From 217542640ed219c980fff2b3c307c4520120f20f Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 18 May 2006 18:46:44 -0700 Subject: built-in tar-tree and remote tar-tree This makes tar-tree a built-in. As an added bonus, you can now say: git tar-tree --remote=remote-repository [] This does not work with git-daemon yet, but should work with localhost and git over ssh transports. Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index 4fd6520..f4bcec4 100644 --- a/Makefile +++ b/Makefile @@ -161,7 +161,7 @@ PROGRAMS = \ git-receive-pack$X git-rev-parse$X \ git-send-pack$X git-show-branch$X git-shell$X \ git-show-index$X git-ssh-fetch$X \ - git-ssh-upload$X git-tar-tree$X git-unpack-file$X \ + git-ssh-upload$X git-unpack-file$X \ git-unpack-objects$X git-update-index$X git-update-server-info$X \ git-upload-pack$X git-verify-pack$X git-write-tree$X \ git-update-ref$X git-symbolic-ref$X \ @@ -171,7 +171,7 @@ PROGRAMS = \ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-count-objects$X git-diff$X git-push$X \ git-grep$X git-rev-list$X git-check-ref-format$X \ - git-init-db$X + git-init-db$X git-tar-tree$X git-upload-tar$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -220,7 +220,7 @@ LIB_OBJS = \ BUILTIN_OBJS = \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ - builtin-init-db.o + builtin-init-db.o builtin-tar-tree.o builtin-upload-tar.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-tar-tree.c b/builtin-tar-tree.c new file mode 100644 index 0000000..e97e0af --- /dev/null +++ b/builtin-tar-tree.c @@ -0,0 +1,408 @@ +/* + * Copyright (c) 2005, 2006 Rene Scharfe + */ +#include +#include "cache.h" +#include "tree-walk.h" +#include "commit.h" +#include "strbuf.h" +#include "tar.h" +#include "builtin.h" +#include "pkt-line.h" + +#define RECORDSIZE (512) +#define BLOCKSIZE (RECORDSIZE * 20) + +static const char tar_tree_usage[] = +"git-tar-tree [--remote=] [basedir]"; + +static char block[BLOCKSIZE]; +static unsigned long offset; + +static time_t archive_time; + +/* tries hard to write, either succeeds or dies in the attempt */ +static void reliable_write(void *buf, unsigned long size) +{ + while (size > 0) { + long ret = xwrite(1, buf, size); + if (ret < 0) { + if (errno == EPIPE) + exit(0); + die("git-tar-tree: %s", strerror(errno)); + } else if (!ret) { + die("git-tar-tree: disk full?"); + } + size -= ret; + buf += ret; + } +} + +/* writes out the whole block, but only if it is full */ +static void write_if_needed(void) +{ + if (offset == BLOCKSIZE) { + reliable_write(block, BLOCKSIZE); + offset = 0; + } +} + +/* acquire the next record from the buffer; user must call write_if_needed() */ +static char *get_record(void) +{ + char *p = block + offset; + memset(p, 0, RECORDSIZE); + offset += RECORDSIZE; + return p; +} + +/* + * The end of tar archives is marked by 1024 nul bytes and after that + * follows the rest of the block (if any). + */ +static void write_trailer(void) +{ + get_record(); + write_if_needed(); + get_record(); + write_if_needed(); + while (offset) { + get_record(); + write_if_needed(); + } +} + +/* + * queues up writes, so that all our write(2) calls write exactly one + * full block; pads writes to RECORDSIZE + */ +static void write_blocked(void *buf, unsigned long size) +{ + unsigned long tail; + + if (offset) { + unsigned long chunk = BLOCKSIZE - offset; + if (size < chunk) + chunk = size; + memcpy(block + offset, buf, chunk); + size -= chunk; + offset += chunk; + buf += chunk; + write_if_needed(); + } + while (size >= BLOCKSIZE) { + reliable_write(buf, BLOCKSIZE); + size -= BLOCKSIZE; + buf += BLOCKSIZE; + } + if (size) { + memcpy(block + offset, buf, size); + offset += size; + } + tail = offset % RECORDSIZE; + if (tail) { + memset(block + offset, 0, RECORDSIZE - tail); + offset += RECORDSIZE - tail; + } + write_if_needed(); +} + +static void strbuf_append_string(struct strbuf *sb, const char *s) +{ + int slen = strlen(s); + int total = sb->len + slen; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; + } + memcpy(sb->buf + sb->len, s, slen); + sb->len = total; +} + +/* + * pax extended header records have the format "%u %s=%s\n". %u contains + * the size of the whole string (including the %u), the first %s is the + * keyword, the second one is the value. This function constructs such a + * string and appends it to a struct strbuf. + */ +static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword, + const char *value, unsigned int valuelen) +{ + char *p; + int len, total, tmp; + + /* "%u %s=%s\n" */ + len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; + for (tmp = len; tmp > 9; tmp /= 10) + len++; + + total = sb->len + len; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; + } + + p = sb->buf; + p += sprintf(p, "%u %s=", len, keyword); + memcpy(p, value, valuelen); + p += valuelen; + *p = '\n'; + sb->len = total; +} + +static unsigned int ustar_header_chksum(const struct ustar_header *header) +{ + char *p = (char *)header; + unsigned int chksum = 0; + while (p < header->chksum) + chksum += *p++; + chksum += sizeof(header->chksum) * ' '; + p += sizeof(header->chksum); + while (p < (char *)header + sizeof(struct ustar_header)) + chksum += *p++; + return chksum; +} + +static int get_path_prefix(const struct strbuf *path, int maxlen) +{ + int i = path->len; + if (i > maxlen) + i = maxlen; + while (i > 0 && path->buf[i] != '/') + i--; + return i; +} + +static void write_entry(const unsigned char *sha1, struct strbuf *path, + unsigned int mode, void *buffer, unsigned long size) +{ + struct ustar_header header; + struct strbuf ext_header; + + memset(&header, 0, sizeof(header)); + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + + if (!sha1) { + *header.typeflag = TYPEFLAG_GLOBAL_HEADER; + mode = 0100666; + strcpy(header.name, "pax_global_header"); + } else if (!path) { + *header.typeflag = TYPEFLAG_EXT_HEADER; + mode = 0100666; + sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1)); + } else { + if (S_ISDIR(mode)) { + *header.typeflag = TYPEFLAG_DIR; + mode |= 0777; + } else if (S_ISLNK(mode)) { + *header.typeflag = TYPEFLAG_LNK; + mode |= 0777; + } else if (S_ISREG(mode)) { + *header.typeflag = TYPEFLAG_REG; + mode |= (mode & 0100) ? 0777 : 0666; + } else { + error("unsupported file mode: 0%o (SHA1: %s)", + mode, sha1_to_hex(sha1)); + return; + } + if (path->len > sizeof(header.name)) { + int plen = get_path_prefix(path, sizeof(header.prefix)); + int rest = path->len - plen - 1; + if (plen > 0 && rest <= sizeof(header.name)) { + memcpy(header.prefix, path->buf, plen); + memcpy(header.name, path->buf + plen + 1, rest); + } else { + sprintf(header.name, "%s.data", + sha1_to_hex(sha1)); + strbuf_append_ext_header(&ext_header, "path", + path->buf, path->len); + } + } else + memcpy(header.name, path->buf, path->len); + } + + if (S_ISLNK(mode) && buffer) { + if (size > sizeof(header.linkname)) { + sprintf(header.linkname, "see %s.paxheader", + sha1_to_hex(sha1)); + strbuf_append_ext_header(&ext_header, "linkpath", + buffer, size); + } else + memcpy(header.linkname, buffer, size); + } + + sprintf(header.mode, "%07o", mode & 07777); + sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0); + sprintf(header.mtime, "%011lo", archive_time); + + /* XXX: should we provide more meaningful info here? */ + sprintf(header.uid, "%07o", 0); + sprintf(header.gid, "%07o", 0); + strncpy(header.uname, "git", 31); + strncpy(header.gname, "git", 31); + sprintf(header.devmajor, "%07o", 0); + sprintf(header.devminor, "%07o", 0); + + memcpy(header.magic, "ustar", 6); + memcpy(header.version, "00", 2); + + sprintf(header.chksum, "%07o", ustar_header_chksum(&header)); + + if (ext_header.len > 0) { + write_entry(sha1, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); + } + write_blocked(&header, sizeof(header)); + if (S_ISREG(mode) && buffer && size > 0) + write_blocked(buffer, size); +} + +static void write_global_extended_header(const unsigned char *sha1) +{ + struct strbuf ext_header; + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); + write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); +} + +static void traverse_tree(struct tree_desc *tree, struct strbuf *path) +{ + int pathlen = path->len; + + while (tree->size) { + const char *name; + const unsigned char *sha1; + unsigned mode; + void *eltbuf; + char elttype[20]; + unsigned long eltsize; + + sha1 = tree_entry_extract(tree, &name, &mode); + update_tree_entry(tree); + + eltbuf = read_sha1_file(sha1, elttype, &eltsize); + if (!eltbuf) + die("cannot read %s", sha1_to_hex(sha1)); + + path->len = pathlen; + strbuf_append_string(path, name); + if (S_ISDIR(mode)) + strbuf_append_string(path, "/"); + + write_entry(sha1, path, mode, eltbuf, eltsize); + + if (S_ISDIR(mode)) { + struct tree_desc subtree; + subtree.buf = eltbuf; + subtree.size = eltsize; + traverse_tree(&subtree, path); + } + free(eltbuf); + } +} + +int generate_tar(int argc, const char **argv) +{ + unsigned char sha1[20], tree_sha1[20]; + struct commit *commit; + struct tree_desc tree; + struct strbuf current_path; + + current_path.buf = xmalloc(PATH_MAX); + current_path.alloc = PATH_MAX; + current_path.len = current_path.eof = 0; + + setup_git_directory(); + git_config(git_default_config); + + switch (argc) { + case 3: + strbuf_append_string(¤t_path, argv[2]); + strbuf_append_string(¤t_path, "/"); + /* FALLTHROUGH */ + case 2: + if (get_sha1(argv[1], sha1)) + die("Not a valid object name %s", argv[1]); + break; + default: + usage(tar_tree_usage); + } + + commit = lookup_commit_reference_gently(sha1, 1); + if (commit) { + write_global_extended_header(commit->object.sha1); + archive_time = commit->date; + } else + archive_time = time(NULL); + + tree.buf = read_object_with_reference(sha1, tree_type, &tree.size, + tree_sha1); + if (!tree.buf) + die("not a reference to a tag, commit or tree object: %s", + sha1_to_hex(sha1)); + + if (current_path.len > 0) + write_entry(tree_sha1, ¤t_path, 040777, NULL, 0); + traverse_tree(&tree, ¤t_path); + write_trailer(); + free(current_path.buf); + return 0; +} + +static const char *exec = "git-upload-tar"; + +static int remote_tar(int argc, const char **argv) +{ + int fd[2], ret, len; + pid_t pid; + char buf[1024]; + char *url; + + if (argc < 3 || 4 < argc) + usage(tar_tree_usage); + + /* --remote= */ + url = strdup(argv[1]+9); + pid = git_connect(fd, url, exec); + if (pid < 0) + return 1; + + packet_write(fd[1], "want %s\n", argv[2]); + if (argv[3]) + packet_write(fd[1], "base %s\n", argv[3]); + packet_flush(fd[1]); + + len = packet_read_line(fd[0], buf, sizeof(buf)); + if (!len) + die("git-tar-tree: expected ACK/NAK, got EOF"); + if (buf[len-1] == '\n') + buf[--len] = 0; + if (strcmp(buf, "ACK")) { + if (5 < len && !strncmp(buf, "NACK ", 5)) + die("git-tar-tree: NACK %s", buf + 5); + die("git-tar-tree: protocol error"); + } + /* expect a flush */ + len = packet_read_line(fd[0], buf, sizeof(buf)); + if (len) + die("git-tar-tree: expected a flush"); + + /* Now, start reading from fd[0] and spit it out to stdout */ + ret = copy_fd(fd[0], 1); + close(fd[0]); + + ret |= finish_connect(pid); + return !!ret; +} + +int cmd_tar_tree(int argc, const char **argv, char **envp) +{ + if (argc < 2) + usage(tar_tree_usage); + if (!strncmp("--remote=", argv[1], 9)) + return remote_tar(argc, argv); + return generate_tar(argc, argv); +} diff --git a/builtin-upload-tar.c b/builtin-upload-tar.c new file mode 100644 index 0000000..d4fa7b5 --- /dev/null +++ b/builtin-upload-tar.c @@ -0,0 +1,74 @@ +/* + * Copyright (c) 2006 Junio C Hamano + */ +#include "cache.h" +#include "pkt-line.h" +#include "exec_cmd.h" +#include "builtin.h" + +static const char upload_tar_usage[] = "git-upload-tar "; + +static int nak(const char *reason) +{ + packet_write(1, "NACK %s\n", reason); + packet_flush(1); + return 1; +} + +int cmd_upload_tar(int argc, const char **argv, char **envp) +{ + int len; + const char *dir = argv[1]; + char buf[8192]; + unsigned char sha1[20]; + char *base = NULL; + char hex[41]; + int ac; + const char *av[4]; + + if (argc != 2) + usage(upload_tar_usage); + if (strlen(dir) < sizeof(buf)-1) + strcpy(buf, dir); /* enter-repo smudges its argument */ + else + packet_write(1, "NACK insanely long repository name %s\n", dir); + if (!enter_repo(buf, 0)) { + packet_write(1, "NACK not a git archive %s\n", dir); + packet_flush(1); + return 1; + } + + len = packet_read_line(0, buf, sizeof(buf)); + if (len < 5 || strncmp("want ", buf, 5)) + return nak("expected want"); + if (buf[len-1] == '\n') + buf[--len] = 0; + if (get_sha1(buf + 5, sha1)) + return nak("expected sha1"); + strcpy(hex, sha1_to_hex(sha1)); + + len = packet_read_line(0, buf, sizeof(buf)); + if (len) { + if (len < 5 || strncmp("base ", buf, 5)) + return nak("expected (optional) base"); + if (buf[len-1] == '\n') + buf[--len] = 0; + base = strdup(buf + 5); + len = packet_read_line(0, buf, sizeof(buf)); + } + if (len) + return nak("expected flush"); + + packet_write(1, "ACK\n"); + packet_flush(1); + + ac = 0; + av[ac++] = "tar-tree"; + av[ac++] = hex; + if (base) + av[ac++] = base; + av[ac++] = NULL; + execv_git_cmd(av); + /* should it return that is an error */ + return 1; +} diff --git a/builtin.h b/builtin.h index 6054126..f22783c 100644 --- a/builtin.h +++ b/builtin.h @@ -27,5 +27,7 @@ extern int cmd_grep(int argc, const char **argv, char **envp); extern int cmd_rev_list(int argc, const char **argv, char **envp); extern int cmd_check_ref_format(int argc, const char **argv, char **envp); extern int cmd_init_db(int argc, const char **argv, char **envp); +extern int cmd_tar_tree(int argc, const char **argv, char **envp); +extern int cmd_upload_tar(int argc, const char **argv, char **envp); #endif diff --git a/git.c b/git.c index 3216d31..fd8e9bf 100644 --- a/git.c +++ b/git.c @@ -50,8 +50,10 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "count-objects", cmd_count_objects }, { "diff", cmd_diff }, { "grep", cmd_grep }, - { "rev-list", cmd_rev_list }, { "init-db", cmd_init_db }, + { "tar-tree", cmd_tar_tree }, + { "upload-tar", cmd_upload_tar }, + { "rev-list", cmd_rev_list }, { "check-ref-format", cmd_check_ref_format } }; int i; diff --git a/tar-tree.c b/tar-tree.c deleted file mode 100644 index 3308736..0000000 --- a/tar-tree.c +++ /dev/null @@ -1,350 +0,0 @@ -/* - * Copyright (c) 2005, 2006 Rene Scharfe - */ -#include -#include "cache.h" -#include "tree-walk.h" -#include "commit.h" -#include "strbuf.h" -#include "tar.h" - -#define RECORDSIZE (512) -#define BLOCKSIZE (RECORDSIZE * 20) - -static const char tar_tree_usage[] = "git-tar-tree [basedir]"; - -static char block[BLOCKSIZE]; -static unsigned long offset; - -static time_t archive_time; - -/* tries hard to write, either succeeds or dies in the attempt */ -static void reliable_write(void *buf, unsigned long size) -{ - while (size > 0) { - long ret = xwrite(1, buf, size); - if (ret < 0) { - if (errno == EPIPE) - exit(0); - die("git-tar-tree: %s", strerror(errno)); - } else if (!ret) { - die("git-tar-tree: disk full?"); - } - size -= ret; - buf += ret; - } -} - -/* writes out the whole block, but only if it is full */ -static void write_if_needed(void) -{ - if (offset == BLOCKSIZE) { - reliable_write(block, BLOCKSIZE); - offset = 0; - } -} - -/* acquire the next record from the buffer; user must call write_if_needed() */ -static char *get_record(void) -{ - char *p = block + offset; - memset(p, 0, RECORDSIZE); - offset += RECORDSIZE; - return p; -} - -/* - * The end of tar archives is marked by 1024 nul bytes and after that - * follows the rest of the block (if any). - */ -static void write_trailer(void) -{ - get_record(); - write_if_needed(); - get_record(); - write_if_needed(); - while (offset) { - get_record(); - write_if_needed(); - } -} - -/* - * queues up writes, so that all our write(2) calls write exactly one - * full block; pads writes to RECORDSIZE - */ -static void write_blocked(void *buf, unsigned long size) -{ - unsigned long tail; - - if (offset) { - unsigned long chunk = BLOCKSIZE - offset; - if (size < chunk) - chunk = size; - memcpy(block + offset, buf, chunk); - size -= chunk; - offset += chunk; - buf += chunk; - write_if_needed(); - } - while (size >= BLOCKSIZE) { - reliable_write(buf, BLOCKSIZE); - size -= BLOCKSIZE; - buf += BLOCKSIZE; - } - if (size) { - memcpy(block + offset, buf, size); - offset += size; - } - tail = offset % RECORDSIZE; - if (tail) { - memset(block + offset, 0, RECORDSIZE - tail); - offset += RECORDSIZE - tail; - } - write_if_needed(); -} - -static void strbuf_append_string(struct strbuf *sb, const char *s) -{ - int slen = strlen(s); - int total = sb->len + slen; - if (total > sb->alloc) { - sb->buf = xrealloc(sb->buf, total); - sb->alloc = total; - } - memcpy(sb->buf + sb->len, s, slen); - sb->len = total; -} - -/* - * pax extended header records have the format "%u %s=%s\n". %u contains - * the size of the whole string (including the %u), the first %s is the - * keyword, the second one is the value. This function constructs such a - * string and appends it to a struct strbuf. - */ -static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword, - const char *value, unsigned int valuelen) -{ - char *p; - int len, total, tmp; - - /* "%u %s=%s\n" */ - len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; - for (tmp = len; tmp > 9; tmp /= 10) - len++; - - total = sb->len + len; - if (total > sb->alloc) { - sb->buf = xrealloc(sb->buf, total); - sb->alloc = total; - } - - p = sb->buf; - p += sprintf(p, "%u %s=", len, keyword); - memcpy(p, value, valuelen); - p += valuelen; - *p = '\n'; - sb->len = total; -} - -static unsigned int ustar_header_chksum(const struct ustar_header *header) -{ - char *p = (char *)header; - unsigned int chksum = 0; - while (p < header->chksum) - chksum += *p++; - chksum += sizeof(header->chksum) * ' '; - p += sizeof(header->chksum); - while (p < (char *)header + sizeof(struct ustar_header)) - chksum += *p++; - return chksum; -} - -static int get_path_prefix(const struct strbuf *path, int maxlen) -{ - int i = path->len; - if (i > maxlen) - i = maxlen; - while (i > 0 && path->buf[i] != '/') - i--; - return i; -} - -static void write_entry(const unsigned char *sha1, struct strbuf *path, - unsigned int mode, void *buffer, unsigned long size) -{ - struct ustar_header header; - struct strbuf ext_header; - - memset(&header, 0, sizeof(header)); - ext_header.buf = NULL; - ext_header.len = ext_header.alloc = 0; - - if (!sha1) { - *header.typeflag = TYPEFLAG_GLOBAL_HEADER; - mode = 0100666; - strcpy(header.name, "pax_global_header"); - } else if (!path) { - *header.typeflag = TYPEFLAG_EXT_HEADER; - mode = 0100666; - sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1)); - } else { - if (S_ISDIR(mode)) { - *header.typeflag = TYPEFLAG_DIR; - mode |= 0777; - } else if (S_ISLNK(mode)) { - *header.typeflag = TYPEFLAG_LNK; - mode |= 0777; - } else if (S_ISREG(mode)) { - *header.typeflag = TYPEFLAG_REG; - mode |= (mode & 0100) ? 0777 : 0666; - } else { - error("unsupported file mode: 0%o (SHA1: %s)", - mode, sha1_to_hex(sha1)); - return; - } - if (path->len > sizeof(header.name)) { - int plen = get_path_prefix(path, sizeof(header.prefix)); - int rest = path->len - plen - 1; - if (plen > 0 && rest <= sizeof(header.name)) { - memcpy(header.prefix, path->buf, plen); - memcpy(header.name, path->buf + plen + 1, rest); - } else { - sprintf(header.name, "%s.data", - sha1_to_hex(sha1)); - strbuf_append_ext_header(&ext_header, "path", - path->buf, path->len); - } - } else - memcpy(header.name, path->buf, path->len); - } - - if (S_ISLNK(mode) && buffer) { - if (size > sizeof(header.linkname)) { - sprintf(header.linkname, "see %s.paxheader", - sha1_to_hex(sha1)); - strbuf_append_ext_header(&ext_header, "linkpath", - buffer, size); - } else - memcpy(header.linkname, buffer, size); - } - - sprintf(header.mode, "%07o", mode & 07777); - sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0); - sprintf(header.mtime, "%011lo", archive_time); - - /* XXX: should we provide more meaningful info here? */ - sprintf(header.uid, "%07o", 0); - sprintf(header.gid, "%07o", 0); - strncpy(header.uname, "git", 31); - strncpy(header.gname, "git", 31); - sprintf(header.devmajor, "%07o", 0); - sprintf(header.devminor, "%07o", 0); - - memcpy(header.magic, "ustar", 6); - memcpy(header.version, "00", 2); - - sprintf(header.chksum, "%07o", ustar_header_chksum(&header)); - - if (ext_header.len > 0) { - write_entry(sha1, NULL, 0, ext_header.buf, ext_header.len); - free(ext_header.buf); - } - write_blocked(&header, sizeof(header)); - if (S_ISREG(mode) && buffer && size > 0) - write_blocked(buffer, size); -} - -static void write_global_extended_header(const unsigned char *sha1) -{ - struct strbuf ext_header; - ext_header.buf = NULL; - ext_header.len = ext_header.alloc = 0; - strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); - write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); - free(ext_header.buf); -} - -static void traverse_tree(struct tree_desc *tree, struct strbuf *path) -{ - int pathlen = path->len; - - while (tree->size) { - const char *name; - const unsigned char *sha1; - unsigned mode; - void *eltbuf; - char elttype[20]; - unsigned long eltsize; - - sha1 = tree_entry_extract(tree, &name, &mode); - update_tree_entry(tree); - - eltbuf = read_sha1_file(sha1, elttype, &eltsize); - if (!eltbuf) - die("cannot read %s", sha1_to_hex(sha1)); - - path->len = pathlen; - strbuf_append_string(path, name); - if (S_ISDIR(mode)) - strbuf_append_string(path, "/"); - - write_entry(sha1, path, mode, eltbuf, eltsize); - - if (S_ISDIR(mode)) { - struct tree_desc subtree; - subtree.buf = eltbuf; - subtree.size = eltsize; - traverse_tree(&subtree, path); - } - free(eltbuf); - } -} - -int main(int argc, char **argv) -{ - unsigned char sha1[20], tree_sha1[20]; - struct commit *commit; - struct tree_desc tree; - struct strbuf current_path; - - current_path.buf = xmalloc(PATH_MAX); - current_path.alloc = PATH_MAX; - current_path.len = current_path.eof = 0; - - setup_git_directory(); - git_config(git_default_config); - - switch (argc) { - case 3: - strbuf_append_string(¤t_path, argv[2]); - strbuf_append_string(¤t_path, "/"); - /* FALLTHROUGH */ - case 2: - if (get_sha1(argv[1], sha1)) - die("Not a valid object name %s", argv[1]); - break; - default: - usage(tar_tree_usage); - } - - commit = lookup_commit_reference_gently(sha1, 1); - if (commit) { - write_global_extended_header(commit->object.sha1); - archive_time = commit->date; - } else - archive_time = time(NULL); - - tree.buf = read_object_with_reference(sha1, tree_type, &tree.size, - tree_sha1); - if (!tree.buf) - die("not a reference to a tag, commit or tree object: %s", - sha1_to_hex(sha1)); - - if (current_path.len > 0) - write_entry(tree_sha1, ¤t_path, 040777, NULL, 0); - traverse_tree(&tree, ¤t_path); - write_trailer(); - free(current_path.buf); - return 0; -} -- cgit v0.10.2-6-g49f6 From 0864f26421b3c599b462bc867de948d14b268d76 Mon Sep 17 00:00:00 2001 From: Peter Eriksen Date: Tue, 23 May 2006 14:15:29 +0200 Subject: Builtin git-ls-files. Signed-off-by: Peter Eriksen Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index 5423b7a..c540d7d 100644 --- a/Makefile +++ b/Makefile @@ -155,7 +155,7 @@ PROGRAMS = \ 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-local-fetch$X \ - git-ls-files$X git-ls-tree$X git-mailinfo$X git-merge-base$X \ + git-ls-tree$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$X git-rev-parse$X \ @@ -171,7 +171,7 @@ PROGRAMS = \ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-count-objects$X git-diff$X git-push$X \ git-grep$X git-rev-list$X git-check-ref-format$X \ - git-init-db$X + git-init-db$X git-ls-files$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -220,7 +220,7 @@ LIB_OBJS = \ BUILTIN_OBJS = \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ - builtin-init-db.o + builtin-init-db.o builtin-ls-files.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-ls-files.c b/builtin-ls-files.c new file mode 100644 index 0000000..3a0c5f2 --- /dev/null +++ b/builtin-ls-files.c @@ -0,0 +1,824 @@ +/* + * This merges the file listing in the directory cache index + * with the actual working directory list, and shows different + * combinations of the two. + * + * Copyright (C) Linus Torvalds, 2005 + */ +#include +#include + +#include "cache.h" +#include "quote.h" +#include "builtin.h" + +static int abbrev = 0; +static int show_deleted = 0; +static int show_cached = 0; +static int show_others = 0; +static int show_ignored = 0; +static int show_stage = 0; +static int show_unmerged = 0; +static int show_modified = 0; +static int show_killed = 0; +static int show_other_directories = 0; +static int hide_empty_directories = 0; +static int show_valid_bit = 0; +static int line_terminator = '\n'; + +static int prefix_len = 0, prefix_offset = 0; +static const char *prefix = NULL; +static const char **pathspec = NULL; +static int error_unmatch = 0; +static char *ps_matched = NULL; + +static const char *tag_cached = ""; +static const char *tag_unmerged = ""; +static const char *tag_removed = ""; +static const char *tag_other = ""; +static const char *tag_killed = ""; +static const char *tag_modified = ""; + +static const char *exclude_per_dir = NULL; + +/* We maintain three exclude pattern lists: + * EXC_CMDL lists patterns explicitly given on the command line. + * EXC_DIRS lists patterns obtained from per-directory ignore files. + * EXC_FILE lists patterns from fallback ignore files. + */ +#define EXC_CMDL 0 +#define EXC_DIRS 1 +#define EXC_FILE 2 +static struct exclude_list { + int nr; + int alloc; + struct exclude { + const char *pattern; + const char *base; + int baselen; + } **excludes; +} exclude_list[3]; + +static void add_exclude(const char *string, const char *base, + int baselen, struct exclude_list *which) +{ + struct exclude *x = xmalloc(sizeof (*x)); + + x->pattern = string; + x->base = base; + x->baselen = baselen; + if (which->nr == which->alloc) { + which->alloc = alloc_nr(which->alloc); + which->excludes = realloc(which->excludes, + which->alloc * sizeof(x)); + } + which->excludes[which->nr++] = x; +} + +static int add_excludes_from_file_1(const char *fname, + const char *base, + int baselen, + struct exclude_list *which) +{ + int fd, i; + long size; + char *buf, *entry; + + fd = open(fname, O_RDONLY); + if (fd < 0) + goto err; + size = lseek(fd, 0, SEEK_END); + if (size < 0) + goto err; + lseek(fd, 0, SEEK_SET); + if (size == 0) { + close(fd); + return 0; + } + buf = xmalloc(size+1); + if (read(fd, buf, size) != size) + goto err; + close(fd); + + buf[size++] = '\n'; + entry = buf; + for (i = 0; i < size; i++) { + if (buf[i] == '\n') { + if (entry != buf + i && entry[0] != '#') { + buf[i - (i && buf[i-1] == '\r')] = 0; + add_exclude(entry, base, baselen, which); + } + entry = buf + i + 1; + } + } + return 0; + + err: + if (0 <= fd) + close(fd); + return -1; +} + +static void add_excludes_from_file(const char *fname) +{ + if (add_excludes_from_file_1(fname, "", 0, + &exclude_list[EXC_FILE]) < 0) + die("cannot use %s as an exclude file", fname); +} + +static int push_exclude_per_directory(const char *base, int baselen) +{ + char exclude_file[PATH_MAX]; + struct exclude_list *el = &exclude_list[EXC_DIRS]; + int current_nr = el->nr; + + if (exclude_per_dir) { + memcpy(exclude_file, base, baselen); + strcpy(exclude_file + baselen, exclude_per_dir); + add_excludes_from_file_1(exclude_file, base, baselen, el); + } + return current_nr; +} + +static void pop_exclude_per_directory(int stk) +{ + struct exclude_list *el = &exclude_list[EXC_DIRS]; + + while (stk < el->nr) + free(el->excludes[--el->nr]); +} + +/* Scan the list and let the last match determines the fate. + * Return 1 for exclude, 0 for include and -1 for undecided. + */ +static int excluded_1(const char *pathname, + int pathlen, + struct exclude_list *el) +{ + int i; + + if (el->nr) { + for (i = el->nr - 1; 0 <= i; i--) { + struct exclude *x = el->excludes[i]; + const char *exclude = x->pattern; + int to_exclude = 1; + + if (*exclude == '!') { + to_exclude = 0; + exclude++; + } + + if (!strchr(exclude, '/')) { + /* match basename */ + const char *basename = strrchr(pathname, '/'); + basename = (basename) ? basename+1 : pathname; + if (fnmatch(exclude, basename, 0) == 0) + return to_exclude; + } + else { + /* match with FNM_PATHNAME: + * exclude has base (baselen long) implicitly + * in front of it. + */ + int baselen = x->baselen; + if (*exclude == '/') + exclude++; + + if (pathlen < baselen || + (baselen && pathname[baselen-1] != '/') || + strncmp(pathname, x->base, baselen)) + continue; + + if (fnmatch(exclude, pathname+baselen, + FNM_PATHNAME) == 0) + return to_exclude; + } + } + } + return -1; /* undecided */ +} + +static int excluded(const char *pathname) +{ + int pathlen = strlen(pathname); + int st; + + for (st = EXC_CMDL; st <= EXC_FILE; st++) { + switch (excluded_1(pathname, pathlen, &exclude_list[st])) { + case 0: + return 0; + case 1: + return 1; + } + } + return 0; +} + +struct nond_on_fs { + int len; + char name[FLEX_ARRAY]; /* more */ +}; + +static struct nond_on_fs **dir; +static int nr_dir; +static int dir_alloc; + +static void add_name(const char *pathname, int len) +{ + struct nond_on_fs *ent; + + if (cache_name_pos(pathname, len) >= 0) + return; + + if (nr_dir == dir_alloc) { + dir_alloc = alloc_nr(dir_alloc); + dir = xrealloc(dir, dir_alloc*sizeof(ent)); + } + ent = xmalloc(sizeof(*ent) + len + 1); + ent->len = len; + memcpy(ent->name, pathname, len); + ent->name[len] = 0; + dir[nr_dir++] = ent; +} + +static int dir_exists(const char *dirname, int len) +{ + int pos = cache_name_pos(dirname, len); + if (pos >= 0) + return 1; + pos = -pos-1; + if (pos >= active_nr) /* can't */ + return 0; + return !strncmp(active_cache[pos]->name, dirname, len); +} + +/* + * Read a directory tree. We currently ignore anything but + * directories, regular files and symlinks. That's because git + * doesn't handle them at all yet. Maybe that will change some + * day. + * + * Also, we ignore the name ".git" (even if it is not a directory). + * That likely will not change. + */ +static int read_directory(const char *path, const char *base, int baselen) +{ + DIR *fdir = opendir(path); + int contents = 0; + + if (fdir) { + int exclude_stk; + struct dirent *de; + char fullname[MAXPATHLEN + 1]; + memcpy(fullname, base, baselen); + + exclude_stk = push_exclude_per_directory(base, baselen); + + while ((de = readdir(fdir)) != NULL) { + int len; + + if ((de->d_name[0] == '.') && + (de->d_name[1] == 0 || + !strcmp(de->d_name + 1, ".") || + !strcmp(de->d_name + 1, "git"))) + continue; + len = strlen(de->d_name); + memcpy(fullname + baselen, de->d_name, len+1); + if (excluded(fullname) != show_ignored) { + if (!show_ignored || DTYPE(de) != DT_DIR) { + continue; + } + } + + switch (DTYPE(de)) { + struct stat st; + int subdir, rewind_base; + default: + continue; + case DT_UNKNOWN: + if (lstat(fullname, &st)) + continue; + if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode)) + break; + if (!S_ISDIR(st.st_mode)) + continue; + /* fallthrough */ + case DT_DIR: + memcpy(fullname + baselen + len, "/", 2); + len++; + rewind_base = nr_dir; + subdir = read_directory(fullname, fullname, + baselen + len); + if (show_other_directories && + (subdir || !hide_empty_directories) && + !dir_exists(fullname, baselen + len)) { + // Rewind the read subdirectory + while (nr_dir > rewind_base) + free(dir[--nr_dir]); + break; + } + contents += subdir; + continue; + case DT_REG: + case DT_LNK: + break; + } + add_name(fullname, baselen + len); + contents++; + } + closedir(fdir); + + pop_exclude_per_directory(exclude_stk); + } + + return contents; +} + +static int cmp_name(const void *p1, const void *p2) +{ + const struct nond_on_fs *e1 = *(const struct nond_on_fs **)p1; + const struct nond_on_fs *e2 = *(const struct nond_on_fs **)p2; + + return cache_name_compare(e1->name, e1->len, + e2->name, e2->len); +} + +/* + * Match a pathspec against a filename. The first "len" characters + * are the common prefix + */ +static int match(const char **spec, char *ps_matched, + const char *filename, int len) +{ + const char *m; + + while ((m = *spec++) != NULL) { + int matchlen = strlen(m + len); + + if (!matchlen) + goto matched; + if (!strncmp(m + len, filename + len, matchlen)) { + if (m[len + matchlen - 1] == '/') + goto matched; + switch (filename[len + matchlen]) { + case '/': case '\0': + goto matched; + } + } + if (!fnmatch(m + len, filename + len, 0)) + goto matched; + if (ps_matched) + ps_matched++; + continue; + matched: + if (ps_matched) + *ps_matched = 1; + return 1; + } + return 0; +} + +static void show_dir_entry(const char *tag, struct nond_on_fs *ent) +{ + int len = prefix_len; + int offset = prefix_offset; + + if (len >= ent->len) + die("git-ls-files: internal error - directory entry not superset of prefix"); + + if (pathspec && !match(pathspec, ps_matched, ent->name, len)) + return; + + fputs(tag, stdout); + write_name_quoted("", 0, ent->name + offset, line_terminator, stdout); + putchar(line_terminator); +} + +static void show_other_files(void) +{ + int i; + for (i = 0; i < nr_dir; i++) { + /* We should not have a matching entry, but we + * may have an unmerged entry for this path. + */ + struct nond_on_fs *ent = dir[i]; + int pos = cache_name_pos(ent->name, ent->len); + struct cache_entry *ce; + if (0 <= pos) + die("bug in show-other-files"); + pos = -pos - 1; + if (pos < active_nr) { + ce = active_cache[pos]; + if (ce_namelen(ce) == ent->len && + !memcmp(ce->name, ent->name, ent->len)) + continue; /* Yup, this one exists unmerged */ + } + show_dir_entry(tag_other, ent); + } +} + +static void show_killed_files(void) +{ + int i; + for (i = 0; i < nr_dir; i++) { + struct nond_on_fs *ent = dir[i]; + char *cp, *sp; + int pos, len, killed = 0; + + for (cp = ent->name; cp - ent->name < ent->len; cp = sp + 1) { + sp = strchr(cp, '/'); + if (!sp) { + /* If ent->name is prefix of an entry in the + * cache, it will be killed. + */ + pos = cache_name_pos(ent->name, ent->len); + if (0 <= pos) + die("bug in show-killed-files"); + pos = -pos - 1; + while (pos < active_nr && + ce_stage(active_cache[pos])) + pos++; /* skip unmerged */ + if (active_nr <= pos) + break; + /* pos points at a name immediately after + * ent->name in the cache. Does it expect + * ent->name to be a directory? + */ + len = ce_namelen(active_cache[pos]); + if ((ent->len < len) && + !strncmp(active_cache[pos]->name, + ent->name, ent->len) && + active_cache[pos]->name[ent->len] == '/') + killed = 1; + break; + } + if (0 <= cache_name_pos(ent->name, sp - ent->name)) { + /* If any of the leading directories in + * ent->name is registered in the cache, + * ent->name will be killed. + */ + killed = 1; + break; + } + } + if (killed) + show_dir_entry(tag_killed, dir[i]); + } +} + +static void show_ce_entry(const char *tag, struct cache_entry *ce) +{ + int len = prefix_len; + int offset = prefix_offset; + + if (len >= ce_namelen(ce)) + die("git-ls-files: internal error - cache entry not superset of prefix"); + + if (pathspec && !match(pathspec, ps_matched, ce->name, len)) + return; + + if (tag && *tag && show_valid_bit && + (ce->ce_flags & htons(CE_VALID))) { + static char alttag[4]; + memcpy(alttag, tag, 3); + if (isalpha(tag[0])) + alttag[0] = tolower(tag[0]); + else if (tag[0] == '?') + alttag[0] = '!'; + else { + alttag[0] = 'v'; + alttag[1] = tag[0]; + alttag[2] = ' '; + alttag[3] = 0; + } + tag = alttag; + } + + if (!show_stage) { + fputs(tag, stdout); + write_name_quoted("", 0, ce->name + offset, + line_terminator, stdout); + putchar(line_terminator); + } + else { + printf("%s%06o %s %d\t", + tag, + ntohl(ce->ce_mode), + abbrev ? find_unique_abbrev(ce->sha1,abbrev) + : sha1_to_hex(ce->sha1), + ce_stage(ce)); + write_name_quoted("", 0, ce->name + offset, + line_terminator, stdout); + putchar(line_terminator); + } +} + +static void show_files(void) +{ + int i; + + /* For cached/deleted files we don't need to even do the readdir */ + if (show_others || show_killed) { + const char *path = ".", *base = ""; + int baselen = prefix_len; + + if (baselen) { + path = base = prefix; + if (exclude_per_dir) { + char *p, *pp = xmalloc(baselen+1); + memcpy(pp, prefix, baselen+1); + p = pp; + while (1) { + char save = *p; + *p = 0; + push_exclude_per_directory(pp, p-pp); + *p++ = save; + if (!save) + break; + p = strchr(p, '/'); + if (p) + p++; + else + p = pp + baselen; + } + free(pp); + } + } + read_directory(path, base, baselen); + qsort(dir, nr_dir, sizeof(struct nond_on_fs *), cmp_name); + if (show_others) + show_other_files(); + if (show_killed) + show_killed_files(); + } + if (show_cached | show_stage) { + for (i = 0; i < active_nr; i++) { + struct cache_entry *ce = active_cache[i]; + if (excluded(ce->name) != show_ignored) + continue; + if (show_unmerged && !ce_stage(ce)) + continue; + show_ce_entry(ce_stage(ce) ? tag_unmerged : tag_cached, ce); + } + } + if (show_deleted | show_modified) { + for (i = 0; i < active_nr; i++) { + struct cache_entry *ce = active_cache[i]; + struct stat st; + int err; + if (excluded(ce->name) != show_ignored) + continue; + err = lstat(ce->name, &st); + if (show_deleted && err) + show_ce_entry(tag_removed, ce); + if (show_modified && ce_modified(ce, &st, 0)) + show_ce_entry(tag_modified, ce); + } + } +} + +/* + * Prune the index to only contain stuff starting with "prefix" + */ +static void prune_cache(void) +{ + int pos = cache_name_pos(prefix, prefix_len); + unsigned int first, last; + + if (pos < 0) + pos = -pos-1; + active_cache += pos; + active_nr -= pos; + first = 0; + last = active_nr; + while (last > first) { + int next = (last + first) >> 1; + struct cache_entry *ce = active_cache[next]; + if (!strncmp(ce->name, prefix, prefix_len)) { + first = next+1; + continue; + } + last = next; + } + active_nr = last; +} + +static void verify_pathspec(void) +{ + const char **p, *n, *prev; + char *real_prefix; + unsigned long max; + + prev = NULL; + max = PATH_MAX; + for (p = pathspec; (n = *p) != NULL; p++) { + int i, len = 0; + for (i = 0; i < max; i++) { + char c = n[i]; + if (prev && prev[i] != c) + break; + if (!c || c == '*' || c == '?') + break; + if (c == '/') + len = i+1; + } + prev = n; + if (len < max) { + max = len; + if (!max) + break; + } + } + + if (prefix_offset > max || memcmp(prev, prefix, prefix_offset)) + die("git-ls-files: cannot generate relative filenames containing '..'"); + + real_prefix = NULL; + prefix_len = max; + if (max) { + real_prefix = xmalloc(max + 1); + memcpy(real_prefix, prev, max); + real_prefix[max] = 0; + } + prefix = real_prefix; +} + +static const char ls_files_usage[] = + "git-ls-files [-z] [-t] [-v] (--[cached|deleted|others|stage|unmerged|killed|modified])* " + "[ --ignored ] [--exclude=] [--exclude-from=] " + "[ --exclude-per-directory= ] [--full-name] [--abbrev] " + "[--] []*"; + +int cmd_ls_files(int argc, const char **argv, char** envp) +{ + int i; + int exc_given = 0; + + prefix = setup_git_directory(); + if (prefix) + prefix_offset = strlen(prefix); + git_config(git_default_config); + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + + if (!strcmp(arg, "--")) { + i++; + break; + } + if (!strcmp(arg, "-z")) { + line_terminator = 0; + continue; + } + if (!strcmp(arg, "-t") || !strcmp(arg, "-v")) { + tag_cached = "H "; + tag_unmerged = "M "; + tag_removed = "R "; + tag_modified = "C "; + tag_other = "? "; + tag_killed = "K "; + if (arg[1] == 'v') + show_valid_bit = 1; + continue; + } + if (!strcmp(arg, "-c") || !strcmp(arg, "--cached")) { + show_cached = 1; + continue; + } + if (!strcmp(arg, "-d") || !strcmp(arg, "--deleted")) { + show_deleted = 1; + continue; + } + if (!strcmp(arg, "-m") || !strcmp(arg, "--modified")) { + show_modified = 1; + continue; + } + if (!strcmp(arg, "-o") || !strcmp(arg, "--others")) { + show_others = 1; + continue; + } + if (!strcmp(arg, "-i") || !strcmp(arg, "--ignored")) { + show_ignored = 1; + continue; + } + if (!strcmp(arg, "-s") || !strcmp(arg, "--stage")) { + show_stage = 1; + continue; + } + if (!strcmp(arg, "-k") || !strcmp(arg, "--killed")) { + show_killed = 1; + continue; + } + if (!strcmp(arg, "--directory")) { + show_other_directories = 1; + continue; + } + if (!strcmp(arg, "--no-empty-directory")) { + hide_empty_directories = 1; + continue; + } + if (!strcmp(arg, "-u") || !strcmp(arg, "--unmerged")) { + /* There's no point in showing unmerged unless + * you also show the stage information. + */ + show_stage = 1; + show_unmerged = 1; + continue; + } + if (!strcmp(arg, "-x") && i+1 < argc) { + exc_given = 1; + add_exclude(argv[++i], "", 0, &exclude_list[EXC_CMDL]); + continue; + } + if (!strncmp(arg, "--exclude=", 10)) { + exc_given = 1; + add_exclude(arg+10, "", 0, &exclude_list[EXC_CMDL]); + continue; + } + if (!strcmp(arg, "-X") && i+1 < argc) { + exc_given = 1; + add_excludes_from_file(argv[++i]); + continue; + } + if (!strncmp(arg, "--exclude-from=", 15)) { + exc_given = 1; + add_excludes_from_file(arg+15); + continue; + } + if (!strncmp(arg, "--exclude-per-directory=", 24)) { + exc_given = 1; + exclude_per_dir = arg + 24; + continue; + } + if (!strcmp(arg, "--full-name")) { + prefix_offset = 0; + continue; + } + if (!strcmp(arg, "--error-unmatch")) { + error_unmatch = 1; + continue; + } + if (!strncmp(arg, "--abbrev=", 9)) { + abbrev = strtoul(arg+9, NULL, 10); + if (abbrev && abbrev < MINIMUM_ABBREV) + abbrev = MINIMUM_ABBREV; + else if (abbrev > 40) + abbrev = 40; + continue; + } + if (!strcmp(arg, "--abbrev")) { + abbrev = DEFAULT_ABBREV; + continue; + } + if (*arg == '-') + usage(ls_files_usage); + break; + } + + pathspec = get_pathspec(prefix, argv + i); + + /* Verify that the pathspec matches the prefix */ + if (pathspec) + verify_pathspec(); + + /* Treat unmatching pathspec elements as errors */ + if (pathspec && error_unmatch) { + int num; + for (num = 0; pathspec[num]; num++) + ; + ps_matched = xcalloc(1, num); + } + + if (show_ignored && !exc_given) { + fprintf(stderr, "%s: --ignored needs some exclude pattern\n", + argv[0]); + exit(1); + } + + /* With no flags, we default to showing the cached files */ + if (!(show_stage | show_deleted | show_others | show_unmerged | + show_killed | show_modified)) + show_cached = 1; + + read_cache(); + if (prefix) + prune_cache(); + show_files(); + + if (ps_matched) { + /* We need to make sure all pathspec matched otherwise + * it is an error. + */ + int num, errors = 0; + for (num = 0; pathspec[num]; num++) { + if (ps_matched[num]) + continue; + error("pathspec '%s' did not match any.", + pathspec[num] + prefix_offset); + errors++; + } + return errors ? 1 : 0; + } + + return 0; +} diff --git a/builtin.h b/builtin.h index 6054126..a0713d3 100644 --- a/builtin.h +++ b/builtin.h @@ -27,5 +27,6 @@ extern int cmd_grep(int argc, const char **argv, char **envp); extern int cmd_rev_list(int argc, const char **argv, char **envp); extern int cmd_check_ref_format(int argc, const char **argv, char **envp); extern int cmd_init_db(int argc, const char **argv, char **envp); +extern int cmd_ls_files(int argc, const char **argv, char **envp); #endif diff --git a/git.c b/git.c index 3216d31..9cfa9eb 100644 --- a/git.c +++ b/git.c @@ -52,7 +52,8 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "grep", cmd_grep }, { "rev-list", cmd_rev_list }, { "init-db", cmd_init_db }, - { "check-ref-format", cmd_check_ref_format } + { "check-ref-format", cmd_check_ref_format }, + { "ls-files", cmd_ls_files } }; int i; diff --git a/ls-files.c b/ls-files.c deleted file mode 100644 index 4a4af1c..0000000 --- a/ls-files.c +++ /dev/null @@ -1,823 +0,0 @@ -/* - * This merges the file listing in the directory cache index - * with the actual working directory list, and shows different - * combinations of the two. - * - * Copyright (C) Linus Torvalds, 2005 - */ -#include -#include - -#include "cache.h" -#include "quote.h" - -static int abbrev = 0; -static int show_deleted = 0; -static int show_cached = 0; -static int show_others = 0; -static int show_ignored = 0; -static int show_stage = 0; -static int show_unmerged = 0; -static int show_modified = 0; -static int show_killed = 0; -static int show_other_directories = 0; -static int hide_empty_directories = 0; -static int show_valid_bit = 0; -static int line_terminator = '\n'; - -static int prefix_len = 0, prefix_offset = 0; -static const char *prefix = NULL; -static const char **pathspec = NULL; -static int error_unmatch = 0; -static char *ps_matched = NULL; - -static const char *tag_cached = ""; -static const char *tag_unmerged = ""; -static const char *tag_removed = ""; -static const char *tag_other = ""; -static const char *tag_killed = ""; -static const char *tag_modified = ""; - -static const char *exclude_per_dir = NULL; - -/* We maintain three exclude pattern lists: - * EXC_CMDL lists patterns explicitly given on the command line. - * EXC_DIRS lists patterns obtained from per-directory ignore files. - * EXC_FILE lists patterns from fallback ignore files. - */ -#define EXC_CMDL 0 -#define EXC_DIRS 1 -#define EXC_FILE 2 -static struct exclude_list { - int nr; - int alloc; - struct exclude { - const char *pattern; - const char *base; - int baselen; - } **excludes; -} exclude_list[3]; - -static void add_exclude(const char *string, const char *base, - int baselen, struct exclude_list *which) -{ - struct exclude *x = xmalloc(sizeof (*x)); - - x->pattern = string; - x->base = base; - x->baselen = baselen; - if (which->nr == which->alloc) { - which->alloc = alloc_nr(which->alloc); - which->excludes = realloc(which->excludes, - which->alloc * sizeof(x)); - } - which->excludes[which->nr++] = x; -} - -static int add_excludes_from_file_1(const char *fname, - const char *base, - int baselen, - struct exclude_list *which) -{ - int fd, i; - long size; - char *buf, *entry; - - fd = open(fname, O_RDONLY); - if (fd < 0) - goto err; - size = lseek(fd, 0, SEEK_END); - if (size < 0) - goto err; - lseek(fd, 0, SEEK_SET); - if (size == 0) { - close(fd); - return 0; - } - buf = xmalloc(size+1); - if (read(fd, buf, size) != size) - goto err; - close(fd); - - buf[size++] = '\n'; - entry = buf; - for (i = 0; i < size; i++) { - if (buf[i] == '\n') { - if (entry != buf + i && entry[0] != '#') { - buf[i - (i && buf[i-1] == '\r')] = 0; - add_exclude(entry, base, baselen, which); - } - entry = buf + i + 1; - } - } - return 0; - - err: - if (0 <= fd) - close(fd); - return -1; -} - -static void add_excludes_from_file(const char *fname) -{ - if (add_excludes_from_file_1(fname, "", 0, - &exclude_list[EXC_FILE]) < 0) - die("cannot use %s as an exclude file", fname); -} - -static int push_exclude_per_directory(const char *base, int baselen) -{ - char exclude_file[PATH_MAX]; - struct exclude_list *el = &exclude_list[EXC_DIRS]; - int current_nr = el->nr; - - if (exclude_per_dir) { - memcpy(exclude_file, base, baselen); - strcpy(exclude_file + baselen, exclude_per_dir); - add_excludes_from_file_1(exclude_file, base, baselen, el); - } - return current_nr; -} - -static void pop_exclude_per_directory(int stk) -{ - struct exclude_list *el = &exclude_list[EXC_DIRS]; - - while (stk < el->nr) - free(el->excludes[--el->nr]); -} - -/* Scan the list and let the last match determines the fate. - * Return 1 for exclude, 0 for include and -1 for undecided. - */ -static int excluded_1(const char *pathname, - int pathlen, - struct exclude_list *el) -{ - int i; - - if (el->nr) { - for (i = el->nr - 1; 0 <= i; i--) { - struct exclude *x = el->excludes[i]; - const char *exclude = x->pattern; - int to_exclude = 1; - - if (*exclude == '!') { - to_exclude = 0; - exclude++; - } - - if (!strchr(exclude, '/')) { - /* match basename */ - const char *basename = strrchr(pathname, '/'); - basename = (basename) ? basename+1 : pathname; - if (fnmatch(exclude, basename, 0) == 0) - return to_exclude; - } - else { - /* match with FNM_PATHNAME: - * exclude has base (baselen long) implicitly - * in front of it. - */ - int baselen = x->baselen; - if (*exclude == '/') - exclude++; - - if (pathlen < baselen || - (baselen && pathname[baselen-1] != '/') || - strncmp(pathname, x->base, baselen)) - continue; - - if (fnmatch(exclude, pathname+baselen, - FNM_PATHNAME) == 0) - return to_exclude; - } - } - } - return -1; /* undecided */ -} - -static int excluded(const char *pathname) -{ - int pathlen = strlen(pathname); - int st; - - for (st = EXC_CMDL; st <= EXC_FILE; st++) { - switch (excluded_1(pathname, pathlen, &exclude_list[st])) { - case 0: - return 0; - case 1: - return 1; - } - } - return 0; -} - -struct nond_on_fs { - int len; - char name[FLEX_ARRAY]; /* more */ -}; - -static struct nond_on_fs **dir; -static int nr_dir; -static int dir_alloc; - -static void add_name(const char *pathname, int len) -{ - struct nond_on_fs *ent; - - if (cache_name_pos(pathname, len) >= 0) - return; - - if (nr_dir == dir_alloc) { - dir_alloc = alloc_nr(dir_alloc); - dir = xrealloc(dir, dir_alloc*sizeof(ent)); - } - ent = xmalloc(sizeof(*ent) + len + 1); - ent->len = len; - memcpy(ent->name, pathname, len); - ent->name[len] = 0; - dir[nr_dir++] = ent; -} - -static int dir_exists(const char *dirname, int len) -{ - int pos = cache_name_pos(dirname, len); - if (pos >= 0) - return 1; - pos = -pos-1; - if (pos >= active_nr) /* can't */ - return 0; - return !strncmp(active_cache[pos]->name, dirname, len); -} - -/* - * Read a directory tree. We currently ignore anything but - * directories, regular files and symlinks. That's because git - * doesn't handle them at all yet. Maybe that will change some - * day. - * - * Also, we ignore the name ".git" (even if it is not a directory). - * That likely will not change. - */ -static int read_directory(const char *path, const char *base, int baselen) -{ - DIR *fdir = opendir(path); - int contents = 0; - - if (fdir) { - int exclude_stk; - struct dirent *de; - char fullname[MAXPATHLEN + 1]; - memcpy(fullname, base, baselen); - - exclude_stk = push_exclude_per_directory(base, baselen); - - while ((de = readdir(fdir)) != NULL) { - int len; - - if ((de->d_name[0] == '.') && - (de->d_name[1] == 0 || - !strcmp(de->d_name + 1, ".") || - !strcmp(de->d_name + 1, "git"))) - continue; - len = strlen(de->d_name); - memcpy(fullname + baselen, de->d_name, len+1); - if (excluded(fullname) != show_ignored) { - if (!show_ignored || DTYPE(de) != DT_DIR) { - continue; - } - } - - switch (DTYPE(de)) { - struct stat st; - int subdir, rewind_base; - default: - continue; - case DT_UNKNOWN: - if (lstat(fullname, &st)) - continue; - if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode)) - break; - if (!S_ISDIR(st.st_mode)) - continue; - /* fallthrough */ - case DT_DIR: - memcpy(fullname + baselen + len, "/", 2); - len++; - rewind_base = nr_dir; - subdir = read_directory(fullname, fullname, - baselen + len); - if (show_other_directories && - (subdir || !hide_empty_directories) && - !dir_exists(fullname, baselen + len)) { - // Rewind the read subdirectory - while (nr_dir > rewind_base) - free(dir[--nr_dir]); - break; - } - contents += subdir; - continue; - case DT_REG: - case DT_LNK: - break; - } - add_name(fullname, baselen + len); - contents++; - } - closedir(fdir); - - pop_exclude_per_directory(exclude_stk); - } - - return contents; -} - -static int cmp_name(const void *p1, const void *p2) -{ - const struct nond_on_fs *e1 = *(const struct nond_on_fs **)p1; - const struct nond_on_fs *e2 = *(const struct nond_on_fs **)p2; - - return cache_name_compare(e1->name, e1->len, - e2->name, e2->len); -} - -/* - * Match a pathspec against a filename. The first "len" characters - * are the common prefix - */ -static int match(const char **spec, char *ps_matched, - const char *filename, int len) -{ - const char *m; - - while ((m = *spec++) != NULL) { - int matchlen = strlen(m + len); - - if (!matchlen) - goto matched; - if (!strncmp(m + len, filename + len, matchlen)) { - if (m[len + matchlen - 1] == '/') - goto matched; - switch (filename[len + matchlen]) { - case '/': case '\0': - goto matched; - } - } - if (!fnmatch(m + len, filename + len, 0)) - goto matched; - if (ps_matched) - ps_matched++; - continue; - matched: - if (ps_matched) - *ps_matched = 1; - return 1; - } - return 0; -} - -static void show_dir_entry(const char *tag, struct nond_on_fs *ent) -{ - int len = prefix_len; - int offset = prefix_offset; - - if (len >= ent->len) - die("git-ls-files: internal error - directory entry not superset of prefix"); - - if (pathspec && !match(pathspec, ps_matched, ent->name, len)) - return; - - fputs(tag, stdout); - write_name_quoted("", 0, ent->name + offset, line_terminator, stdout); - putchar(line_terminator); -} - -static void show_other_files(void) -{ - int i; - for (i = 0; i < nr_dir; i++) { - /* We should not have a matching entry, but we - * may have an unmerged entry for this path. - */ - struct nond_on_fs *ent = dir[i]; - int pos = cache_name_pos(ent->name, ent->len); - struct cache_entry *ce; - if (0 <= pos) - die("bug in show-other-files"); - pos = -pos - 1; - if (pos < active_nr) { - ce = active_cache[pos]; - if (ce_namelen(ce) == ent->len && - !memcmp(ce->name, ent->name, ent->len)) - continue; /* Yup, this one exists unmerged */ - } - show_dir_entry(tag_other, ent); - } -} - -static void show_killed_files(void) -{ - int i; - for (i = 0; i < nr_dir; i++) { - struct nond_on_fs *ent = dir[i]; - char *cp, *sp; - int pos, len, killed = 0; - - for (cp = ent->name; cp - ent->name < ent->len; cp = sp + 1) { - sp = strchr(cp, '/'); - if (!sp) { - /* If ent->name is prefix of an entry in the - * cache, it will be killed. - */ - pos = cache_name_pos(ent->name, ent->len); - if (0 <= pos) - die("bug in show-killed-files"); - pos = -pos - 1; - while (pos < active_nr && - ce_stage(active_cache[pos])) - pos++; /* skip unmerged */ - if (active_nr <= pos) - break; - /* pos points at a name immediately after - * ent->name in the cache. Does it expect - * ent->name to be a directory? - */ - len = ce_namelen(active_cache[pos]); - if ((ent->len < len) && - !strncmp(active_cache[pos]->name, - ent->name, ent->len) && - active_cache[pos]->name[ent->len] == '/') - killed = 1; - break; - } - if (0 <= cache_name_pos(ent->name, sp - ent->name)) { - /* If any of the leading directories in - * ent->name is registered in the cache, - * ent->name will be killed. - */ - killed = 1; - break; - } - } - if (killed) - show_dir_entry(tag_killed, dir[i]); - } -} - -static void show_ce_entry(const char *tag, struct cache_entry *ce) -{ - int len = prefix_len; - int offset = prefix_offset; - - if (len >= ce_namelen(ce)) - die("git-ls-files: internal error - cache entry not superset of prefix"); - - if (pathspec && !match(pathspec, ps_matched, ce->name, len)) - return; - - if (tag && *tag && show_valid_bit && - (ce->ce_flags & htons(CE_VALID))) { - static char alttag[4]; - memcpy(alttag, tag, 3); - if (isalpha(tag[0])) - alttag[0] = tolower(tag[0]); - else if (tag[0] == '?') - alttag[0] = '!'; - else { - alttag[0] = 'v'; - alttag[1] = tag[0]; - alttag[2] = ' '; - alttag[3] = 0; - } - tag = alttag; - } - - if (!show_stage) { - fputs(tag, stdout); - write_name_quoted("", 0, ce->name + offset, - line_terminator, stdout); - putchar(line_terminator); - } - else { - printf("%s%06o %s %d\t", - tag, - ntohl(ce->ce_mode), - abbrev ? find_unique_abbrev(ce->sha1,abbrev) - : sha1_to_hex(ce->sha1), - ce_stage(ce)); - write_name_quoted("", 0, ce->name + offset, - line_terminator, stdout); - putchar(line_terminator); - } -} - -static void show_files(void) -{ - int i; - - /* For cached/deleted files we don't need to even do the readdir */ - if (show_others || show_killed) { - const char *path = ".", *base = ""; - int baselen = prefix_len; - - if (baselen) { - path = base = prefix; - if (exclude_per_dir) { - char *p, *pp = xmalloc(baselen+1); - memcpy(pp, prefix, baselen+1); - p = pp; - while (1) { - char save = *p; - *p = 0; - push_exclude_per_directory(pp, p-pp); - *p++ = save; - if (!save) - break; - p = strchr(p, '/'); - if (p) - p++; - else - p = pp + baselen; - } - free(pp); - } - } - read_directory(path, base, baselen); - qsort(dir, nr_dir, sizeof(struct nond_on_fs *), cmp_name); - if (show_others) - show_other_files(); - if (show_killed) - show_killed_files(); - } - if (show_cached | show_stage) { - for (i = 0; i < active_nr; i++) { - struct cache_entry *ce = active_cache[i]; - if (excluded(ce->name) != show_ignored) - continue; - if (show_unmerged && !ce_stage(ce)) - continue; - show_ce_entry(ce_stage(ce) ? tag_unmerged : tag_cached, ce); - } - } - if (show_deleted | show_modified) { - for (i = 0; i < active_nr; i++) { - struct cache_entry *ce = active_cache[i]; - struct stat st; - int err; - if (excluded(ce->name) != show_ignored) - continue; - err = lstat(ce->name, &st); - if (show_deleted && err) - show_ce_entry(tag_removed, ce); - if (show_modified && ce_modified(ce, &st, 0)) - show_ce_entry(tag_modified, ce); - } - } -} - -/* - * Prune the index to only contain stuff starting with "prefix" - */ -static void prune_cache(void) -{ - int pos = cache_name_pos(prefix, prefix_len); - unsigned int first, last; - - if (pos < 0) - pos = -pos-1; - active_cache += pos; - active_nr -= pos; - first = 0; - last = active_nr; - while (last > first) { - int next = (last + first) >> 1; - struct cache_entry *ce = active_cache[next]; - if (!strncmp(ce->name, prefix, prefix_len)) { - first = next+1; - continue; - } - last = next; - } - active_nr = last; -} - -static void verify_pathspec(void) -{ - const char **p, *n, *prev; - char *real_prefix; - unsigned long max; - - prev = NULL; - max = PATH_MAX; - for (p = pathspec; (n = *p) != NULL; p++) { - int i, len = 0; - for (i = 0; i < max; i++) { - char c = n[i]; - if (prev && prev[i] != c) - break; - if (!c || c == '*' || c == '?') - break; - if (c == '/') - len = i+1; - } - prev = n; - if (len < max) { - max = len; - if (!max) - break; - } - } - - if (prefix_offset > max || memcmp(prev, prefix, prefix_offset)) - die("git-ls-files: cannot generate relative filenames containing '..'"); - - real_prefix = NULL; - prefix_len = max; - if (max) { - real_prefix = xmalloc(max + 1); - memcpy(real_prefix, prev, max); - real_prefix[max] = 0; - } - prefix = real_prefix; -} - -static const char ls_files_usage[] = - "git-ls-files [-z] [-t] [-v] (--[cached|deleted|others|stage|unmerged|killed|modified])* " - "[ --ignored ] [--exclude=] [--exclude-from=] " - "[ --exclude-per-directory= ] [--full-name] [--abbrev] " - "[--] []*"; - -int main(int argc, const char **argv) -{ - int i; - int exc_given = 0; - - prefix = setup_git_directory(); - if (prefix) - prefix_offset = strlen(prefix); - git_config(git_default_config); - - for (i = 1; i < argc; i++) { - const char *arg = argv[i]; - - if (!strcmp(arg, "--")) { - i++; - break; - } - if (!strcmp(arg, "-z")) { - line_terminator = 0; - continue; - } - if (!strcmp(arg, "-t") || !strcmp(arg, "-v")) { - tag_cached = "H "; - tag_unmerged = "M "; - tag_removed = "R "; - tag_modified = "C "; - tag_other = "? "; - tag_killed = "K "; - if (arg[1] == 'v') - show_valid_bit = 1; - continue; - } - if (!strcmp(arg, "-c") || !strcmp(arg, "--cached")) { - show_cached = 1; - continue; - } - if (!strcmp(arg, "-d") || !strcmp(arg, "--deleted")) { - show_deleted = 1; - continue; - } - if (!strcmp(arg, "-m") || !strcmp(arg, "--modified")) { - show_modified = 1; - continue; - } - if (!strcmp(arg, "-o") || !strcmp(arg, "--others")) { - show_others = 1; - continue; - } - if (!strcmp(arg, "-i") || !strcmp(arg, "--ignored")) { - show_ignored = 1; - continue; - } - if (!strcmp(arg, "-s") || !strcmp(arg, "--stage")) { - show_stage = 1; - continue; - } - if (!strcmp(arg, "-k") || !strcmp(arg, "--killed")) { - show_killed = 1; - continue; - } - if (!strcmp(arg, "--directory")) { - show_other_directories = 1; - continue; - } - if (!strcmp(arg, "--no-empty-directory")) { - hide_empty_directories = 1; - continue; - } - if (!strcmp(arg, "-u") || !strcmp(arg, "--unmerged")) { - /* There's no point in showing unmerged unless - * you also show the stage information. - */ - show_stage = 1; - show_unmerged = 1; - continue; - } - if (!strcmp(arg, "-x") && i+1 < argc) { - exc_given = 1; - add_exclude(argv[++i], "", 0, &exclude_list[EXC_CMDL]); - continue; - } - if (!strncmp(arg, "--exclude=", 10)) { - exc_given = 1; - add_exclude(arg+10, "", 0, &exclude_list[EXC_CMDL]); - continue; - } - if (!strcmp(arg, "-X") && i+1 < argc) { - exc_given = 1; - add_excludes_from_file(argv[++i]); - continue; - } - if (!strncmp(arg, "--exclude-from=", 15)) { - exc_given = 1; - add_excludes_from_file(arg+15); - continue; - } - if (!strncmp(arg, "--exclude-per-directory=", 24)) { - exc_given = 1; - exclude_per_dir = arg + 24; - continue; - } - if (!strcmp(arg, "--full-name")) { - prefix_offset = 0; - continue; - } - if (!strcmp(arg, "--error-unmatch")) { - error_unmatch = 1; - continue; - } - if (!strncmp(arg, "--abbrev=", 9)) { - abbrev = strtoul(arg+9, NULL, 10); - if (abbrev && abbrev < MINIMUM_ABBREV) - abbrev = MINIMUM_ABBREV; - else if (abbrev > 40) - abbrev = 40; - continue; - } - if (!strcmp(arg, "--abbrev")) { - abbrev = DEFAULT_ABBREV; - continue; - } - if (*arg == '-') - usage(ls_files_usage); - break; - } - - pathspec = get_pathspec(prefix, argv + i); - - /* Verify that the pathspec matches the prefix */ - if (pathspec) - verify_pathspec(); - - /* Treat unmatching pathspec elements as errors */ - if (pathspec && error_unmatch) { - int num; - for (num = 0; pathspec[num]; num++) - ; - ps_matched = xcalloc(1, num); - } - - if (show_ignored && !exc_given) { - fprintf(stderr, "%s: --ignored needs some exclude pattern\n", - argv[0]); - exit(1); - } - - /* With no flags, we default to showing the cached files */ - if (!(show_stage | show_deleted | show_others | show_unmerged | - show_killed | show_modified)) - show_cached = 1; - - read_cache(); - if (prefix) - prune_cache(); - show_files(); - - if (ps_matched) { - /* We need to make sure all pathspec matched otherwise - * it is an error. - */ - int num, errors = 0; - for (num = 0; pathspec[num]; num++) { - if (ps_matched[num]) - continue; - error("pathspec '%s' did not match any.", - pathspec[num] + prefix_offset); - errors++; - } - return errors ? 1 : 0; - } - - return 0; -} -- cgit v0.10.2-6-g49f6 From aae01bda7f6d3224cf6b2ce0aa9aa668ce35d0b7 Mon Sep 17 00:00:00 2001 From: Peter Eriksen Date: Tue, 23 May 2006 14:15:30 +0200 Subject: Builtin git-ls-tree. Signed-off-by: Peter Eriksen Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index c540d7d..2afd089 100644 --- a/Makefile +++ b/Makefile @@ -155,7 +155,7 @@ PROGRAMS = \ 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-local-fetch$X \ - git-ls-tree$X git-mailinfo$X git-merge-base$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$X git-rev-parse$X \ @@ -171,7 +171,7 @@ PROGRAMS = \ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-count-objects$X git-diff$X git-push$X \ git-grep$X git-rev-list$X git-check-ref-format$X \ - git-init-db$X git-ls-files$X + git-init-db$X git-ls-files$X git-ls-tree$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -220,7 +220,7 @@ LIB_OBJS = \ BUILTIN_OBJS = \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ - builtin-init-db.o builtin-ls-files.o + builtin-init-db.o builtin-ls-files.o builtin-ls-tree.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-ls-tree.c b/builtin-ls-tree.c new file mode 100644 index 0000000..48385d5 --- /dev/null +++ b/builtin-ls-tree.c @@ -0,0 +1,156 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + */ +#include "cache.h" +#include "blob.h" +#include "tree.h" +#include "quote.h" +#include "builtin.h" + +static int line_termination = '\n'; +#define LS_RECURSIVE 1 +#define LS_TREE_ONLY 2 +#define LS_SHOW_TREES 4 +#define LS_NAME_ONLY 8 +static int abbrev = 0; +static int ls_options = 0; +static const char **pathspec; +static int chomp_prefix = 0; +static const char *prefix; + +static const char ls_tree_usage[] = + "git-ls-tree [-d] [-r] [-t] [-z] [--name-only] [--name-status] [--full-name] [--abbrev[=]] [path...]"; + +static int show_recursive(const char *base, int baselen, const char *pathname) +{ + const char **s; + + if (ls_options & LS_RECURSIVE) + return 1; + + s = pathspec; + if (!s) + return 0; + + for (;;) { + const char *spec = *s++; + int len, speclen; + + if (!spec) + return 0; + if (strncmp(base, spec, baselen)) + continue; + len = strlen(pathname); + spec += baselen; + speclen = strlen(spec); + if (speclen <= len) + continue; + if (memcmp(pathname, spec, len)) + continue; + return 1; + } +} + +static int show_tree(unsigned char *sha1, const char *base, int baselen, + const char *pathname, unsigned mode, int stage) +{ + int retval = 0; + const char *type = blob_type; + + if (S_ISDIR(mode)) { + if (show_recursive(base, baselen, pathname)) { + retval = READ_TREE_RECURSIVE; + if (!(ls_options & LS_SHOW_TREES)) + return retval; + } + type = tree_type; + } + else if (ls_options & LS_TREE_ONLY) + return 0; + + if (chomp_prefix && + (baselen < chomp_prefix || memcmp(prefix, base, chomp_prefix))) + return 0; + + if (!(ls_options & LS_NAME_ONLY)) + printf("%06o %s %s\t", mode, type, + abbrev ? find_unique_abbrev(sha1,abbrev) + : sha1_to_hex(sha1)); + write_name_quoted(base + chomp_prefix, baselen - chomp_prefix, + pathname, + line_termination, stdout); + putchar(line_termination); + return retval; +} + +int cmd_ls_tree(int argc, const char **argv, char **envp) +{ + unsigned char sha1[20]; + struct tree *tree; + + prefix = setup_git_directory(); + git_config(git_default_config); + if (prefix && *prefix) + chomp_prefix = strlen(prefix); + while (1 < argc && argv[1][0] == '-') { + switch (argv[1][1]) { + case 'z': + line_termination = 0; + break; + case 'r': + ls_options |= LS_RECURSIVE; + break; + case 'd': + ls_options |= LS_TREE_ONLY; + break; + case 't': + ls_options |= LS_SHOW_TREES; + break; + case '-': + if (!strcmp(argv[1]+2, "name-only") || + !strcmp(argv[1]+2, "name-status")) { + ls_options |= LS_NAME_ONLY; + break; + } + if (!strcmp(argv[1]+2, "full-name")) { + chomp_prefix = 0; + break; + } + if (!strncmp(argv[1]+2, "abbrev=",7)) { + abbrev = strtoul(argv[1]+9, NULL, 10); + if (abbrev && abbrev < MINIMUM_ABBREV) + abbrev = MINIMUM_ABBREV; + else if (abbrev > 40) + abbrev = 40; + break; + } + if (!strcmp(argv[1]+2, "abbrev")) { + abbrev = DEFAULT_ABBREV; + break; + } + /* otherwise fallthru */ + default: + usage(ls_tree_usage); + } + argc--; argv++; + } + /* -d -r should imply -t, but -d by itself should not have to. */ + if ( (LS_TREE_ONLY|LS_RECURSIVE) == + ((LS_TREE_ONLY|LS_RECURSIVE) & ls_options)) + ls_options |= LS_SHOW_TREES; + + if (argc < 2) + usage(ls_tree_usage); + if (get_sha1(argv[1], sha1)) + die("Not a valid object name %s", argv[1]); + + pathspec = get_pathspec(prefix, argv + 2); + tree = parse_tree_indirect(sha1); + if (!tree) + die("not a tree object"); + read_tree_recursive(tree, "", 0, 0, pathspec, show_tree); + + return 0; +} diff --git a/builtin.h b/builtin.h index a0713d3..951f206 100644 --- a/builtin.h +++ b/builtin.h @@ -28,5 +28,6 @@ extern int cmd_rev_list(int argc, const char **argv, char **envp); extern int cmd_check_ref_format(int argc, const char **argv, char **envp); extern int cmd_init_db(int argc, const char **argv, char **envp); extern int cmd_ls_files(int argc, const char **argv, char **envp); +extern int cmd_ls_tree(int argc, const char **argv, char **envp); #endif diff --git a/git.c b/git.c index 9cfa9eb..8574775 100644 --- a/git.c +++ b/git.c @@ -53,7 +53,8 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "rev-list", cmd_rev_list }, { "init-db", cmd_init_db }, { "check-ref-format", cmd_check_ref_format }, - { "ls-files", cmd_ls_files } + { "ls-files", cmd_ls_files }, + { "ls-tree", cmd_ls_tree } }; int i; diff --git a/ls-tree.c b/ls-tree.c deleted file mode 100644 index f2b3bc1..0000000 --- a/ls-tree.c +++ /dev/null @@ -1,155 +0,0 @@ -/* - * GIT - The information manager from hell - * - * Copyright (C) Linus Torvalds, 2005 - */ -#include "cache.h" -#include "blob.h" -#include "tree.h" -#include "quote.h" - -static int line_termination = '\n'; -#define LS_RECURSIVE 1 -#define LS_TREE_ONLY 2 -#define LS_SHOW_TREES 4 -#define LS_NAME_ONLY 8 -static int abbrev = 0; -static int ls_options = 0; -const char **pathspec; -static int chomp_prefix = 0; -static const char *prefix; - -static const char ls_tree_usage[] = - "git-ls-tree [-d] [-r] [-t] [-z] [--name-only] [--name-status] [--full-name] [--abbrev[=]] [path...]"; - -static int show_recursive(const char *base, int baselen, const char *pathname) -{ - const char **s; - - if (ls_options & LS_RECURSIVE) - return 1; - - s = pathspec; - if (!s) - return 0; - - for (;;) { - const char *spec = *s++; - int len, speclen; - - if (!spec) - return 0; - if (strncmp(base, spec, baselen)) - continue; - len = strlen(pathname); - spec += baselen; - speclen = strlen(spec); - if (speclen <= len) - continue; - if (memcmp(pathname, spec, len)) - continue; - return 1; - } -} - -static int show_tree(unsigned char *sha1, const char *base, int baselen, - const char *pathname, unsigned mode, int stage) -{ - int retval = 0; - const char *type = blob_type; - - if (S_ISDIR(mode)) { - if (show_recursive(base, baselen, pathname)) { - retval = READ_TREE_RECURSIVE; - if (!(ls_options & LS_SHOW_TREES)) - return retval; - } - type = tree_type; - } - else if (ls_options & LS_TREE_ONLY) - return 0; - - if (chomp_prefix && - (baselen < chomp_prefix || memcmp(prefix, base, chomp_prefix))) - return 0; - - if (!(ls_options & LS_NAME_ONLY)) - printf("%06o %s %s\t", mode, type, - abbrev ? find_unique_abbrev(sha1,abbrev) - : sha1_to_hex(sha1)); - write_name_quoted(base + chomp_prefix, baselen - chomp_prefix, - pathname, - line_termination, stdout); - putchar(line_termination); - return retval; -} - -int main(int argc, const char **argv) -{ - unsigned char sha1[20]; - struct tree *tree; - - prefix = setup_git_directory(); - git_config(git_default_config); - if (prefix && *prefix) - chomp_prefix = strlen(prefix); - while (1 < argc && argv[1][0] == '-') { - switch (argv[1][1]) { - case 'z': - line_termination = 0; - break; - case 'r': - ls_options |= LS_RECURSIVE; - break; - case 'd': - ls_options |= LS_TREE_ONLY; - break; - case 't': - ls_options |= LS_SHOW_TREES; - break; - case '-': - if (!strcmp(argv[1]+2, "name-only") || - !strcmp(argv[1]+2, "name-status")) { - ls_options |= LS_NAME_ONLY; - break; - } - if (!strcmp(argv[1]+2, "full-name")) { - chomp_prefix = 0; - break; - } - if (!strncmp(argv[1]+2, "abbrev=",7)) { - abbrev = strtoul(argv[1]+9, NULL, 10); - if (abbrev && abbrev < MINIMUM_ABBREV) - abbrev = MINIMUM_ABBREV; - else if (abbrev > 40) - abbrev = 40; - break; - } - if (!strcmp(argv[1]+2, "abbrev")) { - abbrev = DEFAULT_ABBREV; - break; - } - /* otherwise fallthru */ - default: - usage(ls_tree_usage); - } - argc--; argv++; - } - /* -d -r should imply -t, but -d by itself should not have to. */ - if ( (LS_TREE_ONLY|LS_RECURSIVE) == - ((LS_TREE_ONLY|LS_RECURSIVE) & ls_options)) - ls_options |= LS_SHOW_TREES; - - if (argc < 2) - usage(ls_tree_usage); - if (get_sha1(argv[1], sha1)) - die("Not a valid object name %s", argv[1]); - - pathspec = get_pathspec(prefix, argv + 2); - tree = parse_tree_indirect(sha1); - if (!tree) - die("not a tree object"); - read_tree_recursive(tree, "", 0, 0, pathspec, show_tree); - - return 0; -} -- cgit v0.10.2-6-g49f6 From 56d1398ad305498faf57d6e433f97ad393d7909e Mon Sep 17 00:00:00 2001 From: Peter Eriksen Date: Tue, 23 May 2006 14:15:31 +0200 Subject: Builtin git-tar-tree. Signed-off-by: Peter Eriksen Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index 2afd089..a3164f8 100644 --- a/Makefile +++ b/Makefile @@ -161,7 +161,7 @@ PROGRAMS = \ git-receive-pack$X git-rev-parse$X \ git-send-pack$X git-show-branch$X git-shell$X \ git-show-index$X git-ssh-fetch$X \ - git-ssh-upload$X git-tar-tree$X git-unpack-file$X \ + git-ssh-upload$X git-unpack-file$X \ git-unpack-objects$X git-update-index$X git-update-server-info$X \ git-upload-pack$X git-verify-pack$X git-write-tree$X \ git-update-ref$X git-symbolic-ref$X \ @@ -171,7 +171,8 @@ PROGRAMS = \ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-count-objects$X git-diff$X git-push$X \ git-grep$X git-rev-list$X git-check-ref-format$X \ - git-init-db$X git-ls-files$X git-ls-tree$X + git-init-db$X git-ls-files$X git-ls-tree$X \ + git-tar-tree$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -220,7 +221,8 @@ LIB_OBJS = \ BUILTIN_OBJS = \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ - builtin-init-db.o builtin-ls-files.o builtin-ls-tree.o + builtin-init-db.o builtin-ls-files.o builtin-ls-tree.o \ + builtin-tar-tree.