diff options
-rw-r--r-- | .gitignore | 1 | ||||
-rw-r--r-- | Documentation/git-rebase.txt | 76 | ||||
-rw-r--r-- | Documentation/git-repo-config.txt | 4 | ||||
-rw-r--r-- | Documentation/git-var.txt | 3 | ||||
-rw-r--r-- | Makefile | 4 | ||||
-rw-r--r-- | builtin-log.c | 39 | ||||
-rw-r--r-- | builtin.h | 1 | ||||
-rw-r--r-- | commit.c | 37 | ||||
-rw-r--r-- | commit.h | 1 | ||||
-rw-r--r-- | delta.h | 75 | ||||
-rw-r--r-- | diff-delta.c | 168 | ||||
-rw-r--r-- | diff.c | 18 | ||||
-rwxr-xr-x | git-cvsserver.perl | 20 | ||||
-rwxr-xr-x | git-fetch.sh | 16 | ||||
-rwxr-xr-x | git-rebase.sh | 62 | ||||
-rw-r--r-- | git.c | 1 | ||||
-rw-r--r-- | gsimm.c | 94 | ||||
-rw-r--r-- | gsimm.h | 28 | ||||
-rw-r--r-- | log-tree.c | 27 | ||||
-rw-r--r-- | patch-delta.c | 4 | ||||
-rw-r--r-- | rabinpoly.c | 154 | ||||
-rw-r--r-- | rabinpoly.h | 31 | ||||
-rw-r--r-- | repo-config.c | 16 | ||||
-rw-r--r-- | test-gsimm.c | 209 | ||||
-rw-r--r-- | update-index.c | 2 |
25 files changed, 928 insertions, 163 deletions
diff --git a/.gitignore b/.gitignore index 7906909b30..cdb2d53318 100644 --- a/.gitignore +++ b/.gitignore @@ -124,6 +124,7 @@ git-core-*/?* test-date test-delta test-dump-cache-tree +test-gsimm common-cmds.h *.tar.gz *.dsc diff --git a/Documentation/git-rebase.txt b/Documentation/git-rebase.txt index 4a7e67a4d2..1b482abecd 100644 --- a/Documentation/git-rebase.txt +++ b/Documentation/git-rebase.txt @@ -3,38 +3,54 @@ git-rebase(1) NAME ---- -git-rebase - Rebase local commits to new upstream head +git-rebase - Rebase local commits to a new head SYNOPSIS -------- 'git-rebase' [--onto <newbase>] <upstream> [<branch>] +'git-rebase' --continue + +'git-rebase' --abort + DESCRIPTION ----------- -git-rebase applies to <upstream> (or optionally to <newbase>) commits -from <branch> that do not appear in <upstream>. When <branch> is not -specified it defaults to the current branch (HEAD). +git-rebase replaces <branch> with a new branch of the same name. When +the --onto option is provided the new branch starts out with a HEAD equal +to <newbase>, otherwise it is equal to <upstream>. It then attempts to +create a new commit for each commit from the original <branch> that does +not exist in the <upstream> branch. -When git-rebase is complete, <branch> will be updated to point to the -newly created line of commit objects, so the previous line will not be -accessible unless there are other references to it already. +It is possible that a merge failure will prevent this process from being +completely automatic. You will have to resolve any such merge failure +and run `git rebase --continue`. If you can not resolve the merge +failure, running `git rebase --abort` will restore the original <branch> +and remove the working files found in the .dotest directory. + +Note that if <branch> is not specified on the command line, the currently +checked out branch is used. Assume the following history exists and the current branch is "topic": +------------ A---B---C topic / D---E---F---G master +------------ From this point, the result of either of the following commands: + git-rebase master git-rebase master topic would be: +------------ A'--B'--C' topic / D---E---F---G master +------------ While, starting from the same point, the result of either of the following commands: @@ -44,21 +60,33 @@ commands: would be: +------------ A'--B'--C' topic / D---E---F---G master +------------ In case of conflict, git-rebase will stop at the first problematic commit -and leave conflict markers in the tree. After resolving the conflict manually -and updating the index with the desired resolution, you can continue the -rebasing process with +and leave conflict markers in the tree. You can use git diff to locate +the markers (<<<<<<) and make edits to resolve the conflict. For each +file you edit, you need to tell git that the conflict has been resolved, +typically this would be done with + + + git update-index <filename> + + +After resolving the conflict manually and updating the index with the +desired resolution, you can continue the rebasing process with + + + git rebase --continue - git am --resolved --3way Alternatively, you can undo the git-rebase with - git reset --hard ORIG_HEAD - rm -r .dotest + + git rebase --abort OPTIONS ------- @@ -73,6 +101,28 @@ OPTIONS <branch>:: Working branch; defaults to HEAD. +--continue:: + Restart the rebasing process after having resolved a merge conflict. + +--abort:: + Restore the original branch and abort the rebase operation. + +NOTES +----- +When you rebase a branch, you are changing its history in a way that +will cause problems for anyone who already has a copy of the branch +in their repository and tries to pull updates from you. You should +understand the implications of using 'git rebase' on a repository that +you share. + +When the git rebase command is run, it will first execute a "pre-rebase" +hook if one exists. You can use this hook to do sanity checks and +reject the rebase if it isn't appropriate. Please see the template +pre-rebase hook script for an example. + +You must be in the top directory of your project to start (or continue) +a rebase. Upon completion, <branch> will be the current branch. + Author ------ Written by Junio C Hamano <junkio@cox.net> diff --git a/Documentation/git-repo-config.txt b/Documentation/git-repo-config.txt index 71f96bdd10..566cfa1836 100644 --- a/Documentation/git-repo-config.txt +++ b/Documentation/git-repo-config.txt @@ -15,6 +15,7 @@ SYNOPSIS 'git-repo-config' [type] --get-all name [value_regex] 'git-repo-config' [type] --unset name [value_regex] 'git-repo-config' [type] --unset-all name [value_regex] +'git-repo-config' -l | --list DESCRIPTION ----------- @@ -64,6 +65,9 @@ OPTIONS --unset-all:: Remove all matching lines from .git/config. +-l, --list:: + List all variables set in .git/config. + EXAMPLE ------- diff --git