diff options
| -rw-r--r-- | Documentation/git-ls-files.txt | 9 | ||||
| -rw-r--r-- | Documentation/git-ls-tree.txt | 9 | ||||
| -rw-r--r-- | Makefile | 4 | ||||
| -rw-r--r-- | blame.c | 1 | ||||
| -rw-r--r-- | cache.h | 1 | ||||
| -rw-r--r-- | cat-file.c | 1 | ||||
| -rw-r--r-- | config.c | 5 | ||||
| -rw-r--r-- | count-delta.c | 72 | ||||
| -rw-r--r-- | count-delta.h | 10 | ||||
| -rw-r--r-- | diff.c | 2 | ||||
| -rw-r--r-- | diffcore-break.c | 46 | ||||
| -rw-r--r-- | diffcore-delta.c | 228 | ||||
| -rw-r--r-- | diffcore-rename.c | 27 | ||||
| -rw-r--r-- | diffcore.h | 7 | ||||
| -rw-r--r-- | environment.c | 1 | ||||
| -rw-r--r-- | fetch-pack.c | 18 | ||||
| -rwxr-xr-x | git-clone.sh | 212 | ||||
| -rwxr-xr-x | git-fetch.sh | 10 | ||||
| -rwxr-xr-x | git-fmt-merge-msg.perl | 8 | ||||
| -rwxr-xr-x | git-merge.sh | 67 | ||||
| -rwxr-xr-x | git-parse-remote.sh | 8 | ||||
| -rw-r--r-- | ls-files.c | 19 | ||||
| -rw-r--r-- | ls-tree.c | 20 | ||||
| -rw-r--r-- | merge-base.c | 1 | ||||
| -rw-r--r-- | name-rev.c | 1 | ||||
| -rw-r--r-- | read-tree.c | 1 | ||||
| -rw-r--r-- | rev-list.c | 11 | ||||
| -rw-r--r-- | rev-parse.c | 2 | ||||
| -rw-r--r-- | send-pack.c | 2 | ||||
| -rw-r--r-- | sha1_name.c | 35 | ||||
| -rwxr-xr-x | t/t5000-tar-tree.sh | 3 | ||||
| -rw-r--r-- | tar-tree.c | 386 | ||||
| -rw-r--r-- | tar.h | 25 | ||||
| -rw-r--r-- | unpack-file.c | 1 | ||||
| -rw-r--r-- | update-ref.c | 1 |
35 files changed, 790 insertions, 464 deletions
diff --git a/Documentation/git-ls-files.txt b/Documentation/git-ls-files.txt index e813f84..59f6adc 100644 --- a/Documentation/git-ls-files.txt +++ b/Documentation/git-ls-files.txt @@ -14,9 +14,9 @@ SYNOPSIS (-[c|d|o|i|s|u|k|m])\* [-x <pattern>|--exclude=<pattern>] [-X <file>|--exclude-from=<file>] - [--exclude-per-directory=<file>] + [--exclude-per-directory=<file>] [--error-unmatch] - [--full-name] [--] [<file>]\* + [--full-name] [--abbrev] [--] [<file>]\* DESCRIPTION ----------- @@ -98,6 +98,11 @@ OPTIONS option forces paths to be output relative to the project top directory. +--abbrev[=<n>]:: + Instead of showing the full 40-byte hexadecimal object + lines, show only handful hexdigits prefix. + Non default number of digits can be specified with --abbrev=<n>. + --:: Do not interpret any more arguments as options. diff --git a/Documentation/git-ls-tree.txt b/Documentation/git-ls-tree.txt index 5bf6d8b..018c401 100644 --- a/Documentation/git-ls-tree.txt +++ b/Documentation/git-ls-tree.txt @@ -8,7 +8,9 @@ git-ls-tree - Lists the contents of a tree object SYNOPSIS -------- -'git-ls-tree' [-d] [-r] [-t] [-z] [--name-only] [--name-status] <tree-ish> [paths...] +'git-ls-tree' [-d] [-r] [-t] [-z] + [--name-only] [--name-status] [--full-name] [--abbrev=[<n>]] + <tree-ish> [paths...] DESCRIPTION ----------- @@ -40,6 +42,11 @@ OPTIONS --name-status:: List only filenames (instead of the "long" output), one per line. +--abbrev[=<n>]:: + Instead of showing the full 40-byte hexadecimal object + lines, show only handful hexdigits prefix. + Non default number of digits can be specified with --abbrev=<n>. + paths:: When paths are given, show them (note that this isn't really raw pathnames, but rather a list of patterns to match). Otherwise @@ -191,7 +191,7 @@ LIB_FILE=libgit.a XDIFF_LIB=xdiff/lib.a LIB_H = \ - blob.h cache.h commit.h count-delta.h csum-file.h delta.h \ + blob.h cache.h commit.h csum-file.h delta.h \ diff.h object.h pack.h pkt-line.h quote.h refs.h \ run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h @@ -201,7 +201,7 @@ DIFF_OBJS = \ diffcore-delta.o LIB_OBJS = \ - blob.o commit.o connect.o count-delta.o csum-file.o \ + blob.o commit.o connect.o csum-file.o \ date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \ object.o pack-check.o patch-delta.o path.o pkt-line.o \ quote.o read-cache.o refs.o run-command.o \ @@ -752,6 +752,7 @@ int main(int argc, const char **argv) int found_rename; const char* prefix = setup_git_directory(); + git_config(git_default_config); for(i = 1; i < argc; i++) { if(options) { @@ -165,6 +165,7 @@ extern void rollback_index_file(struct cache_file *); extern int trust_executable_bit; extern int assume_unchanged; extern int only_use_symrefs; +extern int warn_ambiguous_refs; extern int diff_rename_limit_default; extern int shared_repository; extern const char *apply_default_whitespace; @@ -100,6 +100,7 @@ int main(int argc, char **argv) int opt; setup_git_directory(); + git_config(git_default_config); if (argc != 3 || get_sha1(argv[2], sha1)) usage("git-cat-file [-t|-s|-e|-p|<type>] <sha1>"); @@ -232,6 +232,11 @@ int git_default_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.warnambiguousrefs")) { + warn_ambiguous_refs = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "user.name")) { strncpy(git_default_name, value, sizeof(git_default_name)); return 0; diff --git a/count-delta.c b/count-delta.c deleted file mode 100644 index 058a2aa..0000000 --- a/count-delta.c +++ /dev/null @@ -1,72 +0,0 @@ -/* - * Copyright (C) 2005 Junio C Hamano - * The delta-parsing part is almost straight copy of patch-delta.c - * which is (C) 2005 Nicolas Pitre <nico@cam.org>. - */ -#include <stdlib.h> -#include <string.h> -#include <limits.h> -#include "delta.h" -#include "count-delta.h" - -/* - * NOTE. We do not _interpret_ delta fully. As an approximation, we - * just count the number of bytes that are copied from the source, and - * the number of literal data bytes that are inserted. - * - * Number of bytes that are _not_ copied from the source is deletion, - * and number of inserted literal bytes are addition, so sum of them - * is the extent of damage. - */ -int count_delta(void *delta_buf, unsigned long delta_size, - unsigned long *src_copied, unsigned long *literal_added) -{ - unsigned long copied_from_source, added_literal; - const unsigned char *data, *top; - unsigned char cmd; - unsigned long src_size, dst_size, out; - - if (delta_size < DELTA_SIZE_MIN) - return -1; - - data = delta_buf; - top = delta_buf + delta_size; - - src_size = get_delta_hdr_size(&data); - dst_size = get_delta_hdr_size(&data); - - added_literal = copied_from_source = out = 0; - while (data < top) { - cmd = *data++; - if (cmd & 0x80) { - unsigned long cp_off = 0, cp_size = 0; - if (cmd & 0x01) cp_off = *data++; - if (cmd & 0x02) cp_off |= (*data++ << 8); - if (cmd & 0x04) cp_off |= (*data++ << 16); - if (cmd & 0x08) cp_off |= (*data++ << 24); - if (cmd & 0x10) cp_size = *data++; - if (cmd & 0x20) cp_size |= (*data++ << 8); - if (cmd & 0x40) cp_size |= (*data++ << 16); - if (cp_size == 0) cp_size = 0x10000; - - copied_from_source += cp_size; - out += cp_size; - } else { - /* write literal into dst */ - added_literal += cmd; - out += cmd; - data += cmd; - } - } - - /* sanity check */ - if (data != top || out != dst_size) - return -1; - - /* delete size is what was _not_ copied from source. - * edit size is that and literal additions. - */ - *src_copied = copied_from_source; - *literal_added = added_literal; - return 0; -} diff --git a/count-delta.h