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-tar-tree.c b/builtin-tar-tree.c new file mode 100644 index 0000000..6ada04c --- /dev/null +++ b/builtin-tar-tree.c @@ -0,0 +1,351 @@ +/* + * Copyright (c) 2005, 2006 Rene Scharfe + */ +#include +#include "cache.h" +#include "tree-walk.h" +#include "commit.h" +#include "strbuf.h" +#include "tar.h" +#include "builtin.h" + +#define RECORDSIZE (512) +#define BLOCKSIZE (RECORDSIZE * 20) + +static const char tar_tree_usage[] = "git-tar-tree [basedir]"; + +static char block[BLOCKSIZE]; +static unsigned long offset; + +static time_t archive_time; + +/* tries hard to write, either succeeds or dies in the attempt */ +static void reliable_write(void *buf, unsigned long size) +{ + while (size > 0) { + long ret = xwrite(1, buf, size); + if (ret < 0) { + if (errno == EPIPE) + exit(0); + die("git-tar-tree: %s", strerror(errno)); + } else if (!ret) { + die("git-tar-tree: disk full?"); + } + size -= ret; + buf += ret; + } +} + +/* writes out the whole block, but only if it is full */ +static void write_if_needed(void) +{ + if (offset == BLOCKSIZE) { + reliable_write(block, BLOCKSIZE); + offset = 0; + } +} + +/* acquire the next record from the buffer; user must call write_if_needed() */ +static char *get_record(void) +{ + char *p = block + offset; + memset(p, 0, RECORDSIZE); + offset += RECORDSIZE; + return p; +} + +/* + * The end of tar archives is marked by 1024 nul bytes and after that + * follows the rest of the block (if any). + */ +static void write_trailer(void) +{ + get_record(); + write_if_needed(); + get_record(); + write_if_needed(); + while (offset) { + get_record(); + write_if_needed(); + } +} + +/* + * queues up writes, so that all our write(2) calls write exactly one + * full block; pads writes to RECORDSIZE + */ +static void write_blocked(void *buf, unsigned long size) +{ + unsigned long tail; + + if (offset) { + unsigned long chunk = BLOCKSIZE - offset; + if (size < chunk) + chunk = size; + memcpy(block + offset, buf, chunk); + size -= chunk; + offset += chunk; + buf += chunk; + write_if_needed(); + } + while (size >= BLOCKSIZE) { + reliable_write(buf, BLOCKSIZE); + size -= BLOCKSIZE; + buf += BLOCKSIZE; + } + if (size) { + memcpy(block + offset, buf, size); + offset += size; + } + tail = offset % RECORDSIZE; + if (tail) { + memset(block + offset, 0, RECORDSIZE - tail); + offset += RECORDSIZE - tail; + } + write_if_needed(); +} + +static void strbuf_append_string(struct strbuf *sb, const char *s) +{ + int slen = strlen(s); + int total = sb->len + slen; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; + } + memcpy(sb->buf + sb->len, s, slen); + sb->len = total; +} + +/* + * pax extended header records have the format "%u %s=%s\n". %u contains + * the size of the whole string (including the %u), the first %s is the + * keyword, the second one is the value. This function constructs such a + * string and appends it to a struct strbuf. + */ +static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword, + const char *value, unsigned int valuelen) +{ + char *p; + int len, total, tmp; + + /* "%u %s=%s\n" */ + len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; + for (tmp = len; tmp > 9; tmp /= 10) + len++; + + total = sb->len + len; + if (total > sb->alloc) { + sb->buf = xrealloc(sb->buf, total); + sb->alloc = total; + } + + p = sb->buf; + p += sprintf(p, "%u %s=", len, keyword); + memcpy(p, value, valuelen); + p += valuelen; + *p = '\n'; + sb->len = total; +} + +static unsigned int ustar_header_chksum(const struct ustar_header *header) +{ + char *p = (char *)header; + unsigned int chksum = 0; + while (p < header->chksum) + chksum += *p++; + chksum += sizeof(header->chksum) * ' '; + p += sizeof(header->chksum); + while (p < (char *)header + sizeof(struct ustar_header)) + chksum += *p++; + return chksum; +} + +static int get_path_prefix(const struct strbuf *path, int maxlen) +{ + int i = path->len; + if (i > maxlen) + i = maxlen; + while (i > 0 && path->buf[i] != '/') + i--; + return i; +} + +static void write_entry(const unsigned char *sha1, struct strbuf *path, + unsigned int mode, void *buffer, unsigned long size) +{ + struct ustar_header header; + struct strbuf ext_header; + + memset(&header, 0, sizeof(header)); + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + + if (!sha1) { + *header.typeflag = TYPEFLAG_GLOBAL_HEADER; + mode = 0100666; + strcpy(header.name, "pax_global_header"); + } else if (!path) { + *header.typeflag = TYPEFLAG_EXT_HEADER; + mode = 0100666; + sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1)); + } else { + if (S_ISDIR(mode)) { + *header.typeflag = TYPEFLAG_DIR; + mode |= 0777; + } else if (S_ISLNK(mode)) { + *header.typeflag = TYPEFLAG_LNK; + mode |= 0777; + } else if (S_ISREG(mode)) { + *header.typeflag = TYPEFLAG_REG; + mode |= (mode & 0100) ? 0777 : 0666; + } else { + error("unsupported file mode: 0%o (SHA1: %s)", + mode, sha1_to_hex(sha1)); + return; + } + if (path->len > sizeof(header.name)) { + int plen = get_path_prefix(path, sizeof(header.prefix)); + int rest = path->len - plen - 1; + if (plen > 0 && rest <= sizeof(header.name)) { + memcpy(header.prefix, path->buf, plen); + memcpy(header.name, path->buf + plen + 1, rest); + } else { + sprintf(header.name, "%s.data", + sha1_to_hex(sha1)); + strbuf_append_ext_header(&ext_header, "path", + path->buf, path->len); + } + } else + memcpy(header.name, path->buf, path->len); + } + + if (S_ISLNK(mode) && buffer) { + if (size > sizeof(header.linkname)) { + sprintf(header.linkname, "see %s.paxheader", + sha1_to_hex(sha1)); + strbuf_append_ext_header(&ext_header, "linkpath", + buffer, size); + } else + memcpy(header.linkname, buffer, size); + } + + sprintf(header.mode, "%07o", mode & 07777); + sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0); + sprintf(header.mtime, "%011lo", archive_time); + + /* XXX: should we provide more meaningful info here? */ + sprintf(header.uid, "%07o", 0); + sprintf(header.gid, "%07o", 0); + strncpy(header.uname, "git", 31); + strncpy(header.gname, "git", 31); + sprintf(header.devmajor, "%07o", 0); + sprintf(header.devminor, "%07o", 0); + + memcpy(header.magic, "ustar", 6); + memcpy(header.version, "00", 2); + + sprintf(header.chksum, "%07o", ustar_header_chksum(&header)); + + if (ext_header.len > 0) { + write_entry(sha1, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); + } + write_blocked(&header, sizeof(header)); + if (S_ISREG(mode) && buffer && size > 0) + write_blocked(buffer, size); +} + +static void write_global_extended_header(const unsigned char *sha1) +{ + struct strbuf ext_header; + ext_header.buf = NULL; + ext_header.len = ext_header.alloc = 0; + strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); + write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); + free(ext_header.buf); +} + +static void traverse_tree(struct tree_desc *tree, struct strbuf *path) +{ + int pathlen = path->len; + + while (tree->size) { + const char *name; + const unsigned char *sha1; + unsigned mode; + void *eltbuf; + char elttype[20]; + unsigned long eltsize; + + sha1 = tree_entry_extract(tree, &name, &mode); + update_tree_entry(tree); + + eltbuf = read_sha1_file(sha1, elttype, &eltsize); + if (!eltbuf) + die("cannot read %s", sha1_to_hex(sha1)); + + path->len = pathlen; + strbuf_append_string(path, name); + if (S_ISDIR(mode)) + strbuf_append_string(path, "/"); + + write_entry(sha1, path, mode, eltbuf, eltsize); + + if (S_ISDIR(mode)) { + struct tree_desc subtree; + subtree.buf = eltbuf; + subtree.size = eltsize; + traverse_tree(&subtree, path); + } + free(eltbuf); + } +} + +int cmd_tar_tree(int argc, const char **argv, char** envp) +{ + unsigned char sha1[20], tree_sha1[20]; + struct commit *commit; + struct tree_desc tree; + struct strbuf current_path; + + current_path.buf = xmalloc(PATH_MAX); + current_path.alloc = PATH_MAX; + current_path.len = current_path.eof = 0; + + setup_git_directory(); + git_config(git_default_config); + + switch (argc) { + case 3: + strbuf_append_string(¤t_path, argv[2]); + strbuf_append_string(¤t_path, "/"); + /* FALLTHROUGH */ + case 2: + if (get_sha1(argv[1], sha1)) + die("Not a valid object name %s", argv[1]); + break; + default: + usage(tar_tree_usage); + } + + commit = lookup_commit_reference_gently(sha1, 1); + if (commit) { + write_global_extended_header(commit->object.sha1); + archive_time = commit->date; + } else + archive_time = time(NULL); + + tree.buf = read_object_with_reference(sha1, tree_type, &tree.size, + tree_sha1); + if (!tree.buf) + die("not a reference to a tag, commit or tree object: %s", + sha1_to_hex(sha1)); + + if (current_path.len > 0) + write_entry(tree_sha1, ¤t_path, 040777, NULL, 0); + traverse_tree(&tree, ¤t_path); + write_trailer(); + free(current_path.buf); + return 0; +} diff --git a/builtin.h b/builtin.h index 951f206..d210543 100644 --- a/builtin.h +++ b/builtin.h @@ -29,5 +29,6 @@ extern int cmd_check_ref_format(int argc, const char **argv, char **envp); extern int cmd_init_db(int argc, const char **argv, char **envp); extern int cmd_ls_files(int argc, const char **argv, char **envp); extern int cmd_ls_tree(int argc, const char **argv, char **envp); +extern int cmd_tar_tree(int argc, const char **argv, char **envp); #endif diff --git a/git.c b/git.c index 8574775..c253e60 100644 --- a/git.c +++ b/git.c @@ -54,7 +54,8 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "init-db", cmd_init_db }, { "check-ref-format", cmd_check_ref_format }, { "ls-files", cmd_ls_files }, - { "ls-tree", cmd_ls_tree } + { "ls-tree", cmd_ls_tree }, + { "tar-tree", cmd_tar_tree } }; int i; diff --git a/tar-tree.c b/tar-tree.c deleted file mode 100644 index 3308736..0000000 --- a/tar-tree.c +++ /dev/null @@ -1,350 +0,0 @@ -/* - * Copyright (c) 2005, 2006 Rene Scharfe - */ -#include -#include "cache.h" -#include "tree-walk.h" -#include "commit.h" -#include "strbuf.h" -#include "tar.h" - -#define RECORDSIZE (512) -#define BLOCKSIZE (RECORDSIZE * 20) - -static const char tar_tree_usage[] = "git-tar-tree [basedir]"; - -static char block[BLOCKSIZE]; -static unsigned long offset; - -static time_t archive_time; - -/* tries hard to write, either succeeds or dies in the attempt */ -static void reliable_write(void *buf, unsigned long size) -{ - while (size > 0) { - long ret = xwrite(1, buf, size); - if (ret < 0) { - if (errno == EPIPE) - exit(0); - die("git-tar-tree: %s", strerror(errno)); - } else if (!ret) { - die("git-tar-tree: disk full?"); - } - size -= ret; - buf += ret; - } -} - -/* writes out the whole block, but only if it is full */ -static void write_if_needed(void) -{ - if (offset == BLOCKSIZE) { - reliable_write(block, BLOCKSIZE); - offset = 0; - } -} - -/* acquire the next record from the buffer; user must call write_if_needed() */ -static char *get_record(void) -{ - char *p = block + offset; - memset(p, 0, RECORDSIZE); - offset += RECORDSIZE; - return p; -} - -/* - * The end of tar archives is marked by 1024 nul bytes and after that - * follows the rest of the block (if any). - */ -static void write_trailer(void) -{ - get_record(); - write_if_needed(); - get_record(); - write_if_needed(); - while (offset) { - get_record(); - write_if_needed(); - } -} - -/* - * queues up writes, so that all our write(2) calls write exactly one - * full block; pads writes to RECORDSIZE - */ -static void write_blocked(void *buf, unsigned long size) -{ - unsigned long tail; - - if (offset) { - unsigned long chunk = BLOCKSIZE - offset; - if (size < chunk) - chunk = size; - memcpy(block + offset, buf, chunk); - size -= chunk; - offset += chunk; - buf += chunk; - write_if_needed(); - } - while (size >= BLOCKSIZE) { - reliable_write(buf, BLOCKSIZE); - size -= BLOCKSIZE; - buf += BLOCKSIZE; - } - if (size) { - memcpy(block + offset, buf, size); - offset += size; - } - tail = offset % RECORDSIZE; - if (tail) { - memset(block + offset, 0, RECORDSIZE - tail); - offset += RECORDSIZE - tail; - } - write_if_needed(); -} - -static void strbuf_append_string(struct strbuf *sb, const char *s) -{ - int slen = strlen(s); - int total = sb->len + slen; - if (total > sb->alloc) { - sb->buf = xrealloc(sb->buf, total); - sb->alloc = total; - } - memcpy(sb->buf + sb->len, s, slen); - sb->len = total; -} - -/* - * pax extended header records have the format "%u %s=%s\n". %u contains - * the size of the whole string (including the %u), the first %s is the - * keyword, the second one is the value. This function constructs such a - * string and appends it to a struct strbuf. - */ -static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword, - const char *value, unsigned int valuelen) -{ - char *p; - int len, total, tmp; - - /* "%u %s=%s\n" */ - len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; - for (tmp = len; tmp > 9; tmp /= 10) - len++; - - total = sb->len + len; - if (total > sb->alloc) { - sb->buf = xrealloc(sb->buf, total); - sb->alloc = total; - } - - p = sb->buf; - p += sprintf(p, "%u %s=", len, keyword); - memcpy(p, value, valuelen); - p += valuelen; - *p = '\n'; - sb->len = total; -} - -static unsigned int ustar_header_chksum(const struct ustar_header *header) -{ - char *p = (char *)header; - unsigned int chksum = 0; - while (p < header->chksum) - chksum += *p++; - chksum += sizeof(header->chksum) * ' '; - p += sizeof(header->chksum); - while (p < (char *)header + sizeof(struct ustar_header)) - chksum += *p++; - return chksum; -} - -static int get_path_prefix(const struct strbuf *path, int maxlen) -{ - int i = path->len; - if (i > maxlen) - i = maxlen; - while (i > 0 && path->buf[i] != '/') - i--; - return i; -} - -static void write_entry(const unsigned char *sha1, struct strbuf *path, - unsigned int mode, void *buffer, unsigned long size) -{ - struct ustar_header header; - struct strbuf ext_header; - - memset(&header, 0, sizeof(header)); - ext_header.buf = NULL; - ext_header.len = ext_header.alloc = 0; - - if (!sha1) { - *header.typeflag = TYPEFLAG_GLOBAL_HEADER; - mode = 0100666; - strcpy(header.name, "pax_global_header"); - } else if (!path) { - *header.typeflag = TYPEFLAG_EXT_HEADER; - mode = 0100666; - sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1)); - } else { - if (S_ISDIR(mode)) { - *header.typeflag = TYPEFLAG_DIR; - mode |= 0777; - } else if (S_ISLNK(mode)) { - *header.typeflag = TYPEFLAG_LNK; - mode |= 0777; - } else if (S_ISREG(mode)) { - *header.typeflag = TYPEFLAG_REG; - mode |= (mode & 0100) ? 0777 : 0666; - } else { - error("unsupported file mode: 0%o (SHA1: %s)", - mode, sha1_to_hex(sha1)); - return; - } - if (path->len > sizeof(header.name)) { - int plen = get_path_prefix(path, sizeof(header.prefix)); - int rest = path->len - plen - 1; - if (plen > 0 && rest <= sizeof(header.name)) { - memcpy(header.prefix, path->buf, plen); - memcpy(header.name, path->buf + plen + 1, rest); - } else { - sprintf(header.name, "%s.data", - sha1_to_hex(sha1)); - strbuf_append_ext_header(&ext_header, "path", - path->buf, path->len); - } - } else - memcpy(header.name, path->buf, path->len); - } - - if (S_ISLNK(mode) && buffer) { - if (size > sizeof(header.linkname)) { - sprintf(header.linkname, "see %s.paxheader", - sha1_to_hex(sha1)); - strbuf_append_ext_header(&ext_header, "linkpath", - buffer, size); - } else - memcpy(header.linkname, buffer, size); - } - - sprintf(header.mode, "%07o", mode & 07777); - sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0); - sprintf(header.mtime, "%011lo", archive_time); - - /* XXX: should we provide more meaningful info here? */ - sprintf(header.uid, "%07o", 0); - sprintf(header.gid, "%07o", 0); - strncpy(header.uname, "git", 31); - strncpy(header.gname, "git", 31); - sprintf(header.devmajor, "%07o", 0); - sprintf(header.devminor, "%07o", 0); - - memcpy(header.magic, "ustar", 6); - memcpy(header.version, "00", 2); - - sprintf(header.chksum, "%07o", ustar_header_chksum(&header)); - - if (ext_header.len > 0) { - write_entry(sha1, NULL, 0, ext_header.buf, ext_header.len); - free(ext_header.buf); - } - write_blocked(&header, sizeof(header)); - if (S_ISREG(mode) && buffer && size > 0) - write_blocked(buffer, size); -} - -static void write_global_extended_header(const unsigned char *sha1) -{ - struct strbuf ext_header; - ext_header.buf = NULL; - ext_header.len = ext_header.alloc = 0; - strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); - write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); - free(ext_header.buf); -} - -static void traverse_tree(struct tree_desc *tree, struct strbuf *path) -{ - int pathlen = path->len; - - while (tree->size) { - const char *name; - const unsigned char *sha1; - unsigned mode; - void *eltbuf; - char elttype[20]; - unsigned long eltsize; - - sha1 = tree_entry_extract(tree, &name, &mode); - update_tree_entry(tree); - - eltbuf = read_sha1_file(sha1, elttype, &eltsize); - if (!eltbuf) - die("cannot read %s", sha1_to_hex(sha1)); - - path->len = pathlen; - strbuf_append_string(path, name); - if (S_ISDIR(mode)) - strbuf_append_string(path, "/"); - - write_entry(sha1, path, mode, eltbuf, eltsize); - - if (S_ISDIR(mode)) { - struct tree_desc subtree; - subtree.buf = eltbuf; - subtree.size = eltsize; - traverse_tree(&subtree, path); - } - free(eltbuf); - } -} - -int main(int argc, char **argv) -{ - unsigned char sha1[20], tree_sha1[20]; - struct commit *commit; - struct tree_desc tree; - struct strbuf current_path; - - current_path.buf = xmalloc(PATH_MAX); - current_path.alloc = PATH_MAX; - current_path.len = current_path.eof = 0; - - setup_git_directory(); - git_config(git_default_config); - - switch (argc) { - case 3: - strbuf_append_string(¤t_path, argv[2]); - strbuf_append_string(¤t_path, "/"); - /* FALLTHROUGH */ - case 2: - if (get_sha1(argv[1], sha1)) - die("Not a valid object name %s", argv[1]); - break; - default: - usage(tar_tree_usage); - } - - commit = lookup_commit_reference_gently(sha1, 1); - if (commit) { - write_global_extended_header(commit->object.sha1); - archive_time = commit->date; - } else - archive_time = time(NULL); - - tree.buf = read_object_with_reference(sha1, tree_type, &tree.size, - tree_sha1); - if (!tree.buf) - die("not a reference to a tag, commit or tree object: %s", - sha1_to_hex(sha1)); - - if (current_path.len > 0) - write_entry(tree_sha1, ¤t_path, 040777, NULL, 0); - traverse_tree(&tree, ¤t_path); - write_trailer(); - free(current_path.buf); - return 0; -} -- cgit v0.10.2-6-g49f6 From d147e501f37a596e73a430ce46f125f83e06aa07 Mon Sep 17 00:00:00 2001 From: Peter Eriksen Date: Tue, 23 May 2006 14:15:32 +0200 Subject: Builtin git-read-tree. Signed-off-by: Peter Eriksen Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index a3164f8..1aebcf5 100644 --- a/Makefile +++ b/Makefile @@ -157,7 +157,7 @@ PROGRAMS = \ git-hash-object$X git-index-pack$X git-local-fetch$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-peek-remote$X git-prune-packed$X \ git-receive-pack$X git-rev-parse$X \ git-send-pack$X git-show-branch$X git-shell$X \ git-show-index$X git-ssh-fetch$X \ @@ -172,7 +172,7 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-count-objects$X git-diff$X git-push$X \ git-grep$X git-rev-list$X git-check-ref-format$X \ git-init-db$X git-ls-files$X git-ls-tree$X \ - git-tar-tree$X + git-tar-tree$X git-read-tree$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -222,7 +222,7 @@ BUILTIN_OBJS = \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ builtin-init-db.o builtin-ls-files.o builtin-ls-tree.o \ - builtin-tar-tree.o + builtin-tar-tree.o builtin-read-tree.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-read-tree.c b/builtin-read-tree.c new file mode 100644 index 0000000..ec40d01 --- /dev/null +++ b/builtin-read-tree.c @@ -0,0 +1,882 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + */ +#define DBRT_DEBUG 1 + +#include "cache.h" + +#include "object.h" +#include "tree.h" +#include +#include +#include "builtin.h" + +static int reset = 0; +static int merge = 0; +static int update = 0; +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; + +static struct object_list *trees = NULL; + +static struct cache_entry df_conflict_entry = { +}; + +static struct tree_entry_list df_conflict_list = { + .name = NULL, + .next = &df_conflict_list +}; + +typedef int (*merge_fn_t)(struct cache_entry **src); + +static int entcmp(char *name1, int dir1, char *name2, int dir2) +{ + int len1 = strlen(name1); + int len2 = strlen(name2); + int len = len1 < len2 ? len1 : len2; + int ret = memcmp(name1, name2, len); + unsigned char c1, c2; + if (ret) + return ret; + c1 = name1[len]; + c2 = name2[len]; + if (!c1 && dir1) + c1 = '/'; + if (!c2 && dir2) + c2 = '/'; + ret = (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0; + if (c1 && c2 && !ret) + ret = len1 - len2; + return ret; +} + +static int unpack_trees_rec(struct tree_entry_list **posns, int len, + const char *base, merge_fn_t fn, int *indpos) +{ + int baselen = strlen(base); + int src_size = len + 1; + do { + int i; + char *first; + int firstdir = 0; + int pathlen; + unsigned ce_size; + struct tree_entry_list **subposns; + struct cache_entry **src; + int any_files = 0; + int any_dirs = 0; + char *cache_name; + int ce_stage; + + /* Find the first name in the input. */ + + first = NULL; + cache_name = NULL; + + /* Check the cache */ + if (merge && *indpos < active_nr) { + /* This is a bit tricky: */ + /* If the index has a subdirectory (with + * contents) as the first name, it'll get a + * filename like "foo/bar". But that's after + * "foo", so the entry in trees will get + * handled first, at which point we'll go into + * "foo", and deal with "bar" from the index, + * because the base will be "foo/". The only + * way we can actually have "foo/bar" first of + * all the things is if the trees don't + * contain "foo" at all, in which case we'll + * handle "foo/bar" without going into the + * directory, but that's fine (and will return + * an error anyway, with the added unknown + * file case. + */ + + cache_name = active_cache[*indpos]->name; + if (strlen(cache_name) > baselen && + !memcmp(cache_name, base, baselen)) { + cache_name += baselen; + first = cache_name; + } else { + cache_name = NULL; + } + } + +#if DBRT_DEBUG > 1 + if (first) + printf("index %s\n", first); +#endif + for (i = 0; i < len; i++) { + if (!posns[i] || posns[i] == &df_conflict_list) + continue; +#if DBRT_DEBUG > 1 + printf("%d %s\n", i + 1, posns[i]->name); +#endif + if (!first || entcmp(first, firstdir, + posns[i]->name, + posns[i]->directory) > 0) { + first = posns[i]->name; + firstdir = posns[i]->directory; + } + } + /* No name means we're done */ + if (!first) + return 0; + + pathlen = strlen(first); + ce_size = cache_entry_size(baselen + pathlen); + + src = xcalloc(src_size, sizeof(struct cache_entry *)); + + subposns = xcalloc(len, sizeof(struct tree_list_entry *)); + + if (cache_name && !strcmp(cache_name, first)) { + any_files = 1; + src[0] = active_cache[*indpos]; + remove_cache_entry_at(*indpos); + } + + for (i = 0; i < len; i++) { + struct cache_entry *ce; + + if (!posns[i] || + (posns[i] != &df_conflict_list && + strcmp(first, posns[i]->name))) { + continue; + } + + if (posns[i] == &df_conflict_list) { + src[i + merge] = &df_conflict_entry; + continue; + } + + if (posns[i]->directory) { + any_dirs = 1; + parse_tree(posns[i]->item.tree); + subposns[i] = posns[i]->item.tree->entries; + posns[i] = posns[i]->next; + src[i + merge] = &df_conflict_entry; + continue; + } + + if (!merge) + ce_stage = 0; + else if (i + 1 < head_idx) + ce_stage = 1; + else if (i + 1 > head_idx) + ce_stage = 3; + else + ce_stage = 2; + + ce = xcalloc(1, ce_size); + ce->ce_mode = create_ce_mode(posns[i]->mode); + ce->ce_flags = create_ce_flags(baselen + pathlen, + ce_stage); + memcpy(ce->name, base, baselen); + memcpy(ce->name + baselen, first, pathlen + 1); + + any_files = 1; + + memcpy(ce->sha1, posns[i]->item.any->sha1, 20); + src[i + merge] = ce; + subposns[i] = &df_conflict_list; + posns[i] = posns[i]->next; + } + if (any_files) { + if (merge) { + int ret; + +#if DBRT_DEBUG > 1 + printf("%s:\n", first); + for (i = 0; i < src_size; i++) { + printf(" %d ", i); + if (src[i]) + printf("%s\n", sha1_to_hex(src[i]->sha1)); + else + printf("\n"); + } +#endif + ret = fn(src); + +#if DBRT_DEBUG > 1 + printf("Added %d entries\n", ret); +#endif + *indpos += ret; + } else { + for (i = 0; i < src_size; i++) { + if (src[i]) { + add_cache_entry(src[i], ADD_CACHE_OK_TO_ADD|ADD_CACHE_SKIP_DFCHECK); + } + } + } + } + if (any_dirs) { + char *newbase = xmalloc(baselen + 2 + pathlen); + memcpy(newbase, base, baselen); + memcpy(newbase + baselen, first, pathlen); + newbase[baselen + pathlen] = '/'; + newbase[baselen + pathlen + 1] = '\0'; + if (unpack_trees_rec(subposns, len, newbase, fn, + indpos)) + return -1; + free(newbase); + } + free(subposns); + free(src); + } while (1); +} + +static void reject_merge(struct cache_entry *ce) +{ + die("Entry '%s' would be overwritten by merge. Cannot merge.", + ce->name); +} + +/* Unlink the last component and attempt to remove leading + * directories, in case this unlink is the removal of the + * last entry in the directory -- empty directories are removed. + */ +static void unlink_entry(char *name) +{ + char *cp, *prev; + + if (unlink(name)) + return; + prev = NULL; + while (1) { + int status; + cp = strrchr(name, '/'); + if (prev) + *prev = '/'; + if (!cp) + break; + + *cp = 0; + status = rmdir(name); + if (status) { + *cp = '/'; + break; + } + prev = cp; + } +} + +static void progress_interval(int signum) +{ + progress_update = 1; +} + +static void setup_progress_signal(void) +{ + struct sigaction sa; + struct itimerval v; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = progress_interval; + sigemptyset(&sa.sa_mask); + sa.sa_flags = SA_RESTART; + sigaction(SIGALRM, &sa, NULL); + + v.it_interval.tv_sec = 1; + v.it_interval.tv_usec = 0; + v.it_value = v.it_interval; + setitimer(ITIMER_REAL, &v, NULL); +} + +static void check_updates(struct cache_entry **src, int nr) +{ + static struct checkout state = { + .base_dir = "", + .force = 1, + .quiet = 1, + .refresh_cache = 1, + }; + unsigned short mask = htons(CE_UPDATE); + unsigned last_percent = 200, cnt = 0, total = 0; + + if (update && verbose_update) { + 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) { + fprintf(stderr, "Checking files out...\n"); + setup_progress_signal(); + 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); + continue; + } + if (ce->ce_flags & mask) { + ce->ce_flags &= ~mask; + if (update) + checkout_entry(ce, &state, NULL); + } + } + if (total) { + signal(SIGALRM, SIG_IGN); + fputc('\n', stderr); + } +} + +static int unpack_trees(merge_fn_t fn) +{ + int indpos = 0; + unsigned len = object_list_length(trees); + struct tree_entry_list **posns; + int i; + struct object_list *posn = trees; + merge_size = len; + + if (len) { + posns = xmalloc(len * sizeof(struct tree_entry_list *)); + for (i = 0; i < len; i++) { + posns[i] = ((struct tree *) posn->item)->entries; + posn = posn->next; + } + if (unpack_trees_rec(posns, len, "", fn, &indpos)) + return -1; + } + + if (trivial_merges_only && nontrivial_merge) + die("Merge requires file-level merging"); + + check_updates(active_cache, active_nr); + return 0; +} + +static int list_tree(unsigned char *sha1) +{ + struct tree *tree = parse_tree_indirect(sha1); + if (!tree) + return -1; + object_list_append(&tree->object, &trees); + return 0; +} + +static int same(struct cache_entry *a, struct cache_entry *b) +{ + if (!!a != !!b) + return 0; + if (!a && !b) + return 1; + return a->ce_mode == b->ce_mode && + !memcmp(a->sha1, b->sha1, 20); +} + + +/* + * When a CE gets turned into an unmerged entry, we + * want it to be up-to-date + */ +static void verify_uptodate(struct cache_entry *ce) +{ + struct stat st; + + if (index_only || reset) + return; + + if (!lstat(ce->name, &st)) { + unsigned changed = ce_match_stat(ce, &st, 1); + if (!changed) + return; + errno = 0; + } + if (reset) { + ce->ce_flags |= htons(CE_UPDATE); + return; + } + if (errno == ENOENT) + return; + die("Entry '%s' not uptodate. Cannot merge.", ce->name); +} + +/* + * We do not want to remove or overwrite a working tree file that + * is not tracked. + */ +static void verify_absent(const char *path, const char *action) +{ + struct stat st; + + if (index_only || reset || !update) + return; + if (!lstat(path, &st)) + die("Untracked working tree file '%s' " + "would be %s by merge.", path, action); +} + +static int merged_entry(struct cache_entry *merge, struct cache_entry *old) +{ + merge->ce_flags |= htons(CE_UPDATE); + if (old) { + /* + * See if we can re-use the old CE directly? + * That way we get the uptodate stat info. + * + * This also removes the UPDATE flag on + * a match. + */ + if (same(old, merge)) { + *merge = *old; + } else { + verify_uptodate(old); + } + } + else + verify_absent(merge->name, "overwritten"); + + merge->ce_flags &= ~htons(CE_STAGEMASK); + add_cache_entry(merge, ADD_CACHE_OK_TO_ADD); + return 1; +} + +static int deleted_entry(struct cache_entry *ce, struct cache_entry *old) +{ + if (old) + verify_uptodate(old); + else + verify_absent(ce->name, "removed"); + ce->ce_mode = 0; + add_cache_entry(ce, ADD_CACHE_OK_TO_ADD); + return 1; +} + +static int keep_entry(struct cache_entry *ce) +{ + add_cache_entry(ce, ADD_CACHE_OK_TO_ADD); + return 1; +} + +#if DBRT_DEBUG +static void show_stage_entry(FILE *o, + const char *label, const struct cache_entry *ce) +{ + if (!ce) + fprintf(o, "%s (missing)\n", label); + else + fprintf(o, "%s%06o %s %d\t%s\n", + label, + ntohl(ce->ce_mode), + sha1_to_hex(ce->sha1), + ce_stage(ce), + ce->name); +} +#endif + +static int threeway_merge(struct cache_entry **stages) +{ + struct cache_entry *index; + struct cache_entry *head; + struct cache_entry *remote = stages[head_idx + 1]; + int count; + int head_match = 0; + int remote_match = 0; + const char *path = NULL; + + int df_conflict_head = 0; + int df_conflict_remote = 0; + + int any_anc_missing = 0; + int no_anc_exists = 1; + int i; + + for (i = 1; i < head_idx; i++) { + if (!stages[i]) + any_anc_missing = 1; + else { + if (!path) + path = stages[i]->name; + no_anc_exists = 0; + } + } + + index = stages[0]; + head = stages[head_idx]; + + if (head == &df_conflict_entry) { + df_conflict_head = 1; + head = NULL; + } + + if (remote == &df_conflict_entry) { + df_conflict_remote = 1; + remote = NULL; + } + + if (!path && index) + path = index->name; + if (!path && head) + path = head->name; + if (!path && remote) + path = remote->name; + + /* First, if there's a #16 situation, note that to prevent #13 + * and #14. + */ + if (!same(remote, head)) { + for (i = 1; i < head_idx; i++) { + if (same(stages[i], head)) { + head_match = i; + } + if (same(stages[i], remote)) { + remote_match = i; + } + } + } + + /* We start with cases where the index is allowed to match + * something other than the head: #14(ALT) and #2ALT, where it + * is permitted to match the result instead. + */ + /* #14, #14ALT, #2ALT */ + if (remote && !df_conflict_head && head_match && !remote_match) { + if (index && !same(index, remote) && !same(index, head)) + reject_merge(index); + return merged_entry(remote, index); + } + /* + * If we have an entry in the index cache, then we want to + * make sure that it matches head. + */ + if (index && !same(index, head)) { + reject_merge(index); + } + + if (head) { + /* #5ALT, #15 */ + if (same(head, remote)) + return merged_entry(head, index); + /* #13, #3ALT */ + if (!df_conflict_remote && remote_match && !head_match) + return merged_entry(head, index); + } + + /* #1 */ + if (!head && !remote && any_anc_missing) + return 0; + + /* Under the new "aggressive" rule, we resolve mostly trivial + * cases that we historically had git-merge-one-file resolve. + */ + if (aggressive) { + int head_deleted = !head && !df_conflict_head; + int remote_deleted = !remote && !df_conflict_remote; + /* + * Deleted in both. + * Deleted in one and unchanged in the other. + */ + if ((head_deleted && remote_deleted) || + (head_deleted && remote && remote_match) || + (remote_deleted && head && head_match)) { + if (index) + return deleted_entry(index, index); + else if (path) + verify_absent(path, "removed"); + return 0; + } + /* + * Added in both, identically. + */ + if (no_anc_exists && head && remote && same(head, remote)) + return merged_entry(head, index); + + } + + /* Below are "no merge" cases, which require that the index be + * up-to-date to avoid the files getting overwritten with + * conflict resolution files. + */ + if (index) { + verify_uptodate(index); + } + else if (path) + verify_absent(path, "overwritten"); + + nontrivial_merge = 1; + + /* #2, #3, #4, #6, #7, #9, #11. */ + count = 0; + if (!head_match || !remote_match) { + for (i = 1; i < head_idx; i++) { + if (stages[i]) { + keep_entry(stages[i]); + count++; + break; + } + } + } +#if DBRT_DEBUG + else { + fprintf(stderr, "read-tree: warning #16 detected\n"); + show_stage_entry(stderr, "head ", stages[head_match]); + show_stage_entry(stderr, "remote ", stages[remote_match]); + } +#endif + if (head) { count += keep_entry(head); } + if (remote) { count += keep_entry(remote); } + return count; +} + +/* + * Two-way merge. + * + * The rule is to "carry forward" what is in the index without losing + * information across a "fast forward", favoring a successful merge + * over a merge failure when it makes sense. For details of the + * "carry forward" rule, please see . + * + */ +static int twoway_merge(struct cache_entry **src) +{ + struct cache_entry *current = src[0]; + struct cache_entry *oldtree = src[1], *newtree = src[2]; + + if (merge_size != 2) + return error("Cannot do a twoway merge of %d trees", + merge_size); + + if (current) { + if ((!oldtree && !newtree) || /* 4 and 5 */ + (!oldtree && newtree && + same(current, newtree)) || /* 6 and 7 */ + (oldtree && newtree && + same(oldtree, newtree)) || /* 14 and 15 */ + (oldtree && newtree && + !same(oldtree, newtree) && /* 18 and 19*/ + same(current, newtree))) { + return keep_entry(current); + } + else if (oldtree && !newtree && same(current, oldtree)) { + /* 10 or 11 */ + return deleted_entry(oldtree, current); + } + else if (oldtree && newtree && + same(current, oldtree) && !same(current, newtree)) { + /* 20 or 21 */ + return merged_entry(newtree, current); + } + else { + /* all other failures */ + if (oldtree) + reject_merge(oldtree); + if (current) + reject_merge(current); + if (newtree) + reject_merge(newtree); + return -1; + } + } + else if (newtree) + return merged_entry(newtree, current); + else + return deleted_entry(oldtree, current); +} + +/* + * One-way merge. + * + * The rule is: + * - take the stat information from stage0, take the data from stage1 + */ +static int oneway_merge(struct cache_entry **src) +{ + struct cache_entry *old = src[0]; + struct cache_entry *a = src[1]; + + if (merge_size != 1) + return error("Cannot do a oneway merge of %d trees", + merge_size); + + if (!a) + return deleted_entry(old, old); + if (old && same(old, a)) { + if (reset) { + struct stat st; + if (lstat(old->name, &st) || + ce_match_stat(old, &st, 1)) + old->ce_flags |= htons(CE_UPDATE); + } + return keep_entry(old); + } + return merged_entry(a, old); +} + +static int read_cache_unmerged(void) +{ + int i, deleted; + struct cache_entry **dst; + + read_cache(); + dst = active_cache; + deleted = 0; + for (i = 0; i < active_nr; i++) { + struct cache_entry *ce = active_cache[i]; + if (ce_stage(ce)) { + deleted++; + continue; + } + if (deleted) + *dst = ce; + dst++; + } + active_nr -= deleted; + return deleted; +} + +static const char read_tree_usage[] = "git-read-tree ( | -m [--aggressive] [-u | -i] [ []])"; + +static struct cache_file cache_file; + +int cmd_read_tree(int argc, const char **argv, char **envp) +{ + int i, newfd, stage = 0; + unsigned char sha1[20]; + merge_fn_t fn = NULL; + + setup_git_directory(); + git_config(git_default_config); + + newfd = hold_index_file_for_update(&cache_file, get_index_file()); + if (newfd < 0) + die("unable to create new cachefile"); + + git_config(git_default_config); + + merge = 0; + reset = 0; + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + + /* "-u" means "update", meaning that a merge will update + * the working tree. + */ + if (!strcmp(arg, "-u")) { + update = 1; + 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. + */ + if (!strcmp(arg, "-i")) { + index_only = 1; + continue; + } + + /* This differs from "-m" in that we'll silently ignore unmerged entries */ + if (!strcmp(arg, "--reset")) { + if (stage || merge) + usage(read_tree_usage); + reset = 1; + merge = 1; + stage = 1; + read_cache_unmerged(); + continue; + } + + if (!strcmp(arg, "--trivial")) { + trivial_merges_only = 1; + continue; + } + + if (!strcmp(arg, "--aggressive")) { + aggressive = 1; + continue; + } + + /* "-m" stands for "merge", meaning we start in stage 1 */ + if (!strcmp(arg, "-m")) { + if (stage || merge) + usage(read_tree_usage); + if (read_cache_unmerged()) + die("you need to resolve your current index first"); + stage = 1; + merge = 1; + continue; + } + + /* using -u and -i at the same time makes no sense */ + if (1 < index_only + update) + usage(read_tree_usage); + + if (get_sha1(arg, sha1)) + die("Not a valid object name %s", arg); + if (list_tree(sha1) < 0) + die("failed to unpack tree