a/Documentation/git-var.txt b/Documentation/git-var.txt index 379571eef0..a5b1a0dbab 100644 --- a/Documentation/git-var.txt +++ b/Documentation/git-var.txt @@ -19,7 +19,8 @@ OPTIONS -l:: Cause the logical variables to be listed. In addition, all the variables of the git configuration file .git/config are listed - as well. + as well. (However, the configuration variables listing functionality + is deprecated in favor of `git-repo-config -l`.) EXAMPLE -------- @@ -614,6 +614,9 @@ test-delta$X: test-delta.c diff-delta.o patch-delta.o test-dump-cache-tree$X: dump-cache-tree.o $(GITLIBS) $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) +test-gsimm$X: test-gsimm.c gsimm.o rabinpoly.o + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^ + check: for i in *.c; do sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; done @@ -662,6 +665,7 @@ clean: rm -f *.o mozilla-sha1/*.o arm/*.o ppc/*.o compat/*.o xdiff/*.o \ $(LIB_FILE) $(XDIFF_LIB) rm -f $(ALL_PROGRAMS) $(BUILT_INS) git$X + rm -f test-date$X test-delta$X test-gsimm$X rm -f *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags rm -rf $(GIT_TARNAME) rm -f $(GIT_TARNAME).tar.gz git-core_$(GIT_VERSION)-*.tar.gz diff --git a/builtin-log.c b/builtin-log.c index 69f2911cb4..a39aed6d86 100644 --- a/builtin-log.c +++ b/builtin-log.c @@ -9,6 +9,7 @@ #include "diff.h" #include "revision.h" #include "log-tree.h" +#include "builtin.h" static int cmd_log_wc(int argc, const char **argv, char **envp, struct rev_info *rev) @@ -67,3 +68,41 @@ int cmd_log(int argc, const char **argv, char **envp) rev.diffopt.recursive = 1; return cmd_log_wc(argc, argv, envp, &rev); } + +int cmd_format_patch(int argc, const char **argv, char **envp) +{ + struct commit *commit; + struct commit **list = NULL; + struct rev_info rev; + int nr = 0; + + init_revisions(&rev); + rev.commit_format = CMIT_FMT_EMAIL; + rev.verbose_header = 1; + rev.diff = 1; + rev.diffopt.with_raw = 0; + rev.diffopt.with_stat = 1; + rev.combine_merges = 0; + rev.ignore_merges = 1; + rev.diffopt.output_format = DIFF_FORMAT_PATCH; + argc = setup_revisions(argc, argv, &rev, "HEAD"); + + prepare_revision_walk(&rev); + while ((commit = get_revision(&rev)) != NULL) { + nr++; + list = realloc(list, nr * sizeof(list[0])); + list[nr - 1] = commit; + } + while (0 <= --nr) { + int shown; + commit = list[nr]; + shown = log_tree_commit(&rev, commit); + free(commit->buffer); + commit->buffer = NULL; + if (shown) + printf("-- \n%s\n\n", git_version_string); + } + free(list); + return 0; +} + @@ -19,5 +19,6 @@ extern int cmd_version(int argc, const char **argv, char **envp); extern int cmd_whatchanged(int argc, const char **argv, char **envp); extern int cmd_show(int argc, const char **argv, char **envp); extern int cmd_log(int argc, const char **argv, char **envp); +extern int cmd_format_patch(int argc, const char **argv, char **envp); #endif @@ -36,6 +36,8 @@ enum cmit_fmt get_commit_format(const char *arg) return CMIT_FMT_FULL; if (!strcmp(arg, "=fuller")) return CMIT_FMT_FULLER; + if (!strcmp(arg, "=email")) + return CMIT_FMT_EMAIL; if (!strcmp(arg, "=oneline")) return CMIT_FMT_ONELINE; die("invalid --pretty format"); @@ -428,6 +430,10 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const c time = strtoul(date, &date, 10); tz = strtol(date, NULL, 10); + if (fmt == CMIT_FMT_EMAIL) { + what = "From"; + filler = ""; + } ret = sprintf(buf, "%s: %.*s%.*s\n", what, (fmt == CMIT_FMT_FULLER) ? 4 : 0, filler, namelen, line); @@ -435,6 +441,9 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const c case CMIT_FMT_MEDIUM: ret += sprintf(buf + ret, "Date: %s\n", show_date(time, tz)); break; + case CMIT_FMT_EMAIL: + ret += sprintf(buf + ret, "Date: %s\n", show_date(time, tz)); + break; case CMIT_FMT_FULLER: ret += sprintf(buf + ret, "%sDate: %s\n", what, show_date(time, tz)); break; @@ -445,10 +454,12 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const c return ret; } -static int is_empty_line(const char *line, int len) +static int is_empty_line(const char *line, int *len_p) { + int len = *len_p; while (len && isspace(line[len-1])) len--; + *len_p = len; return !len; } @@ -457,7 +468,8 @@ static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *com struct commit_list *parent = commit->parents; int offset; - if ((fmt == CMIT_FMT_ONELINE) || !parent || !parent->next) + if ((fmt == CMIT_FMT_ONELINE) || (fmt == CMIT_FMT_EMAIL) || + !parent || !parent->next) return 0; offset = sprintf(buf, "Merge:"); @@ -480,9 +492,15 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit { int hdr = 1, body = 0; unsigned long offset = 0; - int indent = (fmt == CMIT_FMT_ONELINE) ? 0 : 4; + int indent = 4; int parents_shown = 0; const char *msg = commit->buffer; + const char *subject = NULL; + + if (fmt == CMIT_FMT_EMAIL) + subject = "Subject: [PATCH] "; + if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL) + indent = 0; for (;;) { const char *line = msg; @@ -506,7 +524,7 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit if (hdr) { if (linelen == 1) { hdr = 0; - if (fmt != CMIT_FMT_ONELINE) + if ((fmt != CMIT_FMT_ONELINE) && !subject) buf[offset++] = '\n'; continue; } @@ -544,20 +562,29 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit continue; } - if (is_empty_line(line, linelen)) { + if (is_empty_line(line, &linelen)) { if (!body) continue; + if (subject) + continue; if (fmt == CMIT_FMT_SHORT) break; } else { body = 1; } + if (subject) { + int slen = strlen(subject); + memcpy(buf + offset, subject, slen); + offset += slen; + } memset(buf + offset, ' ', indent); memcpy(buf + offset + indent, line, linelen); offset += linelen + indent; + buf[offset++] = '\n'; if (fmt == CMIT_FMT_ONELINE) break; + subject = NULL; } while (offset && isspace(buf[offset-1])) offset--; @@ -45,6 +45,7 @@ enum cmit_fmt { CMIT_FMT_FULL, CMIT_FMT_FULLER, CMIT_FMT_ONELINE, + CMIT_FMT_EMAIL, CMIT_FMT_UNSPECIFIED, }; @@ -1,12 +1,73 @@ #ifndef DELTA_H #define DELTA_H -/* handling of delta buffers */ -extern void *diff_delta(void *from_buf, unsigned long from_size, - void *to_buf, unsigned long to_size, - unsigned long *delta_size, unsigned long max_size); -extern void *patch_delta(void *src_buf, unsigned long src_size, - void *delta_buf, unsigned long delta_size, +/* opaque object for delta index */ +struct delta_index; + +/* + * create_delta_index: compute index data from given buffer + * + * This returns a pointer to a struct delta_index that should be passed to + * subsequent create_delta() calls, or to free_delta_index(). A NULL pointer + * is returned on failure. The given buffer must not be freed nor altered + * before free_delta_index() is called. The returned pointer must be freed + * using free_delta_index(). + */ +extern struct delta_index * +create_delta_index(const void *buf, unsigned long bufsize); + +/* + * free_delta_index: free the index created by create_delta_index() + */ +extern void free_delta_index(struct delta_index *index); + +/* + * create_delta: create a delta from given index for the given buffer + * + * This function may be called multiple times with different buffers using + * the same delta_index pointer. If max_delta_size is non-zero and the + * resulting delta is to be larger than max_delta_size then NULL is returned. + * On success, a non-NULL pointer to the buffer with the delta data is + * returned and *delta_size is updated with its size. The returned buffer + * must be freed by the caller. + */ +extern void * +create_delta(const struct delta_index *index, + const void *buf, unsigned long bufsize, + unsigned long *delta_size, unsigned long max_delta_size); + +/* + * diff_delta: create a delta from source buffer to target buffer + * + * If max_delta_size is non-zero and the resulting delta is to be larger + * than max_delta_size then NULL is returned. On success, a non-NULL + * pointer to the buffer with the delta data is returned and *delta_size is + * updated with its size. The returned buffer must be freed by the caller. + */ +static inline void * +diff_delta(const void *src_buf, unsigned long src_bufsize, + const void *trg_buf, unsigned long trg_bufsize, + unsigned long *delta_size, unsigned long max_delta_size) +{ + struct delta_index *index = create_delta_index(src_buf, src_bufsize); + if (index) { + void *delta = create_delta(index, trg_buf, trg_bufsize, + delta_size, max_delta_size); + free_delta_index(index); + return delta; + } + return NULL; +} + +/* + * patch_delta: recreate target buffer given source buffer and delta data + * + * On success, a non-NULL pointer to the target buffer is returned and + * *trg_bufsize is updated with its size. On failure a NULL pointer is + * returned. The returned buffer must be freed by the caller. + */ +extern void *patch_delta(const void *src_buf, unsigned long src_size, + const void *delta_buf, unsigned long delta_size, unsigned long *dst_size); /* the smallest possible delta size is 4 bytes */ @@ -14,7 +75,7 @@ extern void *patch_delta(void *src_buf, unsigned long src_size, /* * This must be called twice on the delta data buffer, first to get the - * expected reference buffer size, and again to get the result buffer size. + * expected source buffer size, and again to get the target buffer size. */ static inline unsigned long get_delta_hdr_size(const unsigned char **datap, const unsigned char *top) diff --git a/diff-delta.c b/diff-delta.c index 1188b31cd0..fdedf94cce 100644 --- a/diff-delta.c +++ b/diff-delta.c @@ -27,53 +27,70 @@ /* block size: min = 16, max = 64k, power of 2 */ #define BLK_SIZE 16 -#define MIN(a, b) ((a) < (b) ? (a) : (b)) +/* maximum hash entry list for the same hash bucket */ +#define HASH_LIMIT 64 #define GR_PRIME 0x9e370001 #define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift)) -struct index { +struct index_entry { const unsigned char *ptr; unsigned int val; - struct index *next; + struct index_entry *next; }; -static struct index ** delta_index(const unsigned char *buf, - unsigned long bufsize, - unsigned long trg_bufsize, - unsigned int *hash_shift) +struct delta_index { + const void *src_buf; + unsigned long src_size; + unsigned int hash_shift; + struct index_entry *hash[0]; +}; + +struct delta_index * create_delta_index(const void *buf, unsigned long bufsize) { - unsigned int i, hsize, hshift, hlimit, entries, *hash_count; - const unsigned char *data; - struct index *entry, **hash; + unsigned int i, hsize, hshift, entries, *hash_count; + const unsigned char *data, *buffer = buf; + struct delta_index *index; + struct index_entry *entry, **hash; void *mem; + if (!buf || !bufsize) + return NULL; + /* determine index hash size */ entries = bufsize / BLK_SIZE; hsize = entries / 4; for (i = 4; (1 << i) < hsize && i < 31; i++); hsize = 1 << i; hshift = 32 - i; - *hash_shift = hshift; /* allocate lookup index */ - mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry)); + mem = malloc(sizeof(*index) + + sizeof(*hash) * hsize + + sizeof(*entry) * entries); if (!mem) return NULL; + index = mem; + mem = index + 1; hash = mem; - entry = mem + hsize * sizeof(*hash); + mem = hash + hsize; + entry = mem; + + index->src_buf = buf; + index->src_size = bufsize; + index->hash_shift = hshift; memset(hash, 0, hsize * sizeof(*hash)); /* allocate an array to count hash entries */ hash_count = calloc(hsize, sizeof(*hash_count)); if (!hash_count) { - free(hash); + free(index); return NULL; } /* then populate the index */ - data = buf + entries * BLK_SIZE - BLK_SIZE; - while (data >= buf) { + data = buffer + entries * BLK_SIZE - BLK_SIZE; + while (data >= buffer) { unsigned int val = adler32(0, data, BLK_SIZE); i = HASH(val, hshift); entry->ptr = data; @@ -91,27 +108,18 @@ static struct index ** delta_index(const unsigned char *buf, * bucket that would bring us to O(m*n) computing