b/count-delta.h deleted file mode 100644 index 7359629..0000000 --- a/count-delta.h +++ /dev/null @@ -1,10 +0,0 @@ -/* - * Copyright (C) 2005 Junio C Hamano - */ -#ifndef COUNT_DELTA_H -#define COUNT_DELTA_H - -int count_delta(void *, unsigned long, - unsigned long *src_copied, unsigned long *literal_added); - -#endif @@ -561,6 +561,8 @@ void diff_free_filespec_data(struct diff_filespec *s) munmap(s->data, s->size); s->should_free = s->should_munmap = 0; s->data = NULL; + free(s->cnt_data); + s->cnt_data = NULL; } static void prep_temp_blob(struct diff_tempfile *temp, diff --git a/diffcore-break.c b/diffcore-break.c index 0fc2b86..ed0e14c 100644 --- a/diffcore-break.c +++ b/diffcore-break.c @@ -45,8 +45,8 @@ static int should_break(struct diff_filespec *src, * The value we return is 1 if we want the pair to be broken, * or 0 if we do not. */ - unsigned long delta_size, base_size, src_copied, literal_added; - int to_break = 0; + unsigned long delta_size, base_size, src_copied, literal_added, + src_removed; *merge_score_p = 0; /* assume no deletion --- "do not break" * is the default. @@ -68,37 +68,45 @@ static int should_break(struct diff_filespec *src, if (diffcore_count_changes(src->data, src->size, dst->data, dst->size, + NULL, NULL, 0, &src_copied, &literal_added)) return 0; + /* sanity */ + if (src->size < src_copied) + src_copied = src->size; + if (dst->size < literal_added + src_copied) { + if (src_copied < dst->size) + literal_added = dst->size - src_copied; + else + literal_added = 0; + } + src_removed = src->size - src_copied; + /* Compute merge-score, which is "how much is removed * from the source material". The clean-up stage will * merge the surviving pair together if the score is * less than the minimum, after rename/copy runs. */ - if (src->size <= src_copied) - ; /* all copied, nothing removed */ - else { - delta_size = src->size - src_copied; - *merge_score_p = delta_size * MAX_SCORE / src->size; - } - + *merge_score_p = src_removed * MAX_SCORE / src->size; + /* Extent of damage, which counts both inserts and * deletes. */ - if (src->size + literal_added <= src_copied) - delta_size = 0; /* avoid wrapping around */ - else - delta_size = (src->size - src_copied) + literal_added; - - /* We break if the edit exceeds the minimum. - * i.e. (break_score / MAX_SCORE < delta_size / base_size) + delta_size = src_removed + literal_added; + if (delta_size * MAX_SCORE / base_size < break_score) + return 0; + + /* If you removed a lot without adding new material, that is + * not really a rewrite. */ - if (break_score * base_size < delta_size * MAX_SCORE) - to_break = 1; + if ((src->size * break_score < src_removed * MAX_SCORE) && + (literal_added * 20 < src_removed) && + (literal_added * 20 < src_copied)) + return 0; - return to_break; + return 1; } void diffcore_break(int break_score) diff --git a/diffcore-delta.c b/diffcore-delta.c index 1e6a691..7338a40 100644 --- a/diffcore-delta.c +++ b/diffcore-delta.c @@ -1,43 +1,213 @@ #include "cache.h" #include "diff.h" #include "diffcore.h" -#include "delta.h" -#include "count-delta.h" - -static int diffcore_count_changes_1(void *src, unsigned long src_size, - void *dst, unsigned long dst_size, - unsigned long delta_limit, - unsigned long *src_copied, - unsigned long *literal_added) + +/* + * Idea here is very simple. + * + * We have total of (sz-N+1) N-byte overlapping sequences in buf whose + * size is sz. If the same N-byte sequence appears in both source and + * destination, we say the byte that starts that sequence is shared + * between them (i.e. copied from source to destination). + * + * For each possible N-byte sequence, if the source buffer has more + * instances of it than the destination buffer, that means the + * difference are the number of bytes not copied from source to + * destination. If the counts are the same, everything was copied + * from source to destination. If the destination has more, + * everything was copied, and destination added more. + * + * We are doing an approximation so we do not really have to waste + * memory by actually storing the sequence. We just hash them into + * somewhere around 2^16 hashbuckets and count the occurrences. + * + * The length of the sequence is arbitrarily set to 8 for now. + */ + +/* Wild guess at the initial hash size */ +#define INITIAL_HASH_SIZE 9 + +/* We leave more room in smaller hash but do not let it + * grow to have unused hole too much. + */ +#define INITIAL_FREE(sz_log2) ((1<<(sz_log2))*(sz_log2-3)/(sz_log2)) + +/* A prime rather carefully chosen between 2^16..2^17, so that + * HASHBASE < INITIAL_FREE(17). We want to keep the maximum hashtable + * size under the current 2<<17 maximum, which can hold this many + * different values before overflowing to hashtable of size 2<<18. + */ +#define HASHBASE 107927 + +struct spanhash { + unsigned int hashval; + unsigned int cnt; +}; +struct spanhash_top { + int alloc_log2; + int free; + struct spanhash data[FLEX_ARRAY]; +}; + +static struct spanhash *spanhash_find(struct spanhash_top *top, + unsigned int hashval) { - void *delta; - unsigned long delta_size; - - delta = diff_delta(src, src_size, - dst, dst_size, - &delta_size, delta_limit); - if (!delta) - /* If delta_limit is exceeded, we have too much differences */ - return -1; - - /* Estimate the edit size by interpreting delta. */ - if (count_delta(delta, delta_size, src_copied, literal_added)) { - free(delta); - return -1; + int sz = 1 << top->alloc_log2; + int bucket = hashval & (sz - 1); + while (1) { + struct spanhash *h = &(top->data[bucket++]); + if (!h->cnt) + return NULL; + if (h->hashval == hashval) + return h; + if (sz <= bucket) + bucket = 0; } - free(delta); - return 0; +} + +static struct spanhash_top *spanhash_rehash(struct spanhash_top *orig) +{ + struct spanhash_top *new; + int i; + int osz = 1 << orig->alloc_log2; + int sz = osz << 1; + + new = xmalloc(sizeof(*orig) + sizeof(struct spanhash) * sz); + new->alloc_log2 = orig->alloc_log2 + 1; + new->free = INITIAL_FREE(new->alloc_log2); + memset(new->data, 0, sizeof(struct spanhash) * sz); + for (i = 0; i < osz; i++) { + struct spanhash *o = &(orig->data[i]); + int bucket; + if (!o->cnt) + continue; + bucket = o->hashval & (sz - 1); + while (1) { + struct spanhash *h = &(new->data[bucket++]); + if (!h->cnt) { + h->hashval = o->hashval; + h->cnt = o->cnt; + new->free--; + break; + } + if (sz <= bucket) + bucket = 0; + } + } + free(orig); + return new; +} + +static struct spanhash_top *add_spanhash(struct spanhash_top *top, + unsigned int hashval, int cnt) +{ + int bucket, lim; + struct spanhash *h; + + lim = (1 << top->alloc_log2); + bucket = hashval & (lim - 1); + while (1) { + h = &(top->data[bucket++]); + if (!h->cnt) { + h->hashval = hashval; + h->cnt = cnt; + top->free--; + if (top->free < 0) + return spanhash_rehash(top); + return top; + } + if (h->hashval == hashval) { + h->cnt += cnt; + return top; + } + if (lim <= bucket) + bucket = 0; + } +} + +static struct spanhash_top *hash_chars(unsigned char *buf, unsigned