diff options
64 files changed, 2310 insertions, 496 deletions
diff --git a/Documentation/git-add.txt b/Documentation/git-add.txt index 89e461402e..7e293834d1 100644 --- a/Documentation/git-add.txt +++ b/Documentation/git-add.txt @@ -7,7 +7,7 @@ git-add - Add files to the index file. SYNOPSIS -------- -'git-add' [-n] [-v] <file>... +'git-add' [-n] [-v] [--] <file>... DESCRIPTION ----------- @@ -26,6 +26,11 @@ OPTIONS -v:: Be verbose. +--:: + This option can be used to separate command-line options from + the list of files, (useful when filenames might be mistaken + for command-line options). + DISCUSSION ---------- diff --git a/Documentation/git-ls-files.txt b/Documentation/git-ls-files.txt index fe5341295c..e813f84202 100644 --- a/Documentation/git-ls-files.txt +++ b/Documentation/git-ls-files.txt @@ -8,12 +8,14 @@ git-ls-files - Information about files in the index/working directory SYNOPSIS -------- -'git-ls-files' [-z] [-t] +[verse] +'git-ls-files' [-z] [-t] [-v] (--[cached|deleted|others|ignored|stage|unmerged|killed|modified])\* (-[c|d|o|i|s|u|k|m])\* [-x <pattern>|--exclude=<pattern>] [-X <file>|--exclude-from=<file>] [--exclude-per-directory=<file>] + [--error-unmatch] [--full-name] [--] [<file>]\* DESCRIPTION @@ -72,6 +74,10 @@ OPTIONS read additional exclude patterns that apply only to the directory and its subdirectories in <file>. +--error-unmatch:: + If any <file> does not appear in the index, treat this as an + error (return 1). + -t:: Identify the file status with the following tags (followed by a space) at the start of each line: @@ -82,6 +88,10 @@ OPTIONS K:: to be killed ?:: other +-v:: + Similar to `-t`, but use lowercase letters for files + that are marked as 'always matching index'. + --full-name:: When run from a subdirectory, the command usually outputs paths relative to the current directory. This diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt index 2d67d3911e..4cb2e83faa 100644 --- a/Documentation/git-pack-objects.txt +++ b/Documentation/git-pack-objects.txt @@ -8,7 +8,10 @@ git-pack-objects - Create a packed archive of objects. SYNOPSIS -------- -'git-pack-objects' [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list +[verse] +'git-pack-objects' [-q] [--no-reuse-delta] [--non-empty] + [--local] [--incremental] [--window=N] [--depth=N] + {--stdout | base-name} < object-list DESCRIPTION @@ -32,6 +35,10 @@ Placing both in the pack/ subdirectory of $GIT_OBJECT_DIRECTORY (or any of the directories on $GIT_ALTERNATE_OBJECT_DIRECTORIES) enables git to read from such an archive. +In a packed archive, an object is either stored as a compressed +whole, or as a difference from some other object. The latter is +often called a delta. + OPTIONS ------- @@ -74,6 +81,18 @@ base-name:: Only create a packed archive if it would contain at least one object. +-q:: + This flag makes the command not to report its progress + on the standard error stream. + +--no-reuse-delta:: + When creating a packed archive in a repository that + has existing packs, the command reuses existing deltas. + This sometimes results in a slightly suboptimal pack. + This flag tells the command not to reuse existing deltas + but compute them from scratch. + + Author ------ Written by Linus Torvalds <torvalds@osdl.org> diff --git a/Documentation/git-push.txt b/Documentation/git-push.txt index 5b891105b2..6f4a48a109 100644 --- a/Documentation/git-push.txt +++ b/Documentation/git-push.txt @@ -43,6 +43,12 @@ to fast forward the remote ref that matches <dst>. If the optional plus `+` is used, the remote ref is updated even if it does not result in a fast forward update. + +Note: If no explicit refspec is found, (that is neither +on the command line nor in any Push line of the +corresponding remotes file---see below), then all the +refs that exist both on the local side and on the remote +side are updated. ++ Some short-cut notations are also supported. + * `tag <tag>` means the same as `refs/tags/<tag>:refs/tags/<tag>`. diff --git a/Documentation/git-rebase.txt b/Documentation/git-rebase.txt index 16c158f439..f037d1280e 100644 --- a/Documentation/git-rebase.txt +++ b/Documentation/git-rebase.txt @@ -7,14 +7,54 @@ git-rebase - Rebase local commits to new upstream head. SYNOPSIS -------- -'git-rebase' <upstream> [<head>] +'git-rebase' [--onto <newbase>] <upstream> [<branch>] DESCRIPTION ----------- -Rebases local commits to the new head of the upstream tree. +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. + +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 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 the following +commands: + + git-rebase --onto master~1 master + git-rebase --onto master~1 master topic + +would be: + + A'--B'--C' topic + / + D---E---F---G master OPTIONS ------- +<newbase>:: + Starting point at which to create the new commits. If the + --onto option is not specified, the starting point is + <upstream>. + <upstream>:: Upstream branch to compare against. diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt index 9060fe8897..6c0f792dad 100644 --- a/Documentation/git-repack.txt +++ b/Documentation/git-repack.txt @@ -9,7 +9,7 @@ objects into pack files. SYNOPSIS -------- -'git-repack' [-a] [-d] [-l] [-n] +'git-repack' [-a] [-d] [-f] [-l] [-n] [-q] DESCRIPTION ----------- @@ -43,6 +43,14 @@ OPTIONS Pass the `--local` option to `git pack-objects`, see gitlink:git-pack-objects[1]. +-f:: + Pass the `--no-reuse-delta` option to `git pack-objects`, see + gitlink:git-pack-objects[1]. + +-q:: + Pass the `-q` option to `git pack-objects`, see + gitlink:git-pack-objects[1]. + -n:: Do not update the server information with `git update-server-info`. diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt index c74311dabd..0a1b0ad56d 100644 --- a/Documentation/git-update-index.txt +++ b/Documentation/git-update-index.txt @@ -8,11 +8,14 @@ git-update-index - Modifies the index or directory cache SYNOPSIS -------- +[verse] 'git-update-index' [--add] [--remove | --force-remove] [--replace] [--refresh [-q] [--unmerged] [--ignore-missing]] [--cacheinfo <mode> <object> <file>]\* [--chmod=(+|-)x] + [--assume-unchanged | --no-assume-unchanged] + [--really-refresh] [--info-only] [--index-info] [-z] [--stdin] [--verbose] @@ -65,6 +68,18 @@ OPTIONS --chmod=(+|-)x:: Set the execute permissions on the updated files. +--assume-unchanged, --no-assume-unchanged:: + When these flags are specified, the object name recorded + for the paths are not updated. Instead, these options + sets and unsets the "assume unchanged" bit for the + paths. When the "assume unchanged" bit is on, git stops + checking the working tree files for possible + modifications, so you need to manually unset the bit to + tell git when you change the working tree file. This is + sometimes helpful when working with a big project on a + filesystem that has very slow lstat(2) system call + (e.g. cifs). + --info-only:: Do not create objects in the object database for all <file> arguments that follow this flag; just insert @@ -193,6 +208,37 @@ $ git ls-files -s ------------ +Using "assume unchanged" bit +---------------------------- + +Many operations in git depend on your filesystem to have an +efficient `lstat(2)` implementation, so that `st_mtime` +information for working tree files can be cheaply checked to see +if the file contents have changed from the version recorded in +the index file. Unfortunately, some filesystems have +inefficient `lstat(2)`. If your filesystem is one of them, you +can set "assume unchanged" bit to paths you have not changed to +cause git not to do this check. Note that setting this bit on a +path does not mean git will check the contents of the file to +see if it has changed -- it makes git to omit any checking and +assume it has *not* changed. When you make changes to working +tree files, you have to explicitly tell git about it by dropping +"assume unchanged" bit, either before or after you modify them. + +In order to set "assume unchanged" bit, use `--assume-unchanged` +option. To unset, use `--no-assume-unchanged`. + +The command looks at `core.ignorestat` configuration variable. When +this is true, paths updated with `git-update-index paths...` and +paths updated with other git commands that update both index and +working tree (e.g. `git-apply --index`, `git-checkout-index -u`, +and `git-read-tree -u`) are automatically marked as "assume +unchanged". Note that "assume unchanged" bit is *not* set if +`git-update-index --refresh` finds the working tree file matches +the index (use `git-update-index --really-refresh` if you want +to mark them as "assume unchanged"). + + Examples -------- To update and refresh only the files already checked out: @@ -201,6 +247,35 @@ To update and refresh only the files already checked out: $ git-checkout-index -n -f -a && git-update-index --ignore-missing --refresh ---------------- +On an inefficient filesystem with `core.ignorestat` set: + +------------ +$ git update-index --really-refresh <1> +$ git update-index --no-assume-unchanged foo.c <2> +$ git diff --name-only <3> +$ edit foo.c +$ git diff --name-only <4> +M foo.c +$ git update-index foo.c <5> +$ git diff --name-only <6> +$ edit foo.c +$ git diff --name-only <7> +$ git update-index --no-assume-unchanged foo.c <8> +$ git diff --name-only <9> +M foo.c + +<1> forces lstat(2) to set "assume unchanged" bits for paths + that match index. +<2> mark the path to be edited. +<3> this does lstat(2) and finds index matches the path. +<4> this does lstat(2) and finds index does not match the path. +<5> registering the new version to index sets "assume unchanged" bit. +<6> and it is assumed unchanged. +<7> even after you edit it. +<8> you can tell about the change after the fact. +<9> now it checks with lstat(2) and finds it has been changed. +------------ + Configuration ------------- @@ -213,6 +288,9 @@ in the index and the file mode on the filesystem if they differ only on executable bit. On such an unfortunate filesystem, you may need to use `git-update-index --chmod=`. +The command looks at `core.ignorestat` configuration variable. See +'Using "assume unchanged" bit' section above. + See Also -------- @@ -55,6 +55,11 @@ all: # # Define NO_ICONV if your libc does not properly support iconv. # +# Define NO_ACCURATE_DIFF if your diff program at least sometimes misses +# a missing newline at the end of the file. +# +# Define NO_PYTHON if you want to loose all benefits of the recursive merge. +# # Define COLLISION_CHECK below if you believe that SHA1's # 1461501637330902918203684832716283019655932542976 hashes do not give you # sufficient guarantee that no collisions between objects will ever happen. @@ -72,6 +77,12 @@ GIT-VERSION-FILE: .FORCE-GIT-VERSION-FILE @$(SHELL_PATH) ./GIT-VERSION-GEN -include GIT-VERSION-FILE +uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not') +uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not') +uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not') +uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not') +uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not') + # CFLAGS and LDFLAGS are for the users to override from the command line. CFLAGS = -g -O2 -Wall @@ -82,7 +93,7 @@ STRIP ?= strip prefix = $(HOME) bindir = $(prefix)/bin -gitexecdir = $(prefix)/bin +gitexecdir = $(bindir) template_dir = $(prefix)/share/git-core/templates/ GIT_PYTHON_DIR = $(prefix)/share/git-core/python # DESTDIR= @@ -132,7 +143,7 @@ SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \ # The ones that do not have to link with lcrypto nor lz. SIMPLE_PROGRAMS = \ - git-get-tar-commit-id$X git-mailinfo$X git-mailsplit$X \ + git-get-tar-commit-id$X git-mailsplit$X \ git-stripspace$X git-daemon$X # ... and all the rest that could be moved out of bindir to gitexecdir @@ -144,7 +155,7 @@ PROGRAMS = \ git-diff-tree$X git-fetch-pack$X git-fsck-objects$X \ git-hash-object$X git-index-pack$X git-init-db$X \ git-local-fetch$X git-ls-files$X git-ls-tree$X git-merge-base$X \ - git-merge-index$X git-mktag$X git-pack-objects$X git-patch-id$X \ + git-merge-index$X git-mktag$X git-mktree$X git-pack-objects$X git-patch-id$X \ git-peek-remote$X git-prune-packed$X git-read-tree$X \ git-receive-pack$X git-rev-list$X git-rev-parse$X \ git-send-pack$X git-show-branch$X git-shell$X \ @@ -154,7 +165,7 @@ PROGRAMS = \ git-upload-pack$X git-verify-pack$X git-write-tree$X \ git-update-ref$X git-symbolic-ref$X git-check-ref-format$X \ git-name-rev$X git-pack-redundant$X git-repo-config$X git-var$X \ - git-describe$X + git-describe$X git-merge-tree$X git-blame$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -200,12 +211,6 @@ LIB_OBJS = \ LIBS = $(LIB_FILE) LIBS += -lz -# Shell quote; -# Result of this needs to be placed inside '' -shq = $(subst ','\'',$(1)) -# This has surrounding '' -shellquote = '$(call shq,$(1))' - # # Platform specific tweaks # @@ -213,10 +218,6 @@ shellquote = '$(call shq,$(1))' # We choose to avoid "if .. else if .. else .. endif endif" # because maintaining the nesting to match is a pain. If # we had "elif" things would have been much nicer... -uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not') -uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not') -uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not') -uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not') ifeq ($(uname_S),Darwin) NEEDS_SSL_WITH_CRYPTO = YesPlease @@ -231,10 +232,10 @@ endif ifeq ($(uname_S),SunOS) NEEDS_SOCKET = YesPlease NEEDS_NSL = YesPlease - NEEDS_LIBICONV = YesPlease SHELL_PATH = /bin/bash NO_STRCASESTR = YesPlease ifeq ($(uname_R),5.8) + NEEDS_LIBICONV = YesPlease NO_UNSETENV = YesPlease NO_SETENV = YesPlease endif @@ -274,6 +275,16 @@ ifeq ($(uname_S),AIX) NO_STRCASESTR=YesPlease NEEDS_LIBICONV=YesPlease endif +ifeq ($(uname_S),IRIX64) + NO_IPV6=YesPlease + NO_SETENV=YesPlease + NO_STRCASESTR=YesPlease + NO_SOCKADDR_STORAGE=YesPlease + SHELL_PATH=/usr/gnu/bin/bash + ALL_CFLAGS += -DPATH_MAX=1024 + # for now, build 32-bit version + ALL_LDFLAGS += -L/usr/lib32 +endif ifneq (,$(findstring arm,$(uname_M))) ARM_SHA1 = YesPlease endif @@ -283,8 +294,10 @@ endif ifdef WITH_OWN_SUBPROCESS_PY PYMODULES += compat/subprocess.py else - ifneq ($(shell $(PYTHON_PATH) -c 'import subprocess;print"OK"' 2>/dev/null),OK) - PYMODULES += compat/subprocess.py + ifeq ($(NO_PYTHON),) + ifneq ($(shell $(PYTHON_PATH) -c 'import subprocess;print"OK"' 2>/dev/null),OK) + PYMODULES += compat/subprocess.py + endif endif endif @@ -404,8 +417,25 @@ else endif endif endif +ifdef NO_ACCURATE_DIFF + ALL_CFLAGS += -DNO_ACCURATE_DIFF +endif + +# Shell quote (do not use $(call) to accomodate ancient setups); + +SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER)) -ALL_CFLAGS += -DSHA1_HEADER=$(call shellquote,$(SHA1_HEADER)) $(COMPAT_CFLAGS) +DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) +bindir_SQ = $(subst ','\'',$(bindir)) +gitexecdir_SQ = $(subst ','\'',$(gitexecdir)) +template_dir_SQ = $(subst ','\'',$(template_dir)) + +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) +PYTHON_PATH_SQ = $(subst ','\'',$(PYTHON_PATH)) +GIT_PYTHON_DIR_SQ = $(subst ','\'',$(GIT_PYTHON_DIR)) + +ALL_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' $(COMPAT_CFLAGS) LIB_OBJS += $(COMPAT_OBJS) export prefix TAR INSTALL DESTDIR SHELL_PATH template_dir ### Build rules @@ -424,23 +454,24 @@ git$X: git.c $(LIB_FILE) $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh rm -f $@ - sed -e '1s|#!.