diff options
50 files changed, 5431 insertions, 751 deletions
diff --git a/.gitignore b/.gitignore index d7e8d2ac0d..5be239a4aa 100644 --- a/.gitignore +++ b/.gitignore @@ -2,6 +2,7 @@ GIT-VERSION-FILE git git-add git-am +git-annotate git-apply git-applymbox git-applypatch @@ -22,6 +23,7 @@ git-convert-objects git-count-objects git-cvsexportcommit git-cvsimport +git-cvsserver git-daemon git-diff git-diff-files @@ -53,6 +55,7 @@ git-mailsplit git-merge git-merge-base git-merge-index +git-merge-tree git-merge-octopus git-merge-one-file git-merge-ours @@ -60,6 +63,7 @@ git-merge-recursive git-merge-resolve git-merge-stupid git-mktag +git-mktree git-name-rev git-mv git-pack-redundant @@ -84,6 +88,7 @@ git-resolve git-rev-list git-rev-parse git-revert +git-rm git-send-email git-send-pack git-sh-setup diff --git a/Documentation/git-cvsserver.txt b/Documentation/git-cvsserver.txt new file mode 100644 index 0000000000..88f07ff15d --- /dev/null +++ b/Documentation/git-cvsserver.txt @@ -0,0 +1,89 @@ +git-cvsserver(1) +================ + +NAME +---- +git-cvsserver - A CVS server emulator for git + + +SYNOPSIS +-------- +[verse] +export CVS_SERVER=git-cvsserver +'cvs' -d :ext:user@server/path/repo.git co <HEAD_name> + + +DESCRIPTION +----------- + +This application is a CVS emulation layer for git. + +It is highly functional. However, not all methods are implemented, +and for those methods that are implemented, +not all switches are implemented. + +Testing has been done using both the CLI CVS client, and the Eclipse CVS +plugin. Most functionality works fine with both of these clients. + +LIMITATIONS +----------- +Currently gitcvs only works over ssh connections. + + +INSTALLATION +------------ +1. Put server.pl somewhere useful on the same machine that is hosting your git repos + +2. For each repo that you want accessible from CVS you need to edit config in + the repo and add the following section. + + [gitcvs] + enabled=1 + logfile=/path/to/logfile + + n.b. you need to ensure each user that is going to invoke server.pl has + write access to the log file. + +5. On each client machine you need to set the following variables. + CVSROOT should be set as per normal, but the directory should point at the + appropriate git repo. + CVS_SERVER should be set to the server.pl script that has been put on the + remote machine. + +6. Clients should now be able to check out modules (where modules are the names + of branches in git). + $ cvs co -d mylocaldir master + +Operations supported +-------------------- + +All the operations required for normal use are supported, including +checkout, diff, status, update, log, add, remove, commit. +Legacy monitoring operations are not supported (edit, watch and related). +Exports and tagging (tags and branches) are not supported at this stage. + +The server will set the -k mode to binary when relevant. In proper GIT +tradition, the contents of the files are always respected. +No keyword expansion or newline munging is supported. + +Dependencies +------------ + +git-cvsserver depends on DBD::SQLite. + +Copyright and Authors +--------------------- + +This program is copyright The Open University UK - 2006. + +Authors: Martyn Smith <martyn@catalyst.net.nz> + Martin Langhoff <martin@catalyst.net.nz> + with ideas and patches from participants of the git-list <git@vger.kernel.org>. + +Documentation +-------------- +Documentation by Martyn Smith <martyn@catalyst.net.nz> and Martin Langhoff <martin@catalyst.net.nz>Matthias Urlichs <smurf@smurf.noris.de>. + +GIT +--- +Part of the gitlink:git[7] suite diff --git a/Documentation/git-rm.txt b/Documentation/git-rm.txt new file mode 100644 index 0000000000..401bfb2d9c --- /dev/null +++ b/Documentation/git-rm.txt @@ -0,0 +1,89 @@ +git-rm(1) +========= + +NAME +---- +git-rm - Remove files from the working tree and from the index. + +SYNOPSIS +-------- +'git-rm' [-f] [-n] [-v] [--] <file>... + +DESCRIPTION +----------- +A convenience wrapper for git-update-index --remove. For those coming +from cvs, git-rm provides an operation similar to "cvs rm" or "cvs +remove". + + +OPTIONS +------- +<file>...:: + Files to remove from the index and optionally, from the + working tree as well. + +-f:: + Remove files from the working tree as well as from the index. + +-n:: + Don't actually remove the file(s), just show if they exist in + the index. + +-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 +---------- + +The list of <file> given to the command is fed to `git-ls-files` +command to list files that are registered in the index and +are not ignored/excluded by `$GIT_DIR/info/exclude` file or +`.gitignore` file in each directory. This means two things: + +. You can put the name of a directory on the command line, and the + command will remove all files in it and its subdirectories (the + directories themselves are never removed from the working tree); + +. Giving the name of a file that is not in the index does not + remove that file. + + +EXAMPLES +-------- +git-rm Documentation/\\*.txt:: + + Removes all `\*.txt` files from the index that are under the + `Documentation` directory and any of its subdirectories. The + files are not removed from the working tree. ++ +Note that the asterisk `\*` is quoted from the shell in this +example; this lets the command include the files from +subdirectories of `Documentation/` directory. + +git-rm -f git-*.sh:: + + Remove all git-*.sh scripts that are in the index. The files + are removed from the index, and (because of the -f option), + from the working tree as well. Because this example lets the + shell expand the asterisk (i.e. you are listing the files + explicitly), it does not remove `subdir/git-foo.sh`. + + +Author +------ +Written by Linus Torvalds <torvalds@osdl.org> + +Documentation +-------------- +Documentation by Junio C Hamano and the git-list <git@vger.kernel.org>. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/git-svnimport.txt b/Documentation/git-svnimport.txt index 5c543d5d1b..a1588138ea 100644 --- a/Documentation/git-svnimport.txt +++ b/Documentation/git-svnimport.txt @@ -10,10 +10,11 @@ git-svnimport - Import a SVN repository into git SYNOPSIS -------- 'git-svnimport' [ -o <branch-for-HEAD> ] [ -h ] [ -v ] [ -d | -D ] - [ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev] - [ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ] - [ -s start_chg ] [ -m ] [ -M regex ] - <SVN_repository_URL> [ <path> ] + [ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev] + [ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ] + [ -s start_chg ] [ -m ] [ -r ] [ -M regex ] + [ -I <ignorefile_name> ] [ -A <author_file> ] + <SVN_repository_URL> [ <path> ] DESCRIPTION @@ -65,6 +66,27 @@ When importing incrementally, you might need to edit the .git/svn2git file. Prepend 'rX: ' to commit messages, where X is the imported subversion revision. +-I <ignorefile_name>:: + Import the svn:ignore directory property to files with this + name in each directory. (The Subversion and GIT ignore + syntaxes are similar enough that using the Subversion patterns + directly with "-I .gitignore" will almost always just work.) + +-A <author_file>:: + Read a file with lines on the form + + username = User's Full Name <email@addr.es> + + and use "User's Full Name <email@addr.es>" as the GIT + author and committer for Subversion commits made by + "username". If encountering a commit made by a user not in the + list, abort. + + For convenience, this data is saved to $GIT_DIR/svn-authors + each time the -A option is provided, and read from that same + file each time git-svnimport is run with an existing GIT + repository without -A. + -m:: Attempt to detect merges based on the commit message. This option will enable default regexes that try to capture the name source @@ -120,7 +120,7 @@ SCRIPT_SH = \ git-merge-one-file.sh git-parse-remote.sh \ git-prune.sh git-pull.sh git-push.sh git-rebase.sh \ git-repack.sh git-request-pull.sh git-reset.sh \ - git-resolve.sh git-revert.sh git-sh-setup.sh \ + git-resolve.sh git-revert.sh git-rm.sh git-sh-setup.sh \ git-tag.sh git-verify-tag.sh git-whatchanged.sh \ git-applymbox.sh git-applypatch.sh git-am.sh \ git-merge.sh git-merge-stupid.sh git-merge-octopus.sh \ @@ -130,6 +130,7 @@ SCRIPT_SH = \ SCRIPT_PERL = \ git-archimport.perl git-cvsimport.perl git-relink.perl \ git-shortlog.perl git-fmt-merge-msg.perl git-rerere.perl \ + git-annotate.perl git-cvsserver.perl \ git-svnimport.perl git-mv.perl git-cvsexportcommit.perl SCRIPT_PYTHON = \ @@ -152,8 +153,8 @@ PROGRAMS = \ git-convert-objects$X git-diff-files$X \ git-diff-index$X git-diff-stages$X \ git-diff-tree$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$X \ + git-hash-object$X git-index-pack$X git-init-db$X git-local-fetch$X \ + git-ls-files$X git-ls-tree$X git-mailinfo$X git-merge-base$X \ git-merge-index$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 \ @@ -164,7 +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$X git-merge-tree$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) @@ -191,7 +192,7 @@ LIB_FILE=libgit.a LIB_H = \ blob.h cache.h commit.h count-delta.h csum-file.h delta.h \ diff.h epoch.h object.h pack.h pkt-line.h quote.h refs.h \ - run-command.h strbuf.h tag.h tree.h git-compat-util.h + run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h DIFF_OBJS = \ diff.o diffcore-break.o diffcore-order.o diffcore-pathspec.o \ @@ -204,7 +205,7 @@ LIB_OBJS = \ quote.o read-cache.o refs.o run-command.o \ server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \ tag.o tree.o usage.o config.o environment.o ctype.o copy.o \ - fetch-clone.o \ + fetch-clone.o revision.o \ $(DIFF_OBJS) LIBS = $(LIB_FILE) @@ -34,6 +34,56 @@ static int line_termination = '\n'; static const char apply_usage[] = "git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] <patch>..."; +static enum whitespace_eol { + nowarn_whitespace, + warn_on_whitespace, + error_on_whitespace, + strip_whitespace, +} new_whitespace = warn_on_whitespace; +static int whitespace_error = 0; +static int squelch_whitespace_errors = 5; +static int applied_after_stripping = 0; +static const char *patch_input_file = NULL; + +static void parse_whitespace_option(const char *option) +{ + if (!option) { + new_whitespace = warn_on_whitespace; + return; + } + if (!strcmp(option, "warn")) { + new_whitespace = warn_on_whitespace; + return; + } + if (!strcmp(option, "nowarn")) { + new_whitespace = nowarn_whitespace; + return; + } + if (!strcmp(option, "error")) { + new_whitespace = error_on_whitespace; + return; + } + if (!strcmp(option, "error-all")) { + new_whitespace = error_on_whitespace; + squelch_whitespace_errors = 0; + return; + } + if (!strcmp(option, "strip")) { + new_whitespace = strip_whitespace; + return; + } + die("unrecognized whitespace option '%s'", option); +} + +static void set_default_whitespace_mode(const char *whitespace_option) +{ + if (!whitespace_option && !apply_default_whitespace) { + new_whitespace = (apply + ? warn_on_whitespace + : nowarn_whitespace); + } +} + /* * For "diff-stat" like behaviour, we keep track of the biggest change * we've seen, and the longest filename. That allows us to do simple @@ -815,6 +865,25 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s oldlines--; break; case '+': + /* + * We know len is at least two, since we have a '+' and + * we checked that the last character was a '\n' above. + * That is, an addition of an empty line would check + * the '+' here. Sneaky... + */ + if ((new_whitespace != nowarn_whitespace) && + isspace(line[len-2])) { + whitespace_error++; + if (squelch_whitespace_errors && + squelch_whitespace_errors < + whitespace_error) + ; + else { + fprintf(stderr, "Adds trailing whitespace.\n%s:%d:%.*s\n", + patch_input_file, + linenr, len-2, line+1); + } + } added++; newlines--; break; @@ -1092,6 +1161,28 @@ struct buffer_desc { unsigned long alloc; }; +static int apply_line(char *output, const char *patch, int plen) +{ + /* plen is number of bytes to be copied from patch, + * starting at patch+1 (patch[0] is '+'). Typically + * patch[plen] is '\n'. + */ + int add_nl_to_tail = 0; + if ((new_whitespace == strip_whitespace) && + 1 < plen && isspace(patch[plen-1])) { + if (patch[plen] == '\n') + add_nl_to_tail = 1; + plen--; + while (0 < plen && isspace(patch[plen])) + plen--; + applied_after_stripping++; + } + memcpy(output, patch + 1, plen); + if (add_nl_to_tail) + output[plen++] = '\n'; + return plen; +} + static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag) { char *buf = desc->buffer; @@ -1127,10 +1218,9 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag) break; /* Fall-through for ' ' */ case '+': - if (*patch != '+' || !no_add) { - memcpy(new + newsize, patch + 1, plen); - newsize += plen; - } + if (*patch != '+' || !no_add) + newsize += apply_line(new + newsize, patch, + plen); break; case '@': case '\\': /* Ignore it, we already handled it */ @@ -1699,7 +1789,7 @@ static int use_patch(struct patch *p) return 1; } -static int apply_patch(int fd) +static int apply_patch(int fd, const char *filename) { int newfd; unsigned long offset, size; @@ -1707,6 +1797,7 @@ static int apply_patch(int fd) struct patch *list = NULL, **listp = &list; int skipped_patch = 0; + patch_input_file = filename; if (!buffer) return -1; offset = 0; @@ -1733,6 +1824,9 @@ static int apply_patch(int fd) } newfd = -1; + if (whitespace_error && (new_whitespace == error_on_whitespace)) + apply = 0; + write_index = check_index && apply; if (write_index) newfd = hold_index_file_for_update(&cache_file, get_index_file()); @@ -1769,17 +1863,28 @@ static int apply_patch(int fd) return 0; } +static int git_apply_config(const char *var, const char *value) +{ + if (!strcmp(var, "apply.whitespace")) { + apply_default_whitespace = strdup(value); + return 0; + } + return git_default_config(var, value); +} + + int main(int argc, char **argv) { int i; int read_stdin = 1; + const char *whitespace_option = NULL; for (i = 1; i < argc; i++) { const char *arg = argv[i]; int fd; if (!strcmp(arg, "-")) { - apply_patch(0); + apply_patch(0, "<stdin>"); read_stdin = 0; continue; } @@ -1839,11 +1944,18 @@ int main(int argc, char **argv) line_termination = 0; continue; } + if (!strncmp(arg, "--whitespace=", 13)) { + whitespace_option = arg + 13; + parse_whitespace_option(arg + 13); + continue; + } if (check_index && prefix_length < 0) { prefix = setup_git_directory(); prefix_length = prefix ? strlen(prefix) : 0; - git_config(git_default_config); + git_config(git_apply_config); + if (!whitespace_option && apply_default_whitespace) + parse_whitespace_option(apply_default_whitespace); } if (0 < prefix_length) arg = prefix_filename(prefix, prefix_length, arg); @@ -1852,10 +1964,38 @@ int main(int argc, char **argv) if (fd < 0) usage(apply_usage); read_stdin = 0; - apply_patch(fd); + set_default_whitespace_mode(whitespace_option); + apply_patch(fd, arg); close(fd); } + set_default_whitespace_mode(whitespace_option); if (read_stdin) - apply_patch(0); + apply_patch(0, "<stdin>"); + if (whitespace_error) { + if (squelch_whitespace_errors && + squelch_whitespace_errors < whitespace_error) { + int squelched = + whitespace_error - squelch_whitespace_errors; + fprintf(stderr, "warning: squelched %d whitespace error%s\n", + squelched, + squelched == 1 ? "" : "s"); + } + if (new_whitespace == error_on_whitespace) + die("%d line%s add%s trailing whitespaces.", + whitespace_error, + whitespace_error == 1 ? "" : "s", + whitespace_error == 1 ? "s" : ""); + if (applied_after_stripping) + fprintf(stderr, "warning: %d line%s applied after" + " stripping trailing whitespaces.\n", + applied_after_stripping, + applied_after_stripping == 1 ? "" : "s"); + else if (whitespace_error) + fprintf(stderr, "warning: %d line%s add%s trailing" + " whitespaces.\n", + whitespace_error, + whitespace_error == 1 ? "" : "s", + whitespace_error == 1 ? "s" : ""); + } return 0; } 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; +} @@ -10,7 +10,7 @@ #define deflateBound(c,s) ((s) + (((s) + 7) >> 3) + (((s) + 63) >> 6) + 11) #endif -#if defined(DT_UNKNOWN) && !NO_D_TYPE_IN_DIRENT +#if defined(DT_UNKNOWN) && !defined(NO_D_TYPE_IN_DIRENT) #define DTYPE(de) ((de)->d_type) #else #undef DT_UNKNOWN @@ -161,11 +161,13 @@ extern int hold_index_file_for_update(struct cache_file *, const char *path); extern int commit_index_file(struct cache_file *); extern void rollback_index_file(struct cache_file *); +/* Environment bits from configuration mechanism */ extern int trust_executable_bit; extern int assume_unchanged; extern int only_use_symrefs; extern int diff_rename_limit_default; extern int shared_repository; +extern const char *apply_default_whitespace; #define GIT_REPO_VERSION 0 extern int repository_format_version; diff --git a/combine-diff.c b/combine-diff.c index d812600d11..a23894d869 100644 --- a/combine-diff.c +++ b/combine-diff.c @@ -621,7 +621,8 @@ static void reuse_combine_diff(struct sline *sline, unsigned long cnt, } static int show_patch_diff(struct combine_diff_path *elem, int num_parent, - int dense, const char *header) + int dense, const char *header, + struct diff_options *opt) { unsigned long size, cnt, lno; char *result, *cp, *ep; @@ -631,6 +632,7 @@ static int show_patch_diff(struct combine_diff_path *elem, int num_parent, char ourtmp_buf[TMPPATHLEN]; char *ourtmp = ourtmp_buf; int working_tree_file = !memcmp(elem->sha1, null_sha1, 20); + int abbrev = opt->full_index ? 40 : DEFAULT_ABBREV; /* Read the result of merge first */ if (!working_tree_file) { @@ -724,7 +726,7 @@ static int show_patch_diff(struct combine_diff_path *elem, int num_parent, if (header) { shown_header++; - puts(header); + printf("%s%c", header, opt->line_termination); } printf("diff --%s ", dense ? "cc" : "combined"); if (quote_c_style(elem->path, NULL, NULL, 0)) @@ -735,10 +737,10 @@ static int show_patch_diff(struct combine_diff_path *elem, int num_parent, printf("index "); for (i = 0; i < num_parent; i++) { abb = find_unique_abbrev(elem->parent[i].sha1, - DEFAULT_ABBREV); + abbrev); printf("%s%s", i ? "," : "", abb); } - abb = find_unique_abbrev(elem->sha1, DEFAULT_ABBREV); + abb = find_unique_abbrev(elem->sha1, abbrev); printf("..%s\n", abb); if (mode_differs) { @@ -797,7 +799,7 @@ static void show_raw_diff(struct combine_diff_path *p, int num_parent, const cha inter_name_termination = 0; if (header) - puts(header); + printf("%s%c", header, line_termination); for (i = 0; i < num_parent; i++) { if (p->parent[i].mode) @@ -862,7 +864,7 @@ int show_combined_diff(struct combine_diff_path *p, default: case DIFF_FORMAT_PATCH: - return show_patch_diff(p, num_parent, dense, header); + return show_patch_diff(p, num_parent, dense, header, opt); } } @@ -212,7 +212,8 @@ int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size) if (memcmp(bufptr, "tree ", 5)) return error("bogus commit object %s", sha1_to_hex(item->object.sha1)); if (get_sha1_hex(bufptr + 5, parent) < 0) - return error("bad tree pointer in commit %s\n", sha1_to_hex(item->object.sha1)); + return error("bad tree pointer in commit %s", + sha1_to_hex(item->object.sha1)); item->tree = lookup_tree(parent); if (item->tree) n_refs++; diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index a32ce15701..0b7416526d 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -8,7 +8,7 @@ use vars qw/ $AUTHOR $VERSION $GIT_SVN_INDEX $GIT_SVN $GIT_DIR $REV_DIR/; $AUTHOR = 'Eric Wong <normalperson@yhbt.net>'; -$VERSION = '0.9.1'; +$VERSION = '0.10.0'; $GIT_DIR = $ENV{GIT_DIR} || "$ENV{PWD}/.git"; $GIT_SVN = $ENV{GIT_SVN_ID} || 'git-svn'; $GIT_SVN_INDEX = "$GIT_DIR/$GIT_SVN/index"; @@ -30,6 +30,7 @@ use File::Basename qw/dirname basename/; use File::Path qw/mkpath/; use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; use File::Spec qw//; +use POSIX qw/strftime/; my $sha1 = qr/[a-f\d]{40}/; my $sha1_short = qr/[a-f\d]{6,40}/; my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, @@ -49,6 +50,7 @@ my %cmd = ( fetch => [ \&fetch, "Download new revisions from SVN" ], init => [ \&init, "Initialize and fetch (import)"], commit => [ \&commit, "Commit git revisions to SVN" ], + 'show-ignore' => [ \&show_ignore, "Show svn:ignore listings" ], rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)" ], help => [ \&usage, "Show help" ], ); @@ -258,6 +260,30 @@ sub commit { } +sub show_ignore { + require File::Find or die $!; + my $exclude_file = "$GIT_DIR/info/exclude"; + open my $fh, '<', $exclude_file or croak $!; + chomp(my @excludes = (<$fh>)); + close $fh or croak $!; + + $SVN_URL ||= file_to_s("$GIT_DIR/$GIT_SVN/info/url"); + chdir $SVN_WC or croak $!; + my %ign; + File::Find::find({wanted=>sub{if(lstat $_ && -d _ && -d "$_/.svn"){ + s#^\./##; + @{$ign{$_}} = safe_qx(qw(svn propget svn:ignore),$_); + }}, no_chdir=>1},'.'); + + print "\n# /\n"; + foreach (@{$ign{'.'}}) { print '/',$_ if /\S/ } + delete $ign{'.'}; + foreach my $i (sort keys %ign) { + print "\n# ",$i,"\n"; + foreach (@{$ign{$i}}) { print '/',$i,'/',$_ if /\S/ } + } +} + ########################### utility functions ######################### sub setup_git_svn { @@ -566,6 +592,7 @@ sub handle_rmdir { sub svn_commit_tree { my ($svn_rev, $commit) = @_; my $commit_msg = "$GIT_DIR/$GIT_SVN/.svn-commit.tmp.$$"; + my %log_msg = ( msg => '' ); open my $msg, '>', $commit_msg or croak $!; chomp(my $type = `git-cat-file -t $commit`); @@ -581,6 +608,7 @@ sub svn_commit_tree { if (!$in_msg) { $in_msg = 1 if (/^\s*$/); } else { + $log_msg{msg} .= $_; print $msg $_ or croak $!; } } @@ -600,9 +628,30 @@ sub svn_commit_tree { join("\n",@ci_output),"\n"; my ($rev_committed) = ($committed =~ /^Committed revision (\d+)\./); - # resync immediately - my @svn_up = (qw(svn up), "-r$svn_rev"); + my @svn_up = qw(svn up); push @svn_up, '--ignore-externals' unless $_no_ignore_ext; + if ($rev_committed == ($svn_rev + 1)) { + push @svn_up, "-r$rev_committed"; + sys(@svn_up); + my $info = svn_info('.'); + my $date = $info->{'Last Changed Date'} or die "Missing date\n"; + if ($info->{'Last Changed Rev'} != $rev_committed) { + croak "$info->{'Last Changed Rev'} != $rev_committed\n" + } + my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ + /(\d{4})\-(\d\d)\-(\d\d)\s + (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) + or croak "Failed to parse date: $date\n"; + $log_msg{date} = "$tz $Y-$m-$d $H:$M:$S"; + $log_msg{author} = $info->{'Last Changed Author'}; + $log_msg{revision} = $rev_committed; + $log_msg{msg} .= "\n"; + my $parent = file_to_s("$REV_DIR/$svn_rev"); + git_commit(\%log_msg, $parent, $commit); + return $rev_committed; + } + # resync immediately + push @svn_up, "-r$svn_rev"; sys(@svn_up); return fetch("$rev_committed=$commit")->{revision}; } @@ -699,7 +748,7 @@ sub svn_info { # only single-lines seem to exist in svn info output while (<$info_fh>) { chomp $_; - if (m#^([^:]+)\s*:\s*(\S*)$#) { + if (m#^([^:]+)\s*:\s*(\S.