int sz) +{ + int i, n; + unsigned int accum1, accum2, hashval; + struct spanhash_top *hash; + + i = INITIAL_HASH_SIZE; + hash = xmalloc(sizeof(*hash) + sizeof(struct spanhash) * (1<<i)); + hash->alloc_log2 = i; + hash->free = INITIAL_FREE(i); + memset(hash->data, 0, sizeof(struct spanhash) * (1<<i)); + + n = 0; + accum1 = accum2 = 0; + while (sz) { + unsigned int c = *buf++; + unsigned int old_1 = accum1; + sz--; + accum1 = (accum1 << 7) ^ (accum2 >> 25); + accum2 = (accum2 << 7) ^ (old_1 >> 25); + accum1 += c; + if (++n < 64 && c != '\n') + continue; + hashval = (accum1 + accum2 * 0x61) % HASHBASE; + hash = add_spanhash(hash, hashval, n); + n = 0; + accum1 = accum2 = 0; + } + return hash; } int diffcore_count_changes(void *src, unsigned long src_size, void *dst, unsigned long dst_size, + void **src_count_p, + void **dst_count_p, unsigned long delta_limit, unsigned long *src_copied, unsigned long *literal_added) { - return diffcore_count_changes_1(src, src_size, - dst, dst_size, - delta_limit, - src_copied, - literal_added); + int i, ssz; + struct spanhash_top *src_count, *dst_count; + unsigned long sc, la; + + src_count = dst_count = NULL; + if (src_count_p) + src_count = *src_count_p; + if (!src_count) { + src_count = hash_chars(src, src_size); + if (src_count_p) + *src_count_p = src_count; + } + if (dst_count_p) + dst_count = *dst_count_p; + if (!dst_count) { + dst_count = hash_chars(dst, dst_size); + if (dst_count_p) + *dst_count_p = dst_count; + } + sc = la = 0; + + ssz = 1 << src_count->alloc_log2; + for (i = 0; i < ssz; i++) { + struct spanhash *s = &(src_count->data[i]); + struct spanhash *d; + unsigned dst_cnt, src_cnt; + if (!s->cnt) + continue; + src_cnt = s->cnt; + d = spanhash_find(dst_count, s->hashval); + dst_cnt = d ? d->cnt : 0; + if (src_cnt < dst_cnt) { + la += dst_cnt - src_cnt; + sc += src_cnt; + } + else + sc += dst_cnt; + } + + if (!src_count_p) + free(src_count); + if (!dst_count_p) + free(dst_count); + *src_copied = sc; + *literal_added = la; + return 0; } diff --git a/diffcore-rename.c b/diffcore-rename.c index 55cf1c3..e992698 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -133,7 +133,7 @@ static int estimate_similarity(struct diff_filespec *src, * match than anything else; the destination does not even * call into this function in that case. */ - unsigned long delta_size, base_size, src_copied, literal_added; + unsigned long max_size, delta_size, base_size, src_copied, literal_added; unsigned long delta_limit; int score; @@ -144,9 +144,9 @@ static int estimate_similarity(struct diff_filespec *src, if (!S_ISREG(src->mode) || !S_ISREG(dst->mode)) return 0; - delta_size = ((src->size < dst->size) ? - (dst->size - src->size) : (src->size - dst->size)); + max_size = ((src->size > dst->size) ? src->size : dst->size); base_size = ((src->size < dst->size) ? src->size : dst->size); + delta_size = max_size - base_size; /* We would not consider edits that change the file size so * drastically. delta_size must be smaller than @@ -166,23 +166,18 @@ static int estimate_similarity(struct diff_filespec *src, delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE; if (diffcore_count_changes(src->data, src->size, dst->data, dst->size, + &src->cnt_data, &dst->cnt_data, delta_limit, &src_copied, &literal_added)) return 0; - /* Extent of damage */ - if (src->size + literal_added < src_copied) - delta_size = 0; - else - delta_size = (src->size - src_copied) + literal_added; - - /* - * Now we will give some score to it. 100% edit gets 0 points - * and 0% edit gets MAX_SCORE points. + /* How similar are they? + * what percentage of material in dst are from source? */ - score = MAX_SCORE - (MAX_SCORE * delta_size / base_size); - if (score < 0) return 0; - if (MAX_SCORE < score) return MAX_SCORE; + if (!dst->size) + score = 0; /* should not happen */ + else + score = src_copied * MAX_SCORE / max_size; return score; } @@ -310,6 +305,8 @@ void diffcore_rename(struct diff_options *options) m->score = estimate_similarity(one, two, minimum_score); } + /* We do not need the text anymore */ + diff_free_filespec_data(two); dst_cnt++; } /* cost matrix sorted by most to least similar pair */ @@ -17,8 +17,8 @@ */ #define MAX_SCORE 60000.0 #define DEFAULT_RENAME_SCORE 30000 /* rename/copy similarity minimum (50%) */ -#define DEFAULT_BREAK_SCORE 30000 /* minimum for break to happen (50%)*/ -#define DEFAULT_MERGE_SCORE 48000 /* maximum for break-merge to happen (80%)*/ +#define DEFAULT_BREAK_SCORE 30000 /* minimum for break to happen (50%) */ +#define DEFAULT_MERGE_SCORE 36000 /* maximum for break-merge to happen 60%) */ #define MINIMUM_BREAK_SIZE 400 /* do not break a file smaller than this */ @@ -26,6 +26,7 @@ struct diff_filespec { unsigned char sha1[20]; char *path; void *data; + void *cnt_data; unsigned long size; int xfrm_flags; /* for use by the xfrm */ unsigned short mode; /* file mode */ @@ -103,6 +104,8 @@ void diff_debug_queue(const char *, struct diff_queue_struct *); extern int diffcore_count_changes(void *src, unsigned long src_size, void *dst, unsigned long dst_size, + void **src_count_p, + void **dst_count_p, unsigned long delta_limit, unsigned long *src_copied, unsigned long *literal_added); diff --git a/environment.c b/environment.c index 16c08f0..6df6478 100644 --- a/environment.c +++ b/environment.c @@ -14,6 +14,7 @@ char git_default_name[MAX_GITNAME]; int trust_executable_bit = 1; int assume_unchanged = 0; int only_use_symrefs = 0; +int warn_ambiguous_refs = 1; int repository_format_version = 0; char git_commit_encoding[MAX_ENCODING_LENGTH] = "utf-8"; int shared_repository = 0; diff --git a/fetch-pack.c b/fetch-pack.c index 535de10..a3bcad0 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -7,8 +7,9 @@ static int keep_pack; static int quiet; static int verbose; +static int fetch_all; static const char fetch_pack_usage[] = -"git-fetch-pack [-q] [-v] [-k] [--thin] [--exec=upload-pack] [host:]directory <refs>..."; +"git-fetch-pack [--all] [-q] [-v] [-k] [--thin] [--exec=upload-pack] [host:]directory <refs>..."; static const char *exec = "git-upload-pack"; #define COMPLETE (1U << 0) @@ -266,8 +267,9 @@ static void filter_refs(struct ref **refs, int nr_match, char **match) for (prev = NULL, current = *refs; current; current = next) { next = current->next; if ((!memcmp(current->name, "refs/", 5) && - check_ref_format(current->name + 5)) || - !path_match(current->name, nr_match, match)) { + check_ref_format(current->name + 5)) || + (!fetch_all && + !path_match(current->name, nr_match, match))) { if (prev == NULL) *refs = next; else @@ -376,7 +378,11 @@ static int fetch_pack(int fd[2], int nr_match, char **match) goto all_done; } if (find_common(fd, sha1, ref) < 0) - fprintf(stderr, "warning: no common commits\n"); + if (!keep_pack) + /* When cloning, it is not unusual to have + * no common commit. + */ + fprintf(stderr, "warning: no common commits\n"); if (keep_pack) status = receive_keep_pack(fd, "git-fetch-pack", quiet); @@ -426,6 +432,10 @@ int main(int argc, char **argv) use_thin_pack = 1; continue; } + if (!strcmp("--all", arg)) { + fetch_all = 1; + continue; + } if (!strcmp("-v", arg)) { verbose = 1; continue; diff --git a/git-clone.sh b/git-clone.sh index 4ed861d..6887321 100755 --- a/git-clone.sh +++ b/git-clone.sh @@ -9,7 +9,7 @@ unset CDPATH usage() { - echo >&2 "Usage: $0 [--bare] [-l [-s]] [-q] [-u <upload-pack>] [-o <name>] [-n] <repo> [<dir>]" + echo >&2 "Usage: $0 [--use-separate-remote] [--reference <reference-repo>] [--bare] [-l [-s]] [-q] [-u <upload-pack>] [-o <name>] [-n] <repo> [<dir>]" exit 1 } @@ -40,13 +40,62 @@ Perhaps git-update-server-info needs to be run there?" do name=`expr "$refname" : 'refs/\(.