*/sh|#!$(call shq,$(SHELL_PATH))|' \ + sed -e '1s|#!.*/sh|#!$(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 $@ $(patsubst %.perl,%,$(SCRIPT_PERL)) : % : %.perl rm -f $@ - sed -e '1s|#!.*perl|#!$(call shq,$(PERL_PATH))|' \ + sed -e '1s|#!.*perl|#!$(PERL_PATH_SQ)|' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ $@.perl >$@ chmod +x $@ $(patsubst %.py,%,$(SCRIPT_PYTHON)) : % : %.py rm -f $@ - sed -e '1s|#!.*python|#!$(call shq,$(PYTHON_PATH))|' \ - -e 's|@@GIT_PYTHON_PATH@@|$(call shq,$(GIT_PYTHON_DIR))|g' \ + sed -e '1s|#!.*python|#!$(PYTHON_PATH_SQ)|' \ + -e 's|@@GIT_PYTHON_PATH@@|$(GIT_PYTHON_DIR_SQ)|g' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ $@.py >$@ chmod +x $@ @@ -466,32 +497,42 @@ git$X git.spec \ %.o: %.S $(CC) -o $*.o -c $(ALL_CFLAGS) $< -exec_cmd.o: ALL_CFLAGS += -DGIT_EXEC_PATH=\"$(gitexecdir)\" +exec_cmd.o: exec_cmd.c + $(CC) -o $*.o -c $(ALL_CFLAGS) '-DGIT_EXEC_PATH="$(gitexecdir_SQ)"' $< git-%$X: %.o $(LIB_FILE) $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) -git-mailinfo$X : SIMPLE_LIB += $(LIB_4_ICONV) $(SIMPLE_PROGRAMS) : $(LIB_FILE) $(SIMPLE_PROGRAMS) : git-%$X : %.o $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ $(LIB_FILE) $(SIMPLE_LIB) -git-http-fetch$X: fetch.o http.o -git-http-push$X: http.o +git-mailinfo$X: mailinfo.o $(LIB_FILE) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ + $(LIB_FILE) $(SIMPLE_LIB) $(LIB_4_ICONV) + git-local-fetch$X: fetch.o git-ssh-fetch$X: rsh.o fetch.o git-ssh-upload$X: rsh.o git-ssh-pull$X: rsh.o fetch.o git-ssh-push$X: rsh.o -git-http-fetch$X: LIBS += $(CURL_LIBCURL) -git-http-push$X: LIBS += $(CURL_LIBCURL) $(EXPAT_LIBEXPAT) -git-rev-list$X: LIBS += $(OPENSSL_LIBSSL) +git-http-fetch$X: fetch.o http.o http-fetch.o $(LIB_FILE) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ + $(LIBS) $(CURL_LIBCURL) + +git-http-push$X: http.o http-push.o $(LIB_FILE) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ + $(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT) + +git-rev-list$X: rev-list.o $(LIB_FILE) + $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ + $(LIBS) $(OPENSSL_LIBSSL) init-db.o: init-db.c $(CC) -c $(ALL_CFLAGS) \ - -DDEFAULT_GIT_TEMPLATE_DIR=$(call shellquote,"$(template_dir)") $*.c + -DDEFAULT_GIT_TEMPLATE_DIR='"$(template_dir_SQ)"' $*.c $(LIB_OBJS): $(LIB_H) $(patsubst git-%$X,%.o,$(PROGRAMS)): $(LIB_H) @@ -506,6 +547,12 @@ doc: ### Testing rules +# GNU make supports exporting all variables by "export" without parameters. +# However, the environment gets quite big, and some programs have problems +# with that. + +export NO_PYTHON + test: all $(MAKE) -C t/ all @@ -523,13 +570,13 @@ check: ### Installation rules install: all - $(INSTALL) -d -m755 $(call shellquote,$(DESTDIR)$(bindir)) - $(INSTALL) -d -m755 $(call shellquote,$(DESTDIR)$(gitexecdir)) - $(INSTALL) $(ALL_PROGRAMS) $(call shellquote,$(DESTDIR)$(gitexecdir)) - $(INSTALL) git$X gitk $(call shellquote,$(DESTDIR)$(bindir)) + $(INSTALL) -d -m755 '$(DESTDIR_SQ)$(bindir_SQ)' + $(INSTALL) -d -m755 '$(DESTDIR_SQ)$(gitexecdir_SQ)' + $(INSTALL) $(ALL_PROGRAMS) '$(DESTDIR_SQ)$(gitexecdir_SQ)' + $(INSTALL) git$X gitk '$(DESTDIR_SQ)$(bindir_SQ)' $(MAKE) -C templates install - $(INSTALL) -d -m755 $(call shellquote,$(DESTDIR)$(GIT_PYTHON_DIR)) - $(INSTALL) $(PYMODULES) $(call shellquote,$(DESTDIR)$(GIT_PYTHON_DIR)) + $(INSTALL) -d -m755 '$(DESTDIR_SQ)$(GIT_PYTHON_DIR_SQ)' + $(INSTALL) $(PYMODULES) '$(DESTDIR_SQ)$(GIT_PYTHON_DIR_SQ)' install-doc: $(MAKE) -C Documentation install @@ -1142,6 +1142,14 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag) size -= len; } +#ifdef NO_ACCURATE_DIFF + if (oldsize > 0 && old[oldsize - 1] == '\n' && + newsize > 0 && new[newsize - 1] == '\n') { + oldsize--; + newsize--; + } +#endif + offset = find_offset(buf, desc->size, old, oldsize, frag->newpos); if (offset >= 0) { int diff = newsize - oldsize; @@ -1309,7 +1317,7 @@ static int check_patch(struct patch *patch) return -1; } - changed = ce_match_stat(active_cache[pos], &st); + changed = ce_match_stat(active_cache[pos], &st, 1); if (changed) return error("%s: does not match index", old_name); diff --git a/blame.c b/blame.c new file mode 100644 index 0000000000..1e655466a8 --- /dev/null +++ b/blame.c @@ -0,0 +1,443 @@ +#include <assert.h> + +#include "cache.h" +#include "refs.h" +#include "tag.h" +#include "commit.h" +#include "tree.h" +#include "blob.h" +#include "epoch.h" +#include "diff.h" + +#define DEBUG 0 + +struct commit** blame_lines; +int num_blame_lines; + +struct util_info +{ + int* line_map; + int num_lines; + unsigned char sha1[20]; /* blob sha, not commit! */ + char* buf; + unsigned long size; +// const char* path; +}; + +struct chunk +{ + int off1, len1; // --- + int off2, len2; // +++ +}; + +struct patch +{ + struct chunk* chunks; + int num; +}; + +static void get_blob(struct commit* commit); + +int num_get_patch = 0; +int num_commits = 0; + +struct patch* get_patch(struct commit* commit, struct commit* other) +{ + struct patch* ret = xmalloc(sizeof(struct patch)); + ret->chunks = NULL; + ret->num = 0; + + struct util_info* info_c = (struct util_info*) commit->object.util; + struct util_info* info_o = (struct util_info*) other->object.util; + + if(!memcmp(info_c->sha1, info_o->sha1, 20)) + return ret; + + get_blob(commit); + get_blob(other); + + FILE* fout = fopen("/tmp/git-blame-tmp1", "w"); + if(!fout) + die("fopen tmp1 failed: %s", strerror(errno)); + + if(fwrite(info_c->buf, info_c->size, 1, fout) != 1) + die("fwrite 1 failed: %s", strerror(errno)); + fclose(fout); + + fout = fopen("/tmp/git-blame-tmp2", "w"); + if(!fout) + die("fopen tmp2 failed: %s", strerror(errno)); + + if(fwrite(info_o->buf, info_o->size, 1, fout) != 1) + die("fwrite 2 failed: %s", strerror(errno)); + fclose(fout); + + FILE* fin = popen("diff -u0 /tmp/git-blame-tmp1 /tmp/git-blame-tmp2", "r"); + if(!fin) + die("popen failed: %s", strerror(errno)); + + char buf[1024]; + while(fgets(buf, sizeof(buf), fin)) { + if(buf[0] != '@' || buf[1] != '@') + continue; + + if(DEBUG) + printf("chunk line: %s", buf); + ret->num++; + ret->chunks = xrealloc(ret->chunks, sizeof(struct chunk)*ret->num); + struct chunk* chunk = &ret->chunks[ret->num-1]; + + assert(!strncmp(buf, "@@ -", 4)); + + char* start = buf+4; + char* sp = index(start, ' '); + *sp = '\0'; + if(index(start, ',')) { + int ret = sscanf(start, "%d,%d", &chunk->off1, &chunk->len1); + assert(ret == 2); + } else { + int ret = sscanf(start, "%d", &chunk->off1); + assert(ret == 1); + chunk->len1 = 1; + } + *sp = ' '; + + start = sp+1; + sp = index(start, ' '); + *sp = '\0'; + if(index(start, ',')) { + int ret = sscanf(start, "%d,%d", &chunk->off2, &chunk->len2); + assert(ret == 2); + } else { + int ret = sscanf(start, "%d", &chunk->off2); + assert(ret == 1); + chunk->len2 = 1; + } + *sp = ' '; + + if(chunk->off1 > 0) + chunk->off1 -= 1; + if(chunk->off2 > 0) + chunk->off2 -= 1; + + assert(chunk->off1 >= 0); + assert(chunk->off2 >= 0); + } + fclose(fin); + + num_get_patch++; + return ret; +} + +void free_patch(struct patch* p) +{ + free(p->chunks); + free(p); +} + +static int get_blob_sha1_internal(unsigned char *sha1, const char *base, int baselen, + const char *pathname, unsigned mode, int stage); + + +static unsigned char blob_sha1[20]; +static int get_blob_sha1(struct tree* t, const char* pathname, unsigned char* sha1) +{ + const char *pathspec[2]; + pathspec[0] = pathname; + pathspec[1] = NULL; + memset(blob_sha1, 0, sizeof(blob_sha1)); + read_tree_recursive(t, "", 0, 0, pathspec, get_blob_sha1_internal); + + int i; + for(i = 0; i < 20; i++) { + if(blob_sha1[i] != 0) + break; + } + + if(i == 20) + return -1; + + memcpy(sha1, blob_sha1, 20); + return 0; +} + +static int get_blob_sha1_internal(unsigned char *sha1, const char *base, int baselen, + const char *pathname, unsigned mode, int stage) +{ +// printf("Got blob: %s base: '%s' baselen: %d pathname: '%s' mode: %o stage: %d\n", +// sha1_to_hex(sha1), base, baselen, pathname, mode, stage); + + if(S_ISDIR(mode)) + return READ_TREE_RECURSIVE; + + memcpy(blob_sha1, sha1, 20); + return -1; +} + +static void get_blob(struct commit* commit) +{ + struct util_info* info = commit->object.util; + char type[20]; + + if(info->buf) + return; + + info->buf = read_sha1_file(info->sha1, type, &info->size); + assert(!strcmp(type, "blob")); +} + +void print_patch(struct patch* p) +{ + printf("Num chunks: %d\n", p->num); + int i; + for(i = 0; i < p->num; i++) { + printf("%d,%d %d,%d\n", p->chunks[i].off1, p->chunks[i].len1, p->chunks[i].off2, p->chunks[i].len2); + } +} + + +// p is a patch from commit to other. +void fill_line_map(struct commit* commit, struct commit* other, struct patch* p) +{ + int num_lines = ((struct util_info*) commit->object.util)->num_lines; + int* line_map = ((struct util_info*) commit->object.util)->line_map; + int num_lines2 = ((struct util_info*) other->object.util)->num_lines; + int* line_map2 = ((struct util_info*) other->object.util)->line_map; + int cur_chunk = 0; + int i1, i2; + + if(p->num && DEBUG) + print_patch(p); + + for(i1 = 0; i1 < num_lines; i1++) + line_map[i1] = -1; + + if(DEBUG) + printf("num lines 1: %d num lines 2: %d\n", num_lines, num_lines2); + + for(i1 = 0, i2 = 0; i1 < num_lines; i1++, i2++) { + if(DEBUG > 1) + printf("%d %d\n", i1, i2); + + if(i2 >= num_lines2) + break; + + line_map[i1] = line_map2[i2]; + + struct chunk* chunk = NULL; + if(cur_chunk < p->num) + chunk = &p->chunks[cur_chunk]; + + if(chunk && chunk->off1 == i1) { + i2 = chunk->off2; + + if(chunk->len1 > 0) + i1 += chunk->len1-1; + if(chunk->len2 > 0) + i2 += chunk->len2-1; + cur_chunk++; + } + } +} + +int map_line(struct commit* commit, int line) +{ + struct util_info* info = commit->object.util; + assert(line >= 0 && line < info->num_lines); + return info->line_map[line]; +} + +int fill_util_info(struct commit* commit, const char* path) +{ + if(commit->object.util) + return 0; + + struct util_info* util = xmalloc(sizeof(struct util_info)); + util->buf = NULL; + util->size = 0; + util->num_lines = -1; + util->line_map = NULL; + + commit->object.util = util; + + if(get_blob_sha1(commit->tree, path, util->sha1)) + return -1; + + return 0; +} + +void alloc_line_map(struct commit* commit) +{ + struct util_info* util = commit->object.util; + + if(util->line_map) + return; + + get_blob(commit); + + int i; + util->num_lines = 0; + for(i = 0; i < util->size; i++) { + if(util->buf[i] == '\n') + util->num_lines++; + } + util->line_map = xmalloc(sizeof(int)*util->num_lines); +} + +void copy_line_map(struct commit* dst, struct commit* src) +{ + struct util_info* u_dst = dst->object.util; + struct util_info* u_src = src->object.util; + + u_dst->line_map = u_src->line_map; + u_dst->num_lines = u_src->num_lines; + u_dst->buf = u_src->buf; + u_dst->size = u_src->size; +} + +void process_commits(struct commit_list* list, const char* path) +{ + int i; + + while(list) { + struct commit* commit = pop_commit(&list); + struct commit_list* parents; + struct util_info* info; + + info = commit->object.util; + num_commits++; + if(DEBUG) + printf("\nProcessing commit: %d %s\n", num_commits, sha1_to_hex(commit->object.sha1)); + for(parents = commit->parents; + parents != NULL; parents = parents->next) { + struct commit* parent = parents->item; + + if(parse_commit(parent) < 0) + die("parse_commit error"); + + if(DEBUG) + printf("parent: %s\n", sha1_to_hex(parent->object.sha1)); + + if(fill_util_info(parent, path)) + continue; + + // Temporarily assign everything to the parent. + int num_blame = 0; + for(i = 0; i < num_blame_lines; i++) { + if(blame_lines[i] == commit) { + num_blame++; + blame_lines[i] = parent; + } + } + + if(num_blame == 0) + continue; + + struct patch* patch = get_patch(parent, commit); + if(patch->num == 0) { + copy_line_map(parent, commit); + } else { + alloc_line_map(parent); + fill_line_map(parent, commit, patch); + } + + for(i = 0; i < patch->num; i++) { + int l; + for(l = 0; l < patch->chunks[i].len2; l++) { + int mapped_line = map_line(commit, patch->chunks[i].off2 + l); + if(mapped_line != -1 && blame_lines[mapped_line] == parent) + blame_lines[mapped_line] = commit; + } + } + free_patch(patch); + } + } +} + +#define SEEN 1 +struct commit_list* get_commit_list(struct commit* commit, const char* pathname) +{ + struct commit_list* ret = NULL; + struct commit_list* process = NULL; + unsigned char sha1[20]; + + commit_list_insert(commit, &process); + + while(process) { + struct commit* com = pop_commit(&process); + if(com->object.flags & SEEN) + continue; + + com->object.flags |= SEEN; + commit_list_insert(com, &ret); + struct commit_list* parents; + + parse_commit(com); + + for(parents = com->parents; + parents != NULL; parents = parents->next) { + struct commit* parent = parents->item; + + parse_commit(parent); + + if(!get_blob_sha1(parent->tree, pathname, sha1)) + commit_list_insert(parent, &process); + } + } + + return ret; +} + +int main(int argc, const char **argv) +{ + unsigned char sha1[20]; + struct commit *commit; + const char* filename; + int i; + + setup_git_directory(); + + if (argc != 3) + die("Usage: blame commit-ish file"); + + if (get_sha1(argv[1], sha1)) + die("get_sha1 failed"); + + commit = lookup_commit_reference(sha1); + + filename = argv[2]; + + struct commit_list* list = get_commit_list(commit, filename); + sort_in_topological_order(&list, 1); + + if(fill_util_info(commit, filename)) { + printf("%s not found in %s\n", filename, argv[1]); + return 0; + } + alloc_line_map(commit); + + struct util_info* util = commit->object.util; + num_blame_lines = util->num_lines; + blame_lines = xmalloc(sizeof(struct commit*)*num_blame_lines); + + + for(i = 0; i < num_blame_lines; i++) { + blame_lines[i] = commit; + + ((struct util_info*) commit->object.util)->line_map[i] = i; + } + + process_commits(list, filename); + + for(i = 0; i < num_blame_lines; i++) { + printf("%d %s\n", i+1-1, sha1_to_hex(blame_lines[i]->object.sha1)); +// printf("%d %s\n", i+1-1, find_unique_abbrev(blame_lines[i]->object.sha1, 6)); + } + + if(DEBUG) { + printf("num get patch: %d\n", num_get_patch); + printf("num commits: %d\n", num_commits); + } + + return 0; +} @@ -91,6 +91,7 @@ struct cache_entry { #define CE_NAMEMASK (0x0fff) #define CE_STAGEMASK (0x3000) #define CE_UPDATE (0x4000) +#define CE_VALID (0x8000) #define CE_STAGESHIFT 12 #define create_ce_flags(len, stage) htons((len) | ((stage) << CE_STAGESHIFT)) @@ -144,8 +145,8 @@ extern int add_cache_entry(struct cache_entry *ce, int option); extern int remove_cache_entry_at(int pos); extern int