*)$#) { $ret->{$1} = $2; push @{$ret->{-order}}, $1; } diff --git a/contrib/git-svn/git-svn.txt b/contrib/git-svn/git-svn.txt index cf098d733a..b29073997c 100644 --- a/contrib/git-svn/git-svn.txt +++ b/contrib/git-svn/git-svn.txt @@ -43,6 +43,11 @@ fetch:: Fetch unfetched revisions from the SVN_URL we are tracking. refs/heads/git-svn-HEAD will be updated to the latest revision. + Note: You should never attempt to modify the git-svn-HEAD branch + outside of git-svn. Instead, create a branch from git-svn-HEAD + and work on that branch. Use the 'commit' command (see below) + to write git commits back to git-svn-HEAD. + commit:: Commit specified commit or tree objects to SVN. This relies on your imported fetch data being up-to-date. This makes @@ -61,6 +66,11 @@ rebuild:: the directory/repository you're tracking has moved or changed protocols. +show-ignore:: + Recursively finds and lists the svn:ignore property on + directories. The output is suitable for appending to + the $GIT_DIR/info/exclude file. + OPTIONS ------- -r <ARG>:: @@ -149,9 +159,11 @@ Tracking and contributing to an Subversion managed-project: # Commit only the git commits you want to SVN:: git-svn commit <tree-ish> [<tree-ish_2> ...] # Commit all the git commits from my-branch that don't exist in SVN:: - git commit git-svn-HEAD..my-branch + git-svn commit git-svn-HEAD..my-branch # Something is committed to SVN, pull the latest into your branch:: git-svn fetch && git pull . git-svn-HEAD +# Append svn:ignore settings to the default git exclude file: + git-svn show-ignore >> .git/info/exclude DESIGN PHILOSOPHY ----------------- @@ -172,7 +184,9 @@ SVN repositories via one git repository. Simply set the GIT_SVN_ID environment variable to a name other other than "git-svn" (the default) and git-svn will ignore the contents of the $GIT_DIR/git-svn directory and instead do all of its work in $GIT_DIR/$GIT_SVN_ID for that -invocation. +invocation. The interface branch will be $GIT_SVN_ID-HEAD, instead of +git-svn-HEAD. Any $GIT_SVN_ID-HEAD branch should never be modified +by the user outside of git-svn commands. ADDITIONAL FETCH ARGUMENTS -------------------------- diff --git a/contrib/gitview/gitview b/contrib/gitview/gitview index 5c338c0220..048caf6f86 100755 --- a/contrib/gitview/gitview +++ b/contrib/gitview/gitview @@ -154,7 +154,7 @@ class CellRendererGraph(gtk.GenericCellRenderer): cols = self.node[0] for start, end, colour in self.in_lines + self.out_lines: - cols = max(cols, start, end) + cols = int(max(cols, start, end)) (column, colour, names) = self.node names_len = 0 @@ -162,7 +162,7 @@ class CellRendererGraph(gtk.GenericCellRenderer): for item in names: 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 @@ -261,11 +261,11 @@ class Commit: children_sha1 = {} def __init__(self, commit_lines): - self.message = "" + self.message = "" self.author = "" - self.date = "" - self.committer = "" - self.commit_date = "" + self.date = "" + self.committer = "" + self.commit_date = "" self.commit_sha1 = "" self.parent_sha1 = [ ] self.parse_commit(commit_lines) @@ -391,7 +391,7 @@ class DiffWindow: sourceview.show() - def set_diff(self, commit_sha1, parent_sha1): + def set_diff(self, commit_sha1, parent_sha1, encoding): """Set the differences showed by this window. Compares the two trees and populates the window with the differences. @@ -401,7 +401,7 @@ class DiffWindow: return fp = os.popen("git diff-tree -p " + parent_sha1 + " " + commit_sha1) - self.buffer.set_text(fp.read()) + self.buffer.set_text(unicode(fp.read(), encoding).encode('utf-8')) fp.close() self.window.show() @@ -422,14 +422,15 @@ class DiffWindow: class GitView: """ This is the main class """ - version = "0.6" + version = "0.7" def __init__(self, with_diff=0): self.with_diff = with_diff - self.window = gtk.Window(gtk.WINDOW_TOPLEVEL) + self.window = gtk.Window(gtk.WINDOW_TOPLEVEL) self.window.set_border_width(0) self.window.set_title("Git repository browser") + self.get_encoding() self.get_bt_sha1() # Use three-quarters of the screen by default @@ -454,11 +455,7 @@ class GitView: self.bt_sha1 = { } ls_remote = re.compile('^(.{40})\trefs/([^^]+)(?:\\^(..))?$'); - git_dir = os.getenv("GIT_DIR") - if (git_dir == None): - git_dir = ".git" - - fp = os.popen('git ls-remote ' + git_dir) + fp = os.popen('git ls-remote "${GIT_DIR-.git}"') while 1: line = string.strip(fp.readline()) if line == '': @@ -472,6 +469,13 @@ class GitView: self.bt_sha1[sha1].append(name) fp.close() + def get_encoding(self): + fp = os.popen("git repo-config --get i18n.commitencoding") + self.encoding=string.strip(fp.readline()) + fp.close() + if (self.encoding == ""): + self.encoding = "utf-8" + def construct(self): """Construct the window contents.""" @@ -687,7 +691,7 @@ class GitView: self.revid_label.set_text(revid_label) self.committer_label.set_text(committer) self.timestamp_label.set_text(timestamp) - self.message_buffer.set_text(message) + self.message_buffer.set_text(unicode(message, self.encoding).encode('utf-8')) for widget in self.parents_widgets: self.table.remove(widget) @@ -732,7 +736,7 @@ class GitView: button.set_relief(gtk.RELIEF_NONE) button.set_sensitive(True) button.connect("clicked", self._show_clicked_cb, - commit.commit_sha1, parent_id) + commit.commit_sha1, parent_id, self.encoding) hbox.pack_start(button, expand=False, fill=True) button.show() @@ -827,6 +831,7 @@ class GitView: self.colours = {} self.nodepos = {} self.incomplete_line = {} + self.commits = [] index = 0 last_colour = 0 @@ -844,12 +849,7 @@ class GitView: commit = Commit(commit_lines) if (commit != None ): - (out_line, last_colour, last_nodepos) = self.draw_graph(commit, - index, out_line, - last_colour, - last_nodepos) - self.index[commit.commit_sha1] = index - index += 1 + self.commits.append(commit) # Skip the '\0 commit_lines = [] @@ -858,6 +858,14 @@ class GitView: fp.close() + for commit in self.commits: + (out_line, last_colour, last_nodepos) = self.draw_graph(commit, + index, out_line, + last_colour, + last_nodepos) + self.index[commit.commit_sha1] = index + index += 1 + self.treeview.set_model(self.model) self.treeview.show() @@ -870,28 +878,22 @@ class GitView: # Reset nodepostion if (last_nodepos > 5): - last_nodepos = 0 + last_nodepos = -1 # Add the incomplete lines of the last cell in this - for sha1 in self.incomplete_line.keys(): - if ( sha1 != commit.commit_sha1): - for pos in self.incomplete_line[sha1]: - in_line.append((pos, pos, self.colours[sha1])) - else: - del self.incomplete_line[sha1] - try: colour = self.colours[commit.commit_sha1] except KeyError: - last_colour +=1 - self.colours[commit.commit_sha1] = last_colour - colour = last_colour + self.colours[commit.commit_sha1] = last_colour+1 + last_colour = self.colours[commit.commit_sha1] + colour = self.colours[commit.commit_sha1] + try: node_pos = self.nodepos[commit.commit_sha1] except KeyError: - last_nodepos +=1 - self.nodepos[commit.commit_sha1] = last_nodepos - node_pos = last_nodepos + self.nodepos[commit.commit_sha1] = last_nodepos+1 + last_nodepos = self.nodepos[commit.commit_sha1] + node_pos = self.nodepos[commit.commit_sha1] #The first parent always continue on the same line try: @@ -901,25 +903,26 @@ class GitView: self.colours[commit.parent_sha1[0]] = colour self.nodepos[commit.parent_sha1[0]] = node_pos - in_line.append((node_pos, self.nodepos[commit.parent_sha1[0]], - self.colours[commit.parent_sha1[0]])) - - self.add_incomplete_line(commit.parent_sha1[0], index+1) + for sha1 in self.incomplete_line.keys(): + if (sha1 != commit.commit_sha1): + self.draw_incomplete_line(sha1, node_pos, + out_line, in_line, index) + else: + del self.incomplete_line[sha1] - if (len(commit.parent_sha1) > 1): - for parent_id in commit.parent_sha1[1:]: - try: - tmp_node_pos = self.nodepos[parent_id] - except KeyError: - last_colour += 1; - self.colours[parent_id] = last_colour - last_nodepos +=1 - self.nodepos[parent_id] = last_nodepos - in_line.append((node_pos, self.nodepos[parent_id], - self.colours[parent_id])) - self.add_incomplete_line(parent_id, index+1) + for parent_id in commit.parent_sha1: + try: + tmp_node_pos = self.nodepos[parent_id] + except KeyError: + self.colours[parent_id] = last_colour+1 + last_colour = self.colours[parent_id] + self.nodepos[parent_id] = last_nodepos+1 + last_nodepos = self.nodepos[parent_id] + in_line.append((node_pos, self.nodepos[parent_id], + self.colours[parent_id])) + self.add_incomplete_line(parent_id) try: branch_tag = self.bt_sha1[commit.commit_sha1] @@ -934,12 +937,31 @@ class GitView: return (in_line, last_colour, last_nodepos) - def add_incomplete_line(self, sha1, index): + def add_incomplete_line(self, sha1): try: self.incomplete_line[sha1].append(self.nodepos[sha1]) except KeyError: self.incomplete_line[sha1] = [self.nodepos[sha1]] + def draw_incomplete_line(self, sha1, node_pos, out_line, in_line, index): + for idx, pos in enumerate(self.incomplete_line[sha1]): + if(pos == node_pos): + #remove the straight line and add a slash + if ((pos, pos, self.colours[sha1]) in out_line): + out_line.remove((pos, pos, self.colours[sha1])) + out_line.append((pos, pos+0.5, self.colours[sha1])) + self.incomplete_line[sha1][idx] = pos = pos+0.5 + try: + next_commit = self.commits[index+1] + if (next_commit.commit_sha1 == sha1 and pos != int(pos)): + # join the line back to the node point + # This need to be done only if we modified it + in_line.append((pos, pos-0.5, self.colours[sha1])) + continue; + except IndexError: + pass + in_line.append((pos, pos, self.colours[sha1])) + def _go_clicked_cb(self, widget, revid): """Callback for when the go button for a parent is clicked.""" @@ -953,10 +975,10 @@ class GitView: self.treeview.grab_focus() - def _show_clicked_cb(self, widget, commit_sha1, parent_sha1): + def _show_clicked_cb(self, widget, commit_sha1, parent_sha1, encoding): """Callback for when the show button for a parent is clicked.""" window = DiffWindow() - window.set_diff(commit_sha1, parent_sha1) + window.set_diff(commit_sha1, parent_sha1, encoding) self.treeview.grab_focus() if __name__ == "__main__": @@ -178,11 +178,12 @@ static void emit_rewrite_diff(const char *name_a, copy_file('+', temp[1].name); } -static void builtin_diff(const char *name_a, +static const char *builtin_diff(const char *name_a, const char *name_b, struct diff_tempfile *temp, const char *xfrm_msg, - int complete_rewrite) + int complete_rewrite, + const char **args) { int i, next_at, cmd_size; const char *const diff_cmd = "diff -L%s -L%s"; @@ -242,19 +243,24 @@ static void builtin_diff(const char *name_a, } if (xfrm_msg && xfrm_msg[0]) puts(xfrm_msg); + /* + * we do not run diff between different kind + * of objects. + */ if (strncmp(temp[0].mode, temp[1].mode, 3)) - /* we do not run diff between different kind - * of objects. - */ - exit(0); + return NULL; if (complete_rewrite) { - fflush(NULL); emit_rewrite_diff(name_a, name_b, temp); - exit(0); + return NULL; } } - fflush(NULL); - execlp("/bin/sh","sh", "-c", cmd, NULL); + + /* This is disgusting */ + *args++ = "sh"; + *args++ = "-c"; + *args++ = cmd; + *args = NULL; + return "/bin/sh"; } struct diff_filespec *alloc_filespec(const char *path) @@ -559,6 +565,40 @@ static void remove_tempfile_on_signal(int signo) raise(signo); } +static int spawn_prog(const char *pgm, const char **arg) +{ + pid_t pid; + int status; + + fflush(NULL); + pid = fork(); + if (pid < 0) + die("unable to fork"); + if (!pid) { + execvp(pgm, (char *const*) arg); + exit(255); + } + + while (waitpid(pid, &status, 0) < 0) { + if (errno == EINTR) + continue; + return -1; + } + + /* Earlier we did not check the exit status because + * diff exits non-zero if files are different, and + * we are not interested in knowing that. It was a + * mistake which made it harder to quit a diff-* + * session that uses the git-apply-patch-script as + * the GIT_EXTERNAL_DIFF. A custom GIT_EXTERNAL_DIFF + * should also exit non-zero only when it wants to + * abort the entire diff-* session. + */ + if (WIFEXITED(status) && !WEXITSTATUS(status)) + return 0; + return -1; +} + /* An external diff command takes: * * diff-cmd name infile1 infile1-sha1 infile1-mode \ @@ -573,9 +613,9 @@ static void run_external_diff(const char *pgm, const char *xfrm_msg, int complete_rewrite) { + const char *spawn_arg[10]; struct diff_tempfile *temp = diff_temp; - pid_t pid; - int status; + int retval; static int atexit_asked = 0; const char *othername; @@ -592,59 +632,41 @@ static void run_external_diff(const char *pgm, signal(SIGINT, remove_tempfile_on_signal); } - fflush(NULL); - pid = fork(); - if (pid < 0) - die("unable to fork"); - if (!pid) { - if (pgm) { - if (one && two) { - const char *exec_arg[10]; - const char **arg = &exec_arg[0]; - *arg++ = pgm; - *arg++ = name; - *arg++ = temp[0].name; - *arg++ = temp[0].hex; - *arg++ = temp[0].mode; - *arg++ = temp[1].name; - *arg++ = temp[1].hex; - *arg++ = temp[1].mode; - if (other) { - *arg++ = other; - *arg++ = xfrm_msg; - } - *arg = NULL; - execvp(pgm, (char *const*) exec_arg); + if (pgm) { + const char **arg = &spawn_arg[0]; + if (one && two) { + *arg++ = pgm; + *arg++ = name; + *arg++ = temp[0].name; + *arg++ = temp[0].hex; + *arg++ = temp[0].mode; + *arg++ = temp[1].name; + *arg++ = temp[1].hex; + *arg++ = temp[1].mode; + if (other) { + *arg++ = other; + *arg++ = xfrm_msg; } - else - execlp(pgm, pgm, name, NULL); + } else { + *arg++ = pgm; + *arg++ = name; } - /* - * otherwise we use the built-in one. - */ - if (one && two) - builtin_diff(name, othername, temp, xfrm_msg, - complete_rewrite); - else + *arg = NULL; + } else { + if (one && two) { + pgm = builtin_diff(name, othername, temp, xfrm_msg, complete_rewrite, spawn_arg); + } else printf("* Unmerged path %s\n", name); - exit(0); } - if (waitpid(pid, &status, 0) < 0 || - !WIFEXITED(status) || WEXITSTATUS(status)) { - /* Earlier we did not check the exit status because - * diff exits non-zero if files are different, and - * we are not interested in knowing that. It was a - * mistake which made it harder to quit a diff-* - * session that uses the git-apply-patch-script as - * the GIT_EXTERNAL_DIFF. A custom GIT_EXTERNAL_DIFF - * should also exit non-zero only when it wants to - * abort the entire diff-* session. - */ - remove_tempfile(); + + retval = 0; + if (pgm) + retval = spawn_prog(pgm, spawn_arg); + remove_tempfile(); + if (retval) { fprintf(stderr, "external diff died, stopping at %s.\n", name); exit(1); } - remove_tempfile(); } static void diff_fill_sha1_info(struct diff_filespec *one) diff --git a/diffcore-rename.c b/diffcore-rename.c index 39d9126cb9..ffd126af0d 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -176,8 +176,10 @@ static int estimate_similarity(struct diff_filespec *src, /* A delta that has a lot of literal additions would have * big delta_size no matter what else it does. */ - if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE) + if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE) { + free(delta); return 0; + } /* Estimate the edit size by interpreting delta. */ if (count_delta(delta, delta_size, &src_copied, &literal_added)) { diff --git a/environment.c b/environment.c index 251e53ca09..16c08f0697 100644 --- a/environment.c +++ b/environment.c @@ -17,6 +17,7 @@ int only_use_symrefs = 0; int repository_format_version = 0; char git_commit_encoding[MAX_ENCODING_LENGTH] = "utf-8"; int shared_repository = 0; +const char *apply_default_whitespace = NULL; static char *git_dir, *git_object_dir, *git_index_file, *git_refs_dir, *git_graft_file; @@ -15,6 +15,7 @@ #include "cache.h" #include "commit.h" +#include "revision.h" #include "epoch.h" struct fraction { @@ -11,7 +11,6 @@ typedef int (*emitter_func) (struct commit *); int sort_list_in_merge_order(struct commit_list *list, emitter_func emitter); /* Low bits are used by rev-list */ -#define UNINTERESTING (1u<<10) #define BOUNDARY (1u<<11) #define VISITED (1u<<12) #define DISCONTINUITY (1u<<13) diff --git a/exec_cmd.c b/exec_cmd.c index 55af33bb7e..b5e59a9ae9 100644 --- a/exec_cmd.c +++ b/exec_cmd.c @@ -13,7 +13,7 @@ void git_set_exec_path(const char *exec_path) /* Returns the highest-priority, location to look for git programs. */ -const char *git_exec_path() +const char *git_exec_path(void) { const char *env; diff --git a/fetch-pack.c b/fetch-pack.c index aa6f42ae1b..535de10660 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) { @@ -82,7 +82,7 @@ static void mark_common(struct commit *commit, Get the next rev to send, ignoring the common. */ -static const unsigned char* get_rev() +static const unsigned char* get_rev(void) { struct commit *commit = NULL; @@ -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/fsck-objects.c b/fsck-objects.c index 6439d55126..4ddd67699c 100644 --- a/fsck-objects.c +++ b/fsck-objects.c @@ -20,7 +20,7 @@ static int check_strict = 0; static int keep_cache_objects = 0; static unsigned char head_sha1[20]; -#if NO_D_INO_IN_DIRENT +#ifdef NO_D_INO_IN_DIRENT #define SORT_DIRENT 0 #define DIRENT_SORT_HINT(de) 0 #else @@ -300,7 +300,7 @@ do } >"$dotest/final-commit" ;; *) - case "$resolved,$interactive" in + case "$resolved$interactive" in tt) # This is used only for interactive view option. git-diff-index -p --cached HEAD >"$dotest/patch" @@ -364,6 +364,12 @@ do # trust what the user has in the index file and the # working tree. resolved= + changed="$(git-diff-index --cached --name-only HEAD)" + if test '' = "$changed" + then + echo "No changes - did you forget update-index?" + stop_here $this + fi apply_status=0 ;; esac @@ -374,7 +380,7 @@ do then # Applying the patch to an earlier tree and merging the # result may have produced the same tree as ours. - changed="$(git-diff-index --cached --name-only -z HEAD)" + changed="$(git-diff-index --cached --name-only HEAD)" if test '' = "$changed" then echo No changes -- Patch already applied. diff --git a/git-annotate.perl b/git-annotate.perl new file mode 100755 index 0000000000..f9c2c6caf5 --- /dev/null +++ b/git-annotate.perl @@ -0,0 +1,488 @@ +#!/usr/bin/perl +# Copyright 2006, Ryan Anderson <ryan@michonline.com> +# +# GPL v2 (See COPYING) +# +# This file is licensed under the GPL v2, or a later version +# at the discretion of Linus Torvalds. + +use warnings; +use strict; +use Getopt::Long; +use POSIX qw(strftime gmtime); + +sub usage() { + print STDERR 'Usage: ${\basename $0} [-s] [-S revs-file] file [ revision ] + -l, --long + Show long rev (Defaults off) + -r, --rename + Follow renames (Defaults on). + -S, --rev-file revs-file + use revs from revs-file instead of calling git-rev-list + -h, --help + This message. +'; + + exit(1); +} + +our ($help, $longrev, $rename, $starting_rev, $rev_file) = (0, 0, 1); + +my $rc = GetOptions( "long|l" => \$longrev, + "help|h" => \$help, + "rename|r" => \$rename, + "rev-file|S" => \$rev_file); +if (!$rc or $help) { + usage(); +} + +my $filename = shift @ARGV; +if (@ARGV) { + $starting_rev = shift @ARGV; +} + +my @stack = ( + { + 'rev' => defined $starting_rev ? $starting_rev : "HEAD", + 'filename' => $filename, + }, +); + +our @filelines = (); + +if (defined $starting_rev) { + @filelines = git_cat_file($starting_rev, $filename); +} else { + open(F,"<",$filename) + or die "Failed to open filename: $!"; + + while(<F>) { + chomp; + push @filelines, $_; + } + close(F); + +} + +our %revs; +our @revqueue; +our $head; + +my $revsprocessed = 0; +while (my $bound = pop @stack) { + my @revisions = git_rev_list($bound->{'rev'}, $bound->{'filename'}); + foreach my $revinst (@revisions) { + my ($rev, @parents) = @$revinst; + $head ||= $rev; + + if (!defined($rev)) { + $rev = ""; + } + $revs{$rev}{'filename'} = $bound->{'filename'}; + if (scalar @parents > 0) { + $revs{$rev}{'parents'} = \@parents; + next; + } + + if (!$rename) { + next; + } + + my $newbound = find_parent_renames($rev, $bound->{'filename'}); + if ( exists $newbound->{'filename'} && $newbound->{'filename'} ne $bound->{'filename'}) { + push @stack, $newbound; + $revs{$rev}{'parents'} = [$newbound->{'rev'}]; + } + } +} +push @revqueue, $head; +init_claim( defined $starting_rev ? $starting_rev : 'dirty'); +unless (defined $starting_rev) { + my $diff = open_pipe("git","diff","-R", "HEAD", "--",$filename) + or die "Failed to call git diff to check for dirty state: $!"; + + _git_diff_parse($diff, $head, "dirty", ( + 'author' => gitvar_name("GIT_AUTHOR_IDENT"), + 'author_date' => sprintf("%s +0000",time()), + ) + ); + close($diff); +} +handle_rev(); + + +my $i = 0; +foreach my $l (@filelines) { + my ($output, $rev, $committer, $date); + if (ref $l eq 'ARRAY') { + ($output, $rev, $committer, $date) = @$l; + if (!$longrev && length($rev) > 8) { + $rev = substr($rev,0,8); + } + } else { + $output = $l; + ($rev, $committer, $date) = ('unknown', 'unknown', 'unknown'); + } + + printf("%s\t(%10s\t%10s\t%d)%s\n", $rev, $committer, + format_date($date), $i++, $output); +} + +sub init_claim { + my ($rev) = @_; + for (my $i = 0; $i < @filelines; $i++) { + $filelines[$i] = [ $filelines[$i], '', '', '', 1]; + # line, + # rev, + # author, + # date, + # 1 <-- belongs to the original file. + } + $revs{$rev}{'lines'} = \@filelines; +} + + +sub handle_rev { + my $i = 0; + my %seen; + while (my $rev = shift @revqueue) { + next if $seen{$rev}++; + + my %revinfo = git_commit_info($rev); + + foreach my $p (@{$revs{$rev}{'parents'}}) { + + git_diff_parse($p, $rev, %revinfo); + push @revqueue, $p; + } + + + if (scalar @{$revs{$rev}{parents}} == 0) { + # We must be at the initial rev here, so claim everything that is left. + for (my $i = 0; $i < @{$revs{$rev}{lines}}; $i++) { + if (ref ${$revs{$rev}{lines}}[$i] eq '' || ${$revs{$rev}{lines}}[$i][1] eq '') { + claim_line($i, $rev, $revs{$rev}{lines}, %revinfo); + } + } + } + } +} + + +sub git_rev_list { + my ($rev, $file) = @_; + + my $revlist; + if ($rev_file) { + open($revlist, '<' . $rev_file); + } else { + $revlist = open_pipe("git-rev-list","--parents","--remove-empty",$rev,"--",$file) + or die "Failed to exec git-rev-list: $!"; + } + + my @revs; + while(my $line = <$revlist>) { + chomp $line; + my ($rev, @parents) = split /\s+/, $line; + push @revs, [ $rev, @parents ]; + } + close($revlist); + + printf("0 revs found for rev %s (%s)\n", $rev, $file) if (@revs == 0); + return @revs; +} + +sub find_parent_renames { + my ($rev, $file) = @_; + + my $patch = open_pipe("git-diff-tree", "-M50", "-r","--name-status", "-z","$rev") + or die "Failed to exec git-diff: $!"; + + local $/ = "\0"; + my %bound; + my $junk = <$patch>; + while (my $change = <$patch>) { + chomp $change; + my $filename = <$patch>; + chomp $filename; + + if ($change =~ m/^[AMD]$/ ) { + next; + } elsif ($change =~ m/^R/ ) { + my $oldfilename = $filename; + $filename = <$patch>; + chomp $filename; + if ( $file eq $filename ) { + my $parent = git_find_parent($rev, $oldfilename); + @bound{'rev','filename'} = ($parent, $oldfilename); + last; + } + } + } + close($patch); + + return \%bound; +} + + +sub git_find_parent { + my ($rev, $filename) = @_; + + my $revparent = open_pipe("git-rev-list","--remove-empty", "--parents","--max-count=1","$rev","--",$filename) + or die "Failed to open git-rev-list to find a single parent: $!"; + + my $parentline = <$revparent>; + chomp $parentline; + my ($revfound,$parent) = split m/\s+/, $parentline; + + close($revparent); + + return $parent; +} + + +# Get a diff between the current revision and a parent. +# Record the commit information that results. +sub git_diff_parse { + my ($parent, $rev, %revinfo) = @_; + + my $diff = open_pipe("git-diff-tree","-M","-p",$rev,$parent,"--", + $revs{$rev}{'filename'}, $revs{$parent}{'filename'}) + or die "Failed to call git-diff for annotation: $!"; + + _git_diff_parse($diff, $parent, $rev, %revinfo); + + close($diff); +} + +sub _git_diff_parse { + my ($diff, $parent, $rev, %revinfo) = @_; + + my ($ri, $pi) = (0,0); + my $slines = $revs{$rev}{'lines'}; + my @plines; + + my $gotheader = 0; + my ($remstart); + my ($hunk_start, $hunk_index); + while(<$diff>) { + chomp; + if (m/^@@ -(\d+),(\d+) \+(\d+),(\d+)/) { + $remstart = $1; + # Adjust for 0-based arrays + $remstart--; + # Reinit hunk tracking. + $hunk_start = $remstart; + $hunk_index = 0; + $gotheader = 1; + + for (my $i = $ri; $i < $remstart; $i++) { + $plines[$pi++] = $slines->[$i]; + $ri++; + } + next; + } elsif (!