*\)'` && case "$name" in - *^*) ;; - *) - git-http-fetch -v -a -w "$name" "$name" "$1/" || exit 1 + *^*) continue;; esac + if test -n "$use_separate_remote" && + branch_name=`expr "$name" : 'heads/\(.*\)'` + then + tname="remotes/$origin/$branch_name" + else + tname=$name + fi + git-http-fetch -v -a -w "$tname" "$name" "$1/" || exit 1 done <"$clone_tmp/refs" rm -fr "$clone_tmp" + http_fetch "$1/HEAD" "$GIT_DIR/REMOTE_HEAD" +} + +# Read git-fetch-pack -k output and store the remote branches. +copy_refs=' +use File::Path qw(mkpath); +use File::Basename qw(dirname); +my $git_dir = $ARGV[0]; +my $use_separate_remote = $ARGV[1]; +my $origin = $ARGV[2]; + +my $branch_top = ($use_separate_remote ? "remotes/$origin" : "heads"); +my $tag_top = "tags"; + +sub store { + my ($sha1, $name, $top) = @_; + $name = "$git_dir/refs/$top/$name"; + mkpath(dirname($name)); + open O, ">", "$name"; + print O "$sha1\n"; + close O; +} + +open FH, "<", "$git_dir/CLONE_HEAD"; +while (<FH>) { + my ($sha1, $name) = /^([0-9a-f]{40})\s(.*)$/; + next if ($name =~ /\^\173/); + if ($name eq "HEAD") { + open O, ">", "$git_dir/REMOTE_HEAD"; + print O "$sha1\n"; + close O; + next; + } + if ($name =~ s/^refs\/heads\///) { + store($sha1, $name, $branch_top); + next; + } + if ($name =~ s/^refs\/tags\///) { + store($sha1, $name, $tag_top); + next; + } } +close FH; +' quiet= use_local=no @@ -54,8 +103,10 @@ local_shared=no no_checkout= upload_pack= bare= -origin=origin +reference= +origin= origin_override= +use_separate_remote= while case "$#,$1" in 0,*) break ;; @@ -68,9 +119,21 @@ while *,-s|*,--s|*,--sh|*,--sha|*,--shar|*,--share|*,--shared) local_shared=yes; use_local=yes ;; *,-q|*,--quiet) quiet=-q ;; + *,--use-separate-remote) + use_separate_remote=t ;; 1,-o) usage;; + 1,--reference) usage ;; + *,--reference) + shift; reference="$1" ;; + *,--reference=*) + reference=`expr "$1" : '--reference=\(.*\)'` ;; *,-o) - git-check-ref-format "$2" || { + case "$2" in + */*) + echo >&2 "'$2' is not suitable for an origin name" + exit 1 + esac + git-check-ref-format "heads/$2" || { echo >&2 "'$2' is not suitable for a branch name" exit 1 } @@ -100,9 +163,19 @@ then echo >&2 '--bare and -o $origin options are incompatible.' exit 1 fi + if test t = "$use_separate_remote" + then + echo >&2 '--bare and --use-separate-remote options are incompatible.' + exit 1 + fi no_checkout=yes fi +if test -z "$origin" +then + origin=origin +fi + # Turn the source into an absolute path if # it is local repo="$1" @@ -130,6 +203,28 @@ yes) GIT_DIR="$D/.git" ;; esac +if test -n "$reference" +then + if test -d "$reference" + then + if test -d "$reference/.git/objects" + then + reference="$reference/.git" + fi + reference=$(cd "$reference" && pwd) + echo "$reference/objects" >"$GIT_DIR/objects/info/alternates" + (cd "$reference" && tar cf - refs) | + (cd "$GIT_DIR/refs" && + mkdir reference-tmp && + cd reference-tmp && + tar xf -) + else + echo >&2 "$reference: not a local directory." && usage + fi +fi + +rm -f "$GIT_DIR/CLONE_HEAD" + # We do local magic only when the user tells us to. case "$local,$use_local" in yes,yes) @@ -165,24 +260,14 @@ yes,yes) } >"$GIT_DIR/objects/info/alternates" ;; esac - - # Make a duplicate of refs and HEAD pointer - HEAD= - if test -f "$repo/HEAD" - then - HEAD=HEAD - fi - (cd "$repo" && tar cf - refs $HEAD) | - (cd "$GIT_DIR" && tar xf -) || exit 1 + git-ls-remote "$repo" >"$GIT_DIR/CLONE_HEAD" ;; *) case "$repo" in rsync://*) rsync $quiet -av --ignore-existing \ - --exclude info "$repo/objects/" "$GIT_DIR/objects/" && - rsync $quiet -av --ignore-existing \ - --exclude info "$repo/refs/" "$GIT_DIR/refs/" || exit - + --exclude info "$repo/objects/" "$GIT_DIR/objects/" || + exit # Look at objects/info/alternates for rsync -- http will # support it natively and git native ones will do it on the # remote end. Not having that file is not a crime. @@ -205,6 +290,7 @@ yes,yes) done rm -f "$GIT_DIR/TMP_ALT" fi + git-ls-remote "$repo" >"$GIT_DIR/CLONE_HEAD" ;; http://*) if test -z "@@NO_CURL@@" @@ -217,38 +303,89 @@ yes,yes) ;; *) cd "$D" && case "$upload_pack" in - '') git-clone-pack $quiet "$repo" ;; - *) git-clone-pack $quiet "$upload_pack" "$repo" ;; - esac || { - echo >&2 "clone-pack from '$repo' failed." + '') git-fetch-pack --all -k $quiet "$repo" ;; + *) git-fetch-pack --all -k $quiet "$upload_pack" "$repo" ;; + esac >"$GIT_DIR/CLONE_HEAD" || { + echo >&2 "fetch-pack from '$repo' failed." exit 1 } ;; esac ;; esac +test -d "$GIT_DIR/refs/reference-tmp" && rm -fr "$GIT_DIR/refs/reference-tmp" + +if test -f "$GIT_DIR/CLONE_HEAD" +then + # Figure out where the remote HEAD points at. + perl -e "$copy_refs" "$GIT_DIR" "$use_separate_remote" "$origin" +fi cd "$D" || exit -if test -f "$GIT_DIR/HEAD" && test -z "$bare" +if test -z "$bare" && test -f "$GIT_DIR/REMOTE_HEAD" then - head_points_at=`git-symbolic-ref HEAD` + head_sha1=`cat "$GIT_DIR/REMOTE_HEAD"` + # Figure out which remote branch HEAD points at. + case "$use_separate_remote" in + '') remote_top=refs/heads ;; + *) remote_top="refs/remotes/$origin" ;; + esac + + # What to use to track the remote primary branch + if test -n "$use_separate_remote" + then + origin_tracking="remotes/$origin/master" + else + origin_tracking="heads/$origin" + fi + + # The name under $remote_top the remote HEAD seems to point at + head_points_at=$( + ( + echo "master" + cd "$GIT_DIR/$remote_top" && + find . -type f -print | sed -e 's/^\.\///' + ) | ( + done=f + while read name + do + test t = $done && continue + branch_tip=`cat "$GIT_DIR/$remote_top/$name"` + if test "$head_sha1" = "$branch_tip" + then + echo "$name" + done=t + fi + done + ) + ) + + # Write out remotes/$origin file. case "$head_points_at" in - refs/heads/*) - head_points_at=`expr "$head_points_at" : 'refs/heads/\(.*\)'` + ?*) mkdir -p "$GIT_DIR/remotes" && - echo >"$GIT_DIR/remotes/origin" \ + echo >"$GIT_DIR/remotes/$origin" \ "URL: $repo -Pull: $head_points_at:$origin" && - git-update-ref "refs/heads/$origin" $(git-rev-parse HEAD) && - (cd "$GIT_DIR" && find "refs/heads" -type f -print) | - while read ref +Pull: refs/heads/$head_points_at:refs/$origin_tracking" && + case "$use_separate_remote" in + t) git-update-ref HEAD "$head_sha1" ;; + *) git-update-ref "refs/heads/$origin" $(git-rev-parse HEAD) ;; + esac && + (cd "$GIT_DIR/$remote_top" && find . -type f -print) | + while read dotslref do - head=`expr "$ref" : 'refs/heads/\(.