remove_file_from_cache(const char *path); extern int ce_same_name(struct cache_entry *a, struct cache_entry *b); -extern int ce_match_stat(struct cache_entry *ce, struct stat *st); -extern int ce_modified(struct cache_entry *ce, struct stat *st); +extern int ce_match_stat(struct cache_entry *ce, struct stat *st, int); +extern int ce_modified(struct cache_entry *ce, struct stat *st, int); extern int ce_path_match(const struct cache_entry *ce, const char **pathspec); extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, const char *type); extern int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object); @@ -161,6 +162,7 @@ extern int commit_index_file(struct cache_file *); extern void rollback_index_file(struct cache_file *); extern int trust_executable_bit; +extern int assume_unchanged; extern int only_use_symrefs; extern int diff_rename_limit_default; extern int shared_repository; @@ -246,8 +248,8 @@ void datestamp(char *buf, int bufsize); unsigned long approxidate(const char *); extern int setup_ident(void); -extern const char *git_author_info(void); -extern const char *git_committer_info(void); +extern const char *git_author_info(int); +extern const char *git_committer_info(int); struct checkout { const char *base_dir; diff --git a/checkout-index.c b/checkout-index.c index 53dd8cba6f..957b4a86b0 100644 --- a/checkout-index.c +++ b/checkout-index.c @@ -116,6 +116,7 @@ int main(int argc, char **argv) int all = 0; prefix = setup_git_directory(); + git_config(git_default_config); prefix_length = prefix ? strlen(prefix) : 0; if (read_cache() < 0) { diff --git a/commit-tree.c b/commit-tree.c index b1c8dca48d..88871b022d 100644 --- a/commit-tree.c +++ b/commit-tree.c @@ -118,8 +118,8 @@ int main(int argc, char **argv) add_buffer(&buffer, &size, "parent %s\n", sha1_to_hex(parent_sha1[i])); /* Person/date information */ - add_buffer(&buffer, &size, "author %s\n", git_author_info()); - add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info()); + add_buffer(&buffer, &size, "author %s\n", git_author_info(1)); + add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info(1)); /* And add the comment */ while (fgets(comment, sizeof(comment), stdin) != NULL) @@ -222,6 +222,11 @@ int git_default_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.ignorestat")) { + assume_unchanged = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "core.symrefsonly")) { only_use_symrefs = git_config_bool(var, value); return 0; diff --git a/contrib/gitview/gitview b/contrib/gitview/gitview index 5862fcca41..5c338c0220 100755 --- a/contrib/gitview/gitview +++ b/contrib/gitview/gitview @@ -56,20 +56,6 @@ def show_date(epoch, tz): return time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime(secs)) -def get_sha1_from_tags(line): - fp = os.popen("git cat-file -t " + line) - entry = string.strip(fp.readline()) - fp.close() - if (entry == "commit"): - return line - elif (entry == "tag"): - fp = os.popen("git cat-file tag "+ line) - entry = string.strip(fp.readline()) - fp.close() - obj = re.split(" ", entry) - if (obj[0] == "object"): - return obj[1] - return None class CellRendererGraph(gtk.GenericCellRenderer): """Cell renderer for directed graph. @@ -174,9 +160,9 @@ class CellRendererGraph(gtk.GenericCellRenderer): names_len = 0 if (len(names) != 0): for item in names: - names_len += len(item)/3 + names_len += len(item) - width = box_size * (cols + 1 + names_len ) + width = box_size * (cols + 1 ) + names_len height = box_size # FIXME I have no idea how to use cell_area properly @@ -258,6 +244,8 @@ class CellRendererGraph(gtk.GenericCellRenderer): for item in names: name = name + item + " " + ctx.select_font_face("Monospace") + ctx.set_font_size(13) ctx.text_path(name) self.set_colour(ctx, colour, 0.0, 0.5) @@ -465,32 +453,24 @@ class GitView: respective sha1 details """ self.bt_sha1 = { } + ls_remote = re.compile('^(.{40})\trefs/([^^]+)(?:\\^(..))?$'); git_dir = os.getenv("GIT_DIR") if (git_dir == None): git_dir = ".git" - #FIXME the path seperator - ref_files = os.listdir(git_dir + "/refs/tags") - for file in ref_files: - fp = open(git_dir + "/refs/tags/"+file) - sha1 = get_sha1_from_tags(string.strip(fp.readline())) - try: - self.bt_sha1[sha1].append(file) - except KeyError: - self.bt_sha1[sha1] = [file] - fp.close() - - - #FIXME the path seperator - ref_files = os.listdir(git_dir + "/refs/heads") - for file in ref_files: - fp = open(git_dir + "/refs/heads/" + file) - sha1 = get_sha1_from_tags(string.strip(fp.readline())) - try: - self.bt_sha1[sha1].append(file) - except KeyError: - self.bt_sha1[sha1] = [file] - fp.close() + fp = os.popen('git ls-remote ' + git_dir) + while 1: + line = string.strip(fp.readline()) + if line == '': + break + m = ls_remote.match(line) + if not m: + continue + (sha1, name) = (m.group(1), m.group(2)) + if not self.bt_sha1.has_key(sha1): + self.bt_sha1[sha1] = [] + self.bt_sha1[sha1].append(name) + fp.close() def construct(self): @@ -537,8 +517,8 @@ class GitView: cell = CellRendererGraph() column = gtk.TreeViewColumn() - column.set_resizable(False) - column.pack_start(cell, expand=False) + column.set_resizable(True) + column.pack_start(cell, expand=True) column.add_attribute(cell, "node", 1) column.add_attribute(cell, "in-lines", 2) column.add_attribute(cell, "out-lines", 3) diff --git a/diff-delta.c b/diff-delta.c index c2f656ae39..2ed5984b1c 100644 --- a/diff-delta.c +++ b/diff-delta.c @@ -19,8 +19,9 @@ */ #include <stdlib.h> +#include <string.h> +#include <zlib.h> #include "delta.h" -#include "zlib.h" /* block size: min = 16, max = 64k, power of 2 */ @@ -29,149 +30,87 @@ #define MIN(a, b) ((a) < (b) ? (a) : (b)) #define GR_PRIME 0x9e370001 -#define HASH(v, b) (((unsigned int)(v) * GR_PRIME) >> (32 - (b))) - -static unsigned int hashbits(unsigned int size) -{ - unsigned int val = 1, bits = 0; - while (val < size && bits < 32) { - val <<= 1; - bits++; - } - return bits ? bits: 1; -} - -typedef struct s_chanode { - struct s_chanode *next; - int icurr; -} chanode_t; - -typedef struct s_chastore { - int isize, nsize; - chanode_t *ancur; -} chastore_t; - -static void cha_init(chastore_t *cha, int isize, int icount) -{ - cha->isize = isize; - cha->nsize = icount * isize; - cha->ancur = NULL; -} - -static void *cha_alloc(chastore_t *cha) -{ - chanode_t *ancur; - void *data; +#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift)) - ancur = cha->ancur; - if (!ancur || ancur->icurr == cha->nsize) { - ancur = malloc(sizeof(chanode_t) + cha->nsize); - if (!ancur) - return NULL; - ancur->icurr = 0; - ancur->next = cha->ancur; - cha->ancur = ancur; - } - - data = (void *)ancur + sizeof(chanode_t) + ancur->icurr; - ancur->icurr += cha->isize; - return data; -} - -static void cha_free(chastore_t *cha) -{ - chanode_t *cur = cha->ancur; - while (cur) { - chanode_t *tmp = cur; - cur = cur->next; - free(tmp); - } -} - -typedef struct s_bdrecord { - struct s_bdrecord *next; - unsigned int fp; +struct index { const unsigned char *ptr; -} bdrecord_t; - -typedef struct s_bdfile { - chastore_t cha; - unsigned int fphbits; - bdrecord_t **fphash; -} bdfile_t; + unsigned int val; + struct index *next; +}; -static int delta_prepare(const unsigned char *buf, int bufsize, bdfile_t *bdf) +static struct index ** delta_index(const unsigned char *buf, + unsigned long bufsize, + unsigned int *hash_shift) { - unsigned int fphbits; - int i, hsize; - const unsigned char *data, *top; - bdrecord_t *brec; - bdrecord_t **fphash; - - fphbits = hashbits(bufsize / BLK_SIZE + 1); - hsize = 1 << fphbits; - fphash = malloc(hsize * sizeof(bdrecord_t *)); - if (!fphash) - return -1; - for (i = 0; i < hsize; i++) - fphash[i] = NULL; - cha_init(&bdf->cha, sizeof(bdrecord_t), hsize / 4 + 1); - - top = buf + bufsize; - data = buf + (bufsize / BLK_SIZE) * BLK_SIZE; - if (data == top) + unsigned int hsize, hshift, entries, blksize, i; + const unsigned char *data; + struct index *entry, **hash; + void *mem; + + /* determine index hash size */ + entries = (bufsize + BLK_SIZE - 1) / BLK_SIZE; + hsize = entries / 4; + for (i = 4; (1 << i) < hsize && i < 16; i++); + hsize = 1 << i; + hshift = 32 - i; + *hash_shift = hshift; + + /* allocate lookup index */ + mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry)); + if (!mem) + return NULL; + hash = mem; + entry = mem + hsize * sizeof(*hash); + memset(hash, 0, hsize * sizeof(*hash)); + + /* then populate it */ + data = buf + entries * BLK_SIZE - BLK_SIZE; + blksize = bufsize - (data - buf); + while (data >= buf) { + unsigned int val = adler32(0, data, blksize); + i = HASH(val, hshift); + entry->ptr = data; + entry->val = val; + entry->next = hash[i]; + hash[i] = entry++; + blksize = BLK_SIZE; data -= BLK_SIZE; + } - for ( ; data >= buf; data -= BLK_SIZE) { - brec = cha_alloc(&bdf->cha); - if (!brec) { - cha_free(&bdf->cha); - free(fphash); - return -1; - } - brec->fp = adler32(0, data, MIN(BLK_SIZE, top - data)); - brec->ptr = data; - i = HASH(brec->fp, fphbits); - brec->next = fphash[i]; - fphash[i] = brec; - } - - bdf->fphbits = fphbits; - bdf->fphash = fphash; - - return 0; -} - -static void delta_cleanup(bdfile_t *bdf) -{ - free(bdf->fphash); - cha_free(&bdf->cha); + return hash; } +/* provide the size of the copy opcode given the block offset and size */ #define COPYOP_SIZE(o, s) \ (!!(o & 0xff) + !!(o & 0xff00) + !!(o & 0xff0000) + !!(o & 0xff000000) + \ !!(s & 0xff) + !!(s & 0xff00) + 1) +/* 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) { - int i, outpos, outsize, inscnt, csize, msize, moff; - unsigned int fp; - const unsigned char *ref_data, *ref_top, *data, *top, *ptr1, *ptr2; - unsigned char *out, *orig; - bdrecord_t *brec; - bdfile_t bdf; + unsigned int i, outpos, outsize, inscnt, hash_shift; + const unsigned char *ref_data, *ref_top, *data, *top; + unsigned char *out; + struct index *entry, **hash; - if (!from_size || !to_size || delta_prepare(from_buf, from_size, &bdf)) + if (!from_size || !to_size) + return NULL; + hash = delta_index(from_buf, from_size, &hash_shift); + if (!hash) return NULL; - + outpos = 0; outsize = 8192; + if (max_size && outsize >= max_size) + outsize = max_size + MAX_OP_SIZE + 1; out = malloc(outsize); if (!out) { - delta_cleanup(&bdf); + free(hash); return NULL; } @@ -199,28 +138,32 @@ void *diff_delta(void *from_buf, unsigned long from_size, } inscnt = 0; - moff = 0; - while (data < top) { - msize = 0; - fp = adler32(0, data, MIN(top - data, BLK_SIZE)); - i = HASH(fp, bdf.fphbits); - for (brec = bdf.fphash[i]; brec; brec = brec->next) { - if (brec->fp == fp) { - csize = ref_top - brec->ptr; - if (csize > top - data) - csize = top - data; - for (ptr1 = brec->ptr, ptr2 = data; - csize && *ptr1 == *ptr2; - csize--, ptr1++, ptr2++); - csize = ptr1 - brec->ptr; - if (csize > msize) { - moff = brec->ptr - ref_data; - msize = csize; - if (msize >= 0x10000) { - msize = 0x10000; - break; - } + while (data < top) { + unsigned int moff = 0, msize = 0; + unsigned int blksize = MIN(top - data, BLK_SIZE); + unsigned int val = adler32(0, data, blksize); + 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; + while (ref_size && *src++ == *ref) { + ref++; + ref_size--; + } + ref_size = ref - entry->ptr; + if (ref_size > msize) { + /* this is our best match so far */ + moff = entry->ptr - ref_data; + msize = ref_size; + if (msize >= 0x10000) { + msize = 0x10000; + break; } } } @@ -235,13 +178,15 @@ void *diff_delta(void *from_buf, unsigned long from_size, inscnt = 0; } } else { + unsigned char *op; + if (inscnt) { out[outpos - inscnt - 1] = inscnt; inscnt = 0; } data += msize; - orig = out + outpos++; + op = out + outpos++; i = 0x80; if (moff & 0xff) { out[outpos++] = moff; i |= 0x01; } @@ -256,23 +201,21 @@ void *diff_delta(void *from_buf, unsigned long from_size, msize >>= 8; if (msize & 0xff) { out[outpos++] = msize; i |= 0x20; } - *orig = i; - } - - if (max_size && outpos > max_size) { - free(out); - delta_cleanup(&bdf); - return NULL; + *op = i; } - /* next time around the largest possible output is 1 + 4 + 3 */ - if (outpos > outsize - 8) { + if (outpos >= outsize - MAX_OP_SIZE) { void *tmp = out; outsize = outsize * 3 / 2; - out = realloc(out, outsize); + if (max_size && outsize >= max_size) + outsize = max_size + MAX_OP_SIZE + 1; + if (max_size && outpos > max_size) + out = NULL; + else + out = realloc(out, outsize); if (!out) { free(tmp); - delta_cleanup(&bdf); + free(hash); return NULL; } } @@ -281,7 +224,7 @@ void *diff_delta(void *from_buf, unsigned long from_size, if (inscnt) out[outpos - inscnt - 1] = inscnt; - delta_cleanup(&bdf); + free(hash); *delta_size = outpos; return out; } diff --git a/diff-files.c b/diff-files.c index 0c3f80046b..b1c05b325a 100644 --- a/diff-files.c +++ b/diff-files.c @@ -193,7 +193,7 @@ int main(int argc, const char **argv) show_file('-', ce); continue; } - changed = ce_match_stat(ce, &st); + changed = ce_match_stat(ce, &st, 0); if (!changed && !diff_options.find_copies_harder) continue; oldmode = ntohl(ce->ce_mode); diff --git a/diff-index.c b/diff-index.c index f8a102ec16..12a9418d6b 100644 --- a/diff-index.c +++ b/diff-index.c @@ -33,7 +33,7 @@ static int get_stat_data(struct cache_entry *ce, } return -1; } - changed = ce_match_stat(ce, &st); + changed = ce_match_stat(ce, &st, 0); if (changed) { mode = create_ce_mode(st.st_mode); if (!trust_executable_bit && @@ -311,7 +311,7 @@ static int work_tree_matches(const char *name, const unsigned char *sha1) ce = active_cache[pos]; if ((lstat(name, &st) < 0) || !S_ISREG(st.st_mode) || /* careful! */ - ce_match_stat(ce, &st) || + ce_match_stat(ce, &st, 0) || memcmp(sha1, ce->sha1, 20)) return 0; /* we return 1 only when we can stat, it is a regular file, @@ -123,7 +123,7 @@ int checkout_entry(struct cache_entry *ce, struct checkout *state) strcpy(path + len, ce->name); if (!lstat(path, &st)) { - unsigned changed = ce_match_stat(ce, &st); + unsigned changed = ce_match_stat(ce, &st, 1); if (!changed) return 0; if (!state->force) { diff --git a/environment.c b/environment.c index 0596fc647b..251e53ca09 100644 --- a/environment.c +++ b/environment.c @@ -12,6 +12,7 @@ char git_default_email[MAX_GITNAME]; char git_default_name[MAX_GITNAME]; int trust_executable_bit = 1; +int assume_unchanged = 0; int only_use_symrefs = 0; int repository_format_version = 0; char git_commit_encoding[MAX_ENCODING_LENGTH] = "utf-8"; diff --git a/fetch-pack.c b/fetch-pack.c index aa6f42ae1b..09738fee91 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -8,7 +8,7 @@ static int keep_pack; static int quiet; static int verbose; static const char fetch_pack_usage[] = -"git-fetch-pack [-q] [-v] [-k] [--exec=upload-pack] [host:]directory <refs>..."; +"git-fetch-pack [-q] [-v] [-k] [--thin] [--exec=upload-pack] [host:]directory <refs>..."; static const char *exec = "git-upload-pack"; #define COMPLETE (1U << 0) @@ -18,7 +18,7 @@ static const char *exec = "git-upload-pack"; #define POPPED (1U << 4) static struct commit_list *rev_list = NULL; -static int non_common_revs = 0, multi_ack = 0; +static int non_common_revs = 0, multi_ack = 0, use_thin_pack = 0; static void rev_list_push(struct commit *commit, int mark) { @@ -156,8 +156,9 @@ static int find_common(int fd[2], unsigned char *result_sha1, continue; } - packet_write(fd[1], "want %s%s\n", sha1_to_hex(remote), - multi_ack ? " multi_ack" : ""); + packet_write(fd[1], "want %s%s%s\n", sha1_to_hex(remote), + (multi_ack ? " multi_ack" : ""), + (use_thin_pack ? " thin-pack" : "")); fetching++; } packet_flush(fd[1]); @@ -421,6 +422,10 @@ int main(int argc, char **argv) keep_pack = 1; continue; } + if (!strcmp("--thin", arg)) { + use_thin_pack = 1; + continue; + } if (!strcmp("-v", arg)) { verbose = 1; continue; @@ -434,6 +439,8 @@ int main(int argc, char **argv) } if (!dest) usage(fetch_pack_usage); + if (keep_pack) + use_thin_pack = 0; pid = git_connect(fd, dest, exec); if (pid < 0) return 1; diff --git a/git-add.sh b/git-add.sh index 13fad820d4..d6a4bc7d09 100755 --- a/git-add.sh +++ b/git-add.sh @@ -14,6 +14,10 @@ while : ; do -v) verbose=--verbose ;; + --) + shift + break + ;; -*) usage ;; @@ -1,11 +1,13 @@ #!