$gotheader) { + next; + } + + if (m/^\+(.*)$/) { + my $line = $1; + $plines[$pi++] = [ $line, '', '', '', 0 ]; + next; + + } elsif (m/^-(.*)$/) { + my $line = $1; + if (get_line($slines, $ri) eq $line) { + # Found a match, claim + claim_line($ri, $rev, $slines, %revinfo); + } else { + die sprintf("Sync error: %d/%d\n|%s\n|%s\n%s => %s\n", + $ri, $hunk_start + $hunk_index, + $line, + get_line($slines, $ri), + $rev, $parent); + } + $ri++; + + } else { + if (substr($_,1) ne get_line($slines,$ri) ) { + die sprintf("Line %d (%d) does not match:\n|%s\n|%s\n%s => %s\n", + $hunk_start + $hunk_index, $ri, + substr($_,1), + get_line($slines,$ri), + $rev, $parent); + } + $plines[$pi++] = $slines->[$ri++]; + } + $hunk_index++; + } + for (my $i = $ri; $i < @{$slines} ; $i++) { + push @plines, $slines->[$ri++]; + } + + $revs{$parent}{lines} = \@plines; + return; +} + +sub get_line { + my ($lines, $index) = @_; + + return ref $lines->[$index] ne '' ? $lines->[$index][0] : $lines->[$index]; +} + +sub git_cat_file { + my ($rev, $filename) = @_; + return () unless defined $rev && defined $filename; + + my $blob = git_ls_tree($rev, $filename); + + my $catfile = open_pipe("git","cat-file", "blob", $blob) + or die "Failed to git-cat-file blob $blob (rev $rev, file $filename): " . $!; + + my @lines; + while(<$catfile>) { + chomp; + push @lines, $_; + } + close($catfile); + + return @lines; +} + +sub git_ls_tree { + my ($rev, $filename) = @_; + + my $lstree = open_pipe("git","ls-tree",$rev,$filename) + or die "Failed to call git ls-tree: $!"; + + my ($mode, $type, $blob, $tfilename); + while(<$lstree>) { + ($mode, $type, $blob, $tfilename) = split(/\s+/, $_, 4); + last if ($tfilename eq $filename); + } + close($lstree); + + return $blob if $filename eq $filename; + die "git-ls-tree failed to find blob for $filename"; + +} + + + +sub claim_line { + my ($floffset, $rev, $lines, %revinfo) = @_; + my $oline = get_line($lines, $floffset); + @{$lines->[$floffset]} = ( $oline, $rev, + $revinfo{'author'}, $revinfo{'author_date'} ); + #printf("Claiming line %d with rev %s: '%s'\n", + # $floffset, $rev, $oline) if 1; +} + +sub git_commit_info { + my ($rev) = @_; + my $commit = open_pipe("git-cat-file", "commit", $rev) + or die "Failed to call git-cat-file: $!"; + + my %info; + while(<$commit>) { + chomp; + last if (length $_ == 0); + + if (m/^author (.*) <(.*)> (.*)$/) { + $info{'author'} = $1; + $info{'author_email'} = $2; + $info{'author_date'} = $3; + } elsif (m/^committer (.*) <(.*)> (.*)$/) { + $info{'committer'} = $1; + $info{'committer_email'} = $2; + $info{'committer_date'} = $3; + } + } + close($commit); + + return %info; +} + +sub format_date { + my ($timestamp, $timezone) = split(' ', $_[0]); + + return strftime("%Y-%m-%d %H:%M:%S " . $timezone, gmtime($timestamp)); +} + +# Copied from git-send-email.perl - We need a Git.pm module.. +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 $val; +} + +sub gitvar_name { + my ($name) = @_; + my $val = gitvar($name); + my @field = split(/\s+/, $val); + return join(' ', @field[0...(@field-4)]); +} + +sub open_pipe { + if ($^O eq '##INSERT_ACTIVESTATE_STRING_HERE##') { + return open_pipe_activestate(@_); + } else { + return open_pipe_normal(@_); + } +} + +sub open_pipe_activestate { + tie *fh, "Git::ActiveStatePipe", @_; + return *fh; +} + +sub open_pipe_normal { + my (@execlist) = @_; + + my $pid = open my $kid, "-|"; + defined $pid or die "Cannot fork: $!"; + + unless ($pid) { + exec @execlist; + die "Cannot exec @execlist: $!"; + } + + return $kid; +} + +package Git::ActiveStatePipe; +use strict; + +sub TIEHANDLE { + my ($class, @params) = @_; + my $cmdline = join " ", @params; + my @data = qx{$cmdline}; + bless { i => 0, data => \@data }, $class; +} + +sub READLINE { + my $self = shift; + if ($self->{i} >= scalar @{$self->{data}}) { + return undef; + } + return $self->{'data'}->[ $self->{i}++ ]; +} + +sub CLOSE { + my $self = shift; + delete $self->{data}; + delete $self->{i}; +} + +sub EOF { + my $self = shift; + return ($self->{i} >= scalar @{$self->{data}}); +} diff --git a/git-clone.sh b/git-clone.sh index dc0ad552a3..4ed861d576 100755 --- a/git-clone.sh +++ b/git-clone.sh @@ -118,7 +118,7 @@ dir="$2" [ -e "$dir" ] && echo "$dir already exists." && usage mkdir -p "$dir" && D=$(cd "$dir" && pwd) && -trap 'err=$?; rm -r $D; exit $err' exit +trap 'err=$?; cd ..; rm -r "$D"; exit $err' exit case "$bare" in yes) GIT_DIR="$D" ;; *) GIT_DIR="$D/.git" ;; @@ -253,7 +253,7 @@ Pull: $head_points_at:$origin" && case "$no_checkout" in '') - git checkout + git-read-tree -m -u -v HEAD HEAD esac fi diff --git a/git-cvsserver.perl b/git-cvsserver.perl new file mode 100755 index 0000000000..d20d1a8c4b --- /dev/null +++ b/git-cvsserver.perl @@ -0,0 +1,2449 @@ +#!/usr/bin/perl + +#### +#### This application is a CVS emulation layer for git. +#### It is intended for clients to connect over SSH. +#### See the documentation for more details. +#### +#### Copyright The Open University UK - 2006. +#### +#### Authors: Martyn Smith <martyn@catalyst.net.nz> +#### Martin Langhoff <martin@catalyst.net.nz> +#### +#### +#### Released under the GNU Public License, version 2. +#### +#### + +use strict; +use warnings; + +use Fcntl; +use File::Temp qw/tempdir tempfile/; +use File::Basename; + +my $log = GITCVS::log->new(); +my $cfg; + +my $DATE_LIST = { + Jan => "01", + Feb => "02", + Mar => "03", + Apr => "04", + May => "05", + Jun => "06", + Jul => "07", + Aug => "08", + Sep => "09", + Oct => "10", + Nov => "11", + Dec => "12", +}; + +# Enable autoflush for STDOUT (otherwise the whole thing falls apart) +$| = 1; + +#### Definition and mappings of functions #### + +my $methods = { + 'Root' => \&req_Root, + 'Valid-responses' => \&req_Validresponses, + 'valid-requests' => \&req_validrequests, + 'Directory' => \&req_Directory, + 'Entry' => \&req_Entry, + 'Modified' => \&req_Modified, + 'Unchanged' => \&req_Unchanged, + 'Argument' => \&req_Argument, + 'Argumentx' => \&req_Argument, + 'expand-modules' => \&req_expandmodules, + 'add' => \&req_add, + 'remove' => \&req_remove, + 'co' => \&req_co, + 'update' => \&req_update, + 'ci' => \&req_ci, + 'diff' => \&req_diff, + 'log' => \&req_log, + 'tag' => \&req_CATCHALL, + 'status' => \&req_status, + 'admin' => \&req_CATCHALL, + 'history' => \&req_CATCHALL, + 'watchers' => \&req_CATCHALL, + 'editors' => \&req_CATCHALL, + 'annotate' => \&req_annotate, + 'Global_option' => \&req_Globaloption, + #'annotate' => \&req_CATCHALL, +}; + +############################################## + + +# $state holds all the bits of information the clients sends us that could +# potentially be useful when it comes to actually _doing_ something. +my $state = {}; +$log->info("--------------- STARTING -----------------"); + +my $TEMP_DIR = tempdir( CLEANUP => 1 ); +$log->debug("Temporary directory is '$TEMP_DIR'"); + +# Keep going until the client closes the connection +while (<STDIN>) +{ + chomp; + + # Check to see if we've seen this method, and call appropiate function. + if ( /^([\w-]+)(?:\s+(.*))?$/ and defined($methods->{$1}) ) + { + # use the $methods hash to call the appropriate sub for this command + #$log->info("Method : $1"); + &{$methods->{$1}}($1,$2); + } else { + # log fatal because we don't understand this function. If this happens + # we're fairly screwed because we don't know if the client is expecting + # a response. If it is, the client will hang, we'll hang, and the whole + # thing will be custard. + $log->fatal("Don't understand command $_\n"); + die("Unknown command $_"); + } +} + +$log->debug("Processing time : user=" . (times)[0] . " system=" . (times)[1]); +$log->info("--------------- FINISH -----------------"); + +# Magic catchall method. +# This is the method that will handle all commands we haven't yet +# implemented. It simply sends a warning to the log file indicating a +# command that hasn't been implemented has been invoked. +sub req_CATCHALL +{ + my ( $cmd, $data ) = @_; + $log->warn("Unhandled command : req_$cmd : $data"); +} + + +# Root pathname \n +# Response expected: no. Tell the server which CVSROOT to use. Note that +# pathname is a local directory and not a fully qualified CVSROOT variable. +# pathname must already exist; if creating a new root, use the init +# request, not Root. pathname does not include the hostname of the server, +# how to access the server, etc.; by the time the CVS protocol is in use, +# connection, authentication, etc., are already taken care of. The Root +# request must be sent only once, and it must be sent before any requests +# other than Valid-responses, valid-requests, UseUnchanged, Set or init. +sub req_Root +{ + my ( $cmd, $data ) = @_; + $log->debug("req_Root : $data"); + + $state->{CVSROOT} = $data; + + $ENV{GIT_DIR} = $state->{CVSROOT} . "/"; + + foreach my $line ( `git-var -l` ) + { + next unless ( $line =~ /^(.*?)\.(.*?)=(.*)$/ ); + $cfg->{$1}{$2} = $3; + } + + unless ( defined ( $cfg->{gitcvs}{enabled} ) and $cfg->{gitcvs}{enabled} =~ /^\s*(1|true|yes)\s*$/i ) + { + print "E GITCVS emulation needs to be enabled on this repo\n"; + print "E the repo config file needs a [gitcvs] section added, and the parameter 'enabled' set to 1\n"; + print "E \n"; + print "error 1 GITCVS emulation disabled\n"; + } + + if ( defined ( $cfg->{gitcvs}{logfile} ) ) + { + $log->setfile($cfg->{gitcvs}{logfile}); + } else { + $log->nofile(); + } +} + +# Global_option option \n +# Response expected: no. Transmit one of the global options `-q', `-Q', +# `-l', `-t', `-r', or `-n'. option must be one of those strings, no +# variations (such as combining of options) are allowed. For graceful +# handling of valid-requests, it is probably better to make new global +# options separate requests, rather than trying to add them to this +# request. +sub req_Globaloption +{ + my ( $cmd, $data ) = @_; + $log->debug("req_Globaloption : $data"); + + # TODO : is this data useful ??? +} + +# Valid-responses request-list \n +# Response expected: no. Tell the server what responses the client will +# accept. request-list is a space separated list of tokens. +sub req_Validresponses +{ + my ( $cmd, $data ) = @_; + $log->debug("req_Validrepsonses : $data"); + + # TODO : re-enable this, currently it's not particularly useful + #$state->{validresponses} = [ split /\s+/, $data ]; +} + +# valid-requests \n +# Response expected: yes. Ask the server to send back a Valid-requests +# response. +sub req_validrequests +{ + my ( $cmd, $data ) = @_; + + $log->debug("req_validrequests"); + + $log->debug("SEND : Valid-requests " . join(" ",keys %$methods)); + $log->debug("SEND : ok"); + + print "Valid-requests " . join(" ",keys %$methods) . "\n"; + print "ok\n"; +} + +# Directory local-directory \n +# Additional data: repository \n. Response expected: no. Tell the server +# what directory to use. The repository should be a directory name from a +# previous server response. Note that this both gives a default for Entry +# and Modified and also for ci and the other commands; normal usage is to +# send Directory for each directory in which there will be an Entry or +# Modified, and then a final Directory for the original directory, then the +# command. The local-directory is relative to the top level at which the +# command is occurring (i.e. the last Directory which is sent before the +# command); to indicate that top level, `.' should be sent for +# local-directory. +sub req_Directory +{ + my ( $cmd, $data ) = @_; + + my $repository = <STDIN>; + chomp $repository; + + + $state->{localdir} = $data; + $state->{repository} = $repository; + $state->{directory} = $repository; + $state->{directory} =~ s/^$state->{CVSROOT}\///; + $state->{module} = $1 if ($state->{directory} =~ s/^(.*?)(\/|$)//); + $state->{directory} .= "/" if ( $state->{directory} =~ /\S/ ); + + $log->debug("req_Directory : localdir=$data repository=$repository directory=$state->{directory} module=$state->{module}"); +} + +# Entry entry-line \n +# Response expected: no. Tell the server what version of a file is on the +# local machine. The name in entry-line is a name relative to the directory +# most recently specified with Directory. If the user is operating on only +# some files in a directory, Entry requests for only those files need be +# included. If an Entry request is sent without Modified, Is-modified, or +# Unchanged, it means the file is lost (does not exist in the working +# directory). If both Entry and one of Modified, Is-modified, or Unchanged +# are sent for the same file, Entry must be sent first. For a given file, +# one can send Modified, Is-modified, or Unchanged, but not more than one +# of these three. +sub req_Entry +{ + my ( $cmd, $data ) = @_; + + $log->debug("req_Entry : $data"); + + my @data = split(/\//, $data); + + $state->{entries}{$state->{directory}.$data[1]} = { + revision => $data[2], + conflict => $data[3], + options => $data[4], + tag_or_date => $data[5], + }; +} + +# add \n +# Response expected: yes. Add a file or directory. This uses any previous +# Argument, Directory, Entry, or Modified requests, if they have been sent. +# The last Directory sent specifies the working directory at the time of +# the operation. To add a directory, send the directory to be added using +# Directory and Argument requests. +sub req_add +{ + my ( $cmd, $data ) = @_; + + argsplit("add"); + + my $addcount = 0; + + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + unless ( defined ( $state->{entries}{$filename}{modified_filename} ) ) + { + print "E cvs add: nothing known about `$filename'\n"; + next; + } + # TODO : check we're not squashing an already existing file + if ( defined ( $state->{entries}{$filename}{revision} ) ) + { + print "E cvs add: `$filename' has already been entered\n"; + next; + } + + + my ( $filepart, $dirpart ) = filenamesplit($filename); + + print "E cvs add: scheduling file `$filename' for addition\n"; + + print "Checked-in $dirpart\n"; + print "$filename\n"; + print "/$filepart/0///\n"; + + $addcount++; + } + + if ( $addcount == 1 ) + { + print "E cvs add: use `cvs commit' to add this file permanently\n"; + } + elsif ( $addcount > 1 ) + { + print "E cvs add: use `cvs commit' to add these files permanently\n"; + } + + print "ok\n"; +} + +# remove \n +# Response expected: yes. Remove a file. This uses any previous Argument, +# Directory, Entry, or Modified requests, if they have been sent. The last +# Directory sent specifies the working directory at the time of the +# operation. Note that this request does not actually do anything to the +# repository; the only effect of a successful remove request is to supply +# the client with a new entries line containing `-' to indicate a removed +# file. In fact, the client probably could perform this operation without +# contacting the server, although using remove may cause the server to +# perform a few more checks. The client sends a subsequent ci request to +# actually record the removal in the repository. +sub req_remove +{ + my ( $cmd, $data ) = @_; + + argsplit("remove"); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + #$log->debug("add state : " . Dumper($state)); + + my $rmcount = 0; + + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + if ( defined ( $state->{entries}{$filename}{unchanged} ) or defined ( $state->{entries}{$filename}{modified_filename} ) ) + { + print "E cvs remove: file `$filename' still in working directory\n"; + next; + } + + my $meta = $updater->getmeta($filename); + my $wrev = revparse($filename); + + unless ( defined ( $wrev ) ) + { + print "E cvs remove: nothing known about `$filename'\n"; + next; + } + + if ( defined($wrev) and $wrev < 0 ) + { + print "E cvs remove: file `$filename' already scheduled for removal\n"; + next; + } + + unless ( $wrev == $meta->{revision} ) + { + # TODO : not sure if the format of this message is quite correct. + print "E cvs remove: Up to date check failed for `$filename'\n"; + next; + } + + + my ( $filepart, $dirpart ) = filenamesplit($filename); + + print "E cvs remove: scheduling `$filename' for removal\n"; + + print "Checked-in $dirpart\n"; + print "$filename\n"; + print "/$filepart/-1.$wrev///\n"; + + $rmcount++; + } + + if ( $rmcount == 1 ) + { + print "E cvs remove: use `cvs commit' to remove this file permanently\n"; + } + elsif ( $rmcount > 1 ) + { + print "E cvs remove: use `cvs commit' to remove these files permanently\n"; + } + + print "ok\n"; +} + +# Modified filename \n +# Response expected: no. Additional data: mode, \n, file transmission. Send +# the server a copy of one locally modified file. filename is a file within +# the most recent directory sent with Directory; it must not contain `/'. +# If the user is operating on only some files in a directory, only those +# files need to be included. This can also be sent without Entry, if there +# is no entry for the file. +sub req_Modified +{ + my ( $cmd, $data ) = @_; + + my $mode = <STDIN>; + chomp $mode; + my $size = <STDIN>; + chomp $size; + + # Grab config information + my $blocksize = 8192; + my $bytesleft = $size; + my $tmp; + + # Get a filehandle/name to write it to + my ( $fh, $filename ) = tempfile( DIR => $TEMP_DIR ); + + # Loop over file data writing out to temporary file. + while ( $bytesleft ) + { + $blocksize = $bytesleft if ( $bytesleft < $blocksize ); + read STDIN, $tmp, $blocksize; + print $fh $tmp; + $bytesleft -= $blocksize; + } + + close $fh; + + # Ensure we have something sensible for the file mode + if ( $mode =~ /u=(\w+)/ ) + { + $mode = $1; + } else { + $mode = "rw"; + } + + # Save the file data in $state + $state->{entries}{$state->{directory}.$data}{modified_filename} = $filename; + $state->{entries}{$state->{directory}.$data}{modified_mode} = $mode; + $state->{entries}{$state->{directory}.$data}{modified_hash} = `git-hash-object $filename`; + $state->{entries}{$state->{directory}.$data}{modified_hash} =~ s/\s.*$//s; + + #$log->debug("req_Modified : file=$data mode=$mode size=$size"); +} + +# Unchanged filename \n +# Response expected: no. Tell the server that filename has not been +# modified in the checked out directory. The filename is a file within the +# most recent directory sent with Directory; it must not contain `/'. +sub req_Unchanged +{ + my ( $cmd, $data ) = @_; + + $state->{entries}{$state->{directory}.$data}{unchanged} = 1; + + #$log->debug("req_Unchanged : $data"); +} + +# Argument text \n +# Response expected: no. Save argument for use in a subsequent command. +# Arguments accumulate until an argument-using command is given, at which +# point they are forgotten. +# Argumentx text \n +# Response expected: no. Append \n followed by text to the current argument +# being saved. +sub req_Argument +{ + my ( $cmd, $data ) = @_; + + # TODO : Not quite sure how Argument and Argumentx differ, but I assume + # it's for multi-line arguments ... somehow ... + + $log->debug("$cmd : $data"); + + push @{$state->{arguments}}, $data; +} + +# expand-modules \n +# Response expected: yes. Expand the modules which are specified in the +# arguments. Returns the data in Module-expansion responses. Note that the +# server can assume that this is checkout or export, not rtag or rdiff; the +# latter do not access the working directory and thus have no need to +# expand modules on the client side. Expand may not be the best word for +# what this request does. It does not necessarily tell you all the files +# contained in a module, for example. Basically it is a way of telling you +# which working directories the server needs to know about in order to +# handle a checkout of the specified modules. For example, suppose that the +# server has a module defined by +# aliasmodule -a 1dir +# That is, one can check out aliasmodule and it will take 1dir in the +# repository and check it out to 1dir in the working directory. Now suppose +# the client already has this module checked out and is planning on using +# the co request to update it. Without using expand-modules, the client +# would have two bad choices: it could either send information about all +# working directories under the current directory, which could be +# unnecessarily slow, or it could be ignorant of the fact that aliasmodule +# stands for 1dir, and neglect to send information for 1dir, which would +# lead to incorrect operation. With expand-modules, the client would first +# ask for the module to be expanded: +sub req_expandmodules +{ + my ( $cmd, $data ) = @_; + + argsplit(); + + $log->debug("req_expandmodules : " . ( defined($data) ? $data : "[NULL]" ) ); + + unless ( ref $state->{arguments} eq "ARRAY" ) + { + print "ok\n"; + return; + } + + foreach my $module ( @{$state->{arguments}} ) + { + $log->debug("SEND : Module-expansion $module"); + print "Module-expansion $module\n"; + } + + print "ok\n"; + statecleanup(); +} + +# co \n +# Response expected: yes. Get files from the repository. This uses any +# previous Argument, Directory, Entry, or Modified requests, if they have +# been sent. Arguments to this command are module names; the client cannot +# know what directories they correspond to except by (1) just sending the +# co request, and then seeing what directory names the server sends back in +# its responses, and (2) the expand-modules request. +sub req_co +{ + my ( $cmd, $data ) = @_; + + argsplit("co"); + + my $module = $state->{args}[0]; + my $checkout_path = $module; + + # use the user specified directory if we're given it + $checkout_path = $state->{opt}{d} if ( exists ( $state->{opt}{d} ) ); + + $log->debug("req_co : " . ( defined($data) ? $data : "[NULL]" ) ); + + $log->info("Checking out module '$module' ($state->{CVSROOT}) to '$checkout_path'"); + + $ENV{GIT_DIR} = $state->{CVSROOT} . "/"; + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $module, $log); + $updater->update(); + + # instruct the client that we're checking out to $checkout_path + print "E cvs server: updating $checkout_path\n"; + + foreach my $git ( @{$updater->gethead} ) + { + # Don't want to check out deleted files + next if ( $git->{filehash} eq "deleted" ); + + ( $git->{name}, $git->{dir} ) = filenamesplit($git->{name}); + + # modification time of this file + print "Mod-time $git->{modified}\n"; + + # print some information to the client + print "MT +updated\n"; + print "MT text U\n"; + if ( defined ( $git->{dir} ) and $git->{dir} ne "./" ) + { + print "MT fname $checkout_path/$git->{dir}$git->{name}\n"; + } else { + print "MT fname $checkout_path/$git->{name}\n"; + } + print "MT newline\n"; + print "MT -updated\n"; + + # instruct client we're sending a file to put in this path + print "Created $checkout_path/" . ( defined ( $git->{dir} ) ? $git->{dir} . "/" : "" ) . "\n"; + + print $state->{CVSROOT} . "/$module/" . ( defined ( $git->{dir} ) ? $git->{dir} . "/" : "" ) . "$git->{name}\n"; + + # this is an "entries" line + print "/$git->{name}/1.