*\)'` && - test "$head_points_at" = "$head" || - test "$origin" = "$head" || - echo "Pull: ${head}:${head}" - done >>"$GIT_DIR/remotes/origin" + name=`expr "$dotslref" : './\(.*\)'` && + test "$head_points_at" = "$name" || + test "$origin" = "$name" || + echo "Pull: refs/heads/${name}:$remote_top/${name}" + done >>"$GIT_DIR/remotes/$origin" && + case "$use_separate_remote" in + t) + rm -f "refs/remotes/$origin/HEAD" + git-symbolic-ref "refs/remotes/$origin/HEAD" \ + "refs/remotes/$origin/$head_points_at" + esac esac case "$no_checkout" in @@ -256,6 +393,7 @@ Pull: $head_points_at:$origin" && git-read-tree -m -u -v HEAD HEAD esac fi +rm -f "$GIT_DIR/CLONE_HEAD" "$GIT_DIR/REMOTE_HEAD" trap - exit diff --git a/git-fetch.sh b/git-fetch.sh index 6835634..954901d 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -94,6 +94,9 @@ append_fetch_head () { # remote-nick is the URL given on the command line (or a shorthand) # remote-name is the $GIT_DIR relative refs/ path we computed # for this refspec. + + # the $note_ variable will be fed to git-fmt-merge-msg for further + # processing. case "$remote_name_" in HEAD) note_= ;; @@ -103,6 +106,9 @@ append_fetch_head () { refs/tags/*) note_="$(expr "$remote_name_" : 'refs/tags/\(.*\)')" note_="tag '$note_' of " ;; + refs/remotes/*) + note_="$(expr "$remote_name_" : 'refs/remotes/\(.*\)')" + note_="remote branch '$note_' of " ;; *) note_="$remote_name of " ;; esac @@ -147,10 +153,10 @@ fast_forward_local () { else echo >&2 "* $1: storing $3" fi - git-update-ref "$1" "$2" + git-update-ref "$1" "$2" ;; - refs/heads/*) + refs/heads/* | refs/remotes/*) # $1 is the ref being updated. # $2 is the new value for the ref. local=$(git-rev-parse --verify "$1^0" 2>/dev/null) diff --git a/git-fmt-merge-msg.perl b/git-fmt-merge-msg.perl index afe80e6..5986e54 100755 --- a/git-fmt-merge-msg.perl +++ b/git-fmt-merge-msg.perl @@ -75,6 +75,7 @@ while (<>) { $src{$src} = { BRANCH => [], TAG => [], + R_BRANCH => [], GENERIC => [], # &1 == has HEAD. # &2 == has others. @@ -91,6 +92,11 @@ while (<>) { push @{$src{$src}{TAG}}, $1; $src{$src}{HEAD_STATUS} |= 2; } + elsif (/^remote branch (.*)$/) { + $origin = $1; + push @{$src{$src}{R_BRANCH}}, $1; + $src{$src}{HEAD_STATUS} |= 2; + } elsif (/^HEAD$/) { $origin = $src; $src{$src}{HEAD_STATUS} |= 1; @@ -123,6 +129,8 @@ for my $src (@src) { } push @this, andjoin("branch ", "branches ", $src{$src}{BRANCH}); + push @this, andjoin("remote branch ", "remote branches ", + $src{$src}{R_BRANCH}); push @this, andjoin("tag ", "tags ", $src{$src}{TAG}); push @this, andjoin("commit ", "commits ", diff --git a/git-merge.sh b/git-merge.sh index cc0952a..78ab422 100755 --- a/git-merge.sh +++ b/git-merge.sh @@ -11,11 +11,15 @@ LF=' ' all_strategies='recursive octopus resolve stupid ours' -default_strategies='recursive' +default_twohead_strategies='recursive' +default_octopus_strategies='octopus' +no_trivial_merge_strategies='ours' use_strategies= + +index_merge=t if test "@@NO_PYTHON@@"; then all_strategies='resolve octopus stupid ours' - default_strategies='resolve' + default_twohead_strategies='resolve' fi dropsave() { @@ -90,8 +94,6 @@ do shift done -test "$#" -le 2 && usage ;# we need at least two heads. - merge_msg="$1" shift head_arg="$1" @@ -99,6 +101,8 @@ head=$(git-rev-parse --verify "$1"^0) || usage shift # All the rest are remote heads +test "$#" = 0 && usage ;# we need at least one remote head. + remoteheads= for remote do @@ -108,6 +112,27 @@ do done set x $remoteheads ; shift +case "$use_strategies" in +'') + case "$#" in + 1) + use_strategies="$default_twohead_strategies" ;; + *) + use_strategies="$default_octopus_strategies" ;; + esac + ;; +esac + +for s in $use_strategies +do + case " $s " in + *" $no_trivial_merge_strategies "*) + index_merge=f + break + ;; + esac +done + case "$#" in 1) common=$(git-merge-base --all $head "$@") @@ -118,18 +143,21 @@ case "$#" in esac echo "$head" >"$GIT_DIR/ORIG_HEAD" -case "$#,$common,$no_commit" in -*,'',*) +case "$index_merge,$#,$common,$no_commit" in +f,*) + # We've been told not to try anything clever. Skip to real merge. + ;; +?,*,'',*) # No common ancestors found. We need a real merge. ;; -1,"$1",*) +?,1,"$1",*) # If head can reach all the merge then we are up to date. - # but first the most common case of merging one remote + # but first the most common case of merging one remote. echo "Already up-to-date." dropsave exit 0 ;; -1,"$head",*) +?,1,"$head",*) # Again the most common case of merging one remote. echo "Updating from $head to $1" git-update-index --refresh 2>/dev/null @@ -139,11 +167,11 @@ case "$#,$common,$no_commit" in dropsave exit 0 ;; -1,?*"$LF"?*,*) +?,1,?*"$LF"?*,*) # We are not doing octopus and not fast forward. Need a # real merge. ;; -1,*,) +?,1,*,) # We are not doing octopus, not fast forward, and have only # one common. See if it is really trivial. git var GIT_COMMITTER_IDENT >/dev/null || exit @@ -188,17 +216,6 @@ esac # We are going to make a new commit. git var GIT_COMMITTER_IDENT >/dev/null || exit -case "$use_strategies" in -'') - case "$#" in - 1) - use_strategies="$default_strategies" ;; - *) - use_strategies=octopus ;; - esac - ;; -esac - # At this point, we need a real merge. No matter what strategy # we use, it would operate on the index, possibly affecting the # working tree, and when resolved cleanly, have the desired tree @@ -270,11 +287,7 @@ done # auto resolved the merge cleanly. if test '' != "$result_tree" then - parents="-p $head" - for remote - do - parents="$parents -p $remote" - done + parents=$(git-show-branch --independent "$head" "$@" | sed -e 's/^/-p /') result_commit=$(echo "$merge_msg" | git-commit-tree $result_tree $parents) || exit finish "$result_commit" "Merge $result_commit, made by $wt_strategy." dropsave diff --git a/git-parse-remote.sh b/git-parse-remote.sh index 5f158c6..63f2281 100755 --- a/git-parse-remote.sh +++ b/git-parse-remote.sh @@ -86,14 +86,14 @@ canon_refs_list_for_fetch () { local=$(expr "$ref" : '[^:]*:\(.