object %s", arg); + stage++; + } + if ((update||index_only) && !merge) + usage(read_tree_usage); + + if (merge) { + if (stage < 2) + die("just how do you expect me to merge %d trees?", stage-1); + switch (stage - 1) { + case 1: + fn = oneway_merge; + break; + case 2: + fn = twoway_merge; + break; + case 3: + fn = threeway_merge; + break; + default: + fn = threeway_merge; + break; + } + + if (stage - 1 >= 3) + head_idx = stage - 2; + else + head_idx = 1; + } + + unpack_trees(fn); + if (write_cache(newfd, active_cache, active_nr) || + commit_index_file(&cache_file)) + die("unable to write new index file"); + return 0; +} diff --git a/builtin.h b/builtin.h index d210543..88b3523 100644 --- a/builtin.h +++ b/builtin.h @@ -30,5 +30,6 @@ extern int cmd_init_db(int argc, const char **argv, char **envp); extern int cmd_ls_files(int argc, const char **argv, char **envp); extern int cmd_ls_tree(int argc, const char **argv, char **envp); extern int cmd_tar_tree(int argc, const char **argv, char **envp); +extern int cmd_read_tree(int argc, const char **argv, char **envp); #endif diff --git a/git.c b/git.c index c253e60..300e2b2 100644 --- a/git.c +++ b/git.c @@ -55,7 +55,8 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "check-ref-format", cmd_check_ref_format }, { "ls-files", cmd_ls_files }, { "ls-tree", cmd_ls_tree }, - { "tar-tree", cmd_tar_tree } + { "tar-tree", cmd_tar_tree }, + { "read-tree", cmd_read_tree } }; int i; diff --git a/read-tree.c b/read-tree.c deleted file mode 100644 index 82e2a9a..0000000 --- a/read-tree.c +++ /dev/null @@ -1,881 +0,0 @@ -/* - * GIT - The information manager from hell - * - * Copyright (C) Linus Torvalds, 2005 - */ -#define DBRT_DEBUG 1 - -#include "cache.h" - -#include "object.h" -#include "tree.h" -#include -#include - -static int reset = 0; -static int merge = 0; -static int update = 0; -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; - -static struct object_list *trees = NULL; - -static struct cache_entry df_conflict_entry = { -}; - -static struct tree_entry_list df_conflict_list = { - .name = NULL, - .next = &df_conflict_list -}; - -typedef int (*merge_fn_t)(struct cache_entry **src); - -static int entcmp(char *name1, int dir1, char *name2, int dir2) -{ - int len1 = strlen(name1); - int len2 = strlen(name2); - int len = len1 < len2 ? len1 : len2; - int ret = memcmp(name1, name2, len); - unsigned char c1, c2; - if (ret) - return ret; - c1 = name1[len]; - c2 = name2[len]; - if (!c1 && dir1) - c1 = '/'; - if (!c2 && dir2) - c2 = '/'; - ret = (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0; - if (c1 && c2 && !ret) - ret = len1 - len2; - return ret; -} - -static int unpack_trees_rec(struct tree_entry_list **posns, int len, - const char *base, merge_fn_t fn, int *indpos) -{ - int baselen = strlen(base); - int src_size = len + 1; - do { - int i; - char *first; - int firstdir = 0; - int pathlen; - unsigned ce_size; - struct tree_entry_list **subposns; - struct cache_entry **src; - int any_files = 0; - int any_dirs = 0; - char *cache_name; - int ce_stage; - - /* Find the first name in the input. */ - - first = NULL; - cache_name = NULL; - - /* Check the cache */ - if (merge && *indpos < active_nr) { - /* This is a bit tricky: */ - /* If the index has a subdirectory (with - * contents) as the first name, it'll get a - * filename like "foo/bar". But that's after - * "foo", so the entry in trees will get - * handled first, at which point we'll go into - * "foo", and deal with "bar" from the index, - * because the base will be "foo/". The only - * way we can actually have "foo/bar" first of - * all the things is if the trees don't - * contain "foo" at all, in which case we'll - * handle "foo/bar" without going into the - * directory, but that's fine (and will return - * an error anyway, with the added unknown - * file case. - */ - - cache_name = active_cache[*indpos]->name; - if (strlen(cache_name) > baselen && - !memcmp(cache_name, base, baselen)) { - cache_name += baselen; - first = cache_name; - } else { - cache_name = NULL; - } - } - -#if DBRT_DEBUG > 1 - if (first) - printf("index %s\n", first); -#endif - for (i = 0; i < len; i++) { - if (!posns[i] || posns[i] == &df_conflict_list) - continue; -#if DBRT_DEBUG > 1 - printf("%d %s\n", i + 1, posns[i]->name); -#endif - if (!first || entcmp(first, firstdir, - posns[i]->name, - posns[i]->directory) > 0) { - first = posns[i]->name; - firstdir = posns[i]->directory; - } - } - /* No name means we're done */ - if (!first) - return 0; - - pathlen = strlen(first); - ce_size = cache_entry_size(baselen + pathlen); - - src = xcalloc(src_size, sizeof(struct cache_entry *)); - - subposns = xcalloc(len, sizeof(struct tree_list_entry *)); - - if (cache_name && !strcmp(cache_name, first)) { - any_files = 1; - src[0] = active_cache[*indpos]; - remove_cache_entry_at(*indpos); - } - - for (i = 0; i < len; i++) { - struct cache_entry *ce; - - if (!posns[i] || - (posns[i] != &df_conflict_list && - strcmp(first, posns[i]->name))) { - continue; - } - - if (posns[i] == &df_conflict_list) { - src[i + merge] = &df_conflict_entry; - continue; - } - - if (posns[i]->directory) { - any_dirs = 1; - parse_tree(posns[i]->item.tree); - subposns[i] = posns[i]->item.tree->entries; - posns[i] = posns[i]->next; - src[i + merge] = &df_conflict_entry; - continue; - } - - if (!merge) - ce_stage = 0; - else if (i + 1 < head_idx) - ce_stage = 1; - else if (i + 1 > head_idx) - ce_stage = 3; - else - ce_stage = 2; - - ce = xcalloc(1, ce_size); - ce->ce_mode = create_ce_mode(posns[i]->mode); - ce->ce_flags = create_ce_flags(baselen + pathlen, - ce_stage); - memcpy(ce->name, base, baselen); - memcpy(ce->name + baselen, first, pathlen + 1); - - any_files = 1; - - memcpy(ce->sha1, posns[i]->item.any->sha1, 20); - src[i + merge] = ce; - subposns[i] = &df_conflict_list; - posns[i] = posns[i]->next; - } - if (any_files) { - if (merge) { - int ret; - -#if DBRT_DEBUG > 1 - printf("%s:\n", first); - for (i = 0; i < src_size; i++) { - printf(" %d ", i); - if (src[i]) - printf("%s\n", sha1_to_hex(src[i]->sha1)); - else - printf("\n"); - } -#endif - ret = fn(src); - -#if DBRT_DEBUG > 1 - printf("Added %d entries\n", ret); -#endif - *indpos += ret; - } else { - for (i = 0; i < src_size; i++) { - if (src[i]) { - add_cache_entry(src[i], ADD_CACHE_OK_TO_ADD|ADD_CACHE_SKIP_DFCHECK); - } - } - } - } - if (any_dirs) { - char *newbase = xmalloc(baselen + 2 + pathlen); - memcpy(newbase, base, baselen); - memcpy(newbase + baselen, first, pathlen); - newbase[baselen + pathlen] = '/'; - newbase[baselen + pathlen + 1] = '\0'; - if (unpack_trees_rec(subposns, len, newbase, fn, - indpos)) - return -1; - free(newbase); - } - free(subposns); - free(src); - } while (1); -} - -static void reject_merge(struct cache_entry *ce) -{ - die("Entry '%s' would be overwritten by merge. Cannot merge.", - ce->name); -} - -/* Unlink the last component and attempt to remove leading - * directories, in case this unlink is the removal of the - * last entry in the directory -- empty directories are removed. - */ -static void unlink_entry(char *name) -{ - char *cp, *prev; - - if (unlink(name)) - return; - prev = NULL; - while (1) { - int status; - cp = strrchr(name, '/'); - if (prev) - *prev = '/'; - if (!cp) - break; - - *cp = 0; - status = rmdir(name); - if (status) { - *cp = '/'; - break; - } - prev = cp; - } -} - -static void progress_interval(int signum) -{ - progress_update = 1; -} - -static void setup_progress_signal(void) -{ - struct sigaction sa; - struct itimerval v; - - memset(&sa, 0, sizeof(sa)); - sa.sa_handler = progress_interval; - sigemptyset(&sa.sa_mask); - sa.sa_flags = SA_RESTART; - sigaction(SIGALRM, &sa, NULL); - - v.it_interval.tv_sec = 1; - v.it_interval.tv_usec = 0; - v.it_value = v.it_interval; - setitimer(ITIMER_REAL, &v, NULL); -} - -static void check_updates(struct cache_entry **src, int nr) -{ - static struct checkout state = { - .base_dir = "", - .force = 1, - .quiet = 1, - .refresh_cache = 1, - }; - unsigned short mask = htons(CE_UPDATE); - unsigned last_percent = 200, cnt = 0, total = 0; - - if (update && verbose_update) { - 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) { - fprintf(stderr, "Checking files out...\n"); - setup_progress_signal(); - 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); - continue; - } - if (ce->ce_flags & mask) { - ce->ce_flags &= ~mask; - if (update) - checkout_entry(ce, &state, NULL); - } - } - if (total) { - signal(SIGALRM, SIG_IGN); - fputc('\n', stderr); - } -} - -static int unpack_trees(merge_fn_t fn) -{ - int indpos = 0; - unsigned len = object_list_length(trees); - struct tree_entry_list **posns; - int i; - struct object_list *posn = trees; - merge_size = len; - - if (len) { - posns = xmalloc(len * sizeof(struct tree_entry_list *)); - for (i = 0; i < len; i++) { - posns[i] = ((struct tree *) posn->item)->entries; - posn = posn->next; - } - if (unpack_trees_rec(posns, len, "", fn, &indpos)) - return -1; - } - - if (trivial_merges_only && nontrivial_merge) - die("Merge requires file-level merging"); - - check_updates(active_cache, active_nr); - return 0; -} - -static int list_tree(unsigned char *sha1) -{ - struct tree *tree = parse_tree_indirect(sha1); - if (!tree) - return -1; - object_list_append(&tree->object, &trees); - return 0; -} - -static int same(struct cache_entry *a, struct cache_entry *b) -{ - if (!!a != !!b) - return 0; - if (!a && !b) - return 1; - return a->ce_mode == b->ce_mode && - !memcmp(a->sha1, b->sha1, 20); -} - - -/* - * When a CE gets turned into an unmerged entry, we - * want it to be up-to-date - */ -static void verify_uptodate(struct cache_entry *ce) -{ - struct stat st; - - if (index_only || reset) - return; - - if (!lstat(ce->name, &st)) { - unsigned changed = ce_match_stat(ce, &st, 1); - if (!changed) - return; - errno = 0; - } - if (reset) { - ce->ce_flags |= htons(CE_UPDATE); - return; - } - if (errno == ENOENT) - return; - die("Entry '%s' not uptodate. Cannot merge.", ce->name); -} - -/* - * We do not want to remove or overwrite a working tree file that - * is not tracked. - */ -static void verify_absent(const char *path, const char *action) -{ - struct stat st; - - if (index_only || reset || !update) - return; - if (!lstat(path, &st)) - die("Untracked working tree file '%s' " - "would be %s by merge.", path, action); -} - -static int merged_entry(struct cache_entry *merge, struct cache_entry *old) -{ - merge->ce_flags |= htons(CE_UPDATE); - if (old) { - /* - * See if we can re-use the old CE directly? - * That way we get the uptodate stat info. - * - * This also removes the UPDATE flag on - * a match. - */ - if (same(old, merge)) { - *merge = *old; - } else { - verify_uptodate(old); - } - } - else - verify_absent(merge->name, "overwritten"); - - merge->ce_flags &= ~htons(CE_STAGEMASK); - add_cache_entry(merge, ADD_CACHE_OK_TO_ADD); - return 1; -} - -static int deleted_entry(struct cache_entry *ce, struct cache_entry *old) -{ - if (old) - verify_uptodate(old); - else - verify_absent(ce->name, "removed"); - ce->ce_mode = 0; - add_cache_entry(ce, ADD_CACHE_OK_TO_ADD); - return 1; -} - -static int keep_entry(struct cache_entry *ce) -{ - add_cache_entry(ce, ADD_CACHE_OK_TO_ADD); - return 1; -} - -#if DBRT_DEBUG -static void show_stage_entry(FILE *o, - const char *label, const struct cache_entry *ce) -{ - if (!ce) - fprintf(o, "%s (missing)\n", label); - else - fprintf(o, "%s%06o %s %d\t%s\n", - label, - ntohl(ce->ce_mode), - sha1_to_hex(ce->sha1), - ce_stage(ce), - ce->name); -} -#endif - -static int threeway_merge(struct cache_entry **stages) -{ - struct cache_entry *index; - struct cache_entry *head; - struct cache_entry *remote = stages[head_idx + 1]; - int count; - int head_match = 0; - int remote_match = 0; - const char *path = NULL; - - int df_conflict_head = 0; - int df_conflict_remote = 0; - - int any_anc_missing = 0; - int no_anc_exists = 1; - int i; - - for (i = 1; i < head_idx; i++) { - if (!stages[i]) - any_anc_missing = 1; - else { - if (!path) - path = stages[i]->name; - no_anc_exists = 0; - } - } - - index = stages[0]; - head = stages[head_idx]; - - if (head == &df_conflict_entry) { - df_conflict_head = 1; - head = NULL; - } - - if (remote == &df_conflict_entry) { - df_conflict_remote = 1; - remote = NULL; - } - - if (!path && index) - path = index->name; - if (!path && head) - path = head->name; - if (!path && remote) - path = remote->name; - - /* First, if there's a #16 situation, note that to prevent #13 - * and #14. - */ - if (!same(remote, head)) { - for (i = 1; i < head_idx; i++) { - if (same(stages[i], head)) { - head_match = i; - } - if (same(stages[i], remote)) { - remote_match = i; - } - } - } - - /* We start with cases where the index is allowed to match - * something other than the head: #14(ALT) and #2ALT, where it - * is permitted to match the result instead. - */ - /* #14, #14ALT, #2ALT */ - if (remote && !df_conflict_head && head_match && !remote_match) { - if (index && !same(index, remote) && !same(index, head)) - reject_merge(index); - return merged_entry(remote, index); - } - /* - * If we have an entry in the index cache, then we want to - * make sure that it matches head. - */ - if (index && !same(index, head)) { - reject_merge(index); - } - - if (head) { - /* #5ALT, #15 */ - if (same(head, remote)) - return merged_entry(head, index); - /* #13, #3ALT */ - if (!df_conflict_remote && remote_match && !head_match) - return merged_entry(head, index); - } - - /* #1 */ - if (!head && !remote && any_anc_missing) - return 0; - - /* Under the new "aggressive" rule, we resolve mostly trivial - * cases that we historically had git-merge-one-file resolve. - */ - if (aggressive) { - int head_deleted = !head && !df_conflict_head; - int remote_deleted = !remote && !df_conflict_remote; - /* - * Deleted in both. - * Deleted in one and unchanged in the other. - */ - if ((head_deleted && remote_deleted) || - (head_deleted && remote && remote_match) || - (remote_deleted && head && head_match)) { - if (index) - return deleted_entry(index, index); - else if (path) - verify_absent(path, "removed"); - return 0; - } - /* - * Added in both, identically. - */ - if (no_anc_exists && head && remote && same(head, remote)) - return merged_entry(head, index); - - } - - /* Below are "no merge" cases, which require that the index be - * up-to-date to avoid the files getting overwritten with - * conflict resolution files. - */ - if (index) { - verify_uptodate(index); - } - else if (path) - verify_absent(path, "overwritten"); - - nontrivial_merge = 1; - - /* #2, #3, #4, #6, #7, #9, #11. */ - count = 0; - if (!head_match || !remote_match) { - for (i = 1; i < head_idx; i++) { - if (stages[i]) { - keep_entry(stages[i]); - count++; - break; - } - } - } -#if DBRT_DEBUG - else { - fprintf(stderr, "read-tree: warning #16 detected\n"); - show_stage_entry(stderr, "head ", stages[head_match]); - show_stage_entry(stderr, "remote ", stages[remote_match]); - } -#endif - if (head) { count += keep_entry(head); } - if (remote) { count += keep_entry(remote); } - return count; -} - -/* - * Two-way merge. - * - * The rule is to "carry forward" what is in the index without losing - * information across a "fast forward", favoring a successful merge - * over a merge failure when it makes sense. For details of the - * "carry forward" rule, please see . - * - */ -static int twoway_merge(struct cache_entry **src) -{ - struct cache_entry *current = src[0]; - struct cache_entry *oldtree = src[1], *newtree = src[2]; - - if (merge_size != 2) - return error("Cannot do a twoway merge of %d trees", - merge_size); - - if (current) { - if ((!oldtree && !newtree) || /* 4 and 5 */ - (!oldtree && newtree && - same(current, newtree)) || /* 6 and 7 */ - (oldtree && newtree && - same(oldtree, newtree)) || /* 14 and 15 */ - (oldtree && newtree && - !same(oldtree, newtree) && /* 18 and 19*/ - same(current, newtree))) { - return keep_entry(current); - } - else if (oldtree && !newtree && same(current, oldtree)) { - /* 10 or 11 */ - return deleted_entry(oldtree, current); - } - else if (oldtree && newtree && - same(current, oldtree) && !same(current, newtree)) { - /* 20 or 21 */ - return merged_entry(newtree, current); - } - else { - /* all other failures */ - if (oldtree) - reject_merge(oldtree); - if (current) - reject_merge(current); - if (newtree) - reject_merge(newtree); - return -1; - } - } - else if (newtree) - return merged_entry(newtree, current); - else - return deleted_entry(oldtree, current); -} - -/* - * One-way merge. - * - * The rule is: - * - take the stat information from stage0, take the data from stage1 - */ -static int oneway_merge(struct cache_entry **src) -{ - struct cache_entry *old = src[0]; - struct cache_entry *a = src[1]; - - if (merge_size != 1) - return error("Cannot do a oneway merge of %d trees", - merge_size); - - if (!a) - return deleted_entry(old, old); - if (old && same(old, a)) { - if (reset) { - struct stat st; - if (lstat(old->name, &st) || - ce_match_stat(old, &st, 1)) - old->ce_flags |= htons(CE_UPDATE); - } - return keep_entry(old); - } - return merged_entry(a, old); -} - -static int read_cache_unmerged(void) -{ - int i, deleted; - struct cache_entry **dst; - - read_cache(); - dst = active_cache; - deleted = 0; - for (i = 0; i < active_nr; i++) { - struct cache_entry *ce = active_cache[i]; - if (ce_stage(ce)) { - deleted++; - continue; - } - if (deleted) - *dst = ce; - dst++; - } - active_nr -= deleted; - return deleted; -} - -static const char read_tree_usage[] = "git-read-tree ( | -m [--aggressive] [-u | -i] [ []])"; - -static struct cache_file cache_file; - -int main(int argc, char **argv) -{ - int i, newfd, stage = 0; - unsigned char sha1[20]; - merge_fn_t fn = NULL; - - setup_git_directory(); - git_config(git_default_config); - - newfd = hold_index_file_for_update(&cache_file, get_index_file()); - if (newfd < 0) - die("unable to create new cachefile"); - - git_config(git_default_config); - - merge = 0; - reset = 0; - for (i = 1; i < argc; i++) { - const char *arg = argv[i]; - - /* "-u" means "update", meaning that a merge will update - * the working tree. - */ - if (!strcmp(arg, "-u")) { - update = 1; - 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. - */ - if (!strcmp(arg, "-i")) { - index_only = 1; - continue; - } - - /* This differs from "-m" in that we'll silently ignore unmerged entries */ - if (!strcmp(arg, "--reset")) { - if (stage || merge) - usage(read_tree_usage); - reset = 1; - merge = 1; - stage = 1; - read_cache_unmerged(); - continue; - } - - if (!strcmp(arg, "--trivial")) { - trivial_merges_only = 1; - continue; - } - - if (!strcmp(arg, "--aggressive")) { - aggressive = 1; - continue; - } - - /* "-m" stands for "merge", meaning we start in stage 1 */ - if (!strcmp(arg, "-m")) { - if (stage || merge) - usage(read_tree_usage); - if (read_cache_unmerged()) - die("you need to resolve your current index first"); - stage = 1; - merge = 1; - continue; - } - - /* using -u and -i at the same time makes no sense */ - if (1 < index_only + update) - usage(read_tree_usage); - - if (get_sha1(arg, sha1)) - die("Not a valid object name %s", arg); - if (list_tree(sha1) < 0) - die("failed to unpack tree object %s", arg); - stage++; - } - if ((update||index_only) && !merge) - usage(read_tree_usage); - - if (merge) { - if (stage < 2) - die("just how do you expect me to merge %d trees?", stage-1); - switch (stage - 1) { - case 1: - fn = oneway_merge; - break; - case 2: - fn = twoway_merge; - break; - case 3: - fn = threeway_merge; - break; - default: - fn = threeway_merge; - break; - } - - if (stage - 1 >= 3) - head_idx = stage - 2; - else - head_idx = 1; - } - - unpack_trees(fn); - if (write_cache(newfd, active_cache, active_nr) || - commit_index_file(&cache_file)) - die("unable to write new index file"); - return 0; -} -- cgit v0.10.2-6-g49f6 From 6d96ac18e52aca19ff1087ffa64e2d616cc75c6f Mon Sep 17 00:00:00 2001 From: Peter Eriksen Date: Tue, 23 May 2006 14:15:33 +0200 Subject: Builtin git-commit-tree. Signed-off-by: Peter Eriksen Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index 1aebcf5..a1bee61 100644 --- a/Makefile +++ b/Makefile @@ -150,7 +150,7 @@ SIMPLE_PROGRAMS = \ # ... and all the rest that could be moved out of bindir to gitexecdir PROGRAMS = \ git-apply$X git-cat-file$X \ - git-checkout-index$X git-clone-pack$X git-commit-tree$X \ + git-checkout-index$X git-clone-pack$X \ 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$X \ @@ -172,7 +172,7 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-count-objects$X git-diff$X git-push$X \ git-grep$X git-rev-list$X git-check-ref-format$X \ git-init-db$X git-ls-files$X git-ls-tree$X \ - git-tar-tree$X git-read-tree$X + git-tar-tree$X git-read-tree$X git-commit-tree$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -222,7 +222,7 @@ BUILTIN_OBJS = \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ builtin-init-db.o builtin-ls-files.o builtin-ls-tree.o \ - builtin-tar-tree.o builtin-read-tree.o + builtin-tar-tree.o builtin-read-tree.o builtin-commit-tree.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-commit-tree.c b/builtin-commit-tree.c new file mode 100644 index 0000000..ec082bf --- /dev/null +++ b/builtin-commit-tree.c @@ -0,0 +1,140 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + */ +#include "cache.h" +#include "commit.h" +#include "tree.h" +#include "builtin.h" + +#define BLOCKING (1ul << 14) + +/* + * FIXME! Share the code with "write-tree.c" + */ +static void init_buffer(char **bufp, unsigned int *sizep) +{ + char *buf = xmalloc(BLOCKING); + *sizep = 0; + *bufp = buf; +} + +static void add_buffer(char **bufp, unsigned int *sizep, const char *fmt, ...) +{ + char one_line[2048]; + va_list args; + int len; + unsigned long alloc, size, newsize; + char *buf; + + va_start(args, fmt); + len = vsnprintf(one_line, sizeof(one_line), fmt, args); + va_end(args); + size = *sizep; + newsize = size + len; + alloc = (size + 32767) & ~32767; + buf = *bufp; + if (newsize > alloc) { + alloc = (newsize + 32767) & ~32767; + buf = xrealloc(buf, alloc); + *bufp = buf; + } + *sizep = newsize; + memcpy(buf + size, one_line, len); +} + +static void check_valid(unsigned char *sha1, const char *expect) +{ + char type[20]; + + if (sha1_object_info(sha1, type, NULL)) + die("%s is not a valid object", sha1_to_hex(sha1)); + if (expect && strcmp(type, expect)) + die("%s is not a valid '%s' object", sha1_to_hex(sha1), + expect); +} + +/* + * Having more than two parents is not strange at all, and this is + * how multi-way merges are represented. + */ +#define MAXPARENT (16) +static unsigned char parent_sha1[MAXPARENT][20]; + +static const char commit_tree_usage[] = "git-commit-tree [-p ]* < changelog"; + +static int new_parent(int idx) +{ + int i; + unsigned char *sha1 = parent_sha1[idx]; + for (i = 0; i < idx; i++) { + if (!memcmp(parent_sha1[i], sha1, 20)) { + error("duplicate parent %s ignored", sha1_to_hex(sha1)); + return 0; + } + } + return 1; +} + +int cmd_commit_tree(int argc, const char **argv, char **envp) +{ + int i; + int parents = 0; + unsigned char tree_sha1[20]; + unsigned char commit_sha1[20]; + char comment[1000]; + char *buffer; + unsigned int size; + + setup_ident(); + setup_git_directory(); + + git_config(git_default_config); + + if (argc < 2) + usage(commit_tree_usage); + if (get_sha1(argv[1], tree_sha1)) + die("Not a valid object name %s", argv[1]); + + check_valid(tree_sha1, tree_type); + for (i = 2; i < argc; i += 2) { + const char *a, *b; + a = argv[i]; b = argv[i+1]; + if (!b || strcmp(a, "-p")) + usage(commit_tree_usage); + if (get_sha1(b, parent_sha1[parents])) + die("Not a valid object name %s", b); + check_valid(parent_sha1[parents], commit_type); + if (new_parent(parents)) + parents++; + } + if (!parents) + fprintf(stderr, "Committing initial tree %s\n", argv[1]); + + init_buffer(&buffer, &size); + add_buffer(&buffer, &size, "tree %s\n", sha1_to_hex(tree_sha1)); + + /* + * NOTE! This ordering means that the same exact tree merged with a + * different order of parents will be a _different_ changeset even + * if everything else stays the same. + */ + for (i = 0; i < parents; i++) + add_buffer(&buffer, &size, "parent %s\n", sha1_to_hex(parent_sha1[i])); + + /* Person/date information */ + add_buffer(&buffer, &size, "author %s\n", git_author_info(1)); + add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info(1)); + + /* And add the comment */ + while (fgets(comment, sizeof(comment), stdin) != NULL) + add_buffer(&buffer, &size, "%s", comment); + + if (!write_sha1_file(buffer, size, commit_type, commit_sha1)) { + printf("%s\n", sha1_to_hex(commit_sha1)); + return 0; + } + else + return 1; +} diff --git a/builtin.h b/builtin.h index 88b3523..c6b07d9 100644 --- a/builtin.h +++ b/builtin.h @@ -31,5 +31,6 @@ extern int cmd_ls_files(int argc, const char **argv, char **envp); extern int cmd_ls_tree(int argc, const char **argv, char **envp); extern int cmd_tar_tree(int argc, const char **argv, char **envp); extern int cmd_read_tree(int argc, const char **argv, char **envp); +extern int cmd_commit_tree(int argc, const char **argv, char **envp); #endif diff --git a/commit-tree.c b/commit-tree.c deleted file mode 100644 index 0320036..0000000 --- a/commit-tree.c +++ /dev/null @@ -1,139 +0,0 @@ -/* - * GIT - The information manager from hell - * - * Copyright (C) Linus Torvalds, 2005 - */ -#include "cache.h" -#include "commit.h" -#include "tree.h" - -#define BLOCKING (1ul << 14) - -/* - * FIXME! Share the code with "write-tree.c" - */ -static void init_buffer(char **bufp, unsigned int *sizep) -{ - char *buf = xmalloc(BLOCKING); - *sizep = 0; - *bufp = buf; -} - -static void add_buffer(char **bufp, unsigned int *sizep, const char *fmt, ...) -{ - char one_line[2048]; - va_list args; - int len; - unsigned long alloc, size, newsize; - char *buf; - - va_start(args, fmt); - len = vsnprintf(one_line, sizeof(one_line), fmt, args); - va_end(args); - size = *sizep; - newsize = size + len; - alloc = (size + 32767) & ~32767; - buf = *bufp; - if (newsize > alloc) { - alloc = (newsize + 32767) & ~32767; - buf = xrealloc(buf, alloc); - *bufp = buf; - } - *sizep = newsize; - memcpy(buf + size, one_line, len); -} - -static void check_valid(unsigned char *sha1, const char *expect) -{ - char type[20]; - - if (sha1_object_info(sha1, type, NULL)) - die("%s is not a valid object", sha1_to_hex(sha1)); - if (expect && strcmp(type, expect)) - die("%s is not a valid '%s' object", sha1_to_hex(sha1), - expect); -} - -/* - * Having more than two parents is not strange at all, and this is - * how multi-way merges are represented. - */ -#define MAXPARENT (16) -static unsigned char parent_sha1[MAXPARENT][20]; - -static const char commit_tree_usage[] = "git-commit-tree [-p ]* < changelog"; - -static int new_parent(int idx) -{ - int i; - unsigned char *sha1 = parent_sha1[idx]; - for (i = 0; i < idx; i++) { - if (!memcmp(parent_sha1[i], sha1, 20)) { - error("duplicate parent %s ignored", sha1_to_hex(sha1)); - return 0; - } - } - return 1; -} - -int main(int argc, char **argv) -{ - int i; - int parents = 0; - unsigned char tree_sha1[20]; - unsigned char commit_sha1[20]; - char comment[1000]; - char *buffer; - unsigned int size; - - setup_ident(); - setup_git_directory(); - - git_config(git_default_config); - - if (argc < 2) - usage(commit_tree_usage); - if (get_sha1(argv[1], tree_sha1)) - die("Not a valid object name %s", argv[1]); - - check_valid(tree_sha1, tree_type); - for (i = 2; i < argc; i += 2) { - char *a, *b; - a = argv[i]; b = argv[i+1]; - if (!b || strcmp(a, "-p")) - usage(commit_tree_usage); - if (get_sha1(b, parent_sha1[parents])) - die("Not a valid object name %s", b); - check_valid(parent_sha1[parents], commit_type); - if (new_parent(parents)) - parents++; - } - if (!parents) - fprintf(stderr, "Committing initial tree %s\n", argv[1]); - - init_buffer(&buffer, &size); - add_buffer(&buffer, &size, "tree %s\n", sha1_to_hex(tree_sha1)); - - /* - * NOTE! This ordering means that the same exact tree merged with a - * different order of parents will be a _different_ changeset even - * if everything else stays the same. - */ - for (i = 0; i < parents; i++) - add_buffer(&buffer, &size, "parent %s\n", sha1_to_hex(parent_sha1[i])); - - /* Person/date information */ - add_buffer(&buffer, &size, "author %s\n", git_author_info(1)); - add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info(1)); - - /* And add the comment */ - while (fgets(comment, sizeof(comment), stdin) != NULL) - add_buffer(&buffer, &size, "%s", comment); - - if (!write_sha1_file(buffer, size, commit_type, commit_sha1)) { - printf("%s\n", sha1_to_hex(commit_sha1)); - return 0; - } - else - return 1; -} diff --git a/git.c b/git.c index 300e2b2..4c2c062 100644 --- a/git.c +++ b/git.c @@ -56,7 +56,8 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "ls-files", cmd_ls_files }, { "ls-tree", cmd_ls_tree }, { "tar-tree", cmd_tar_tree }, - { "read-tree", cmd_read_tree } + { "read-tree", cmd_read_tree }, + { "commit-tree", cmd_commit_tree } }; int i; -- cgit v0.10.2-6-g49f6 From ac6245e31a359200b65bfdd910bba9a0fbe90c11 Mon Sep 17 00:00:00 2001 From: Peter Eriksen Date: Tue, 23 May 2006 14:15:34 +0200 Subject: Builtin git-apply. Signed-off-by: Peter Eriksen Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index a1bee61..3da5768 100644 --- a/Makefile +++ b/Makefile @@ -149,7 +149,7 @@ SIMPLE_PROGRAMS = \ # ... and all the rest that could be moved out of bindir to gitexecdir PROGRAMS = \ - git-apply$X git-cat-file$X \ + git-cat-file$X \ git-checkout-index$X git-clone-pack$X \ git-convert-objects$X git-diff-files$X \ git-diff-index$X git-diff-stages$X \ @@ -172,7 +172,8 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-count-objects$X git-diff$X git-push$X \ git-grep$X git-rev-list$X git-check-ref-format$X \ git-init-db$X git-ls-files$X git-ls-tree$X \ - git-tar-tree$X git-read-tree$X git-commit-tree$X + git-tar-tree$X git-read-tree$X git-commit-tree$X \ + git-apply$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -222,7 +223,8 @@ BUILTIN_OBJS = \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ builtin-init-db.o builtin-ls-files.o builtin-ls-tree.o \ - builtin-tar-tree.o builtin-read-tree.o builtin-commit-tree.o + builtin-tar-tree.o builtin-read-tree.o builtin-commit-tree.o \ + builtin-apply.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/apply.c b/apply.c deleted file mode 100644 index 0ed9d13..0000000 --- a/apply.c +++ /dev/null @@ -1,2299 +0,0 @@ -/* - * apply.c - * - * Copyright (C) Linus Torvalds, 2005 - * - * This applies patches on top of some (arbitrary) version of the SCM. - * - */ -#include -#include "cache.h" -#include "quote.h" -#include "blob.h" -#include "delta.h" - -// --check turns on checking that the working tree matches the -// files that are being modified, but doesn't apply the patch -// --stat does just a diffstat, and doesn't actually apply -// --numstat does numeric diffstat, and doesn't actually apply -// --index-info shows the old and new index info for paths if available. -// --index updates the cache as well. -// --cached updates only the cache without ever touching the working tree. -// -static const char *prefix; -static int prefix_length = -1; -static int newfd = -1; - -static int p_value = 1; -static int allow_binary_replacement = 0; -static int check_index = 0; -static int write_index = 0; -static int cached = 0; -static int diffstat = 0; -static int numstat = 0; -static int summary = 0; -static int check = 0; -static int apply = 1; -static int no_add = 0; -static int show_index_info = 0; -static int line_termination = '\n'; -static unsigned long p_context = -1; -static const char apply_usage[] = -"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--cached] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] [-CNUM] [--whitespace=] ..."; - -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 - * scaling. - */ -static int max_change, max_len; - -/* - * Various "current state", notably line numbers and what - * file (and how) we're patching right now.. The "is_xxxx" - * things are flags, where -1 means "don't know yet". - */ -static int linenr = 1; - -struct fragment { - unsigned long leading, trailing; - unsigned long oldpos, oldlines; - unsigned long newpos, newlines; - const char *patch; - int size; - struct fragment *next; -}; - -struct patch { - char *new_name, *old_name, *def_name; - unsigned int old_mode, new_mode; - int is_rename, is_copy, is_new, is_delete, is_binary; -#define BINARY_DELTA_DEFLATED 1 -#define BINARY_LITERAL_DEFLATED 2 - unsigned long deflate_origlen; - int lines_added, lines_deleted; - int score; - struct fragment *fragments; - char *result; - unsigned long resultsize; - char old_sha1_prefix[41]; - char new_sha1_prefix[41]; - struct patch *next; -}; - -#define CHUNKSIZE (8192) -#define SLOP (16) - -static void *read_patch_file(int fd, unsigned long *sizep) -{ - unsigned long size = 0, alloc = CHUNKSIZE; - void *buffer = xmalloc(alloc); - - for (;;) { - int nr = alloc - size; - if (nr < 1024) { - alloc += CHUNKSIZE; - buffer = xrealloc(buffer, alloc); - nr = alloc - size; - } - nr = xread(fd, buffer + size, nr); - if (!nr) - break; - if (nr < 0) - die("git-apply: read returned %s", strerror(errno)); - size += nr; - } - *sizep = size; - - /* - * Make sure that we have some slop in the buffer - * so that we can do speculative "memcmp" etc, and - * see to it that it is NUL-filled. - */ - if (alloc < size + SLOP) - buffer = xrealloc(buffer, size + SLOP); - memset(buffer + size, 0, SLOP); - return buffer; -} - -static unsigned long linelen(const char *buffer, unsigned long size) -{ - unsigned long len = 0; - while (size--) { - len++; - if (*buffer++ == '\n') - break; - } - return len; -} - -static int is_dev_null(const char *str) -{ - return !memcmp("/dev/null", str, 9) && isspace(str[9]); -} - -#define TERM_SPACE 1 -#define TERM_TAB 2 - -static int name_terminate(const char *name, int namelen, int c, int terminate) -{ - if (c == ' ' && !(terminate & TERM_SPACE)) - return 0; - if (c == '\t' && !(terminate & TERM_TAB)) - return 0; - - return 1; -} - -static char * find_name(const char *line, char *def, int p_value, int terminate) -{ - int len; - const char *start = line; - char *name; - - if (*line == '"') { - /* Proposed "new-style" GNU patch/diff format; see - * http://marc.theaimsgroup.com/?l=git&m=112927316408690&w=2 - */ - name = unquote_c_style(line, NULL); - if (name) { - char *cp = name; - while (p_value) { - cp = strchr(name, '/'); - if (!cp) - break; - cp++; - p_value--; - } - if (cp) { - /* name can later be freed, so we need - * to memmove, not just return cp - */ - memmove(name, cp, strlen(cp) + 1); - free(def); - return name; - } - else { - free(name); - name = NULL; - } - } - } - - for (;;) { - char c = *line; - - if (isspace(c)) { - if (c == '\n') - break; - if (name_terminate(start, line-start, c, terminate)) - break; - } - line++; - if (c == '/' && !