$git->{revision}///\n"; + # permissions + print "u=$git->{mode},g=$git->{mode},o=$git->{mode}\n"; + + # transmit file + transmitfile($git->{filehash}); + } + + print "ok\n"; + + statecleanup(); +} + +# update \n +# Response expected: yes. Actually do a cvs update command. This uses any +# previous Argument, Directory, Entry, or Modified requests, if they have +# been sent. The last Directory sent specifies the working directory at the +# time of the operation. The -I option is not used--files which the client +# can decide whether to ignore are not mentioned and the client sends the +# Questionable request for others. +sub req_update +{ + my ( $cmd, $data ) = @_; + + $log->debug("req_update : " . ( defined($data) ? $data : "[NULL]" )); + + argsplit("update"); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing status on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + #$log->debug("update state : " . Dumper($state)); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + # if we have a -C we should pretend we never saw modified stuff + if ( exists ( $state->{opt}{C} ) ) + { + delete $state->{entries}{$filename}{modified_hash}; + delete $state->{entries}{$filename}{modified_filename}; + $state->{entries}{$filename}{unchanged} = 1; + } + + my $meta; + if ( defined($state->{opt}{r}) and $state->{opt}{r} =~ /^1\.(\d+)/ ) + { + $meta = $updater->getmeta($filename, $1); + } else { + $meta = $updater->getmeta($filename); + } + + next unless ( $meta->{revision} ); + + my $oldmeta = $meta; + + my $wrev = revparse($filename); + + # If the working copy is an old revision, lets get that version too for comparison. + if ( defined($wrev) and $wrev != $meta->{revision} ) + { + $oldmeta = $updater->getmeta($filename, $wrev); + } + + #$log->debug("Target revision is $meta->{revision}, current working revision is $wrev"); + + # Files are up to date if the working copy and repo copy have the same revision, and the working copy is unmodified _and_ the user hasn't specified -C + next if ( defined ( $wrev ) and defined($meta->{revision}) and $wrev == $meta->{revision} and $state->{entries}{$filename}{unchanged} and not exists ( $state->{opt}{C} ) ); + + if ( $meta->{filehash} eq "deleted" ) + { + my ( $filepart, $dirpart ) = filenamesplit($filename); + + $log->info("Removing '$filename' from working copy (no longer in the repo)"); + + print "E cvs update: `$filename' is no longer in the repository\n"; + print "Removed $dirpart\n"; + print "$filepart\n"; + } + elsif ( not defined ( $state->{entries}{$filename}{modified_hash} ) or $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} ) + { + $log->info("Updating '$filename'"); + # normal update, just send the new revision (either U=Update, or A=Add, or R=Remove) + print "MT +updated\n"; + print "MT text U\n"; + print "MT fname $filename\n"; + print "MT newline\n"; + print "MT -updated\n"; + + my ( $filepart, $dirpart ) = filenamesplit($filename); + $dirpart =~ s/^$state->{directory}//; + + if ( defined ( $wrev ) ) + { + # instruct client we're sending a file to put in this path as a replacement + print "Update-existing $dirpart\n"; + $log->debug("Updating existing file 'Update-existing $dirpart'"); + } else { + # instruct client we're sending a file to put in this path as a new file + print "Created $dirpart\n"; + $log->debug("Creating new file 'Created $dirpart'"); + } + print $state->{CVSROOT} . "/$state->{module}/$filename\n"; + + # this is an "entries" line + $log->debug("/$filepart/1.$meta->{revision}///"); + print "/$filepart/1.$meta->{revision}///\n"; + + # permissions + $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}"); + print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n"; + + # transmit file + transmitfile($meta->{filehash}); + } else { + my ( $filepart, $dirpart ) = filenamesplit($meta->{name}); + + my $dir = tempdir( DIR => $TEMP_DIR, CLEANUP => 1 ) . "/"; + + chdir $dir; + my $file_local = $filepart . ".mine"; + system("ln","-s",$state->{entries}{$filename}{modified_filename}, $file_local); + my $file_old = $filepart . "." . $oldmeta->{revision}; + transmitfile($oldmeta->{filehash}, $file_old); + my $file_new = $filepart . "." . $meta->{revision}; + transmitfile($meta->{filehash}, $file_new); + + # we need to merge with the local changes ( M=successful merge, C=conflict merge ) + $log->info("Merging $file_local, $file_old, $file_new"); + + $log->debug("Temporary directory for merge is $dir"); + + my $return = system("merge", $file_local, $file_old, $file_new); + $return >>= 8; + + if ( $return == 0 ) + { + $log->info("Merged successfully"); + print "M M $filename\n"; + $log->debug("Update-existing $dirpart"); + print "Update-existing $dirpart\n"; + $log->debug($state->{CVSROOT} . "/$state->{module}/$filename"); + print $state->{CVSROOT} . "/$state->{module}/$filename\n"; + $log->debug("/$filepart/1.$meta->{revision}///"); + print "/$filepart/1.$meta->{revision}///\n"; + } + elsif ( $return == 1 ) + { + $log->info("Merged with conflicts"); + print "M C $filename\n"; + print "Update-existing $dirpart\n"; + print $state->{CVSROOT} . "/$state->{module}/$filename\n"; + print "/$filepart/1.$meta->{revision}/+//\n"; + } + else + { + $log->warn("Merge failed"); + next; + } + + # permissions + $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}"); + print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n"; + + # transmit file, format is single integer on a line by itself (file + # size) followed by the file contents + # TODO : we should copy files in blocks + my $data = `cat $file_local`; + $log->debug("File size : " . length($data)); + print length($data) . "\n"; + print $data; + + chdir "/"; + } + + } + + print "ok\n"; +} + +sub req_ci +{ + my ( $cmd, $data ) = @_; + + argsplit("ci"); + + #$log->debug("State : " . Dumper($state)); + + $log->info("req_ci : " . ( defined($data) ? $data : "[NULL]" )); + + if ( -e $state->{CVSROOT} . "/index" ) + { + print "error 1 Index already exists in git repo\n"; + exit; + } + + my $lockfile = "$state->{CVSROOT}/refs/heads/$state->{module}.lock"; + unless ( sysopen(LOCKFILE,$lockfile,O_EXCL|O_CREAT|O_WRONLY) ) + { + print "error 1 Lock file '$lockfile' already exists, please try again\n"; + exit; + } + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + my $tmpdir = tempdir ( DIR => $TEMP_DIR ); + my ( undef, $file_index ) = tempfile ( DIR => $TEMP_DIR, OPEN => 0 ); + $log->info("Lock successful, basing commit on '$tmpdir', index file is '$file_index'"); + + $ENV{GIT_DIR} = $state->{CVSROOT} . "/"; + $ENV{GIT_INDEX_FILE} = $file_index; + + chdir $tmpdir; + + # populate the temporary index based + system("git-read-tree", $state->{module}); + unless ($? == 0) + { + die "Error running git-read-tree $state->{module} $file_index $!"; + } + $log->info("Created index '$file_index' with for head $state->{module} - exit status $?"); + + + my @committedfiles = (); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + next unless ( exists $state->{entries}{$filename}{modified_filename} or not $state->{entries}{$filename}{unchanged} ); + + my $meta = $updater->getmeta($filename); + + my $wrev = revparse($filename); + + my ( $filepart, $dirpart ) = filenamesplit($filename); + + # do a checkout of the file if it part of this tree + if ($wrev) { + system('git-checkout-index', '-f', '-u', $filename); + unless ($? == 0) { + die "Error running git-checkout-index -f -u $filename : $!"; + } + } + + my $addflag = 0; + my $rmflag = 0; + $rmflag = 1 if ( defined($wrev) and $wrev < 0 ); + $addflag = 1 unless ( -e $filename ); + + # Do up to date checking + unless ( $addflag or $wrev == $meta->{revision} or ( $rmflag and -$wrev == $meta->{revision} ) ) + { + # fail everything if an up to date check fails + print "error 1 Up to date check failed for $filename\n"; + close LOCKFILE; + unlink($lockfile); + chdir "/"; + exit; + } + + push @committedfiles, $filename; + $log->info("Committing $filename"); + + system("mkdir","-p",$dirpart) unless ( -d $dirpart ); + + unless ( $rmflag ) + { + $log->debug("rename $state->{entries}{$filename}{modified_filename} $filename"); + rename $state->{entries}{$filename}{modified_filename},$filename; + + # Calculate modes to remove + my $invmode = ""; + foreach ( qw (r w x) ) { $invmode .= $_ unless ( $state->{entries}{$filename}{modified_mode} =~ /$_/ ); } + + $log->debug("chmod u+" . $state->{entries}{$filename}{modified_mode} . "-" . $invmode . " $filename"); + system("chmod","u+" . $state->{entries}{$filename}{modified_mode} . "-" . $invmode, $filename); + } + + if ( $rmflag ) + { + $log->info("Removing file '$filename'"); + unlink($filename); + system("git-update-index", "--remove", $filename); + } + elsif ( $addflag ) + { + $log->info("Adding file '$filename'"); + system("git-update-index", "--add", $filename); + } else { + $log->info("Updating file '$filename'"); + system("git-update-index", $filename); + } + } + + unless ( scalar(@committedfiles) > 0 ) + { + print "E No files to commit\n"; + print "ok\n"; + close LOCKFILE; + unlink($lockfile); + chdir "/"; + return; + } + + my $treehash = `git-write-tree`; + my $parenthash = `cat $ENV{GIT_DIR}refs/heads/$state->{module}`; + chomp $treehash; + chomp $parenthash; + + $log->debug("Treehash : $treehash, Parenthash : $parenthash"); + + # write our commit message out if we have one ... + my ( $msg_fh, $msg_filename ) = tempfile( DIR => $TEMP_DIR ); + print $msg_fh $state->{opt}{m};# if ( exists ( $state->{opt}{m} ) ); + print $msg_fh "\n\nvia git-CVS emulator\n"; + close $msg_fh; + + my $commithash = `git-commit-tree $treehash -p $parenthash < $msg_filename`; + $log->info("Commit hash : $commithash"); + + unless ( $commithash =~ /[a-zA-Z0-9]{40}/ ) + { + $log->warn("Commit failed (Invalid commit hash)"); + print "error 1 Commit failed (unknown reason)\n"; + close LOCKFILE; + unlink($lockfile); + chdir "/"; + exit; + } + + open FILE, ">", "$ENV{GIT_DIR}refs/heads/$state->{module}"; + print FILE $commithash; + close FILE; + + $updater->update(); + + # foreach file specified on the commandline ... + foreach my $filename ( @committedfiles ) + { + $filename = filecleanup($filename); + + my $meta = $updater->getmeta($filename); + + my ( $filepart, $dirpart ) = filenamesplit($filename); + + $log->debug("Checked-in $dirpart : $filename"); + + if ( $meta->{filehash} eq "deleted" ) + { + print "Remove-entry $dirpart\n"; + print "$filename\n"; + } else { + print "Checked-in $dirpart\n"; + print "$filename\n"; + print "/$filepart/1.$meta->{revision}///\n"; + } + } + + close LOCKFILE; + unlink($lockfile); + chdir "/"; + + print "ok\n"; +} + +sub req_status +{ + my ( $cmd, $data ) = @_; + + argsplit("status"); + + $log->info("req_status : " . ( defined($data) ? $data : "[NULL]" )); + #$log->debug("status state : " . Dumper($state)); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing status on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + my $meta = $updater->getmeta($filename); + my $oldmeta = $meta; + + my $wrev = revparse($filename); + + # If the working copy is an old revision, lets get that version too for comparison. + if ( defined($wrev) and $wrev != $meta->{revision} ) + { + $oldmeta = $updater->getmeta($filename, $wrev); + } + + # TODO : All possible statuses aren't yet implemented + my $status; + # Files are up to date if the working copy and repo copy have the same revision, and the working copy is unmodified + $status = "Up-to-date" if ( defined ( $wrev ) and defined($meta->{revision}) and $wrev == $meta->{revision} + and + ( ( $state->{entries}{$filename}{unchanged} and ( not defined ( $state->{entries}{$filename}{conflict} ) or $state->{entries}{$filename}{conflict} !~ /^\+=/ ) ) + or ( defined($state->{entries}{$filename}{modified_hash}) and $state->{entries}{$filename}{modified_hash} eq $meta->{filehash} ) ) + ); + + # Need checkout if the working copy has an older revision than the repo copy, and the working copy is unmodified + $status ||= "Needs Checkout" if ( defined ( $wrev ) and defined ( $meta->{revision} ) and $meta->{revision} > $wrev + and + ( $state->{entries}{$filename}{unchanged} + or ( defined($state->{entries}{$filename}{modified_hash}) and $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} ) ) + ); + + # Need checkout if it exists in the repo but doesn't have a working copy + $status ||= "Needs Checkout" if ( not defined ( $wrev ) and defined ( $meta->{revision} ) ); + + # Locally modified if working copy and repo copy have the same revision but there are local changes + $status ||= "Locally Modified" if ( defined ( $wrev ) and defined($meta->{revision}) and $wrev == $meta->{revision} and $state->{entries}{$filename}{modified_filename} ); + + # Needs Merge if working copy revision is less than repo copy and there are local changes + $status ||= "Needs Merge" if ( defined ( $wrev ) and defined ( $meta->{revision} ) and $meta->{revision} > $wrev and $state->{entries}{$filename}{modified_filename} ); + + $status ||= "Locally Added" if ( defined ( $state->{entries}{$filename}{revision} ) and not defined ( $meta->{revision} ) ); + $status ||= "Locally Removed" if ( defined ( $wrev ) and defined ( $meta->{revision} ) and -$wrev == $meta->{revision} ); + $status ||= "Unresolved Conflict" if ( defined ( $state->{entries}{$filename}{conflict} ) and $state->{entries}{$filename}{conflict} =~ /^\+=/ ); + $status ||= "File had conflicts on merge" if ( 0 ); + + $status ||= "Unknown"; + + print "M ===================================================================\n"; + print "M File: $filename\tStatus: $status\n"; + if ( defined($state->{entries}{$filename}{revision}) ) + { + print "M Working revision:\t" . $state->{entries}{$filename}{revision} . "\n"; + } else { + print "M Working revision:\tNo entry for $filename\n"; + } + if ( defined($meta->{revision}) ) + { + print "M Repository revision:\t1." . $meta->{revision} . "\t$state->{repository}/$filename,v\n"; + print "M Sticky Tag:\t\t(none)\n"; + print "M Sticky Date:\t\t(none)\n"; + print "M Sticky Options:\t\t(none)\n"; + } else { + print "M Repository revision:\tNo revision control file\n"; + } + print "M\n"; + } + + print "ok\n"; +} + +sub req_diff +{ + my ( $cmd, $data ) = @_; + + argsplit("diff"); + + $log->debug("req_diff : " . ( defined($data) ? $data : "[NULL]" )); + #$log->debug("status state : " . Dumper($state)); + + my ($revision1, $revision2); + if ( defined ( $state->{opt}{r} ) and ref $state->{opt}{r} eq "ARRAY" ) + { + $revision1 = $state->{opt}{r}[0]; + $revision2 = $state->{opt}{r}[1]; + } else { + $revision1 = $state->{opt}{r}; + } + + $revision1 =~ s/^1\.// if ( defined ( $revision1 ) ); + $revision2 =~ s/^1\.// if ( defined ( $revision2 ) ); + + $log->debug("Diffing revisions " . ( defined($revision1) ? $revision1 : "[NULL]" ) . " and " . ( defined($revision2) ? $revision2 : "[NULL]" ) ); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing status on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + my ( $fh, $file1, $file2, $meta1, $meta2, $filediff ); + + my $wrev = revparse($filename); + + # We need _something_ to diff against + next unless ( defined ( $wrev ) ); + + # if we have a -r switch, use it + if ( defined ( $revision1 ) ) + { + ( undef, $file1 ) = tempfile( DIR => $TEMP_DIR, OPEN => 0 ); + $meta1 = $updater->getmeta($filename, $revision1); + unless ( defined ( $meta1 ) and $meta1->{filehash} ne "deleted" ) + { + print "E File $filename at revision 1.$revision1 doesn't exist\n"; + next; + } + transmitfile($meta1->{filehash}, $file1); + } + # otherwise we just use the working copy revision + else + { + ( undef, $file1 ) = tempfile( DIR => $TEMP_DIR, OPEN => 0 ); + $meta1 = $updater->getmeta($filename, $wrev); + transmitfile($meta1->{filehash}, $file1); + } + + # if we have a second -r switch, use it too + if ( defined ( $revision2 ) ) + { + ( undef, $file2 ) = tempfile( DIR => $TEMP_DIR, OPEN => 0 ); + $meta2 = $updater->getmeta($filename, $revision2); + + unless ( defined ( $meta2 ) and $meta2->{filehash} ne "deleted" ) + { + print "E File $filename at revision 1.$revision2 doesn't exist\n"; + next; + } + + transmitfile($meta2->{filehash}, $file2); + } + # otherwise we just use the working copy + else + { + $file2 = $state->{entries}{$filename}{modified_filename}; + } + + # if we have been given -r, and we don't have a $file2 yet, lets get one + if ( defined ( $revision1 ) and not defined ( $file2 ) ) + { + ( undef, $file2 ) = tempfile( DIR => $TEMP_DIR, OPEN => 0 ); + $meta2 = $updater->getmeta($filename, $wrev); + transmitfile($meta2->{filehash}, $file2); + } + + # We need to have retrieved something useful + next unless ( defined ( $meta1 ) ); + + # Files to date if the working copy and repo copy have the same revision, and the working copy is unmodified + next if ( not defined ( $meta2 ) and $wrev == $meta1->{revision} + and + ( ( $state->{entries}{$filename}{unchanged} and ( not defined ( $state->{entries}{$filename}{conflict} ) or $state->{entries}{$filename}{conflict} !~ /^\+=/ ) ) + or ( defined($state->{entries}{$filename}{modified_hash}) and $state->{entries}{$filename}{modified_hash} eq $meta1->{filehash} ) ) + ); + + # Apparently we only show diffs for locally modified files + next unless ( defined($meta2) or defined ( $state->{entries}{$filename}{modified_filename} ) ); + + print "M Index: $filename\n"; + print "M ===================================================================\n"; + print "M RCS file: $state->{CVSROOT}/$state->{module}/$filename,v\n"; + print "M retrieving revision 1.$meta1->{revision}\n" if ( defined ( $meta1 ) ); + print "M retrieving revision 1.$meta2->{revision}\n" if ( defined ( $meta2 ) ); + print "M diff "; + foreach my $opt ( keys %{$state->{opt}} ) + { + if ( ref $state->{opt}{$opt} eq "ARRAY" ) + { + foreach my $value ( @{$state->{opt}{$opt}} ) + { + print "-$opt $value "; + } + } else { + print "-$opt "; + print "$state->{opt}{$opt} " if ( defined ( $state->{opt}{$opt} ) ); + } + } + print "$filename\n"; + + $log->info("Diffing $filename -r $meta1->{revision} -r " . ( $meta2->{revision} or "workingcopy" )); + + ( $fh, $filediff ) = tempfile ( DIR => $TEMP_DIR ); + + if ( exists $state->{opt}{u} ) + { + system("diff -u -L '$filename revision 1.$meta1->{revision}' -L '$filename " . ( defined($meta2->{revision}) ? "revision 1.$meta2->{revision}" : "working copy" ) . "' $file1 $file2 > $filediff"); + } else { + system("diff $file1 $file2 > $filediff"); + } + + while ( <$fh> ) + { + print "M $_"; + } + close $fh; + } + + print "ok\n"; +} + +sub req_log +{ + my ( $cmd, $data ) = @_; + + argsplit("log"); + + $log->debug("req_log : " . ( defined($data) ? $data : "[NULL]" )); + #$log->debug("log state : " . Dumper($state)); + + my ( $minrev, $maxrev ); + if ( defined ( $state->{opt}{r} ) and $state->{opt}{r} =~ /([\d.]+)?(::?)([\d.]+)?/ ) + { + my $control = $2; + $minrev = $1; + $maxrev = $3; + $minrev =~ s/^1\.// if ( defined ( $minrev ) ); + $maxrev =~ s/^1\.// if ( defined ( $maxrev ) ); + $minrev++ if ( defined($minrev) and $control eq "::" ); + } + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing status on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + my $headmeta = $updater->getmeta($filename); + + my $revisions = $updater->getlog($filename); + my $totalrevisions = scalar(@$revisions); + + if ( defined ( $minrev ) ) + { + $log->debug("Removing revisions less than $minrev"); + while ( scalar(@$revisions) > 0 and $revisions->[-1]{revision} < $minrev ) + { + pop @$revisions; + } + } + if ( defined ( $maxrev ) ) + { + $log->debug("Removing revisions greater than $maxrev"); + while ( scalar(@$revisions) > 0 and $revisions->[0]{revision} > $maxrev ) + { + shift @$revisions; + } + } + + next unless ( scalar(@$revisions) ); + + print "M \n"; + print "M RCS file: $state->{CVSROOT}/$state->{module}/$filename,v\n"; + print "M Working file: $filename\n"; + print "M head: 1.$headmeta->{revision}\n"; + print "M branch:\n"; + print "M locks: strict\n"; + print "M access list:\n"; + print "M symbolic names:\n"; + print "M keyword substitution: kv\n"; + print "M total revisions: $totalrevisions;\tselected revisions: " . scalar(@$revisions) . "\n"; + print "M description:\n"; + + foreach my $revision ( @$revisions ) + { + print "M ----------------------------\n"; + print "M revision 1.$revision->{revision}\n"; + # reformat the date for log output + $revision->{modified} = sprintf('%04d/%02d/%02d %s', $3, $DATE_LIST->{$2}, $1, $4 ) if ( $revision->{modified} =~ /(\d+)\s+(\w+)\s+(\d+)\s+(\S+)/ and defined($DATE_LIST->{$2}) ); + $revision->{author} =~ s/\s+.*//; + $revision->{author} =~ s/^(.{8}).*/$1/; + print "M date: $revision->{modified}; author: $revision->{author}; state: " . ( $revision->{filehash} eq "deleted" ? "dead" : "Exp" ) . "; lines: +2 -3\n"; + my $commitmessage = $updater->commitmessage($revision->{commithash}); + $commitmessage =~ s/^/M /mg; + print $commitmessage . "\n"; + } + print "M =============================================================================\n"; + } + + print "ok\n"; +} + +sub req_annotate +{ + my ( $cmd, $data ) = @_; + + argsplit("annotate"); + + $log->info("req_annotate : " . ( defined($data) ? $data : "[NULL]" )); + #$log->debug("status state : " . Dumper($state)); + + # Grab a handle to the SQLite db and do any necessary updates + my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log); + $updater->update(); + + # if no files were specified, we need to work out what files we should be providing annotate on ... + argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 ); + + # we'll need a temporary checkout dir + my $tmpdir = tempdir ( DIR => $TEMP_DIR ); + my ( undef, $file_index ) = tempfile ( DIR => $TEMP_DIR, OPEN => 0 ); + $log->info("Temp checkoutdir creation successful, basing annotate session work on '$tmpdir', index file is '$file_index'"); + + $ENV{GIT_DIR} = $state->{CVSROOT} . "/"; + $ENV{GIT_INDEX_FILE} = $file_index; + + chdir $tmpdir; + + # foreach file specified on the commandline ... + foreach my $filename ( @{$state->{args}} ) + { + $filename = filecleanup($filename); + + my $meta = $updater->getmeta($filename); + + next unless ( $meta->{revision} ); + + # get all the commits that this file was in + # in dense format -- aka skip dead revisions + my $revisions = $updater->gethistorydense($filename); + my $lastseenin = $revisions->[0][2]; + + # populate the temporary index based on the latest commit were we saw + # the file -- but do it cheaply without checking out any files + # TODO: if we got a revision from the client, use that instead + # to look up the commithash in sqlite (still good to default to + # the current head as we do now) + system("git-read-tree", $lastseenin); + unless ($? == 0) + { + die "Error running git-read-tree $lastseenin $file_index $!"; + } + $log->info("Created index '$file_index' with commit $lastseenin - exit status $?"); + + # do a checkout of the file + system('git-checkout-index', '-f', '-u', $filename); + unless ($? == 0) { + die "Error running git-checkout-index -f -u $filename : $!"; + } + + $log->info("Annotate $filename"); + + # Prepare a file with the commits from the linearized + # history that annotate should know about. This prevents + # git-jsannotate telling us about commits we are hiding + # from the client. + + open(ANNOTATEHINTS, ">$tmpdir/.annotate_hints") or die "Error opening > $tmpdir/.annotate_hints $!"; + for (my $i=0; $i < @$revisions; $i++) + { + print ANNOTATEHINTS $revisions->[$i][2]; + if ($i+1 < @$revisions) { # have we got a parent? + print ANNOTATEHINTS ' ' . $revisions->[$i+1][2]; + } + print ANNOTATEHINTS "\n"; + } + + print ANNOTATEHINTS "\n"; + close ANNOTATEHINTS; + + my $annotatecmd = 'git-annotate'; + open(ANNOTATE, "-|", $annotatecmd, '-l', '-S', "$tmpdir/.annotate_hints", $filename) + or die "Error invoking $annotatecmd -l -S $tmpdir/.annotate_hints $filename : $!"; + my $metadata = {}; + print "E Annotations for $filename\n"; + print "E ***************\n"; + while ( <ANNOTATE> ) + { + if (m/^([a-zA-Z0-9]{40})\t\([^\)]*\)(.