret = -1;
+ strbuf_release(&sbuf);
+ return ret;
+}
+
#define SMALL_FILE_SIZE (32*1024)
-int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
- enum object_type type, const char *path, int format_check)
+static int index_core(unsigned char *sha1, int fd, size_t size,
+ enum object_type type, const char *path,
+ unsigned flags)
{
int ret;
- size_t size = xsize_t(st->st_size);
- if (!S_ISREG(st->st_mode)) {
- struct strbuf sbuf = STRBUF_INIT;
- if (strbuf_read(&sbuf, fd, 4096) >= 0)
- ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
- type, path, format_check);
- else
- ret = -1;
- strbuf_release(&sbuf);
- } else if (!size) {
- ret = index_mem(sha1, NULL, size, write_object, type, path,
- format_check);
+ if (!size) {
+ ret = index_mem(sha1, NULL, size, type, path, flags);
} else if (size <= SMALL_FILE_SIZE) {
char *buf = xmalloc(size);
if (size == read_in_full(fd, buf, size))
- ret = index_mem(sha1, buf, size, write_object, type,
- path, format_check);
+ ret = index_mem(sha1, buf, size, type, path, flags);
else
ret = error("short read %s", strerror(errno));
free(buf);
} else {
void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
- ret = index_mem(sha1, buf, size, write_object, type, path,
- format_check);
+ ret = index_mem(sha1, buf, size, type, path, flags);
munmap(buf, size);
}
+ return ret;
+}
+
+/*
+ * This creates one packfile per large blob, because the caller
+ * immediately wants the result sha1, and fast-import can report the
+ * object name via marks mechanism only by closing the created
+ * packfile.
+ *
+ * This also bypasses the usual "convert-to-git" dance, and that is on
+ * purpose. We could write a streaming version of the converting
+ * functions and insert that before feeding the data to fast-import
+ * (or equivalent in-core API described above), but the primary
+ * motivation for trying to stream from the working tree file and to
+ * avoid mmaping it in core is to deal with large binary blobs, and
+ * by definition they do _not_ want to get any conversion.
+ */
+static int index_stream(unsigned char *sha1, int fd, size_t size,
+ enum object_type type, const char *path,
+ unsigned flags)
+{
+ struct child_process fast_import;
+ char export_marks[512];
+ const char *argv[] = { "fast-import", "--quiet", export_marks, NULL };
+ char tmpfile[512];
+ char fast_import_cmd[512];
+ char buf[512];
+ int len, tmpfd;
+
+ strcpy(tmpfile, git_path("hashstream_XXXXXX"));
+ tmpfd = git_mkstemp_mode(tmpfile, 0600);
+ if (tmpfd < 0)
+ die_errno("cannot create tempfile: %s", tmpfile);
+ if (close(tmpfd))
+ die_errno("cannot close tempfile: %s", tmpfile);
+ sprintf(export_marks, "--export-marks=%s", tmpfile);
+
+ memset(&fast_import, 0, sizeof(fast_import));
+ fast_import.in = -1;
+ fast_import.argv = argv;
+ fast_import.git_cmd = 1;
+ if (start_command(&fast_import))
+ die_errno("index-stream: git fast-import failed");
+
+ len = sprintf(fast_import_cmd, "blob\nmark :1\ndata %lu\n",
+ (unsigned long) size);
+ write_or_whine(fast_import.in, fast_import_cmd, len,
+ "index-stream: feeding fast-import");
+ while (size) {
+ char buf[10240];
+ size_t sz = size < sizeof(buf) ? size : sizeof(buf);
+ ssize_t actual;
+
+ actual = read_in_full(fd, buf, sz);
+ if (actual < 0)
+ die_errno("index-stream: reading input");
+ if (write_in_full(fast_import.in, buf, actual) != actual)
+ die_errno("index-stream: feeding fast-import");
+ size -= actual;
+ }
+ if (close(fast_import.in))
+ die_errno("index-stream: closing fast-import");
+ if (finish_command(&fast_import))
+ die_errno("index-stream: finishing fast-import");
+
+ tmpfd = open(tmpfile, O_RDONLY);
+ if (tmpfd < 0)
+ die_errno("index-stream: cannot open fast-import mark");
+ len = read(tmpfd, buf, sizeof(buf));
+ if (len < 0)
+ die_errno("index-stream: reading fast-import mark");
+ if (close(tmpfd) < 0)
+ die_errno("index-stream: closing fast-import mark");
+ if (unlink(tmpfile))
+ die_errno("index-stream: unlinking fast-import mark");
+ if (len != 44 ||
+ memcmp(":1 ", buf, 3) ||
+ get_sha1_hex(buf + 3, sha1))
+ die_errno("index-stream: unexpected fast-import mark: <%s>", buf);
+ return 0;
+}
+
+int index_fd(unsigned char *sha1, int fd, struct stat *st,
+ enum object_type type, const char *path, unsigned flags)
+{
+ int ret;
+ size_t size = xsize_t(st->st_size);
+
+ if (!S_ISREG(st->st_mode))
+ ret = index_pipe(sha1, fd, type, path, flags);
+ else if (size <= big_file_threshold || type != OBJ_BLOB)
+ ret = index_core(sha1, fd, size, type, path, flags);
+ else
+ ret = index_stream(sha1, fd, size, type, path, flags);
close(fd);
return ret;
}
-int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object)
+int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags)
{
int fd;
struct strbuf sb = STRBUF_INIT;
if (fd < 0)
return error("open(\"%s\"): %s", path,
strerror(errno));
- if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path, 0) < 0)
+ if (index_fd(sha1, fd, st, OBJ_BLOB, path, flags) < 0)
return error("%s: failed to insert into database",
path);
break;
return error("readlink(\"%s\"): %s", path,
errstr);
}
- if (!write_object)
+ if (!(flags & HASH_WRITE_OBJECT))
hash_sha1_file(sb.buf, sb.len, blob_type, sha1);
else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1))
return error("%s: failed to insert into database",