diff options
36 files changed, 1114 insertions, 273 deletions
diff --git a/.gitignore b/.gitignore index 199cc310a2..afd0876218 100644 --- a/.gitignore +++ b/.gitignore @@ -116,6 +116,7 @@ git-update-index git-update-ref git-update-server-info git-upload-pack +git-upload-tar git-var git-verify-pack git-verify-tag @@ -124,6 +125,7 @@ git-write-tree git-core-*/?* test-date test-delta +test-dump-cache-tree common-cmds.h *.tar.gz *.dsc diff --git a/Documentation/Makefile b/Documentation/Makefile index 2a08f592d9..2b0efe7921 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -52,9 +52,9 @@ man1: $(DOC_MAN1) man7: $(DOC_MAN7) install: man - $(INSTALL) -d -m755 $(DESTDIR)/$(man1) $(DESTDIR)/$(man7) - $(INSTALL) $(DOC_MAN1) $(DESTDIR)/$(man1) - $(INSTALL) $(DOC_MAN7) $(DESTDIR)/$(man7) + $(INSTALL) -d -m755 $(DESTDIR)$(man1) $(DESTDIR)$(man7) + $(INSTALL) $(DOC_MAN1) $(DESTDIR)$(man1) + $(INSTALL) $(DOC_MAN7) $(DESTDIR)$(man7) # diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt index 504eb1b16a..5e9cbf875d 100644 --- a/Documentation/git-cat-file.txt +++ b/Documentation/git-cat-file.txt @@ -8,12 +8,12 @@ git-cat-file - Provide content or type information for repository objects SYNOPSIS -------- -'git-cat-file' [-t | -s | -e | <type>] <object> +'git-cat-file' [-t | -s | -e | -p | <type>] <object> DESCRIPTION ----------- Provides content or type of objects in the repository. The type -is required unless '-t' is used to find the object type, +is required unless '-t' or '-p' is used to find the object type, or '-s' is used to find the object size. OPTIONS @@ -33,6 +33,9 @@ OPTIONS Suppress all output; instead exit with zero status if <object> exists and is a valid object. +-p:: + Pretty-print the contents of <object> based on its type. + <type>:: Typically this matches the real type of <object> but asking for a type that can trivially be dereferenced from the given @@ -49,6 +52,8 @@ If '-s' is specified, the size of the <object> in bytes. If '-e' is specified, no output. +If '-p' is specified, the contents of <object> are pretty-printed. + Otherwise the raw (though uncompressed) contents of the <object> will be returned. diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt index b333f51045..94d9393372 100644 --- a/Documentation/git-clone.txt +++ b/Documentation/git-clone.txt @@ -9,8 +9,8 @@ git-clone - Clones a repository SYNOPSIS -------- [verse] -'git-clone' [-l [-s]] [-q] [-n] [--bare] [-o <name>] [-u <upload-pack>] - [--reference <repository>] +'git-clone' [--template=<template_directory>] [-l [-s]] [-q] [-n] [--bare] + [-o <name>] [-u <upload-pack>] [--reference <repository>] <repository> [<directory>] DESCRIPTION @@ -89,6 +89,11 @@ OPTIONS the command to specify non-default path for the command run on the other end. +--template=<template_directory>:: + Specify the directory from which templates will be used; + if unset the templates are taken from the installation + defined default, typically `/usr/share/git-core/templates`. + <repository>:: The (possibly remote) repository to clone from. It can be any URL git-fetch supports. @@ -210,7 +210,7 @@ DIFF_OBJS = \ diffcore-delta.o log-tree.o LIB_OBJS = \ - blob.o commit.o connect.o csum-file.o base85.o \ + blob.o commit.o connect.o csum-file.o cache-tree.o base85.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 dir.o \ @@ -496,37 +496,43 @@ $(BUILT_INS): git$X rm -f $@ && ln git$X $@ common-cmds.h: Documentation/git-*.txt - ./generate-cmdlist.sh > $@ + ./generate-cmdlist.sh > $@+ + mv $@+ $@ $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh - rm -f $@ + rm -f $@ $@+ sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ -e 's/@@NO_CURL@@/$(NO_CURL)/g' \ -e 's/@@NO_PYTHON@@/$(NO_PYTHON)/g' \ - $@.sh >$@ - chmod +x $@ + $@.sh >$@+ + chmod +x $@+ + mv $@+ $@ $(patsubst %.perl,%,$(SCRIPT_PERL)) : % : %.perl - rm -f $@ + rm -f $@ $@+ sed -e '1s|#!.*perl|#!$(PERL_PATH_SQ)|' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ - $@.perl >$@ - chmod +x $@ + $@.perl >$@+ + chmod +x $@+ + mv $@+ $@ $(patsubst %.py,%,$(SCRIPT_PYTHON)) : % : %.py - rm -f $@ + rm -f $@ $@+ sed -e '1s|#!.*python|#!$(PYTHON_PATH_SQ)|' \ -e 's|@@GIT_PYTHON_PATH@@|$(GIT_PYTHON_DIR_SQ)|g' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ - $@.py >$@ - chmod +x $@ + $@.py >$@+ + chmod +x $@+ + mv $@+ $@ git-cherry-pick: git-revert - cp $< $@ + cp $< $@+ + mv $@+ $@ git-status: git-commit - cp $< $@ + cp $< $@+ + mv $@+ $@ # These can record GIT_VERSION git$X git.spec \ @@ -620,6 +626,9 @@ test-date$X: test-date.c date.o ctype.o test-delta$X: test-delta.c diff-delta.o patch-delta.o $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^ +test-dump-cache-tree$X: dump-cache-tree.o $(GITLIBS) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) + check: for i in *.c; do sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; done @@ -653,7 +662,8 @@ install-doc: ### Maintainer's dist rules git.spec: git.spec.in - sed -e 's/@@VERSION@@/$(GIT_VERSION)/g' < $< > $@ + sed -e 's/@@VERSION@@/$(GIT_VERSION)/g' < $< > $@+ + mv $@+ $@ GIT_TARNAME=git-$(GIT_VERSION) dist: git.spec git-tar-tree @@ -680,7 +690,7 @@ dist-doc: : rm -fr .doc-tmp-dir mkdir .doc-tmp-dir .doc-tmp-dir/man1 .doc-tmp-dir/man7 - $(MAKE) -C Documentation DESTDIR=. \ + $(MAKE) -C Documentation DESTDIR=./ \ man1=../.doc-tmp-dir/man1 \ man7=../.doc-tmp-dir/man7 \ install @@ -724,4 +734,3 @@ check-docs:: *) echo "no link: $$v";; \ esac ; \ done | sort - diff --git a/builtin-add.c b/builtin-add.c index 6166f66bce..02fe38b0c4 100644 --- a/builtin-add.c +++ b/builtin-add.c @@ -8,6 +8,7 @@ #include "cache.h" #include "builtin.h" #include "dir.h" +#include "cache-tree.h" static const char builtin_add_usage[] = "git-add [-n] [-v] <filepattern>..."; @@ -117,6 +118,7 @@ static int add_file_to_index(const char *path, int verbose) die("unable to add %s to index",path); if (verbose) printf("add '%s'\n", path); + cache_tree_invalidate_path(active_cache_tree, path); return 0; } diff --git a/builtin-apply.c b/builtin-apply.c index 69c8e6a608..6a4fb9663d 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -8,6 +8,7 @@ */ #include <fnmatch.h> #include "cache.h" +#include "cache-tree.h" #include "quote.h" #include "blob.h" #include "delta.h" @@ -1935,6 +1936,7 @@ static void remove_file(struct patch *patch) if (write_index) { if (remove_file_from_cache(patch->old_name) < 0) die("unable to remove %s from index", patch->old_name); + cache_tree_invalidate_path(active_cache_tree, patch->old_name); } if (!cached) unlink(patch->old_name); @@ -2036,8 +2038,9 @@ static void create_file(struct patch *patch) if (!mode) mode = S_IFREG | 0644; - create_one_file(path, mode, buf, size); + create_one_file(path, mode, buf, size); add_index_file(path, mode, buf, size); + cache_tree_invalidate_path(active_cache_tree, path); } static void write_out_one_result(struct patch *patch) diff --git a/builtin-cat-file.c b/builtin-cat-file.c index 8ab136e981..4d36817e5f 100644 --- a/builtin-cat-file.c +++ b/builtin-cat-file.c @@ -141,7 +141,7 @@ int cmd_cat_file(int argc, const char **argv, char **envp) /* custom pretty-print here */ if (!strcmp(type, tree_type)) - return execl_git_cmd("ls-tree", argv[2], NULL); + return cmd_ls_tree(2, argv + 1, NULL); buf = read_sha1_file(sha1, type, &size); if (!buf) diff --git a/builtin-log.c b/builtin-log.c index c8feb0f795..db1912a05b 100644 --- a/builtin-log.c +++ b/builtin-log.c @@ -148,6 +148,7 @@ int cmd_format_patch(int argc, const char **argv, char **envp) int nr = 0, total, i, j; int use_stdout = 0; int numbered = 0; + int start_number = -1; int keep_subject = 0; init_revisions(&rev); @@ -171,7 +172,14 @@ int cmd_format_patch(int argc, const char **argv, char **envp) else if (!strcmp(argv[i], "-n") || !strcmp(argv[i], "--numbered")) numbered = 1; - else if (!strcmp(argv[i], "-k") || + else if (!strncmp(argv[i], "--start-number=", 15)) + start_number = strtol(argv[i] + 15, NULL, 10); + else if (!strcmp(argv[i], "--start-number")) { + i++; + if (i == argc) + die("Need a number for --start-number"); + start_number = strtol(argv[i], NULL, 10); + } else if (!strcmp(argv[i], "-k") || !strcmp(argv[i], "--keep-subject")) { keep_subject = 1; rev.total = -1; @@ -193,7 +201,9 @@ int cmd_format_patch(int argc, const char **argv, char **envp) } argc = j; - if (numbered && keep_subject < 0) + if (start_number < 0) + start_number = 1; + if (numbered && keep_subject) die ("-n and -k are mutually exclusive."); argc = setup_revisions(argc, argv, &rev, "HEAD"); @@ -219,16 +229,25 @@ int cmd_format_patch(int argc, const char **argv, char **envp) } total = nr; if (numbered) - rev.total = total; + rev.total = total + start_number - 1; while (0 <= --nr) { int shown; commit = list[nr]; - rev.nr = total - nr; + rev.nr = total - nr + (start_number - 1); if (!use_stdout) reopen_stdout(commit, rev.nr, keep_subject); shown = log_tree_commit(&rev, commit); free(commit->buffer); commit->buffer = NULL; + + /* We put one extra blank line between formatted + * patches and this flag is used by log-tree code + * to see if it needs to emit a LF before showing + * the log; when using one file per patch, we do + * not want the extra blank line. + */ + if (!use_stdout) + rev.shown_one = 0; if (shown) { if (rev.mime_boundary) printf("\n--%s%s--\n\n\n", diff --git a/builtin-read-tree.c b/builtin-read-tree.c index ec40d013c4..716f792514 100644 --- a/builtin-read-tree.c +++ b/builtin-read-tree.c @@ -9,6 +9,7 @@ #include "object.h" #include "tree.h" +#include "cache-tree.h" #include <sys/time.h> #include <signal.h> #include "builtin.h" @@ -427,6 +428,12 @@ static void verify_uptodate(struct cache_entry *ce) die("Entry '%s' not uptodate. Cannot merge.", ce->name); } +static void invalidate_ce_path(struct cache_entry *ce) +{ + if (ce) + cache_tree_invalidate_path(active_cache_tree, ce->name); +} + /* * We do not want to remove or overwrite a working tree file that * is not tracked. @@ -457,10 +464,13 @@ static int merged_entry(struct cache_entry *merge, struct cache_entry *old) *merge = *old; } else { verify_uptodate(old); + invalidate_ce_path(old); } } - else + else { verify_absent(merge->name, "overwritten"); + invalidate_ce_path(merge); + } merge->ce_flags &= ~htons(CE_STAGEMASK); add_cache_entry(merge, ADD_CACHE_OK_TO_ADD); @@ -475,6 +485,7 @@ static int deleted_entry(struct cache_entry *ce, struct cache_entry *old) verify_absent(ce->name, "removed"); ce->ce_mode = 0; add_cache_entry(ce, ADD_CACHE_OK_TO_ADD); + invalidate_ce_path(ce); return 1; } @@ -750,6 +761,7 @@ static int read_cache_unmerged(void) struct cache_entry *ce = active_cache[i]; if (ce_stage(ce)) { deleted++; + invalidate_ce_path(ce); continue; } if (deleted) @@ -760,6 +772,39 @@ static int read_cache_unmerged(void) return deleted; } +static void prime_cache_tree_rec(struct cache_tree *it, struct tree *tree) +{ + struct tree_entry_list *ent; + int cnt; + + memcpy(it->sha1, tree->object.sha1, 20); + for (cnt = 0, ent = tree->entries; ent; ent = ent->next) { + if (!ent->directory) + cnt++; + else { + struct cache_tree_sub *sub; + struct tree *subtree = (struct tree *)ent->item.tree; + if (!subtree->object.parsed) + parse_tree(subtree); + sub = cache_tree_sub(it, ent->name); + sub->cache_tree = cache_tree(); + prime_cache_tree_rec(sub->cache_tree, subtree); + cnt += sub->cache_tree->entry_count; + } + } + it->entry_count = cnt; +} + +static void prime_cache_tree(void) +{ + struct tree *tree = (struct tree *)trees->item; + if (!tree) + return; + active_cache_tree = cache_tree(); + prime_cache_tree_rec(active_cache_tree, tree); + +} + static const char read_tree_usage[] = "git-read-tree (<sha> | -m [--aggressive] [-u | -i] <sha1> [<sha2> [<sha3>]])"; static struct cache_file cache_file; @@ -861,10 +906,9 @@ int cmd_read_tree(int argc, const char **argv, char **envp) fn = twoway_merge; break; case 3: - fn = threeway_merge; - break; default: fn = threeway_merge; + cache_tree_free(&active_cache_tree); break; } @@ -875,6 +919,18 @@ int cmd_read_tree(int argc, const char **argv, char **envp) } unpack_trees(fn); + + /* + * When reading only one tree (either the most basic form, + * "-m ent" or "--reset ent" form), we can obtain a fully + * valid cache-tree because the index must match exactly + * what came from the tree. + */ + if (trees && trees->item && (!merge || (stage == 2))) { + cache_tree_free(&active_cache_tree); + prime_cache_tree(); + } + if (write_cache(newfd, active_cache, active_nr) || commit_index_file(&cache_file)) die("unable to write new index file"); diff --git a/builtin-rev-list.c b/builtin-rev-list.c index f11dbd65c1..5277d3cf12 100644 --- a/builtin-rev-list.c +++ b/builtin-rev-list.c @@ -103,6 +103,7 @@ static struct object_list **process_blob(struct blob *blob, if (obj->flags & (UNINTERESTING | SEEN)) return p; obj->flags |= SEEN; + name = strdup(name); return add_object(obj, p, path, name); } @@ -122,6 +123,7 @@ static struct object_list **process_tree(struct tree *tree, if (parse_tree(tree) < 0) die("bad tree object %s", sha1_to_hex(obj->sha1)); obj->flags |= SEEN; + name = strdup(name); p = add_object(obj, p, path, name); me.up = path; me.elem = name; @@ -134,6 +136,7 @@ static struct object_list **process_tree(struct tree *tree, p = process_tree(entry->item.tree, p, &me, entry->name); else p = process_blob(entry->item.blob, p, &me, entry->name); + free(entry->name); free(entry); entry = next; } diff --git a/builtin-rm.c b/builtin-rm.c index 9014c61556..e7793a20f5 100644 --- a/builtin-rm.c +++ b/builtin-rm.c @@ -6,6 +6,7 @@ #include "cache.h" #include "builtin.h" #include "dir.h" +#include "cache-tree.h" static const char builtin_rm_usage[] = "git-rm [-n] [-v] [-f] <filepattern>..."; @@ -117,6 +118,7 @@ int cmd_rm(int argc, const char **argv, char **envp) if (remove_file_from_cache(path)) die("git rm: unable to remove %s", path); + cache_tree_invalidate_path(active_cache_tree, path); } /* diff --git a/cache-tree.c b/cache-tree.c new file mode 100644 index 0000000000..a880c97b38 --- /dev/null +++ b/cache-tree.c @@ -0,0 +1,531 @@ +#include "cache.h" +#include "tree.h" +#include "cache-tree.h" + +#define DEBUG 0 + +struct cache_tree *cache_tree(void) +{ + struct cache_tree *it = xcalloc(1, sizeof(struct cache_tree)); + it->entry_count = -1; + return it; +} + +void cache_tree_free(struct cache_tree **it_p) +{ + int i; + struct cache_tree *it = *it_p; + + if (!it) + return; + for (i = 0; i < it->subtree_nr; i++) + if (it->down[i]) + cache_tree_free(&it->down[i]->cache_tree); + free(it->down); + free(it); + *it_p = NULL; +} + +static int subtree_name_cmp(const char *one, int onelen, + const char *two, int twolen) +{ + if (onelen < twolen) + return -1; + if (twolen < onelen) + return 1; + return memcmp(one, two, onelen); +} + +static int subtree_pos(struct cache_tree *it, const char *path, int pathlen) +{ + struct cache_tree_sub **down = it->down; + int lo, hi; + lo = 0; + hi = it->subtree_nr; + while (lo < hi) { + int mi = (lo + hi) / 2; + struct cache_tree_sub *mdl = down[mi]; + int cmp = subtree_name_cmp(path, pathlen, + mdl->name, mdl->namelen); + if (!cmp) + return mi; + if (cmp < 0) + hi = mi; + else + lo = mi + 1; + } + return -lo-1; +} + +static struct cache_tree_sub *find_subtree(struct cache_tree *it, + const char *path, + int pathlen, + int create) +{ + struct cache_tree_sub *down; + int pos = subtree_pos(it, path, pathlen); + if (0 <= pos) + return it->down[pos]; + if (!create) + return NULL; + + pos = -pos-1; + if (it->subtree_alloc <= it->subtree_nr) { + it->subtree_alloc = alloc_nr(it->subtree_alloc); + it->down = xrealloc(it->down, it->subtree_alloc * + sizeof(*it->down)); + } + it->subtree_nr++; + + down = xmalloc(sizeof(*down) + pathlen + 1); + down->cache_tree = NULL; + down->namelen = pathlen; + memcpy(down->name, path, pathlen); + down->name[pathlen] = 0; + + if (pos < it->subtree_nr) + memmove(it->down + pos + 1, + it->down + pos, + sizeof(down) * (it->subtree_nr - pos - 1)); + it->down[pos] = down; + return down; +} + +struct cache_tree_sub *cache_tree_sub(struct cache_tree *it, const char *path) +{ + int pathlen = strlen(path); + return find_subtree(it, path, pathlen, 1); +} + +void cache_tree_invalidate_path(struct cache_tree *it, const char *path) +{ + /* a/b/c + * ==> invalidate self + * ==> find "a", have it invalidate "b/c" + * a + * ==> invalidate self + * ==> if "a" exists as a subtree, remove it. + */ + const char *slash; + int namelen; + struct cache_tree_sub *down; + +#if DEBUG + fprintf(stderr, "cache-tree invalidate <%s>\n", path); +#endif + + if (!it) + return; + slash = strchr(path, '/'); + it->entry_count = -1; + if (!slash) { + int pos; + namelen = strlen(path); + pos = subtree_pos(it, path, namelen); + if (0 <= pos) { + cache_tree_free(&it->down[pos]->cache_tree); + free(it->down[pos]); + /* 0 1 2 3 4 5 + * ^ ^subtree_nr = 6 + * pos + * move 4 and 5 up one place (2 entries) + * 2 = 6 - 3 - 1 = subtree_nr - pos - 1 + */ + memmove(it->down+pos, it->down+pos+1, + sizeof(struct cache_tree_sub *) * + (it->subtree_nr - pos - 1)); + it->subtree_nr--; + } + return; + } + namelen = slash - path; + down = find_subtree(it, path, namelen, 0); + if (down) + cache_tree_invalidate_path(down->cache_tree, slash + 1); +} + +static int verify_cache(struct cache_entry **cache, + int entries) +{ + int i, funny; + + /* Verify that the tree is merged */ + funny = 0; + for (i = 0; i < entries; i++) { + struct cache_entry *ce = cache[i]; + if (ce_stage(ce)) { + if (10 < ++funny) { + fprintf(stderr, "...\n"); + break; + } + fprintf(stderr, "%s: unmerged (%s)\n", + ce->name, sha1_to_hex(ce->sha1)); + } + } + if (funny) + return -1; + + /* Also verify that the cache does not have path and path/file + * at the same time. At this point we know the cache has only + * stage 0 entries. + */ + funny = 0; + for (i = 0; i < entries - 1; i++) { + /* path/file always comes after path because of the way + * the cache is sorted. Also path can appear only once, + * which means conflicting one would immediately follow. + */ + const char *this_name = cache[i]->name; + const char *next_name = cache[i+1]->name; + int this_len = strlen(this_name); + if (this_len < strlen(next_name) && + strncmp(this_name, next_name, this_len) == 0 && + next_name[this_len] == '/') { + if (10 < ++funny) { + fprintf(stderr, "...\n"); + break; + } + fprintf(stderr, "You have both %s and %s\n", + this_name, next_name); + } + } + if (funny) + return -1; + return 0; +} + +static void discard_unused_subtrees(struct cache_tree *it) +{ + struct cache_tree_sub **down = it->down; + int nr = it->subtree_nr; + int dst, src; + for (dst = src = 0; src < nr; src++) { + struct cache_tree_sub *s = down[src]; + if (s->used) + down[dst++] = s; + else { + cache_tree_free(&s->cache_tree); + free(s); + it->subtree_nr--; + } + } +} + +int cache_tree_fully_valid(struct cache_tree *it) +{ + int i; + if (!it) + return 0; + if (it->entry_count < 0 || !has_sha1_file(it->sha1)) + return 0; + for (i = 0; i < it->subtree_nr; i++) { + if (!cache_tree_fully_valid(it->down[i]->cache_tree)) + return 0; + } + return 1; +} + +static int update_one(struct cache_tree *it, + struct cache_entry **cache, + int entries, + const char *base, + int baselen, + int missing_ok, + int dryrun) +{ + unsigned long size, offset; + char *buffer; + int i; + + if (0 <= it->entry_count && has_sha1_file(it->sha1)) + return it->entry_count; + + /* + * We first scan for subtrees and update them; we start by + * marking existing subtrees -- the ones that are unmarked + * should not be in the result. + */ + for (i = 0; i < it->subtree_nr; i++) + it->down[i]->used = 0; + + /* + * Find the subtrees and update them. + */ + for (i = 0; i < entries; i++) { + struct cache_entry *ce = cache[i]; + struct cache_tree_sub *sub; + const char *path, *slash; + int pathlen, sublen, subcnt; + + path = ce->name; + pathlen = ce_namelen(ce); + if (pathlen <= baselen || memcmp(base, path, baselen)) + break; /* at the end of this level */ + + slash = strchr(path + baselen, '/'); + if (!slash) + continue; + /* + * a/bbb/c (base = a/, slash = /c) + * ==> + * path+baselen = bbb/c, sublen = 3 + */ + sublen = slash - (path + baselen); + sub = find_subtree(it, path + baselen, sublen, 1); + if (!sub->cache_tree) + sub->cache_tree = cache_tree(); + subcnt = update_one(sub->cache_tree, + cache + i, entries - i, + path, + baselen + sublen + 1, + missing_ok, + dryrun); + i += subcnt - 1; + sub->used = 1; + } + + discard_unused_subtrees(it); + + /* + * Then write out the tree object for this level. + */ + size = 8192; + buffer = xmalloc(size); + offset = 0; + + for (i = 0; i < entries; i++) { + struct cache_entry *ce = cache[i]; + struct cache_tree_sub *sub; + const char *path, *slash; + int pathlen, entlen; + const unsigned char *sha1; + unsigned mode; + + path = ce->name; + pathlen = ce_namelen(ce); + if (pathlen <= baselen || memcmp(base, path, baselen)) + break; /* at the end of this level */ + + slash = strchr(path + baselen, '/'); + if (slash) { + entlen = slash - (path + baselen); + sub = find_subtree(it, path + baselen, entlen, 0); + if (!sub) + die("cache-tree.c: '%.*s' in '%s' not found", + entlen, path + baselen, path); + i += sub->cache_tree->entry_count - 1; + sha1 = sub->cache_tree->sha1; + mode = S_IFDIR; + } + else { + sha1 = ce->sha1; + mode = ntohl(ce->ce_mode); + entlen = pathlen - baselen; + } + if (!missing_ok && !has_sha1_file(sha1)) + return error("invalid object %s", sha1_to_hex(sha1)); + + if (!ce->ce_mode) + continue; /* entry being removed */ + + if (size < offset + entlen + 100) { + size = alloc_nr(offset + entlen + 100); + buffer = xrealloc(buffer, size); + } + offset += sprintf(buffer + offset, + "%o %.*s", mode, entlen, path + baselen); + buffer[offset++] = 0; + memcpy(buffer + offset, sha1, 20); + offset += 20; + +#if DEBUG + fprintf(stderr, "cache-tree update-one %o %.*s\n", + mode, entlen, path + baselen); +#endif + } + + if (dryrun) { + unsigned char hdr[200]; + int hdrlen; + write_sha1_file_prepare(buffer, offset, tree_type, it->sha1, + hdr, &hdrlen); + } + else + write_sha1_file(buffer, offset, tree_type, it->sha1); + free(buffer); + it->entry_count = i; +#if DEBUG + fprintf(stderr, "cache-tree update-one (%d ent, %d subtree) %s\n", + it->entry_count, it->subtree_nr, + sha1_to_hex(it->sha1)); +#endif + return i; +} + +int cache_tree_update(struct cache_tree *it, + struct cache_entry **cache, + int entries, + int missing_ok, + int dryrun) +{ + int i; + i = verify_cache(cache, entries); + if (i) + return i; + i = update_one(it, cache, entries, "", 0, missing_ok, dryrun); + if (i < 0) + return i; + return 0; +} + +static void *write_one(struct cache_tree *it, + char *path, + int pathlen, + char *buffer, + unsigned long *size, + unsigned long *offset) +{ + int i; + + /* One "cache-tree" entry consists of the following: + * path (NUL terminated) + * entry_count, subtree_nr ("%d %d\n") + * tree-sha1 (missing if invalid) + * subtree_nr "cache-tree" entries for subtrees. + */ + if (*size < *offset + pathlen + 100) { + *size = alloc_nr(*offset + pathlen + 100); + buffer = xrealloc(buffer, *size); + } + *offset += sprintf(buffer + *offset, "%.*s%c%d %d\n", + pathlen, path, 0, + it->entry_count, it->subtree_nr); + +#if DEBUG + if (0 <= it->entry_count) + fprintf(stderr, "cache-tree <%.*s> (%d ent, %d subtree) %s\n", + pathlen, path, it->entry_count, it->subtree_nr, + sha1_to_hex(it->sha1)); + else + fprintf(stderr, "cache-tree <%.