*)$/i) + { + my $commithash = $1; + my $data = $2; + unless ( defined ( $metadata->{$commithash} ) ) + { + $metadata->{$commithash} = $updater->getmeta($filename, $commithash); + $metadata->{$commithash}{author} =~ s/\s+.*//; + $metadata->{$commithash}{author} =~ s/^(.{8}).*/$1/; + $metadata->{$commithash}{modified} = sprintf("%02d-%s-%02d", $1, $2, $3) if ( $metadata->{$commithash}{modified} =~ /^(\d+)\s(\w+)\s\d\d(\d\d)/ ); + } + printf("M 1.%-5d (%-8s %10s): %s\n", + $metadata->{$commithash}{revision}, + $metadata->{$commithash}{author}, + $metadata->{$commithash}{modified}, + $data + ); + } else { + $log->warn("Error in annotate output! LINE: $_"); + print "E Annotate error \n"; + next; + } + } + close ANNOTATE; + } + + # done; get out of the tempdir + chdir "/"; + + print "ok\n"; + +} + +# This method takes the state->{arguments} array and produces two new arrays. +# The first is $state->{args} which is everything before the '--' argument, and +# the second is $state->{files} which is everything after it. +sub argsplit +{ + return unless( defined($state->{arguments}) and ref $state->{arguments} eq "ARRAY" ); + + my $type = shift; + + $state->{args} = []; + $state->{files} = []; + $state->{opt} = {}; + + if ( defined($type) ) + { + my $opt = {}; + $opt = { A => 0, N => 0, P => 0, R => 0, c => 0, f => 0, l => 0, n => 0, p => 0, s => 0, r => 1, D => 1, d => 1, k => 1, j => 1, } if ( $type eq "co" ); + $opt = { v => 0, l => 0, R => 0 } if ( $type eq "status" ); + $opt = { A => 0, P => 0, C => 0, d => 0, f => 0, l => 0, R => 0, p => 0, k => 1, r => 1, D => 1, j => 1, I => 1, W => 1 } if ( $type eq "update" ); + $opt = { l => 0, R => 0, k => 1, D => 1, D => 1, r => 2 } if ( $type eq "diff" ); + $opt = { c => 0, R => 0, l => 0, f => 0, F => 1, m => 1, r => 1 } if ( $type eq "ci" ); + $opt = { k => 1, m => 1 } if ( $type eq "add" ); + $opt = { f => 0, l => 0, R => 0 } if ( $type eq "remove" ); + $opt = { l => 0, b => 0, h => 0, R => 0, t => 0, N => 0, S => 0, r => 1, d => 1, s => 1, w => 1 } if ( $type eq "log" ); + + + while ( scalar ( @{$state->{arguments}} ) > 0 ) + { + my $arg = shift @{$state->{arguments}}; + + next if ( $arg eq "--" ); + next unless ( $arg =~ /\S/ ); + + # if the argument looks like a switch + if ( $arg =~ /^-(\w)(.*)/ ) + { + # if it's a switch that takes an argument + if ( $opt->{$1} ) + { + # If this switch has already been provided + if ( $opt->{$1} > 1 and exists ( $state->{opt}{$1} ) ) + { + $state->{opt}{$1} = [ $state->{opt}{$1} ]; + if ( length($2) > 0 ) + { + push @{$state->{opt}{$1}},$2; + } else { + push @{$state->{opt}{$1}}, shift @{$state->{arguments}}; + } + } else { + # if there's extra data in the arg, use that as the argument for the switch + if ( length($2) > 0 ) + { + $state->{opt}{$1} = $2; + } else { + $state->{opt}{$1} = shift @{$state->{arguments}}; + } + } + } else { + $state->{opt}{$1} = undef; + } + } + else + { + push @{$state->{args}}, $arg; + } + } + } + else + { + my $mode = 0; + + foreach my $value ( @{$state->{arguments}} ) + { + if ( $value eq "--" ) + { + $mode++; + next; + } + push @{$state->{args}}, $value if ( $mode == 0 ); + push @{$state->{files}}, $value if ( $mode == 1 ); + } + } +} + +# This method uses $state->{directory} to populate $state->{args} with a list of filenames +sub argsfromdir +{ + my $updater = shift; + + $state->{args} = []; + + foreach my $file ( @{$updater->gethead} ) + { + next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) ); + next unless ( $file->{name} =~ s/^$state->{directory}// ); + push @{$state->{args}}, $file->{name}; + } +} + +# This method cleans up the $state variable after a command that uses arguments has run +sub statecleanup +{ + $state->{files} = []; + $state->{args} = []; + $state->{arguments} = []; + $state->{entries} = {}; +} + +sub revparse +{ + my $filename = shift; + + return undef unless ( defined ( $state->{entries}{$filename}{revision} ) ); + + return $1 if ( $state->{entries}{$filename}{revision} =~ /^1\.(\d+)/ ); + return -$1 if ( $state->{entries}{$filename}{revision} =~ /^-1\.(\d+)/ ); + + return undef; +} + +# This method takes a file hash and does a CVS "file transfer" which transmits the +# size of the file, and then the file contents. +# If a second argument $targetfile is given, the file is instead written out to +# a file by the name of $targetfile +sub transmitfile +{ + my $filehash = shift; + my $targetfile = shift; + + if ( defined ( $filehash ) and $filehash eq "deleted" ) + { + $log->warn("filehash is 'deleted'"); + return; + } + + die "Need filehash" unless ( defined ( $filehash ) and $filehash =~ /^[a-zA-Z0-9]{40}$/ ); + + my $type = `git-cat-file -t $filehash`; + chomp $type; + + die ( "Invalid type '$type' (expected 'blob')" ) unless ( defined ( $type ) and $type eq "blob" ); + + my $size = `git-cat-file -s $filehash`; + chomp $size; + + $log->debug("transmitfile($filehash) size=$size, type=$type"); + + if ( open my $fh, '-|', "git-cat-file", "blob", $filehash ) + { + if ( defined ( $targetfile ) ) + { + open NEWFILE, ">", $targetfile or die("Couldn't open '$targetfile' for writing : $!"); + print NEWFILE $_ while ( <$fh> ); + close NEWFILE; + } else { + print "$size\n"; + print while ( <$fh> ); + } + close $fh or die ("Couldn't close filehandle for transmitfile()"); + } else { + die("Couldn't execute git-cat-file"); + } +} + +# This method takes a file name, and returns ( $dirpart, $filepart ) which +# refers to the directory porition and the file portion of the filename +# respectively +sub filenamesplit +{ + my $filename = shift; + + my ( $filepart, $dirpart ) = ( $filename, "." ); + ( $filepart, $dirpart ) = ( $2, $1 ) if ( $filename =~ /(.*)\/(.*)/ ); + $dirpart .= "/"; + + return ( $filepart, $dirpart ); +} + +sub filecleanup +{ + my $filename = shift; + + return undef unless(defined($filename)); + if ( $filename =~ /^\// ) + { + print "E absolute filenames '$filename' not supported by server\n"; + return undef; + } + + $filename =~ s/^\.\///g; + $filename = $state->{directory} . $filename; + + return $filename; +} + +package GITCVS::log; + +#### +#### Copyright The Open University UK - 2006. +#### +#### Authors: Martyn Smith <martyn@catalyst.net.nz> +#### Martin Langhoff <martin@catalyst.net.nz> +#### +#### + +use strict; +use warnings; + +=head1 NAME + +GITCVS::log + +=head1 DESCRIPTION + +This module provides very crude logging with a similar interface to +Log::Log4perl + +=head1 METHODS + +=cut + +=head2 new + +Creates a new log object, optionally you can specify a filename here to +indicate the file to log to. If no log file is specified, you can specifiy one +later with method setfile, or indicate you no longer want logging with method +nofile. + +Until one of these methods is called, all log calls will buffer messages ready +to write out. + +=cut +sub new +{ + my $class = shift; + my $filename = shift; + + my $self = {}; + + bless $self, $class; + + if ( defined ( $filename ) ) + { + open $self->{fh}, ">>", $filename or die("Couldn't open '$filename' for writing : $!"); + } + + return $self; +} + +=head2 setfile + +This methods takes a filename, and attempts to open that file as the log file. +If successful, all buffered data is written out to the file, and any further +logging is written directly to the file. + +=cut +sub setfile +{ + my $self = shift; + my $filename = shift; + + if ( defined ( $filename ) ) + { + open $self->{fh}, ">>", $filename or die("Couldn't open '$filename' for writing : $!"); + } + + return unless ( defined ( $self->{buffer} ) and ref $self->{buffer} eq "ARRAY" ); + + while ( my $line = shift @{$self->{buffer}} ) + { + print {$self->{fh}} $line; + } +} + +=head2 nofile + +This method indicates no logging is going to be used. It flushes any entries in +the internal buffer, and sets a flag to ensure no further data is put there. + +=cut +sub nofile +{ + my $self = shift; + + $self->{nolog} = 1; + + return unless ( defined ( $self->{buffer} ) and ref $self->{buffer} eq "ARRAY" ); + + $self->{buffer} = []; +} + +=head2 _logopen + +Internal method. Returns true if the log file is open, false otherwise. + +=cut +sub _logopen +{ + my $self = shift; + + return 1 if ( defined ( $self->{fh} ) and ref $self->{fh} eq "GLOB" ); + return 0; +} + +=head2 debug info warn fatal + +These four methods are wrappers to _log. They provide the actual interface for +logging data. + +=cut +sub debug { my $self = shift; $self->_log("debug", @_); } +sub info { my $self = shift; $self->_log("info" , @_); } +sub warn { my $self = shift; $self->_log("warn" , @_); } +sub fatal { my $self = shift; $self->_log("fatal", @_); } + +=head2 _log + +This is an internal method called by the logging functions. It generates a +timestamp and pushes the logged line either to file, or internal buffer. + +=cut +sub _log +{ + my $self = shift; + my $level = shift; + + return if ( $self->{nolog} ); + + my @time = localtime; + my $timestring = sprintf("%4d-%02d-%02d %02d:%02d:%02d : %-5s", + $time[5] + 1900, + $time[4] + 1, + $time[3], + $time[2], + $time[1], + $time[0], + uc $level, + ); + + if ( $self->_logopen ) + { + print {$self->{fh}} $timestring . " - " . join(" ",@_) . "\n"; + } else { + push @{$self->{buffer}}, $timestring . " - " . join(" ",@_) . "\n"; + } +} + +=head2 DESTROY + +This method simply closes the file handle if one is open + +=cut +sub DESTROY +{ + my $self = shift; + + if ( $self->_logopen ) + { + close $self->{fh}; + } +} + +package GITCVS::updater; + +#### +#### Copyright The Open University UK - 2006. +#### +#### Authors: Martyn Smith <martyn@catalyst.net.nz> +#### Martin Langhoff <martin@catalyst.net.nz> +#### +#### + +use strict; +use warnings; +use DBI; + +=head1 METHODS + +=cut + +=head2 new + +=cut +sub new +{ + my $class = shift; + my $config = shift; + my $module = shift; + my $log = shift; + + die "Need to specify a git repository" unless ( defined($config) and -d $config ); + die "Need to specify a module" unless ( defined($module) ); + + $class = ref($class) || $class; + + my $self = {}; + + bless $self, $class; + + $self->{dbdir} = $config . "/"; + die "Database dir '$self->{dbdir}' isn't a directory" unless ( defined($self->{dbdir}) and -d $self->{dbdir} ); + + $self->{module} = $module; + $self->{file} = $self->{dbdir} . "/gitcvs.$module.sqlite"; + + $self->{git_path} = $config . "/"; + + $self->{log} = $log; + + die "Git repo '$self->{git_path}' doesn't exist" unless ( -d $self->{git_path} ); + + $self->{dbh} = DBI->connect("dbi:SQLite:dbname=" . $self->{file},"",""); + + $self->{tables} = {}; + foreach my $table ( $self->{dbh}->tables ) + { + $table =~ s/^"//; + $table =~ s/"$//; + $self->{tables}{$table} = 1; + } + + # Construct the revision table if required + unless ( $self->{tables}{revision} ) + { + $self->{dbh}->do(" + CREATE TABLE revision ( + name TEXT NOT NULL, + revision INTEGER NOT NULL, + filehash TEXT NOT NULL, + commithash TEXT NOT NULL, + author TEXT NOT NULL, + modified TEXT NOT NULL, + mode TEXT NOT NULL + ) + "); + } + + # Construct the revision table if required + unless ( $self->{tables}{head} ) + { + $self->{dbh}->do(" + CREATE TABLE head ( + name TEXT NOT NULL, + revision INTEGER NOT NULL, + filehash TEXT NOT NULL, + commithash TEXT NOT NULL, + author TEXT NOT NULL, + modified TEXT NOT NULL, + mode TEXT NOT NULL + ) + "); + } + + # Construct the properties table if required + unless ( $self->{tables}{properties} ) + { + $self->{dbh}->do(" + CREATE TABLE properties ( + key TEXT NOT NULL PRIMARY KEY, + value TEXT + ) + "); + } + + # Construct the commitmsgs table if required + unless ( $self->{tables}{commitmsgs} ) + { + $self->{dbh}->do(" + CREATE TABLE commitmsgs ( + key TEXT NOT NULL PRIMARY KEY, + value TEXT + ) + "); + } + + return $self; +} + +=head2 update + +=cut +sub update +{ + my $self = shift; + + # first lets get the commit list + $ENV{GIT_DIR} = $self->{git_path}; + + # prepare database queries + my $db_insert_rev = $self->{dbh}->prepare_cached("INSERT INTO revision (name, revision, filehash, commithash, modified, author, mode) VALUES (?,?,?,?,?,?,?)",{},1); + my $db_insert_mergelog = $self->{dbh}->prepare_cached("INSERT INTO commitmsgs (key, value) VALUES (?,?)",{},1); + my $db_delete_head = $self->{dbh}->prepare_cached("DELETE FROM head",{},1); + my $db_insert_head = $self->{dbh}->prepare_cached("INSERT INTO head (name, revision, filehash, commithash, modified, author, mode) VALUES (?,?,?,?,?,?,?)",{},1); + + my $commitinfo = `git-cat-file commit $self->{module} 2>&1`; + unless ( $commitinfo =~ /tree\s+[a-zA-Z0-9]{40}/ ) + { + die("Invalid module '$self->{module}'"); + } + + + my $git_log; + my $lastcommit = $self->_get_prop("last_commit"); + + # Start exclusive lock here... + $self->{dbh}->begin_work() or die "Cannot lock database for BEGIN"; + + # TODO: log processing is memory bound + # if we can parse into a 2nd file that is in reverse order + # we can probably do something really efficient + my @git_log_params = ('--parents', '--topo-order'); + + if (defined $lastcommit) { + push @git_log_params, "$lastcommit..$self->{module}"; + } else { + push @git_log_params, $self->{module}; + } + open(GITLOG, '-|', 'git-log', @git_log_params) or die "Cannot call git-log: $!"; + + my @commits; + + my %commit = (); + + while ( <GITLOG> ) + { + chomp; + if (m/^commit\s+(.*)$/) { + # on ^commit lines put the just seen commit in the stack + # and prime things for the next one + if (keys %commit) { + my %copy = %commit; + unshift @commits, \%copy; + %commit = (); + } + my @parents = split(m/\s+/, $1); + $commit{hash} = shift @parents; + $commit{parents} = \@parents; + } elsif (m/^(\w+?):\s+(.*)$/ && !exists($commit{message})) { + # on rfc822-like lines seen before we see any message, + # lowercase the entry and put it in the hash as key-value + $commit{lc($1)} = $2; + } else { + # message lines - skip initial empty line + # and trim whitespace + if (!exists($commit{message}) && m/^\s*$/) { + # define it to mark the end of headers + $commit{message} = ''; + next; + } + s/^\s+//; s/\s+$//; # trim ws + $commit{message} .= $_ . "\n"; + } + } + close GITLOG; + + unshift @commits, \%commit if ( keys %commit ); + + # Now all the commits are in the @commits bucket + # ordered by time DESC. for each commit that needs processing, + # determine whether it's following the last head we've seen or if + # it's on its own branch, grab a file list, and add whatever's changed + # NOTE: $lastcommit refers to the last commit from previous run + # $lastpicked is the last commit we picked in this run + my $lastpicked; + my $head = {}; + if (defined $lastcommit) { + $lastpicked = $lastcommit; + } + + my $committotal = scalar(@commits); + my $commitcount = 0; + + # Load the head table into $head (for cached lookups during the update process) + foreach my $file ( @{$self->gethead()} ) + { + $head->{$file->{name}} = $file; + } + + foreach my $commit ( @commits ) + { + $self->{log}->debug("GITCVS::updater - Processing commit $commit->{hash} (" . (++$commitcount) . " of $committotal)"); + if (defined $lastpicked) + { + if (!in_array($lastpicked, @{$commit->{parents}})) + { + # skip, we'll see this delta + # as part of a merge later + # warn "skipping off-track $commit->{hash}\n"; + next; + } elsif (@{$commit->{parents}} > 1) { + # it is a merge commit, for each parent that is + # not $lastpicked, see if we can get a log + # from the merge-base to that parent to put it + # in the message as a merge summary. + my @parents = @{$commit->{parents}}; + foreach my $parent (@parents) { + # git-merge-base can potentially (but rarely) throw + # several candidate merge bases. let's assume + # that the first one is the best one. + if ($parent eq $lastpicked) { + next; + } + open my $p, 'git-merge-base '. $lastpicked . ' ' + . $parent . '|'; + my @output = (<$p>); + close $p; + my $base = join('', @output); + chomp $base; + if ($base) { + my @merged; + # print "want to log between $base $parent \n"; + open(GITLOG, '-|', 'git-log', "$base..$parent") + or die "Cannot call git-log: $!"; + my $mergedhash; + while (<GITLOG>) { + chomp; + if (!defined $mergedhash) { + if (m/^commit\s+(.+)$/) { + $mergedhash = $1; + } else { + next; + } + } else { + # grab the first line that looks non-rfc822 + # aka has content after leading space + if (m/^\s+(\S.*)$/) { + my $title = $1; + $title = substr($title,0,100); # truncate + unshift @merged, "$mergedhash $title"; + undef $mergedhash; + } + } + } + close GITLOG; + if (@merged) { + $commit->{mergemsg} = $commit->{message}; + $commit->{mergemsg} .= "\nSummary of merged commits:\n\n"; + foreach my $summary (@merged) { + $commit->{mergemsg} .= "\t$summary\n"; + } + $commit->{mergemsg} .= "\n\n"; + # print "Message for $commit->{hash} \n$commit->{mergemsg}"; + } + } + } + } + } + + # convert the date to CVS-happy format + $commit->{date} = "$2 $1 $4 $3 $5" if ( $commit->{date} =~ /^\w+\s+(\w+)\s+(\d+)\s+(\d+:\d+:\d+)\s+(\d+)\s+([+-]\d+)$/ ); + + if ( defined ( $lastpicked ) ) + { + my $filepipe = open(FILELIST, '-|', 'git-diff-tree', '-r', $lastpicked, $commit->{hash}) or die("Cannot call git-diff-tree : $!"); + while ( <FILELIST> ) + { + unless ( /^:\d{6}\s+\d{3}(\d)\d{2}\s+[a-zA-Z0-9]{40}\s+([a-zA-Z0-9]{40})\s+(\w)\s+(.*)$/o ) + { + die("Couldn't process git-diff-tree line : $_"); + } + + # $log->debug("File mode=$1, hash=$2, change=$3, name=$4"); + + my $git_perms = ""; + $git_perms .= "r" if ( $1 & 4 ); + $git_perms .= "w" if ( $1 & 2 ); + $git_perms .= "x" if ( $1 & 1 ); + $git_perms = "rw" if ( $git_perms eq "" ); + + if ( $3 eq "D" ) + { + #$log->debug("DELETE $4"); + $head->{$4} = { + name => $4, + revision => $head->{$4}{revision} + 1, + filehash => "deleted", + commithash => $commit->{hash}, + modified => $commit->{date}, + author => $commit->{author}, + mode => $git_perms, + }; + $db_insert_rev->execute($4, $head->{$4}{revision}, $2, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + } + elsif ( $3 eq "M" ) + { + #$log->debug("MODIFIED $4"); + $head->{$4} = { + name => $4, + revision => $head->{$4}{revision} + 1, + filehash => $2, + commithash => $commit->{hash}, + modified => $commit->{date}, + author => $commit->{author}, + mode => $git_perms, + }; + $db_insert_rev->execute($4, $head->{$4}{revision}, $2, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + } + elsif ( $3 eq "A" ) + { + #$log->debug("ADDED $4"); + $head->{$4} = { + name => $4, + revision => 1, + filehash => $2, + commithash => $commit->{hash}, + modified => $commit->{date}, + author => $commit->{author}, + mode => $git_perms, + }; + $db_insert_rev->execute($4, $head->{$4}{revision}, $2, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + } + else + { + $log->warn("UNKNOWN FILE CHANGE mode=$1, hash=$2, change=$3, name=$4"); + die; + } + } + close FILELIST; + } else { + # this is used to detect files removed from the repo + my $seen_files = {}; + + my $filepipe = open(FILELIST, '-|', 'git-ls-tree', '-r', $commit->{hash}) or die("Cannot call git-ls-tree : $!"); + while ( <FILELIST> ) + { + unless ( /^(\d+)\s+(\w+)\s+([a-zA-Z0-9]+)\s+(.*)$/o ) + { + die("Couldn't process git-ls-tree line : $_"); + } + + my ( $git_perms, $git_type, $git_hash, $git_filename ) = ( $1, $2, $3, $4 ); + + $seen_files->{$git_filename} = 1; + + my ( $oldhash, $oldrevision, $oldmode ) = ( + $head->{$git_filename}{filehash}, + $head->{$git_filename}{revision}, + $head->{$git_filename}{mode} + ); + + if ( $git_perms =~ /^\d\d\d(\d)\d\d/o ) + { + $git_perms = ""; + $git_perms .= "r" if ( $1 & 4 ); + $git_perms .= "w" if ( $1 & 2 ); + $git_perms .