/bin/sh # -# +# Copyright (c) 2005, 2006 Junio C Hamano USAGE='[--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] <mbox> or, when resuming [--skip | --resolved]' . git-sh-setup +git var GIT_COMMITTER_IDENT >/dev/null || exit + stop_here () { echo "$1" >"$dotest/next" exit 1 diff --git a/git-applymbox.sh b/git-applymbox.sh index 61c8c024c6..5569fdcc34 100755 --- a/git-applymbox.sh +++ b/git-applymbox.sh @@ -21,6 +21,8 @@ USAGE='[-u] [-k] [-q] [-m] (-c .dotest/<num> | mbox) [signoff]' . git-sh-setup +git var GIT_COMMITTER_IDENT >/dev/null || exit + keep_subject= query_apply= continue= utf8= resume=t while case "$#" in 0) break ;; esac do diff --git a/git-clone.sh b/git-clone.sh index d184ceb7a6..dc0ad552a3 100755 --- a/git-clone.sh +++ b/git-clone.sh @@ -154,7 +154,7 @@ yes,yes) fi && rm -f "$GIT_DIR/objects/sample" && cd "$repo" && - find objects -depth -print | cpio -puamd$l "$GIT_DIR/" || exit 1 + find objects -depth -print | cpio -pumd$l "$GIT_DIR/" || exit 1 ;; yes) mkdir -p "$GIT_DIR/objects/info" diff --git a/git-cvsimport.perl b/git-cvsimport.perl index 24f9834342..b46469ab32 100755 --- a/git-cvsimport.perl +++ b/git-cvsimport.perl @@ -846,8 +846,12 @@ while(<CVS>) { print "Drop $fn\n" if $opt_v; } else { print "".($init ? "New" : "Update")." $fn: $size bytes\n" if $opt_v; - open my $F, '-|', "git-hash-object -w $tmpname" + my $pid = open(my $F, '-|'); + die $! unless defined $pid; + if (!$pid) { + exec("git-hash-object", "-w", $tmpname) or die "Cannot create object: $!\n"; + } my $sha = <$F>; chomp $sha; close $F; diff --git a/git-fetch.sh b/git-fetch.sh index b4325d9d98..23d965f327 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -320,7 +320,7 @@ fetch_main () { ( : subshell because we muck with IFS IFS=" $LF" ( - git-fetch-pack $exec $keep "$remote" $rref || echo failed "$remote" + git-fetch-pack $exec $keep --thin "$remote" $rref || echo failed "$remote" ) | while read sha1 remote_name do diff --git a/git-fmt-merge-msg.perl b/git-fmt-merge-msg.perl index c34ddc5d5e..c13af4884a 100755 --- a/git-fmt-merge-msg.perl +++ b/git-fmt-merge-msg.perl @@ -28,11 +28,12 @@ sub andjoin { } sub repoconfig { - my $fh; my $val; eval { - open $fh, '-|', 'git-repo-config', '--get', 'merge.summary' - or die "$!"; + my $pid = open(my $fh, '-|'); + if (!$pid) { + exec('git-repo-config', '--get', 'merge.summary'); + } ($val) = <$fh>; close $fh; }; @@ -41,25 +42,32 @@ sub repoconfig { sub current_branch { my $fh; - open $fh, '-|', 'git-symbolic-ref', 'HEAD' or die "$!"; + my $pid = open($fh, '-|'); + die "$!" unless defined $pid; + if (!$pid) { + exec('git-symbolic-ref', 'HEAD') or die "$!"; + } my ($bra) = <$fh>; chomp($bra); + close $fh or die "$!"; $bra =~ s|^refs/heads/||; if ($bra ne 'master') { $bra = " into $bra"; } else { $bra = ""; } - return $bra; } sub shortlog { - my ($tip, $limit) = @_; + my ($tip) = @_; my ($fh, @result); - open $fh, '-|', ('git-log', "--max-count=$limit", '--topo-order', - '--pretty=oneline', $tip, '^HEAD') - or die "$!"; + my $pid = open($fh, '-|'); + die "$!" unless defined $pid; + if (!$pid) { + exec('git-log', '--topo-order', + '--pretty=oneline', $tip, '^HEAD') or die "$!"; + } while (<$fh>) { s/^[0-9a-f]{40}\s+//; push @result, $_; @@ -160,7 +168,7 @@ my $limit = 20; for (@origin) { my ($sha1, $name) = @$_; - my @log = shortlog($sha1, $limit + 1); + my @log = shortlog($sha1); if ($limit + 1 <= @log) { print "\n* $name: (" . scalar(@log) . " commits)\n"; } diff --git a/git-format-patch.sh b/git-format-patch.sh index e54c9e4a94..eb75de4601 100755 --- a/git-format-patch.sh +++ b/git-format-patch.sh @@ -189,7 +189,7 @@ my @month_names = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); sub show_date { my ($time, $tz) = @_; my $minutes = abs($tz); - $minutes = ($minutes / 100) * 60 + ($minutes % 100); + $minutes = int($minutes / 100) * 60 + ($minutes % 100); if ($tz < 0) { $minutes = -$minutes; } diff --git a/git-merge.sh b/git-merge.sh index 74f07610fa..4609fe54d5 100755 --- a/git-merge.sh +++ b/git-merge.sh @@ -13,6 +13,10 @@ LF=' all_strategies='recursive octopus resolve stupid ours' default_strategies='recursive' use_strategies= +if test "@@NO_PYTHON@@"; then + all_strategies='resolve octopus stupid ours' + default_strategies='resolve' +fi dropsave() { rm -f -- "$GIT_DIR/MERGE_HEAD" "$GIT_DIR/MERGE_MSG" \ @@ -142,6 +146,8 @@ case "$#,$common,$no_commit" in 1,*,) # We are not doing octopus, not fast forward, and have only # one common. See if it is really trivial. + git var GIT_COMMITTER_IDENT >/dev/null || exit + echo "Trying really trivial in-index merge..." git-update-index --refresh 2>/dev/null if git-read-tree --trivial -m -u $common $head "$1" && @@ -179,6 +185,9 @@ case "$#,$common,$no_commit" in ;; esac +# We are going to make a new commit. +git var GIT_COMMITTER_IDENT >/dev/null || exit + case "$use_strategies" in '') case "$#" in diff --git a/git-push.sh b/git-push.sh index 706db9933e..73dcf067cb 100755 --- a/git-push.sh +++ b/git-push.sh @@ -8,6 +8,7 @@ USAGE='[--all] [--tags] [--force] <repository> [<refspec>...]' has_all= has_force= has_exec= +has_thin= remote= do_tags= @@ -22,6 +23,8 @@ do has_force=--force ;; --exec=*) has_exec="$1" ;; + --thin) + has_thin="$1" ;; -*) usage ;; *) @@ -72,6 +75,7 @@ set x "$remote" "$@"; shift test "$has_all" && set x "$has_all" "$@" && shift test "$has_force" && set x "$has_force" "$@" && shift test "$has_exec" && set x "$has_exec" "$@" && shift +test "$has_thin" && set x "$has_thin" "$@" && shift case "$remote" in http://* | https://*) diff --git a/git-rebase.sh b/git-rebase.sh index 21c3d83c3a..5956f0654e 100755 --- a/git-rebase.sh +++ b/git-rebase.sh @@ -4,24 +4,28 @@ # USAGE='[--onto <newbase>] <upstream> [<branch>]' -LONG_USAGE='If <branch> is specified, switch to that branch first. Then, -extract commits in the current branch that are not in <upstream>, -and reconstruct the current on top of <upstream>, discarding the original -development history. If --onto <newbase> is specified, the history is -reconstructed on top of <newbase>, instead of <upstream>. For example, -while on "topic" 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 - $ '"$0"' --onto master~1 master topic +The result of the following command: -would rewrite the history to look like this: + git-rebase --onto master~1 master topic + would be: - A'\''--B'\''--C'\'' topic - / + A'\''--B'\''--C'\'' topic + / D---E---F---G master ' @@ -71,7 +75,7 @@ esac # The upstream head must be given. Make sure it is valid. upstream_name="$1" upstream=`git rev-parse --verify "${upstream_name}^0"` || - die "invalid upsteram $upstream_name" + die "invalid upstream $upstream_name" # If a hook exists, give it a chance to interrupt if test -x "$GIT_DIR/hooks/pre-rebase" diff --git a/git-repack.sh b/git-repack.sh index 1fafb6ecf6..3d6fec1c9a 100755 --- a/git-repack.sh +++ b/git-repack.sh @@ -3,17 +3,20 @@ # Copyright (c) 2005 Linus Torvalds # -USAGE='[-a] [-d] [-l] [-n]' +USAGE='[-a] [-d] [-f] [-l] [-n] [-q]' . git-sh-setup -no_update_info= all_into_one= remove_redundant= local= +no_update_info= all_into_one= remove_redundant= +local= quiet= no_reuse_delta= while case "$#" in 0) break ;; esac do case "$1" in -n) no_update_info=t ;; -a) all_into_one=t ;; -d) remove_redundant=t ;; - -l) local=t ;; + -q) quiet=-q ;; + -f) no_reuse_delta=--no-reuse-delta ;; + -l) local=--local ;; *) usage ;; esac shift @@ -39,9 +42,7 @@ case ",$all_into_one," in find . -type f \( -name '*.pack' -o -name '*.idx' \) -print` ;; esac -if [ "$local" ]; then - pack_objects="$pack_objects --local" -fi +pack_objects="$pack_objects $local $quiet $no_reuse_delta" name=$(git-rev-list --objects $rev_list $(git-rev-parse $rev_parse) 2>&1 | git-pack-objects --non-empty $pack_objects .tmp-pack) || exit 1 diff --git a/git-rerere.perl b/git-rerere.perl index df119517fe..d3664ff491 100755 --- a/git-rerere.perl +++ b/git-rerere.perl @@ -131,7 +131,11 @@ sub record_preimage { sub find_conflict { my $in; local $/ = "\0"; - open $in, '-|', qw(git ls-files -z -u) or die "$!: ls-files"; + my $pid = open($in, '-|'); + die "$!" unless defined $pid; + if (!$pid) { + exec(qw(git ls-files -z -u)) or die "$!: ls-files"; + } my %path = (); my @path = (); while (<$in>) { diff --git a/git-resolve.sh b/git-resolve.sh index 9263070054..b53ede8d87 100755 --- a/git-resolve.sh +++ b/git-resolve.sh @@ -50,6 +50,9 @@ case "$common" in ;; esac +# We are going to make a new commit. +git var GIT_COMMITTER_IDENT >/dev/null || exit + # Find an optimum merge base if there are more than one candidates. LF=' ' diff --git a/git-revert.sh b/git-revert.sh index 2c5870684c..c19d3a6916 100755 --- a/git-revert.sh +++ b/git-revert.sh @@ -141,8 +141,9 @@ git-read-tree -m -u $base $head $next && result=$(git-write-tree 2>/dev/null) || { echo >&2 "Simple $me fails; trying Automatic $me." git-merge-index -o git-merge-one-file -a || { - echo >&2 "Automatic $me failed. After fixing it up," - echo >&2 "you can use \"git commit -F .msg\"" + echo >&2 "Automatic $me failed. After resolving the conflicts," + echo >&2 "mark the corrected paths with 'git-update-index <paths>'" + echo >&2 "and commit with 'git commit -F .msg'" case "$me" in cherry-pick) echo >&2 "You may choose to use the following when making" diff --git a/git-send-email.perl b/git-send-email.perl index 13b85dddd1..b0d095b4e9 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -59,24 +59,29 @@ my $rc = GetOptions("from=s" => \$from, # Now, let's fill any that aren't set in with defaults: -open(GITVAR,"-|","git-var","-l") - or die "Failed to open pipe from git-var: $!"; - -my ($author,$committer); -while(<GITVAR>) { - chomp; - my ($var,$data) = split /=/,$_,2; - my @fields = split /\s+/, $data; - - my $ident = join(" ", @fields[0...(@fields-3)]); +sub gitvar { + my ($var) = @_; + my $fh; + my $pid = open($fh, '-|'); + die "$!" unless defined $pid; + if (!$pid) { + exec('git-var', $var) or die "$!"; + } + my ($val) = <$fh>; + close $fh or die "$!"; + chomp($val); + return $val; +} - if ($var eq 'GIT_AUTHOR_IDENT') { - $author = $ident; - } elsif ($var eq 'GIT_COMMITTER_IDENT') { - $committer = $ident; - } +sub gitvar_ident { + my ($name) = @_; + my $val = gitvar($name); + my @field = split(/\s+/, $val); + return join(' ', @field[0...(@field-3)]); } -close(GITVAR); + +my ($author) = gitvar_ident('GIT_AUTHOR_IDENT'); +my ($committer) = gitvar_ident('GIT_COMMITTER_IDENT'); my $prompting = 0; if (!defined $from) { diff --git a/git-svnimport.perl b/git-svnimport.perl index c536d7026d..ee2940f480 100755 --- a/git-svnimport.perl +++ b/git-svnimport.perl @@ -10,7 +10,6 @@ # The head revision is on branch "origin" by default. # You can change that with the '-o' option. -require 5.008; # for shell-safe open("-|",LIST) use strict; use warnings; use Getopt::Std; @@ -322,8 +321,12 @@ sub get_file($$$) { return undef unless defined $name; } - open my $F, '-|', "git-hash-object", "-w", $name + my $pid = open(my $F, '-|'); + die $! unless defined $pid; + if (!$pid) { + exec("git-hash-object", "-w", $name) or die "Cannot create object: $!\n"; + } my $sha = <$F>; chomp $sha; close $F; @@ -398,7 +401,12 @@ sub copy_path($$$$$$$$) { $srcpath =~ s#/*$#/#; } - open my $f,"-|","git-ls-tree","-r","-z",$gitrev,$srcpath; + my $pid = open my $f,'-|'; + die $! unless defined $pid; + if (!$pid) { + exec("git-ls-tree","-r","-z",$gitrev,$srcpath) + or die $!; + } local $/ = "\0"; while(<$f>) { chomp; @@ -554,7 +562,11 @@ sub commit { @o1 = @old; @old = (); } - open my $F, "-|", "git-ls-files", "-z", @o1 or die $!; + my $pid = open my $F, "-|"; + die "$!" unless defined $pid; + if (!$pid) { + exec("git-ls-files", "-z", @o1) or die $!; + } @o1 = (); local $/ = "\0"; while(<$F>) { @@ -1936,7 +1936,7 @@ proc findfiles {} { global selectedline numcommits lineid ctext global ffileline finddidsel parents nparents global findinprogress findstartline findinsertpos - global treediffs fdiffids fdiffsneeded fdiffpos + global treediffs fdiffid fdiffsneeded fdiffpos global findmergefiles if {$numcommits == 0} return @@ -1953,11 +1953,9 @@ proc findfiles {} { while 1 { set id $lineid($l) if {$findmergefiles || $nparents($id) == 1} { - foreach p $parents($id) { - if {![info exists treediffs([list $id $p])]} { - append diffsneeded "$id $p\n" - lappend fdiffsneeded [list $id $p] - } + if {![info exists treediffs($id)]} { + append diffsneeded "$id\n" + lappend fdiffsneeded $id } } if {[incr l] >= $numcommits} { @@ -1974,7 +1972,7 @@ proc findfiles {} { error_popup "Error starting search process: $err" return } - catch {unset fdiffids} + catch {unset fdiffid} set fdiffpos 0 fconfigure $df -blocking 0 fileevent $df readable [list readfilediffs $df] @@ -1983,16 +1981,15 @@ proc findfiles {} { set finddidsel 0 set findinsertpos end set id $lineid($l) - set p [lindex $parents($id) 0] . config -cursor watch settextcursor watch set findinprogress 1 - findcont [list $id $p] + findcont $id update } proc readfilediffs {df} { - global findids fdiffids fdiffs + global findid fdiffid fdiffs set n [gets $df line] if {$n < 0} { @@ -2002,19 +1999,19 @@ proc readfilediffs {df} { stopfindproc bell error_popup "Error in git-diff-tree: $err" - } elseif {[info exists findids]} { - set ids $findids + } elseif {[info exists findid]} { + set id $findid stopfindproc bell - error_popup "Couldn't find diffs for {$ids}" + error_popup "Couldn't find diffs for $id" } } return } - if {[regexp {^([0-9a-f]{40}) \(from ([0-9a-f]{40})\)} $line match id p]} { + if {[regexp {^([0-9a-f]{40})$} $line match id]} { # start of a new string of diffs donefilediff - set fdiffids [list $id $p] + set fdiffid $id set fdiffs {} } elseif {[string match ":*" $line]} { lappend fdiffs [lindex $line 5] @@ -2022,53 +2019,50 @@ proc readfilediffs {df} { } proc donefilediff {} { - global fdiffids fdiffs treediffs findids + global fdiffid fdiffs treediffs findid global fdiffsneeded fdiffpos - if {[info exists fdiffids]} { - while {[lindex $fdiffsneeded $fdiffpos] ne $fdiffids + if {[info exists fdiffid]} { + while {[lindex $fdiffsneeded $fdiffpos] ne $fdiffid && $fdiffpos < [llength $fdiffsneeded]} { # git-diff-tree doesn't output anything for a commit # which doesn't change anything - set nullids [lindex $fdiffsneeded $fdiffpos] - set treediffs($nullids) {} - if {[info exists findids] && $nullids eq $findids} { - unset findids - findcont $nullids + set nullid [lindex $fdiffsneeded $fdiffpos] + set treediffs($nullid) {} + if {[info exists findid] && $nullid eq $findid} { + unset findid + findcont $nullid } incr fdiffpos } incr fdiffpos - if {![info exists treediffs($fdiffids)]} { - set treediffs($fdiffids) $fdiffs + if {![info exists treediffs($fdiffid)]} { + set treediffs($fdiffid) $fdiffs } - if {[info exists findids] && $fdiffids eq $findids} { - unset findids - findcont $fdiffids + if {[info exists findid] && $fdiffid eq $findid} { + unset findid + findcont $fdiffid } } } -proc findcont {ids} { - global findids treediffs parents nparents +proc findcont {id} { + global findid treediffs parents nparents global ffileline findstartline finddidsel global lineid numcommits matchinglines findinprogress global findmergefiles - set id [lindex $ids 0] - set p [lindex $ids 1] - set pi [lsearch -exact $parents($id) $p] set l $ffileline while 1 { if {$findmergefiles || $nparents($id) == 1} { - if {![info exists treediffs($ids)]} { - set findids $ids + if {![info exists treediffs($id)]} { + set findid $id set ffileline $l return } set doesmatch 0 - foreach f $treediffs($ids) { + foreach f $treediffs($id) { set x [findmatches $f] if {$x != {}} { set doesmatch 1 @@ -2077,21 +2071,13 @@ proc findcont {ids} { } if {$doesmatch} { insertmatch $l $id - set pi $nparents($id) } - } else { - set pi $nparents($id) } - if {[incr pi] >= $nparents($id)} { - set pi 0 - if {[incr l] >= $numcommits} { - set l 0 - } - if {$l == $findstartline} break - set id $lineid($l) + if {[incr l] >= $numcommits} { + set l 0 } - set p [lindex $parents($id) $pi] - set ids [list $id $p] + if {$l == $findstartline} break + set id $lineid($l) } stopfindproc if {!