*\)') case "$remote" in '') remote=HEAD ;; - refs/heads/* | refs/tags/*) ;; - heads/* | tags/* ) remote="refs/$remote" ;; + refs/heads/* | refs/tags/* | refs/remotes/*) ;; + heads/* | tags/* | remotes/* ) remote="refs/$remote" ;; *) remote="refs/heads/$remote" ;; esac case "$local" in '') local= ;; - refs/heads/* | refs/tags/*) ;; - heads/* | tags/* ) local="refs/$local" ;; + refs/heads/* | refs/tags/* | refs/remotes/*) ;; + heads/* | tags/* | remotes/* ) local="refs/$local" ;; *) local="refs/heads/$local" ;; esac @@ -11,6 +11,7 @@ #include "cache.h" #include "quote.h" +static int abbrev = 0; static int show_deleted = 0; static int show_cached = 0; static int show_others = 0; @@ -489,7 +490,8 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce) printf("%s%06o %s %d\t", tag, ntohl(ce->ce_mode), - sha1_to_hex(ce->sha1), + abbrev ? find_unique_abbrev(ce->sha1,abbrev) + : sha1_to_hex(ce->sha1), ce_stage(ce)); write_name_quoted("", 0, ce->name + offset, line_terminator, stdout); @@ -630,7 +632,8 @@ static void verify_pathspec(void) static const char ls_files_usage[] = "git-ls-files [-z] [-t] [-v] (--[cached|deleted|others|stage|unmerged|killed|modified])* " "[ --ignored ] [--exclude=<pattern>] [--exclude-from=<file>] " - "[ --exclude-per-directory=<filename> ] [--full-name] [--] [<file>]*"; + "[ --exclude-per-directory=<filename> ] [--full-name] [--abbrev] " + "[--] [<file>]*"; int main(int argc, const char **argv) { @@ -737,6 +740,18 @@ int main(int argc, const char **argv) error_unmatch = 1; continue; } + if (!strncmp(arg, "--abbrev=", 9)) { + abbrev = strtoul(arg+9, NULL, 10); + if (abbrev && abbrev < MINIMUM_ABBREV) + abbrev = MINIMUM_ABBREV; + else if (abbrev > 40) + abbrev = 40; + continue; + } + if (!strcmp(arg, "--abbrev")) { + abbrev = DEFAULT_ABBREV; + continue; + } if (*arg == '-') usage(ls_files_usage); break; @@ -13,13 +13,14 @@ static int line_termination = '\n'; #define LS_TREE_ONLY 2 #define LS_SHOW_TREES 4 #define LS_NAME_ONLY 8 +static int abbrev = 0; static int ls_options = 0; const char **pathspec; static int chomp_prefix = 0; static const char *prefix; static const char ls_tree_usage[] = - "git-ls-tree [-d] [-r] [-t] [-z] [--name-only] [--name-status] [--full-name] <tree-ish> [path...]"; + "git-ls-tree [-d] [-r] [-t] [-z] [--name-only] [--name-status] [--full-name] [--abbrev[=<n>]] <tree-ish> [path...]"; static int show_recursive(const char *base, int baselen, const char *pathname) { @@ -73,7 +74,9 @@ static int show_tree(unsigned char *sha1, const char *base, int baselen, return 0; if (!(ls_options & LS_NAME_ONLY)) - printf("%06o %s %s\t", mode, type, sha1_to_hex(sha1)); + printf("%06o %s %s\t", mode, type, + abbrev ? find_unique_abbrev(sha1,abbrev) + : sha1_to_hex(sha1)); write_name_quoted(base + chomp_prefix, baselen - chomp_prefix, pathname, line_termination, stdout); @@ -87,6 +90,7 @@ int main(int argc, const char **argv) struct tree *tree; prefix = setup_git_directory(); + git_config(git_default_config); if (prefix && *prefix) chomp_prefix = strlen(prefix); while (1 < argc && argv[1][0] == '-') { @@ -113,6 +117,18 @@ int main(int argc, const char **argv) chomp_prefix = 0; break; } + if (!strncmp(argv[1]+2, "abbrev=",7)) { + abbrev = strtoul(argv[1]+9, NULL, 10); + if (abbrev && abbrev < MINIMUM_ABBREV) + abbrev = MINIMUM_ABBREV; + else if (abbrev > 40) + abbrev = 40; + break; + } + if (!strcmp(argv[1]+2, "abbrev")) { + abbrev = DEFAULT_ABBREV; + break; + } /* otherwise fallthru */ default: usage(ls_tree_usage); diff --git a/merge-base.c b/merge-base.c index e73fca7..07f5ab4 100644 --- a/merge-base.c +++ b/merge-base.c @@ -237,6 +237,7 @@ int main(int argc, char **argv) unsigned char rev1key[20], rev2key[20]; setup_git_directory(); + git_config(git_default_config); while (1 < argc && argv[1][0] == '-') { char *arg = argv[1]; @@ -127,6 +127,7 @@ int main(int argc, char **argv) int as_is = 0, all = 0, transform_stdin = 0; setup_git_directory(); + git_config(git_default_config); if (argc < 2) usage(name_rev_usage); diff --git a/read-tree.c b/read-tree.c index 1c3b09b..eaff444 100644 --- a/read-tree.c +++ b/read-tree.c @@ -717,6 +717,7 @@ int main(int argc, char **argv) merge_fn_t fn = NULL; setup_git_directory(); + git_config(git_default_config); newfd = hold_index_file_for_update(&cache_file, get_index_file()); if (newfd < 0) @@ -40,13 +40,18 @@ static int bisect_list = 0; static int verbose_header = 0; static int abbrev = DEFAULT_ABBREV; static int show_parents = 0; +static int show_timestamp = 0; static int hdr_termination = 0; static const char *commit_prefix = ""; static enum cmit_fmt commit_format = CMIT_FMT_RAW; static void show_commit(struct commit *commit) { - printf("%s%s", commit_prefix, sha1_to_hex(commit->object.sha1)); + if (show_timestamp) + printf("%lu ", commit->date); + if (commit_prefix[0]) + fputs(commit_prefix, stdout); + fputs(sha1_to_hex(commit->object.sha1), stdout); if (show_parents) { struct commit_list *parents = commit->parents; while (parents) { @@ -335,6 +340,10 @@ int main(int argc, const char **argv) show_parents = 1; continue; } + if (!strcmp(arg, "--timestamp")) { + show_timestamp = 1; + continue; + } if (!strcmp(arg, "--bisect")) { bisect_list = 1; continue; diff --git a/rev-parse.c b/rev-parse.c index f90e999..19a5ef7 100644 --- a/rev-parse.c +++ b/rev-parse.c @@ -166,6 +166,8 @@ int main(int argc, char **argv) unsigned char sha1[20]; const char *prefix = setup_git_directory(); + git_config(git_default_config); + for (i = 1; i < argc; i++) { struct stat st; char *arg = argv[i]; diff --git a/send-pack.c b/send-pack.c index c8ffc8d..409f188 100644 --- a/send-pack.c +++ b/send-pack.c @@ -362,6 +362,8 @@ int main(int argc, char **argv) pid_t pid; setup_git_directory(); + git_config(git_default_config); + argv++; for (i = 1; i < argc; i++, argv++) { char *arg = *argv; diff --git a/sha1_name.c b/sha1_name.c index d67de18..4f92e12 100644 --- a/sha1_name.c +++ b/sha1_name.c @@ -235,14 +235,21 @@ static int ambiguous_path(const char *path, int len) static int get_sha1_basic(const char *str, int len, unsigned char *sha1) { - static const char *prefix[] = { - "", - "refs", - "refs/tags", - "refs/heads", + static const char *fmt[] = { + "%.*s", + "refs/%.*s", + "refs/tags/%.*s", + "refs/heads/%.*s", + "refs/remotes/%.*s", + "refs/remotes/%.*s/HEAD", NULL }; const char **p; + const char *warning = "warning: refname '%.*s' is ambiguous.\n"; + char *pathname; + int already_found = 0; + unsigned char *this_result; + unsigned char sha1_from_ref[20]; if (len == 40 && !get_sha1_hex(str, sha1)) return 0; @@ -251,11 +258,21 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1) if (ambiguous_path(str, len)) return -1; - for (p = prefix; *p; p++) { - char *pathname = git_path("%s/%.*s", *p, len, str); - if (!read_ref(pathname, sha1)) - return 0; + for (p = fmt; *p; p++) { + this_result = already_found ? sha1_from_ref : sha1; + pathname = git_path(*p, len, str); + if (!read_ref(pathname, this_result)) { + if (warn_ambiguous_refs) { + if (already_found) + fprintf(stderr, warning, len, str); + already_found++; + } + else + return 0; + } } + if (already_found) + return 0; return -1; } diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh index adc5e93..278eb66 100755 --- a/t/t5000-tar-tree.sh +++ b/t/t5000-tar-tree.sh @@ -34,6 +34,9 @@ test_expect_success \ mkdir a/bin && cp /bin/sh a/bin && ln -s a a/l1 && + (p=long_path_to_a_file && cd a && + for depth in 1 2 3 4 5; do mkdir $p && cd $p; done && + echo text >file_with_long_path) && (cd a && find .) | sort >a.lst' test_expect_success \ @@ -1,37 +1,23 @@ /* - * Copyright (c) 2005 Rene Scharfe + * Copyright (c) 2005, 2006 Rene Scharfe */ #include <time.h> #include "cache.h" #include "diff.h" #include "commit.h" +#include "strbuf.h" +#include "tar.h" #define RECORDSIZE (512) #define BLOCKSIZE (RECORDSIZE * 20) -#define TYPEFLAG_AUTO '\0' -#define TYPEFLAG_REG '0' -#define TYPEFLAG_LNK '2' -#define TYPEFLAG_DIR '5' -#define TYPEFLAG_GLOBAL_HEADER 'g' -#define