= "x" if ( $1 & 1 ); + } else { + $git_perms = "rw"; + } + + # unless the file exists with the same hash, we need to update it ... + unless ( defined($oldhash) and $oldhash eq $git_hash and defined($oldmode) and $oldmode eq $git_perms ) + { + my $newrevision = ( $oldrevision or 0 ) + 1; + + $head->{$git_filename} = { + name => $git_filename, + revision => $newrevision, + filehash => $git_hash, + commithash => $commit->{hash}, + modified => $commit->{date}, + author => $commit->{author}, + mode => $git_perms, + }; + + + $db_insert_rev->execute($git_filename, $newrevision, $git_hash, $commit->{hash}, $commit->{date}, $commit->{author}, $git_perms); + } + } + close FILELIST; + + # Detect deleted files + foreach my $file ( keys %$head ) + { + unless ( exists $seen_files->{$file} or $head->{$file}{filehash} eq "deleted" ) + { + $head->{$file}{revision}++; + $head->{$file}{filehash} = "deleted"; + $head->{$file}{commithash} = $commit->{hash}; + $head->{$file}{modified} = $commit->{date}; + $head->{$file}{author} = $commit->{author}; + + $db_insert_rev->execute($file, $head->{$file}{revision}, $head->{$file}{filehash}, $commit->{hash}, $commit->{date}, $commit->{author}, $head->{$file}{mode}); + } + } + # END : "Detect deleted files" + } + + + if (exists $commit->{mergemsg}) + { + $db_insert_mergelog->execute($commit->{hash}, $commit->{mergemsg}); + } + + $lastpicked = $commit->{hash}; + + $self->_set_prop("last_commit", $commit->{hash}); + } + + $db_delete_head->execute(); + foreach my $file ( keys %$head ) + { + $db_insert_head->execute( + $file, + $head->{$file}{revision}, + $head->{$file}{filehash}, + $head->{$file}{commithash}, + $head->{$file}{modified}, + $head->{$file}{author}, + $head->{$file}{mode}, + ); + } + # invalidate the gethead cache + $self->{gethead_cache} = undef; + + + # Ending exclusive lock here + $self->{dbh}->commit() or die "Failed to commit changes to SQLite"; +} + +sub _headrev +{ + my $self = shift; + my $filename = shift; + + my $db_query = $self->{dbh}->prepare_cached("SELECT filehash, revision, mode FROM head WHERE name=?",{},1); + $db_query->execute($filename); + my ( $hash, $revision, $mode ) = $db_query->fetchrow_array; + + return ( $hash, $revision, $mode ); +} + +sub _get_prop +{ + my $self = shift; + my $key = shift; + + my $db_query = $self->{dbh}->prepare_cached("SELECT value FROM properties WHERE key=?",{},1); + $db_query->execute($key); + my ( $value ) = $db_query->fetchrow_array; + + return $value; +} + +sub _set_prop +{ + my $self = shift; + my $key = shift; + my $value = shift; + + my $db_query = $self->{dbh}->prepare_cached("UPDATE properties SET value=? WHERE key=?",{},1); + $db_query->execute($value, $key); + + unless ( $db_query->rows ) + { + $db_query = $self->{dbh}->prepare_cached("INSERT INTO properties (key, value) VALUES (?,?)",{},1); + $db_query->execute($key, $value); + } + + return $value; +} + +=head2 gethead + +=cut + +sub gethead +{ + my $self = shift; + + return $self->{gethead_cache} if ( defined ( $self->{gethead_cache} ) ); + + my $db_query = $self->{dbh}->prepare_cached("SELECT name, filehash, mode, revision, modified, commithash, author FROM head",{},1); + $db_query->execute(); + + my $tree = []; + while ( my $file = $db_query->fetchrow_hashref ) + { + push @$tree, $file; + } + + $self->{gethead_cache} = $tree; + + return $tree; +} + +=head2 getlog + +=cut + +sub getlog +{ + my $self = shift; + my $filename = shift; + + my $db_query = $self->{dbh}->prepare_cached("SELECT name, filehash, author, mode, revision, modified, commithash FROM revision WHERE name=? ORDER BY revision DESC",{},1); + $db_query->execute($filename); + + my $tree = []; + while ( my $file = $db_query->fetchrow_hashref ) + { + push @$tree, $file; + } + + return $tree; +} + +=head2 getmeta + +This function takes a filename (with path) argument and returns a hashref of +metadata for that file. + +=cut + +sub getmeta +{ + my $self = shift; + my $filename = shift; + my $revision = shift; + + my $db_query; + if ( defined($revision) and $revision =~ /^\d+$/ ) + { + $db_query = $self->{dbh}->prepare_cached("SELECT * FROM revision WHERE name=? AND revision=?",{},1); + $db_query->execute($filename, $revision); + } + elsif ( defined($revision) and $revision =~ /^[a-zA-Z0-9]{40}$/ ) + { + $db_query = $self->{dbh}->prepare_cached("SELECT * FROM revision WHERE name=? AND commithash=?",{},1); + $db_query->execute($filename, $revision); + } else { + $db_query = $self->{dbh}->prepare_cached("SELECT * FROM head WHERE name=?",{},1); + $db_query->execute($filename); + } + + return $db_query->fetchrow_hashref; +} + +=head2 commitmessage + +this function takes a commithash and returns the commit message for that commit + +=cut +sub commitmessage +{ + my $self = shift; + my $commithash = shift; + + die("Need commithash") unless ( defined($commithash) and $commithash =~ /^[a-zA-Z0-9]{40}$/ ); + + my $db_query; + $db_query = $self->{dbh}->prepare_cached("SELECT value FROM commitmsgs WHERE key=?",{},1); + $db_query->execute($commithash); + + my ( $message ) = $db_query->fetchrow_array; + + if ( defined ( $message ) ) + { + $message .= " " if ( $message =~ /\n$/ ); + return $message; + } + + my @lines = safe_pipe_capture("git-cat-file", "commit", $commithash); + shift @lines while ( $lines[0] =~ /\S/ ); + $message = join("",@lines); + $message .= " " if ( $message =~ /\n$/ ); + return $message; +} + +=head2 gethistory + +This function takes a filename (with path) argument and returns an arrayofarrays +containing revision,filehash,commithash ordered by revision descending + +=cut +sub gethistory +{ + my $self = shift; + my $filename = shift; + + my $db_query; + $db_query = $self->{dbh}->prepare_cached("SELECT revision, filehash, commithash FROM revision WHERE name=? ORDER BY revision DESC",{},1); + $db_query->execute($filename); + + return $db_query->fetchall_arrayref; +} + +=head2 gethistorydense + +This function takes a filename (with path) argument and returns an arrayofarrays +containing revision,filehash,commithash ordered by revision descending. + +This version of gethistory skips deleted entries -- so it is useful for annotate. +The 'dense' part is a reference to a '--dense' option available for git-rev-list +and other git tools that depend on it. + +=cut +sub gethistorydense +{ + my $self = shift; + my $filename = shift; + + my $db_query; + $db_query = $self->{dbh}->prepare_cached("SELECT revision, filehash, commithash FROM revision WHERE name=? AND filehash!='deleted' ORDER BY revision DESC",{},1); + $db_query->execute($filename); + + return $db_query->fetchall_arrayref; +} + +=head2 in_array() + +from Array::PAT - mimics the in_array() function +found in PHP. Yuck but works for small arrays. + +=cut +sub in_array +{ + my ($check, @array) = @_; + my $retval = 0; + foreach my $test (@array){ + if($check eq $test){ + $retval = 1; + } + } + return $retval; +} + +=head2 safe_pipe_capture + +an alterative to `command` that allows input to be passed as an array +to work around shell problems with weird characters in arguments + +=cut +sub safe_pipe_capture { + + my @output; + + if (my $pid = open my $child, '-|') { + @output = (<$child>); + close $child or die join(' ',@_).": $! $?"; + } else { + exec(@_) or die "$! $?"; # exec() can fail the executable can't be found + } + return wantarray ? @output : join('',@output); +} + + +1; diff --git a/git-fetch.sh b/git-fetch.sh index b4325d9d98..0346d4a45c 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -164,6 +164,7 @@ fast_forward_local () { ;; *,$local) echo >&2 "* $1: fast forward to $3" + echo >&2 " from $local to $2" git-update-ref "$1" "$2" "$local" ;; *) @@ -320,7 +321,7 @@ 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 @@ -368,20 +369,25 @@ fetch_main "$reflist" # automated tag following case "$no_tags$tags" in '') - taglist=$(IFS=" " && - git-ls-remote $upload_pack --tags "$remote" | - sed -ne 's|^\([0-9a-f]*\)[ ]\(refs/tags/.*\)^{}$|\1 \2|p' | - while read sha1 name - do - test -f "$GIT_DIR/$name" && continue - git-check-ref-format "$name" || { - echo >&2 "warning: tag ${name} ignored" - continue - } - git-cat-file -t "$sha1" >/dev/null 2>&1 || continue - echo >&2 "Auto-following $name" - echo ".${name}:${name}" - done) + case "$reflist" in + *:refs/*) + # effective only when we are following remote branch + # using local tracking branch. + taglist=$(IFS=" " && + git-ls-remote $upload_pack --tags "$remote" | + sed -ne 's|^\([0-9a-f]*\)[ ]\(refs/tags/.*\)^{}$|\1 \2|p' | + while read sha1 name + do + test -f "$GIT_DIR/$name" && continue + git-check-ref-format "$name" || { + echo >&2 "warning: tag ${name} ignored" + continue + } + git-cat-file -t "$sha1" >/dev/null 2>&1 || continue + echo >&2 "Auto-following $name" + echo ".${name}:${name}" + done) + esac case "$taglist" in '') ;; ?*) diff --git a/git-fmt-merge-msg.perl b/git-fmt-merge-msg.perl index c13af4884a..dae383f231 100755 --- a/git-fmt-merge-msg.perl +++ b/git-fmt-merge-msg.perl @@ -28,28 +28,13 @@ sub andjoin { } sub repoconfig { - my $val; - eval { - my $pid = open(my $fh, '-|'); - if (!$pid) { - exec('git-repo-config', '--get', 'merge.summary'); - } - ($val) = <$fh>; - close $fh; - }; + my ($val) = qx{git-repo-config --get merge.summary}; return $val; } sub current_branch { - my $fh; - my $pid = open($fh, '-|'); - die "$!" unless defined $pid; - if (!$pid) { - exec('git-symbolic-ref', 'HEAD') or die "$!"; - } - my ($bra) = <$fh>; + my ($bra) = qx{git-symbolic-ref HEAD}; chomp($bra); - close $fh or die "$!"; $bra =~ s|^refs/heads/||; if ($bra ne 'master') { $bra = " into $bra"; @@ -61,18 +46,12 @@ sub current_branch { sub shortlog { my ($tip) = @_; - my ($fh, @result); - my $pid = open($fh, '-|'); - die "$!" unless defined $pid; - if (!$pid) { - exec('git-log', '--topo-order', - '--pretty=oneline', $tip, '^HEAD') or die "$!"; - } - while (<$fh>) { + my @result; + foreach ( qx{git-log --topo-order --pretty=oneline $tip ^HEAD} ) { s/^[0-9a-f]{40}\s+//; push @result, $_; } - close $fh or die "$!"; + die "git-log failed\n" if $?; return @result; } diff --git a/git-format-patch.sh b/git-format-patch.sh index eb75de4601..2bd26395ec 100755 --- a/git-format-patch.sh +++ b/git-format-patch.sh @@ -174,7 +174,7 @@ titleScript=' process_one () { perl -w -e ' my ($keep_subject, $num, $signoff, $commsg) = @ARGV; -my ($signoff_pattern, $done_header, $done_subject, $signoff_seen, +my ($signoff_pattern, $done_header, $done_subject, $done_separator, $signoff_seen, $last_was_signoff); if ($signoff) { @@ -228,6 +228,11 @@ while (<FH>) { $done_subject = 1; next; } + unless ($done_separator) { + print "\n"; + $done_separator = 1; + next if (/^$/); + } $last_was_signoff = 0; if (/Signed-off-by:/i) { diff --git a/git-merge.sh b/git-merge.sh index 4609fe54d5..7be9e81f1f 100755 --- a/git-merge.sh +++ b/git-merge.sh @@ -134,7 +134,7 @@ case "$#,$common,$no_commit" in echo "Updating from $head to $1." git-update-index --refresh 2>/dev/null new_head=$(git-rev-parse --verify "$1^0") && - git-read-tree -u -m $head "$new_head" && + git-read-tree -u -v -m $head "$new_head" && finish "$new_head" "Fast forward" dropsave exit 0 @@ -150,7 +150,7 @@ case "$#,$common,$no_commit" in echo "Trying really trivial in-index merge..." git-update-index --refresh 2>/dev/null - if git-read-tree --trivial -m -u $common $head "$1" && + if git-read-tree --trivial -m -u -v $common $head "$1" && result_tree=$(git-write-tree) then echo "Wonderful." 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-rm.sh b/git-rm.sh new file mode 100755 index 0000000000..fda4541c76 --- /dev/null +++ b/git-rm.sh @@ -0,0 +1,70 @@ +#!/bin/sh + +USAGE='[-f] [-n] [-v] [--] <file>...' +SUBDIRECTORY_OK='Yes' +. git-sh-setup + +remove_files= +show_only= +verbose= +while : ; do + case "$1" in + -f) + remove_files=true + ;; + -n) + show_only=true + ;; + -v) + verbose=--verbose + ;; + --) + shift; break + ;; + -*) + usage + ;; + *) + break + ;; + esac + shift +done + +# This is typo-proofing. If some paths match and some do not, we want +# to do nothing. +case "$#" in +0) ;; +*) + git-ls-files --error-unmatch -- "$@" >/dev/null || { + echo >&2 "Maybe you misspelled it?" + exit 1 + } + ;; +esac + +if test -f "$GIT_DIR/info/exclude" +then + git-ls-files -z \ + --exclude-from="$GIT_DIR/info/exclude" \ + --exclude-per-directory=.gitignore -- "$@" +else + git-ls-files -z \ + --exclude-per-directory=.gitignore -- "$@" +fi | +case "$show_only,$remove_files" in +true,*) + xargs -0 echo + ;; +*,true) + xargs -0 sh -c " + while [ \$# -gt 0 ]; do + file=\$1; shift + rm -- \"\$file\" && git-update-index --remove $verbose \"\$file\" + done + " inline + ;; +*) + git-update-index --force-remove $verbose -z --stdin + ;; +esac diff --git a/git-svnimport.perl b/git-svnimport.perl index ee2940f480..639aa41861 100755 --- a/git-svnimport.perl +++ b/git-svnimport.perl @@ -13,6 +13,7 @@ use strict; use warnings; use Getopt::Std; +use File::Copy; use File::Spec; use File::Temp qw(tempfile); use File::Path qw(mkpath); @@ -29,19 +30,21 @@ die "Need SVN:Core 1.2.1 or better" if $SVN::Core::VERSION lt "1.2.1"; $SIG{'PIPE'}="IGNORE"; $ENV{'TZ'}="UTC"; -our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,$opt_b,$opt_r,$opt_s,$opt_l,$opt_d,$opt_D); +our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T, + $opt_b,$opt_r,$opt_I,$opt_A,$opt_s,$opt_l,$opt_d,$opt_D); sub usage() { print STDERR <<END; Usage: ${\basename $0} # fetch/update GIT from SVN [-o branch-for-HEAD] [-h] [-v] [-l max_rev] [-C GIT_repository] [-t tagname] [-T trunkname] [-b branchname] - [-d|-D] [-i] [-u] [-r] [-s start_chg] [-m] [-M regex] [SVN_URL] + [-d|-D] [-i] [-u] [-r] [-I ignorefilename] [-s start_chg] + [-m] [-M regex] [-A author_file] [SVN_URL] END exit(1); } -getopts("b:C:dDhil:mM:o:rs:t:T:uv") or usage(); +getopts("A:b:C:dDhiI:l:mM:o:rs:t:T:uv") or usage(); usage if $opt_h; my $tag_name = $opt_t || "tags"; @@ -66,6 +69,25 @@ if ($opt_M) { push (@mergerx, qr/$opt_M/); } +# Absolutize filename now, since we will have chdir'ed by the time we +# get around to opening it. +$opt_A = File::Spec->rel2abs($opt_A) if $opt_A; + +our %users = (); +our $users_file = undef; +sub read_users($) { + $users_file = File::Spec->rel2abs(@_); + die "Cannot open $users_file\n" unless -f $users_file; + open(my $authors,$users_file); + while(<$authors>) { + chomp; + next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/; + (my $user,my $name,my $email) = ($1,$2,$3); + $users{$user} = [$name,$email]; + } + close($authors); +} + select(STDERR); $|=1; select(STDOUT); @@ -112,16 +134,40 @@ sub file { DIR => File::Spec->tmpdir(), UNLINK => 1); print "... $rev $path ...\n" if $opt_v; - my $pool = SVN::Pool->new(); - eval { $self->{'svn'}->get_file($path,$rev,$fh,$pool); }; - $pool->clear; + my (undef, $properties); + eval { (undef, $properties) + = $self->{'svn'}->get_file($path,$rev,$fh); }; if($@) { return undef if $@ =~ /Attempted to get checksum/; die $@; } + my $mode; + if (exists $properties->{'svn:executable'}) { + $mode = '0755'; + } else { + $mode = '0644'; + } close ($fh); - return $name; + return ($name, $mode); +} + +sub ignore { + my($self,$path,$rev) = @_; + + print "... $rev $path ...\n" if $opt_v; + my (undef,undef,$properties) + = $self->{'svn'}->get_dir($path,$rev,undef); + if (exists $properties->{'svn:ignore'}) { + my ($fh, $name) = tempfile('gitsvn.XXXXXX', + DIR => File::Spec->tmpdir(), + UNLINK => 1); + print $fh $properties->{'svn:ignore'}; + close($fh); + return $name; + } else { + return undef; + } } package main; @@ -263,6 +309,14 @@ EOM -d $git_dir or die "Could not create git subdir ($git_dir).\n"; +my $default_authors = "$git_dir/svn-authors"; +if ($opt_A) { + read_users($opt_A); + copy($opt_A,$default_authors) or die "Copy failed: $!"; +} else { + read_users($default_authors) if -f $default_authors; +} + open BRANCHES,">>", "$git_dir/svn2git"; sub node_kind($$$) { @@ -296,7 +350,7 @@ sub get_file($$$) { my $svnpath = revert_split_path($branch,$path); # now get it - my $name; + my ($name,$mode); if($opt_d) { my($req,$res); @@ -316,8 +370,9 @@ sub get_file($$$) { return undef if $res->code == 301; # directory? die $res->status_line." at $url\n"; } + $mode = '0644'; # can't obtain mode via direct http request? } else { - $name = $svn->file("$svnpath",$rev); + ($name,$mode) = $svn->file("$svnpath",$rev); return undef unless defined $name; } @@ -331,10 +386,37 @@ sub get_file($$$) { chomp $sha; close $F; unlink $name; - my $mode = "0644"; # SV does not seem to store any file modes return [$mode, $sha, $path]; } +sub get_ignore($$$$$) { + my($new,$old,$rev,$branch,$path) = @_; + + return unless $opt_I; + my $svnpath = revert_split_path($branch,$path); + my $name = $svn->ignore("$svnpath",$rev); + if ($path eq '/') { + $path = $opt_I; + } else { + $path = File::Spec->catfile($path,$opt_I); + } + if (defined $name) { + my $pid = open(my $F, '-|'); + die $! unless defined $pid; + if (!$pid) { + exec("git-hash-object", "-w", $name) + or die "Cannot create object: $!\n"; + } + my $sha = <$F>; + chomp $sha; + close $F; + unlink $name; + push(@$new,['0644',$sha,$path]); + } else { + push(@$old,$path); + } +} + sub split_path($$) { my($rev,$path) = @_; my $branch; @@ -431,6 +513,10 @@ sub commit { if (not defined $author) { $author_name = $author_email = "unknown"; + } elsif (defined $users_file) { + die "User $author is not listed in $users_file\n" + unless exists $users{$author}; + ($author_name,$author_email) = @{$users{$author}}; } elsif ($author =~ /^(.*?)\s+<(.*)>$/) { ($author_name, $author_email) = ($1, $2); } else { @@ -540,6 +626,9 @@ sub commit { my $opath = $action->[3]; print STDERR "$revision: $branch: could not fetch '$opath'\n"; } + } elsif ($node_kind eq $SVN::Node::dir) { + get_ignore(\@new, \@old, $revision, + $branch,$path); } } elsif ($action->[0] eq "D") { push(@old,$path); @@ -548,6 +637,9 @@ sub commit { if ($node_kind eq $SVN::Node::file) { my $f = get_file($revision,$branch,$path); push(@new,$f) if $f; + } elsif ($node_kind eq $SVN::Node::dir) { + get_ignore(\@new, \@old, $revision, + $branch,$path); } } else { die "$revision: unknown action '".$action->[0]."' for $path\n"; @@ -230,62 +230,141 @@ static void show_man_page(char *git_cmd) execlp("man", "man", page, NULL); } +static int cmd_version(int argc, char **argv, char **envp) +{ + printf("git version %s\n", GIT_VERSION); + return 0; +} + +static int cmd_help(int argc, char **argv, char **envp) +{ + char *help_cmd = argv[1]; + if (!help_cmd) + cmd_usage(git_exec_path(), NULL); + show_man_page(help_cmd); + return 0; +} + +#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) + +static void handle_internal_command(int argc, char **argv, char **envp) +{ + const char *cmd = argv[0]; + static struct cmd_struct { + const char *cmd; + int (*fn)(int, char **, char **); + } commands[] = { + { "version", cmd_version }, + { "help", cmd_help }, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(commands); i++) { + struct cmd_struct *p = commands+i; + if (strcmp(p->cmd, cmd)) + continue; + exit(p->fn(argc, argv, envp)); + } +} + int main(int argc, char **argv, char **envp) { + char *cmd = argv[0]; + char *slash = strrchr(cmd, '/'); char git_command[PATH_MAX + 1]; - char wd[PATH_MAX + 1]; - int i, show_help = 0; - const char *exec_path; + const char *exec_path = NULL; + + /* + * Take the basename of argv[0] as the command + * name, and the dirname as the default exec_path + * if it's an absolute path and we don't have + * anything better. + */ + if (slash) { + *slash++ = 0; + if (*cmd == '/') + exec_path = cmd; + cmd = slash; + } - getcwd(wd, PATH_MAX); + /* + * "git-xxxx" is the same as "git xxxx", but we obviously: + * + * - cannot take flags in between the "git" and the "xxxx". + * - cannot execute it externally (since it would just do + * the same thing over again) + * + * So we just directly call the internal command handler, and + * die if that one cannot handle it. + */ + if (!strncmp(cmd, "git-", 4)) { + cmd += 4; + argv[0] = cmd; + handle_internal_command(argc, argv, envp); + die("cannot handle %s internally", cmd); + } - for (i = 1; i < argc; i++) { - char *arg = argv[i]; + /* Default command: "help" */ + cmd = "help"; - if (!strcmp(arg, "help")) { - show_help = 1; - continue; - } + /* Look for flags.. */ + while (argc > 1) { + cmd = *++argv; + argc--; - if (strncmp(arg, "--", 2)) + if (strncmp(cmd, "--", 2)) break; - arg += 2; + cmd += 2; + + /* + * For legacy reasons, the "version" and "help" + * commands can be written with "--" prepended + * to make them look like flags. + */ + if (!strcmp(cmd, "help")) + break; + if (!strcmp(cmd, "version")) + break; - if (!strncmp(arg, "exec-path", 9)) { - arg += 9; - if (*arg == '=') { - exec_path = arg + 1; - git_set_exec_path(exec_path); - } else { - puts(git_exec_path()); - exit(0); + /* + * Check remaining flags (which by now must be + * "--exec-path", but maybe we will accept + * other arguments some day) + */ + if (!strncmp(cmd, "exec-path", 9)) { + cmd += 9; + if (*cmd == '=') { + git_set_exec_path(cmd + 1); + continue; } - } - else if (!strcmp(arg, "version")) { - printf("git version %s\n", GIT_VERSION); + puts(git_exec_path()); exit(0); } - else if (!strcmp(arg, "help")) - show_help = 1; - else if (!show_help) - cmd_usage(NULL, NULL); - } - - if (i >= argc || show_help) { - if (i >= argc) - cmd_usage(git_exec_path(), NULL); - - show_man_page(argv[i]); + cmd_usage(NULL, NULL); } - + argv[0] = cmd; + + /* + * We search for git commands in the following order: + * - git_exec_path() + * - the path of the "git" command if we could find it + * in $0 + * - the regular PATH. + */ + if (exec_path) + prepend_to_path(exec_path, strlen(exec_path)); exec_path = git_exec_path(); prepend_to_path(exec_path, strlen(exec_path)); - execv_git_cmd(argv + i); + /* See if it's an internal command */ + handle_internal_command(argc, argv, envp); + + /* .. then try the external ones */ + execv_git_cmd(argv); if (errno == ENOENT) - cmd_usage(exec_path, "'%s' is not a git-command", argv[i]); + cmd_usage(exec_path, "'%s' is not a git-command", cmd); fprintf(stderr, "Failed to run command '%s': %s\n", git_command, strerror(errno)); diff --git a/http-fetch.c b/http-fetch.c index ce3df5f35c..8fd9de081f 100644 --- a/http-fetch.c +++ b/http-fetch.c @@ -130,7 +130,7 @@ static void start_object_request(struct object_request *obj_req) if (obj_req->local < 0) { obj_req->state = ABORTED; - error("Couldn't create temporary file %s for %s: %s\n", + error("Couldn't create temporary file %s for %s: %s", obj_req->tmpfile, obj_req->filename, strerror(errno)); return; } @@ -830,9 +830,9 @@ static int fetch_object(struct alt_base *repo, unsigned char *sha1) obj_req->errorstr, obj_req->curl_result, obj_req->http_code, hex); } else if (obj_req->zret != Z_STREAM_END) { - ret = error("File %s (%s) corrupt\n", hex, obj_req->url); + ret = error("File %s (%s) corrupt", hex, obj_req->url); } else if (memcmp(obj_req->sha1, obj_req->real_sha1, 20)) { - ret = error("File %s has bad hash\n", hex); + ret = error("File %s has bad hash", hex); } else if (obj_req->rename < 0) { ret = error("unable to write sha1 filename %s", obj_req->filename); @@ -854,7 +854,7 @@ int fetch(unsigned char *sha1) fetch_alternates(alt->base); altbase = altbase->next; } - return error("Unable to find %s under %s\n", sha1_to_hex(sha1), + return error("Unable to find %s under %s", sha1_to_hex(sha1), alt->base); } diff --git a/ls-files.c b/ls-files.c index 90b289f03d..df25c8c012 100644 --- a/ls-files.c +++ b/ls-files.c @@ -279,8 +279,11 @@ static void read_directory(const char *path, const char *base, int baselen) continue; len = strlen(de->d_name); memcpy(fullname + baselen, de->d_name, len+1); - if (excluded(fullname) != show_ignored) - continue; + if (excluded(fullname) != show_ignored) { + if (!show_ignored || DTYPE(de) != DT_DIR) { + continue; + } + } switch (DTYPE(de)) { struct stat st; diff --git a/pack-objects.c b/pack-objects.c index e3946db5ca..21ee572f48 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -3,7 +3,9 @@ #include "delta.h" #include "pack.h" #include "csum-file.h" +#include "diff.h" #include <sys/time.h> +#include <signal.h> 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"; @@ -26,6 +28,13 @@ struct object_entry { 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. + */ }; /* @@ -48,10 +57,11 @@ 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; +static volatile int progress_update = 0; /* * The object names in objects array are hashed with this hashtable, @@ -89,7 +99,7 @@ static int reused_delta = 0; static int pack_revindex_ix(struct packed_git *p) { - unsigned int ui = (unsigned int) p; + unsigned long ui = (unsigned long)(long)p; int i; ui = ui ^ (ui >> 16); /* defeat structure alignment */ @@ -229,7 +239,8 @@ 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]; @@ -239,6 +250,9 @@ static unsigned long write_object(struct sha1file *f, struct object_entry *entry enum object_type obj_type; int to_reuse = 0; + if (entry->preferred_base) + return 0; + obj_type = entry->type; if (! entry->in_pack) to_reuse = 0; /* can't reuse what we don't have */ @@ -322,28 +336,51 @@ static void write_pack_file(void) struct sha1file *f; unsigned long offset; struct pack_header hdr; + unsigned last_percent = 999; + int do_progress = 0; if (!base_name) f = sha1fd(1, "<stdout>"); - else - f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "pack"); + else { + f = sha1create("%s-%s.