--p_value) - start = line; - } - if (!start) - return def; - len = line - start; - if (!len) - return def; - - /* - * Generally we prefer the shorter name, especially - * if the other one is just a variation of that with - * something else tacked on to the end (ie "file.orig" - * or "file~"). - */ - if (def) { - int deflen = strlen(def); - if (deflen < len && !strncmp(start, def, deflen)) - return def; - } - - name = xmalloc(len + 1); - memcpy(name, start, len); - name[len] = 0; - free(def); - return name; -} - -/* - * Get the name etc info from the --/+++ lines of a traditional patch header - * - * NOTE! This hardcodes "-p1" behaviour in filename detection. - * - * FIXME! The end-of-filename heuristics are kind of screwy. For existing - * files, we can happily check the index for a match, but for creating a - * new file we should try to match whatever "patch" does. I have no idea. - */ -static void parse_traditional_patch(const char *first, const char *second, struct patch *patch) -{ - char *name; - - first += 4; // skip "--- " - second += 4; // skip "+++ " - if (is_dev_null(first)) { - patch->is_new = 1; - patch->is_delete = 0; - name = find_name(second, NULL, p_value, TERM_SPACE | TERM_TAB); - patch->new_name = name; - } else if (is_dev_null(second)) { - patch->is_new = 0; - patch->is_delete = 1; - name = find_name(first, NULL, p_value, TERM_SPACE | TERM_TAB); - patch->old_name = name; - } else { - name = find_name(first, NULL, p_value, TERM_SPACE | TERM_TAB); - name = find_name(second, name, p_value, TERM_SPACE | TERM_TAB); - patch->old_name = patch->new_name = name; - } - if (!name) - die("unable to find filename in patch at line %d", linenr); -} - -static int gitdiff_hdrend(const char *line, struct patch *patch) -{ - return -1; -} - -/* - * We're anal about diff header consistency, to make - * sure that we don't end up having strange ambiguous - * patches floating around. - * - * As a result, gitdiff_{old|new}name() will check - * their names against any previous information, just - * to make sure.. - */ -static char *gitdiff_verify_name(const char *line, int isnull, char *orig_name, const char *oldnew) -{ - if (!orig_name && !isnull) - return find_name(line, NULL, 1, 0); - - if (orig_name) { - int len; - const char *name; - char *another; - name = orig_name; - len = strlen(name); - if (isnull) - die("git-apply: bad git-diff - expected /dev/null, got %s on line %d", name, linenr); - another = find_name(line, NULL, 1, 0); - if (!another || memcmp(another, name, len)) - die("git-apply: bad git-diff - inconsistent %s filename on line %d", oldnew, linenr); - free(another); - return orig_name; - } - else { - /* expect "/dev/null" */ - if (memcmp("/dev/null", line, 9) || line[9] != '\n') - die("git-apply: bad git-diff - expected /dev/null on line %d", linenr); - return NULL; - } -} - -static int gitdiff_oldname(const char *line, struct patch *patch) -{ - patch->old_name = gitdiff_verify_name(line, patch->is_new, patch->old_name, "old"); - return 0; -} - -static int gitdiff_newname(const char *line, struct patch *patch) -{ - patch->new_name = gitdiff_verify_name(line, patch->is_delete, patch->new_name, "new"); - return 0; -} - -static int gitdiff_oldmode(const char *line, struct patch *patch) -{ - patch->old_mode = strtoul(line, NULL, 8); - return 0; -} - -static int gitdiff_newmode(const char *line, struct patch *patch) -{ - patch->new_mode = strtoul(line, NULL, 8); - return 0; -} - -static int gitdiff_delete(const char *line, struct patch *patch) -{ - patch->is_delete = 1; - patch->old_name = patch->def_name; - return gitdiff_oldmode(line, patch); -} - -static int gitdiff_newfile(const char *line, struct patch *patch) -{ - patch->is_new = 1; - patch->new_name = patch->def_name; - return gitdiff_newmode(line, patch); -} - -static int gitdiff_copysrc(const char *line, struct patch *patch) -{ - patch->is_copy = 1; - patch->old_name = find_name(line, NULL, 0, 0); - return 0; -} - -static int gitdiff_copydst(const char *line, struct patch *patch) -{ - patch->is_copy = 1; - patch->new_name = find_name(line, NULL, 0, 0); - return 0; -} - -static int gitdiff_renamesrc(const char *line, struct patch *patch) -{ - patch->is_rename = 1; - patch->old_name = find_name(line, NULL, 0, 0); - return 0; -} - -static int gitdiff_renamedst(const char *line, struct patch *patch) -{ - patch->is_rename = 1; - patch->new_name = find_name(line, NULL, 0, 0); - return 0; -} - -static int gitdiff_similarity(const char *line, struct patch *patch) -{ - if ((patch->score = strtoul(line, NULL, 10)) == ULONG_MAX) - patch->score = 0; - return 0; -} - -static int gitdiff_dissimilarity(const char *line, struct patch *patch) -{ - if ((patch->score = strtoul(line, NULL, 10)) == ULONG_MAX) - patch->score = 0; - return 0; -} - -static int gitdiff_index(const char *line, struct patch *patch) -{ - /* index line is N hexadecimal, "..", N hexadecimal, - * and optional space with octal mode. - */ - const char *ptr, *eol; - int len; - - ptr = strchr(line, '.'); - if (!ptr || ptr[1] != '.' || 40 < ptr - line) - return 0; - len = ptr - line; - memcpy(patch->old_sha1_prefix, line, len); - patch->old_sha1_prefix[len] = 0; - - line = ptr + 2; - ptr = strchr(line, ' '); - eol = strchr(line, '\n'); - - if (!ptr || eol < ptr) - ptr = eol; - len = ptr - line; - - if (40 < len) - return 0; - memcpy(patch->new_sha1_prefix, line, len); - patch->new_sha1_prefix[len] = 0; - if (*ptr == ' ') - patch->new_mode = patch->old_mode = strtoul(ptr+1, NULL, 8); - return 0; -} - -/* - * This is normal for a diff that doesn't change anything: we'll fall through - * into the next diff. Tell the parser to break out. - */ -static int gitdiff_unrecognized(const char *line, struct patch *patch) -{ - return -1; -} - -static const char *stop_at_slash(const char *line, int llen) -{ - int i; - - for (i = 0; i < llen; i++) { - int ch = line[i]; - if (ch == '/') - return line + i; - } - return NULL; -} - -/* This is to extract the same name that appears on "diff --git" - * line. We do not find and return anything if it is a rename - * patch, and it is OK because we will find the name elsewhere. - * We need to reliably find name only when it is mode-change only, - * creation or deletion of an empty file. In any of these cases, - * both sides are the same name under a/ and b/ respectively. - */ -static char *git_header_name(char *line, int llen) -{ - int len; - const char *name; - const char *second = NULL; - - line += strlen("diff --git "); - llen -= strlen("diff --git "); - - if (*line == '"') { - const char *cp; - char *first = unquote_c_style(line, &second); - if (!first) - return NULL; - - /* advance to the first slash */ - cp = stop_at_slash(first, strlen(first)); - if (!cp || cp == first) { - /* we do not accept absolute paths */ - free_first_and_fail: - free(first); - return NULL; - } - len = strlen(cp+1); - memmove(first, cp+1, len+1); /* including NUL */ - - /* second points at one past closing dq of name. - * find the second name. - */ - while ((second < line + llen) && isspace(*second)) - second++; - - if (line + llen <= second) - goto free_first_and_fail; - if (*second == '"') { - char *sp = unquote_c_style(second, NULL); - if (!sp) - goto free_first_and_fail; - cp = stop_at_slash(sp, strlen(sp)); - if (!cp || cp == sp) { - free_both_and_fail: - free(sp); - goto free_first_and_fail; - } - /* They must match, otherwise ignore */ - if (strcmp(cp+1, first)) - goto free_both_and_fail; - free(sp); - return first; - } - - /* unquoted second */ - cp = stop_at_slash(second, line + llen - second); - if (!cp || cp == second) - goto free_first_and_fail; - cp++; - if (line + llen - cp != len + 1 || - memcmp(first, cp, len)) - goto free_first_and_fail; - return first; - } - - /* unquoted first name */ - name = stop_at_slash(line, llen); - if (!name || name == line) - return NULL; - - name++; - - /* since the first name is unquoted, a dq if exists must be - * the beginning of the second name. - */ - for (second = name; second < line + llen; second++) { - if (*second == '"') { - const char *cp = second; - const char *np; - char *sp = unquote_c_style(second, NULL); - - if (!sp) - return NULL; - np = stop_at_slash(sp, strlen(sp)); - if (!np || np == sp) { - free_second_and_fail: - free(sp); - return NULL; - } - np++; - len = strlen(np); - if (len < cp - name && - !strncmp(np, name, len) && - isspace(name[len])) { - /* Good */ - memmove(sp, np, len + 1); - return sp; - } - goto free_second_and_fail; - } - } - - /* - * Accept a name only if it shows up twice, exactly the same - * form. - */ - for (len = 0 ; ; len++) { - char c = name[len]; - - switch (c) { - default: - continue; - case '\n': - return NULL; - case '\t': case ' ': - second = name+len; - for (;;) { - char c = *second++; - if (c == '\n') - return NULL; - if (c == '/') - break; - } - if (second[len] == '\n' && !memcmp(name, second, len)) { - char *ret = xmalloc(len + 1); - memcpy(ret, name, len); - ret[len] = 0; - return ret; - } - } - } - return NULL; -} - -/* Verify that we recognize the lines following a git header */ -static int parse_git_header(char *line, int len, unsigned int size, struct patch *patch) -{ - unsigned long offset; - - /* A git diff has explicit new/delete information, so we don't guess */ - patch->is_new = 0; - patch->is_delete = 0; - - /* - * Some things may not have the old name in the - * rest of the headers anywhere (pure mode changes, - * or removing or adding empty files), so we get - * the default name from the header. - */ - patch->def_name = git_header_name(line, len); - - line += len; - size -= len; - linenr++; - for (offset = len ; size > 0 ; offset += len, size -= len, line += len, linenr++) { - static const struct opentry { - const char *str; - int (*fn)(const char *, struct patch *); - } optable[] = { - { "@@ -", gitdiff_hdrend }, - { "--- ", gitdiff_oldname }, - { "+++ ", gitdiff_newname }, - { "old mode ", gitdiff_oldmode }, - { "new mode ", gitdiff_newmode }, - { "deleted file mode ", gitdiff_delete }, - { "new file mode ", gitdiff_newfile }, - { "copy from ", gitdiff_copysrc }, - { "copy to ", gitdiff_copydst }, - { "rename old ", gitdiff_renamesrc }, - { "rename new ", gitdiff_renamedst }, - { "rename from ", gitdiff_renamesrc }, - { "rename to ", gitdiff_renamedst }, - { "similarity index ", gitdiff_similarity }, - { "dissimilarity index ", gitdiff_dissimilarity }, - { "index ", gitdiff_index }, - { "", gitdiff_unrecognized }, - }; - int i; - - len = linelen(line, size); - if (!len || line[len-1] != '\n') - break; - for (i = 0; i < ARRAY_SIZE(optable); i++) { - const struct opentry *p = optable + i; - int oplen = strlen(p->str); - if (len < oplen || memcmp(p->str, line, oplen)) - continue; - if (p->fn(line + oplen, patch) < 0) - return offset; - break; - } - } - - return offset; -} - -static int parse_num(const char *line, unsigned long *p) -{ - char *ptr; - - if (!isdigit(*line)) - return 0; - *p = strtoul(line, &ptr, 10); - return ptr - line; -} - -static int parse_range(const char *line, int len, int offset, const char *expect, - unsigned long *p1, unsigned long *p2) -{ - int digits, ex; - - if (offset < 0 || offset >= len) - return -1; - line += offset; - len -= offset; - - digits = parse_num(line, p1); - if (!digits) - return -1; - - offset += digits; - line += digits; - len -= digits; - - *p2 = 1; - if (*line == ',') { - digits = parse_num(line+1, p2); - if (!digits) - return -1; - - offset += digits+1; - line += digits+1; - len -= digits+1; - } - - ex = strlen(expect); - if (ex > len) - return -1; - if (memcmp(line, expect, ex)) - return -1; - - return offset + ex; -} - -/* - * Parse a unified diff fragment header of the - * form "@@ -a,b +c,d @@" - */ -static int parse_fragment_header(char *line, int len, struct fragment *fragment) -{ - int offset; - - if (!len || line[len-1] != '\n') - return -1; - - /* Figure out the number of lines in a fragment */ - offset = parse_range(line, len, 4, " +", &fragment->oldpos, &fragment->oldlines); - offset = parse_range(line, len, offset, " @@", &fragment->newpos, &fragment->newlines); - - return offset; -} - -static int find_header(char *line, unsigned long size, int *hdrsize, struct patch *patch) -{ - unsigned long offset, len; - - patch->is_rename = patch->is_copy = 0; - patch->is_new = patch->is_delete = -1; - patch->old_mode = patch->new_mode = 0; - patch->old_name = patch->new_name = NULL; - for (offset = 0; size > 0; offset += len, size -= len, line += len, linenr++) { - unsigned long nextlen; - - len = linelen(line, size); - if (!len) - break; - - /* Testing this early allows us to take a few shortcuts.. */ - if (len < 6) - continue; - - /* - * Make sure we don't find any unconnected patch fragmants. - * That's a sign that we didn't find a header, and that a - * patch has become corrupted/broken up. - */ - if (!memcmp("@@ -", line, 4)) { - struct fragment dummy; - if (parse_fragment_header(line, len, &dummy) < 0) - continue; - error("patch fragment without header at line %d: %.*s", linenr, (int)len-1, line); - } - - if (size < len + 6) - break; - - /* - * Git patch? It might not have a real patch, just a rename - * or mode change, so we handle that specially - */ - if (!memcmp("diff --git ", line, 11)) { - int git_hdr_len = parse_git_header(line, len, size, patch); - if (git_hdr_len <= len) - continue; - if (!patch->old_name && !patch->new_name) { - if (!patch->def_name) - die("git diff header lacks filename information (line %d)", linenr); - patch->old_name = patch->new_name = patch->def_name; - } - *hdrsize = git_hdr_len; - return offset; - } - - /** --- followed by +++ ? */ - if (memcmp("--- ", line, 4) || memcmp("+++ ", line + len, 4)) - continue; - - /* - * We only accept unified patches, so we want it to - * at least have "@@ -a,b +c,d @@\n", which is 14 chars - * minimum - */ - nextlen = linelen(line + len, size - len); - if (size < nextlen + 14 || memcmp("@@ -", line + len + nextlen, 4)) - continue; - - /* Ok, we'll consider it a patch */ - parse_traditional_patch(line, line+len, patch); - *hdrsize = len + nextlen; - linenr += 2; - return offset; - } - return -1; -} - -/* - * Parse a unified diff. Note that this really needs - * to parse each fragment separately, since the only - * way to know the difference between a "---" that is - * part of a patch, and a "---" that starts the next - * patch is to look at the line counts.. - */ -static int parse_fragment(char *line, unsigned long size, struct patch *patch, struct fragment *fragment) -{ - int added, deleted; - int len = linelen(line, size), offset; - unsigned long oldlines, newlines; - unsigned long leading, trailing; - - offset = parse_fragment_header(line, len, fragment); - if (offset < 0) - return -1; - oldlines = fragment->oldlines; - newlines = fragment->newlines; - leading = 0; - trailing = 0; - - if (patch->is_new < 0) { - patch->is_new = !oldlines; - if (!oldlines) - patch->old_name = NULL; - } - if (patch->is_delete < 0) { - patch->is_delete = !newlines; - if (!newlines) - patch->new_name = NULL; - } - - if (patch->is_new && oldlines) - return error("new file depends on old contents"); - if (patch->is_delete != !newlines) { - if (newlines) - return error("deleted file still has contents"); - fprintf(stderr, "** warning: file %s becomes empty but is not deleted\n", patch->new_name); - } - - /* Parse the thing.. */ - line += len; - size -= len; - linenr++; - added = deleted = 0; - for (offset = len; size > 0; offset += len, size -= len, line += len, linenr++) { - if (!oldlines && !newlines) - break; - len = linelen(line, size); - if (!len || line[len-1] != '\n') - return -1; - switch (*line) { - default: - return -1; - case ' ': - oldlines--; - newlines--; - if (!deleted && !added) - leading++; - trailing++; - break; - case '-': - deleted++; - oldlines--; - trailing = 0; - 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--; - trailing = 0; - break; - - /* We allow "\ No newline at end of file". Depending - * on locale settings when the patch was produced we - * don't know what this line looks like. The only - * thing we do know is that it begins with "\ ". - * Checking for 12 is just for sanity check -- any - * l10n of "\ No newline..." is at least that long. - */ - case '\\': - if (len < 12 || memcmp(line, "\\ ", 2)) - return -1; - break; - } - } - if (oldlines || newlines) - return -1; - fragment->leading = leading; - fragment->trailing = trailing; - - /* If a fragment ends with an incomplete line, we failed to include - * it in the above loop because we hit oldlines == newlines == 0 - * before seeing it. - */ - if (12 < size && !memcmp(line, "\\ ", 2)) - offset += linelen(line, size); - - patch->lines_added += added; - patch->lines_deleted += deleted; - return offset; -} - -static int parse_single_patch(char *line, unsigned long size, struct patch *patch) -{ - unsigned long offset = 0; - struct fragment **fragp = &patch->fragments; - - while (size > 4 && !memcmp(line, "@@ -", 4)) { - struct fragment *fragment; - int len; - - fragment = xcalloc(1, sizeof(*fragment)); - len = parse_fragment(line, size, patch, fragment); - if (len <= 0) - die("corrupt patch at line %d", linenr); - - fragment->patch = line; - fragment->size = len; - - *fragp = fragment; - fragp = &fragment->next; - - offset += len; - line += len; - size -= len; - } - return offset; -} - -static inline int metadata_changes(struct patch *patch) -{ - return patch->is_rename > 0 || - patch->is_copy > 0 || - patch->is_new > 0 || - patch->is_delete || - (patch->old_mode && patch->new_mode && - patch->old_mode != patch->new_mode); -} - -static int parse_binary(char *buffer, unsigned long size, struct patch *patch) -{ - /* We have read "GIT binary patch\n"; what follows is a line - * that says the patch method (currently, either "deflated - * literal" or "deflated delta") and the length of data before - * deflating; a sequence of 'length-byte' followed by base-85 - * encoded data follows. - * - * Each 5-byte sequence of base-85 encodes up to 4 bytes, - * and we would limit the patch line to 66 characters, - * so one line can fit up to 13 groups that would decode - * to 52 bytes max. The length byte 'A'-'Z' corresponds - * to 1-26 bytes, and 'a'-'z' corresponds to 27-52 bytes. - * The end of binary is signalled with an empty line. - */ - int llen, used; - struct fragment *fragment; - char *data = NULL; - - patch->fragments = fragment = xcalloc(1, sizeof(*fragment)); - - /* Grab the type of patch */ - llen = linelen(buffer, size); - used = llen; - linenr++; - - if (!strncmp(buffer, "delta ", 6)) { - patch->is_binary = BINARY_DELTA_DEFLATED; - patch->deflate_origlen = strtoul(buffer + 6, NULL, 10); - } - else if (!strncmp(buffer, "literal ", 8)) { - patch->is_binary = BINARY_LITERAL_DEFLATED; - patch->deflate_origlen = strtoul(buffer + 8, NULL, 10); - } - else - return error("unrecognized binary patch at line %d: %.*s", - linenr-1, llen-1, buffer); - buffer += llen; - while (1) { - int byte_length, max_byte_length, newsize; - llen = linelen(buffer, size); - used += llen; - linenr++; - if (llen == 1) - break; - /* Minimum line is "A00000\n" which is 7-byte long, - * and the line length must be multiple of 5 plus 2. - */ - if ((llen < 7) || (llen-2) % 5) - goto corrupt; - max_byte_length = (llen - 2) / 5 * 4; - byte_length = *buffer; - if ('A' <= byte_length && byte_length <= 'Z') - byte_length = byte_length - 'A' + 1; - else if ('a' <= byte_length && byte_length <= 'z') - byte_length = byte_length - 'a' + 27; - else - goto corrupt; - /* if the input length was not multiple of 4, we would - * have filler at the end but the filler should never - * exceed 3 bytes - */ - if (max_byte_length < byte_length || - byte_length <= max_byte_length - 4) - goto corrupt; - newsize = fragment->size + byte_length; - data = xrealloc(data, newsize); - if (decode_85(data + fragment->size, - buffer + 1, - byte_length)) - goto corrupt; - fragment->size = newsize; - buffer += llen; - size -= llen; - } - fragment->patch = data; - return used; - corrupt: - return error("corrupt binary patch at line %d: %.*s", - linenr-1, llen-1, buffer); -} - -static int parse_chunk(char *buffer, unsigned long size, struct patch *patch) -{ - int hdrsize, patchsize; - int offset = find_header(buffer, size, &hdrsize, patch); - - if (offset < 0) - return offset; - - patchsize = parse_single_patch(buffer + offset + hdrsize, size - offset - hdrsize, patch); - - if (!patchsize) { - static const char *binhdr[] = { - "Binary files ", - "Files ", - NULL, - }; - static const char git_binary[] = "GIT binary patch\n"; - int i; - int hd = hdrsize + offset; - unsigned long llen = linelen(buffer + hd, size - hd); - - if (llen == sizeof(git_binary) - 1 && - !memcmp(git_binary, buffer + hd, llen)) { - int used; - linenr++; - used = parse_binary(buffer + hd + llen, - size - hd - llen, patch); - if (used) - patchsize = used + llen; - else - patchsize = 0; - } - else if (!memcmp(" differ\n", buffer + hd + llen - 8, 8)) { - for (i = 0; binhdr[i]; i++) { - int len = strlen(binhdr[i]); - if (len < size - hd && - !memcmp(binhdr[i], buffer + hd, len)) { - linenr++; - patch->is_binary = 1; - patchsize = llen; - break; - } - } - } - - /* Empty patch cannot be applied if: - * - it is a binary patch and we do not do binary_replace, or - * - text patch without metadata change - */ - if ((apply || check) && - (patch->is_binary - ? !allow_binary_replacement - : !metadata_changes(patch))) - die("patch with only garbage at line %d", linenr); - } - - return offset + hdrsize + patchsize; -} - -static const char pluses[] = "++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"; -static const char minuses[]= "----------------------------------------------------------------------"; - -static void show_stats(struct patch *patch) -{ - const char *prefix = ""; - char *name = patch->new_name; - char *qname = NULL; - int len, max, add, del, total; - - if (!name) - name = patch->old_name; - - if (0 < (len = quote_c_style(name, NULL, NULL, 0))) { - qname = xmalloc(len + 1); - quote_c_style(name, qname, NULL, 0); - name = qname; - } - - /* - * "scale" the filename - */ - len = strlen(name); - max = max_len; - if (max > 50) - max = 50; - if (len > max) { - char *slash; - prefix = "..."; - max -= 3; - name += len - max; - slash = strchr(name, '/'); - if (slash) - name = slash; - } - len = max; - - /* - * scale the add/delete - */ - max = max_change; - if (max + len > 70) - max = 70 - len; - - add = patch->lines_added; - del = patch->lines_deleted; - total = add + del; - - if (max_change > 0) { - total = (total * max + max_change / 2) / max_change; - add = (add * max + max_change / 2) / max_change; - del = total - add; - } - if (patch->is_binary) - printf(" %s%-*s | Bin\n", prefix, len, name); - else - printf(" %s%-*s |%5d %.*s%.*s\n", prefix, - len, name, patch->lines_added + patch->lines_deleted, - add, pluses, del, minuses); - if (qname) - free(qname); -} - -static int read_old_data(struct stat *st, const char *path, void *buf, unsigned long size) -{ - int fd; - unsigned long got; - - switch (st->st_mode & S_IFMT) { - case S_IFLNK: - return readlink(path, buf, size); - case S_IFREG: - fd = open(path, O_RDONLY); - if (fd < 0) - return error("unable to open %s", path); - got = 0; - for (;;) { - int ret = xread(fd, buf + got, size - got); - if (ret <= 0) - break; - got += ret; - } - close(fd); - return got; - - default: - return -1; - } -} - -static int find_offset(const char *buf, unsigned long size, const char *fragment, unsigned long fragsize, int line, int *lines) -{ - int i; - unsigned long start, backwards, forwards; - - if (fragsize > size) - return -1; - - start = 0; - if (line > 1) { - unsigned long offset = 0; - i = line-1; - while (offset + fragsize <= size) { - if (buf[offset++] == '\n') { - start = offset; - if (!--i) - break; - } - } - } - - /* Exact line number? */ - if (!memcmp(buf + start, fragment, fragsize)) - return start; - - /* - * There's probably some smart way to do this, but I'll leave - * that to the smart and beautiful people. I'm simple and stupid. - */ - backwards = start; - forwards = start; - for (i = 0; ; i++) { - unsigned long try; - int n; - - /* "backward" */ - if (i & 1) { - if (!backwards) { - if (forwards + fragsize > size) - break; - continue; - } - do { - --backwards; - } while (backwards && buf[backwards-1] != '\n'); - try = backwards; - } else { - while (forwards + fragsize <= size) { - if (buf[forwards++] == '\n') - break; - } - try = forwards; - } - - if (try + fragsize > size) - continue; - if (memcmp(buf + try, fragment, fragsize)) - continue; - n = (i >> 1)+1; - if (i & 1) - n = -n; - *lines = n; - return try; - } - - /* - * We should start searching forward and backward. - */ - return -1; -} - -static void remove_first_line(const char **rbuf, int *rsize) -{ - const char *buf = *rbuf; - int size = *rsize; - unsigned long offset; - offset = 0; - while (offset <= size) { - if (buf[offset++] == '\n') - break; - } - *rsize = size - offset; - *rbuf = buf + offset; -} - -static void remove_last_line(const char **rbuf, int *rsize) -{ - const char *buf = *rbuf; - int size = *rsize; - unsigned long offset; - offset = size - 1; - while (offset > 0) { - if (buf[--offset] == '\n') - break; - } - *rsize = offset + 1; -} - -struct buffer_desc { - char *buffer; - unsigned long size; - 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; - const char *patch = frag->patch; - int offset, size = frag->size; - char *old = xmalloc(size); - char *new = xmalloc(size); - const char *oldlines, *newlines; - int oldsize = 0, newsize = 0; - unsigned long leading, trailing; - int pos, lines; - - while (size > 0) { - int len = linelen(patch, size); - int plen; - - if (!len) - break; - - /* - * "plen" is how much of the line we should use for - * the actual patch data. Normally we just remove the - * first character on the line, but if the line is - * followed by "\ No newline", then we also remove the - * last one (which is the newline, of course). - */ - plen = len-1; - if (len < size && patch[len] == '\\') - plen--; - switch (*patch) { - case ' ': - case '-': - memcpy(old + oldsize, patch + 1, plen); - oldsize += plen; - if (*patch == '-') - break; - /* Fall-through for ' ' */ - case '+': - if (*patch != '+' || !no_add) - newsize += apply_line(new + newsize, patch, - plen); - break; - case '@': case '\\': - /* Ignore it, we already handled it */ - break; - default: - return -1; - } - patch += len; - size -= len; - } - -#ifdef NO_ACCURATE_DIFF - if (oldsize > 0 && old[oldsize - 1] == '\n' && - newsize > 0 && new[newsize - 1] == '\n') { - oldsize--; - newsize--; - } -#endif - - oldlines = old; - newlines = new; - leading = frag->leading; - trailing = frag->trailing; - lines = 0; - pos = frag->newpos; - for (;;) { - offset = find_offset(buf, desc->size, oldlines, oldsize, pos, &lines); - if (offset >= 0) { - int diff = newsize - oldsize; - unsigned long size = desc->size + diff; - unsigned long alloc = desc->alloc; - - /* Warn if it was necessary to reduce the number - * of context lines. - */ - if ((leading != frag->leading) || (trailing != frag->trailing)) - fprintf(stderr, "Context reduced to (%ld/%ld) to apply fragment at %d\n", - leading, trailing, pos + lines); - - if (size > alloc) { - alloc = size + 8192; - desc->alloc = alloc; - buf = xrealloc(buf, alloc); - desc->buffer = buf; - } - desc->size = size; - memmove(buf + offset + newsize, buf + offset + oldsize, size - offset - newsize); - memcpy(buf + offset, newlines, newsize); - offset = 0; - - break; - } - - /* Am I at my context limits? */ - if ((leading <= p_context) && (trailing <= p_context)) - break; - /* Reduce the number of context lines - * Reduce both leading and trailing if they are equal - * otherwise just reduce the larger context. - */ - if (leading >= trailing) { - remove_first_line(&oldlines, &oldsize); - remove_first_line(&newlines, &newsize); - pos--; - leading--; - } - if (trailing > leading) { - remove_last_line(&oldlines, &oldsize); - remove_last_line(&newlines, &newsize); - trailing--; - } - } - - free(old); - free(new); - return offset; -} - -static char *inflate_it(const void *data, unsigned long size, - unsigned long inflated_size) -{ - z_stream stream; - void *out; - int st; - - memset(&stream, 0, sizeof(stream)); - - stream.next_in = (unsigned char *)data; - stream.avail_in = size; - stream.next_out = out = xmalloc(inflated_size); - stream.avail_out = inflated_size; - inflateInit(&stream); - st = inflate(&stream, Z_FINISH); - if ((st != Z_STREAM_END) || stream.total_out != inflated_size) { - free(out); - return NULL; - } - return out; -} - -static int apply_binary_fragment(struct buffer_desc *desc, struct patch *patch) -{ - unsigned long dst_size; - struct fragment *fragment = patch->fragments; - void *data; - void *result; - - data = inflate_it(fragment->patch, fragment->size, - patch->deflate_origlen); - if (!data) - return error("corrupt patch data"); - switch (patch->is_binary) { - case BINARY_DELTA_DEFLATED: - result = patch_delta(desc->buffer, desc->size, - data, - patch->deflate_origlen, - &dst_size); - free(desc->buffer); - desc->buffer = result; - free(data); - break; - case BINARY_LITERAL_DEFLATED: - free(desc->buffer); - desc->buffer = data; - dst_size = patch->deflate_origlen; - break; - } - if (!desc->buffer) - return -1; - desc->size = desc->alloc = dst_size; - return 0; -} - -static int apply_binary(struct buffer_desc *desc, struct patch *patch) -{ - const char *name = patch->old_name ? patch->old_name : patch->new_name; - unsigned char sha1[20]; - unsigned char hdr[50]; - int hdrlen; - - if (!allow_binary_replacement) - return error("cannot apply binary patch to '%s' " - "without --allow-binary-replacement", - name); - - /* For safety, we require patch index line to contain - * full 40-byte textual SHA1 for old and new, at least for now. - */ - if (strlen(patch->old_sha1_prefix) != 40 || - strlen(patch->new_sha1_prefix) != 40 || - get_sha1_hex(patch->old_sha1_prefix, sha1) || - get_sha1_hex(patch->new_sha1_prefix, sha1)) - return error("cannot apply binary patch to '%s' " - "without full index line", name); - - if (patch->old_name) { - /* See if the old one matches what the patch - * applies to. - */ - write_sha1_file_prepare(desc->buffer, desc->size, - blob_type, sha1, hdr, &hdrlen); - if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix)) - return error("the patch applies to '%s' (%s), " - "which does not match the " - "current contents.", - name, sha1_to_hex(sha1)); - } - else { - /* Otherwise, the old one must be empty. */ - if (desc->size) - return error("the patch applies to an empty " - "'%s' but it is not empty", name); - } - - get_sha1_hex(patch->new_sha1_prefix, sha1); - if (!memcmp(sha1, null_sha1, 20)) { - free(desc->buffer); - desc->alloc = desc->size = 0; - desc->buffer = NULL; - return 0; /* deletion patch */ - } - - if (has_sha1_file(sha1)) { - /* We already have the postimage */ - char type[10]; - unsigned long size; - - free(desc->buffer); - desc->buffer = read_sha1_file(sha1, type, &size); - if (!desc->buffer) - return error("the necessary postimage %s for " - "'%s' cannot be read", - patch->new_sha1_prefix, name); - desc->alloc = desc->size = size; - } - else { - /* We have verified desc matches the preimage; - * apply the patch data to it, which is stored - * in the patch->fragments->{patch,size}. - */ - if (apply_binary_fragment(desc, patch)) - return error("binary patch does not apply to '%s'", - name); - - /* verify that the result matches */ - write_sha1_file_prepare(desc->buffer, desc->size, blob_type, - sha1, hdr, &hdrlen); - if (strcmp(sha1_to_hex(sha1), patch->new_sha1_prefix)) - return error("binary patch to '%s' creates incorrect result", name); - } - - return 0; -} - -static int apply_fragments(struct buffer_desc *desc, struct patch *patch) -{ - struct fragment *frag = patch->fragments; - const char *name = patch->old_name ? patch->old_name : patch->new_name; - - if (patch->is_binary) - return apply_binary(desc, patch); - - while (frag) { - if (apply_one_fragment(desc, frag) < 0) - return error("patch failed: %s:%ld", - name, frag->oldpos); - frag = frag->next; - } - return 0; -} - -static int apply_data(struct patch *patch, struct stat *st, struct cache_entry *ce) -{ - char *buf; - unsigned long size, alloc; - struct buffer_desc desc; - - size = 0; - alloc = 0; - buf = NULL; - if (cached) { - if (ce) { - char type[20]; - buf = read_sha1_file(ce->sha1, type, &size); - if (!buf) - return error("read of %s failed", - patch->old_name); - alloc = size; - } - } - else if (patch->old_name) { - size = st->st_size; - alloc = size + 8192; - buf = xmalloc(alloc); - if (read_old_data(st, patch->old_name, buf, alloc) != size) - return error("read of %s failed", patch->old_name); - } - - desc.size = size; - desc.alloc = alloc; - desc.buffer = buf; - if (apply_fragments(&desc, patch) < 0) - return -1; - patch->result = desc.buffer; - patch->resultsize = desc.size; - - if (patch->is_delete && patch->resultsize) - return error("removal patch leaves file contents"); - - return 0; -} - -static int check_patch(struct patch *patch) -{ - struct stat st; - const char *old_name = patch->old_name; - const char *new_name = patch->new_name; - const char *name = old_name ? old_name : new_name; - struct cache_entry *ce = NULL; - - if (old_name) { - int changed = 0; - int stat_ret = 0; - unsigned st_mode = 0; - - if (!cached) - stat_ret = lstat(old_name, &st); - if (check_index) { - int pos = cache_name_pos(old_name, strlen(old_name)); - if (pos < 0) - return error("%s: does not exist in index", - old_name); - ce = active_cache[pos]; - if (stat_ret < 0) { - struct checkout costate; - if (errno != ENOENT) - return error("%s: %s", old_name, - strerror(errno)); - /* checkout */ - costate.base_dir = ""; - costate.base_dir_len = 0; - costate.force = 0; - costate.quiet = 0; - costate.not_new = 0; - costate.refresh_cache = 1; - if (checkout_entry(ce, - &costate, - NULL) || - lstat(old_name, &st)) - return -1; - } - if (!cached) - changed = ce_match_stat(ce, &st, 1); - if (changed) - return error("%s: does not match index", - old_name); - if (cached) - st_mode = ntohl(ce->ce_mode); - } - else if (stat_ret < 0) - return error("%s: %s", old_name, strerror(errno)); - - if (!cached) - st_mode = ntohl(create_ce_mode(st.st_mode)); - - if (patch->is_new < 0) - patch->is_new = 0; - if (!patch->old_mode) - patch->old_mode = st_mode; - if ((st_mode ^ patch->old_mode) & S_IFMT) - return error("%s: wrong type", old_name); - if (st_mode != patch->old_mode) - fprintf(stderr, "warning: %s has type %o, expected %o\n", - old_name, st_mode, patch->old_mode); - } - - if (new_name && (patch->is_new | patch->is_rename | patch->is_copy)) { - if (check_index && cache_name_pos(new_name, strlen(new_name)) >= 0) - return error("%s: already exists in index", new_name); - if (!cached) { - if (!lstat(new_name, &st)) - return error("%s: already exists in working directory", new_name); - if (errno != ENOENT) - return error("%s: %s", new_name, strerror(errno)); - } - if (!patch->new_mode) { - if (patch->is_new) - patch->new_mode = S_IFREG | 0644; - else - patch->new_mode = patch->old_mode; - } - } - - if (new_name && old_name) { - int same = !strcmp(old_name, new_name); - if (!patch->new_mode) - patch->new_mode = patch->old_mode; - if ((patch->old_mode ^ patch->new_mode) & S_IFMT) - return error("new mode (%o) of %s does not match old mode (%o)%s%s", - patch->new_mode, new_name, patch->old_mode, - same ? "" : " of ", same ? "" : old_name); - } - - if (apply_data(patch, &st, ce) < 0) - return error("%s: patch does not apply", name); - return 0; -} - -static int check_patch_list(struct patch *patch) -{ - int error = 0; - - for (;patch ; patch = patch->next) - error |= check_patch(patch); - return error; -} - -static inline int is_null_sha1(const unsigned char *sha1) -{ - return !memcmp(sha1, null_sha1, 20); -} - -static void show_index_list(struct patch *list) -{ - struct patch *patch; - - /* Once we start supporting the reverse patch, it may be - * worth showing the new sha1 prefix, but until then... - */ - for (patch = list; patch; patch = patch->next) { - const unsigned char *sha1_ptr; - unsigned char sha1[20]; - const char *name; - - name = patch->old_name ? patch->old_name : patch->new_name; - if (patch->is_new) - sha1_ptr = null_sha1; - else if (get_sha1(patch->old_sha1_prefix, sha1)) - die("sha1 information is lacking or useless (%s).", - name); - else - sha1_ptr = sha1; - - printf("%06o %s ",patch->old_mode, sha1_to_hex(sha1_ptr)); - if (line_termination && quote_c_style(name, NULL, NULL, 0)) - quote_c_style(name, NULL, stdout, 0); - else - fputs(name, stdout); - putchar(line_termination); - } -} - -static void stat_patch_list(struct patch *patch) -{ - int files, adds, dels; - - for (files = adds = dels = 0 ; patch ; patch = patch->next) { - files++; - adds += patch->lines_added; - dels += patch->lines_deleted; - show_stats(patch); - } - - printf(" %d files changed, %d insertions(+), %d deletions(-)\n", files, adds, dels); -} - -static void numstat_patch_list(struct patch *patch) -{ - for ( ; patch; patch = patch->next) { - const char *name; - name = patch->new_name ? patch->new_name : patch->old_name; - printf("%d\t%d\t", patch->lines_added, patch->lines_deleted); - if (line_termination && quote_c_style(name, NULL, NULL, 0)) - quote_c_style(name, NULL, stdout, 0); - else - fputs(name, stdout); - putchar('\n'); - } -} - -static void show_file_mode_name(const char *newdelete, unsigned int mode, const char *name) -{ - if (mode) - printf(" %s mode %06o %s\n", newdelete, mode, name); - else - printf(" %s %s\n", newdelete, name); -} - -static void show_mode_change(struct patch *p, int show_name) -{ - if (p->old_mode && p->new_mode && p->old_mode != p->new_mode) { - if (show_name) - printf(" mode change %06o => %06o %s\n", - p->old_mode, p->new_mode, p->new_name); - else - printf(" mode change %06o => %06o\n", - p->old_mode, p->new_mode); - } -} - -static void show_rename_copy(struct patch *p) -{ - const char *renamecopy = p->is_rename ? "rename" : "copy"; - const char *old, *new; - - /* Find common prefix */ - old = p->old_name; - new = p->new_name; - while (1) { - const char *slash_old, *slash_new; - slash_old = strchr(old, '/'); - slash_new = strchr(new, '/'); - if (!slash_old || - !slash_new || - slash_old - old != slash_new - new || - memcmp(old, new, slash_new - new)) - break; - old = slash_old + 1; - new = slash_new + 1; - } - /* p->old_name thru old is the common prefix, and old and new - * through the end of names are renames - */ - if (old != p->old_name) - printf(" %s %.