TYPEFLAG_EXT_HEADER 'x' - -#define EXT_HEADER_PATH 1 -#define EXT_HEADER_LINKPATH 2 - static const char tar_tree_usage[] = "git-tar-tree <key> [basedir]"; static char block[BLOCKSIZE]; static unsigned long offset; -static const char *basedir; static time_t archive_time; -struct path_prefix { - struct path_prefix *prev; - const char *name; -}; - /* tries hard to write, either succeeds or dies in the attempt */ static void reliable_write(void *buf, unsigned long size) { @@ -119,230 +105,170 @@ static void write_blocked(void *buf, unsigned long size) write_if_needed(); } -static void append_string(char **p, const char *s) -{ - unsigned int len = strlen(s); - memcpy(*p, s, len); - *p += len; -} - -static void append_char(char **p, char c) -{ - **p = c; - *p += 1; -} - -static void append_path_prefix(char **buffer, struct path_prefix *prefix) +static void strbuf_append_string(struct strbuf *sb, const char *s) { - if (!prefix) - return; - append_path_prefix(buffer, prefix->prev); - append_string(buffer, prefix->name); - append_char(buffer, '/'); -} - -static unsigned int path_prefix_len(struct path_prefix *prefix) -{ - if (!prefix) - return 0; - return path_prefix_len(prefix->prev) + strlen(prefix->name) + 1; -} - -static void append_path(char **p, int is_dir, const char *basepath, - struct path_prefix *prefix, const char *path) -{ - if (basepath) { - append_string(p, basepath); - append_char(p, '/'); + int slen = strlen(s); + int total = sb->len + slen; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; } - append_path_prefix(p, prefix); - append_string(p, path); - if (is_dir) - append_char(p, '/'); + memcpy(sb->buf + sb->len, s, slen); + sb->len = total; } -static unsigned int path_len(int is_dir, const char *basepath, - struct path_prefix *prefix, const char *path) -{ - unsigned int len = 0; - if (basepath) - len += strlen(basepath) + 1; - len += path_prefix_len(prefix) + strlen(path); - if (is_dir) - len++; - return len; -} - -static void append_extended_header_prefix(char **p, unsigned int size, - const char *keyword) +/* + * pax extended header records have the format "%u %s=%s\n". %u contains + * the size of the whole string (including the %u), the first %s is the + * keyword, the second one is the value. This function constructs such a + * string and appends it to a struct strbuf. + */ +static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword, + const char *value, unsigned int valuelen) { - int len = sprintf(*p, "%u %s=", size, keyword); - *p += len; -} + char *p; + int len, total, tmp; -static unsigned int extended_header_len(const char *keyword, - unsigned int valuelen) -{ /* "%u %s=%s\n" */ - unsigned int len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; - if (len > 9) - len++; - if (len > 99) + len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; + for (tmp = len; tmp > 9; tmp /= 10) len++; - return len; -} -static void append_extended_header(char **p, const char *keyword, - const char *value, unsigned int len) -{ - unsigned int size = extended_header_len(keyword, len); - append_extended_header_prefix(p, size, keyword); - memcpy(*p, value, len); - *p += len; - append_char(p, '\n'); -} + total = sb->len + len; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; + } -static void write_header(const unsigned char *, char, const char *, struct path_prefix *, - const char *, unsigned int, void *, unsigned long); + p = sb->buf; + p += sprintf(p, "%u %s=", len, keyword); + memcpy(p, value, valuelen); + p += valuelen; + *p = '\n'; + sb->len = total; +} -/* stores a pax extended header directly in the block buffer */ -static void write_extended_header(const char *headerfilename, int is_dir, - unsigned int flags, const char *basepath, - struct path_prefix *prefix, - const char *path, unsigned int namelen, - void *content, unsigned int contentsize) +static unsigned int ustar_header_chksum(const struct ustar_header *header) { - char *buffer, *p; - unsigned int pathlen, size, linkpathlen = 0; - - size = pathlen = extended_header_len("path", namelen); - if (flags & EXT_HEADER_LINKPATH) { - linkpathlen = extended_header_len("linkpath", contentsize); - size += linkpathlen; - } - write_header(NULL, TYPEFLAG_EXT_HEADER, NULL, NULL, headerfilename, - 0100600, NULL, size); - - buffer = p = malloc(size); - if (!buffer) - die("git-tar-tree: %s", strerror(errno)); - append_extended_header_prefix(&p, pathlen, "path"); - append_path(&p, is_dir, basepath, prefix, path); - append_char(&p, '\n'); - if (flags & EXT_HEADER_LINKPATH) - append_extended_header(&p, "linkpath", content, contentsize); - write_blocked(buffer, size); - free(buffer); + char *p = (char *)header; + unsigned int chksum = 0; + while (p < header->chksum) + chksum += *p++; + chksum += sizeof(header->chksum) * ' '; + p += sizeof(header->chksum); + while (p < (char *)header + sizeof(struct ustar_header)) + chksum += *p++; + return chksum; } -static void write_global_extended_header(const unsigned char *sha1) +static int get_path_prefix(const struct strbuf *path, int maxlen) { - char *p; - unsigned int size; - - size = extended_header_len("comment", 40); - write_header(NULL, TYPEFLAG_GLOBAL_HEADER, NULL, NULL, - "pax_global_header", 0100600, NULL, size); - - p = get_record(); - append_extended_header(&p, "comment", sha1_to_hex(sha1), 40); - write_if_needed(); + int i = path->len; + if (i > maxlen) + i = maxlen; + while (i > 0 && path->buf[i] != '/') + i--; + return i; } -/* stores a ustar header directly in the block buffer */ -static void write_header(const unsigned char *sha1, char typeflag, const char *basepath, - struct path_prefix *prefix, const char *path, - unsigned int mode, void *buffer, unsigned long size) +static void write_entry(const unsigned char *sha1, struct strbuf *path, + unsigned int mode, void *buffer, unsigned long size) { - unsigned int namelen; - char *header = NULL; - unsigned int checksum = 0; - int i; - unsigned int ext_header = 0; - - if (typeflag == TYPEFLAG_AUTO) { - if (S_ISDIR(mode)) - typeflag = TYPEFLAG_DIR; - else if (S_ISLNK(mode)) - typeflag = TYPEFLAG_LNK; - else - typeflag = TYPEFLAG_REG; - } - - namelen = path_len(S_ISDIR(mode), basepath, prefix, path); - if (namelen > 100) - ext_header |= EXT_HEADER_PATH; - if (typeflag == TYPEFLAG_LNK && size > 100) - ext_header |= EXT_HEADER_LINKPATH; - - /* the extended header must be written before the normal one */ - if (ext_header) { - char headerfilename[51]; - sprintf(headerfilename, "%s.paxheader", sha1_to_hex(sha1)); - write_extended_header(headerfilename, S_ISDIR(mode), - ext_header, basepath, prefix, path, - namelen, buffer, size); - } - - header = get_record(); - - if (ext_header) { - sprintf(header, "%s.data", sha1_to_hex(sha1)); + struct ustar_header header; + struct strbuf ext_header; + + memset(&header, 0, sizeof(header)); + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + + if (!sha1) { + *header.typeflag = TYPEFLAG_GLOBAL_HEADER; + mode = 0100666; + strcpy(header.name, "pax_global_header"); + } else if (!path) { + *header.typeflag = TYPEFLAG_EXT_HEADER; + mode = 0100666; + sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1)); } else { - char *p = header; - append_path(&p, S_ISDIR(mode), basepath, prefix, path); + if (S_ISDIR(mode)) { + *header.typeflag = TYPEFLAG_DIR; + mode |= 0777; + } else if (S_ISLNK(mode)) { + *header.typeflag = TYPEFLAG_LNK; + mode |= 0777; + } else if (S_ISREG(mode)) { + *header.typeflag = TYPEFLAG_REG; + mode |= (mode & 0100) ? 