*s> (%d subtree) invalid\n", + pathlen, path, it->subtree_nr); +#endif + + if (0 <= it->entry_count) { + memcpy(buffer + *offset, it->sha1, 20); + *offset += 20; + } + for (i = 0; i < it->subtree_nr; i++) { + struct cache_tree_sub *down = it->down[i]; + if (i) { + struct cache_tree_sub *prev = it->down[i-1]; + if (subtree_name_cmp(down->name, down->namelen, + prev->name, prev->namelen) <= 0) + die("fatal - unsorted cache subtree"); + } + buffer = write_one(down->cache_tree, down->name, down->namelen, + buffer, size, offset); + } + return buffer; +} + +void *cache_tree_write(struct cache_tree *root, unsigned long *size_p) +{ + char path[PATH_MAX]; + unsigned long size = 8192; + char *buffer = xmalloc(size); + + *size_p = 0; + path[0] = 0; + return write_one(root, path, 0, buffer, &size, size_p); +} + +static struct cache_tree *read_one(const char **buffer, unsigned long *size_p) +{ + const char *buf = *buffer; + unsigned long size = *size_p; + const char *cp; + char *ep; + struct cache_tree *it; + int i, subtree_nr; + + it = NULL; + /* skip name, but make sure name exists */ + while (size && *buf) { + size--; + buf++; + } + if (!size) + goto free_return; + buf++; size--; + it = cache_tree(); + + cp = buf; + it->entry_count = strtol(cp, &ep, 10); + if (cp == ep) + goto free_return; + cp = ep; + subtree_nr = strtol(cp, &ep, 10); + if (cp == ep) + goto free_return; + while (size && *buf && *buf != '\n') { + size--; + buf++; + } + if (!size) + goto free_return; + buf++; size--; + if (0 <= it->entry_count) { + if (size < 20) + goto free_return; + memcpy(it->sha1, buf, 20); + buf += 20; + size -= 20; + } + +#if DEBUG + if (0 <= it->entry_count) + fprintf(stderr, "cache-tree <%s> (%d ent, %d subtree) %s\n", + *buffer, it->entry_count, subtree_nr, + sha1_to_hex(it->sha1)); + else + fprintf(stderr, "cache-tree <%s> (%d subtrees) invalid\n", + *buffer, subtree_nr); +#endif + + /* + * Just a heuristic -- we do not add directories that often but + * we do not want to have to extend it immediately when we do, + * hence +2. + */ + it->subtree_alloc = subtree_nr + 2; + it->down = xcalloc(it->subtree_alloc, sizeof(struct cache_tree_sub *)); + for (i = 0; i < subtree_nr; i++) { + /* read each subtree */ + struct cache_tree *sub; + struct cache_tree_sub *subtree; + const char *name = buf; + + sub = read_one(&buf, &size); + if (!sub) + goto free_return; + subtree = cache_tree_sub(it, name); + subtree->cache_tree = sub; + } + if (subtree_nr != it->subtree_nr) + die("cache-tree: internal error"); + *buffer = buf; + *size_p = size; + return it; + + free_return: + cache_tree_free(&it); + return NULL; +} + +struct cache_tree *cache_tree_read(const char *buffer, unsigned long size) +{ + if (buffer[0]) + return NULL; /* not the whole tree */ + return read_one(&buffer, &size); +} diff --git a/cache-tree.h b/cache-tree.h new file mode 100644 index 0000000000..72c64801f5 --- /dev/null +++ b/cache-tree.h @@ -0,0 +1,31 @@ +#ifndef CACHE_TREE_H +#define CACHE_TREE_H + +struct cache_tree; +struct cache_tree_sub { + struct cache_tree *cache_tree; + int namelen; + int used; + char name[FLEX_ARRAY]; +}; + +struct cache_tree { + int entry_count; /* negative means "invalid" */ + unsigned char sha1[20]; + int subtree_nr; + int subtree_alloc; + struct cache_tree_sub **down; +}; + +struct cache_tree *cache_tree(void); +void cache_tree_free(struct cache_tree **); +void cache_tree_invalidate_path(struct cache_tree *, const char *); +struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *); + +void *cache_tree_write(struct cache_tree *root, unsigned long *size_p); +struct cache_tree *cache_tree_read(const char *buffer, unsigned long size); + +int cache_tree_fully_valid(struct cache_tree *); +int cache_tree_update(struct cache_tree *, struct cache_entry **, int, int, int); + +#endif @@ -114,6 +114,7 @@ static inline unsigned int create_ce_mode(unsigned int mode) extern struct cache_entry **active_cache; extern unsigned int active_nr, active_alloc, active_cache_changed; +extern struct cache_tree *active_cache_tree; #define GIT_DIR_ENVIRONMENT "GIT_DIR" #define DEFAULT_GIT_DIR_ENVIRONMENT ".git" diff --git a/checkout-index.c b/checkout-index.c index cc3a745c14..9876af6fd6 100644 --- a/checkout-index.c +++ b/checkout-index.c @@ -39,6 +39,7 @@ #include "cache.h" #include "strbuf.h" #include "quote.h" +#include "cache-tree.h" #define CHECKOUT_ALL 4 static const char *prefix; diff --git a/contrib/gitview/gitview b/contrib/gitview/gitview index 781badbc5b..b836047cf3 100755 --- a/contrib/gitview/gitview +++ b/contrib/gitview/gitview @@ -425,7 +425,7 @@ class DiffWindow: class GitView: """ This is the main class """ - version = "0.7" + version = "0.8" def __init__(self, with_diff=0): self.with_diff = with_diff @@ -449,8 +449,17 @@ class GitView: self.accel_group = gtk.AccelGroup() self.window.add_accel_group(self.accel_group) + self.accel_group.connect_group(0xffc2, 0, gtk.ACCEL_LOCKED, self.refresh); - self.construct() + self.window.add(self.construct()) + + def refresh(self, widget, event=None, *arguments, **keywords): + self.get_encoding() + self.get_bt_sha1() + Commit.children_sha1 = {} + self.set_branch(sys.argv[without_diff:]) + self.window.show() + return True def get_bt_sha1(self): """ Update the bt_sha1 dictionary with the @@ -500,9 +509,9 @@ class GitView: menu_bar.show() vbox.pack_start(menu_bar, expand=False, fill=True) vbox.pack_start(paned, expand=True, fill=True) - self.window.add(vbox) paned.show() vbox.show() + return vbox def construct_top(self): @@ -974,10 +983,15 @@ class GitView: try: self.treeview.set_cursor(self.index[revid]) except KeyError: - print "Revision %s not present in the list" % revid + dialog = gtk.MessageDialog(parent=None, flags=0, + type=gtk.MESSAGE_WARNING, buttons=gtk.BUTTONS_CLOSE, + message_format=None) + dialog.set_markup("Revision <b>%s</b> not present in the list" % revid) # revid == 0 is the parent of the first commit if (revid != 0 ): - print "Try running gitview without any options" + dialog.format_secondary_text("Try running gitview without any options") + dialog.run() + dialog.destroy() self.treeview.grab_focus() @@ -987,8 +1001,8 @@ class GitView: window.set_diff(commit_sha1, parent_sha1, encoding) self.treeview.grab_focus() +without_diff = 0 if __name__ == "__main__": - without_diff = 0 if (len(sys.argv) > 1 ): if (sys.argv[1] == "--without-diff"): diff --git a/contrib/gitview/gitview.txt b/contrib/gitview/gitview.txt index fcf759c307..e3bc4f46c2 100644 --- a/contrib/gitview/gitview.txt +++ b/contrib/gitview/gitview.txt @@ -25,6 +25,9 @@ OPTIONS <args> All the valid option for git-rev-list(1) + Key Bindings: + F5: + To reread references. EXAMPLES ------ @@ -33,6 +36,5 @@ EXAMPLES or drivers/scsi subdirectories gitview --since=2.weeks.ago - Show the changes during the last two weeks + Show the changes during the last two weeks - diff --git a/dump-cache-tree.c b/dump-cache-tree.c new file mode 100644 index 0000000000..1ccaf51773 --- /dev/null +++ b/dump-cache-tree.c @@ -0,0 +1,64 @@ +#include "cache.h" +#include "tree.h" +#include "cache-tree.h" + + +static void dump_one(struct cache_tree *it, const char *pfx, const char *x) +{ + if (it->entry_count < 0) + printf("%-40s %s%s (%d subtrees)\n", + "invalid", x, pfx, it->subtree_nr); + else + printf("%s %s%s (%d entries, %d subtrees)\n", + sha1_to_hex(it->sha1), x, pfx, + it->entry_count, it->subtree_nr); +} + +static int dump_cache_tree(struct cache_tree *it, + struct cache_tree *ref, + const char *pfx) +{ + int i; + int errs = 0; + + if (!it || !ref) + /* missing in either */ + return 0; + + if (it->entry_count < 0) { + dump_one(it, pfx, ""); + dump_one(ref, pfx, "#(ref) "); + if (it->subtree_nr != ref->subtree_nr) + errs = 1; + } + else { + dump_one(it, pfx, ""); + if (memcmp(it->sha1, ref->sha1, 20) || + ref->entry_count != it->entry_count || + ref->subtree_nr != it->subtree_nr) { + dump_one(ref, pfx, "#(ref) "); + errs = 1; + } + } + + for (i = 0; i < it->subtree_nr; i++) { + char path[PATH_MAX]; + struct cache_tree_sub *down = it->down[i]; + struct cache_tree_sub *rdwn; + + rdwn = cache_tree_sub(ref, down->name); + sprintf(path, "%s%.