*s{%s => %s} (%d%%)\n", renamecopy, - (int)(old - p->old_name), p->old_name, - old, new, p->score); - else - printf(" %s %s => %s (%d%%)\n", renamecopy, - p->old_name, p->new_name, p->score); - show_mode_change(p, 0); -} - -static void summary_patch_list(struct patch *patch) -{ - struct patch *p; - - for (p = patch; p; p = p->next) { - if (p->is_new) - show_file_mode_name("create", p->new_mode, p->new_name); - else if (p->is_delete) - show_file_mode_name("delete", p->old_mode, p->old_name); - else { - if (p->is_rename || p->is_copy) - show_rename_copy(p); - else { - if (p->score) { - printf(" rewrite %s (%d%%)\n", - p->new_name, p->score); - show_mode_change(p, 0); - } - else - show_mode_change(p, 1); - } - } - } -} - -static void patch_stats(struct patch *patch) -{ - int lines = patch->lines_added + patch->lines_deleted; - - if (lines > max_change) - max_change = lines; - if (patch->old_name) { - int len = quote_c_style(patch->old_name, NULL, NULL, 0); - if (!len) - len = strlen(patch->old_name); - if (len > max_len) - max_len = len; - } - if (patch->new_name) { - int len = quote_c_style(patch->new_name, NULL, NULL, 0); - if (!len) - len = strlen(patch->new_name); - if (len > max_len) - max_len = len; - } -} - -static void remove_file(struct patch *patch) -{ - if (write_index) { - if (remove_file_from_cache(patch->old_name) < 0) - die("unable to remove %s from index", patch->old_name); - } - if (!cached) - unlink(patch->old_name); -} - -static void add_index_file(const char *path, unsigned mode, void *buf, unsigned long size) -{ - struct stat st; - struct cache_entry *ce; - int namelen = strlen(path); - unsigned ce_size = cache_entry_size(namelen); - - if (!write_index) - return; - - ce = xcalloc(1, ce_size); - memcpy(ce->name, path, namelen); - ce->ce_mode = create_ce_mode(mode); - ce->ce_flags = htons(namelen); - if (!cached) { - if (lstat(path, &st) < 0) - die("unable to stat newly created file %s", path); - fill_stat_cache_info(ce, &st); - } - if (write_sha1_file(buf, size, blob_type, ce->sha1) < 0) - die("unable to create backing store for newly created file %s", path); - if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD) < 0) - die("unable to add cache entry for %s", path); -} - -static int try_create_file(const char *path, unsigned int mode, const char *buf, unsigned long size) -{ - int fd; - - if (S_ISLNK(mode)) - return symlink(buf, path); - fd = open(path, O_CREAT | O_EXCL | O_WRONLY, (mode & 0100) ? 0777 : 0666); - if (fd < 0) - return -1; - while (size) { - int written = xwrite(fd, buf, size); - if (written < 0) - die("writing file %s: %s", path, strerror(errno)); - if (!written) - die("out of space writing file %s", path); - buf += written; - size -= written; - } - if (close(fd) < 0) - die("closing file %s: %s", path, strerror(errno)); - return 0; -} - -/* - * We optimistically assume that the directories exist, - * which is true 99% of the time anyway. If they don't, - * we create them and try again. - */ -static void create_one_file(char *path, unsigned mode, const char *buf, unsigned long size) -{ - if (cached) - return; - if (!try_create_file(path, mode, buf, size)) - return; - - if (errno == ENOENT) { - if (safe_create_leading_directories(path)) - return; - if (!try_create_file(path, mode, buf, size)) - return; - } - - if (errno == EEXIST) { - unsigned int nr = getpid(); - - for (;;) { - const char *newpath; - newpath = mkpath("%s~%u", path, nr); - if (!try_create_file(newpath, mode, buf, size)) { - if (!rename(newpath, path)) - return; - unlink(newpath); - break; - } - if (errno != EEXIST) - break; - ++nr; - } - } - die("unable to write file %s mode %o", path, mode); -} - -static void create_file(struct patch *patch) -{ - char *path = patch->new_name; - unsigned mode = patch->new_mode; - unsigned long size = patch->resultsize; - char *buf = patch->result; - - if (!mode) - mode = S_IFREG | 0644; - create_one_file(path, mode, buf, size); - add_index_file(path, mode, buf, size); -} - -static void write_out_one_result(struct patch *patch) -{ - if (patch->is_delete > 0) { - remove_file(patch); - return; - } - if (patch->is_new > 0 || patch->is_copy) { - create_file(patch); - return; - } - /* - * Rename or modification boils down to the same - * thing: remove the old, write the new - */ - remove_file(patch); - create_file(patch); -} - -static void write_out_results(struct patch *list, int skipped_patch) -{ - if (!list && !skipped_patch) - die("No changes"); - - while (list) { - write_out_one_result(list); - list = list->next; - } -} - -static struct cache_file cache_file; - -static struct excludes { - struct excludes *next; - const char *path; -} *excludes; - -static int use_patch(struct patch *p) -{ - const char *pathname = p->new_name ? p->new_name : p->old_name; - struct excludes *x = excludes; - while (x) { - if (fnmatch(x->path, pathname, 0) == 0) - return 0; - x = x->next; - } - if (0 < prefix_length) { - int pathlen = strlen(pathname); - if (pathlen <= prefix_length || - memcmp(prefix, pathname, prefix_length)) - return 0; - } - return 1; -} - -static int apply_patch(int fd, const char *filename) -{ - unsigned long offset, size; - char *buffer = read_patch_file(fd, &size); - struct patch *list = NULL, **listp = &list; - int skipped_patch = 0; - - patch_input_file = filename; - if (!buffer) - return -1; - offset = 0; - while (size > 0) { - struct patch *patch; - int nr; - - patch = xcalloc(1, sizeof(*patch)); - nr = parse_chunk(buffer + offset, size, patch); - if (nr < 0) - break; - if (use_patch(patch)) { - patch_stats(patch); - *listp = patch; - listp = &patch->next; - } else { - /* perhaps free it a bit better? */ - free(patch); - skipped_patch++; - } - offset += nr; - size -= nr; - } - - if (whitespace_error && (new_whitespace == error_on_whitespace)) - apply = 0; - - write_index = check_index && apply; - if (write_index && newfd < 0) - newfd = hold_index_file_for_update(&cache_file, get_index_file()); - if (check_index) { - if (read_cache() < 0) - die("unable to read index file"); - } - - if ((check || apply) && check_patch_list(list) < 0) - exit(1); - - if (apply) - write_out_results(list, skipped_patch); - - if (show_index_info) - show_index_list(list); - - if (diffstat) - stat_patch_list(list); - - if (numstat) - numstat_patch_list(list); - - if (summary) - summary_patch_list(list); - - free(buffer); - 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]; - char *end; - int fd; - - if (!strcmp(arg, "-")) { - apply_patch(0, ""); - read_stdin = 0; - continue; - } - if (!strncmp(arg, "--exclude=", 10)) { - struct excludes *x = xmalloc(sizeof(*x)); - x->path = arg + 10; - x->next = excludes; - excludes = x; - continue; - } - if (!strncmp(arg, "-p", 2)) { - p_value = atoi(arg + 2); - continue; - } - if (!strcmp(arg, "--no-add")) { - no_add = 1; - continue; - } - if (!strcmp(arg, "--stat")) { - apply = 0; - diffstat = 1; - continue; - } - if (!strcmp(arg, "--allow-binary-replacement") || - !strcmp(arg, "--binary")) { - allow_binary_replacement = 1; - continue; - } - if (!strcmp(arg, "--numstat")) { - apply = 0; - numstat = 1; - continue; - } - if (!strcmp(arg, "--summary")) { - apply = 0; - summary = 1; - continue; - } - if (!strcmp(arg, "--check")) { - apply = 0; - check = 1; - continue; - } - if (!strcmp(arg, "--index")) { - check_index = 1; - continue; - } - if (!strcmp(arg, "--cached")) { - check_index = 1; - cached = 1; - continue; - } - if (!strcmp(arg, "--apply")) { - apply = 1; - continue; - } - if (!strcmp(arg, "--index-info")) { - apply = 0; - show_index_info = 1; - continue; - } - if (!strcmp(arg, "-z")) { - line_termination = 0; - continue; - } - if (!strncmp(arg, "-C", 2)) { - p_context = strtoul(arg + 2, &end, 0); - if (*end != '\0') - die("unrecognized context count '%s'", arg + 2); - 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_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); - - fd = open(arg, O_RDONLY); - if (fd < 0) - usage(apply_usage); - read_stdin = 0; - set_default_whitespace_mode(whitespace_option); - apply_patch(fd, arg); - close(fd); - } - set_default_whitespace_mode(whitespace_option); - if (read_stdin) - apply_patch(0, ""); - 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" : ""); - } - - if (write_index) { - if (write_cache(newfd, active_cache, active_nr) || - commit_index_file(&cache_file)) - die("Unable to write new cachefile"); - } - - return 0; -} diff --git a/builtin-apply.c b/builtin-apply.c new file mode 100644 index 0000000..4056b9d --- /dev/null +++ b/builtin-apply.c @@ -0,0 +1,2300 @@ +/* + * apply.c + * + * Copyright (C) Linus Torvalds, 2005 + * + * This applies patches on top of some (arbitrary) version of the SCM. + * + */ +#include +#include "cache.h" +#include "quote.h" +#include "blob.h" +#include "delta.h" +#include "builtin.h" + +// --check turns on checking that the working tree matches the +// files that are being modified, but doesn't apply the patch +// --stat does just a diffstat, and doesn't actually apply +// --numstat does numeric diffstat, and doesn't actually apply +// --index-info shows the old and new index info for paths if available. +// --index updates the cache as well. +// --cached updates only the cache without ever touching the working tree. +// +static const char *prefix; +static int prefix_length = -1; +static int newfd = -1; + +static int p_value = 1; +static int allow_binary_replacement = 0; +static int check_index = 0; +static int write_index = 0; +static int cached = 0; +static int diffstat = 0; +static int numstat = 0; +static int summary = 0; +static int check = 0; +static int apply = 1; +static int no_add = 0; +static int show_index_info = 0; +static int line_termination = '\n'; +static unsigned long p_context = -1; +static const char apply_usage[] = +"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--cached] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] [-CNUM] [--whitespace=] ..."; + +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 + * scaling. + */ +static int max_change, max_len; + +/* + * Various "current state", notably line numbers and what + * file (and how) we're patching right now.. The "is_xxxx" + * things are flags, where -1 means "don't know yet". + */ +static int linenr = 1; + +struct fragment { + unsigned long leading, trailing; + unsigned long oldpos, oldlines; + unsigned long newpos, newlines; + const char *patch; + int size; + struct fragment *next; +}; + +struct patch { + char *new_name, *old_name, *def_name; + unsigned int old_mode, new_mode; + int is_rename, is_copy, is_new, is_delete, is_binary; +#define BINARY_DELTA_DEFLATED 1 +#define BINARY_LITERAL_DEFLATED 2 + unsigned long deflate_origlen; + int lines_added, lines_deleted; + int score; + struct fragment *fragments; + char *result; + unsigned long resultsize; + char old_sha1_prefix[41]; + char new_sha1_prefix[41]; + struct patch *next; +}; + +#define CHUNKSIZE (8192) +#define SLOP (16) + +static void *read_patch_file(int fd, unsigned long *sizep) +{ + unsigned long size = 0, alloc = CHUNKSIZE; + void *buffer = xmalloc(alloc); + + for (;;) { + int nr = alloc - size; + if (nr < 1024) { + alloc += CHUNKSIZE; + buffer = xrealloc(buffer, alloc); + nr = alloc - size; + } + nr = xread(fd, buffer + size, nr); + if (!nr) + break; + if (nr < 0) + die("git-apply: read returned %s", strerror(errno)); + size += nr; + } + *sizep = size; + + /* + * Make sure that we have some slop in the buffer + * so that we can do speculative "memcmp" etc, and + * see to it that it is NUL-filled. + */ + if (alloc < size + SLOP) + buffer = xrealloc(buffer, size + SLOP); + memset(buffer + size, 0, SLOP); + return buffer; +} + +static unsigned long linelen(const char *buffer, unsigned long size) +{ + unsigned long len = 0; + while (size--) { + len++; + if (*buffer++ == '\n') + break; + } + return len; +} + +static int is_dev_null(const char *str) +{ + return !memcmp("/dev/null", str, 9) && isspace(str[9]); +} + +#define TERM_SPACE 1 +#define TERM_TAB 2 + +static int name_terminate(const char *name, int namelen, int c, int terminate) +{ + if (c == ' ' && !(terminate & TERM_SPACE)) + return 0; + if (c == '\t' && !(terminate & TERM_TAB)) + return 0; + + return 1; +} + +static char * find_name(const char *line, char *def, int p_value, int terminate) +{ + int len; + const char *start = line; + char *name; + + if (*line == '"') { + /* Proposed "new-style" GNU patch/diff format; see + * http://marc.theaimsgroup.com/?l=git&m=112927316408690&w=2 + */ + name = unquote_c_style(line, NULL); + if (name) { + char *cp = name; + while (p_value) { + cp = strchr(name, '/'); + if (!cp) + break; + cp++; + p_value--; + } + if (cp) { + /* name can later be freed, so we need + * to memmove, not just return cp + */ + memmove(name, cp, strlen(cp) + 1); + free(def); + return name; + } + else { + free(name); + name = NULL; + } + } + } + + for (;;) { + char c = *line; + + if (isspace(c)) { + if (c == '\n') + break; + if (name_terminate(start, line-start, c, terminate)) + break; + } + line++; + if (c == '/' && !--p_value) + start = line; + } + if (!start) + return def; + len = line - start; + if (!len) + return def; + + /* + * Generally we prefer the shorter name, especially + * if the other one is just a variation of that with + * something else tacked on to the end (ie "file.orig" + * or "file~"). + */ + if (def) { + int deflen = strlen(def); + if (deflen < len && !strncmp(start, def, deflen)) + return def; + } + + name = xmalloc(len + 1); + memcpy(name, start, len); + name[len] = 0; + free(def); + return name; +} + +/* + * Get the name etc info from the --/+++ lines of a traditional patch header + * + * NOTE! This hardcodes "-p1" behaviour in filename detection. + * + * FIXME! The end-of-filename heuristics are kind of screwy. For existing + * files, we can happily check the index for a match, but for creating a + * new file we should try to match whatever "patch" does. I have no idea. + */ +static void parse_traditional_patch(const char *first, const char *second, struct patch *patch) +{ + char *name; + + first += 4; // skip "--- " + second += 4; // skip "+++ " + if (is_dev_null(first)) { + patch->is_new = 1; + patch->is_delete = 0; + name = find_name(second, NULL, p_value, TERM_SPACE | TERM_TAB); + patch->new_name = name; + } else if (is_dev_null(second)) { + patch->is_new = 0; + patch->is_delete = 1; + name = find_name(first, NULL, p_value, TERM_SPACE | TERM_TAB); + patch->old_name = name; + } else { + name = find_name(first, NULL, p_value, TERM_SPACE | TERM_TAB); + name = find_name(second, name, p_value, TERM_SPACE | TERM_TAB); + patch->old_name = patch->new_name = name; + } + if (!name) + die("unable to find filename in patch at line %d", linenr); +} + +static int gitdiff_hdrend(const char *line, struct patch *patch) +{ + return -1; +} + +/* + * We're anal about diff header consistency, to make + * sure that we don't end up having strange ambiguous + * patches floating around. + * + * As a result, gitdiff_{old|new}name() will check + * their names against any previous information, just + * to make sure.. + */ +static char *gitdiff_verify_name(const char *line, int isnull, char *orig_name, const char *oldnew) +{ + if (!orig_name && !isnull) + return find_name(line, NULL, 1, 0); + + if (orig_name) { + int len; + const char *name; + char *another; + name = orig_name; + len = strlen(name); + if (isnull) + die("git-apply: bad git-diff - expected /dev/null, got %s on line %d", name, linenr); + another = find_name(line, NULL, 1, 0); + if (!another || memcmp(another, name, len)) + die("git-apply: bad git-diff - inconsistent %s filename on line %d", oldnew, linenr); + free(another); + return orig_name; + } + else { + /* expect "/dev/null" */ + if (memcmp("/dev/null", line, 9) || line[9] != '\n') + die("git-apply: bad git-diff - expected /dev/null on line %d", linenr); + return NULL; + } +} + +static int gitdiff_oldname(const char *line, struct patch *patch) +{ + patch->old_name = gitdiff_verify_name(line, patch->is_new, patch->old_name, "old"); + return 0; +} + +static int gitdiff_newname(const char *line, struct patch *patch) +{ + patch->new_name = gitdiff_verify_name(line, patch->is_delete, patch->new_name, "new"); + return 0; +} + +static int gitdiff_oldmode(const char *line, struct patch *patch) +{ + patch->old_mode = strtoul(line, NULL, 8); + return 0; +} + +static int gitdiff_newmode(const char *line, struct patch *patch) +{ + patch->new_mode = strtoul(line, NULL, 8); + return 0; +} + +static int gitdiff_delete(const char *line, struct patch *patch) +{ + patch->is_delete = 1; + patch->old_name = patch->def_name; + return gitdiff_oldmode(line, patch); +} + +static int gitdiff_newfile(const char *line, struct patch *patch) +{ + patch->is_new = 1; + patch->new_name = patch->def_name; + return gitdiff_newmode(line, patch); +} + +static int gitdiff_copysrc(const char *line, struct patch *patch) +{ + patch->is_copy = 1; + patch->old_name = find_name(line, NULL, 0, 0); + return 0; +} + +static int gitdiff_copydst(const char *line, struct patch *patch) +{ + patch->is_copy = 1; + patch->new_name = find_name(line, NULL, 0, 0); + return 0; +} + +static int gitdiff_renamesrc(const char *line, struct patch *patch) +{ + patch->is_rename = 1; + patch->old_name = find_name(line, NULL, 0, 0); + return 0; +} + +static int gitdiff_renamedst(const char *line, struct patch *patch) +{ + patch->is_rename = 1; + patch->new_name = find_name(line, NULL, 0, 0); + return 0; +} + +static int gitdiff_similarity(const char *line, struct patch *patch) +{ + if ((patch->score = strtoul(line, NULL, 10)) == ULONG_MAX) + patch->score = 0; + return 0; +} + +static int gitdiff_dissimilarity(const char *line, struct patch *patch) +{ + if ((patch->score = strtoul(line, NULL, 10)) == ULONG_MAX) + patch->score = 0; + return 0; +} + +static int gitdiff_index(const char *line, struct patch *patch) +{ + /* index line is N hexadecimal, "..", N hexadecimal, + * and optional space with octal mode. + */ + const char *ptr, *eol; + int len; + + ptr = strchr(line, '.'); + if (!ptr || ptr[1] != '.' || 40 < ptr - line) + return 0; + len = ptr - line; + memcpy(patch->old_sha1_prefix, line, len); + patch->old_sha1_prefix[len] = 0; + + line = ptr + 2; + ptr = strchr(line, ' '); + eol = strchr(line, '\n'); + + if (!ptr || eol < ptr) + ptr = eol; + len = ptr - line; + + if (40 < len) + return 0; + memcpy(patch->new_sha1_prefix, line, len); + patch->new_sha1_prefix[len] = 0; + if (*ptr == ' ') + patch->new_mode = patch->old_mode = strtoul(ptr+1, NULL, 8); + return 0; +} + +/* + * This is normal for a diff that doesn't change anything: we'll fall through + * into the next diff. Tell the parser to break out. + */ +static int gitdiff_unrecognized(const char *line, struct patch *patch) +{ + return -1; +} + +static const char *stop_at_slash(const char *line, int llen) +{ + int i; + + for (i = 0; i < llen; i++) { + int ch = line[i]; + if (ch == '/') + return line + i; + } + return NULL; +} + +/* This is to extract the same name that appears on "diff --git" + * line. We do not find and return anything if it is a rename + * patch, and it is OK because we will find the name elsewhere. + * We need to reliably find name only when it is mode-change only, + * creation or deletion of an empty file. In any of these cases, + * both sides are the same name under a/ and b/ respectively. + */ +static char *git_header_name(char *line, int llen) +{ + int len; + const char *name; + const char *second = NULL; + + line += strlen("diff --git "); + llen -= strlen("diff --git "); + + if (*line == '"') { + const char *cp; + char *first = unquote_c_style(line, &second); + if (!first) + return NULL; + + /* advance to the first slash */ + cp = stop_at_slash(first, strlen(first)); + if (!cp || cp == first) { + /* we do not accept absolute paths */ + free_first_and_fail: + free(first); + return NULL; + } + len = strlen(cp+1); + memmove(first, cp+1, len+1); /* including NUL */ + + /* second points at one past closing dq of name. + * find the second name. + */ + while ((second < line + llen) && isspace(*second)) + second++; + + if (line + llen <= second) + goto free_first_and_fail; + if (*second == '"') { + char *sp = unquote_c_style(second, NULL); + if (!sp) + goto free_first_and_fail; + cp = stop_at_slash(sp, strlen(sp)); + if (!cp || cp == sp) { + free_both_and_fail: + free(sp); + goto free_first_and_fail; + } + /* They must match, otherwise ignore */ + if (strcmp(cp+1, first)) + goto free_both_and_fail; + free(sp); + return first; + } + + /* unquoted second */ + cp = stop_at_slash(second, line + llen - second); + if (!cp || cp == second) + goto free_first_and_fail; + cp++; + if (line + llen - cp != len + 1 || + memcmp(first, cp, len)) + goto free_first_and_fail; + return first; + } + + /* unquoted first name */ + name = stop_at_slash(line, llen); + if (!name || name == line) + return NULL; + + name++; + + /* since the first name is unquoted, a dq if exists must be + * the beginning of the second name. + */ + for (second = name; second < line + llen; second++) { + if (*second == '"') { + const char *cp = second; + const char *np; + char *sp = unquote_c_style(second, NULL); + + if (!sp) + return NULL; + np = stop_at_slash(sp, strlen(sp)); + if (!np || np == sp) { + free_second_and_fail: + free(sp); + return NULL; + } + np++; + len = strlen(np); + if (len < cp - name && + !strncmp(np, name, len) && + isspace(name[len])) { + /* Good */ + memmove(sp, np, len + 1); + return sp; + } + goto free_second_and_fail; + } + } + + /* + * Accept a name only if it shows up twice, exactly the same + * form. + */ + for (len = 0 ; ; len++) { + char c = name[len]; + + switch (c) { + default: + continue; + case '\n': + return NULL; + case '\t': case ' ': + second = name+len; + for (;;) { + char c = *second++; + if (c == '\n') + return NULL; + if (c == '/') + break; + } + if (second[len] == '\n' && !memcmp(name, second, len)) { + char *ret = xmalloc(len + 1); + memcpy(ret, name, len); + ret[len] = 0; + return ret; + } + } + } + return NULL; +} + +/* Verify that we recognize the lines following a git header */ +static int parse_git_header(char *line, int len, unsigned int size, struct patch *patch) +{ + unsigned long offset; + + /* A git diff has explicit new/delete information, so we don't guess */ + patch->is_new = 0; + patch->is_delete = 0; + + /* + * Some things may not have the old name in the + * rest of the headers anywhere (pure mode changes, + * or removing or adding empty files), so we get + * the default name from the header. + */ + patch->def_name = git_header_name(line, len); + + line += len; + size -= len; + linenr++; + for (offset = len ; size > 0 ; offset += len, size -= len, line += len, linenr++) { + static const struct opentry { + const char *str; + int (*fn)(const char *, struct patch *); + } optable[] = { + { "@@ -", gitdiff_hdrend }, + { "--- ", gitdiff_oldname }, + { "+++ ", gitdiff_newname }, + { "old mode ", gitdiff_oldmode }, + { "new mode ", gitdiff_newmode }, + { "deleted file mode ", gitdiff_delete }, + { "new file mode ", gitdiff_newfile }, + { "copy from ", gitdiff_copysrc }, + { "copy to ", gitdiff_copydst }, + { "rename old ", gitdiff_renamesrc }, + { "rename new ", gitdiff_renamedst }, + { "rename from ", gitdiff_renamesrc }, + { "rename to ", gitdiff_renamedst }, + { "similarity index ", gitdiff_similarity }, + { "dissimilarity index ", gitdiff_dissimilarity }, + { "index ", gitdiff_index }, + { "", gitdiff_unrecognized }, + }; + int i; + + len = linelen(line, size); + if (!len || line[len-1] != '\n') + break; + for (i = 0; i < ARRAY_SIZE(optable); i++) { + const struct opentry *p = optable + i; + int oplen = strlen(p->str); + if (len < oplen || memcmp(p->str, line, oplen)) + continue; + if (p->fn(line + oplen, patch) < 0) + return offset; + break; + } + } + + return offset; +} + +static int parse_num(const char *line, unsigned long *p) +{ + char *ptr; + + if (!isdigit(*line)) + return 0; + *p = strtoul(line, &ptr, 10); + return ptr - line; +} + +static int parse_range(const char *line, int len, int offset, const char *expect, + unsigned long *p1, unsigned long *p2) +{ + int digits, ex; + + if (offset < 0 || offset >= len) + return -1; + line += offset; + len -= offset; + + digits = parse_num(line, p1); + if (!digits) + return -1; + + offset += digits; + line += digits; + len -= digits; + + *p2 = 1; + if (*line == ',') { + digits = parse_num(line+1, p2); + if (!digits) + return -1; + + offset += digits+1; + line += digits+1; + len -= digits+1; + } + + ex = strlen(expect); + if (ex > len) + return -1; + if (memcmp(line, expect, ex)) + return -1; + + return offset + ex; +} + +/* + * Parse a unified diff fragment header of the + * form "@@ -a,b +c,d @@" + */ +static int parse_fragment_header(char *line, int len, struct fragment *fragment) +{ + int offset; + + if (!len || line[len-1] != '\n') + return -1; + + /* Figure out the number of lines in a fragment */ + offset = parse_range(line, len, 4, " +", &fragment->oldpos, &fragment->oldlines); + offset = parse_range(line, len, offset, " @@", &fragment->newpos, &fragment->newlines); + + return offset; +} + +static int find_header(char *line, unsigned long size, int *hdrsize, struct patch *patch) +{ + unsigned long offset, len; + + patch->is_rename = patch->is_copy = 0; + patch->is_new = patch->is_delete = -1; + patch->old_mode = patch->new_mode = 0; + patch->old_name = patch->new_name = NULL; + for (offset = 0; size > 0; offset += len, size -= len, line += len, linenr++) { + unsigned long nextlen; + + len = linelen(line, size); + if (!len) + break; + + /* Testing this early allows us to take a few shortcuts.. */ + if (len < 6) + continue; + + /* + * Make sure we don't find any unconnected patch fragmants. + * That's a sign that we didn't find a header, and that a + * patch has become corrupted/broken up. + */ + if (!memcmp("@@ -", line, 4)) { + struct fragment dummy; + if (parse_fragment_header(line, len, &dummy) < 0) + continue; + error("patch fragment without header at line %d: %.*s", linenr, (int)len-1, line); + } + + if (size < len + 6) + break; + + /* + * Git patch? It might not have a real patch, just a rename + * or mode change, so we handle that specially + */ + if (!memcmp("diff --git ", line, 11)) { + int git_hdr_len = parse_git_header(line, len, size, patch); + if (git_hdr_len <= len) + continue; + if (!patch->old_name && !patch->new_name) { + if (!patch->def_name) + die("git diff header lacks filename information (line %d)", linenr); + patch->old_name = patch->new_name = patch->def_name; + } + *hdrsize = git_hdr_len; + return offset; + } + + /** --- followed by +++ ? */ + if (memcmp("--- ", line, 4) || memcmp("+++ ", line + len, 4)) + continue; + + /* + * We only accept unified patches, so we want it to + * at least have "@@ -a,b +c,d @@\n", which is 14 chars + * minimum + */ + nextlen = linelen(line + len, size - len); + if (size < nextlen + 14 || memcmp("@@ -", line + len + nextlen, 4)) + continue; + + /* Ok, we'll consider it a patch */ + parse_traditional_patch(line, line+len, patch); + *hdrsize = len + nextlen; + linenr += 2; + return offset; + } + return -1; +} + +/* + * Parse a unified diff. Note that this really needs + * to parse each fragment separately, since the only + * way to know the difference between a "---" that is + * part of a patch, and a "---" that starts the next + * patch is to look at the line counts.. + */ +static int parse_fragment(char *line, unsigned long size, struct patch *patch, struct fragment *fragment) +{ + int added, deleted; + int len = linelen(line, size), offset; + unsigned long oldlines, newlines; + unsigned long leading, trailing; + + offset = parse_fragment_header(line, len, fragment); + if (offset < 0) + return -1; + oldlines = fragment->oldlines; + newlines = fragment->newlines; + leading = 0; + trailing = 0; + + if (patch->is_new < 0) { + patch->is_new = !oldlines; + if (!oldlines) + patch->old_name = NULL; + } + if (patch->is_delete < 0) { + patch->is_delete = !newlines; + if (!newlines) + patch->new_name = NULL; + } + + if (patch->is_new && oldlines) + return error("new file depends on old contents"); + if (patch->is_delete != !newlines) { + if (newlines) + return error("deleted file still has contents"); + fprintf(stderr, "** warning: file %s becomes empty but is not deleted\n", patch->new_name); + } + + /* Parse the thing.. */ + line += len; + size -= len; + linenr++; + added = deleted = 0; + for (offset = len; size > 0; offset += len, size -= len, line += len, linenr++) { + if (!oldlines && !newlines) + break; + len = linelen(line, size); + if (!len || line[len-1] != '\n') + return -1; + switch (*line) { + default: + return -1; + case ' ': + oldlines--; + newlines--; + if (!deleted && !added) + leading++; + trailing++; + break; + case '-': + deleted++; + oldlines--; + trailing = 0; + 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--; + trailing = 0; + break; + + /* We allow "\ No newline at end of file". Depending + * on locale settings when the patch was produced we + * don't know what this line looks like. The only + * thing we do know is that it begins with "\ ". + * Checking for 12 is just for sanity check -- any + * l10n of "\ No newline..." is at least that long. + */ + case '\\': + if (len < 12 || memcmp(line, "\\ ", 2)) + return -1; + break; + } + } + if (oldlines || newlines) + return -1; + fragment->leading = leading; + fragment->trailing = trailing; + + /* If a fragment ends with an incomplete line, we failed to include + * it in the above loop because we hit oldlines == newlines == 0 + * before seeing it. + */ + if (12 < size && !memcmp(line, "\\ ", 2)) + offset += linelen(line, size); + + patch->lines_added += added; + patch->lines_deleted += deleted; + return offset; +} + +static int parse_single_patch(char *line, unsigned long size, struct patch *patch) +{ + unsigned long offset = 0; + struct fragment **fragp = &patch->fragments; + + while (size > 4 && !memcmp(line, "@@ -", 4)) { + struct fragment *fragment; + int len; + + fragment = xcalloc(1, sizeof(*fragment)); + len = parse_fragment(line, size, patch, fragment); + if (len <= 0) + die("corrupt patch at line %d", linenr); + + fragment->patch = line; + fragment->size = len; + + *fragp = fragment; + fragp = &fragment->next; + + offset += len; + line += len; + size -= len; + } + return offset; +} + +static inline int metadata_changes(struct patch *patch) +{ + return patch->is_rename > 0 || + patch->is_copy > 0 || + patch->is_new > 0 || + patch->is_delete || + (patch->old_mode && patch->new_mode && + patch->old_mode != patch->new_mode); +} + +static int parse_binary(char *buffer, unsigned long size, struct patch *patch) +{ + /* We have read "GIT binary patch\n"; what follows is a line + * that says the patch method (currently, either "deflated + * literal" or "deflated delta") and the length of data before + * deflating; a sequence of 'length-byte' followed by base-85 + * encoded data follows. + * + * Each 5-byte sequence of base-85 encodes up to 4 bytes, + * and we would limit the patch line to 66 characters, + * so one line can fit up to 13 groups that would decode + * to 52 bytes max. The length byte 'A'-'Z' corresponds + * to 1-26 bytes, and 'a'-'z' corresponds to 27-52 bytes. + * The end of binary is signalled with an empty line. + */ + int llen, used; + struct fragment *fragment; + char *data = NULL; + + patch->fragments = fragment = xcalloc(1, sizeof(*fragment)); + + /* Grab the type of patch */ + llen = linelen(buffer, size); + used = llen; + linenr++; + + if (!strncmp(buffer, "delta ", 6)) { + patch->is_binary = BINARY_DELTA_DEFLATED; + patch->deflate_origlen = strtoul(buffer + 6, NULL, 10); + } + else if (!strncmp(buffer, "literal ", 8)) { + patch->is_binary = BINARY_LITERAL_DEFLATED; + patch->deflate_origlen = strtoul(buffer + 8, NULL, 10); + } + else + return error("unrecognized binary patch at line %d: %.*s", + linenr-1, llen-1, buffer); + buffer += llen; + while (1) { + int byte_length, max_byte_length, newsize; + llen = linelen(buffer, size); + used += llen; + linenr++; + if (llen == 1) + break; + /* Minimum line is "A00000\n" which is 7-byte long, + * and the line length must be multiple of 5 plus 2. + */ + if ((llen < 7) || (llen-2) % 5) + goto corrupt; + max_byte_length = (llen - 2) / 5 * 4; + byte_length = *buffer; + if ('A' <= byte_length && byte_length <= 'Z') + byte_length = byte_length - 'A' + 1; + else if ('a' <= byte_length && byte_length <= 'z') + byte_length = byte_length - 'a' + 27; + else + goto corrupt; + /* if the input length was not multiple of 4, we would + * have filler at the end but the filler should never + * exceed 3 bytes + */ + if (max_byte_length < byte_length || + byte_length <= max_byte_length - 4) + goto corrupt; + newsize = fragment->size + byte_length; + data = xrealloc(data, newsize); + if (decode_85(data + fragment->size, + buffer + 1, + byte_length)) + goto corrupt; + fragment->size = newsize; + buffer += llen; + size -= llen; + } + fragment->patch = data; + return used; + corrupt: + return error("corrupt binary patch at line %d: %.*s", + linenr-1, llen-1, buffer); +} + +static int parse_chunk(char *buffer, unsigned long size, struct patch *patch) +{ + int hdrsize, patchsize; + int offset = find_header(buffer, size, &hdrsize, patch); + + if (offset < 0) + return offset; + + patchsize = parse_single_patch(buffer + offset + hdrsize, size - offset - hdrsize, patch); + + if (!patchsize) { + static const char *binhdr[] = { + "Binary files ", + "Files ", + NULL, + }; + static const char git_binary[] = "GIT binary patch\n"; + int i; + int hd = hdrsize + offset; + unsigned long llen = linelen(buffer + hd, size - hd); + + if (llen == sizeof(git_binary) - 1 && + !memcmp(git_binary, buffer + hd, llen)) { + int used; + linenr++; + used = parse_binary(buffer + hd + llen, + size - hd - llen, patch); + if (used) + patchsize = used + llen; + else + patchsize = 0; + } + else if (!memcmp(" differ\n", buffer + hd + llen - 8, 8)) { + for (i = 0; binhdr[i]; i++) { + int len = strlen(binhdr[i]); + if (len < size - hd && + !memcmp(binhdr[i], buffer + hd, len)) { + linenr++; + patch->is_binary = 1; + patchsize = llen; + break; + } + } + } + + /* Empty patch cannot be applied if: + * - it is a binary patch and we do not do binary_replace, or + * - text patch without metadata change + */ + if ((apply || check) && + (patch->is_binary + ? !allow_binary_replacement + : !metadata_changes(patch))) + die("patch with only garbage at line %d", linenr); + } + + return offset + hdrsize + patchsize; +} + +static const char pluses[] = "++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"; +static const char minuses[]= "----------------------------------------------------------------------"; + +static void show_stats(struct patch *patch) +{ + const char *prefix = ""; + char *name = patch->new_name; + char *qname = NULL; + int len, max, add, del, total; + + if (!name) + name = patch->old_name; + + if (0 < (len = quote_c_style(name, NULL, NULL, 0))) { + qname = xmalloc(len + 1); + quote_c_style(name, qname, NULL, 0); + name = qname; + } + + /* + * "scale" the filename + */ + len = strlen(name); + max = max_len; + if (max > 50) + max = 50; + if (len > max) { + char *slash; + prefix = "..."; + max -= 3; + name += len - max; + slash = strchr(name, '/'); + if (slash) + name = slash; + } + len = max; + + /* + * scale the add/delete + */ + max = max_change; + if (max + len > 70) + max = 70 - len; + + add = patch->lines_added; + del = patch->lines_deleted; + total = add + del; + + if (max_change > 0) { + total = (total * max + max_change / 2) / max_change; + add = (add * max + max_change / 2) / max_change; + del = total - add; + } + if (patch->is_binary) + printf(" %s%-*s | Bin\n", prefix, len, name); + else + printf(" %s%-*s |%5d %.*s%.