costs (m and n * corresponding to reference and target buffer sizes). * - * The more the target buffer is large, the more it is important to - * have small entry lists for each hash buckets. With such a limit - * the cost is bounded to something more like O(m+n). - */ - hlimit = (1 << 26) / trg_bufsize; - if (hlimit < 4*BLK_SIZE) - hlimit = 4*BLK_SIZE; - - /* - * Now make sure none of the hash buckets has more entries than + * Make sure none of the hash buckets has more entries than * we're willing to test. Otherwise we cull the entry list * uniformly to still preserve a good repartition across * the reference buffer. */ for (i = 0; i < hsize; i++) { - if (hash_count[i] < hlimit) + if (hash_count[i] < HASH_LIMIT) continue; entry = hash[i]; do { - struct index *keep = entry; - int skip = hash_count[i] / hlimit / 2; + struct index_entry *keep = entry; + int skip = hash_count[i] / HASH_LIMIT / 2; do { entry = entry->next; } while(--skip && entry); @@ -120,7 +128,12 @@ static struct index ** delta_index(const unsigned char *buf, } free(hash_count); - return hash; + return index; +} + +void free_delta_index(struct delta_index *index) +{ + free(index); } /* provide the size of the copy opcode given the block offset and size */ @@ -131,21 +144,17 @@ static struct index ** delta_index(const unsigned char *buf, /* the maximum size for any opcode */ #define MAX_OP_SIZE COPYOP_SIZE(0xffffffff, 0xffffffff) -void *diff_delta(void *from_buf, unsigned long from_size, - void *to_buf, unsigned long to_size, - unsigned long *delta_size, - unsigned long max_size) +void * +create_delta(const struct delta_index *index, + const void *trg_buf, unsigned long trg_size, + unsigned long *delta_size, unsigned long max_size) { unsigned int i, outpos, outsize, hash_shift; int inscnt; const unsigned char *ref_data, *ref_top, *data, *top; unsigned char *out; - struct index *entry, **hash; - if (!from_size || !to_size) - return NULL; - hash = delta_index(from_buf, from_size, to_size, &hash_shift); - if (!hash) + if (!trg_buf || !trg_size) return NULL; outpos = 0; @@ -153,60 +162,55 @@ void *diff_delta(void *from_buf, unsigned long from_size, if (max_size && outsize >= max_size) outsize = max_size + MAX_OP_SIZE + 1; out = malloc(outsize); - if (!out) { - free(hash); + if (!out) return NULL; - } - - ref_data = from_buf; - ref_top = from_buf + from_size; - data = to_buf; - top = to_buf + to_size; /* store reference buffer size */ - out[outpos++] = from_size; - from_size >>= 7; - while (from_size) { - out[outpos - 1] |= 0x80; - out[outpos++] = from_size; - from_size >>= 7; + i = index->src_size; + while (i >= 0x80) { + out[outpos++] = i | 0x80; + i >>= 7; } + out[outpos++] = i; /* store target buffer size */ - out[outpos++] = to_size; - to_size >>= 7; - while (to_size) { - out[outpos - 1] |= 0x80; - out[outpos++] = to_size; - to_size >>= 7; + i = trg_size; + while (i >= 0x80) { + out[outpos++] = i | 0x80; + i >>= 7; } + out[outpos++] = i; + ref_data = index->src_buf; + ref_top = ref_data + index->src_size; + data = trg_buf; + top = trg_buf + trg_size; + hash_shift = index->hash_shift; inscnt = 0; while (data < top) { unsigned int moff = 0, msize = 0; - if (data + BLK_SIZE <= top) { - unsigned int val = adler32(0, data, BLK_SIZE); - i = HASH(val, hash_shift); - for (entry = hash[i]; entry; entry = entry->next) { - const unsigned char *ref = entry->ptr; - const unsigned char *src = data; - unsigned int ref_size = ref_top - ref; - if (entry->val != val) - continue; - if (ref_size > top - src) - ref_size = top - src; - if (ref_size > 0x10000) - ref_size = 0x10000; - if (ref_size <= msize) - break; - while (ref_size-- && *src++ == *ref) - ref++; - if (msize < ref - entry->ptr) { - /* this is our best match so far */ - msize = ref - entry->ptr; - moff = entry->ptr - ref_data; - } + struct index_entry *entry; + unsigned int val = adler32(0, data, BLK_SIZE); + i = HASH(val, hash_shift); + for (entry = index->hash[i]; entry; entry = entry->next) { + const unsigned char *ref = entry->ptr; + const unsigned char *src = data; + unsigned int ref_size = ref_top - ref; + if (entry->val != val) + continue; + if (ref_size > top - src) + ref_size = top - src; + if (ref_size > 0x10000) + ref_size = 0x10000; + if (ref_size <= msize) + break; + while (ref_size-- && *src++ == *ref) + ref++; + if (msize < ref - entry->ptr) { + /* this is our best match so far */ + msize = ref - entry->ptr; + moff = entry->ptr - ref_data; } } @@ -271,7 +275,6 @@ void *diff_delta(void *from_buf, unsigned long from_size, out = realloc(out, outsize); if (!out) { free(tmp); - free(hash); return NULL; } } @@ -280,7 +283,6 @@ void *diff_delta(void *from_buf, unsigned long from_size, if (inscnt) out[outpos - inscnt - 1] = inscnt; - free(hash); *delta_size = outpos; return out; } @@ -485,7 +485,8 @@ static void builtin_diff(const char *name_a, static void builtin_diffstat(const char *name_a, const char *name_b, struct diff_filespec *one, struct diff_filespec *two, - struct diffstat_t *diffstat) + struct diffstat_t *diffstat, + int complete_rewrite) { mmfile_t mf1, mf2; struct diffstat_file *data; @@ -496,7 +497,13 @@ static void builtin_diffstat(const char *name_a, const char *name_b, data->is_unmerged = 1; return; } - + if (complete_rewrite) { + diff_populate_filespec(one, 0); + diff_populate_filespec(two, 0); + data->deleted = count_lines(one->data, one->size); + data->added = count_lines(two->data, two->size); + return; + } if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) die("unable to read files to diff"); @@ -1055,10 +1062,11 @@ static void run_diffstat(struct diff_filepair *p, struct diff_options *o, { const char *name; const char *other; + int complete_rewrite = 0; if (DIFF_PAIR_UNMERGED(p)) { /* unmerged */ - builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat); + builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat, 