*s/", pfx, down->namelen, down->name); + if (dump_cache_tree(down->cache_tree, rdwn->cache_tree, path)) + errs = 1; + } + return errs; +} + +int main(int ac, char **av) +{ + struct cache_tree *another = cache_tree(); + if (read_cache() < 0) + die("unable to read index file"); + cache_tree_update(another, active_cache, active_nr, 0, 1); + return dump_cache_tree(active_cache_tree, another, ""); +} @@ -9,8 +9,6 @@ const char *write_ref = NULL; -const unsigned char *current_ref = NULL; - int get_tree = 0; int get_history = 0; int get_all = 0; @@ -205,19 +203,12 @@ static int mark_complete(const char *path, const unsigned char *sha1) int pull(char *target) { unsigned char sha1[20]; - int fd = -1; save_commit_buffer = 0; track_object_refs = 0; - if (write_ref && current_ref) { - fd = lock_ref_sha1(write_ref, current_ref); - if (fd < 0) - return -1; - } - if (!get_recover) { + if (!get_recover) for_each_ref(mark_complete); - } if (interpret_target(target, sha1)) return error("Could not interpret %s as something to pull", @@ -227,12 +218,7 @@ int pull(char *target) if (loop()) return -1; - if (write_ref) { - if (current_ref) { - write_ref_sha1(write_ref, fd, sha1); - } else { - write_ref_sha1_unlocked(write_ref, sha1); - } - } + if (write_ref) + write_ref_sha1_unlocked(write_ref, sha1); return 0; } @@ -25,9 +25,6 @@ extern int fetch_ref(char *ref, unsigned char *sha1); /* If set, the ref filename to write the target value to. */ extern const char *write_ref; -/* If set, the hash that the current value of write_ref must be. */ -extern const unsigned char *current_ref; - /* Set to fetch the target tree. */ extern int get_tree; diff --git a/fsck-objects.c b/fsck-objects.c index 59b25904cb..1922b6d84c 100644 --- a/fsck-objects.c +++ b/fsck-objects.c @@ -8,6 +8,7 @@ #include "tag.h" #include "refs.h" #include "pack.h" +#include "cache-tree.h" #define REACHABLE 0x0001 @@ -438,6 +439,28 @@ static int fsck_head_link(void) return 0; } +static int fsck_cache_tree(struct cache_tree *it) +{ + int i; + int err = 0; + + if (0 <= it->entry_count) { + struct object *obj = parse_object(it->sha1); + if (!obj) { + error("%s: invalid sha1 pointer in cache-tree", + sha1_to_hex(it->sha1)); + return 1; + } + mark_reachable(obj, REACHABLE); + obj->used = 1; + if (obj->type != tree_type) + err |= objerror(obj, "non-tree in cache-tree"); + } + for (i = 0; i < it->subtree_nr; i++) + err |= fsck_cache_tree(it->down[i]->cache_tree); + return err; +} + int main(int argc, char **argv) { int i, heads; @@ -547,6 +570,8 @@ int main(int argc, char **argv) obj->used = 1; mark_reachable(obj, REACHABLE); } + if (active_cache_tree) + fsck_cache_tree(active_cache_tree); } check_connectivity(); diff --git a/git-clone.sh b/git-clone.sh index d96894d4c2..de59904d56 100755 --- a/git-clone.sh +++ b/git-clone.sh @@ -9,7 +9,7 @@ unset CDPATH usage() { - echo >&2 "Usage: $0 [--use-separate-remote] [--reference <reference-repo>] [--bare] [-l [-s]] [-q] [-u <upload-pack>] [--origin <name>] [-n] <repo> [<dir>]" + echo >&2 "Usage: $0 [--template=<template_directory>] [--use-separate-remote] [--reference <reference-repo>] [--bare] [-l [-s]] [-q] [-u <upload-pack>] [--origin <name>] [-n] <repo> [<dir>]" exit 1 } @@ -102,6 +102,7 @@ quiet= local=no use_local=no local_shared=no +unset template no_checkout= upload_pack= bare= @@ -120,6 +121,11 @@ while *,-l|*,--l|*,--lo|*,--loc|*,--loca|*,--local) use_local=yes ;; *,-s|*,--s|*,--sh|*,--sha|*,--shar|*,--share|*,--shared) local_shared=yes; use_local=yes ;; + 1,--template) usage ;; + *,--template) + shift; template="--template=$1" ;; + *,--template=*) + template="$1" ;; *,-q|*,--quiet) quiet=-q ;; *,--use-separate-remote) use_separate_remote=t ;; @@ -203,7 +209,7 @@ trap 'err=$?; cd ..; rm -r "$D"; exit $err' 0 case "$bare" in yes) GIT_DIR="$D" ;; *) GIT_DIR="$D/.git" ;; -esac && export GIT_DIR && git-init-db || usage +esac && export GIT_DIR && git-init-db ${template+"$template"} || usage case "$bare" in yes) GIT_DIR="$D" ;; diff --git a/git-commit.sh b/git-commit.sh index 6785826fef..1983d45828 100755 --- a/git-commit.sh +++ b/git-commit.sh @@ -626,6 +626,9 @@ fi if test -z "$no_edit" then { + echo "" + echo "# Please enter the commit message for your changes." + echo "# (Comment lines starting with '#' will not be included)" test -z "$only_include_assumed" || echo "$only_include_assumed" run_status } >>"$GIT_DIR"/COMMIT_EDITMSG diff --git a/git-cvsexportcommit.perl b/git-cvsexportcommit.perl index f994443c6f..57088c3f0b 100755 --- a/git-cvsexportcommit.perl +++ b/git-cvsexportcommit.perl @@ -1,10 +1,16 @@ #!/usr/bin/perl -w +# Known limitations: +# - cannot add or remove binary files +# - does not propagate permissions +# - tells "ready for commit" even when things could not be completed +# (eg addition of a binary file) + use strict; use Getopt::Std; use File::Temp qw(tempdir); use Data::Dumper; -use File::Basename qw(basename); +use File::Basename qw(basename dirname); unless ($ENV{GIT_DIR} && -r $ENV{GIT_DIR}){ die "GIT_DIR is not defined or is unreadable"; @@ -84,7 +90,7 @@ close MSG; `git-cat-file commit $commit | sed -e '1,/^\$/d' >> .msg`; $? && die "Error extracting the commit message"; -my (@afiles, @dfiles, @mfiles); +my (@afiles, @dfiles, @mfiles, @dirs); my @files = safe_pipe_capture('git-diff-tree', '-r', $parent, $commit); #print @files; $? && die "Error in git-diff-tree"; @@ -92,7 +98,14 @@ foreach my $f (@files) { chomp $f; my @fields = split(m!\s+!, $f); if ($fields[4] eq 'A') { - push @afiles, $fields[5]; + my $path = $fields[5]; + push @afiles, $path; + # add any needed parent directories + $path = dirname $path; + while (!-d $path and ! grep { $_ eq $path } @dirs) { + unshift @dirs, $path; + $path = dirname $path; + } } if ($fields[4] eq 'M') { push @mfiles, $fields[5]; @@ -107,13 +120,21 @@ undef @files; # don't need it anymore # check that the files are clean and up to date according to cvs my $dirty; +foreach my $d (@dirs) { + if (-e $d) { + $dirty = 1; + warn "$d exists and is not a directory!\n"; + } +} foreach my $f (@afiles) { # This should return only one value my @status = grep(m/^File/, safe_pipe_capture('cvs', '-q', 'status' ,$f)); if (@status > 1) { warn 'Strange! cvs status returned more than one line?'}; - unless ($status[0] =~ m/Status: Unknown$/) { + if (-d dirname $f and $status[0] !~ m/Status: Unknown$/ + and $status[0] !~ m/^File: no file /) { $dirty = 1; warn "File $f is already known in your CVS checkout -- perhaps it has been added by another user. Or this may indicate that it exists on a different branch. If this is the case, use -f to force the merge.\n"; + warn "Status was: $status\n"; } } foreach my $f (@mfiles, @dfiles) { @@ -139,6 +160,19 @@ if ($dirty) { ### +print "Creating new directories\n"; +foreach my $d (@dirs) { + unless (mkdir $d) { + warn "Could not mkdir $d: $!"; + $dirty = 1; + } + `cvs add $d`; + if ($?) { + $dirty = 1; + warn "Failed to cvs add directory $d -- you may need to do it manually"; + } +} + print "'Patching' binary files\n"; my @bfiles = grep(m/^Binary/, safe_pipe_capture('git-diff-tree', '-p', $parent, $commit)); @@ -151,7 +185,7 @@ foreach my $f (@bfiles) { my $blob = `git-ls-tree $tree "$f" | cut -f 1 | cut -d ' ' -f 3`; chomp $blob; `git-cat-file blob $blob > $tmpdir/blob`; - if (system('cmp', '-q', $f, "$tmpdir/blob")) { + if (system('cmp', '-s', $f, "$tmpdir/blob")) { warn "Binary file $f in CVS does not match parent.