*s\n", prefix, + len, name, patch->lines_added + patch->lines_deleted, + add, pluses, del, minuses); + if (qname) + free(qname); +} + +static int read_old_data(struct stat *st, const char *path, void *buf, unsigned long size) +{ + int fd; + unsigned long got; + + switch (st->st_mode & S_IFMT) { + case S_IFLNK: + return readlink(path, buf, size); + case S_IFREG: + fd = open(path, O_RDONLY); + if (fd < 0) + return error("unable to open %s", path); + got = 0; + for (;;) { + int ret = xread(fd, buf + got, size - got); + if (ret <= 0) + break; + got += ret; + } + close(fd); + return got; + + default: + return -1; + } +} + +static int find_offset(const char *buf, unsigned long size, const char *fragment, unsigned long fragsize, int line, int *lines) +{ + int i; + unsigned long start, backwards, forwards; + + if (fragsize > size) + return -1; + + start = 0; + if (line > 1) { + unsigned long offset = 0; + i = line-1; + while (offset + fragsize <= size) { + if (buf[offset++] == '\n') { + start = offset; + if (!--i) + break; + } + } + } + + /* Exact line number? */ + if (!memcmp(buf + start, fragment, fragsize)) + return start; + + /* + * There's probably some smart way to do this, but I'll leave + * that to the smart and beautiful people. I'm simple and stupid. + */ + backwards = start; + forwards = start; + for (i = 0; ; i++) { + unsigned long try; + int n; + + /* "backward" */ + if (i & 1) { + if (!backwards) { + if (forwards + fragsize > size) + break; + continue; + } + do { + --backwards; + } while (backwards && buf[backwards-1] != '\n'); + try = backwards; + } else { + while (forwards + fragsize <= size) { + if (buf[forwards++] == '\n') + break; + } + try = forwards; + } + + if (try + fragsize > size) + continue; + if (memcmp(buf + try, fragment, fragsize)) + continue; + n = (i >> 1)+1; + if (i & 1) + n = -n; + *lines = n; + return try; + } + + /* + * We should start searching forward and backward. + */ + return -1; +} + +static void remove_first_line(const char **rbuf, int *rsize) +{ + const char *buf = *rbuf; + int size = *rsize; + unsigned long offset; + offset = 0; + while (offset <= size) { + if (buf[offset++] == '\n') + break; + } + *rsize = size - offset; + *rbuf = buf + offset; +} + +static void remove_last_line(const char **rbuf, int *rsize) +{ + const char *buf = *rbuf; + int size = *rsize; + unsigned long offset; + offset = size - 1; + while (offset > 0) { + if (buf[--offset] == '\n') + break; + } + *rsize = offset + 1; +} + +struct buffer_desc { + char *buffer; + unsigned long size; + 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; + const char *patch = frag->patch; + int offset, size = frag->size; + char *old = xmalloc(size); + char *new = xmalloc(size); + const char *oldlines, *newlines; + int oldsize = 0, newsize = 0; + unsigned long leading, trailing; + int pos, lines; + + while (size > 0) { + int len = linelen(patch, size); + int plen; + + if (!len) + break; + + /* + * "plen" is how much of the line we should use for + * the actual patch data. Normally we just remove the + * first character on the line, but if the line is + * followed by "\ No newline", then we also remove the + * last one (which is the newline, of course). + */ + plen = len-1; + if (len < size && patch[len] == '\\') + plen--; + switch (*patch) { + case ' ': + case '-': + memcpy(old + oldsize, patch + 1, plen); + oldsize += plen; + if (*patch == '-') + break; + /* Fall-through for ' ' */ + case '+': + if (*patch != '+' || !no_add) + newsize += apply_line(new + newsize, patch, + plen); + break; + case '@': case '\\': + /* Ignore it, we already handled it */ + break; + default: + return -1; + } + patch += len; + size -= len; + } + +#ifdef NO_ACCURATE_DIFF + if (oldsize > 0 && old[oldsize - 1] == '\n' && + newsize > 0 && new[newsize - 1] == '\n') { + oldsize--; + newsize--; + } +#endif + + oldlines = old; + newlines = new; + leading = frag->leading; + trailing = frag->trailing; + lines = 0; + pos = frag->newpos; + for (;;) { + offset = find_offset(buf, desc->size, oldlines, oldsize, pos, &lines); + if (offset >= 0) { + int diff = newsize - oldsize; + unsigned long size = desc->size + diff; + unsigned long alloc = desc->alloc; + + /* Warn if it was necessary to reduce the number + * of context lines. + */ + if ((leading != frag->leading) || (trailing != frag->trailing)) + fprintf(stderr, "Context reduced to (%ld/%ld) to apply fragment at %d\n", + leading, trailing, pos + lines); + + if (size > alloc) { + alloc = size + 8192; + desc->alloc = alloc; + buf = xrealloc(buf, alloc); + desc->buffer = buf; + } + desc->size = size; + memmove(buf + offset + newsize, buf + offset + oldsize, size - offset - newsize); + memcpy(buf + offset, newlines, newsize); + offset = 0; + + break; + } + + /* Am I at my context limits? */ + if ((leading <= p_context) && (trailing <= p_context)) + break; + /* Reduce the number of context lines + * Reduce both leading and trailing if they are equal + * otherwise just reduce the larger context. + */ + if (leading >= trailing) { + remove_first_line(&oldlines, &oldsize); + remove_first_line(&newlines, &newsize); + pos--; + leading--; + } + if (trailing > leading) { + remove_last_line(&oldlines, &oldsize); + remove_last_line(&newlines, &newsize); + trailing--; + } + } + + free(old); + free(new); + return offset; +} + +static char *inflate_it(const void *data, unsigned long size, + unsigned long inflated_size) +{ + z_stream stream; + void *out; + int st; + + memset(&stream, 0, sizeof(stream)); + + stream.next_in = (unsigned char *)data; + stream.avail_in = size; + stream.next_out = out = xmalloc(inflated_size); + stream.avail_out = inflated_size; + inflateInit(&stream); + st = inflate(&stream, Z_FINISH); + if ((st != Z_STREAM_END) || stream.total_out != inflated_size) { + free(out); + return NULL; + } + return out; +} + +static int apply_binary_fragment(struct buffer_desc *desc, struct patch *patch) +{ + unsigned long dst_size; + struct fragment *fragment = patch->fragments; + void *data; + void *result; + + data = inflate_it(fragment->patch, fragment->size, + patch->deflate_origlen); + if (!data) + return error("corrupt patch data"); + switch (patch->is_binary) { + case BINARY_DELTA_DEFLATED: + result = patch_delta(desc->buffer, desc->size, + data, + patch->deflate_origlen, + &dst_size); + free(desc->buffer); + desc->buffer = result; + free(data); + break; + case BINARY_LITERAL_DEFLATED: + free(desc->buffer); + desc->buffer = data; + dst_size = patch->deflate_origlen; + break; + } + if (!desc->buffer) + return -1; + desc->size = desc->alloc = dst_size; + return 0; +} + +static int apply_binary(struct buffer_desc *desc, struct patch *patch) +{ + const char *name = patch->old_name ? patch->old_name : patch->new_name; + unsigned char sha1[20]; + unsigned char hdr[50]; + int hdrlen; + + if (!allow_binary_replacement) + return error("cannot apply binary patch to '%s' " + "without --allow-binary-replacement", + name); + + /* For safety, we require patch index line to contain + * full 40-byte textual SHA1 for old and new, at least for now. + */ + if (strlen(patch->old_sha1_prefix) != 40 || + strlen(patch->new_sha1_prefix) != 40 || + get_sha1_hex(patch->old_sha1_prefix, sha1) || + get_sha1_hex(patch->new_sha1_prefix, sha1)) + return error("cannot apply binary patch to '%s' " + "without full index line", name); + + if (patch->old_name) { + /* See if the old one matches what the patch + * applies to. + */ + write_sha1_file_prepare(desc->buffer, desc->size, + blob_type, sha1, hdr, &hdrlen); + if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix)) + return error("the patch applies to '%s' (%s), " + "which does not match the " + "current contents.", + name, sha1_to_hex(sha1)); + } + else { + /* Otherwise, the old one must be empty. */ + if (desc->size) + return error("the patch applies to an empty " + "'%s' but it is not empty", name); + } + + get_sha1_hex(patch->new_sha1_prefix, sha1); + if (!memcmp(sha1, null_sha1, 20)) { + free(desc->buffer); + desc->alloc = desc->size = 0; + desc->buffer = NULL; + return 0; /* deletion patch */ + } + + if (has_sha1_file(sha1)) { + /* We already have the postimage */ + char type[10]; + unsigned long size; + + free(desc->buffer); + desc->buffer = read_sha1_file(sha1, type, &size); + if (!desc->buffer) + return error("the necessary postimage %s for " + "'%s' cannot be read", + patch->new_sha1_prefix, name); + desc->alloc = desc->size = size; + } + else { + /* We have verified desc matches the preimage; + * apply the patch data to it, which is stored + * in the patch->fragments->{patch,size}. + */ + if (apply_binary_fragment(desc, patch)) + return error("binary patch does not apply to '%s'", + name); + + /* verify that the result matches */ + write_sha1_file_prepare(desc->buffer, desc->size, blob_type, + sha1, hdr, &hdrlen); + if (strcmp(sha1_to_hex(sha1), patch->new_sha1_prefix)) + return error("binary patch to '%s' creates incorrect result", name); + } + + return 0; +} + +static int apply_fragments(struct buffer_desc *desc, struct patch *patch) +{ + struct fragment *frag = patch->fragments; + const char *name = patch->old_name ? patch->old_name : patch->new_name; + + if (patch->is_binary) + return apply_binary(desc, patch); + + while (frag) { + if (apply_one_fragment(desc, frag) < 0) + return error("patch failed: %s:%ld", + name, frag->oldpos); + frag = frag->next; + } + return 0; +} + +static int apply_data(struct patch *patch, struct stat *st, struct cache_entry *ce) +{ + char *buf; + unsigned long size, alloc; + struct buffer_desc desc; + + size = 0; + alloc = 0; + buf = NULL; + if (cached) { + if (ce) { + char type[20]; + buf = read_sha1_file(ce->sha1, type, &size); + if (!buf) + return error("read of %s failed", + patch->old_name); + alloc = size; + } + } + else if (patch->old_name) { + size = st->st_size; + alloc = size + 8192; + buf = xmalloc(alloc); + if (read_old_data(st, patch->old_name, buf, alloc) != size) + return error("read of %s failed", patch->old_name); + } + + desc.size = size; + desc.alloc = alloc; + desc.buffer = buf; + if (apply_fragments(&desc, patch) < 0) + return -1; + patch->result = desc.buffer; + patch->resultsize = desc.size; + + if (patch->is_delete && patch->resultsize) + return error("removal patch leaves file contents"); + + return 0; +} + +static int check_patch(struct patch *patch) +{ + struct stat st; + const char *old_name = patch->old_name; + const char *new_name = patch->new_name; + const char *name = old_name ? old_name : new_name; + struct cache_entry *ce = NULL; + + if (old_name) { + int changed = 0; + int stat_ret = 0; + unsigned st_mode = 0; + + if (!cached) + stat_ret = lstat(old_name, &st); + if (check_index) { + int pos = cache_name_pos(old_name, strlen(old_name)); + if (pos < 0) + return error("%s: does not exist in index", + old_name); + ce = active_cache[pos]; + if (stat_ret < 0) { + struct checkout costate; + if (errno != ENOENT) + return error("%s: %s", old_name, + strerror(errno)); + /* checkout */ + costate.base_dir = ""; + costate.base_dir_len = 0; + costate.force = 0; + costate.quiet = 0; + costate.not_new = 0; + costate.refresh_cache = 1; + if (checkout_entry(ce, + &costate, + NULL) || + lstat(old_name, &st)) + return -1; + } + if (!cached) + changed = ce_match_stat(ce, &st, 1); + if (changed) + return error("%s: does not match index", + old_name); + if (cached) + st_mode = ntohl(ce->ce_mode); + } + else if (stat_ret < 0) + return error("%s: %s", old_name, strerror(errno)); + + if (!cached) + st_mode = ntohl(create_ce_mode(st.st_mode)); + + if (patch->is_new < 0) + patch->is_new = 0; + if (!patch->old_mode) + patch->old_mode = st_mode; + if ((st_mode ^ patch->old_mode) & S_IFMT) + return error("%s: wrong type", old_name); + if (st_mode != patch->old_mode) + fprintf(stderr, "warning: %s has type %o, expected %o\n", + old_name, st_mode, patch->old_mode); + } + + if (new_name && (patch->is_new | patch->is_rename | patch->is_copy)) { + if (check_index && cache_name_pos(new_name, strlen(new_name)) >= 0) + return error("%s: already exists in index", new_name); + if (!cached) { + if (!lstat(new_name, &st)) + return error("%s: already exists in working directory", new_name); + if (errno != ENOENT) + return error("%s: %s", new_name, strerror(errno)); + } + if (!patch->new_mode) { + if (patch->is_new) + patch->new_mode = S_IFREG | 0644; + else + patch->new_mode = patch->old_mode; + } + } + + if (new_name && old_name) { + int same = !strcmp(old_name, new_name); + if (!patch->new_mode) + patch->new_mode = patch->old_mode; + if ((patch->old_mode ^ patch->new_mode) & S_IFMT) + return error("new mode (%o) of %s does not match old mode (%o)%s%s", + patch->new_mode, new_name, patch->old_mode, + same ? "" : " of ", same ? "" : old_name); + } + + if (apply_data(patch, &st, ce) < 0) + return error("%s: patch does not apply", name); + return 0; +} + +static int check_patch_list(struct patch *patch) +{ + int error = 0; + + for (;patch ; patch = patch->next) + error |= check_patch(patch); + return error; +} + +static inline int is_null_sha1(const unsigned char *sha1) +{ + return !memcmp(sha1, null_sha1, 20); +} + +static void show_index_list(struct patch *list) +{ + struct patch *patch; + + /* Once we start supporting the reverse patch, it may be + * worth showing the new sha1 prefix, but until then... + */ + for (patch = list; patch; patch = patch->next) { + const unsigned char *sha1_ptr; + unsigned char sha1[20]; + const char *name; + + name = patch->old_name ? patch->old_name : patch->new_name; + if (patch->is_new) + sha1_ptr = null_sha1; + else if (get_sha1(patch->old_sha1_prefix, sha1)) + die("sha1 information is lacking or useless (%s).", + name); + else + sha1_ptr = sha1; + + printf("%06o %s ",patch->old_mode, sha1_to_hex(sha1_ptr)); + if (line_termination && quote_c_style(name, NULL, NULL, 0)) + quote_c_style(name, NULL, stdout, 0); + else + fputs(name, stdout); + putchar(line_termination); + } +} + +static void stat_patch_list(struct patch *patch) +{ + int files, adds, dels; + + for (files = adds = dels = 0 ; patch ; patch = patch->next) { + files++; + adds += patch->lines_added; + dels += patch->lines_deleted; + show_stats(patch); + } + + printf(" %d files changed, %d insertions(+), %d deletions(-)\n", files, adds, dels); +} + +static void numstat_patch_list(struct patch *patch) +{ + for ( ; patch; patch = patch->next) { + const char *name; + name = patch->new_name ? patch->new_name : patch->old_name; + printf("%d\t%d\t", patch->lines_added, patch->lines_deleted); + if (line_termination && quote_c_style(name, NULL, NULL, 0)) + quote_c_style(name, NULL, stdout, 0); + else + fputs(name, stdout); + putchar('\n'); + } +} + +static void show_file_mode_name(const char *newdelete, unsigned int mode, const char *name) +{ + if (mode) + printf(" %s mode %06o %s\n", newdelete, mode, name); + else + printf(" %s %s\n", newdelete, name); +} + +static void show_mode_change(struct patch *p, int show_name) +{ + if (p->old_mode && p->new_mode && p->old_mode != p->new_mode) { + if (show_name) + printf(" mode change %06o => %06o %s\n", + p->old_mode, p->new_mode, p->new_name); + else + printf(" mode change %06o => %06o\n", + p->old_mode, p->new_mode); + } +} + +static void show_rename_copy(struct patch *p) +{ + const char *renamecopy = p->is_rename ? "rename" : "copy"; + const char *old, *new; + + /* Find common prefix */ + old = p->old_name; + new = p->new_name; + while (1) { + const char *slash_old, *slash_new; + slash_old = strchr(old, '/'); + slash_new = strchr(new, '/'); + if (!slash_old || + !slash_new || + slash_old - old != slash_new - new || + memcmp(old, new, slash_new - new)) + break; + old = slash_old + 1; + new = slash_new + 1; + } + /* p->old_name thru old is the common prefix, and old and new + * through the end of names are renames + */ + if (old != p->old_name) + printf(" %s %.*s{%s => %s} (%d%%)\n", renamecopy, + (int)(old - p->old_name), p->old_name, + old, new, p->score); + else + printf(" %s %s => %s (%d%%)\n", renamecopy, + p->old_name, p->new_name, p->score); + show_mode_change(p, 0); +} + +static void summary_patch_list(struct patch *patch) +{ + struct patch *p; + + for (p = patch; p; p = p->next) { + if (p->is_new) + show_file_mode_name("create", p->new_mode, p->new_name); + else if (p->is_delete) + show_file_mode_name("delete", p->old_mode, p->old_name); + else { + if (p->is_rename || p->is_copy) + show_rename_copy(p); + else { + if (p->score) { + printf(" rewrite %s (%d%%)\n", + p->new_name, p->score); + show_mode_change(p, 0); + } + else + show_mode_change(p, 1); + } + } + } +} + +static void patch_stats(struct patch *patch) +{ + int lines = patch->lines_added + patch->lines_deleted; + + if (lines > max_change) + max_change = lines; + if (patch->old_name) { + int len = quote_c_style(patch->old_name, NULL, NULL, 0); + if (!len) + len = strlen(patch->old_name); + if (len > max_len) + max_len = len; + } + if (patch->new_name) { + int len = quote_c_style(patch->new_name, NULL, NULL, 0); + if (!len) + len = strlen(patch->new_name); + if (len > max_len) + max_len = len; + } +} + +static void remove_file(struct patch *patch) +{ + if (write_index) { + if (remove_file_from_cache(patch->old_name) < 0) + die("unable to remove %s from index", patch->old_name); + } + if (!cached) + unlink(patch->old_name); +} + +static void add_index_file(const char *path, unsigned mode, void *buf, unsigned long size) +{ + struct stat st; + struct cache_entry *ce; + int namelen = strlen(path); + unsigned ce_size = cache_entry_size(namelen); + + if (!write_index) + return; + + ce = xcalloc(1, ce_size); + memcpy(ce->name, path, namelen); + ce->ce_mode = create_ce_mode(mode); + ce->ce_flags = htons(namelen); + if (!cached) { + if (lstat(path, &st) < 0) + die("unable to stat newly created file %s", path); + fill_stat_cache_info(ce, &st); + } + if (write_sha1_file(buf, size, blob_type, ce->sha1) < 0) + die("unable to create backing store for newly created file %s", path); + if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD) < 0) + die("unable to add cache entry for %s", path); +} + +static int try_create_file(const char *path, unsigned int mode, const char *buf, unsigned long size) +{ + int fd; + + if (S_ISLNK(mode)) + return symlink(buf, path); + fd = open(path, O_CREAT | O_EXCL | O_WRONLY, (mode & 0100) ? 0777 : 0666); + if (fd < 0) + return -1; + while (size) { + int written = xwrite(fd, buf, size); + if (written < 0) + die("writing file %s: %s", path, strerror(errno)); + if (!written) + die("out of space writing file %s", path); + buf += written; + size -= written; + } + if (close(fd) < 0) + die("closing file %s: %s", path, strerror(errno)); + return 0; +} + +/* + * We optimistically assume that the directories exist, + * which is true 99% of the time anyway. If they don't, + * we create them and try again. + */ +static void create_one_file(char *path, unsigned mode, const char *buf, unsigned long size) +{ + if (cached) + return; + if (!try_create_file(path, mode, buf, size)) + return; + + if (errno == ENOENT) { + if (safe_create_leading_directories(path)) + return; + if (!try_create_file(path, mode, buf, size)) + return; + } + + if (errno == EEXIST) { + unsigned int nr = getpid(); + + for (;;) { + const char *newpath; + newpath = mkpath("%s~%u", path, nr); + if (!try_create_file(newpath, mode, buf, size)) { + if (!rename(newpath, path)) + return; + unlink(newpath); + break; + } + if (errno != EEXIST) + break; + ++nr; + } + } + die("unable to write file %s mode %o", path, mode); +} + +static void create_file(struct patch *patch) +{ + char *path = patch->new_name; + unsigned mode = patch->new_mode; + unsigned long size = patch->resultsize; + char *buf = patch->result; + + if (!mode) + mode = S_IFREG | 0644; + create_one_file(path, mode, buf, size); + add_index_file(path, mode, buf, size); +} + +static void write_out_one_result(struct patch *patch) +{ + if (patch->is_delete > 0) { + remove_file(patch); + return; + } + if (patch->is_new > 0 || patch->is_copy) { + create_file(patch); + return; + } + /* + * Rename or modification boils down to the same + * thing: remove the old, write the new + */ + remove_file(patch); + create_file(patch); +} + +static void write_out_results(struct patch *list, int skipped_patch) +{ + if (!list && !skipped_patch) + die("No changes"); + + while (list) { + write_out_one_result(list); + list = list->next; + } +} + +static struct cache_file cache_file; + +static struct excludes { + struct excludes *next; + const char *path; +} *excludes; + +static int use_patch(struct patch *p) +{ + const char *pathname = p->new_name ? p->new_name : p->old_name; + struct excludes *x = excludes; + while (x) { + if (fnmatch(x->path, pathname, 0) == 0) + return 0; + x = x->next; + } + if (0 < prefix_length) { + int pathlen = strlen(pathname); + if (pathlen <= prefix_length || + memcmp(prefix, pathname, prefix_length)) + return 0; + } + return 1; +} + +static int apply_patch(int fd, const char *filename) +{ + unsigned long offset, size; + char *buffer = read_patch_file(fd, &size); + struct patch *list = NULL, **listp = &list; + int skipped_patch = 0; + + patch_input_file = filename; + if (!buffer) + return -1; + offset = 0; + while (size > 0) { + struct patch *patch; + int nr; + + patch = xcalloc(1, sizeof(*patch)); + nr = parse_chunk(buffer + offset, size, patch); + if (nr < 0) + break; + if (use_patch(patch)) { + patch_stats(patch); + *listp = patch; + listp = &patch->next; + } else { + /* perhaps free it a bit better? */ + free(patch); + skipped_patch++; + } + offset += nr; + size -= nr; + } + + if (whitespace_error && (new_whitespace == error_on_whitespace)) + apply = 0; + + write_index = check_index && apply; + if (write_index && newfd < 0) + newfd = hold_index_file_for_update(&cache_file, get_index_file()); + if (check_index) { + if (read_cache() < 0) + die("unable to read index file"); + } + + if ((check || apply) && check_patch_list(list) < 0) + exit(1); + + if (apply) + write_out_results(list, skipped_patch); + + if (show_index_info) + show_index_list(list); + + if (diffstat) + stat_patch_list(list); + + if (numstat) + numstat_patch_list(list); + + if (summary) + summary_patch_list(list); + + free(buffer); + 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 cmd_apply(int argc, const char **argv, char **envp) +{ + int i; + int read_stdin = 1; + const char *whitespace_option = NULL; + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + char *end; + int fd; + + if (!strcmp(arg, "-")) { + apply_patch(0, ""); + read_stdin = 0; + continue; + } + if (!strncmp(arg, "--exclude=", 10)) { + struct excludes *x = xmalloc(sizeof(*x)); + x->path = arg + 10; + x->next = excludes; + excludes = x; + continue; + } + if (!strncmp(arg, "-p", 2)) { + p_value = atoi(arg + 2); + continue; + } + if (!strcmp(arg, "--no-add")) { + no_add = 1; + continue; + } + if (!strcmp(arg, "--stat")) { + apply = 0; + diffstat = 1; + continue; + } + if (!strcmp(arg, "--allow-binary-replacement") || + !strcmp(arg, "--binary")) { + allow_binary_replacement = 1; + continue; + } + if (!strcmp(arg, "--numstat")) { + apply = 0; + numstat = 1; + continue; + } + if (!strcmp(arg, "--summary")) { + apply = 0; + summary = 1; + continue; + } + if (!strcmp(arg, "--check")) { + apply = 0; + check = 1; + continue; + } + if (!strcmp(arg, "--index")) { + check_index = 1; + continue; + } + if (!strcmp(arg, "--cached")) { + check_index = 1; + cached = 1; + continue; + } + if (!strcmp(arg, "--apply")) { + apply = 1; + continue; + } + if (!strcmp(arg, "--index-info")) { + apply = 0; + show_index_info = 1; + continue; + } + if (!strcmp(arg, "-z")) { + line_termination = 0; + continue; + } + if (!strncmp(arg, "-C", 2)) { + p_context = strtoul(arg + 2, &end, 0); + if (*end != '\0') + die("unrecognized context count '%s'", arg + 2); + 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_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); + + fd = open(arg, O_RDONLY); + if (fd < 0) + usage(apply_usage); + read_stdin = 0; + set_default_whitespace_mode(whitespace_option); + apply_patch(fd, arg); + close(fd); + } + set_default_whitespace_mode(whitespace_option); + if (read_stdin) + apply_patch(0, ""); + 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" : ""); + } + + if (write_index) { + if (write_cache(newfd, active_cache, active_nr) || + commit_index_file(&cache_file)) + die("Unable to write new cachefile"); + } + + return 0; +} diff --git a/builtin.h b/builtin.h index c6b07d9..d6ff88e 100644 --- a/builtin.h +++ b/builtin.h @@ -32,5 +32,6 @@ extern int cmd_ls_tree(int argc, const char **argv, char **envp); extern int cmd_tar_tree(int argc, const char **argv, char **envp); extern int cmd_read_tree(int argc, const char **argv, char **envp); extern int cmd_commit_tree(int argc, const char **argv, char **envp); +extern int cmd_apply(int argc, const char **argv, char **envp); #endif diff --git a/git.c b/git.c index 4c2c062..f44e08b 100644 --- a/git.c +++ b/git.c @@ -57,7 +57,8 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "ls-tree", cmd_ls_tree }, { "tar-tree", cmd_tar_tree }, { "read-tree", cmd_read_tree }, - { "commit-tree", cmd_commit_tree } + { "commit-tree", cmd_commit_tree }, + { "apply", cmd_apply } }; int i; -- cgit v0.10.2-6-g49f6 From 51ce34b9923d9b119ac53414584f80e05520abea Mon Sep 17 00:00:00 2001 From: Peter Eriksen Date: Tue, 23 May 2006 14:15:35 +0200 Subject: Builtin git-show-branch. Signed-off-by: Peter Eriksen Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index 3da5768..69377e3 100644 --- a/Makefile +++ b/Makefile @@ -159,7 +159,7 @@ PROGRAMS = \ 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-receive-pack$X git-rev-parse$X \ - git-send-pack$X git-show-branch$X git-shell$X \ + git-send-pack$X git-shell$X \ git-show-index$X git-ssh-fetch$X \ git-ssh-upload$X git-unpack-file$X \ git-unpack-objects$X git-update-index$X git-update-server-info$X \ @@ -173,7 +173,7 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-grep$X git-rev-list$X git-check-ref-format$X \ git-init-db$X git-ls-files$X git-ls-tree$X \ git-tar-tree$X git-read-tree$X git-commit-tree$X \ - git-apply$X + git-apply$X git-show-branch$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -224,7 +224,7 @@ BUILTIN_OBJS = \ builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ builtin-init-db.o builtin-ls-files.o builtin-ls-tree.o \ builtin-tar-tree.o builtin-read-tree.o builtin-commit-tree.o \ - builtin-apply.o + builtin-apply.o builtin-show-branch.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-show-branch.c b/builtin-show-branch.c new file mode 100644 index 0000000..3af24e7 --- /dev/null +++ b/builtin-show-branch.c @@ -0,0 +1,789 @@ +#include +#include +#include "cache.h" +#include "commit.h" +#include "refs.h" +#include "builtin.h" + +static const char show_branch_usage[] = +"git-show-branch [--dense] [--current] [--all] [--heads] [--tags] [--topo-order] [--more=count | --list | --independent | --merge-base ] [--topics] [...]"; + +static int default_num = 0; +static int default_alloc = 0; +static const char **default_arg = NULL; + +#define UNINTERESTING 01 + +#define REV_SHIFT 2 +#define MAX_REVS 29 /* should not exceed bits_per_int - REV_SHIFT */ + +static struct commit *interesting(struct commit_list *list) +{ + while (list) { + struct commit *commit = list->item; + list = list->next; + if (commit->object.flags & UNINTERESTING) + continue; + return commit; + } + return NULL; +} + +static struct commit *pop_one_commit(struct commit_list **list_p) +{ + struct commit *commit; + struct commit_list *list; + list = *list_p; + commit = list->item; + *list_p = list->next; + free(list); + return commit; +} + +struct commit_name { + const char *head_name; /* which head's ancestor? */ + int generation; /* how many parents away from head_name */ +}; + +/* Name the commit as nth generation ancestor of head_name; + * we count only the first-parent relationship for naming purposes. + */ +static void name_commit(struct commit *commit, const char *head_name, int nth) +{ + struct commit_name *name; + if (!commit->object.util) + commit->object.util = xmalloc(sizeof(struct commit_name)); + name = commit->object.util; + name->head_name = head_name; + name->generation = nth; +} + +/* Parent is the first parent of the commit. We may name it + * as (n+1)th generation ancestor of the same head_name as + * commit is nth generation ancestor of, if that generation + * number is better than the name it already has. + */ +static void name_parent(struct commit *commit, struct commit *parent) +{ + struct commit_name *commit_name = commit->object.util; + struct commit_name *parent_name = parent->object.util; + if (!commit_name) + return; + if (!parent_name || + commit_name->generation + 1 < parent_name->generation) + name_commit(parent, commit_name->head_name, + commit_name->generation + 1); +} + +static int name_first_parent_chain(struct commit *c) +{ + int i = 0; + while (c) { + struct commit *p; + if (!c->object.util) + break; + if (!c->parents) + break; + p = c->parents->item; + if (!p->object.util) { + name_parent(c, p); + i++; + } + c = p; + } + return i; +} + +static void name_commits(struct commit_list *list, + struct commit **rev, + char **ref_name, + int num_rev) +{ + struct commit_list *cl; + struct commit *c; + int i; + + /* First give names to the given heads */ + for (cl = list; cl; cl = cl->next) { + c = cl->item; + if (c->object.util) + continue; + for (i = 0; i < num_rev; i++) { + if (rev[i] == c) { + name_commit(c, ref_name[i], 0); + break; + } + } + } + + /* Then commits on the first parent ancestry chain */ + do { + i = 0; + for (cl = list; cl; cl = cl->next) { + i += name_first_parent_chain(cl->item); + } + } while (i); + + /* Finally, any unnamed commits */ + do { + i = 0; + for (cl = list; cl; cl = cl->next) { + struct commit_list *parents; + struct commit_name *n; + int nth; + c = cl->item; + if (!c->object.util) + continue; + n = c->object.util; + parents = c->parents; + nth = 0; + while (parents) { + struct commit *p = parents->item; + char newname[1000], *en; + parents = parents->next; + nth++; + if (p->object.util) + continue; + en = newname; + switch (n->generation) { + case 0: + en += sprintf(en, "%s", n->head_name); + break; + case 1: + en += sprintf(en, "%s^", n->head_name); + break; + default: + en += sprintf(en, "%s~%d", + n->head_name, n->generation); + break; + } + if (nth == 1) + en += sprintf(en, "^"); + else + en += sprintf(en, "^%d", nth); + name_commit(p, strdup(newname), 0); + i++; + name_first_parent_chain(p); + } + } + } while (i); +} + +static int mark_seen(struct commit *commit, struct commit_list **seen_p) +{ + if (!commit->object.flags) { + insert_by_date(commit, seen_p); + return 1; + } + return 0; +} + +static void join_revs(struct commit_list **list_p, + struct commit_list **seen_p, + int num_rev, int extra) +{ + int all_mask = ((1u << (REV_SHIFT + num_rev)) - 1); + int all_revs = all_mask & ~((1u << REV_SHIFT) - 1); + + while (*list_p) { + struct commit_list *parents; + int still_interesting = !!interesting(*list_p); + struct commit *commit = pop_one_commit(list_p); + int flags = commit->object.flags & all_mask; + + if (!still_interesting && extra <= 0) + break; + + mark_seen(commit, seen_p); + if ((flags & all_revs) == all_revs) + flags |= UNINTERESTING; + parents = commit->parents; + + while (parents) { + struct commit *p = parents->item; + int this_flag = p->object.flags; + parents = parents->next; + if ((this_flag & flags) == flags) + continue; + if (!p->object.parsed) + parse_commit(p); + if (mark_seen(p, seen_p) && !still_interesting) + extra--; + p->object.flags |= flags; + insert_by_date(p, list_p); + } + } + + /* + * Postprocess to complete well-poisoning. + * + * At this point we have all the commits we have seen in + * seen_p list (which happens to be sorted chronologically but + * it does not really matter). Mark anything that can be + * reached from uninteresting commits not interesting. + */ + for (;;) { + int changed = 0; + struct commit_list *s; + for (s = *seen_p; s; s = s->next) { + struct commit *c = s->item; + struct commit_list *parents; + + if (((c->object.flags & all_revs) != all_revs) && + !(c->object.flags & UNINTERESTING)) + continue; + + /* The current commit is either a merge base or + * already uninteresting one. Mark its parents + * as uninteresting commits _only_ if they are + * already parsed. No reason to find new ones + * here. + */ + parents = c->parents; + while (parents) { + struct commit *p = parents->item; + parents = parents->next; + if (!(p->object.flags & UNINTERESTING)) { + p->object.flags |= UNINTERESTING; + changed = 1; + } + } + } + if (!changed) + break; + } +} + +static void show_one_commit(struct commit *commit, int no_name) +{ + char pretty[256], *cp; + struct commit_name *name = commit->object.util; + if (commit->object.parsed) + pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, + pretty, sizeof(pretty), 0); + else + strcpy(pretty, "(unavailable)"); + if (!strncmp(pretty, "[PATCH] ", 8)) + cp = pretty + 8; + else + cp = pretty; + + if (!no_name) { + if (name && name->head_name) { + printf("[%s", name->head_name); + if (name->generation) { + if (name->generation == 1) + printf("^"); + else + printf("~%d", name->generation); + } + printf("] "); + } + else + printf("[%s] ", + find_unique_abbrev(commit->object.sha1, 7)); + } + puts(cp); +} + +static char *ref_name[MAX_REVS + 1]; +static int ref_name_cnt; + +static const char *find_digit_prefix(const char *s, int *v) +{ + const char *p; + int ver; + char ch; + + for (p = s, ver = 0; + '0' <= (ch = *p) && ch <= '9'; + p++) + ver = ver * 10 + ch - '0'; + *v = ver; + return p; +} + + +static int version_cmp(const char *a, const char *b) +{ + while (1) { + int va, vb; + + a = find_digit_prefix(a, &va); + b = find_digit_prefix(b, &vb); + if (va != vb) + return va - vb; + + while (1) { + int ca = *a; + int cb = *b; + if ('0' <= ca && ca <= '9') + ca = 0; + if ('0' <= cb && cb <= '9') + cb = 0; + if (ca != cb) + return ca - cb; + if (!ca) + break; + a++; + b++; + } + if (!*a && !*b) + return 0; + } +} + +static int compare_ref_name(const void *a_, const void *b_) +{ + const char * const*a = a_, * const*b = b_; + return version_cmp(*a, *b); +} + +static void sort_ref_range(int bottom, int top) +{ + qsort(ref_name + bottom, top - bottom, sizeof(ref_name[0]), + compare_ref_name); +} + +static int append_ref(const char *refname, const unsigned char *sha1) +{ + struct commit *commit = lookup_commit_reference_gently(sha1, 1); + int i; + + if (!commit) + return 0; + /* Avoid adding the same thing twice */ + for (i = 0; i < ref_name_cnt; i++) + if (!strcmp(refname, ref_name[i])) + return 0; + + if (MAX_REVS <= ref_name_cnt) { + fprintf(stderr, "warning: ignoring %s; " + "cannot handle more than %d refs\n", + refname, MAX_REVS); + return 0; + } + ref_name[ref_name_cnt++] = strdup(refname); + ref_name[ref_name_cnt] = NULL; + return 0; +} + +static int append_head_ref(const char *refname, const unsigned char *sha1) +{ + unsigned char tmp[20]; + int ofs = 11; + if (strncmp(refname, "refs/heads/", ofs)) + return 0; + /* If both heads/foo and tags/foo exists, get_sha1 would + * get confused. + */ + if (get_sha1(refname + ofs, tmp) || memcmp(tmp, sha1, 20)) + ofs = 5; + return append_ref(refname + ofs, sha1); +} + +static int append_tag_ref(const char *refname, const unsigned char *sha1) +{ + if (strncmp(refname, "refs/tags/", 10)) + return 0; + return append_ref(refname + 5, sha1); +} + +static const char *match_ref_pattern = NULL; +static int match_ref_slash = 0; +static int count_slash(const char *s) +{ + int cnt = 0; + while (*s) + if (*s++ == '/') + cnt++; + return cnt; +} + +static int append_matching_ref(const char *refname, const unsigned char *sha1) +{ + /* we want to allow pattern hold/ to show all + * branches under refs/heads/hold/, and v0.99.9? to show + * refs/tags/v0.99.9a and friends. + */ + const char *tail; + int slash = count_slash(refname); + for (tail = refname; *tail && match_ref_slash < slash; ) + if (*tail++ == '/') + slash--; + if (!*tail) + return 0; + if (fnmatch(match_ref_pattern, tail, 0)) + return 0; + if (!strncmp("refs/heads/", refname, 11)) + return append_head_ref(refname, sha1); + if (!strncmp("refs/tags/", refname, 10)) + return append_tag_ref(refname, sha1); + return append_ref(refname, sha1); +} + +static void snarf_refs(int head, int tag) +{ + if (head) { + int orig_cnt = ref_name_cnt; + for_each_ref(append_head_ref); + sort_ref_range(orig_cnt, ref_name_cnt); + } + if (tag) { + int orig_cnt = ref_name_cnt; + for_each_ref(append_tag_ref); + sort_ref_range(orig_cnt, ref_name_cnt); + } +} + +static int rev_is_head(char *head_path, int headlen, char *name, + unsigned char *head_sha1, unsigned char *sha1) +{ + int namelen; + if ((!head_path[0]) || + (head_sha1 && sha1 && memcmp(head_sha1, sha1, 20))) + return 0; + namelen = strlen(name); + if ((headlen < namelen) || + memcmp(head_path + headlen - namelen, name, namelen)) + return 0; + if (headlen == namelen || + head_path[headlen - namelen - 1] == '/') + return 1; + return 0; +} + +static int show_merge_base(struct commit_list *seen, int num_rev) +{ + int all_mask = ((1u << (REV_SHIFT + num_rev)) - 1); + int all_revs = all_mask & ~((1u << REV_SHIFT) - 1); + int exit_status = 1; + + while (seen) { + struct commit *commit = pop_one_commit(&seen); + int flags = commit->object.flags & all_mask; + if (!