%s", base_name, + sha1_to_hex(object_list_sha1), "pack"); + do_progress = progress; + } + if (do_progress) + fprintf(stderr, "Writing %d objects.\n", nr_result); + 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++) + if (!nr_result) + goto done; + for (i = 0; i < nr_objects; i++) { offset = write_one(f, objects + i, offset); - + if (do_progress) { + unsigned percent = written * 100 / nr_result; + if (progress_update || percent != last_percent) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, written, nr_result); + progress_update = 0; + last_percent = percent; + } + } + } + if (do_progress) + fputc('\n', stderr); + done: sha1close(f, pack_file_sha1, 1); } 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]; /* @@ -368,7 +405,7 @@ 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); @@ -378,27 +415,139 @@ 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; + } +} + +struct name_path { + struct name_path *up; + const char *elem; + int len; +}; + +#define DIRBITS 12 + +static unsigned name_hash(struct name_path *path, const char *name) +{ + struct name_path *p = path; + const char *n = name + strlen(name); + unsigned hash = 0, name_hash = 0, name_done = 0; + + if (n != name && n[-1] == '\n') + n--; + while (name <= --n) { + unsigned char c = *n; + if (c == '/' && !name_done) { + name_hash = hash; + name_done = 1; + hash = 0; + } + hash = hash * 11 + c; + } + if (!name_done) { + name_hash = hash; + hash = 0; + } + for (p = path; p; p = p->up) { + hash = hash * 11 + '/'; + n = p->elem + p->len; + while (p->elem <= --n) { + unsigned char c = *n; + hash = hash * 11 + c; + } + } + /* + * Make sure "Makefile" and "t/Makefile" are hashed separately + * but close enough. + */ + hash = (name_hash<<DIRBITS) | (hash & ((1U<<DIRBITS )-1)); + + if (0) { /* debug */ + n = name + strlen(name); + if (n != name && n[-1] == '\n') + n--; + while (name <= --n) + fputc(*n, stderr); + for (p = path; p; p = p->up) { + fputc('/', stderr); + n = p->elem + p->len; + while (p->elem <= --n) + fputc(*n, stderr); + } + fprintf(stderr, "\t%08x\n", hash); + } + return hash; +} + +static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclude) { unsigned int idx = nr_objects; struct object_entry *entry; struct packed_git *p; unsigned int found_offset = 0; struct packed_git *found_pack = NULL; - - 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; + int ix, status = 0; + + 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; if (idx >= nr_alloc) { unsigned int needed = (idx + 1024) * 3 / 2; @@ -406,45 +555,94 @@ 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; - if (found_pack) { - entry->in_pack = found_pack; - entry->in_pack_offset = found_offset; + + 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; } - nr_objects = idx+1; - return 1; + status = 1; + + already_added: + if (progress_update) { + fprintf(stderr, "Counting objects...%d\r", nr_objects); + progress_update = 0; + } + if (exclude) + entry->preferred_base = 1; + else { + if (found_pack) { + entry->in_pack = found_pack; + entry->in_pack_offset = found_offset; + } + } + return status; } -static int locate_object_entry_hash(unsigned char *sha1) +static void add_pbase_tree(struct tree_desc *tree, struct name_path *up) { - 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; + while (tree->size) { + const unsigned char *sha1; + const char *name; + unsigned mode, hash; + 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; + + hash = name_hash(up, name); + if (!add_object_entry(sha1, hash, 1)) + continue; + + if (!strcmp(type, "tree")) { + struct tree_desc sub; + void *elem; + struct name_path me; + + elem = read_sha1_file(sha1, type, &sub.size); + sub.buf = elem; + if (sub.buf) { + me.up = up; + me.elem = name; + me.len = strlen(name); + add_pbase_tree(&sub, &me); + free(elem); + } + } } - return -1 - i; } -static struct object_entry *locate_object_entry(unsigned char *sha1) +static void add_preferred_base(unsigned char *sha1) { - int i = locate_object_entry_hash(sha1); - if (0 <= i) - return &objects[object_ix[i]-1]; - return NULL; + struct tree_desc tree; + void *elem; + + elem = read_object_with_reference(sha1, "tree", &tree.size, NULL); + tree.buf = elem; + if (!tree.buf) + return; + if (add_object_entry(sha1, name_hash(NULL, ""), 1)) + add_pbase_tree(&tree, NULL); + free(elem); } static void check_object(struct object_entry *entry) { char type[20]; - if (entry->in_pack) { + if (entry->in_pack && !entry->preferred_base) { unsigned char base[20]; unsigned long size; struct object_entry *base_entry; @@ -463,7 +661,8 @@ static void check_object(struct object_entry *entry) */ if (!no_reuse_delta && entry->in_pack_type == OBJ_DELTA && - (base_entry = locate_object_entry(base))) { + (base_entry = locate_object_entry(base)) && + (!base_entry->preferred_base)) { /* Depth value does not matter - find_deltas() * will never consider reused delta as the @@ -501,25 +700,6 @@ static void check_object(struct object_entry *entry) sha1_to_hex(entry->sha1), type); } -static void hash_objects(void) -{ - int i; - struct object_entry *oe; - - object_ix_hashsz = nr_objects * 2; - object_ix = xcalloc(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) { - error("the same object '%s' added twice", - sha1_to_hex(oe->sha1)); - continue; - } - ix = -1 - ix; - object_ix[ix] = i + 1; - } -} - static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) { struct object_entry *child = me->delta_child; @@ -538,14 +718,26 @@ static void get_object_details(void) int i; struct object_entry *entry; - hash_objects(); 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); + + if (nr_objects == nr_result) { + /* + * Depth of objects that depend on the entry -- this + * is subtracted from depth-max to break too deep + * delta chain because of delta data reusing. + * However, we loosen this restriction when we know we + * are creating a thin pack -- it will have to be + * expanded on the other end anyway, so do not + * artificially cut the delta chain and let it go as + * deep as it wants. + */ + 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 *); @@ -576,6 +768,24 @@ 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(void) +{ + 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) @@ -586,6 +796,10 @@ 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) @@ -610,6 +824,8 @@ 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; @@ -618,9 +834,15 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de if (cur_entry->type != old_entry->type) return -1; - /* If the current object is at edge, take the depth the objects - * that depend on the current object into account -- otherwise - * they would become too deep. + /* 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) @@ -645,8 +867,27 @@ 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 -1; + } + 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, @@ -656,21 +897,30 @@ 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; } +static void progress_interval(int signum) +{ + signal(SIGALRM, progress_interval); + progress_update = 1; +} + static void find_deltas(struct object_entry **list, int window, int depth) { int i, idx; unsigned int array_size = window * sizeof(struct unpacked); struct unpacked *array = xmalloc(array_size); - int eye_candy; + unsigned processed = 0; + unsigned last_percent = 999; memset(array, 0, array_size); i = nr_objects; idx = 0; - eye_candy = i - (nr_objects / 20); + if (progress) + fprintf(stderr, "Deltifying %d objects.\n", nr_result); while (--i >= 0) { struct object_entry *entry = list[i]; @@ -679,9 +929,17 @@ static void find_deltas(struct object_entry **list, int window, int depth) char type[10]; int j; - if (progress && i <= eye_candy) { - eye_candy -= nr_objects / 20; - fputc('.', stderr); + if (!entry->preferred_base) + processed++; + + if (progress) { + unsigned percent = processed * 100 / nr_result; + if (percent != last_percent || progress_update) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, processed, nr_result); + progress_update = 0; + last_percent = percent; + } } if (entry->delta) @@ -713,6 +971,9 @@ static void find_deltas(struct object_entry **list, int window, int depth) idx = 0; } + if (progress) + fputc('\n', stderr); + for (i = 0; i < window; ++i) free(array[i].data); free(array); @@ -720,18 +981,10 @@ 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_objects); get_object_details(); - if (progress) - fputc('.', stderr); - sorted_by_type = create_sorted_list(type_size_sort); if (window && depth) find_deltas(sorted_by_type, window+1, depth); - if (progress) - fputc('\n', stderr); - write_pack_file(); } static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) @@ -795,10 +1048,6 @@ int main(int argc, char **argv) int window = 10, depth = 10, pack_to_stdout = 0; struct object_entry **list; int i; - struct timeval prev_tv; - int eye_candy = 0; - int eye_candy_incr = 500; - setup_git_directory(); @@ -855,61 +1104,60 @@ int main(int argc, char **argv) usage(pack_usage); prepare_packed_git(); + if (progress) { + struct itimerval v; + v.it_interval.tv_sec = 1; + v.it_interval.tv_usec = 0; + v.it_value = v.it_interval; + signal(SIGALRM, progress_interval); + setitimer(ITIMER_REAL, &v, NULL); fprintf(stderr, "Generating pack...\n"); - 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)) { - fprintf(stderr, "Counting objects...%d\r", nr_objects); - if (eye_candy && (50 <= eye_candy_incr)) { - struct timeval tv; - int time_diff; - gettimeofday(&tv, NULL); - time_diff = (tv.tv_sec - prev_tv.tv_sec); - time_diff <<= 10; - time_diff += (tv.tv_usec - prev_tv.tv_usec); - if ((1 << 9) < time_diff) - eye_candy_incr += 50; - else if (50 < eye_candy_incr) - eye_candy_incr -= 50; - } - 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, name_hash(NULL, line+41), 0); } if (progress) fprintf(stderr, "Done counting %d objects.\n", nr_objects); - if (non_empty && !nr_objects) + sorted_by_sha = create_final_object_list(); + if (non_empty && !nr_result) return 0; - sorted_by_sha = create_sorted_list(sha1_sort); 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)) ; else { - prepare_pack(window, depth); + if (nr_result) + prepare_pack(window, depth); + if (progress && pack_to_stdout) { + /* the other end usually displays progress itself */ + struct itimerval v = {{0,},}; + setitimer(ITIMER_REAL, &v, NULL); + signal(SIGALRM, SIG_IGN ); + progress_update = 0; + } + write_pack_file(); if (!pack_to_stdout) { write_index_file(); puts(sha1_to_hex(object_list_sha1)); @@ -917,6 +1165,6 @@ int main(int argc, char **argv) } if (progress) fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n", - nr_objects, written, written_delta, reused, reused_delta); + nr_result, written, written_delta, reused, reused_delta); return 0; } diff --git a/pack-redundant.c b/pack-redundant.c index 1869b38b72..cd81f5a66e 100644 --- a/pack-redundant.c +++ b/pack-redundant.c @@ -45,7 +45,7 @@ static inline void llist_item_put(struct llist_item *item) free_nodes = item; } -static inline struct llist_item *llist_item_get() +static inline struct llist_item *llist_item_get(void) { struct llist_item *new; if ( free_nodes ) { @@ -275,7 +275,7 @@ static void cmp_two_packs(struct pack_list *p1, struct pack_list *p2) } } -void pll_free(struct pll *l) +static void pll_free(struct pll *l) { struct pll *old; struct pack_list *opl; diff --git a/read-tree.c b/read-tree.c index 52f06e312a..f39fe5ca65 100644 --- a/read-tree.c +++ b/read-tree.c @@ -9,6 +9,8 @@ #include "object.h" #include "tree.h" +#include <sys/time.h> +#include <signal.h> static int merge = 0; static int update = 0; @@ -16,6 +18,8 @@ static int index_only = 0; static int nontrivial_merge = 0; static int trivial_merges_only = 0; static int aggressive = 0; +static int verbose_update = 0; +static volatile int progress_update = 0; static int head_idx = -1; static int merge_size = 0; @@ -267,6 +271,12 @@ static void unlink_entry(char *name) } } +static void progress_interval(int signum) +{ + signal(SIGALRM, progress_interval); + progress_update = 1; +} + static void check_updates(struct cache_entry **src, int nr) { static struct checkout state = { @@ -276,8 +286,49 @@ static void check_updates(struct cache_entry **src, int nr) .refresh_cache = 1, }; unsigned short mask = htons(CE_UPDATE); + unsigned last_percent = 200, cnt = 0, total = 0; + + if (update && verbose_update) { + struct itimerval v; + + for (total = cnt = 0; cnt < nr; cnt++) { + struct cache_entry *ce = src[cnt]; + if (!ce->ce_mode || ce->ce_flags & mask) + total++; + } + + /* Don't bother doing this for very small updates */ + if (total < 250) + total = 0; + + if (total) { + v.it_interval.tv_sec = 1; + v.it_interval.tv_usec = 0; + v.it_value = v.it_interval; + signal(SIGALRM, progress_interval); + setitimer(ITIMER_REAL, &v, NULL); + fprintf(stderr, "Checking files out...\n"); + progress_update = 1; + } + cnt = 0; + } + while (nr--) { struct cache_entry *ce = *src++; + + if (total) { + if (!ce->ce_mode || ce->ce_flags & mask) { + unsigned percent; + cnt++; + percent = (cnt * 100) / total; + if (percent != last_percent || + progress_update) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, cnt, total); + last_percent = percent; + } + } + } if (!ce->ce_mode) { if (update) unlink_entry(ce->name); @@ -289,6 +340,10 @@ static void check_updates(struct cache_entry **src, int nr) checkout_entry(ce, &state); } } + if (total) { + fputc('\n', stderr); + signal(SIGALRM, SIG_IGN); + } } static int unpack_trees(merge_fn_t fn) @@ -564,7 +619,7 @@ static int twoway_merge(struct cache_entry **src) struct cache_entry *oldtree = src[1], *newtree = src[2]; if (merge_size != 2) - return error("Cannot do a twoway merge of %d trees\n", + return error("Cannot do a twoway merge of %d trees", merge_size); if (current) { @@ -616,7 +671,7 @@ static int oneway_merge(struct cache_entry **src) struct cache_entry *a = src[1]; if (merge_size != 1) - return error("Cannot do a oneway merge of %d trees\n", + return error("Cannot do a oneway merge of %d trees", merge_size); if (!a) @@ -680,6 +735,11 @@ int main(int argc, char **argv) continue; } + if (!strcmp(arg, "-v")) { + verbose_update = 1; + continue; + } + /* "-i" means "index only", meaning that a merge will * not even look at the working tree. */ diff --git a/receive-pack.c b/receive-pack.c index eae31e370d..2a3db16d68 100644 --- a/receive-pack.c +++ b/receive-pack.c @@ -92,7 +92,7 @@ static int run_update_hook(const char *refname, case -ERR_RUN_COMMAND_WAITPID_WRONG_PID: return error("waitpid is confused"); case -ERR_RUN_COMMAND_WAITPID_SIGNAL: - return error("%s died of signal\n", update_hook); + return error("%s died of signal", update_hook); case -ERR_RUN_COMMAND_WAITPID_NOEXIT: return error("%s died strangely", update_hook); default: @@ -158,7 +158,7 @@ static int update(struct command *cmd) if (run_update_hook(name, old_hex, new_hex)) { unlink(lock_name); cmd->error_string = "hook declined"; - return error("hook declined to update %s\n", name); + return error("hook declined to update %s", name); } else if (rename(lock_name, name) < 0) { unlink(lock_name); @@ -268,7 +268,7 @@ static int write_ref_file(const char *filename, char term = '\n'; if (write(fd, hex, 40) < 40 || write(fd, &term, 1) < 1) { - error("Couldn't write %s\n", filename); + error("Couldn't write %s", filename); close(fd); return -1; } diff --git a/rev-list.c b/rev-list.c index f2d1105cae..2e80930b2c 100644 --- a/rev-list.c +++ b/rev-list.c @@ -6,9 +6,10 @@ #include "blob.h" #include "epoch.h" #include "diff.h" +#include "revision.h" + +/* bits #0 and #1 in revision.h */ -#define SEEN (1u << 0) -#define INTERESTING (1u << 1) #define COUNTED (1u << 2) #define SHOWN (1u << 3) #define TREECHANGE (1u << 4) @@ -30,7 +31,7 @@ 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" @@ -38,29 +39,19 @@ static const char rev_list_usage[] = " --bisect" ; -static int dense = 1; -static int unpacked = 0; +struct rev_info revs; + static int bisect_list = 0; -static int tag_objects = 0; -static int tree_objects = 0; -static int blob_objects = 0; static int verbose_header = 0; static int abbrev = DEFAULT_ABBREV; static int show_parents = 0; static int hdr_termination = 0; static const char *commit_prefix = ""; -static unsigned long max_age = -1; -static unsigned long min_age = -1; -static int max_count = -1; static enum cmit_fmt commit_format = CMIT_FMT_RAW; static int merge_order = 0; static int show_breaks = 0; static int stop_traversal = 0; -static int topo_order = 0; -static int lifo = 1; static int no_merges = 0; -static const char **paths = NULL; -static int remove_empty_trees = 0; static void show_commit(struct commit *commit) { @@ -137,15 +128,15 @@ static int filter_commit(struct commit * commit) return STOP; if (commit->object.flags & (UNINTERESTING|SHOWN)) return CONTINUE; - if (min_age != -1 && (commit->date > min_age)) + if (revs.min_age != -1 && (commit->date > revs.min_age)) return CONTINUE; - if (max_age != -1 && (commit->date < max_age)) { + if (revs.max_age != -1 && (commit->date < revs.max_age)) { stop_traversal=1; return CONTINUE; } if (no_merges && (commit->parents && commit->parents->next)) return CONTINUE; - if (paths && dense) { + if (revs.paths && revs.dense) { if (!(commit->object.flags & TREECHANGE)) return CONTINUE; rewrite_parents(commit); @@ -165,7 +156,7 @@ static int process_commit(struct commit * commit) return CONTINUE; } - if (max_count != -1 && !max_count--) + if (revs.max_count != -1 && !revs.max_count--) return STOP; show_commit(commit); @@ -173,90 +164,88 @@ static int process_commit(struct commit * commit) return CONTINUE; } -static struct object_list **add_object(struct object *obj, struct object_list **p, const char *name) -{ - struct object_list *entry = xmalloc(sizeof(*entry)); - entry->item = obj; - entry->next = *p; - entry->name = name; - *p = entry; - return &entry->next; -} - -static struct object_list **process_blob(struct blob *blob, struct object_list **p, const char *name) +static struct object_list **process_blob(struct blob *blob, + struct object_list **p, + struct name_path *path, + const char *name) { struct object *obj = &blob->object; - if (!blob_objects) + if (!revs.blob_objects) return p; if (obj->flags & (UNINTERESTING | SEEN)) return p; obj->flags |= SEEN; - return add_object(obj, p, name); + return add_object(obj, p, path, name); } -static struct object_list **process_tree(struct tree *tree, struct object_list **p, const char *name) +static struct object_list **process_tree(struct tree *tree, + struct object_list **p, + struct name_path *path, + const char *name) { struct object *obj = &tree->object; struct tree_entry_list *entry; + struct name_path me; - if (!tree_objects) + if (!revs.tree_objects) return p; if (obj->flags & (UNINTERESTING | SEEN)) return p; if (parse_tree(tree) < 0) die("bad tree object %s", sha1_to_hex(obj->sha1)); obj->flags |= SEEN; - p = add_object(obj, p, name); + p = add_object(obj, p, path, name); + me.up = path; + me.elem = name; + me.elem_len = strlen(name); entry = tree->entries; tree->entries = NULL; while (entry) { struct tree_entry_list *next = entry->next; if (entry->directory) - p = process_tree(entry->item.tree, p, entry->name); + p = process_tree(entry->item.tree, p, &me, entry->name); else - p = process_blob(entry->item.blob, p, entry->name); + p = process_blob(entry->item.blob, p, &me, entry->name); free(entry); entry = next; } return p; } -static struct object_list *pending_objects = NULL; - static void show_commit_list(struct commit_list *list) { struct object_list *objects = NULL, **p = &objects, *pending; while (list) { struct commit *commit = pop_most_recent_commit(&list, SEEN); - p = process_tree(commit->tree, p, ""); + p = process_tree(commit->tree, p, NULL, ""); if (process_commit(commit) == STOP) break; } - for (pending = pending_objects; pending; pending = pending->next) { + for (pending = revs.pending_objects; pending; pending = pending->next) { struct object *obj = pending->item; const char *name = pending->name; if (obj->flags & (UNINTERESTING | SEEN)) continue; if (obj->type == tag_type) { obj->flags |= SEEN; - p = add_object(obj, p, name); + p = add_object(obj, p, NULL, name); continue; } if (obj->type == tree_type) { - p = process_tree((struct tree *)obj, p, name); + p = process_tree((struct tree *)obj, p, NULL, name); continue; } if (obj->type == blob_type) { - p = process_blob((struct blob *)obj, p, name); + p = process_blob((struct blob *)obj, p, NULL, name); continue; } 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) { @@ -270,75 +259,6 @@ static void show_commit_list(struct commit_list *list) } } -static void mark_blob_uninteresting(struct blob *blob) -{ - if (!blob_objects) - return; - if (blob->object.flags & UNINTERESTING) - return; - blob->object.flags |= UNINTERESTING; -} - -static void mark_tree_uninteresting(struct tree *tree) -{ - struct object *obj = &tree->object; - struct tree_entry_list *entry; - - if (!tree_objects) - return; - if (obj->flags & UNINTERESTING) - return; - obj->flags |= UNINTERESTING; - if (!has_sha1_file(obj->sha1)) - return; - if (parse_tree(tree) < 0) - die("bad tree %s", sha1_to_hex(obj->sha1)); - entry = tree->entries; - tree->entries = NULL; - while (entry) { - struct tree_entry_list *next = entry->next; - if (entry->directory) - mark_tree_uninteresting(entry->item.tree); - else - mark_blob_uninteresting(entry->item.blob); - free(entry); - entry = next; - } -} - -static void mark_parents_uninteresting(struct commit *commit) -{ - struct commit_list *parents = commit->parents; - - while (parents) { - struct commit *commit = parents->item; - commit->object.flags |= UNINTERESTING; - - /* - * Normally we haven't parsed the parent - * yet, so we won't have a parent of a parent - * here. However, it may turn out that we've - * reached this commit some other way (where it - * wasn't uninteresting), in which case we need - * to mark its parents recursively too.. - */ - if (commit->parents) - mark_parents_uninteresting(commit); - - /* - * A missing commit is ok iff its parent is marked - * uninteresting. - * - * We just mark such a thing parsed, so that when - * it is popped next time around, we won't be trying - * to parse it and get an error. - */ - if (!has_sha1_file(commit->object.sha1)) - commit->object.parsed = 1; - parents = parents->next; - } -} - static int everybody_uninteresting(struct commit_list *orig) { struct commit_list *list = orig; @@ -369,7 +289,7 @@ static int count_distance(struct commit_list *entry) if (commit->object.flags & (UNINTERESTING | COUNTED)) break; - if (!paths || (commit->object.flags & TREECHANGE)) + if (!revs.paths || (commit->object.flags & TREECHANGE)) nr++; commit->object.flags |= COUNTED; p = commit->parents; @@ -403,7 +323,7 @@ static struct commit_list *find_bisection(struct commit_list *list) nr = 0; p = list; while (p) { - if (!paths || (p->item->object.flags & TREECHANGE)) + if (!revs.paths || (p->item->object.flags & TREECHANGE)) nr++; p = p->next; } @@ -413,7 +333,7 @@ static struct commit_list *find_bisection(struct commit_list *list) for (p = list; p; p = p->next) { int distance; - if (paths && !(p->item->object.flags & TREECHANGE)) + if (revs.paths && !