\n"; $dirty = 1; next; diff --git a/git-cvsimport.perl b/git-cvsimport.perl index af331d9c43..76f6246a31 100755 --- a/git-cvsimport.perl +++ b/git-cvsimport.perl @@ -23,7 +23,7 @@ use File::Basename qw(basename dirname); use Time::Local; use IO::Socket; use IO::Pipe; -use POSIX qw(strftime dup2 :errno_h); +use POSIX qw(strftime dup2 ENOENT); use IPC::Open2; $SIG{'PIPE'}="IGNORE"; diff --git a/git-fetch.sh b/git-fetch.sh index 280f62e4b7..69bd810082 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -211,12 +211,12 @@ esac reflist=$(get_remote_refs_for_fetch "$@") if test "$tags" then - taglist=$(IFS=" " && + taglist=`IFS=" " && git-ls-remote $upload_pack --tags "$remote" | while read sha1 name do case "$name" in - (*^*) continue ;; + *^*) continue ;; esac if git-check-ref-format "$name" then @@ -224,7 +224,7 @@ then else echo >&2 "warning: tag ${name} ignored" fi - done) + done` if test "$#" -gt 1 then # remote URL plus explicit refspecs; we need to merge them. diff --git a/git-ls-remote.sh b/git-ls-remote.sh index b6882a90c1..2fdcaf7886 100755 --- a/git-ls-remote.sh +++ b/git-ls-remote.sh @@ -58,11 +58,19 @@ http://* | https://* ) ;; rsync://* ) - mkdir $tmpdir + mkdir $tmpdir && + rsync -rlq "$peek_repo/HEAD" $tmpdir && rsync -rq "$peek_repo/refs" $tmpdir || { echo "failed slurping" exit } + head=$(cat "$tmpdir/HEAD") && + case "$head" in + ref:' '*) + head=$(expr "z$head" : 'zref: \(.*\)') && + head=$(cat "$tmpdir/$head") || exit + esac && + echo "$head HEAD" (cd $tmpdir && find refs -type f) | while read path do diff --git a/mailinfo.c b/mailinfo.c index b27651935d..5b6c2157ed 100644 --- a/mailinfo.c +++ b/mailinfo.c @@ -72,11 +72,14 @@ static int bogus_from(char *line) return 1; } -static int handle_from(char *line) +static int handle_from(char *in_line) { - char *at = strchr(line, '@'); + char line[1000]; + char *at; char *dst; + strcpy(line, in_line); + at = strchr(line, '@'); if (!at) return bogus_from(line); @@ -237,38 +240,46 @@ static int eatspace(char *line) #define SEEN_FROM 01 #define SEEN_DATE 02 #define SEEN_SUBJECT 04 +#define SEEN_BOGUS_UNIX_FROM 010 +#define SEEN_PREFIX 020 /* First lines of body can have From:, Date:, and Subject: */ -static int handle_inbody_header(int *seen, char *line) +static void handle_inbody_header(int *seen, char *line) { + if (!memcmp(">From", line, 5) && isspace(line[5])) { + if (!(*seen & SEEN_BOGUS_UNIX_FROM)) { + *seen |= SEEN_BOGUS_UNIX_FROM; + return; + } + } if (!memcmp("From:", line, 5) && isspace(line[5])) { if (!(*seen & SEEN_FROM) && handle_from(line+6)) { *seen |= SEEN_FROM; - return 1; + return; } } if (!memcmp("Date:", line, 5) && isspace(line[5])) { if (!(*seen & SEEN_DATE)) { handle_date(line+6); *seen |= SEEN_DATE; - return 1; + return; } } if (!memcmp("Subject:", line, 8) && isspace(line[8])) { if (!(*seen & SEEN_SUBJECT)) { handle_subject(line+9); *seen |= SEEN_SUBJECT; - return 1; + return; } } if (!memcmp("[PATCH]", line, 7) && isspace(line[7])) { if (!(*seen & SEEN_SUBJECT)) { handle_subject(line); *seen |= SEEN_SUBJECT; - return 1; + return; } } - return 0; + *seen |= SEEN_PREFIX; } static char *cleanup_subject(char *subject) @@ -324,6 +335,7 @@ static void cleanup_space(char *buf) } } +static void decode_header_bq(char *it); typedef int (*header_fn_t)(char *); struct header_def { const char *name; @@ -331,7 +343,7 @@ struct header_def { int namelen; }; -static void check_header(char *line, int len, struct header_def *header) +static void check_header(char *line, struct header_def *header) { int i; @@ -343,13 +355,17 @@ static void check_header(char *line, int len, struct header_def *header) int len = header[i].namelen; if (!strncasecmp(line, header[i].name, len) && line[len] == ':' && isspace(line[len + 1])) { + /* Unwrap inline B and Q encoding, and optionally + * normalize the meta information to utf8. + */ + decode_header_bq(line + len + 2); header[i].func(line + len + 2); break; } } } -static void check_subheader_line(char *line, int len) +static void check_subheader_line(char *line) { static struct header_def header[] = { { "Content-Type", handle_subcontent_type }, @@ -357,9 +373,9 @@ static void check_subheader_line(char *line, int len) handle_content_transfer_encoding }, { NULL }, }; - check_header(line, len, header); + check_header(line, header); } -static void check_header_line(char *line, int len) +static void check_header_line(char *line) { static struct header_def header[] = { { "From", handle_from }, @@ -370,7 +386,30 @@ static void check_header_line(char *line, int len) handle_content_transfer_encoding }, { NULL }, }; - check_header(line, len, header); + check_header(line, header); +} + +static int is_rfc2822_header(char *line) +{ + /* + * The section that defines the loosest possible + * field name is "3.6.8 Optional fields". + * + * optional-field = field-name ":" unstructured CRLF + * field-name = 1*ftext + * ftext = %d33-57 / %59-126 + */ + int ch; + char *cp = line; + while ((ch = *cp++)) { + if (ch == ':') + return cp != line; + if ((33 <= ch && ch <= 57) || + (59 <= ch && ch <= 126)) + continue; + break; + } + return 0; } static int read_one_header_line(char *line, int sz, FILE *in) @@ -379,18 +418,25 @@ static int read_one_header_line(char *line, int sz, FILE *in) while (ofs < sz) { int peek, len; if (fgets(line + ofs, sz - ofs, in) == NULL) - return ofs; + break; len = eatspace(line + ofs); if (len == 0) - return ofs; - peek = fgetc(in); ungetc(peek, in); - if (peek == ' ' || peek == '\t') { - /* Yuck, 2822 header "folding" */ - ofs += len; - continue; + break; + if (!is_rfc2822_header(line)) { + /* Re-add the newline */ + line[ofs + len] = '\n'; + line[ofs + len + 1] = '\0'; + break; } - return ofs + len; + ofs += len; + /* Yuck, 2822 header "folding" */ + peek = fgetc(in); ungetc(peek, in); + if (peek != ' ' && peek != '\t') + break; } + /* Count mbox From headers as headers */ + if (!ofs && !memcmp(line, "From ", 5)) + ofs = 1; return ofs; } @@ -585,25 +631,13 @@ static void decode_transfer_encoding(char *line) static void handle_info(void) { char *sub; - static int done_info = 0; - - if (done_info) - return; - done_info = 1; sub = cleanup_subject(subject); cleanup_space(name); cleanup_space(date); cleanup_space(email); cleanup_space(sub); - /* Unwrap inline B and Q encoding, and optionally - * normalize the meta information to utf8. - */ - decode_header_bq(name); - decode_header_bq(date); - decode_header_bq(email); - decode_header_bq(sub); printf("Author: %s\nEmail: %s\nSubject: %s\nDate: %s\n\n", name, email, sub, date); } @@ -611,7 +645,7 @@ static void handle_info(void) /* We are inside message body and have read line[] already. * Spit out the commit log. */ -static int handle_commit_msg(void) +static int handle_commit_msg(int *seen) { if (!cmitmsg) return 0; @@ -635,6 +669,11 @@ static int handle_commit_msg(void) decode_transfer_encoding(line); if (metainfo_charset) convert_to_utf8(line, charset); + + handle_inbody_header(seen, line); + if (!(*seen & SEEN_PREFIX)) + continue; + fputs(line, cmitmsg); } while (fgets(line, sizeof(line), stdin) != NULL); fclose(cmitmsg); @@ -666,26 +705,16 @@ static void handle_patch(void) * that the first part to contain commit message and a patch, and * handle other parts as pure patches. */ -static int handle_multipart_one_part(void) +static int handle_multipart_one_part(int *seen) { - int seen = 0; int n = 0; - int len; while (fgets(line, sizeof(line), stdin) != NULL) { again: - len = eatspace(line); n++; - if (!len) - continue; if (is_multipart_boundary(line)) break; - if (0 <= seen && handle_inbody_header(&seen, line)) - continue; - seen = -1; /* no more inbody headers */ - line[len] = '\n'; - handle_info(); - if (handle_commit_msg()) + if (handle_commit_msg(seen)) goto again; handle_patch(); break; @@ -697,6 +726,7 @@ static int handle_multipart_one_part(void) static void handle_multipart_body(void) { + int seen = 0; int part_num = 0; /* Skip up to the first boundary */ @@ -709,16 +739,16 @@ static void handle_multipart_body(void) return; /* We are on boundary line. Start slurping the subhead. */ while (1) { - int len = read_one_header_line(line, sizeof(line), stdin); - if (!len) { - if (handle_multipart_one_part() < 0) + int hdr = read_one_header_line(line, sizeof(line), stdin); + if (!hdr) { + if (handle_multipart_one_part(&seen) < 0) return; /* Reset per part headers */ transfer_encoding = TE_DONTCARE; charset[0] = 0; } else - check_subheader_line(line, len); + check_subheader_line(line); } fclose(patchfile); if (!patch_lines) { @@ -732,18 +762,9 @@ static void handle_body(void) { int seen = 0; - while (fgets(line, sizeof(line), stdin) != NULL) { - int len = eatspace(line); - if (!len) - continue; - if (0 <= seen && handle_inbody_header(&seen, line)) - continue; - seen = -1; /* no more inbody headers */ - line[len] = '\n'; - handle_info(); - handle_commit_msg(); + if (line[0] || fgets(line, sizeof(line), stdin) != NULL) { + handle_commit_msg(&seen); handle_patch(); - break; } fclose(patchfile); if (!patch_lines) { @@ -787,15 +808,16 @@ int main(int argc, char **argv) exit(1); } while (1) { - int len = read_one_header_line(line, sizeof(line), stdin); - if (!len) { + int hdr = read_one_header_line(line, sizeof(line), stdin); + if (!hdr) { if (multipart_boundary[0]) handle_multipart_body(); else handle_body(); + handle_info(); break; } - check_header_line(line, len); + check_header_line(line); } return 0; } diff --git a/read-cache.c b/read-cache.c index 32ba917923..c499c51856 100644 --- a/read-cache.c +++ b/read-cache.c @@ -4,11 +4,26 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "cache.h" +#include "cache-tree.h" + +/* Index extensions. + * + * The first letter should be 'A'..'Z' for extensions that are not + * necessary for a correct operation (i.e. optimization data). + * When new extensions are added that _needs_ to be understood in + * order to correctly interpret the index file, pick character that + * is outside the range, to cause the reader to abort. + */ + +#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) ) +#define CACHE_EXT_TREE 0x54524545 /* "TREE" */ struct cache_entry **active_cache = NULL; static time_t index_file_timestamp; unsigned int active_nr = 0, active_alloc = 0, active_cache_changed = 0; +struct cache_tree *active_cache_tree = NULL; + /* * This only updates the "non-critical" parts of the directory * cache, ie the parts that aren't tracked by GIT, and only used @@ -696,6 +711,22 @@ static int verify_hdr(struct cache_header *hdr, unsigned long size) return 0; } +static int read_index_extension(const char *ext, void *data, unsigned long sz) +{ + switch (CACHE_EXT(ext)) { + case CACHE_EXT_TREE: + active_cache_tree = cache_tree_read(data, sz); + break; + default: + if (*ext < 'A' || 'Z' < *ext) + return error("index uses %.4s extension, which we do not understand", + ext); + fprintf(stderr, "ignoring %.4s extension\n", ext); + break; + } + return 0; +} + int read_cache(void) { int fd, i; @@ -744,6 +775,22 @@ int read_cache(void) active_cache[i] = ce; } index_file_timestamp = st.st_mtime; + while (offset <= size - 20 - 8) { + /* After an array of active_nr index entries, + * there can be arbitrary number of extended + * sections, each of which is prefixed with + * extension name (4-byte) and section length + * in 4-byte network byte order. + */ + unsigned long extsize; + memcpy(&extsize, map + offset + 4, 4); + extsize = ntohl(extsize); + if (read_index_extension(map + offset, + map + offset + 8, extsize) < 0) + goto unmap; + offset += 8; + offset += extsize; + } return active_nr; unmap: @@ -778,6 +825,17 @@ static int ce_write(SHA_CTX *context, int fd, void *data, unsigned int len) return 0; } +static int write_index_ext_header(SHA_CTX *context, int fd, + unsigned int ext, unsigned int sz) +{ + ext = htonl(ext); + sz = htonl(sz); + if ((ce_write(context, fd, &ext, 4) < 0) || + (ce_write(context, fd, &sz, 4) < 0)) + return -1; + return 0; +} + static int ce_flush(SHA_CTX *context, int fd) { unsigned int left = write_buffer_len; @@ -874,5 +932,19 @@ int write_cache(int newfd, struct cache_entry **cache, int entries) if (ce_write(&c, newfd, ce, ce_size(ce)) < 0) return -1; } + + /* Write extension data here */ + if (active_cache_tree) { + unsigned long sz; + void *data = cache_tree_write(active_cache_tree, &sz); + if (data && + !write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sz) && + !ce_write(&c, newfd, data, sz)) + ; + else { + free(data); + return -1; + } + } return ce_flush(&c, newfd); } diff --git a/repo-config.c b/repo-config.c index 127afd784c..08fc4cc57d 100644 --- a/repo-config.c +++ b/repo-config.c @@ -108,7 +108,8 @@ static int get_value(const char* key_, const char* regex_) int main(int argc, const char **argv) { - setup_git_directory(); + int nongit = 0; + setup_git_directory_gently(&nongit); while (1 < argc) { if (!strcmp(argv[1], "--int")) diff --git a/revision.c b/revision.c index 2294b16ea2..42c077a4cb 100644 --- a/revision.c +++ b/revision.c @@ -733,6 +733,14 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch revs->abbrev = DEFAULT_ABBREV; continue; } + if (!strncmp(arg, "--abbrev=", 9)) { + revs->abbrev = strtoul(arg + 9, NULL, 10); + if (revs->abbrev < MINIMUM_ABBREV) + revs->abbrev = MINIMUM_ABBREV; + else if (revs->abbrev > 40) + revs->abbrev = 40; + continue; + } if (!strcmp(arg, "--abbrev-commit")) { revs->abbrev_commit = 1; continue; diff --git a/t/t1002-read-tree-m-u-2way.sh b/t/t1002-read-tree-m-u-2way.sh index 8335a63e2e..da3c81357b 100755 --- a/t/t1002-read-tree-m-u-2way.sh +++ b/t/t1002-read-tree-m-u-2way.sh @@ -75,7 +75,7 @@ test_expect_success \ git-update-index --add yomin && git-read-tree -m -u $treeH $treeM && git-ls-files --stage >4.out || return 1 - diff --unified=0 M.out 4.out >4diff.out + diff -U0 M.out 4.out >4diff.out compare_change 4diff.out expected && check_cache_at yomin clean && sum bozbar frotz nitfol >actual4.sum && @@ -94,7 +94,7 @@ test_expect_success \ echo yomin yomin >yomin && git-read-tree -m -u $treeH $treeM && git-ls-files --stage >5.out || return 1 - diff --unified=0 M.out 5.out >5diff.out + diff -U0 M.out 5.out >5diff.out compare_change 5diff.out expected && check_cache_at yomin dirty && sum bozbar frotz nitfol >actual5.sum && @@ -112,7 +112,7 @@ test_expect_success \ git-update-index --add frotz && git-read-tree -m -u $treeH $treeM && git-ls-files --stage >6.out && - diff --unified=0 M.out 6.out && + diff -U0 M.out 6.out && check_cache_at frotz clean && sum bozbar frotz nitfol >actual3.sum && cmp M.sum actual3.sum && @@ -129,7 +129,7 @@ test_expect_success \ echo frotz frotz >frotz && git-read-tree -m -u $treeH $treeM && git-ls-files --stage >7.out && - diff --unified=0 M.out 7.out && + diff -U0 M.out 7.out && check_cache_at frotz dirty && sum bozbar frotz nitfol >actual7.sum && if cmp M.sum actual7.sum; then false; else :; fi && @@ -206,7 +206,7 @@ test_expect_success \ git-update-index --add nitfol && git-read-tree -m -u $treeH $treeM && git-ls-files --stage >14.out || return 1 - diff --unified=0 M.out 14.out >14diff.out + diff -U0 M.out 14.out >14diff.out compare_change 14diff.out expected && sum bozbar frotz >actual14.sum && grep -v nitfol M.sum > expected14.sum && @@ -227,7 +227,7 @@ test_expect_success \ echo nitfol nitfol nitfol >nitfol && git-read-tree -m -u $treeH $treeM && git-ls-files --stage >15.out || return 1 - diff --unified=0 M.out 15.out >15diff.out + diff -U0 M.out 15.out >15diff.out compare_change 15diff.out expected && check_cache_at nitfol dirty && sum bozbar frotz >actual15.sum && @@ -264,7 +264,7 @@ test_expect_success \ git-update-index --add bozbar && git-read-tree -m -u $treeH $treeM && git-ls-files --stage >18.out && - diff --unified=0 M.out 18.out && + diff -U0 M.out 18.out && check_cache_at bozbar clean && sum bozbar frotz nitfol >actual18.sum && cmp M.sum actual18.sum' @@ -278,7 +278,7 @@ test_expect_success \ echo gnusto gnusto >bozbar && git-read-tree -m -u $treeH $treeM && git-ls-files --stage >19.out && - diff --unified=0 M.out 19.out && + diff -U0 M.out 19.out && check_cache_at bozbar dirty && sum frotz nitfol >actual19.sum && grep -v bozbar M.sum > expected19.sum && @@ -297,7 +297,7 @@ test_expect_success \ git-update-index --add bozbar && git-read-tree -m -u $treeH $treeM && git-ls-files --stage >20.out && - diff --unified=0 M.out 20.out && + diff -U0 M.out 20.out && check_cache_at bozbar clean && sum bozbar frotz nitfol >actual20.sum && cmp M.sum actual20.sum' @@ -338,7 +338,7 @@ test_expect_success \ git-update-index --add DF && git-read-tree -m -u $treeDF $treeDFDF && git-ls-files --stage >DFDFcheck.out && - diff --unified=0 DFDF.out DFDFcheck.out && + diff -U0 DFDF.out DFDFcheck.out && check_cache_at DF/DF clean' test_done diff --git a/tree-walk.c b/tree-walk.c index 9f7abb7cb3..3922058271 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -47,18 +47,33 @@ void update_tree_entry(struct tree_desc *desc) desc->size = size - len; } +static const char *get_mode(const char *str, unsigned int *modep) +{ + unsigned char c; + unsigned int mode = 0; + + while ((c = *str++) != ' ') { + if (c < '0' || c > '7') + return NULL; + mode = (mode << 3) + (c - '0'); + } + *modep = mode; + return str; +} + const unsigned char *tree_entry_extract(struct tree_desc *desc, const char **pathp, unsigned int *modep) { void *tree = desc->buf; unsigned long size = desc->size; int len = strlen(tree)+1; const unsigned char *sha1 = tree + len; - const char *path = strchr(tree, ' '); + const char *path; unsigned int mode; - if (!path || size < len + 20 || sscanf(tree, "%o", &mode) != 1) + path = get_mode(tree, &mode); + if (!path || size < len + 20) die("corrupt tree file"); - *pathp = path+1; + *pathp = path; *modep = canon_mode(mode); return sha1; } diff --git a/update-index.c b/update-index.c index 5854d11fd9..956b6b34f9 100644 --- a/update-index.c +++ b/update-index.c @@ -6,6 +6,7 @@ #include "cache.h" #include "strbuf.h" #include "quote.h" +#include "cache-tree.h" #include "tree-walk.h" /* @@ -51,6 +52,7 @@ static int mark_valid(const char *path) active_cache[pos]->ce_flags &= ~htons(CE_VALID); break; } + cache_tree_invalidate_path(active_cache_tree, path); active_cache_changed = 1; return 0; } @@ -64,6 +66,12 @@ static int add_file_to_cache(const char *path) struct stat st; status = lstat(path, &st); + + /* We probably want to do this in remove_file_from_cache() and + * add_cache_entry() instead... + */ + cache_tree_invalidate_path(active_cache_tree, path); + if (status < 0 || S_ISDIR(st.st_mode)) { /* When we used to have "path" and now we want to add * "path/file", we need a way to remove "path" before @@ -145,6 +153,7 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, return error("%s: cannot add to the index - missing --add option?", path); report("add '%s'", path); + cache_tree_invalidate_path(active_cache_tree, path); return 0; } @@ -169,6 +178,7 @@ static void chmod_path(int flip, const char *path) default: goto fail; } + cache_tree_invalidate_path(active_cache_tree, path); active_cache_changed = 1; report("chmod %cx '%s'", flip, path); return; @@ -190,6 +200,7 @@ static void update_one(const char *path, const char *prefix, int prefix_length) die("Unable to mark file %s", path); goto free_return; } + cache_tree_invalidate_path(active_cache_tree, path); if (force_remove) { if (remove_file_from_cache(p)) @@ -268,6 +279,7 @@ static void read_index_info(int line_termination) free(path_name); continue; } + cache_tree_invalidate_path(active_cache_tree, path_name); if (!mode) { /* mode == 0 means there is no such path -- remove */ @@ -374,6 +386,7 @@ 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); diff --git a/write-tree.c b/write-tree.c index dcad6e6670..7a4f691d8a 100644 --- a/write-tree.c +++ b/write-tree.c @@ -5,95 +5,21 @@ */ #include "cache.h" #include "tree.h" +#include "cache-tree.h" static int missing_ok = 0; -static int check_valid_sha1(unsigned char *sha1) -{ - int ret; - - /* If we were anal, we'd check that the sha1 of the contents actually matches */ - ret = has_sha1_file(sha1); - if (ret == 0) - perror(sha1_file_name(sha1)); - return ret ? 0 : -1; -} - -static int write_tree(struct cache_entry **cachep, int maxentries, const char *base, int baselen, unsigned char *returnsha1) -{ - unsigned char subdir_sha1[20]; - unsigned long size, offset; - char *buffer; - int nr; - - /* Guess at some random initial size */ - size = 8192; - buffer = xmalloc(size); - offset = 0; - - nr = 0; - while (nr < maxentries) { - struct cache_entry *ce = cachep[nr]; - const char *pathname = ce->name, *filename, *dirname; - int pathlen = ce_namelen(ce), entrylen; - unsigned char *sha1; - unsigned int mode; - - /* Did we hit the end of the directory? Return how many we wrote */ - if (baselen >= pathlen || memcmp(base, pathname, baselen)) - break; - - sha1 = ce->sha1; - mode = ntohl(ce->ce_mode); - - /* Do we have _further_ subdirectories? */ - filename = pathname + baselen; - dirname = strchr(filename, '/'); - if (dirname) { - int subdir_written; - - subdir_written = write_tree(cachep + nr, maxentries - nr, pathname, dirname-pathname+1, subdir_sha1); - nr += subdir_written; - - /* Now we need to write out the directory entry into this tree.. */ - mode = S_IFDIR; - pathlen = dirname - pathname; - - /* ..but the directory entry doesn't count towards the total count */ - nr--; - sha1 = subdir_sha1; - } - - if (!missing_ok && check_valid_sha1(sha1) < 0) - exit(1); - - entrylen = pathlen - baselen; - if (offset + entrylen + 100 > size) { - size = alloc_nr(offset + entrylen + 100); - buffer = xrealloc(buffer, size); - } - offset += sprintf(buffer + offset, "%o %.*s", mode, entrylen, filename); - buffer[offset++] = 0; - memcpy(buffer + offset, sha1, 20); - offset += 20; - nr++; - } - - write_sha1_file(buffer, offset, tree_type, returnsha1); - free(buffer); - return nr; -} - static const char write_tree_usage[] = "git-write-tree [--missing-ok]"; +static struct cache_file cache_file; + int main(int argc, char **argv) { - int i, funny; - int entries; - unsigned char sha1[20]; - + int entries, was_valid, newfd; + setup_git_directory(); + newfd = hold_index_file_for_update(&cache_file, get_index_file()); entries = read_cache(); if (argc == 2) { if (!strcmp(argv[1], "--missing-ok")) @@ -108,51 +34,26 @@ int main(int argc, char **argv) if (entries < 0) die("git-write-tree: error reading cache"); - /* Verify that the tree is merged */ - funny = 0; - for (i = 0; i < entries; i++) { - struct cache_entry *ce = active_cache[i]; - if (ce_stage(ce)) { - if (10 < ++funny) { - fprintf(stderr, "...\n"); - break; - } - fprintf(stderr, "%s: unmerged (%s)\n", ce->name, sha1_to_hex(ce->sha1)); + if (!active_cache_tree) + active_cache_tree = cache_tree(); + + was_valid = cache_tree_fully_valid(active_cache_tree); + if (!was_valid) { + if (cache_tree_update(active_cache_tree, + active_cache, active_nr, + missing_ok, 0) < 0) + die("git-write-tree: error building trees"); + if (0 <= newfd) { + if (!write_cache(newfd, active_cache, active_nr)) + commit_index_file(&cache_file); } - } - if (funny) - die("git-write-tree: not able to write tree"); - - /* Also verify that the cache does not have path and path/file - * at the same time. At this point we know the cache has only - * stage 0 entries. - */ - funny = 0; - for (i = 0; i < entries - 1; i++) { - /* path/file always comes after path because of the way - * the cache is sorted. Also path can appear only once, - * which means conflicting one would immediately follow. + /* Not being able to write is fine -- we are only interested + * in updating the cache-tree part, and if the next caller + * ends up using the old index with unupdated cache-tree part + * it misses the work we did here, but that is just a + * performance penalty and not a big deal. */ - const char *this_name = active_cache[i]->name; - const char *next_name = active_cache[i+1]->name; - int this_len = strlen(this_name); - if (this_len < strlen(next_name) && - strncmp(this_name, next_name, this_len) == 0 && - next_name[this_len] == '/') { - if (10 < ++funny) { - fprintf(stderr, "...\n"); - break; - } - fprintf(stderr, "You have both %s and %s\n", - this_name, next_name); - } } - if (funny) - die("git-write-tree: not able to write tree"); - - /* Ok, write it out */ - if (write_tree(active_cache, entries, "", 0, sha1) != entries) - die("git-write-tree: internal error"); - printf("%s\n", sha1_to_hex(sha1)); + printf("%s\n", sha1_to_hex(active_cache_tree->sha1)); return 0; } |