$finddidsel} { @@ -156,8 +156,18 @@ static int copy(char *buf, int size, int offset, const char *src) return offset; } +static const char au_env[] = "GIT_AUTHOR_NAME"; +static const char co_env[] = "GIT_COMMITTER_NAME"; +static const char *env_hint = +"\n*** Environment problem:\n" +"*** Your name cannot be determined from your system services (gecos).\n" +"*** You would need to set %s and %s\n" +"*** environment variables; otherwise you won't be able to perform\n" +"*** certain operations because of \"empty ident\" errors.\n" +"*** Alternatively, you can use user.name configuration variable.\n\n"; + static const char *get_ident(const char *name, const char *email, - const char *date_str) + const char *date_str, int error_on_no_name) { static char buffer[1000]; char date[50]; @@ -168,9 +178,14 @@ static const char *get_ident(const char *name, const char *email, if (!email) email = git_default_email; - if (!*name || !*email) - die("empty ident %s <%s> not allowed", - name, email); + if (!*name) { + if (name == git_default_name && env_hint) { + fprintf(stderr, env_hint, au_env, co_env); + env_hint = NULL; /* warn only once, for "git-var -l" */ + } + if (error_on_no_name) + die("empty ident %s <%s> not allowed", name, email); + } strcpy(date, git_default_date); if (date_str) @@ -187,16 +202,18 @@ static const char *get_ident(const char *name, const char *email, return buffer; } -const char *git_author_info(void) +const char *git_author_info(int error_on_no_name) { return get_ident(getenv("GIT_AUTHOR_NAME"), getenv("GIT_AUTHOR_EMAIL"), - getenv("GIT_AUTHOR_DATE")); + getenv("GIT_AUTHOR_DATE"), + error_on_no_name); } -const char *git_committer_info(void) +const char *git_committer_info(int error_on_no_name) { return get_ident(getenv("GIT_COMMITTER_NAME"), getenv("GIT_COMMITTER_EMAIL"), - getenv("GIT_COMMITTER_DATE")); + getenv("GIT_COMMITTER_DATE"), + error_on_no_name); } diff --git a/ls-files.c b/ls-files.c index df93cf2263..90b289f03d 100644 --- a/ls-files.c +++ b/ls-files.c @@ -20,6 +20,7 @@ static int show_unmerged = 0; static int show_modified = 0; static int show_killed = 0; static int show_other_directories = 0; +static int show_valid_bit = 0; static int line_terminator = '\n'; static int prefix_len = 0, prefix_offset = 0; @@ -457,6 +458,23 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce) if (pathspec && !match(pathspec, ps_matched, ce->name, len)) return; + if (tag && *tag && show_valid_bit && + (ce->ce_flags & htons(CE_VALID))) { + static char alttag[4]; + memcpy(alttag, tag, 3); + if (isalpha(tag[0])) + alttag[0] = tolower(tag[0]); + else if (tag[0] == '?') + alttag[0] = '!'; + else { + alttag[0] = 'v'; + alttag[1] = tag[0]; + alttag[2] = ' '; + alttag[3] = 0; + } + tag = alttag; + } + if (!show_stage) { fputs(tag, stdout); write_name_quoted("", 0, ce->name + offset, @@ -533,7 +551,7 @@ static void show_files(void) err = lstat(ce->name, &st); if (show_deleted && err) show_ce_entry(tag_removed, ce); - if (show_modified && ce_modified(ce, &st)) + if (show_modified && ce_modified(ce, &st, 0)) show_ce_entry(tag_modified, ce); } } @@ -606,7 +624,7 @@ static void verify_pathspec(void) } static const char ls_files_usage[] = - "git-ls-files [-z] [-t] (--[cached|deleted|others|stage|unmerged|killed|modified])* " + "git-ls-files [-z] [-t] [-v] (--[cached|deleted|others|stage|unmerged|killed|modified])* " "[ --ignored ] [--exclude=<pattern>] [--exclude-from=<file>] " "[ --exclude-per-directory=<filename> ] [--full-name] [--] [<file>]*"; @@ -631,13 +649,15 @@ int main(int argc, const char **argv) line_terminator = 0; continue; } - if (!strcmp(arg, "-t")) { + if (!strcmp(arg, "-t") || !strcmp(arg, "-v")) { tag_cached = "H "; tag_unmerged = "M "; tag_removed = "R "; tag_modified = "C "; tag_other = "? "; tag_killed = "K "; + if (arg[1] == 'v') + show_valid_bit = 1; continue; } if (!strcmp(arg, "-c") || !strcmp(arg, "--cached")) { @@ -758,6 +778,7 @@ int main(int argc, const char **argv) continue; error("pathspec '%s' did not match any.", pathspec[num] + prefix_offset); + errors++; } return errors ? 1 : 0; } diff --git a/merge-tree.c b/merge-tree.c new file mode 100644 index 0000000000..768d83a7c2 --- /dev/null +++ b/merge-tree.c @@ -0,0 +1,272 @@ +#include "cache.h" +#include "diff.h" + +static const char merge_tree_usage[] = "git-merge-tree <base-tree> <branch1> <branch2>"; +static int resolve_directories = 1; + +static void merge_trees(struct tree_desc t[3], const char *base); + +static void *fill_tree_descriptor(struct tree_desc *desc, const unsigned char *sha1) +{ + unsigned long size = 0; + void *buf = NULL; + + if (sha1) { + buf = read_object_with_reference(sha1, "tree", &size, NULL); + if (!buf) + die("unable to read tree %s", sha1_to_hex(sha1)); + } + desc->size = size; + desc->buf = buf; + return buf; +} + +struct name_entry { + const unsigned char *sha1; + const char *path; + unsigned int mode; + int pathlen; +}; + +static void entry_clear(struct name_entry *a) +{ + memset(a, 0, sizeof(*a)); +} + +static int entry_compare(struct name_entry *a, struct name_entry *b) +{ + return base_name_compare( + a->path, a->pathlen, a->mode, + b->path, b->pathlen, b->mode); +} + +static void entry_extract(struct tree_desc *t, struct name_entry *a) +{ + a->sha1 = tree_entry_extract(t, &a->path, &a->mode); + a->pathlen = strlen(a->path); +} + +/* An empty entry never compares same, not even to another empty entry */ +static int same_entry(struct name_entry *a, struct name_entry *b) +{ + return a->sha1 && + b->sha1 && + !memcmp(a->sha1, b->sha1, 20) && + a->mode == b->mode; +} + +static const char *sha1_to_hex_zero(const unsigned char *sha1) +{ + if (sha1) + return sha1_to_hex(sha1); + return "0000000000000000000000000000000000000000"; +} + +static void resolve(const char *base, struct name_entry *branch1, struct name_entry *result) +{ + char branch1_sha1[50]; + + /* If it's already branch1, don't bother showing it */ + if (!branch1) + return; + memcpy(branch1_sha1, sha1_to_hex_zero(branch1->sha1), 41); + + printf("0 %06o->%06o %s->%s %s%s\n", + branch1->mode, result->mode, + branch1_sha1, sha1_to_hex_zero(result->sha1), + base, result->path); +} + +static int unresolved_directory(const char *base, struct name_entry n[3]) +{ + int baselen; + char *newbase; + struct name_entry *p; + struct tree_desc t[3]; + void *buf0, *buf1, *buf2; + + if (!resolve_directories) + return 0; + p = n; + if (!p->mode) { + p++; + if (!p->mode) + p++; + } + if (!S_ISDIR(p->mode)) + return 0; + baselen = strlen(base); + newbase = xmalloc(baselen + p->pathlen + 2); + memcpy(newbase, base, baselen); + memcpy(newbase + baselen, p->path, p->pathlen); + memcpy(newbase + baselen + p->pathlen, "/", 2); + + buf0 = fill_tree_descriptor(t+0, n[0].sha1); + buf1 = fill_tree_descriptor(t+1, n[1].sha1); + buf2 = fill_tree_descriptor(t+2, n[2].sha1); + merge_trees(t, newbase); + + free(buf0); + free(buf1); + free(buf2); + free(newbase); + return 1; +} + +static void unresolved(const char *base, struct name_entry n[3]) +{ + if (unresolved_directory(base, n)) + return; + if (n[0].sha1) + printf("1 %06o %s %s%s\n", n[0].mode, sha1_to_hex(n[0].sha1), base, n[0].path); + if (n[1].sha1) + printf("2 %06o %s %s%s\n", n[1].mode, sha1_to_hex(n[1].sha1), base, n[1].path); + if (n[2].sha1) + printf("3 %06o %s %s%s\n", n[2].mode, sha1_to_hex(n[2].sha1), base, n[2].path); +} + +typedef void (*traverse_callback_t)(int n, unsigned long mask, struct name_entry *entry, const char *base); + +static void traverse_trees(int n, struct tree_desc *t, const char *base, traverse_callback_t callback) +{ + struct name_entry *entry = xmalloc(n*sizeof(*entry)); + + for (;;) { + struct name_entry entry[3]; + unsigned long mask = 0; + int i, last; + + last = -1; + for (i = 0; i < n; i++) { + if (!t[i].size) + continue; + entry_extract(t+i, entry+i); + if (last >= 0) { + int cmp = entry_compare(entry+i, entry+last); + + /* + * Is the new name bigger than the old one? + * Ignore it + */ + if (cmp > 0) + continue; + /* + * Is the new name smaller than the old one? + * Ignore all old ones + */ + if (cmp < 0) + mask = 0; + } + mask |= 1ul << i; + last = i; + } + if (!mask) + break; + + /* + * Update the tree entries we've walked, and clear + * all the unused name-entries. + */ + for (i = 0; i < n; i++) { + if (mask & (1ul << i)) { + update_tree_entry(t+i); + continue; + } + entry_clear(entry + i); + } + callback(n, mask, entry, base); + } + free(entry); +} + +/* + * Merge two trees together (t[1] and t[2]), using a common base (t[0]) + * as the origin. + * + * This walks the (sorted) trees in lock-step, checking every possible + * name. Note that directories automatically sort differently from other + * files (see "base_name_compare"), so you'll never see file/directory + * conflicts, because they won't ever compare the same. + * + * IOW, if a directory changes to a filename, it will automatically be + * seen as the directory going away, and the filename being created. + * + * Think of this as a three-way diff. + * + * The output will be either: + * - successful merge + * "0 mode sha1 filename" + * NOTE NOTE NOTE! FIXME! We really really need to walk the index + * in parallel with this too! + * + * - conflict: + * "1 mode sha1 filename" + * "2 mode sha1 filename" + * "3 mode sha1 filename" + * where not all of the 1/2/3 lines may exist, of course. + * + * The successful merge rules are the same as for the three-way merge + * in git-read-tree. + */ +static void threeway_callback(int n, unsigned long mask, struct name_entry *entry, const char *base) +{ + /* Same in both? */ + if (same_entry(entry+1, entry+2)) { + if (entry[0].sha1) { + resolve(base, NULL, entry+1); + return; + } + } + + if (same_entry(entry+0, entry+1)) { + if (entry[2].sha1 && !S_ISDIR(entry[2].mode)) { + resolve(base, entry+1, entry+2); + return; + } + } + + if (same_entry(entry+0, entry+2)) { + if (entry[1].sha1 && !S_ISDIR(entry[1].mode)) { + resolve(base, NULL, entry+1); + return; + } + } + + unresolved(base, entry); +} + +static void merge_trees(struct tree_desc t[3], const char *base) +{ + traverse_trees(3, t, base, threeway_callback); +} + +static void *get_tree_descriptor(struct tree_desc *desc, const char *rev) +{ + unsigned char sha1[20]; + void *buf; + + if (get_sha1(rev, sha1) < 0) + die("unknown rev %s", rev); + buf = fill_tree_descriptor(desc, sha1); + if (!buf) + die("%s is not a tree", rev); + return buf; +} + +int main(int argc, char **argv) +{ + struct tree_desc t[3]; + void *buf1, *buf2, *buf3; + + if (argc < 4) + usage(merge_tree_usage); + + buf1 = get_tree_descriptor(t+0, argv[1]); + buf2 = get_tree_descriptor(t+1, argv[2]); + buf3 = get_tree_descriptor(t+2, argv[3]); + merge_trees(t, ""); + free(buf1); + free(buf2); + free(buf3); + return 0; +} diff --git a/mktree.c b/mktree.c new file mode 100644 index 0000000000..f85358522b --- /dev/null +++ b/mktree.c @@ -0,0 +1,137 @@ +/* + * GIT - the stupid content tracker + * + * Copyright (c) Junio C Hamano, 2006 + */ +#include "cache.h" +#include "strbuf.h" +#include "quote.h" + +static struct treeent { + unsigned mode; + unsigned char sha1[20]; + int len; + char name[FLEX_ARRAY]; +} **entries; +static int alloc, used; + +static void append_to_tree(unsigned mode, unsigned char *sha1, char *path) +{ + struct treeent *ent; + int len = strlen(path); + if (strchr(path, '/')) + die("path %s contains slash", path); + + if (alloc <= used) { + alloc = alloc_nr(used); + entries = xrealloc(entries, sizeof(*entries) * alloc); + } + ent = entries[used++] = xmalloc(sizeof(**entries) + len + 1); + ent->mode = mode; + ent->len = len; + memcpy(ent->sha1, sha1, 20); + memcpy(ent->name, path, len+1); +} + +static int ent_compare(const void *a_, const void *b_) +{ + struct treeent *a = *(struct treeent **)a_; + struct treeent *b = *(struct treeent **)b_; + return base_name_compare(a->name, a->len, a->mode, + b->name, b->len, b->mode); +} + +static void write_tree(unsigned char *sha1) +{ + char *buffer; + unsigned long size, offset; + int i; + + qsort(entries, used, sizeof(*entries), ent_compare); + size = 100; + for (size = i = 0; i < used; i++) + size += 32 + entries[i]->len; + buffer = xmalloc(size); + offset = 0; + + for (i = 0; i < used; i++) { + struct treeent *ent = entries[i]; + + if (offset + ent->len + 100 < size) { + size = alloc_nr(offset + ent->len + 100); + buffer = xrealloc(buffer, size); + } + offset += sprintf(buffer + offset, "%o ", ent->mode); + offset += sprintf(buffer + offset, "%s", ent->name); + buffer[offset++] = 0; + memcpy(buffer + offset, ent->sha1, 20); + offset += 20; + } + write_sha1_file(buffer, offset, "tree", sha1); +} + +static const char mktree_usage[] = "mktree [-z]"; + +int main(int ac, char **av) +{ + struct strbuf sb; + unsigned char sha1[20]; + int line_termination = '\n'; + + setup_git_directory(); + + while ((1 < ac) && av[1][0] == '-') { + char *arg = av[1]; + if (!strcmp("-z", arg)) + line_termination = 0; + else + usage(mktree_usage); + ac--; + av++; + } + + strbuf_init(&sb); + while (1) { + int len; + char *ptr, *ntr; + unsigned mode; + char type[20]; + char *path; + + read_line(&sb, stdin, line_termination); + if (sb.eof) + break; + len = sb.len; + ptr = sb.buf; + /* Input is non-recursive ls-tree output format + * mode SP type SP sha1 TAB name + */ + mode = strtoul(ptr, &ntr, 8); + if (ptr == ntr || !ntr || *ntr != ' ') + die("input format error: %s", sb.buf); + ptr = ntr + 1; /* type */ + ntr = strchr(ptr, ' '); + if (!ntr || sb.buf + len <= ntr + 41 || + ntr[41] != '\t' || + get_sha1_hex(ntr + 1, sha1)) + die("input format error: %s", sb.buf); + if (sha1_object_info(sha1, type, NULL)) + die("object %s unavailable", sha1_to_hex(sha1)); + *ntr++ = 0; /* now at the beginning of SHA1 */ + if (strcmp(ptr, type)) + die("object type %s mismatch (%s)", ptr, type); + ntr += 41; /* at the beginning of name */ + if (line_termination && ntr[0] == '"') + path = unquote_c_style(ntr, NULL); + else + path = ntr; + + append_to_tree(mode, sha1, path); + + if (path != ntr) + free(path); + } + write_tree(sha1); + puts(sha1_to_hex(sha1)); + exit(0); +} diff --git a/pack-objects.c b/pack-objects.c index c5a5e61605..4f8814d8ee 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -3,32 +3,195 @@ #include "delta.h" #include "pack.h" #include "csum-file.h" +#include "diff.h" #include <sys/time.h> -static const char pack_usage[] = "git-pack-objects [-q] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; +static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; struct object_entry { unsigned char sha1[20]; - unsigned long size; - unsigned long offset; - unsigned int depth; - unsigned int hash; + unsigned long size; /* uncompressed size */ + unsigned long offset; /* offset into the final pack file; + * nonzero if already written. + */ + unsigned int depth; /* delta depth */ + unsigned int delta_limit; /* base adjustment for in-pack delta */ + unsigned int hash; /* name hint hash */ enum object_type type; - unsigned long delta_size; - struct object_entry *delta; + enum object_type in_pack_type; /* could be delta */ + unsigned long delta_size; /* delta data size (uncompressed) */ + struct object_entry *delta; /* delta base object */ + struct packed_git *in_pack; /* already in pack */ + unsigned int in_pack_offset; + struct object_entry *delta_child; /* delitified objects who bases me */ + struct object_entry *delta_sibling; /* other deltified objects who + * uses the same base as me + */ + int preferred_base; /* we do not pack this, but is encouraged to + * be used as the base objectto delta huge + * objects against. + */ + int based_on_preferred; /* current delta candidate is a preferred + * one, or delta against a preferred one. + */ }; +/* + * Objects we are going to pack are colected in objects array (dynamically + * expanded). nr_objects & nr_alloc controls this array. They are stored + * in the order we see -- typically rev-list --objects order that gives us + * nice "minimum seek" order. + * + * sorted-by-sha ans sorted-by-type are arrays of pointers that point at + * elements in the objects array. The former is used to build the pack + * index (lists object names in the ascending order to help offset lookup), + * and the latter is used to group similar things together by try_delta() + * heuristics. + */ + static unsigned char object_list_sha1[20]; static int non_empty = 0; +static int no_reuse_delta = 0; static int local = 0; static int incremental = 0; static struct object_entry **sorted_by_sha, **sorted_by_type; static struct object_entry *objects = NULL; -static int nr_objects = 0, nr_alloc = 0; +static int nr_objects = 0, nr_alloc = 0, nr_result = 0; static const char *base_name; static unsigned char pack_file_sha1[20]; static int progress = 1; +/* + * The object names in objects array are hashed with this hashtable, + * to help looking up the entry by object name. Binary search from + * sorted_by_sha is also possible but this was easier to code and faster. + * This hashtable is built after all the objects are seen. + */ +static int *object_ix = NULL; +static int object_ix_hashsz = 0; + +/* + * Pack index for existing packs give us easy access to the offsets into + * corresponding pack file where each object's data starts, but the entries + * do not store the size of the compressed representation (uncompressed + * size is easily available by examining the pack entry header). We build + * a hashtable of existing packs (pack_revindex), and keep reverse index + * here -- pack index file is sorted by object name mapping to offset; this + * pack_revindex[].revindex array is an ordered list of offsets, so if you + * know the offset of an object, next offset is where its packed + * representation ends. + */ +struct pack_revindex { + struct packed_git *p; + unsigned long *revindex; +} *pack_revindex = NULL; +static int pack_revindex_hashsz = 0; + +/* + * stats + */ +static int written = 0; +static int written_delta = 0; +static int reused = 0; +static int reused_delta = 0; + +static int pack_revindex_ix(struct packed_git *p) +{ + unsigned int ui = (unsigned int) p; + int i; + + ui = ui ^ (ui >> 16); /* defeat structure alignment */ + i = (int)(ui % pack_revindex_hashsz); + while (pack_revindex[i].p) { + if (pack_revindex[i].p == p) + return i; + if (++i == pack_revindex_hashsz) + i = 0; + } + return -1 - i; +} + +static void prepare_pack_ix(void) +{ + int num; + struct packed_git *p; + for (num = 0, p = packed_git; p; p = p->next) + num++; + if (!num) + return; + pack_revindex_hashsz = num * 11; + pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz); + for (p = packed_git; p; p = p->next) { + num = pack_revindex_ix(p); + num = - 1 - num; + pack_revindex[num].p = p; + } + /* revindex elements are lazily initialized */ +} + +static int cmp_offset(const void *a_, const void *b_) +{ + unsigned long a = *(unsigned long *) a_; + unsigned long b = *(unsigned long *) b_; + if (a < b) + return -1; + else if (a == b) + return 0; + else + return 1; +} + +/* + * Ordered list of offsets of objects in the pack. + */ +static void prepare_pack_revindex(struct pack_revindex *rix) +{ + struct packed_git *p = rix->p; + int num_ent = num_packed_objects(p); + int i; + void *index = p->index_base + 256; + + rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1)); + for (i = 0; i < num_ent; i++) { + long hl = *((long *)(index + 24 * i)); + rix->revindex[i] = ntohl(hl); + } + /* This knows the pack format -- the 20-byte trailer + * follows immediately after the last object data. + */ + rix->revindex[num_ent] = p->pack_size - 20; + qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset); +} + +static unsigned long find_packed_object_size(struct packed_git *p, + unsigned long ofs) +{ + int num; + int lo, hi; + struct pack_revindex *rix; + unsigned long *revindex; + num = pack_revindex_ix(p); + if (num < 0) + die("internal error: pack revindex uninitialized"); + rix = &pack_revindex[num]; + if (!rix->revindex) + prepare_pack_revindex(rix); + revindex = rix->revindex; + lo = 0; + hi = num_packed_objects(p) + 1; + do { + int mi = (lo + hi) / 2; + if (revindex[mi] == ofs) { + return revindex[mi+1] - ofs; + } + else if (ofs < revindex[mi]) + hi = mi; + else + lo = mi + 1; + } while (lo < hi); + die("internal error: pack revindex corrupt"); +} + static void *delta_against(void *buf, unsigned long size, struct object_entry *entry) { unsigned long othersize, delta_size; @@ -74,39 +237,77 @@ static int encode_header(enum object_type type, unsigned long size, unsigned cha return n; } -static unsigned long write_object(struct sha1file *f, struct object_entry *entry) +static unsigned long write_object(struct sha1file *f, + struct object_entry *entry) { unsigned long size; char type[10]; - void *buf = read_sha1_file(entry->sha1, type, &size); + void *buf; unsigned char header[10]; unsigned hdrlen, datalen; enum object_type obj_type; + int to_reuse = 0; - if (!buf) - die("unable to read %s", sha1_to_hex(entry->sha1)); - if (size != entry->size) - die("object %s size inconsistency (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size); + if (entry->preferred_base) + return 0; - /* - * The object header is a byte of 'type' followed by zero or - * more bytes of length. For deltas, the 20 bytes of delta sha1 - * follows that. - */ obj_type = entry->type; - if (entry->delta) { - buf = delta_against(buf, size, entry); - size = entry->delta_size; - obj_type = OBJ_DELTA; + if (! entry->in_pack) + to_reuse = 0; /* can't reuse what we don't have */ + else if (obj_type == OBJ_DELTA) + to_reuse = 1; /* check_object() decided it for us */ + else if (obj_type != entry->in_pack_type) + to_reuse = 0; /* pack has delta which is unusable */ + else if (entry->delta) + to_reuse = 0; /* we want to pack afresh */ + else + to_reuse = 1; /* we have it in-pack undeltified, + * and we do not need to deltify it. + */ + + if (! to_reuse) { + buf = read_sha1_file(entry->sha1, type, &size); + if (!buf) + die("unable to read %s", sha1_to_hex(entry->sha1)); + if (size != entry->size) + die("object %s size inconsistency (%lu vs %lu)", + sha1_to_hex(entry->sha1), size, entry->size); + if (entry->delta) { + buf = delta_against(buf, size, entry); + size = entry->delta_size; + obj_type = OBJ_DELTA; + } + /* + * The object header is a byte of 'type' followed by zero or + * more bytes of length. For deltas, the 20 bytes of delta + * sha1 follows that. + */ + hdrlen = encode_header(obj_type, size, header); + sha1write(f, header, hdrlen); + + if (entry->delta) { + sha1write(f, entry->delta, 20); + hdrlen += 20; + } + datalen = sha1write_compressed(f, buf, size); + free(buf); } - hdrlen = encode_header(obj_type, size, header); - sha1write(f, header, hdrlen); - if (entry->delta) { - sha1write(f, entry->delta, 20); - hdrlen += 20; + else { + struct packed_git *p = entry->in_pack; + use_packed_git(p); + + datalen = find_packed_object_size(p, entry->in_pack_offset); + buf = p->pack_base + entry->in_pack_offset; + sha1write(f, buf, datalen); + unuse_packed_git(p); + hdrlen = 0; /* not really */ + if (obj_type == OBJ_DELTA) + reused_delta++; + reused++; } - datalen = sha1write_compressed(f, buf, size); - free(buf); + if (obj_type == OBJ_DELTA) + written_delta++; + written++; return hdrlen + datalen; } @@ -132,32 +333,31 @@ static void write_pack_file(void) int i; struct sha1file *f; unsigned long offset; - unsigned long mb; struct pack_header hdr; if (!base_name) f = sha1fd(1, "<stdout>"); else - f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "pack"); + f = sha1create("%s-%s.%s", base_name, + sha1_to_hex(object_list_sha1), "pack"); hdr.hdr_signature = htonl(PACK_SIGNATURE); hdr.hdr_version = htonl(PACK_VERSION); - hdr.hdr_entries = htonl(nr_objects); + hdr.hdr_entries = htonl(nr_result); sha1write(f, &hdr, sizeof(hdr)); offset = sizeof(hdr); for (i = 0; i < nr_objects; i++) offset = write_one(f, objects + i, offset); sha1close(f, pack_file_sha1, 1); - mb = offset >> 20; - offset &= 0xfffff; } static void write_index_file(void) { int i; - struct sha1file *f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "idx"); + struct sha1file *f = sha1create("%s-%s.%s", base_name, + sha1_to_hex(object_list_sha1), "idx"); struct object_entry **list = sorted_by_sha; - struct object_entry **last = list + nr_objects; + struct object_entry **last = list + nr_result; unsigned int array[256]; /* @@ -182,7 +382,7 @@ static void write_index_file(void) * Write the actual SHA1 entries.. */ list = sorted_by_sha; - for (i = 0; i < nr_objects; i++) { + for (i = 0; i < nr_result; i++) { struct object_entry *entry = *list++; unsigned int offset = htonl(entry->offset); sha1write(f, &offset, 4); @@ -192,25 +392,87 @@ static void write_index_file(void) sha1close(f, NULL, 1); } -static int add_object_entry(unsigned char *sha1, unsigned int hash) +static int locate_object_entry_hash(const unsigned char *sha1) { + int i; + unsigned int ui; + memcpy(&ui, sha1, sizeof(unsigned int)); + i = ui % object_ix_hashsz; + while (0 < object_ix[i]) { + if (!memcmp(sha1, objects[object_ix[i]-1].sha1, 20)) + return i; + if (++i == object_ix_hashsz) + i = 0; + } + return -1 - i; +} + +static struct object_entry *locate_object_entry(const unsigned char *sha1) +{ + int i; + + if (!object_ix_hashsz) + return NULL; + + i = locate_object_entry_hash(sha1); + if (0 <= i) + return &objects[object_ix[i]-1]; + return NULL; +} + +static void rehash_objects(void) +{ + int i; + struct object_entry *oe; + + object_ix_hashsz = nr_objects * 3; + if (object_ix_hashsz < 1024) + object_ix_hashsz = 1024; + object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz); + object_ix = memset(object_ix, 0, sizeof(int) * object_ix_hashsz); + for (i = 0, oe = objects; i < nr_objects; i++, oe++) { + int ix = locate_object_entry_hash(oe->sha1); + if (0 <= ix) + continue; + ix = -1 - ix; + object_ix[ix] = i + 1; + } +} + +static int add_object_entry(const unsigned char *sha1, const char *name, int exclude) +{ + unsigned int hash = 0; unsigned int idx = nr_objects; struct object_entry *entry; + struct packed_git *p; + unsigned int found_offset = 0; + struct packed_git *found_pack = NULL; + int ix; - if (incremental || local) { - struct packed_git *p; - + if (!exclude) { for (p = packed_git; p; p = p->next) { struct pack_entry e; - if (find_pack_entry_one(sha1, &e, p)) { if (incremental) return 0; if (local && !p->pack_local) return 0; + if (!found_pack) { + found_offset = e.offset; + found_pack = e.p; + } } } } + if ((entry = locate_object_entry(sha1)) != NULL) + goto already_added; + + while (*name) { + unsigned char c = *name++; + if (isspace(c)) + continue; + hash = hash * 11 + c; + } if (idx >= nr_alloc) { unsigned int needed = (idx + 1024) * 3 / 2; @@ -218,42 +480,161 @@ static int add_object_entry(unsigned char *sha1, unsigned int hash) nr_alloc = needed; } entry = objects + idx; + nr_objects = idx + 1; memset(entry, 0, sizeof(*entry)); memcpy(entry->sha1, sha1, 20); entry->hash = hash; - nr_objects = idx+1; + + if (object_ix_hashsz * 3 <= nr_objects * 4) + rehash_objects(); + else { + ix = locate_object_entry_hash(entry->sha1); + if (0 <= ix) + die("internal error in object hashing."); + object_ix[-1 - ix] = idx + 1; + } + + already_added: + if (exclude) + entry->preferred_base = 1; + else { + if (found_pack) { + entry->in_pack = found_pack; + entry->in_pack_offset = found_offset; + } + } return 1; } +static void add_pbase_tree(struct tree_desc *tree) +{ + while (tree->size) { + const unsigned char *sha1; + const char *name; + unsigned mode; + unsigned long size; + char type[20]; + + sha1 = tree_entry_extract(tree, &name, &mode); + update_tree_entry(tree); + if (!has_sha1_file(sha1)) + continue; + if (sha1_object_info(sha1, type, &size)) + continue; + add_object_entry(sha1, name, 1); + if (!strcmp(type, "tree")) { + struct tree_desc sub; + void *elem; + elem = read_sha1_file(sha1, type, &sub.size); + sub.buf = elem; + if (sub.buf) { + add_pbase_tree(&sub); + free(elem); + } + } + } +} + +static void add_preferred_base(unsigned char *sha1) +{ + struct tree_desc tree; + void *elem; + elem = read_object_with_reference(sha1, "tree", &tree.size, NULL); + tree.buf = elem; + if (!tree.buf) + return; + add_object_entry(sha1, "", 1); + add_pbase_tree(&tree); + free(elem); +} + static void check_object(struct object_entry *entry) { char type[20]; - if (!sha1_object_info(entry->sha1, type, &entry->size)) { - if (!strcmp(type, "commit")) { - entry->type = OBJ_COMMIT; - } else if (!strcmp(type, "tree")) { - entry->type = OBJ_TREE; - } else if (!strcmp(type, "blob")) { - entry->type = OBJ_BLOB; - } else if (!strcmp(type, "tag")) { - entry->type = OBJ_TAG; - } else - die("unable to pack object %s of type %s", - sha1_to_hex(entry->sha1), type); + if (entry->in_pack && !entry->preferred_base) { + unsigned char base[20]; + unsigned long size; + struct object_entry *base_entry; + + /* We want in_pack_type even if we do not reuse delta. + * There is no point not reusing non-delta representations. + */ + check_reuse_pack_delta(entry->in_pack, + entry->in_pack_offset, + base, &size, + &entry->in_pack_type); + + /* Check if it is delta, and the base is also an object + * we are going to pack. If so we will reuse the existing + * delta. + */ + if (!no_reuse_delta && + entry->in_pack_type == OBJ_DELTA && + (base_entry = locate_object_entry(base)) && + (!base_entry->preferred_base)) { + + /* Depth value does not matter - find_deltas() + * will never consider reused delta as the + * base object to deltify other objects + * against, in order to avoid circular deltas. + */ + + /* uncompressed size of the delta data */ + entry->size = entry->delta_size = size; + entry->delta = base_entry; + entry->type = OBJ_DELTA; + + entry->delta_sibling = base_entry->delta_child; + base_entry->delta_child = entry; + + return; + } + /* Otherwise we would do the usual */ } - else + + if (sha1_object_info(entry->sha1, type, &entry->size)) die("unable to get type of object %s", sha1_to_hex(entry->sha1)); + + if (!strcmp(type, "commit")) { + entry->type = OBJ_COMMIT; + } else if (!strcmp(type, "tree")) { + entry->type = OBJ_TREE; + } else if (!strcmp(type, "blob")) { + entry->type = OBJ_BLOB; + } else if (!strcmp(type, "tag")) { + entry->type = OBJ_TAG; + } else + die("unable to pack object %s of type %s", + sha1_to_hex(entry->sha1), type); +} + +static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) +{ + struct object_entry *child = me->delta_child; + unsigned int m = n; + while (child) { + unsigned int c = check_delta_limit(child, n + 1); + if (m < c) + m = c; + child = child->delta_sibling; + } + return m; } static void get_object_details(void) { int i; - struct object_entry *entry = objects; + struct object_entry *entry; - for (i = 0; i < nr_objects; i++) - check_object(entry++); + prepare_pack_ix(); + for (i = 0, entry = objects; i < nr_objects; i++, entry++) + check_object(entry); + for (i = 0, entry = objects; i < nr_objects; i++, entry++) + if (!entry->delta && entry->delta_child) + entry->delta_limit = + check_delta_limit(entry, 1); } typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *); @@ -284,6 +665,24 @@ static int sha1_sort(const struct object_entry *a, const struct object_entry *b) return memcmp(a->sha1, b->sha1, 20); } +static struct object_entry **create_final_object_list() +{ + struct object_entry **list; + int i, j; + + for (i = nr_result = 0; i < nr_objects; i++) + if (!objects[i].preferred_base) + nr_result++; + list = xmalloc(nr_result * sizeof(struct object_entry *)); + for (i = j = 0; i < nr_objects; i++) { + if (!objects[i].preferred_base) + list[j++] = objects + i; + } + current_sort = sha1_sort; + qsort(list, nr_result, sizeof(struct object_entry *), sort_comparator); + return list; +} + static int type_size_sort(const struct object_entry *a, const struct object_entry *b) { if (a->type < b->type) @@ -294,6 +693,10 @@ static int type_size_sort(const struct object_entry *a, const struct object_entr return -1; if (a->hash > b->hash) return 1; + if (a->preferred_base < b->preferred_base) + return -1; + if (a->preferred_base > b->preferred_base) + return 1; if (a->size < b->size) return -1; if (a->size > b->size) @@ -318,6 +721,8 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de { struct object_entry *cur_entry = cur->entry; struct object_entry *old_entry = old->entry; + int old_preferred = (old_entry->preferred_base || + old_entry->based_on_preferred); unsigned long size, oldsize, delta_size, sizediff; long max_size; void *delta_buf; @@ -326,12 +731,27 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de if (cur_entry->type != old_entry->type) return -1; - size = cur_entry->size; - if (size < 50) + /* We do not compute delta to *create* objects we are not + * going to pack. + */ + if (cur_entry->preferred_base) return -1; + + /* If the current object is at pack edge, take the depth the + * objects that depend on the current object into account -- + * otherwise they would become too deep. + */ + if (cur_entry->delta_child) { + if (max_depth <= cur_entry->delta_limit) + return 0; + max_depth -= cur_entry->delta_limit; + } + + size = cur_entry->size; oldsize = old_entry->size; sizediff = oldsize > size ? oldsize - size : size - oldsize; - if (sizediff > size / 8) + + if (size < 50) return -1; if (old_entry->depth >= max_depth) return 0; @@ -344,8 +764,27 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de * delete). */ max_size = size / 2 - 20; - if (cur_entry->delta) - max_size = cur_entry->delta_size-1; + if (cur_entry->delta) { + if (cur_entry->based_on_preferred) { + if (old_preferred) + max_size = cur_entry->delta_size-1; + else + /* trying with non-preferred one when we + * already have a delta based on preferred + * one is pointless. + */ + return 0; + } + else if (!old_preferred) + max_size = cur_entry->delta_size-1; + else + /* otherwise... even if delta with a + * preferred one produces a bigger result than + * what we currently have, which is based on a + * non-preferred one, it is OK. + */ + ; + } if (sizediff >= max_size) return -1; delta_buf = diff_delta(old->data, oldsize, @@ -355,6 +794,7 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de cur_entry->delta = old_entry; cur_entry->delta_size = delta_size; cur_entry->depth = old_entry->depth + 1; + cur_entry->based_on_preferred = old_preferred; free(delta_buf); return 0; } @@ -382,11 +822,19 @@ static void find_deltas(struct object_entry **list, int window, int depth) eye_candy -= nr_objects / 20; fputc('.', stderr); } + + if (entry->delta) + /* This happens if we decided to reuse existing + * delta from a pack. "!no_reuse_delta &&" is implied. + */ + continue; + free(n->data); n->entry = entry; n->data = read_sha1_file(entry->sha1, type, &size); if (size != entry->size) die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size); + j = window; while (--j > 0) { unsigned int other_idx = idx + j; @@ -411,10 +859,12 @@ static void find_deltas(struct object_entry **list, int window, int depth) static void prepare_pack(int window, int depth) { + if (progress) + fprintf(stderr, "Packing %d objects", nr_result); get_object_details(); - if (progress) - fprintf(stderr, "Packing %d objects", nr_objects); + fputc('.', stderr); + sorted_by_type = create_sorted_list(type_size_sort); if (window && depth) find_deltas(sorted_by_type, window+1, depth); @@ -443,8 +893,9 @@ static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) } } - fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects, - sha1_to_hex(sha1)); + if (progress) + fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects, + sha1_to_hex(sha1)); if (pack_to_stdout) { if (copy_fd(ifd, 1)) @@ -524,6 +975,10 @@ int main(int argc, char **argv) progress = 0; continue; } + if (!strcmp("--no-reuse-delta", arg)) { + no_reuse_delta = 1; + continue; + } if (!strcmp("--stdout", arg)) { pack_to_stdout = 1; continue; @@ -544,8 +999,6 @@ int main(int argc, char **argv) gettimeofday(&prev_tv, NULL); } while (fgets(line, sizeof(line), stdin) != NULL) { - unsigned int hash; - char *p; unsigned char sha1[20]; if (progress && (eye_candy <= nr_objects)) { @@ -564,31 +1017,32 @@ int main(int argc, char **argv) } eye_candy += eye_candy_incr; } + if (line[0] == '-') { + if (get_sha1_hex(line+1, sha1)) + die("expected edge sha1, got garbage:\n %s", + line+1); + add_preferred_base(sha1); + continue; + } if (get_sha1_hex(line, sha1)) die("expected sha1, got garbage:\n %s", line); - hash = 0; - p = line+40; - while (*p) { - unsigned char c = *p++; - if (isspace(c)) - continue; - hash = hash * 11 + c; - } - add_object_entry(sha1, hash); + add_object_entry(sha1, line+40, 0); } if (progress) fprintf(stderr, "Done counting %d objects.\n", nr_objects); if (non_empty && !nr_objects) return 0; - sorted_by_sha = create_sorted_list(sha1_sort); + sorted_by_sha = create_final_object_list(); SHA1_Init(&ctx); list = sorted_by_sha; - for (i = 0; i < nr_objects; i++) { + for (i = 0; i < nr_result; i++) { struct object_entry *entry = *list++; SHA1_Update(&ctx, entry->sha1, 20); } SHA1_Final(object_list_sha1, &ctx); + if (progress && (nr_objects != nr_result)) + fprintf(stderr, "Result has %d objects.\n", nr_result); if (reuse_cached_pack(object_list_sha1, pack_to_stdout)) ; @@ -599,5 +1053,8 @@ int main(int argc, char **argv) puts(sha1_to_hex(object_list_sha1)); } } + if (progress) + fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n", + nr_result, written, written_delta, reused, reused_delta); return 0; } @@ -29,5 +29,7 @@ struct pack_header { }; extern int verify_pack(struct packed_git *, int); - +extern int check_reuse_pack_delta(struct packed_git *, unsigned long, + unsigned char *, unsigned long *, + enum object_type *); #endif diff --git a/read-cache.c b/read-cache.c index c5474d4975..f97f92d90a 100644 --- a/read-cache.c +++ b/read-cache.c @@ -27,6 +27,9 @@ void fill_stat_cache_info(struct cache_entry *ce, struct stat *st) ce->ce_uid = htonl(st->st_uid); ce->ce_gid = htonl(st->st_gid); ce->ce_size = htonl(st->st_size); + + if (assume_unchanged) + ce->ce_flags |= htons(CE_VALID); } static int ce_compare_data(struct cache_entry *ce, struct stat *st) @@ -146,9 +149,18 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) return changed; } -int ce_match_stat(struct cache_entry *ce, struct stat *st) +int ce_match_stat(struct cache_entry *ce, struct stat *st, int ignore_valid) { - unsigned int changed = ce_match_stat_basic(ce, st); + unsigned int changed; + + /* + * If it's marked as always valid in the index, it's + * valid whatever the checked-out copy says. + */ + if (!ignore_valid && (ce->ce_flags & htons(CE_VALID))) + return 0; + + changed = ce_match_stat_basic(ce, st); /* * Within 1 second of this sequence: @@ -164,7 +176,7 @@ int ce_match_stat(struct cache_entry *ce, struct stat *st) * effectively mean we can make at most one commit per second, * which is not acceptable. Instead, we check cache entries * whose mtime are the same as the index file timestamp more - * careful than others. + * carefully than others. */ if (!changed && index_file_timestamp && @@ -174,10 +186,10 @@ int ce_match_stat(struct cache_entry *ce, struct stat *st) return changed; } -int ce_modified(struct cache_entry *ce, struct stat *st) +int ce_modified(struct cache_entry *ce, struct stat *st, int really) { int changed, changed_fs; - changed = ce_match_stat(ce, st); + changed = ce_match_stat(ce, st, really); if (!changed) return 0; /* @@ -233,6 +245,11 @@ int cache_name_compare(const char *name1, int flags1, const char *name2, int fla return -1; if (len1 > len2) return 1; + + /* Compare stages */ + flags1 &= CE_STAGEMASK; + flags2 &= CE_STAGEMASK; + if (flags1 < flags2) return -1; if (flags1 > flags2) @@ -430,6 +447,7 @@ int add_cache_entry(struct cache_entry *ce, int option) int ok_to_add = option & ADD_CACHE_OK_TO_ADD; int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE; int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK; + pos = cache_name_pos(ce->name, ntohs(ce->ce_flags)); /* existing match? Just replace it. */ diff --git a/read-tree.c b/read-tree.c index 5580f15ba2..52f06e312a 100644 --- a/read-tree.c +++ b/read-tree.c @@ -349,7 +349,7 @@ static void verify_uptodate(struct cache_entry *ce) return; if (!lstat(ce->name, &st)) { - unsigned changed = ce_match_stat(ce, &st); + unsigned changed = ce_match_stat(ce, &st, 1); if (!changed) return; errno = 0; diff --git a/rev-list.c b/rev-list.c index f2d1105cae..15894005c5 100644 --- a/rev-list.c +++ b/rev-list.c @@ -30,7 +30,7 @@ static const char rev_list_usage[] = " --date-order\n" " formatting output:\n" " --parents\n" -" --objects\n" +" --objects | --objects-edge\n" " --unpacked\n" " --header | --pretty\n" " --abbrev=nr | --no-abbrev\n" @@ -44,6 +44,7 @@ static int bisect_list = 0; static int tag_objects = 0; static int tree_objects = 0; static int blob_objects = 0; +static int edge_hint = 0; static int verbose_header = 0; static int abbrev = DEFAULT_ABBREV; static int show_parents = 0; @@ -255,8 +256,8 @@ static void show_commit_list(struct commit_list *list) die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name); } while (objects) { - /* An object with name "foo\n0000000000000000000000000000000000000000" - * can be used confuse downstream git-pack-objects very badly. + /* An object with name "foo\n0000000..." can be used to + * confuse downstream git-pack-objects very badly. */ const char *ep = strchr(objects->name, '\n'); if (ep) { @@ -430,16 +431,30 @@ static struct commit_list *find_bisection(struct commit_list *list) return best; } +static void mark_edge_parents_uninteresting(struct commit *commit) +{ + struct commit_list *parents; + + for (parents = commit->parents; parents; parents = parents->next) { + struct commit *parent = parents->item; + if (!