(p->item->object.flags & TREECHANGE)) continue; distance = count_distance(p); @@ -430,16 +350,32 @@ 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 (revs.edge_hint && !(parent->object.flags & SHOWN)) { + parent->object.flags |= SHOWN; + 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); } } @@ -553,7 +489,7 @@ static void try_to_simplify_commit(struct commit *commit) return; case TREE_NEW: - if (remove_empty_trees && same_tree_as_empty(p->tree)) { + if (revs.remove_empty_trees && same_tree_as_empty(p->tree)) { *pp = parent->next; continue; } @@ -604,7 +540,7 @@ static void add_parents_to_list(struct commit *commit, struct commit_list **list * simplify the commit history and find the parent * that has no differences in the path set if one exists. */ - if (paths) + if (revs.paths) try_to_simplify_commit(commit); parent = commit->parents; @@ -633,9 +569,9 @@ static struct commit_list *limit_list(struct commit_list *list) list = list->next; free(entry); - if (max_age != -1 && (commit->date < max_age)) + if (revs.max_age != -1 && (commit->date < revs.max_age)) obj->flags |= UNINTERESTING; - if (unpacked && has_sha1_pack(obj->sha1)) + if (revs.unpacked && has_sha1_pack(obj->sha1)) obj->flags |= UNINTERESTING; add_parents_to_list(commit, &list); if (obj->flags & UNINTERESTING) { @@ -644,155 +580,40 @@ static struct commit_list *limit_list(struct commit_list *list) break; continue; } - if (min_age != -1 && (commit->date > min_age)) + if (revs.min_age != -1 && (commit->date > revs.min_age)) continue; p = &commit_list_insert(commit, p)->next; } - if (tree_objects) + if (revs.tree_objects) mark_edges_uninteresting(newlist); if (bisect_list) newlist = find_bisection(newlist); return newlist; } -static void add_pending_object(struct object *obj, const char *name) -{ - add_object(obj, &pending_objects, name); -} - -static struct commit *get_commit_reference(const char *name, const unsigned char *sha1, unsigned int flags) -{ - struct object *object; - - object = parse_object(sha1); - if (!object) - die("bad object %s", name); - - /* - * Tag object? Look what it points to.. - */ - while (object->type == tag_type) { - struct tag *tag = (struct tag *) object; - object->flags |= flags; - if (tag_objects && !(object->flags & UNINTERESTING)) - add_pending_object(object, tag->tag); - object = parse_object(tag->tagged->sha1); - if (!object) - die("bad object %s", sha1_to_hex(tag->tagged->sha1)); - } - - /* - * Commit object? Just return it, we'll do all the complex - * reachability crud. - */ - if (object->type == commit_type) { - struct commit *commit = (struct commit *)object; - object->flags |= flags; - if (parse_commit(commit) < 0) - die("unable to parse commit %s", name); - if (flags & UNINTERESTING) - mark_parents_uninteresting(commit); - return commit; - } - - /* - * Tree object? Either mark it uniniteresting, or add it - * to the list of objects to look at later.. - */ - if (object->type == tree_type) { - struct tree *tree = (struct tree *)object; - if (!tree_objects) - return NULL; - if (flags & UNINTERESTING) { - mark_tree_uninteresting(tree); - return NULL; - } - add_pending_object(object, ""); - return NULL; - } - - /* - * Blob object? You know the drill by now.. - */ - if (object->type == blob_type) { - struct blob *blob = (struct blob *)object; - if (!blob_objects) - return NULL; - if (flags & UNINTERESTING) { - mark_blob_uninteresting(blob); - return NULL; - } - add_pending_object(object, ""); - return NULL; - } - die("%s is unknown object", name); -} - -static void handle_one_commit(struct commit *com, struct commit_list **lst) -{ - if (!com || com->object.flags & SEEN) - return; - com->object.flags |= SEEN; - commit_list_insert(com, lst); -} - -/* for_each_ref() callback does not allow user data -- Yuck. */ -static struct commit_list **global_lst; - -static int include_one_commit(const char *path, const unsigned char *sha1) -{ - struct commit *com = get_commit_reference(path, sha1, 0); - handle_one_commit(com, global_lst); - return 0; -} - -static void handle_all(struct commit_list **lst) -{ - global_lst = lst; - for_each_ref(include_one_commit); - global_lst = NULL; -} - int main(int argc, const char **argv) { - const char *prefix = setup_git_directory(); - struct commit_list *list = NULL; - int i, limited = 0; + struct commit_list *list; + int i; + + argc = setup_revisions(argc, argv, &revs); for (i = 1 ; i < argc; i++) { - int flags; const char *arg = argv[i]; - char *dotdot; - struct commit *commit; - unsigned char sha1[20]; /* accept -<digit>, like traditilnal "head" */ if ((*arg == '-') && isdigit(arg[1])) { - max_count = atoi(arg + 1); + revs.max_count = atoi(arg + 1); continue; } if (!strcmp(arg, "-n")) { if (++i >= argc) die("-n requires an argument"); - max_count = atoi(argv[i]); + revs.max_count = atoi(argv[i]); continue; } if (!strncmp(arg,"-n",2)) { - max_count = atoi(arg + 2); - continue; - } - if (!strncmp(arg, "--max-count=", 12)) { - max_count = atoi(arg + 12); - continue; - } - if (!strncmp(arg, "--max-age=", 10)) { - max_age = atoi(arg + 10); - limited = 1; - continue; - } - if (!strncmp(arg, "--min-age=", 10)) { - min_age = atoi(arg + 10); - limited = 1; + revs.max_count = atoi(arg + 2); continue; } if (!strcmp(arg, "--header")) { @@ -833,21 +654,6 @@ int main(int argc, const char **argv) bisect_list = 1; continue; } - if (!strcmp(arg, "--all")) { - handle_all(&list); - continue; - } - if (!strcmp(arg, "--objects")) { - tag_objects = 1; - tree_objects = 1; - blob_objects = 1; - continue; - } - if (!strcmp(arg, "--unpacked")) { - unpacked = 1; - limited = 1; - continue; - } if (!strcmp(arg, "--merge-order")) { merge_order = 1; continue; @@ -856,100 +662,33 @@ int main(int argc, const char **argv) show_breaks = 1; continue; } - if (!strcmp(arg, "--topo-order")) { - topo_order = 1; - lifo = 1; - limited = 1; - continue; - } - if (!strcmp(arg, "--date-order")) { - topo_order = 1; - lifo = 0; - limited = 1; - continue; - } - if (!strcmp(arg, "--dense")) { - dense = 1; - continue; - } - if (!strcmp(arg, "--sparse")) { - dense = 0; - continue; - } - if (!strcmp(arg, "--remove-empty")) { - remove_empty_trees = 1; - continue; - } - if (!strcmp(arg, "--")) { - i++; - break; - } + usage(rev_list_usage); - if (show_breaks && !merge_order) - usage(rev_list_usage); - - flags = 0; - dotdot = strstr(arg, ".."); - if (dotdot) { - unsigned char from_sha1[20]; - char *next = dotdot + 2; - *dotdot = 0; - if (!*next) - next = "HEAD"; - if (!get_sha1(arg, from_sha1) && !get_sha1(next, sha1)) { - struct commit *exclude; - struct commit *include; - - exclude = get_commit_reference(arg, from_sha1, UNINTERESTING); - include = get_commit_reference(next, sha1, 0); - if (!exclude || !include) - die("Invalid revision range %s..%s", arg, next); - limited = 1; - handle_one_commit(exclude, &list); - handle_one_commit(include, &list); - continue; - } - *dotdot = '.'; - } - if (*arg == '^') { - flags = UNINTERESTING; - arg++; - limited = 1; - } - if (get_sha1(arg, sha1) < 0) { - struct stat st; - if (lstat(arg, &st) < 0) - die("'%s': %s", arg, strerror(errno)); - break; - } - commit = get_commit_reference(arg, sha1, flags); - handle_one_commit(commit, &list); } + list = revs.commits; + if (!list && - (!(tag_objects||tree_objects||blob_objects) && !pending_objects)) + (!(revs.tag_objects||revs.tree_objects||revs.blob_objects) && !revs.pending_objects)) usage(rev_list_usage); - paths = get_pathspec(prefix, argv + i); - if (paths) { - limited = 1; - diff_tree_setup_paths(paths); - } + if (revs.paths) + diff_tree_setup_paths(revs.paths); save_commit_buffer = verbose_header; track_object_refs = 0; if (!merge_order) { sort_by_date(&list); - if (list && !limited && max_count == 1 && - !tag_objects && !tree_objects && !blob_objects) { + if (list && !revs.limited && revs.max_count == 1 && + !revs.tag_objects && !revs.tree_objects && !revs.blob_objects) { show_commit(list->item); return 0; } - if (limited) + if (revs.limited) list = limit_list(list); - if (topo_order) - sort_in_topological_order(&list, lifo); + if (revs.topo_order) + sort_in_topological_order(&list, revs.lifo); show_commit_list(list); } else { #ifndef NO_OPENSSL 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/revision.c b/revision.c new file mode 100644 index 0000000000..67ff4de2d1 --- /dev/null +++ b/revision.c @@ -0,0 +1,383 @@ +#include "cache.h" +#include "tag.h" +#include "blob.h" +#include "tree.h" +#include "commit.h" +#include "refs.h" +#include "revision.h" + +static char *path_name(struct name_path *path, const char *name) +{ + struct name_path *p; + char *n, *m; + int nlen = strlen(name); + int len = nlen + 1; + + for (p = path; p; p = p->up) { + if (p->elem_len) + len += p->elem_len + 1; + } + n = xmalloc(len); + m = n + len - (nlen + 1); + strcpy(m, name); + for (p = path; p; p = p->up) { + if (p->elem_len) { + m -= p->elem_len + 1; + memcpy(m, p->elem, p->elem_len); + m[p->elem_len] = '/'; + } + } + return n; +} + +struct object_list **add_object(struct object *obj, + struct object_list **p, + struct name_path *path, + const char *name) +{ + struct object_list *entry = xmalloc(sizeof(*entry)); + entry->item = obj; + entry->next = *p; + entry->name = path_name(path, name); + *p = entry; + return &entry->next; +} + +static void mark_blob_uninteresting(struct blob *blob) +{ + if (blob->object.flags & UNINTERESTING) + return; + blob->object.flags |= UNINTERESTING; +} + +void mark_tree_uninteresting(struct tree *tree) +{ + struct object *obj = &tree->object; + struct tree_entry_list *entry; + + if (obj->flags & UNINTERESTING) + return; + obj->flags |= UNINTERESTING; + if (!has_sha1_file(obj->sha1)) + return; + if (parse_tree(tree) < 0) + die("bad tree %s", sha1_to_hex(obj->sha1)); + entry = tree->entries; + tree->entries = NULL; + while (entry) { + struct tree_entry_list *next = entry->next; + if (entry->directory) + mark_tree_uninteresting(entry->item.tree); + else + mark_blob_uninteresting(entry->item.blob); + free(entry); + entry = next; + } +} + +void mark_parents_uninteresting(struct commit *commit) +{ + struct commit_list *parents = commit->parents; + + while (parents) { + struct commit *commit = parents->item; + commit->object.flags |= UNINTERESTING; + + /* + * Normally we haven't parsed the parent + * yet, so we won't have a parent of a parent + * here. However, it may turn out that we've + * reached this commit some other way (where it + * wasn't uninteresting), in which case we need + * to mark its parents recursively too.. + */ + if (commit->parents) + mark_parents_uninteresting(commit); + + /* + * A missing commit is ok iff its parent is marked + * uninteresting. + * + * We just mark such a thing parsed, so that when + * it is popped next time around, we won't be trying + * to parse it and get an error. + */ + if (!has_sha1_file(commit->object.sha1)) + commit->object.parsed = 1; + parents = parents->next; + } +} + +static void add_pending_object(struct rev_info *revs, struct object *obj, const char *name) +{ + add_object(obj, &revs->pending_objects, NULL, name); +} + +static struct commit *get_commit_reference(struct rev_info *revs, const char *name, const unsigned char *sha1, unsigned int flags) +{ + struct object *object; + + object = parse_object(sha1); + if (!object) + die("bad object %s", name); + + /* + * Tag object? Look what it points to.. + */ + while (object->type == tag_type) { + struct tag *tag = (struct tag *) object; + object->flags |= flags; + if (revs->tag_objects && !(object->flags & UNINTERESTING)) + add_pending_object(revs, object, tag->tag); + object = parse_object(tag->tagged->sha1); + if (!object) + die("bad object %s", sha1_to_hex(tag->tagged->sha1)); + } + + /* + * Commit object? Just return it, we'll do all the complex + * reachability crud. + */ + if (object->type == commit_type) { + struct commit *commit = (struct commit *)object; + object->flags |= flags; + if (parse_commit(commit) < 0) + die("unable to parse commit %s", name); + if (flags & UNINTERESTING) { + mark_parents_uninteresting(commit); + revs->limited = 1; + } + return commit; + } + + /* + * Tree object? Either mark it uniniteresting, or add it + * to the list of objects to look at later.. + */ + if (object->type == tree_type) { + struct tree *tree = (struct tree *)object; + if (!revs->tree_objects) + return NULL; + if (flags & UNINTERESTING) { + mark_tree_uninteresting(tree); + return NULL; + } + add_pending_object(revs, object, ""); + return NULL; + } + + /* + * Blob object? You know the drill by now.. + */ + if (object->type == blob_type) { + struct blob *blob = (struct blob *)object; + if (!revs->blob_objects) + return NULL; + if (flags & UNINTERESTING) { + mark_blob_uninteresting(blob); + return NULL; + } + add_pending_object(revs, object, ""); + return NULL; + } + die("%s is unknown object", name); +} + +static void add_one_commit(struct commit *commit, struct rev_info *revs) +{ + if (!commit || (commit->object.flags & SEEN)) + return; + commit->object.flags |= SEEN; + commit_list_insert(commit, &revs->commits); +} + +static int all_flags; +static struct rev_info *all_revs; + +static int handle_one_ref(const char *path, const unsigned char *sha1) +{ + struct commit *commit = get_commit_reference(all_revs, path, sha1, all_flags); + add_one_commit(commit, all_revs); + return 0; +} + +static void handle_all(struct rev_info *revs, unsigned flags) +{ + all_revs = revs; + all_flags = flags; + for_each_ref(handle_one_ref); +} + +/* + * Parse revision information, filling in the "rev_info" structure, + * and removing the used arguments from the argument list. + * + * Returns the number of arguments left ("new argc"). + */ +int setup_revisions(int argc, const char **argv, struct rev_info *revs) +{ + int i, flags, seen_dashdash; + const char *def = NULL; + const char **unrecognized = argv+1; + int left = 1; + + memset(revs, 0, sizeof(*revs)); + revs->lifo = 1; + revs->dense = 1; + revs->prefix = setup_git_directory(); + revs->max_age = -1; + revs->min_age = -1; + revs->max_count = -1; + + /* First, search for "--" */ + seen_dashdash = 0; + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (strcmp(arg, "--")) + continue; + argv[i] = NULL; + argc = i; + revs->paths = get_pathspec(revs->prefix, argv + i + 1); + seen_dashdash = 1; + break; + } + + flags = 0; + for (i = 1; i < argc; i++) { + struct commit *commit; + const char *arg = argv[i]; + unsigned char sha1[20]; + char *dotdot; + int local_flags; + + if (*arg == '-') { + if (!strncmp(arg, "--max-count=", 12)) { + revs->max_count = atoi(arg + 12); + continue; + } + if (!strncmp(arg, "--max-age=", 10)) { + revs->max_age = atoi(arg + 10); + revs->limited = 1; + continue; + } + if (!strncmp(arg, "--min-age=", 10)) { + revs->min_age = atoi(arg + 10); + revs->limited = 1; + continue; + } + if (!strcmp(arg, "--all")) { + handle_all(revs, flags); + continue; + } + if (!strcmp(arg, "--not")) { + flags ^= UNINTERESTING; + continue; + } + if (!strcmp(arg, "--default")) { + if (++i >= argc) + die("bad --default argument"); + def = argv[i]; + continue; + } + if (!strcmp(arg, "--topo-order")) { + revs->topo_order = 1; + revs->limited = 1; + continue; + } + if (!strcmp(arg, "--date-order")) { + revs->lifo = 0; + revs->topo_order = 1; + revs->limited = 1; + continue; + } + if (!strcmp(arg, "--dense")) { + revs->dense = 1; + continue; + } + if (!strcmp(arg, "--sparse")) { + revs->dense = 0; + continue; + } + if (!strcmp(arg, "--remove-empty")) { + revs->remove_empty_trees = 1; + continue; + } + if (!strcmp(arg, "--objects")) { + revs->tag_objects = 1; + revs->tree_objects = 1; + revs->blob_objects = 1; + continue; + } + if (!strcmp(arg, "--objects-edge")) { + revs->tag_objects = 1; + revs->tree_objects = 1; + revs->blob_objects = 1; + revs->edge_hint = 1; + continue; + } + if (!strcmp(arg, "--unpacked")) { + revs->unpacked = 1; + revs->limited = 1; + continue; + } + *unrecognized++ = arg; + left++; + continue; + } + dotdot = strstr(arg, ".."); + if (dotdot) { + unsigned char from_sha1[20]; + char *next = dotdot + 2; + *dotdot = 0; + if (!*next) + next = "HEAD"; + if (!get_sha1(arg, from_sha1) && !get_sha1(next, sha1)) { + struct commit *exclude; + struct commit *include; + + exclude = get_commit_reference(revs, arg, from_sha1, flags ^ UNINTERESTING); + include = get_commit_reference(revs, next, sha1, flags); + if (!exclude || !include) + die("Invalid revision range %s..%s", arg, next); + add_one_commit(exclude, revs); + add_one_commit(include, revs); + continue; + } + *dotdot = '.'; + } + local_flags = 0; + if (*arg == '^') { + local_flags = UNINTERESTING; + arg++; + } + if (get_sha1(arg, sha1) < 0) { + struct stat st; + int j; + + if (seen_dashdash || local_flags) + die("bad revision '%s'", arg); + + /* If we didn't have a "--", all filenames must exist */ + for (j = i; j < argc; j++) { + if (lstat(argv[j], &st) < 0) + die("'%s': %s", arg, strerror(errno)); + } + revs->paths = get_pathspec(revs->prefix, argv + i); + break; + } + commit = get_commit_reference(revs, arg, sha1, flags ^ local_flags); + add_one_commit(commit, revs); + } + if (def && !revs->commits) { + unsigned char sha1[20]; + struct commit *commit; + if (get_sha1(def, sha1) < 0) + die("bad default revision '%s'", def); + commit = get_commit_reference(revs, def, sha1, 0); + add_one_commit(commit, revs); + } + if (revs->paths) + revs->limited = 1; + *unrecognized = NULL; + return left; +} diff --git a/revision.h b/revision.h new file mode 100644 index 0000000000..a22f198515 --- /dev/null +++ b/revision.h @@ -0,0 +1,50 @@ +#ifndef REVISION_H +#define REVISION_H + +#define SEEN (1u<<0) +#define UNINTERESTING (1u<<1) + +struct rev_info { + /* Starting list */ + struct commit_list *commits; + struct object_list *pending_objects; + + /* Basic information */ + const char *prefix; + const char **paths; + + /* Traversal flags */ + unsigned int dense:1, + remove_empty_trees:1, + lifo:1, + topo_order:1, + tag_objects:1, + tree_objects:1, + blob_objects:1, + edge_hint:1, + limited:1, + unpacked:1; + + /* special limits */ + int max_count; + unsigned long max_age; + unsigned long min_age; +}; + +/* revision.c */ +extern int setup_revisions(int argc, const char **argv, struct rev_info *revs); +extern void mark_parents_uninteresting(struct commit *commit); +extern void mark_tree_uninteresting(struct tree *tree); + +struct name_path { + struct name_path *up; + int elem_len; + const char *elem; +}; + +extern struct object_list **add_object(struct object *obj, + struct object_list **p, + struct name_path *path, + const char *name); + +#endif 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 9cab99ae7c..a80d849f15 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -247,6 +247,7 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep, for ( ; cp < ep && *cp != sep; cp++) ; if (last != cp) { + struct stat st; struct alternate_object_database *alt; /* 43 = 40-byte + 2 '/' + terminating NUL */ int pfxlen = cp - last; @@ -269,9 +270,19 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep, } else memcpy(ent->base, last, pfxlen); + ent->name = ent->base + pfxlen + 1; - ent->base[pfxlen] = ent->base[pfxlen + 3] = '/'; - ent->base[entlen-1] = 0; + ent->base[pfxlen + 3] = '/'; + ent->base[pfxlen] = ent->base[entlen-1] = 0; + + /* Detect cases where alternate disappeared */ + if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) { + error("object directory %s does not exist; " + "check .git/objects/info/alternates.", + ent->base); + goto bad; + } + ent->base[pfxlen] = '/'; /* Prevent the common mistake of listing the same * thing twice, or object directory itself. @@ -552,7 +563,9 @@ static void prepare_packed_git_one(char *objdir, int local) len = strlen(path); dir = opendir(path); if (!dir) { - fprintf(stderr, "unable to open object pack directory: %s: %s\n", path, strerror(errno)); + if (errno != ENOENT) + error("unable to open object pack directory: %s: %s", + path, strerror(errno)); return; } path[len++] = '/'; @@ -1500,7 +1513,8 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer, local = mkstemp(tmpfile); if (local < 0) - return error("Couldn't open %s for %s\n", tmpfile, sha1_to_hex(sha1)); + return error("Couldn't open %s for %s", + tmpfile, sha1_to_hex(sha1)); memset(&stream, 0, sizeof(stream)); @@ -1548,7 +1562,7 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer, } if (memcmp(sha1, real_sha1, 20)) { unlink(tmpfile); - return error("File %s has bad hash\n", sha1_to_hex(sha1)); + return error("File %s has bad hash", sha1_to_hex(sha1)); } return move_temp_to_file(tmpfile, sha1_file_name(sha1)); diff --git a/t/t3600-rm.sh b/t/t3600-rm.sh new file mode 100755 index 0000000000..cabfadd56d --- /dev/null +++ b/t/t3600-rm.sh @@ -0,0 +1,60 @@ +#!/bin/sh +# +# Copyright (c) 2006 Carl D. Worth +# + +test_description='Test of the various options to git-rm.' + +. ./test-lib.sh + +# Setup some files to be removed, some with funny characters +touch -- foo bar baz 'space embedded' 'tab embedded' 'newline +embedded' -q +git-add -- foo bar baz 'space embedded' 'tab embedded' 'newline +embedded' -q +git-commit -m "add files" + +test_expect_success \ + 'Pre-check that foo exists and is in index before git-rm foo' \ + '[ -f foo ] && git-ls-files --error-unmatch foo' + +test_expect_success \ + 'Test that git-rm foo succeeds' \ + 'git-rm foo' + +test_expect_success \ + 'Post-check that foo exists but is not in index after git-rm foo' \ + '[ -f foo ] && ! git-ls-files --error-unmatch foo' + +test_expect_success \ + 'Pre-check that bar exists and is in index before "git-rm -f bar"' \ + '[ -f bar ] && git-ls-files --error-unmatch bar' + +test_expect_success \ + 'Test that "git-rm -f bar" succeeds' \ + 'git-rm -f bar' + +test_expect_success \ + 'Post-check that bar does not exist and is not in index after "git-rm -f bar"' \ + '! [ -f bar ] && ! git-ls-files --error-unmatch bar' + +test_expect_success \ + 'Test that "git-rm -- -q" succeeds (remove a file that looks like an option)' \ + 'git-rm -- -q' + +test_expect_success \ + "Test that \"git-rm -f\" succeeds with embedded space, tab, or newline characters." \ + "git-rm -f 'space embedded' 'tab embedded' 'newline +embedded'" + +chmod u-w . +test_expect_failure \ + 'Test that "git-rm -f" fails if its rm fails' \ + 'git-rm -f baz' +chmod u+w . + +test_expect_success \ + 'When the rm in "git-rm -f" fails, it should not remove the file from the index' \ + 'git-ls-files --error-unmatch baz' + +test_done diff --git a/templates/hooks--applypatch-msg b/templates/hooks--applypatch-msg index bda3c86be7..02de1ef84c 100644 --- a/templates/hooks--applypatch-msg +++ b/templates/hooks--applypatch-msg @@ -9,6 +9,7 @@ # # To enable this hook, make this file executable. +. git-sh-setup test -x "$GIT_DIR/hooks/commit-msg" && exec "$GIT_DIR/hooks/commit-msg" ${1+"$@"} : diff --git a/templates/hooks--pre-applypatch b/templates/hooks--pre-applypatch index a54751600e..5f56ce8053 100644 --- a/templates/hooks--pre-applypatch +++ b/templates/hooks--pre-applypatch @@ -8,6 +8,7 @@ # # To enable this hook, make this file executable. +. git-sh-setup test -x "$GIT_DIR/hooks/pre-commit" && exec "$GIT_DIR/hooks/pre-commit" ${1+"$@"} : 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) |