0); return; } @@ -1068,7 +1076,9 @@ static void run_diffstat(struct diff_filepair *p, struct diff_options *o, diff_fill_sha1_info(p->one); diff_fill_sha1_info(p->two); - builtin_diffstat(name, other, p->one, p->two, diffstat); + if (p->status == DIFF_STATUS_MODIFIED && p->score) + complete_rewrite = 1; + builtin_diffstat(name, other, p->one, p->two, diffstat, complete_rewrite); } void diff_setup(struct diff_options *options) diff --git a/git-cvsserver.perl b/git-cvsserver.perl index 7d3f78e375..11d153c4cd 100755 --- a/git-cvsserver.perl +++ b/git-cvsserver.perl @@ -88,7 +88,7 @@ my $TEMP_DIR = tempdir( CLEANUP => 1 ); $log->debug("Temporary directory is '$TEMP_DIR'"); # if we are called with a pserver argument, -# deal with the authentication cat before entereing the +# deal with the authentication cat before entering the # main loop if (@ARGV && $ARGV[0] eq 'pserver') { my $line = <STDIN>; chomp $line; @@ -117,7 +117,7 @@ while (<STDIN>) { chomp; - # Check to see if we've seen this method, and call appropiate function. + # Check to see if we've seen this method, and call appropriate function. if ( /^([\w-]+)(?:\s+(.*))?$/ and defined($methods->{$1}) ) { # use the $methods hash to call the appropriate sub for this command @@ -171,11 +171,11 @@ sub req_Root return 0; } - my @gitvars = `git-var -l`; + my @gitvars = `git-repo-config -l`; if ($?) { - print "E problems executing git-var on the server -- this is not a git repository or the PATH is not set correcly.\n"; + print "E problems executing git-repo-config on the server -- this is not a git repository or the PATH is not set correctly.\n"; print "E \n"; - print "error 1 - problem executing git-var\n"; + print "error 1 - problem executing git-repo-config\n"; return 0; } foreach my $line ( @gitvars ) @@ -224,7 +224,7 @@ sub req_Globaloption sub req_Validresponses { my ( $cmd, $data ) = @_; - $log->debug("req_Validrepsonses : $data"); + $log->debug("req_Validresponses : $data"); # TODO : re-enable this, currently it's not particularly useful #$state->{validresponses} = [ split /\s+/, $data ]; @@ -733,7 +733,7 @@ sub req_update argsplit("update"); # - # It may just be a client exploring the available heads/modukles + # It may just be a client exploring the available heads/modules # in that case, list them as top level directories and leave it # at that. Eclipse uses this technique to offer you a list of # projects (heads in this case) to checkout. @@ -1731,7 +1731,7 @@ sub transmitfile } # This method takes a file name, and returns ( $dirpart, $filepart ) which -# refers to the directory porition and the file portion of the filename +# refers to the directory portion and the file portion of the filename # respectively sub filenamesplit { @@ -1790,7 +1790,7 @@ Log::Log4perl =head2 new Creates a new log object, optionally you can specify a filename here to -indicate the file to log to. If no log file is specified, you can specifiy one +indicate the file to log to. If no log file is specified, you can specify one later with method setfile, or indicate you no longer want logging with method nofile. @@ -2595,7 +2595,7 @@ sub in_array =head2 safe_pipe_capture -an alterative to `command` that allows input to be passed as an array +an alternative to `command` that allows input to be passed as an array to work around shell problems with weird characters in arguments =cut diff --git a/git-fetch.sh b/git-fetch.sh index 83143f82cf..280f62e4b7 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -270,14 +270,22 @@ fetch_main () { if [ -n "$GIT_SSL_NO_VERIFY" ]; then curl_extra_args="-k" fi - remote_name_quoted=$(perl -e ' + max_depth=5 + depth=0 + head="ref: $remote_name" + while (expr "z$head" : "zref:" && expr $depth \< $max_depth) >/dev/null + do + remote_name_quoted=$(perl -e ' my $u = $ARGV[0]; + $u =~ s/^ref:\s*//; $u =~ s{([^-a-zA-Z0-9/.])}{sprintf"%%%02x",ord($1)}eg; print "$u"; - ' "$remote_name") - head=$(curl -nsfL $curl_extra_args "$remote/$remote_name_quoted") && + ' "$head") + head=$(curl -nsfL $curl_extra_args "$remote/$remote_name_quoted") + depth=$( expr \( $depth + 1 \) ) + done expr "z$head" : "z$_x40\$" >/dev/null || - die "Failed to fetch $remote_name from $remote" + die "Failed to fetch $remote_name from $remote" echo >&2 Fetching "$remote_name from $remote" using http git-http-fetch -v -a "$head" "$remote/" || exit ;; diff --git a/git-rebase.sh b/git-rebase.sh index f7b2b9401a..9e259028e0 100755 --- a/git-rebase.sh +++ b/git-rebase.sh @@ -4,37 +4,51 @@ # USAGE='[--onto <newbase>] <upstream> [<branch>]' -LONG_USAGE='git-rebase applies to <upstream> (or optionally to <newbase>) commits -from <branch> that do not appear in <upstream>. When <branch> is not -specified it defaults to the current branch (HEAD). - -When git-rebase is complete, <branch> will be updated to point to the -newly created line of commit objects, so the previous line will not be -accessible unless there are other references to it already. - -Assuming the following history: - - A---B---C topic - / - D---E---F---G master - -The result of the following command: - - git-rebase --onto master~1 master topic - - would be: - - A'\''--B'\''--C'\'' topic - / - D---E---F---G master +LONG_USAGE='git-rebase replaces <branch> with a new branch of the +same name. When the --onto option is provided the new branch starts +out with a HEAD equal to <newbase>, otherwise it is equal to <upstream> +It then attempts to create a new commit for each commit from the original +<branch> that does not exist in the <upstream> branch. + +It is possible that a merge failure will prevent this process from being +completely automatic. You will have to resolve any such merge failure +and run git-rebase --continue. If you can not resolve the merge failure, +running git-rebase --abort will restore the original <branch> and remove +the working files found in the .dotest directory. + +Note that if <branch> is not specified on the command line, the +currently checked out branch is used. You must be in the top +directory of your project to start (or continue) a rebase. + +Example: git-rebase master~1 topic + + A---B---C topic A'\''--B'\''--C'\'' topic + / --> / + D---E---F---G master D---E---F---G master ' - . git-sh-setup unset newbase while case "$#" in 0) break ;; esac do case "$1" in + --continue) + diff=$(git-diff-files) + case "$diff" in + ?