(parent->object.flags & UNINTERESTING)) + continue; + mark_tree_uninteresting(parent->tree); + if (edge_hint) + printf("-%s\n", sha1_to_hex(parent->object.sha1)); + } +} + static void mark_edges_uninteresting(struct commit_list *list) { for ( ; list; list = list->next) { - struct commit_list *parents = list->item->parents; + struct commit *commit = list->item; - for ( ; parents; parents = parents->next) { - struct commit *commit = parents->item; - if (commit->object.flags & UNINTERESTING) - mark_tree_uninteresting(commit->tree); + if (commit->object.flags & UNINTERESTING) { + mark_tree_uninteresting(commit->tree); + continue; } + mark_edge_parents_uninteresting(commit); } } @@ -843,6 +858,13 @@ int main(int argc, const char **argv) blob_objects = 1; continue; } + if (!strcmp(arg, "--objects-edge")) { + tag_objects = 1; + tree_objects = 1; + blob_objects = 1; + edge_hint = 1; + continue; + } if (!strcmp(arg, "--unpacked")) { unpacked = 1; limited = 1; diff --git a/rev-parse.c b/rev-parse.c index a5fb93c3ca..610eacb35a 100644 --- a/rev-parse.c +++ b/rev-parse.c @@ -43,6 +43,7 @@ static int is_rev_argument(const char *arg) "--min-age=", "--no-merges", "--objects", + "--objects-edge", "--parents", "--pretty", "--show-breaks", diff --git a/send-pack.c b/send-pack.c index 990be3f1a3..f558386143 100644 --- a/send-pack.c +++ b/send-pack.c @@ -12,6 +12,7 @@ static const char *exec = "git-receive-pack"; static int verbose = 0; static int send_all = 0; static int force_update = 0; +static int use_thin_pack = 0; static int is_zero_sha1(const unsigned char *sha1) { @@ -37,26 +38,47 @@ static void exec_pack_objects(void) static void exec_rev_list(struct ref *refs) { + struct ref *ref; static char *args[1000]; - int i = 0; + int i = 0, j; args[i++] = "rev-list"; /* 0 */ - args[i++] = "--objects"; /* 1 */ - while (refs) { - char *buf = malloc(100); - if (i > 900) + if (use_thin_pack) /* 1 */ + args[i++] = "--objects-edge"; + else + args[i++] = "--objects"; + + /* First send the ones we care about most */ + for (ref = refs; ref; ref = ref->next) { + if (900 < i) die("git-rev-list environment overflow"); - if (!is_zero_sha1(refs->old_sha1) && - has_sha1_file(refs->old_sha1)) { + if (!is_zero_sha1(ref->new_sha1)) { + char *buf = malloc(100); args[i++] = buf; - snprintf(buf, 50, "^%s", sha1_to_hex(refs->old_sha1)); + snprintf(buf, 50, "%s", sha1_to_hex(ref->new_sha1)); buf += 50; + if (!is_zero_sha1(ref->old_sha1) && + has_sha1_file(ref->old_sha1)) { + args[i++] = buf; + snprintf(buf, 50, "^%s", + sha1_to_hex(ref->old_sha1)); + } } - if (!is_zero_sha1(refs->new_sha1)) { + } + + /* Then a handful of the remainder + * NEEDSWORK: we would be better off if used the newer ones first. + */ + for (ref = refs, j = i + 16; + i < 900 && i < j && ref; + ref = ref->next) { + if (is_zero_sha1(ref->new_sha1) && + !is_zero_sha1(ref->old_sha1) && + has_sha1_file(ref->old_sha1)) { + char *buf = malloc(42); args[i++] = buf; - snprintf(buf, 50, "%s", sha1_to_hex(refs->new_sha1)); + snprintf(buf, 42, "^%s", sha1_to_hex(ref->old_sha1)); } - refs = refs->next; } args[i] = NULL; execv_git_cmd(args); @@ -361,6 +383,10 @@ int main(int argc, char **argv) verbose = 1; continue; } + if (!strcmp(arg, "--thin")) { + use_thin_pack = 1; + continue; + } usage(send_pack_usage); } if (!dest) { diff --git a/sha1_file.c b/sha1_file.c index 1d799f793a..9cab99ae7c 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -828,6 +828,25 @@ static unsigned long unpack_object_header(struct packed_git *p, unsigned long of return offset; } +int check_reuse_pack_delta(struct packed_git *p, unsigned long offset, + unsigned char *base, unsigned long *sizep, + enum object_type *kindp) +{ + unsigned long ptr; + int status = -1; + + use_packed_git(p); + ptr = offset; + ptr = unpack_object_header(p, ptr, kindp, sizep); + if (*kindp != OBJ_DELTA) + goto done; + memcpy(base, p->pack_base + ptr, 20); + status = 0; + done: + unuse_packed_git(p); + return status; +} + void packed_object_info_detail(struct pack_entry *e, char *type, unsigned long *size, diff --git a/t/Makefile b/t/Makefile index 5c5a620126..fe65f53c5f 100644 --- a/t/Makefile +++ b/t/Makefile @@ -8,17 +8,18 @@ SHELL_PATH ?= $(SHELL) TAR ?= $(TAR) # Shell quote; -# Result of this needs to be placed inside '' -shq = $(subst ','\'',$(1)) -# This has surrounding '' -shellquote = '$(call shq,$(1))' +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) T = $(wildcard t[0-9][0-9][0-9][0-9]-*.sh) +ifdef NO_PYTHON + GIT_TEST_OPTS += --no-python +endif + all: $(T) clean $(T): - @echo "*** $@ ***"; $(call shellquote,$(SHELL_PATH)) $@ $(GIT_TEST_OPTS) + @echo "*** $@ ***"; '$(SHELL_PATH_SQ)' $@ $(GIT_TEST_OPTS) clean: rm -fr trash diff --git a/t/t0000-basic.sh b/t/t0000-basic.sh index c339a366f4..6729a18266 100755 --- a/t/t0000-basic.sh +++ b/t/t0000-basic.sh @@ -42,7 +42,7 @@ fi . ./test-lib.sh -"$PYTHON" -c 'import subprocess' || { +test "$no_python" || "$PYTHON" -c 'import subprocess' || { echo >&2 'Your python seem to lack "subprocess" module. Please check INSTALL document.' exit 1 diff --git a/t/t3020-ls-files-error-unmatch.sh b/t/t3020-ls-files-error-unmatch.sh new file mode 100755 index 0000000000..d55559e553 --- /dev/null +++ b/t/t3020-ls-files-error-unmatch.sh @@ -0,0 +1,27 @@ +#!/bin/sh +# +# Copyright (c) 2006 Carl D. Worth +# + +test_description='git-ls-files test for --error-unmatch option + +This test runs git-ls-files --error-unmatch to ensure it correctly +returns an error when a non-existent path is provided on the command +line. +' +. ./test-lib.sh + +touch foo bar +git-update-index --add foo bar +git-commit -m "add foo bar" + +test_expect_failure \ + 'git-ls-files --error-unmatch should fail with unmatched path.' \ + 'git-ls-files --error-unmatch foo bar-does-not-match' + +test_expect_success \ + 'git-ls-files --error-unmatch should succeed eith matched paths.' \ + 'git-ls-files --error-unmatch foo bar' + +test_done +1 diff --git a/t/t3700-add.sh b/t/t3700-add.sh new file mode 100755 index 0000000000..6cd05c3d90 --- /dev/null +++ b/t/t3700-add.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# +# Copyright (c) 2006 Carl D. Worth +# + +test_description='Test of git-add, including the -- option.' + +. ./test-lib.sh + +test_expect_success \ + 'Test of git-add' \ + 'touch foo && git-add foo' + +test_expect_success \ + 'Post-check that foo is in the index' \ + 'git-ls-files foo | grep foo' + +test_expect_success \ + 'Test that "git-add -- -q" works' \ + 'touch -- -q && git-add -- -q' + +test_done diff --git a/t/t5600-clone-fail-cleanup.sh b/t/t5600-clone-fail-cleanup.sh new file mode 100755 index 0000000000..0c6a363be9 --- /dev/null +++ b/t/t5600-clone-fail-cleanup.sh @@ -0,0 +1,36 @@ +#!/bin/sh +# +# Copyright (C) 2006 Carl D. Worth <cworth@cworth.org> +# + +test_description='test git-clone to cleanup after failure + +This test covers the fact that if git-clone fails, it should remove +the directory it created, to avoid the user having to manually +remove the directory before attempting a clone again.' + +. ./test-lib.sh + +test_expect_failure \ + 'clone of non-existent source should fail' \ + 'git-clone foo bar' + +test_expect_failure \ + 'failed clone should not leave a directory' \ + 'cd bar' + +# Need a repo to clone +test_create_repo foo + +# clone doesn't like it if there is no HEAD. Is that a bug? +(cd foo && touch file && git add file && git commit -m 'add file' >/dev/null 2>&1) + +test_expect_success \ + 'clone should work now that source exists' \ + 'git-clone foo bar' + +test_expect_success \ + 'successfull clone must leave the directory' \ + 'cd bar' + +test_done diff --git a/t/t6021-merge-criss-cross.sh b/t/t6021-merge-criss-cross.sh index e8606c751d..262381379f 100755 --- a/t/t6021-merge-criss-cross.sh +++ b/t/t6021-merge-criss-cross.sh @@ -10,6 +10,12 @@ test_description='Test criss-cross merge' . ./test-lib.sh +if test "$no_python"; then + echo "Skipping: no python => no recursive merge" + test_done + exit 0 +fi + test_expect_success 'prepare repository' \ 'echo "1 2 diff --git a/t/t6022-merge-rename.sh b/t/t6022-merge-rename.sh index 1292cafd7f..a2d24b5ca9 100755 --- a/t/t6022-merge-rename.sh +++ b/t/t6022-merge-rename.sh @@ -3,6 +3,12 @@ test_description='Merge-recursive merging renames' . ./test-lib.sh +if test "$no_python"; then + echo "Skipping: no python => no recursive merge" + test_done + exit 0 +fi + test_expect_success setup \ ' cat >A <<\EOF && diff --git a/t/test-lib.sh b/t/test-lib.sh index 66f62b9c6f..05f6e79560 100755 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -63,6 +63,8 @@ do exit 0 ;; -v|--v|--ve|--ver|--verb|--verbo|--verbos|--verbose) verbose=t; shift ;; + --no-python) + no_python=t; shift ;; *) break ;; esac diff --git a/update-index.c b/update-index.c index afec98dd48..ce1db38d16 100644 --- a/update-index.c +++ b/update-index.c @@ -23,6 +23,10 @@ static int quiet; /* --refresh needing update is not error */ static int info_only; static int force_remove; static int verbose; +static int mark_valid_only = 0; +#define MARK_VALID 1 +#define UNMARK_VALID 2 + /* Three functions to allow overloaded pointer return; see linux/err.h */ static inline void *ERR_PTR(long error) @@ -53,6 +57,25 @@ static void report(const char *fmt, ...) va_end(vp); } +static int mark_valid(const char *path) +{ + int namelen = strlen(path); + int pos = cache_name_pos(path, namelen); + if (0 <= pos) { + switch (mark_valid_only) { + case MARK_VALID: + active_cache[pos]->ce_flags |= htons(CE_VALID); + break; + case UNMARK_VALID: + active_cache[pos]->ce_flags &= ~htons(CE_VALID); + break; + } + active_cache_changed = 1; + return 0; + } + return -1; +} + static int add_file_to_cache(const char *path) { int size, namelen, option, status; @@ -94,6 +117,7 @@ static int add_file_to_cache(const char *path) ce = xmalloc(size); memset(ce, 0, size); memcpy(ce->name, path, namelen); + ce->ce_flags = htons(namelen); fill_stat_cache_info(ce, &st); ce->ce_mode = create_ce_mode(st.st_mode); @@ -105,7 +129,6 @@ static int add_file_to_cache(const char *path) if (0 <= pos) ce->ce_mode = active_cache[pos]->ce_mode; } - ce->ce_flags = htons(namelen); if (index_path(ce->sha1, path, &st, !info_only)) return -1; @@ -128,7 +151,7 @@ static int add_file_to_cache(const char *path) * For example, you'd want to do this after doing a "git-read-tree", * to link up the stat cache details with the proper files. */ -static struct cache_entry *refresh_entry(struct cache_entry *ce) +static struct cache_entry *refresh_entry(struct cache_entry *ce, int really) { struct stat st; struct cache_entry *updated; @@ -137,21 +160,36 @@ static struct cache_entry *refresh_entry(struct cache_entry *ce) if (lstat(ce->name, &st) < 0) return ERR_PTR(-errno); - changed = ce_match_stat(ce, &st); - if (!changed) - return NULL; + changed = ce_match_stat(ce, &st, really); + if (!changed) { + if (really && assume_unchanged && + !(ce->ce_flags & htons(CE_VALID))) + ; /* mark this one VALID again */ + else + return NULL; + } - if (ce_modified(ce, &st)) + if (ce_modified(ce, &st, really)) return ERR_PTR(-EINVAL); size = ce_size(ce); updated = xmalloc(size); memcpy(updated, ce, size); fill_stat_cache_info(updated, &st); + + /* In this case, if really is not set, we should leave + * CE_VALID bit alone. Otherwise, paths marked with + * --no-assume-unchanged (i.e. things to be edited) will + * reacquire CE_VALID bit automatically, which is not + * really what we want. + */ + if (!really && assume_unchanged && !(ce->ce_flags & htons(CE_VALID))) + updated->ce_flags &= ~htons(CE_VALID); + return updated; } -static int refresh_cache(void) +static int refresh_cache(int really) { int i; int has_errors = 0; @@ -171,12 +209,19 @@ static int refresh_cache(void) continue; } - new = refresh_entry(ce); + new = refresh_entry(ce, really); if (!new) continue; if (IS_ERR(new)) { if (not_new && PTR_ERR(new) == -ENOENT) continue; + if (really && PTR_ERR(new) == -EINVAL) { + /* If we are doing --really-refresh that + * means the index is not valid anymore. + */ + ce->ce_flags &= ~htons(CE_VALID); + active_cache_changed = 1; + } if (quiet) continue; printf("%s: needs update\n", ce->name); @@ -274,6 +319,8 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, memcpy(ce->name, path, len); ce->ce_flags = create_ce_flags(len, stage); ce->ce_mode = create_ce_mode(mode); + if (assume_unchanged) + ce->ce_flags |= htons(CE_VALID); option = allow_add ? ADD_CACHE_OK_TO_ADD : 0; option |= allow_replace ? ADD_CACHE_OK_TO_REPLACE : 0; if (add_cache_entry(ce, option)) @@ -317,6 +364,12 @@ static void update_one(const char *path, const char *prefix, int prefix_length) fprintf(stderr, "Ignoring path %s\n", path); return; } + if (mark_valid_only) { + if (mark_valid(p)) + die("Unable to mark file %s", path); + return; + } + if (force_remove) { if (remove_file_from_cache(p)) die("git-update-index: unable to remove %s", path); @@ -467,7 +520,11 @@ int main(int argc, const char **argv) continue; } if (!strcmp(path, "--refresh")) { - has_errors |= refresh_cache(); + has_errors |= refresh_cache(0); + continue; + } + if (!strcmp(path, "--really-refresh")) { + has_errors |= refresh_cache(1); continue; } if (!strcmp(path, "--cacheinfo")) { @@ -493,6 +550,14 @@ int main(int argc, const char **argv) die("git-update-index: %s cannot chmod %s", path, argv[i]); continue; } + if (!strcmp(path, "--assume-unchanged")) { + mark_valid_only = MARK_VALID; + continue; + } + if (!strcmp(path, "--no-assume-unchanged")) { + mark_valid_only = UNMARK_VALID; + continue; + } if (!strcmp(path, "--info-only")) { info_only = 1; continue; diff --git a/upload-pack.c b/upload-pack.c index 3606529f61..635abb371d 100644 --- a/upload-pack.c +++ b/upload-pack.c @@ -14,6 +14,7 @@ static const char upload_pack_usage[] = "git-upload-pack [--strict] [--timeout=n #define MAX_HAS 256 #define MAX_NEEDS 256 static int nr_has = 0, nr_needs = 0, multi_ack = 0, nr_our_refs = 0; +static int use_thin_pack = 0; static unsigned char has_sha1[MAX_HAS][20]; static unsigned char needs_sha1[MAX_NEEDS][20]; static unsigned int timeout = 0; @@ -49,8 +50,10 @@ static void create_pack_file(void) char *buf; char **p; - if (create_full_pack) + if (create_full_pack) { args = 10; + use_thin_pack = 0; /* no point doing it */ + } else args = nr_has + nr_needs + 5; argv = xmalloc(args * sizeof(char *)); @@ -62,7 +65,7 @@ static void create_pack_file(void) close(fd[0]); close(fd[1]); *p++ = "rev-list"; - *p++ = "--objects"; + *p++ = use_thin_pack ? "--objects-edge" : "--objects"; if (create_full_pack || MAX_NEEDS <= nr_needs) *p++ = "--all"; else { @@ -192,6 +195,8 @@ static int receive_needs(void) "expected to get sha, not '%s'", line); if (strstr(line+45, "multi_ack")) multi_ack = 1; + if (strstr(line+45, "thin-pack")) + use_thin_pack = 1; /* We have sent all our refs already, and the other end * should have chosen out of them; otherwise they are @@ -213,7 +218,7 @@ static int receive_needs(void) static int send_ref(const char *refname, const unsigned char *sha1) { - static char *capabilities = "multi_ack"; + static char *capabilities = "multi_ack thin-pack"; struct object *o = parse_object(sha1); if (!o) @@ -12,7 +12,7 @@ static const char var_usage[] = "git-var [-l | <variable>]"; struct git_var { const char *name; - const char *(*read)(void); + const char *(*read)(int); }; static struct git_var git_vars[] = { { "GIT_COMMITTER_IDENT", git_committer_info }, @@ -24,7 +24,7 @@ static void list_vars(void) { struct git_var *ptr; for(ptr = git_vars; ptr->read; ptr++) { - printf("%s=%s\n", ptr->name, ptr->read()); + printf("%s=%s\n", ptr->name, ptr->read(0)); } } @@ -35,7 +35,7 @@ static const char *read_var(const char *var) val = NULL; for(ptr = git_vars; ptr->read; ptr++) { if (strcmp(var, ptr->name) == 0) { - val = ptr->read(); + val = ptr->read(1); break; } } diff --git a/write-tree.c b/write-tree.c index f866059f24..addb5de3b6 100644 --- a/write-tree.c +++ b/write-tree.c @@ -111,7 +111,7 @@ int main(int argc, char **argv) funny = 0; for (i = 0; i < entries; i++) { struct cache_entry *ce = active_cache[i]; - if (ntohs(ce->ce_flags) & ~CE_NAMEMASK) { + if (ce_stage(ce)) { if (10 < ++funny) { fprintf(stderr, "...\n"); break; |