0777 : 0666; + } else { + error("unsupported file mode: 0%o (SHA1: %s)", + mode, sha1_to_hex(sha1)); + return; + } + if (path->len > sizeof(header.name)) { + int plen = get_path_prefix(path, sizeof(header.prefix)); + int rest = path->len - plen - 1; + if (plen > 0 && rest <= sizeof(header.name)) { + memcpy(header.prefix, path->buf, plen); + memcpy(header.name, path->buf + plen + 1, rest); + } else { + sprintf(header.name, "%s.data", + sha1_to_hex(sha1)); + strbuf_append_ext_header(&ext_header, "path", + path->buf, path->len); + } + } else + memcpy(header.name, path->buf, path->len); } - if (typeflag == TYPEFLAG_LNK) { - if (ext_header & EXT_HEADER_LINKPATH) { - sprintf(&header[157], "see %s.paxheader", + if (S_ISLNK(mode) && buffer) { + if (size > sizeof(header.linkname)) { + sprintf(header.linkname, "see %s.paxheader", sha1_to_hex(sha1)); - } else { - if (buffer) - strncpy(&header[157], buffer, size); - } + strbuf_append_ext_header(&ext_header, "linkpath", + buffer, size); + } else + memcpy(header.linkname, buffer, size); } - if (S_ISDIR(mode)) - mode |= 0777; - else if (S_ISREG(mode)) - mode |= (mode & 0100) ? 0777 : 0666; - else if (S_ISLNK(mode)) - mode |= 0777; - sprintf(&header[100], "%07o", mode & 07777); + sprintf(header.mode, "%07o", mode & 07777); + sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0); + sprintf(header.mtime, "%011lo", archive_time); /* XXX: should we provide more meaningful info here? */ - sprintf(&header[108], "%07o", 0); /* uid */ - sprintf(&header[116], "%07o", 0); /* gid */ - strncpy(&header[265], "git", 31); /* uname */ - strncpy(&header[297], "git", 31); /* gname */ - - if (S_ISDIR(mode) || S_ISLNK(mode)) - size = 0; - sprintf(&header[124], "%011lo", size); - sprintf(&header[136], "%011lo", archive_time); + sprintf(header.uid, "%07o", 0); + sprintf(header.gid, "%07o", 0); + strncpy(header.uname, "git", 31); + strncpy(header.gname, "git", 31); + sprintf(header.devmajor, "%07o", 0); + sprintf(header.devminor, "%07o", 0); - header[156] = typeflag; + memcpy(header.magic, "ustar", 6); + memcpy(header.version, "00", 2); - memcpy(&header[257], "ustar", 6); - memcpy(&header[263], "00", 2); + sprintf(header.chksum, "%07o", ustar_header_chksum(&header)); - sprintf(&header[329], "%07o", 0); /* devmajor */ - sprintf(&header[337], "%07o", 0); /* devminor */ - - memset(&header[148], ' ', 8); - for (i = 0; i < RECORDSIZE; i++) - checksum += header[i]; - sprintf(&header[148], "%07o", checksum & 0x1fffff); + if (ext_header.len > 0) { + write_entry(sha1, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); + } + write_blocked(&header, sizeof(header)); + if (S_ISREG(mode) && buffer && size > 0) + write_blocked(buffer, size); +} - write_if_needed(); +static void write_global_extended_header(const unsigned char *sha1) +{ + struct strbuf ext_header; + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); + write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); } -static void traverse_tree(struct tree_desc *tree, - struct path_prefix *prefix) +static void traverse_tree(struct tree_desc *tree, struct strbuf *path) { - struct path_prefix this_prefix; - this_prefix.prev = prefix; + int pathlen = path->len; while (tree->size) { const char *name; @@ -358,16 +284,19 @@ static void traverse_tree(struct tree_desc *tree, eltbuf = read_sha1_file(sha1, elttype, &eltsize); if (!eltbuf) die("cannot read %s", sha1_to_hex(sha1)); - write_header(sha1, TYPEFLAG_AUTO, basedir, - prefix, name, mode, eltbuf, eltsize); + + path->len = pathlen; + strbuf_append_string(path, name); + if (S_ISDIR(mode)) + strbuf_append_string(path, "/"); + + write_entry(sha1, path, mode, eltbuf, eltsize); + if (S_ISDIR(mode)) { struct tree_desc subtree; subtree.buf = eltbuf; subtree.size = eltsize; - this_prefix.name = name; - traverse_tree(&subtree, &this_prefix); - } else if (!S_ISLNK(mode)) { - write_blocked(eltbuf, eltsize); + traverse_tree(&subtree, path); } free(eltbuf); } @@ -375,15 +304,22 @@ static void traverse_tree(struct tree_desc *tree, int main(int argc, char **argv) { - unsigned char sha1[20]; + unsigned char sha1[20], tree_sha1[20]; struct commit *commit; struct tree_desc tree; + struct strbuf current_path; + + current_path.buf = xmalloc(PATH_MAX); + current_path.alloc = PATH_MAX; + current_path.len = current_path.eof = 0; setup_git_directory(); + git_config(git_default_config); switch (argc) { case 3: - basedir = argv[2]; + strbuf_append_string(¤t_path, argv[2]); + strbuf_append_string(¤t_path, "/"); /* FALLTHROUGH */ case 2: if (get_sha1(argv[1], sha1) < 0) @@ -397,17 +333,19 @@ int main(int argc, char **argv) if (commit) { write_global_extended_header(commit->object.sha1); archive_time = commit->date; - } - tree.buf = read_object_with_reference(sha1, "tree", &tree.size, NULL); + } else + archive_time = time(NULL); + + tree.buf = read_object_with_reference(sha1, "tree", &tree.size, + tree_sha1); if (!tree.buf) die("not a reference to a tag, commit or tree object: %s", sha1_to_hex(sha1)); - if (!archive_time) - archive_time = time(NULL); - if (basedir) - write_header((unsigned char *)"0", TYPEFLAG_DIR, NULL, NULL, - basedir, 040777, NULL, 0); - traverse_tree(&tree, NULL); + + if (current_path.len > 0) + write_entry(tree_sha1, ¤t_path, 040777, NULL, 0); + traverse_tree(&tree, ¤t_path); write_trailer(); + free(current_path.buf); return 0; } @@ -0,0 +1,25 @@ +#define TYPEFLAG_AUTO '\0' +#define TYPEFLAG_REG '0' +#define TYPEFLAG_LNK '2' +#define TYPEFLAG_DIR '5' +#define TYPEFLAG_GLOBAL_HEADER 'g' +#define TYPEFLAG_EXT_HEADER 'x' + +struct ustar_header { + char name[100]; /* 0 */ + char mode[8]; /* 100 */ + char uid[8]; /* 108 */ + char gid[8]; /* 116 */ + char size[12]; /* 124 */ + char mtime[12]; /* 136 */ + char chksum[8]; /* 148 */ + char typeflag[1]; /* 156 */ + char linkname[100]; /* 157 */ + char magic[6]; /* 257 */ + char version[2]; /* 263 */ + char uname[32]; /* 265 */ + char gname[32]; /* 297 */ + char devmajor[8]; /* 329 */ + char devminor[8]; /* 337 */ + char prefix[155]; /* 345 */ +}; diff --git a/unpack-file.c b/unpack-file.c index 07303f8..3accb97 100644 --- a/unpack-file.c +++ b/unpack-file.c @@ -30,6 +30,7 @@ int main(int argc, char **argv) usage("git-unpack-file <sha1>"); setup_git_directory(); + git_config(git_default_config); puts(create_temp_file(sha1)); return 0; diff --git a/update-ref.c b/update-ref.c index e6fbddb..ba4bf51 100644 --- a/update-ref.c +++ b/update-ref.c @@ -25,6 +25,7 @@ int main(int argc, char **argv) int fd, written; setup_git_directory(); + git_config(git_default_config); if (argc < 3 || argc > 4) usage(git_update_ref_usage); |