*) echo "You must edit all merge conflicts and then" + echo "mark them as resolved using git update-index" + exit 1 + ;; + esac + git am --resolved --3way + exit + ;; + --abort) + [ -d .dotest ] || die "No rebase in progress?" + git reset --hard ORIG_HEAD + rm -r .dotest + exit + ;; --onto) test 2 -le "$#" || usage newbase="$2" @@ -47,6 +47,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "log", cmd_log }, { "whatchanged", cmd_whatchanged }, { "show", cmd_show }, + { "fmt-patch", cmd_format_patch }, }; int i; diff --git a/gsimm.c b/gsimm.c new file mode 100644 index 0000000000..7024bf8f58 --- /dev/null +++ b/gsimm.c @@ -0,0 +1,94 @@ +#include "rabinpoly.h" +#include "gsimm.h" + +/* Has to be power of two. Since the Rabin hash only has 63 + usable bits, the number of hashes is limited to 32. + Lower powers of two could be used for speeding up processing + of very large files. */ +#define NUM_HASHES_PER_CHAR 32 + +/* Size of cache used to eliminate duplicate substrings. + Make small enough to comfortably fit in L1 cache. */ +#define DUP_CACHE_SIZE 256 + +/* For the final counting, do not count each bit individually, but + group them. Must be power of two, at most NUM_HASHES_PER_CHAR. + However, larger sizes result in higher cache usage. Use 8 bits + per group for efficient processing of large files on fast machines + with decent caches, or 4 bits for faster processing of small files + and for machines with small caches. */ +#define GROUP_BITS 4 +#define GROUP_COUNTERS (1<<GROUP_BITS) + +static void freq_to_md(u_char *md, int *freq) +{ int j, k; + + for (j = 0; j < MD_LENGTH; j++) + { u_char ch = 0; + + for (k = 0; k < 8; k++) ch = 2*ch + (freq[8*j+k] > 0); + md[j] = ch; + } + bzero (freq, sizeof(freq[0]) * MD_BITS); +} + +void gb_simm_process(u_char *data, unsigned len, u_char *md) +{ size_t j = 0; + u_int32_t ofs; + u_int32_t dup_cache[DUP_CACHE_SIZE]; + u_int32_t count [MD_BITS * (GROUP_COUNTERS/GROUP_BITS)]; + int freq[MD_BITS]; + + bzero (freq, sizeof(freq[0]) * MD_BITS); + bzero (dup_cache, DUP_CACHE_SIZE * sizeof (u_int32_t)); + bzero (count, (MD_BITS * (GROUP_COUNTERS/GROUP_BITS) * sizeof (u_int32_t))); + + /* Ignore incomplete substrings */ + while (j < len && j < RABIN_WINDOW_SIZE) rabin_slide8 (data[j++]); + + while (j < len) + { u_int64_t hash; + u_int32_t ofs, sum; + u_char idx; + int k; + + hash = rabin_slide8 (data[j++]); + + /* In order to update a much larger frequency table + with only 32 bits of checksum, randomly select a + part of the table to update. The selection should + only depend on the content of the represented data, + and be independent of the bits used for the update. + + Instead of updating 32 individual counters, process + the checksum in MD_BITS / GROUP_BITS groups of + GROUP_BITS bits, and count the frequency of each bit pattern. + */ + + idx = (hash >> 32); + sum = (u_int32_t) hash; + ofs = idx % (MD_BITS / NUM_HASHES_PER_CHAR) * NUM_HASHES_PER_CHAR; + idx %= DUP_CACHE_SIZE; + if (dup_cache[idx] != sum) + { dup_cache[idx] = sum; + for (k = 0; k < NUM_HASHES_PER_CHAR / GROUP_BITS; k++) + { count[ofs * GROUP_COUNTERS / GROUP_BITS + (sum % GROUP_COUNTERS)]++; + ofs += GROUP_BITS; + sum >>= GROUP_BITS; + } } } + + /* Distribute the occurrences of each bit group over the frequency table. */ + for (ofs = 0; ofs < MD_BITS; ofs += GROUP_BITS) + { int j; + for (j = 0; j < GROUP_COUNTERS; j++) + { int k; + for (k = 0; k < GROUP_BITS; k++) + { freq[ofs + k] += ((1<<k) & j) + ? count[ofs * GROUP_COUNTERS / GROUP_BITS + j] + : -count[ofs * GROUP_COUNTERS / GROUP_BITS + j]; + } } } + + if (md) + { rabin_reset(); + freq_to_md (md, freq); +} } diff --git a/gsimm.h b/gsimm.h new file mode 100644 index 0000000000..4b023b91a9 --- /dev/null +++ b/gsimm.h @@ -0,0 +1,28 @@ +#ifndef GSIMM_H +#define GSIMM_H + +/* Length of file message digest (MD) in bytes. Longer MD's are + better, but increase processing time for diminishing returns. + Must be multiple of NUM_HASHES_PER_CHAR / 8, and at least 24 + for good results +*/ +#define MD_LENGTH 32 +#define MD_BITS (MD_LENGTH * 8) + +/* The MIN_FILE_SIZE indicates the absolute minimal file size that + can be processed. As indicated above, the first and last + RABIN_WINDOW_SIZE - 1 bytes are skipped. + In order to get at least an average of 12 samples + per bit in the final message digest, require at least 3 * MD_LENGTH + complete windows in the file. */ +#define MIN_FILE_SIZE (3 * MD_LENGTH + 2 * (RABIN_WINDOW_SIZE - 1)) + +/* Limit matching algorithm to files less than 256 MB, so we can use + 32 bit integers everywhere without fear of overflow. For larger + files we should add logic to mmap the file by piece and accumulate + the frequency counts. */ +#define MAX_FILE_SIZE (256*1024*1024 - 1) + +void gb_simm_process(u_char *data, unsigned len, u_char *md); + +#endif diff --git a/log-tree.c b/log-tree.c index 9634c4677f..aaf2b9423f 100644 --- a/log-tree.c +++ b/log-tree.c @@ -37,12 +37,20 @@ void show_log(struct rev_info *opt, struct log_info *log, const char *sep) /* * Print header line of header.. */ - printf("%s%s", - opt->commit_format == CMIT_FMT_ONELINE ? "" : "commit ", - diff_unique_abbrev(commit->object.sha1, abbrev_commit)); - if (parent) - printf(" (from %s)", diff_unique_abbrev(parent->object.sha1, abbrev_commit)); - putchar(opt->commit_format == CMIT_FMT_ONELINE ? ' ' : '\n'); + + if (opt->commit_format == CMIT_FMT_EMAIL) + printf("From %s Thu Apr 7 15:13:13 2005\n", + sha1_to_hex(commit->object.sha1)); + else { + printf("%s%s", + opt->commit_format == CMIT_FMT_ONELINE ? "" : "commit ", + diff_unique_abbrev(commit->object.sha1, abbrev_commit)); + if (parent) + printf(" (from %s)", + diff_unique_abbrev(parent->object.sha1, + abbrev_commit)); + putchar(opt->commit_format == CMIT_FMT_ONELINE ? ' ' : '\n'); + } /* * And then the pretty-printed message itself @@ -152,15 +160,18 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log int log_tree_commit(struct rev_info *opt, struct commit *commit) { struct log_info log; + int shown; log.commit = commit; log.parent = NULL; opt->loginfo = &log; - if (!log_tree_diff(opt, commit, &log) && opt->loginfo && opt->always_show_header) { + shown = log_tree_diff(opt, commit, &log); + if (!shown && opt->loginfo && opt->always_show_header) { log.parent = NULL; show_log(opt, opt->loginfo, ""); + shown = 1; } opt->loginfo = NULL; - return 0; + return shown; } diff --git a/patch-delta.c b/patch-delta.c index d95f0d9721..8f318ed8aa 100644 --- a/patch-delta.c +++ b/patch-delta.c @@ -13,8 +13,8 @@ #include <string.h> #include "delta.h" -void *patch_delta(void *src_buf, unsigned long src_size, - void *delta_buf, unsigned long delta_size, +void *patch_delta(const void *src_buf, unsigned long src_size, + const void *delta_buf, unsigned long delta_size, unsigned long *dst_size) { const unsigned char *data, *top; diff --git a/rabinpoly.c b/rabinpoly.c new file mode 100644 index 0000000000..c26f3829c3 --- /dev/null +++ b/rabinpoly.c @@ -0,0 +1,154 @@ +/* + * + * Copyright (C) 1999 David Mazieres (dm@uun.org) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + * USA + * + */ + + /* Faster generic_fls */ + /* (c) 2002, D.Phillips and Sistina Software */ + +#include "rabinpoly.h" +#define MSB64 0x8000000000000000ULL + +static inline unsigned fls8(unsigned n) +{ + return n & 0xf0? + n & 0xc0? (n >> 7) + 7: (n >> 5) + 5: + n & 0x0c? (n >> 3) + 3: n - ((n + 1) >> 2); +} + +static inline unsigned fls16(unsigned n) +{ + return n & 0xff00? fls8(n >> 8) + 8: fls8(n); +} + +static inline unsigned fls32(unsigned n) +{ + return n & 0xffff0000? fls16(n >> 16) + 16: fls16(n); +} + +static inline unsigned fls64(unsigned long long n) /* should be u64 */ +{ + return n & 0xffffffff00000000ULL? fls32(n >> 32) + 32: fls32(n); +} + + +static u_int64_t polymod (u_int64_t nh, u_int64_t nl, u_int64_t d); +static void polymult (u_int64_t *php, u_int64_t *plp, + u_int64_t x, u_int64_t y); +static u_int64_t polymmult (u_int64_t x, u_int64_t y, u_int64_t d); + +static u_int64_t poly = 0xb15e234bd3792f63ull; // Actual polynomial +static u_int64_t T[256]; // Lookup table for mod +static int shift; + +u_int64_t append8 (u_int64_t p, u_char m) +{ return ((p << 8) | m) ^ T[p >> shift]; +} + +static u_int64_t +polymod (u_int64_t nh, u_int64_t nl, u_int64_t d) +{ int i, k; + assert (d); + k = fls64 (d) - 1; + d <<= 63 - k; + + if (nh) { + if (nh & MSB64) + nh ^= d; + for (i = 62; i >= 0; i--) + if (nh & 1ULL << i) { + nh ^= d >> (63 - i); + nl ^= d << (i + 1); + } + } + for (i = 63; i >= k; i--) + if (nl & 1ULL << i) + nl ^= d >> (63 - i); + return nl; +} + +static void +polymult (u_int64_t *php, u_int64_t *plp, u_int64_t x, u_int64_t y) +{ int i; + u_int64_t ph = 0, pl = 0; + if (x & 1) + pl = y; + for (i = 1; i < 64; i++) + if (x & (1ULL << i)) { + ph ^= y >> (64 - i); + pl ^= y << i; + } + if (php) + *php = ph; + if (plp) + *plp = pl; +} + +static u_int64_t +polymmult (u_int64_t x, u_int64_t y, u_int64_t d) +{ + u_int64_t h, l; + polymult (&h, &l, x, y); + return polymod (h, l, d); +} + +static int size = RABIN_WINDOW_SIZE; +static u_int64_t fingerprint = 0; +static int bufpos = -1; +static u_int64_t U[256]; +static u_char buf[RABIN_WINDOW_SIZE]; + +void rabin_init () +{ u_int64_t sizeshift = 1; + u_int64_t T1; + int xshift; + int i, j; + assert (poly >= 0x100); + xshift = fls64 (poly) - 1; + shift = xshift - 8; + T1 = polymod (0, 1ULL << xshift, poly); + for (j = 0; j < 256; j++) + T[j] = polymmult (j, T1, poly) | ((u_int64_t) j << xshift); + + for (i = 1; i < size; i++) + sizeshift = append8 (sizeshift, 0); + for (i = 0; i < 256; i++) + U[i] = polymmult (i, sizeshift, poly); + bzero (buf, sizeof (buf)); +} + +void +rabin_reset () +{ rabin_init(); + fingerprint = 0; + bzero (buf, sizeof (buf)); +} + +u_int64_t +rabin_slide8 (u_char m) +{ u_char om; + if (++bufpos >= size) bufpos = 0; + + om = buf[bufpos]; + buf[bufpos] = m; + fingerprint = append8 (fingerprint ^ U[om], m); + + return fingerprint; +} + diff --git a/rabinpoly.h b/rabinpoly.h new file mode 100644 index 0000000000..a19a097459 --- /dev/null +++ b/rabinpoly.h @@ -0,0 +1,31 @@ +/* + * + * Copyright (C) 2000 David Mazieres (dm@uun.org) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + * USA + * + * Translated to C and simplified by Geert Bosch (bosch@gnat.com) + */ + +#include <assert.h> +#include <strings.h> +#include <sys/types.h> + +#ifndef RABIN_WINDOW_SIZE +#define RABIN_WINDOW_SIZE 48 +#endif +void rabin_reset(); +u_int64_t rabin_slide8(u_char c); diff --git a/repo-config.c b/repo-config.c index c5ebb7668a..fa8aba7a1b 100644 --- a/repo-config.c +++ b/repo-config.c @@ -2,7 +2,7 @@ #include <regex.h> static const char git_config_set_usage[] = -"git-repo-config [ --bool | --int ] [--get | --get-all | --replace-all | --unset | --unset-all] name [value [value_regex]]"; +"git-repo-config [ --bool | --int ] [--get | --get-all | --replace-all | --unset | --unset-all] name [value [value_regex]] | --list"; static char* key = NULL; static char* value = NULL; @@ -12,6 +12,15 @@ static int do_not_match = 0; static int seen = 0; static enum { T_RAW, T_INT, T_BOOL } type = T_RAW; +static int show_all_config(const char *key_, const char *value_) +{ + if (value_) + printf("%s=%s\n", key_, value_); + else + printf("%s\n", key_); + return 0; +} + static int show_config(const char* key_, const char* value_) { if (value_ == NULL) @@ -67,7 +76,7 @@ static int get_value(const char* key_, const char* regex_) } } - i = git_config(show_config); + git_config(show_config); if (value) { printf("%s\n", value); free(value); @@ -99,6 +108,9 @@ int main(int argc, const char **argv) argv++; } + if (!strcmp(argv[1], "--list") || !strcmp(argv[1], "-l")) + return git_config(show_all_config); + switch (argc) { case 2: return get_value(argv[1], NULL); diff --git a/test-gsimm.c b/test-gsimm.c new file mode 100644 index 0000000000..bd28b7da28 --- /dev/null +++ b/test-gsimm.c @@ -0,0 +1,209 @@ +#include <unistd.h> +#include <stdlib.h> +#include <fcntl.h> +#include <libgen.h> +#include <stdio.h> +#include <assert.h> +#include <math.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/mman.h> + +#include "rabinpoly.h" +#include "gsimm.h" + +#define MIN(x,y) ((y)<(x) ? (y) : (x)) +#define MAX(x,y) ((y)>(x) ? (y) : (x)) + +/* The RABIN_WINDOW_SIZE is the size of fingerprint window used by + Rabin algorithm. This is not a modifiable parameter. + + The first RABIN_WINDOW_SIZE - 1 bytes are skipped, in order to ensure + fingerprints are good hashes. This does somewhat reduce the + influence of the first few bytes in the file (they're part of + fewer windows, like the last few bytes), but that actually isn't + so bad as files often start with fixed content that may bias comparisons. +*/ + +typedef struct fileinfo +{ char *name; + size_t length; + u_char md[MD_LENGTH]; + int match; +} File; + +int flag_verbose = 0; +int flag_debug = 0; +char *flag_relative = 0; + +char cmd[12] = " ..."; +char md_strbuf[MD_LENGTH * 2 + 1]; +u_char relative_md [MD_LENGTH]; + +File *file; +int file_count; +size_t file_bytes; + +char hex[17] = "0123456789abcdef"; + +void usage() +{ fprintf (stderr, "usage: %s [-dhvw] [-r fingerprint] file ...\n", cmd); + fprintf (stderr, " -d\tdebug output, repeate for more verbosity\n"); + fprintf (stderr, " -h\tshow this usage information\n"); + fprintf (stderr, " -r\tshow distance relative to fingerprint " + "(%u hex digits)\n", MD_LENGTH * 2); + fprintf (stderr, " -v\tverbose output, repeat for even more verbosity\n"); + fprintf (stderr, " -w\tenable warnings for suspect statistics\n"); + exit (1); +} + +int dist (u_char *l, u_char *r) +{ int j, k; + int d = 0; + + for (j = 0; j < MD_LENGTH; j++) + { u_char ch = l[j] ^ r[j]; + + for (k = 0; k < 8; k++) d += ((ch & (1<<k)) > 0); + } + + return d; +} + +char *md_to_str(u_char *md) +{ int j; + + for (j = 0; j < MD_LENGTH; j++) + { u_char ch = md[j]; + + md_strbuf[j*2] = hex[ch >> 4]; + md_strbuf[j*2+1] = hex[ch & 0xF]; + } + + md_strbuf[j*2] = 0; + return md_strbuf; +} + +void process_file (char *name) +{ int fd; + struct stat fs; + u_char *data; + File *fi = file+file_count;; + + fd = open (name, O_RDONLY, 0); + if (fd < 0) + { perror (name); + exit (2); + } + + if (fstat (fd, &fs)) + { perror (name); + exit (2); + } + + if (fs.st_size >= MIN_FILE_SIZE + && fs.st_size <= MAX_FILE_SIZE) + { fi->length = fs.st_size; + fi->name = name; + + data = (u_char *) mmap (0, fs.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + + if (data == (u_char *) -1) + { perror (name); + exit (2); + } + + gb_simm_process (data, fs.st_size, fi->md); + if (flag_relative) + { int d = dist (fi->md, relative_md); + double sim = 1.0 - MIN (1.0, (double) (d) / (MD_LENGTH * 4 - 1)); + fprintf (stdout, "%s %llu %u %s %u %3.1f\n", + md_to_str (fi->md), (long long unsigned) 0, + (unsigned) fs.st_size, name, + d, 100.0 * sim); + } + else + { + fprintf (stdout, "%s %llu %u %s\n", + md_to_str (fi->md), (long long unsigned) 0, + (unsigned) fs.st_size, name); + } + munmap (data, fs.st_size); + file_bytes += fs.st_size; + file_count++; + } else if (flag_verbose) + { fprintf (stdout, "skipping %s (size %llu)\n", name, (long long unsigned) fs.st_size); } + + close (fd); +} + +u_char *str_to_md(char *str, u_char *md) +{ int j; + + if (!md || !str) return 0; + + bzero (md, MD_LENGTH); + + for (j = 0; j < MD_LENGTH * 2; j++) + { char ch = str[j]; + + if (ch >= '0' && ch <= '9') + { md [j/2] = (md [j/2] << 4) + (ch - '0'); + } + else + { ch |= 32; + + if (ch < 'a' || ch > 'f') break; + md [j/2] = (md[j/2] << 4) + (ch - 'a' + 10); + } } + + return (j != MD_LENGTH * 2 || str[j] != 0) ? 0 : md; +} + +int main (int argc, char *argv[]) +{ int ch, j; + + strncpy (cmd, basename (argv[0]), 8); + + while ((ch = getopt(argc, argv, "dhr:vw")) != -1) + { switch (ch) + { case 'd': flag_debug++; + break; + case 'r': if (!optarg) + { fprintf (stderr, "%s: missing argument for -r\n", cmd); + return 1; + } + if (str_to_md (optarg, relative_md)) flag_relative = optarg; + else + { fprintf (stderr, "%s: not a valid fingerprint\n", optarg); + return 1; + } + break; + case 'v': flag_verbose++; + break; + case 'w': break; + default : usage(); + return (ch != 'h'); + } } + + argc -= optind; + argv += optind; + + if (argc == 0) usage(); + + rabin_reset (); + if (flag_verbose && flag_relative) + { fprintf (stdout, "distances are relative to %s\n", flag_relative); + } + + file = (File *) calloc (argc, sizeof (File)); + + for (j = 0; j < argc; j++) process_file (argv[j]); + + if (flag_verbose) + { fprintf (stdout, "%li bytes in %i files\n", (long) file_bytes, file_count); + } + + return 0; +} diff --git a/update-index.c b/update-index.c index 258a88cbea..4c6bcfaedd 100644 --- a/update-index.c +++ b/update-index.c @@ -8,6 +8,7 @@ #include "quote.h" #include "cache-tree.h" #include "tree-walk.h" +#include "cache-tree.h" /* * Default to not allowing changes to the list of files. The @@ -562,6 +563,7 @@ static int unresolve_one(const char *path) goto free_return; } + cache_tree_invalidate_path(active_cache_tree, path); remove_file_from_cache(path); if (add_cache_entry(ce_2, ADD_CACHE_OK_TO_ADD)) { error("%s: cannot add our version to the index.", path); |