(flags & UNINTERESTING) && + ((flags & all_revs) == all_revs)) { + puts(sha1_to_hex(commit->object.sha1)); + exit_status = 0; + commit->object.flags |= UNINTERESTING; + } + } + return exit_status; +} + +static int show_independent(struct commit **rev, + int num_rev, + char **ref_name, + unsigned int *rev_mask) +{ + int i; + + for (i = 0; i < num_rev; i++) { + struct commit *commit = rev[i]; + unsigned int flag = rev_mask[i]; + + if (commit->object.flags == flag) + puts(sha1_to_hex(commit->object.sha1)); + commit->object.flags |= UNINTERESTING; + } + return 0; +} + +static void append_one_rev(const char *av) +{ + unsigned char revkey[20]; + if (!get_sha1(av, revkey)) { + append_ref(av, revkey); + return; + } + if (strchr(av, '*') || strchr(av, '?') || strchr(av, '[')) { + /* glob style match */ + int saved_matches = ref_name_cnt; + match_ref_pattern = av; + match_ref_slash = count_slash(av); + for_each_ref(append_matching_ref); + if (saved_matches == ref_name_cnt && + ref_name_cnt < MAX_REVS) + error("no matching refs with %s", av); + if (saved_matches + 1 < ref_name_cnt) + sort_ref_range(saved_matches, ref_name_cnt); + return; + } + die("bad sha1 reference %s", av); +} + +static int git_show_branch_config(const char *var, const char *value) +{ + if (!strcmp(var, "showbranch.default")) { + if (default_alloc <= default_num + 1) { + default_alloc = default_alloc * 3 / 2 + 20; + default_arg = xrealloc(default_arg, sizeof *default_arg * default_alloc); + } + default_arg[default_num++] = strdup(value); + default_arg[default_num] = NULL; + return 0; + } + + return git_default_config(var, value); +} + +static int omit_in_dense(struct commit *commit, struct commit **rev, int n) +{ + /* If the commit is tip of the named branches, do not + * omit it. + * Otherwise, if it is a merge that is reachable from only one + * tip, it is not that interesting. + */ + int i, flag, count; + for (i = 0; i < n; i++) + if (rev[i] == commit) + return 0; + flag = commit->object.flags; + for (i = count = 0; i < n; i++) { + if (flag & (1u << (i + REV_SHIFT))) + count++; + } + if (count == 1) + return 1; + return 0; +} + +int cmd_show_branch(int ac, const char **av, char **envp) +{ + struct commit *rev[MAX_REVS], *commit; + struct commit_list *list = NULL, *seen = NULL; + unsigned int rev_mask[MAX_REVS]; + int num_rev, i, extra = 0; + int all_heads = 0, all_tags = 0; + int all_mask, all_revs; + int lifo = 1; + char head_path[128]; + const char *head_path_p; + int head_path_len; + unsigned char head_sha1[20]; + int merge_base = 0; + int independent = 0; + int no_name = 0; + int sha1_name = 0; + int shown_merge_point = 0; + int with_current_branch = 0; + int head_at = -1; + int topics = 0; + int dense = 1; + + setup_git_directory(); + git_config(git_show_branch_config); + + /* If nothing is specified, try the default first */ + if (ac == 1 && default_num) { + ac = default_num + 1; + av = default_arg - 1; /* ick; we would not address av[0] */ + } + + while (1 < ac && av[1][0] == '-') { + const char *arg = av[1]; + if (!strcmp(arg, "--")) { + ac--; av++; + break; + } + else if (!strcmp(arg, "--all")) + all_heads = all_tags = 1; + else if (!strcmp(arg, "--heads")) + all_heads = 1; + else if (!strcmp(arg, "--tags")) + all_tags = 1; + else if (!strcmp(arg, "--more")) + extra = 1; + else if (!strcmp(arg, "--list")) + extra = -1; + else if (!strcmp(arg, "--no-name")) + no_name = 1; + else if (!strcmp(arg, "--current")) + with_current_branch = 1; + else if (!strcmp(arg, "--sha1-name")) + sha1_name = 1; + else if (!strncmp(arg, "--more=", 7)) + extra = atoi(arg + 7); + else if (!strcmp(arg, "--merge-base")) + merge_base = 1; + else if (!strcmp(arg, "--independent")) + independent = 1; + else if (!strcmp(arg, "--topo-order")) + lifo = 1; + else if (!strcmp(arg, "--topics")) + topics = 1; + else if (!strcmp(arg, "--sparse")) + dense = 0; + else if (!strcmp(arg, "--date-order")) + lifo = 0; + else + usage(show_branch_usage); + ac--; av++; + } + ac--; av++; + + /* Only one of these is allowed */ + if (1 < independent + merge_base + (extra != 0)) + usage(show_branch_usage); + + /* If nothing is specified, show all branches by default */ + if (ac + all_heads + all_tags == 0) + all_heads = 1; + + if (all_heads + all_tags) + snarf_refs(all_heads, all_tags); + while (0 < ac) { + append_one_rev(*av); + ac--; av++; + } + + head_path_p = resolve_ref(git_path("HEAD"), head_sha1, 1); + if (head_path_p) { + head_path_len = strlen(head_path_p); + memcpy(head_path, head_path_p, head_path_len + 1); + } + else { + head_path_len = 0; + head_path[0] = 0; + } + + if (with_current_branch && head_path_p) { + int has_head = 0; + for (i = 0; !has_head && i < ref_name_cnt; i++) { + /* We are only interested in adding the branch + * HEAD points at. + */ + if (rev_is_head(head_path, + head_path_len, + ref_name[i], + head_sha1, NULL)) + has_head++; + } + if (!has_head) { + int pfxlen = strlen(git_path("refs/heads/")); + append_one_rev(head_path + pfxlen); + } + } + + if (!ref_name_cnt) { + fprintf(stderr, "No revs to be shown.\n"); + exit(0); + } + + for (num_rev = 0; ref_name[num_rev]; num_rev++) { + unsigned char revkey[20]; + unsigned int flag = 1u << (num_rev + REV_SHIFT); + + if (MAX_REVS <= num_rev) + die("cannot handle more than %d revs.", MAX_REVS); + if (get_sha1(ref_name[num_rev], revkey)) + die("'%s' is not a valid ref.", ref_name[num_rev]); + commit = lookup_commit_reference(revkey); + if (!commit) + die("cannot find commit %s (%s)", + ref_name[num_rev], revkey); + parse_commit(commit); + mark_seen(commit, &seen); + + /* rev#0 uses bit REV_SHIFT, rev#1 uses bit REV_SHIFT+1, + * and so on. REV_SHIFT bits from bit 0 are used for + * internal bookkeeping. + */ + commit->object.flags |= flag; + if (commit->object.flags == flag) + insert_by_date(commit, &list); + rev[num_rev] = commit; + } + for (i = 0; i < num_rev; i++) + rev_mask[i] = rev[i]->object.flags; + + if (0 <= extra) + join_revs(&list, &seen, num_rev, extra); + + if (merge_base) + return show_merge_base(seen, num_rev); + + if (independent) + return show_independent(rev, num_rev, ref_name, rev_mask); + + /* Show list; --more=-1 means list-only */ + if (1 < num_rev || extra < 0) { + for (i = 0; i < num_rev; i++) { + int j; + int is_head = rev_is_head(head_path, + head_path_len, + ref_name[i], + head_sha1, + rev[i]->object.sha1); + if (extra < 0) + printf("%c [%s] ", + is_head ? '*' : ' ', ref_name[i]); + else { + for (j = 0; j < i; j++) + putchar(' '); + printf("%c [%s] ", + is_head ? '*' : '!', ref_name[i]); + } + /* header lines never need name */ + show_one_commit(rev[i], 1); + if (is_head) + head_at = i; + } + if (0 <= extra) { + for (i = 0; i < num_rev; i++) + putchar('-'); + putchar('\n'); + } + } + if (extra < 0) + exit(0); + + /* Sort topologically */ + sort_in_topological_order(&seen, lifo); + + /* Give names to commits */ + if (!sha1_name && !no_name) + name_commits(seen, rev, ref_name, num_rev); + + all_mask = ((1u << (REV_SHIFT + num_rev)) - 1); + all_revs = all_mask & ~((1u << REV_SHIFT) - 1); + + while (seen) { + struct commit *commit = pop_one_commit(&seen); + int this_flag = commit->object.flags; + int is_merge_point = ((this_flag & all_revs) == all_revs); + + shown_merge_point |= is_merge_point; + + if (1 < num_rev) { + int is_merge = !!(commit->parents && + commit->parents->next); + if (topics && + !is_merge_point && + (this_flag & (1u << REV_SHIFT))) + continue; + if (dense && is_merge && + omit_in_dense(commit, rev, num_rev)) + continue; + for (i = 0; i < num_rev; i++) { + int mark; + if (!(this_flag & (1u << (i + REV_SHIFT)))) + mark = ' '; + else if (is_merge) + mark = '-'; + else if (i == head_at) + mark = '*'; + else + mark = '+'; + putchar(mark); + } + putchar(' '); + } + show_one_commit(commit, no_name); + + if (shown_merge_point && --extra < 0) + break; + } + return 0; +} diff --git a/builtin.h b/builtin.h index d6ff88e..01882ec 100644 --- a/builtin.h +++ b/builtin.h @@ -33,5 +33,6 @@ extern int cmd_tar_tree(int argc, const char **argv, char **envp); extern int cmd_read_tree(int argc, const char **argv, char **envp); extern int cmd_commit_tree(int argc, const char **argv, char **envp); extern int cmd_apply(int argc, const char **argv, char **envp); +extern int cmd_show_branch(int argc, const char **argv, char **envp); #endif diff --git a/git.c b/git.c index f44e08b..d29505c 100644 --- a/git.c +++ b/git.c @@ -58,7 +58,8 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "tar-tree", cmd_tar_tree }, { "read-tree", cmd_read_tree }, { "commit-tree", cmd_commit_tree }, - { "apply", cmd_apply } + { "apply", cmd_apply }, + { "show-branch", cmd_show_branch } }; int i; diff --git a/show-branch.c b/show-branch.c deleted file mode 100644 index 268c57b..0000000 --- a/show-branch.c +++ /dev/null @@ -1,788 +0,0 @@ -#include -#include -#include "cache.h" -#include "commit.h" -#include "refs.h" - -static const char show_branch_usage[] = -"git-show-branch [--dense] [--current] [--all] [--heads] [--tags] [--topo-order] [--more=count | --list | --independent | --merge-base ] [--topics] [...]"; - -static int default_num = 0; -static int default_alloc = 0; -static char **default_arg = NULL; - -#define UNINTERESTING 01 - -#define REV_SHIFT 2 -#define MAX_REVS 29 /* should not exceed bits_per_int - REV_SHIFT */ - -static struct commit *interesting(struct commit_list *list) -{ - while (list) { - struct commit *commit = list->item; - list = list->next; - if (commit->object.flags & UNINTERESTING) - continue; - return commit; - } - return NULL; -} - -static struct commit *pop_one_commit(struct commit_list **list_p) -{ - struct commit *commit; - struct commit_list *list; - list = *list_p; - commit = list->item; - *list_p = list->next; - free(list); - return commit; -} - -struct commit_name { - const char *head_name; /* which head's ancestor? */ - int generation; /* how many parents away from head_name */ -}; - -/* Name the commit as nth generation ancestor of head_name; - * we count only the first-parent relationship for naming purposes. - */ -static void name_commit(struct commit *commit, const char *head_name, int nth) -{ - struct commit_name *name; - if (!commit->object.util) - commit->object.util = xmalloc(sizeof(struct commit_name)); - name = commit->object.util; - name->head_name = head_name; - name->generation = nth; -} - -/* Parent is the first parent of the commit. We may name it - * as (n+1)th generation ancestor of the same head_name as - * commit is nth generation ancestor of, if that generation - * number is better than the name it already has. - */ -static void name_parent(struct commit *commit, struct commit *parent) -{ - struct commit_name *commit_name = commit->object.util; - struct commit_name *parent_name = parent->object.util; - if (!commit_name) - return; - if (!parent_name || - commit_name->generation + 1 < parent_name->generation) - name_commit(parent, commit_name->head_name, - commit_name->generation + 1); -} - -static int name_first_parent_chain(struct commit *c) -{ - int i = 0; - while (c) { - struct commit *p; - if (!c->object.util) - break; - if (!c->parents) - break; - p = c->parents->item; - if (!p->object.util) { - name_parent(c, p); - i++; - } - c = p; - } - return i; -} - -static void name_commits(struct commit_list *list, - struct commit **rev, - char **ref_name, - int num_rev) -{ - struct commit_list *cl; - struct commit *c; - int i; - - /* First give names to the given heads */ - for (cl = list; cl; cl = cl->next) { - c = cl->item; - if (c->object.util) - continue; - for (i = 0; i < num_rev; i++) { - if (rev[i] == c) { - name_commit(c, ref_name[i], 0); - break; - } - } - } - - /* Then commits on the first parent ancestry chain */ - do { - i = 0; - for (cl = list; cl; cl = cl->next) { - i += name_first_parent_chain(cl->item); - } - } while (i); - - /* Finally, any unnamed commits */ - do { - i = 0; - for (cl = list; cl; cl = cl->next) { - struct commit_list *parents; - struct commit_name *n; - int nth; - c = cl->item; - if (!c->object.util) - continue; - n = c->object.util; - parents = c->parents; - nth = 0; - while (parents) { - struct commit *p = parents->item; - char newname[1000], *en; - parents = parents->next; - nth++; - if (p->object.util) - continue; - en = newname; - switch (n->generation) { - case 0: - en += sprintf(en, "%s", n->head_name); - break; - case 1: - en += sprintf(en, "%s^", n->head_name); - break; - default: - en += sprintf(en, "%s~%d", - n->head_name, n->generation); - break; - } - if (nth == 1) - en += sprintf(en, "^"); - else - en += sprintf(en, "^%d", nth); - name_commit(p, strdup(newname), 0); - i++; - name_first_parent_chain(p); - } - } - } while (i); -} - -static int mark_seen(struct commit *commit, struct commit_list **seen_p) -{ - if (!commit->object.flags) { - insert_by_date(commit, seen_p); - return 1; - } - return 0; -} - -static void join_revs(struct commit_list **list_p, - struct commit_list **seen_p, - int num_rev, int extra) -{ - int all_mask = ((1u << (REV_SHIFT + num_rev)) - 1); - int all_revs = all_mask & ~((1u << REV_SHIFT) - 1); - - while (*list_p) { - struct commit_list *parents; - int still_interesting = !!interesting(*list_p); - struct commit *commit = pop_one_commit(list_p); - int flags = commit->object.flags & all_mask; - - if (!still_interesting && extra <= 0) - break; - - mark_seen(commit, seen_p); - if ((flags & all_revs) == all_revs) - flags |= UNINTERESTING; - parents = commit->parents; - - while (parents) { - struct commit *p = parents->item; - int this_flag = p->object.flags; - parents = parents->next; - if ((this_flag & flags) == flags) - continue; - if (!p->object.parsed) - parse_commit(p); - if (mark_seen(p, seen_p) && !still_interesting) - extra--; - p->object.flags |= flags; - insert_by_date(p, list_p); - } - } - - /* - * Postprocess to complete well-poisoning. - * - * At this point we have all the commits we have seen in - * seen_p list (which happens to be sorted chronologically but - * it does not really matter). Mark anything that can be - * reached from uninteresting commits not interesting. - */ - for (;;) { - int changed = 0; - struct commit_list *s; - for (s = *seen_p; s; s = s->next) { - struct commit *c = s->item; - struct commit_list *parents; - - if (((c->object.flags & all_revs) != all_revs) && - !(c->object.flags & UNINTERESTING)) - continue; - - /* The current commit is either a merge base or - * already uninteresting one. Mark its parents - * as uninteresting commits _only_ if they are - * already parsed. No reason to find new ones - * here. - */ - parents = c->parents; - while (parents) { - struct commit *p = parents->item; - parents = parents->next; - if (!(p->object.flags & UNINTERESTING)) { - p->object.flags |= UNINTERESTING; - changed = 1; - } - } - } - if (!changed) - break; - } -} - -static void show_one_commit(struct commit *commit, int no_name) -{ - char pretty[256], *cp; - struct commit_name *name = commit->object.util; - if (commit->object.parsed) - pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, - pretty, sizeof(pretty), 0); - else - strcpy(pretty, "(unavailable)"); - if (!strncmp(pretty, "[PATCH] ", 8)) - cp = pretty + 8; - else - cp = pretty; - - if (!no_name) { - if (name && name->head_name) { - printf("[%s", name->head_name); - if (name->generation) { - if (name->generation == 1) - printf("^"); - else - printf("~%d", name->generation); - } - printf("] "); - } - else - printf("[%s] ", - find_unique_abbrev(commit->object.sha1, 7)); - } - puts(cp); -} - -static char *ref_name[MAX_REVS + 1]; -static int ref_name_cnt; - -static const char *find_digit_prefix(const char *s, int *v) -{ - const char *p; - int ver; - char ch; - - for (p = s, ver = 0; - '0' <= (ch = *p) && ch <= '9'; - p++) - ver = ver * 10 + ch - '0'; - *v = ver; - return p; -} - - -static int version_cmp(const char *a, const char *b) -{ - while (1) { - int va, vb; - - a = find_digit_prefix(a, &va); - b = find_digit_prefix(b, &vb); - if (va != vb) - return va - vb; - - while (1) { - int ca = *a; - int cb = *b; - if ('0' <= ca && ca <= '9') - ca = 0; - if ('0' <= cb && cb <= '9') - cb = 0; - if (ca != cb) - return ca - cb; - if (!ca) - break; - a++; - b++; - } - if (!*a && !*b) - return 0; - } -} - -static int compare_ref_name(const void *a_, const void *b_) -{ - const char * const*a = a_, * const*b = b_; - return version_cmp(*a, *b); -} - -static void sort_ref_range(int bottom, int top) -{ - qsort(ref_name + bottom, top - bottom, sizeof(ref_name[0]), - compare_ref_name); -} - -static int append_ref(const char *refname, const unsigned char *sha1) -{ - struct commit *commit = lookup_commit_reference_gently(sha1, 1); - int i; - - if (!commit) - return 0; - /* Avoid adding the same thing twice */ - for (i = 0; i < ref_name_cnt; i++) - if (!strcmp(refname, ref_name[i])) - return 0; - - if (MAX_REVS <= ref_name_cnt) { - fprintf(stderr, "warning: ignoring %s; " - "cannot handle more than %d refs\n", - refname, MAX_REVS); - return 0; - } - ref_name[ref_name_cnt++] = strdup(refname); - ref_name[ref_name_cnt] = NULL; - return 0; -} - -static int append_head_ref(const char *refname, const unsigned char *sha1) -{ - unsigned char tmp[20]; - int ofs = 11; - if (strncmp(refname, "refs/heads/", ofs)) - return 0; - /* If both heads/foo and tags/foo exists, get_sha1 would - * get confused. - */ - if (get_sha1(refname + ofs, tmp) || memcmp(tmp, sha1, 20)) - ofs = 5; - return append_ref(refname + ofs, sha1); -} - -static int append_tag_ref(const char *refname, const unsigned char *sha1) -{ - if (strncmp(refname, "refs/tags/", 10)) - return 0; - return append_ref(refname + 5, sha1); -} - -static const char *match_ref_pattern = NULL; -static int match_ref_slash = 0; -static int count_slash(const char *s) -{ - int cnt = 0; - while (*s) - if (*s++ == '/') - cnt++; - return cnt; -} - -static int append_matching_ref(const char *refname, const unsigned char *sha1) -{ - /* we want to allow pattern hold/ to show all - * branches under refs/heads/hold/, and v0.99.9? to show - * refs/tags/v0.99.9a and friends. - */ - const char *tail; - int slash = count_slash(refname); - for (tail = refname; *tail && match_ref_slash < slash; ) - if (*tail++ == '/') - slash--; - if (!*tail) - return 0; - if (fnmatch(match_ref_pattern, tail, 0)) - return 0; - if (!strncmp("refs/heads/", refname, 11)) - return append_head_ref(refname, sha1); - if (!strncmp("refs/tags/", refname, 10)) - return append_tag_ref(refname, sha1); - return append_ref(refname, sha1); -} - -static void snarf_refs(int head, int tag) -{ - if (head) { - int orig_cnt = ref_name_cnt; - for_each_ref(append_head_ref); - sort_ref_range(orig_cnt, ref_name_cnt); - } - if (tag) { - int orig_cnt = ref_name_cnt; - for_each_ref(append_tag_ref); - sort_ref_range(orig_cnt, ref_name_cnt); - } -} - -static int rev_is_head(char *head_path, int headlen, char *name, - unsigned char *head_sha1, unsigned char *sha1) -{ - int namelen; - if ((!head_path[0]) || - (head_sha1 && sha1 && memcmp(head_sha1, sha1, 20))) - return 0; - namelen = strlen(name); - if ((headlen < namelen) || - memcmp(head_path + headlen - namelen, name, namelen)) - return 0; - if (headlen == namelen || - head_path[headlen - namelen - 1] == '/') - return 1; - return 0; -} - -static int show_merge_base(struct commit_list *seen, int num_rev) -{ - int all_mask = ((1u << (REV_SHIFT + num_rev)) - 1); - int all_revs = all_mask & ~((1u << REV_SHIFT) - 1); - int exit_status = 1; - - while (seen) { - struct commit *commit = pop_one_commit(&seen); - int flags = commit->object.flags & all_mask; - if (!(flags & UNINTERESTING) && - ((flags & all_revs) == all_revs)) { - puts(sha1_to_hex(commit->object.sha1)); - exit_status = 0; - commit->object.flags |= UNINTERESTING; - } - } - return exit_status; -} - -static int show_independent(struct commit **rev, - int num_rev, - char **ref_name, - unsigned int *rev_mask) -{ - int i; - - for (i = 0; i < num_rev; i++) { - struct commit *commit = rev[i]; - unsigned int flag = rev_mask[i]; - - if (commit->object.flags == flag) - puts(sha1_to_hex(commit->object.sha1)); - commit->object.flags |= UNINTERESTING; - } - return 0; -} - -static void append_one_rev(const char *av) -{ - unsigned char revkey[20]; - if (!get_sha1(av, revkey)) { - append_ref(av, revkey); - return; - } - if (strchr(av, '*') || strchr(av, '?') || strchr(av, '[')) { - /* glob style match */ - int saved_matches = ref_name_cnt; - match_ref_pattern = av; - match_ref_slash = count_slash(av); - for_each_ref(append_matching_ref); - if (saved_matches == ref_name_cnt && - ref_name_cnt < MAX_REVS) - error("no matching refs with %s", av); - if (saved_matches + 1 < ref_name_cnt) - sort_ref_range(saved_matches, ref_name_cnt); - return; - } - die("bad sha1 reference %s", av); -} - -static int git_show_branch_config(const char *var, const char *value) -{ - if (!strcmp(var, "showbranch.default")) { - if (default_alloc <= default_num + 1) { - default_alloc = default_alloc * 3 / 2 + 20; - default_arg = xrealloc(default_arg, sizeof *default_arg * default_alloc); - } - default_arg[default_num++] = strdup(value); - default_arg[default_num] = NULL; - return 0; - } - - return git_default_config(var, value); -} - -static int omit_in_dense(struct commit *commit, struct commit **rev, int n) -{ - /* If the commit is tip of the named branches, do not - * omit it. - * Otherwise, if it is a merge that is reachable from only one - * tip, it is not that interesting. - */ - int i, flag, count; - for (i = 0; i < n; i++) - if (rev[i] == commit) - return 0; - flag = commit->object.flags; - for (i = count = 0; i < n; i++) { - if (flag & (1u << (i + REV_SHIFT))) - count++; - } - if (count == 1) - return 1; - return 0; -} - -int main(int ac, char **av) -{ - struct commit *rev[MAX_REVS], *commit; - struct commit_list *list = NULL, *seen = NULL; - unsigned int rev_mask[MAX_REVS]; - int num_rev, i, extra = 0; - int all_heads = 0, all_tags = 0; - int all_mask, all_revs; - int lifo = 1; - char head_path[128]; - const char *head_path_p; - int head_path_len; - unsigned char head_sha1[20]; - int merge_base = 0; - int independent = 0; - int no_name = 0; - int sha1_name = 0; - int shown_merge_point = 0; - int with_current_branch = 0; - int head_at = -1; - int topics = 0; - int dense = 1; - - setup_git_directory(); - git_config(git_show_branch_config); - - /* If nothing is specified, try the default first */ - if (ac == 1 && default_num) { - ac = default_num + 1; - av = default_arg - 1; /* ick; we would not address av[0] */ - } - - while (1 < ac && av[1][0] == '-') { - char *arg = av[1]; - if (!strcmp(arg, "--")) { - ac--; av++; - break; - } - else if (!strcmp(arg, "--all")) - all_heads = all_tags = 1; - else if (!strcmp(arg, "--heads")) - all_heads = 1; - else if (!strcmp(arg, "--tags")) - all_tags = 1; - else if (!strcmp(arg, "--more")) - extra = 1; - else if (!strcmp(arg, "--list")) - extra = -1; - else if (!strcmp(arg, "--no-name")) - no_name = 1; - else if (!strcmp(arg, "--current")) - with_current_branch = 1; - else if (!strcmp(arg, "--sha1-name")) - sha1_name = 1; - else if (!strncmp(arg, "--more=", 7)) - extra = atoi(arg + 7); - else if (!strcmp(arg, "--merge-base")) - merge_base = 1; - else if (!strcmp(arg, "--independent")) - independent = 1; - else if (!strcmp(arg, "--topo-order")) - lifo = 1; - else if (!strcmp(arg, "--topics")) - topics = 1; - else if (!strcmp(arg, "--sparse")) - dense = 0; - else if (!strcmp(arg, "--date-order")) - lifo = 0; - else - usage(show_branch_usage); - ac--; av++; - } - ac--; av++; - - /* Only one of these is allowed */ - if (1 < independent + merge_base + (extra != 0)) - usage(show_branch_usage); - - /* If nothing is specified, show all branches by default */ - if (ac + all_heads + all_tags == 0) - all_heads = 1; - - if (all_heads + all_tags) - snarf_refs(all_heads, all_tags); - while (0 < ac) { - append_one_rev(*av); - ac--; av++; - } - - head_path_p = resolve_ref(git_path("HEAD"), head_sha1, 1); - if (head_path_p) { - head_path_len = strlen(head_path_p); - memcpy(head_path, head_path_p, head_path_len + 1); - } - else { - head_path_len = 0; - head_path[0] = 0; - } - - if (with_current_branch && head_path_p) { - int has_head = 0; - for (i = 0; !has_head && i < ref_name_cnt; i++) { - /* We are only interested in adding the branch - * HEAD points at. - */ - if (rev_is_head(head_path, - head_path_len, - ref_name[i], - head_sha1, NULL)) - has_head++; - } - if (!has_head) { - int pfxlen = strlen(git_path("refs/heads/")); - append_one_rev(head_path + pfxlen); - } - } - - if (!ref_name_cnt) { - fprintf(stderr, "No revs to be shown.\n"); - exit(0); - } - - for (num_rev = 0; ref_name[num_rev]; num_rev++) { - unsigned char revkey[20]; - unsigned int flag = 1u << (num_rev + REV_SHIFT); - - if (MAX_REVS <= num_rev) - die("cannot handle more than %d revs.", MAX_REVS); - if (get_sha1(ref_name[num_rev], revkey)) - die("'%s' is not a valid ref.", ref_name[num_rev]); - commit = lookup_commit_reference(revkey); - if (!commit) - die("cannot find commit %s (%s)", - ref_name[num_rev], revkey); - parse_commit(commit); - mark_seen(commit, &seen); - - /* rev#0 uses bit REV_SHIFT, rev#1 uses bit REV_SHIFT+1, - * and so on. REV_SHIFT bits from bit 0 are used for - * internal bookkeeping. - */ - commit->object.flags |= flag; - if (commit->object.flags == flag) - insert_by_date(commit, &list); - rev[num_rev] = commit; - } - for (i = 0; i < num_rev; i++) - rev_mask[i] = rev[i]->object.flags; - - if (0 <= extra) - join_revs(&list, &seen, num_rev, extra); - - if (merge_base) - return show_merge_base(seen, num_rev); - - if (independent) - return show_independent(rev, num_rev, ref_name, rev_mask); - - /* Show list; --more=-1 means list-only */ - if (1 < num_rev || extra < 0) { - for (i = 0; i < num_rev; i++) { - int j; - int is_head = rev_is_head(head_path, - head_path_len, - ref_name[i], - head_sha1, - rev[i]->object.sha1); - if (extra < 0) - printf("%c [%s] ", - is_head ? '*' : ' ', ref_name[i]); - else { - for (j = 0; j < i; j++) - putchar(' '); - printf("%c [%s] ", - is_head ? '*' : '!', ref_name[i]); - } - /* header lines never need name */ - show_one_commit(rev[i], 1); - if (is_head) - head_at = i; - } - if (0 <= extra) { - for (i = 0; i < num_rev; i++) - putchar('-'); - putchar('\n'); - } - } - if (extra < 0) - exit(0); - - /* Sort topologically */ - sort_in_topological_order(&seen, lifo); - - /* Give names to commits */ - if (!sha1_name && !no_name) - name_commits(seen, rev, ref_name, num_rev); - - all_mask = ((1u << (REV_SHIFT + num_rev)) - 1); - all_revs = all_mask & ~((1u << REV_SHIFT) - 1); - - while (seen) { - struct commit *commit = pop_one_commit(&seen); - int this_flag = commit->object.flags; - int is_merge_point = ((this_flag & all_revs) == all_revs); - - shown_merge_point |= is_merge_point; - - if (1 < num_rev) { - int is_merge = !!(commit->parents && - commit->parents->next); - if (topics && - !is_merge_point && - (this_flag & (1u << REV_SHIFT))) - continue; - if (dense && is_merge && - omit_in_dense(commit, rev, num_rev)) - continue; - for (i = 0; i < num_rev; i++) { - int mark; - if (!(this_flag & (1u << (i + REV_SHIFT)))) - mark = ' '; - else if (is_merge) - mark = '-'; - else if (i == head_at) - mark = '*'; - else - mark = '+'; - putchar(mark); - } - putchar(' '); - } - show_one_commit(commit, no_name); - - if (shown_merge_point && --extra < 0) - break; - } - return 0; -} -- cgit v0.10.2-6-g49f6 From e8cc9cd98e2ecd7fd8bb03e725d470405c8e2b94 Mon Sep 17 00:00:00 2001 From: Peter Eriksen Date: Tue, 23 May 2006 14:15:36 +0200 Subject: Builtin git-diff-files, git-diff-index, git-diff-stages, and git-diff-tree. Signed-off-by: Peter Eriksen Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index 69377e3..fc5f98b 100644 --- a/Makefile +++ b/Makefile @@ -151,9 +151,7 @@ SIMPLE_PROGRAMS = \ PROGRAMS = \ git-cat-file$X \ git-checkout-index$X git-clone-pack$X \ - 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$X \ + git-convert-objects$X git-fetch-pack$X git-fsck-objects$X \ git-hash-object$X git-index-pack$X git-local-fetch$X \ git-mailinfo$X git-merge-base$X \ git-merge-index$X git-mktag$X git-mktree$X git-pack-objects$X git-patch-id$X \ @@ -173,7 +171,8 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X \ git-grep$X git-rev-list$X git-check-ref-format$X \ git-init-db$X git-ls-files$X git-ls-tree$X \ git-tar-tree$X git-read-tree$X git-commit-tree$X \ - git-apply$X git-show-branch$X + git-apply$X git-show-branch$X git-diff-files$X \ + git-diff-index$X git-diff-stages$X git-diff-tree$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -223,8 +222,9 @@ BUILTIN_OBJS = \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \ builtin-init-db.o builtin-ls-files.o builtin-ls-tree.o \ - builtin-tar-tree.o builtin-read-tree.o builtin-commit-tree.o \ - builtin-apply.o builtin-show-branch.o + builtin-tar-tree.o builtin-read-tree.o builtin-commit-tree.o \ + builtin-apply.o builtin-show-branch.o builtin-diff-files.o \ + builtin-diff-index.o builtin-diff-stages.o builtin-diff-tree.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-diff-files.c b/builtin-diff-files.c new file mode 100644 index 0000000..cebda82 --- /dev/null +++ b/builtin-diff-files.c @@ -0,0 +1,55 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + */ +#include "cache.h" +#include "diff.h" +#include "commit.h" +#include "revision.h" +#include "builtin.h" + +static const char diff_files_usage[] = +"git-diff-files [-q] [-0/-1/2/3 |-c|--cc] [] [...]" +COMMON_DIFF_OPTIONS_HELP; + +int cmd_diff_files(int argc, const char **argv, char **envp) +{ + struct rev_info rev; + int silent = 0; + + git_config(git_diff_config); + init_revisions(&rev); + rev.abbrev = 0; + + argc = setup_revisions(argc, argv, &rev, NULL); + while (1 < argc && argv[1][0] == '-') { + if (!strcmp(argv[1], "--base")) + rev.max_count = 1; + else if (!strcmp(argv[1], "--ours")) + rev.max_count = 2; + else if (!strcmp(argv[1], "--theirs")) + rev.max_count = 3; + else if (!strcmp(argv[1], "-q")) + silent = 1; + else + usage(diff_files_usage); + argv++; argc--; + } + /* + * Make sure there are NO revision (i.e. pending object) parameter, + * rev.max_count is reasonable (0 <= n <= 3), + * there is no other revision filtering parameters. + */ + if (rev.pending_objects || + rev.min_age != -1 || rev.max_age != -1) + usage(diff_files_usage); + /* + * Backward compatibility wart - "diff-files -s" used to + * defeat the common diff option "-s" which asked for + * DIFF_FORMAT_NO_OUTPUT. + */ + if (rev.diffopt.output_format == DIFF_FORMAT_NO_OUTPUT) + rev.diffopt.output_format = DIFF_FORMAT_RAW; + return run_diff_files(&rev, silent); +} diff --git a/builtin-diff-index.c b/builtin-diff-index.c new file mode 100644 index 0000000..1958580 --- /dev/null +++ b/builtin-diff-index.c @@ -0,0 +1,39 @@ +#include "cache.h" +#include "diff.h" +#include "commit.h" +#include "revision.h" +#include "builtin.h" + +static const char diff_cache_usage[] = +"git-diff-index [-m] [--cached] " +"[] [...]" +COMMON_DIFF_OPTIONS_HELP; + +int cmd_diff_index(int argc, const char **argv, char **envp) +{ + struct rev_info rev; + int cached = 0; + int i; + + git_config(git_diff_config); + init_revisions(&rev); + rev.abbrev = 0; + + argc = setup_revisions(argc, argv, &rev, NULL); + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + + if (!strcmp(arg, "--cached")) + cached = 1; + else + usage(diff_cache_usage); + } + /* + * Make sure there is one revision (i.e. pending object), + * and there is no revision filtering parameters. + */ + if (!rev.pending_objects || rev.pending_objects->next || + rev.max_count != -1 || rev.min_age != -1 || rev.max_age != -1) + usage(diff_cache_usage); + return run_diff_index(&rev, cached); +} diff --git a/builtin-diff-stages.c b/builtin-diff-stages.c new file mode 100644 index 0000000..7c157ca --- /dev/null +++ b/builtin-diff-stages.c @@ -0,0 +1,105 @@ +/* + * Copyright (c) 2005 Junio C Hamano + */ + +#include "cache.h" +#include "diff.h" +#include "builtin.h" + +static struct diff_options diff_options; + +static const char diff_stages_usage[] = +"git-diff-stages [] [...]" +COMMON_DIFF_OPTIONS_HELP; + +static void diff_stages(int stage1, int stage2, const char **pathspec) +{ + int i = 0; + while (i < active_nr) { + struct cache_entry *ce, *stages[4] = { NULL, }; + struct cache_entry *one, *two; + const char *name; + int len, skip; + + ce = active_cache[i]; + skip = !ce_path_match(ce, pathspec); + len = ce_namelen(ce); + name = ce->name; + for (;;) { + int stage = ce_stage(ce); + stages[stage] = ce; + if (active_nr <= ++i) + break; + ce = active_cache[i]; + if (ce_namelen(ce) != len || + memcmp(name, ce->name, len)) + break; + } + one = stages[stage1]; + two = stages[stage2]; + + if (skip || (!one && !two)) + continue; + if (!one) + diff_addremove(&diff_options, '+', ntohl(two->ce_mode), + two->sha1, name, NULL); + else if (!two) + diff_addremove(&diff_options, '-', ntohl(one->ce_mode), + one->sha1, name, NULL); + else if (memcmp(one->sha1, two->sha1, 20) || + (one->ce_mode != two->ce_mode) || + diff_options.find_copies_harder) + diff_change(&diff_options, + ntohl(one->ce_mode), ntohl(two->ce_mode), + one->sha1, two->sha1, name, NULL); + } +} + +int cmd_diff_stages(int ac, const char **av, char **envp) +{ + int stage1, stage2; + const char *prefix = setup_git_directory(); + const char **pathspec = NULL; + + git_config(git_diff_config); + read_cache(); + diff_setup(&diff_options); + while (1 < ac && av[1][0] == '-') { + const char *arg = av[1]; + if (!strcmp(arg, "-r")) + ; /* as usual */ + else { + int diff_opt_cnt; + diff_opt_cnt = diff_opt_parse(&diff_options, + av+1, ac-1); + if (diff_opt_cnt < 0) + usage(diff_stages_usage); + else if (diff_opt_cnt) { + av += diff_opt_cnt; + ac -= diff_opt_cnt; + continue; + } + else + usage(diff_stages_usage); + } + ac--; av++; + } + + if (ac < 3 || + sscanf(av[1], "%d", &stage1) != 1 || + ! (0 <= stage1 && stage1 <= 3) || + sscanf(av[2], "%d", &stage2) != 1 || + ! (0 <= stage2 && stage2 <= 3)) + usage(diff_stages_usage); + + av += 3; /* The rest from av[0] are for paths restriction. */ + pathspec = get_pathspec(prefix, av); + + if (diff_setup_done(&diff_options) < 0) + usage(diff_stages_usage); + + diff_stages(stage1, stage2, pathspec); + diffcore_std(&diff_options); + diff_flush(&diff_options); + return 0; +} diff --git a/builtin-diff-tree.c b/builtin-diff-tree.c new file mode 100644 index 0000000..cc53b81 --- /dev/null +++ b/builtin-diff-tree.c @@ -0,0 +1,148 @@ +#include "cache.h" +#include "diff.h" +#include "commit.h" +#include "log-tree.h" +#include "builtin.h" + +static struct rev_info log_tree_opt; + +static int diff_tree_commit_sha1(const unsigned char *sha1) +{ + struct commit *commit = lookup_commit_reference(sha1); + if (!commit) + return -1; + return log_tree_commit(&log_tree_opt, commit); +} + +static int diff_tree_stdin(char *line) +{ + int len = strlen(line); + unsigned char sha1[20]; + struct commit *commit; + + if (!len || line[len-1] != '\n') + return -1; + line[len-1] = 0; + if (get_sha1_hex(line, sha1)) + return -1; + commit = lookup_commit(sha1); + if (!commit || parse_commit(commit)) + return -1; + if (isspace(line[40]) && !get_sha1_hex(line+41, sha1)) { + /* Graft the fake parents locally to the commit */ + int pos = 41; + struct commit_list **pptr, *parents; + + /* Free the real parent list */ + for (parents = commit->parents; parents; ) { + struct commit_list *tmp = parents->next; + free(parents); + parents = tmp; + } + commit->parents = NULL; + pptr = &(commit->parents); + while (line[pos] && !get_sha1_hex(line + pos, sha1)) { + struct commit *parent = lookup_commit(sha1); + if (parent) { + pptr = &commit_list_insert(parent, pptr)->next; + } + pos += 41; + } + } + return log_tree_commit(&log_tree_opt, commit); +} + +static const char diff_tree_usage[] = +"git-diff-tree [--stdin] [-m] [-c] [--cc] [-s] [-v] [--pretty] [-t] [-r] [--root] " +"[] [] [...]\n" +" -r diff recursively\n" +" --root include the initial commit as diff against /dev/null\n" +COMMON_DIFF_OPTIONS_HELP; + +int cmd_diff_tree(int argc, const char **argv, char **envp) +{ + int nr_sha1; + char line[1000]; + struct object *tree1, *tree2; + static struct rev_info *opt = &log_tree_opt; + struct object_list *list; + int read_stdin = 0; + + git_config(git_diff_config); + nr_sha1 = 0; + init_revisions(opt); + opt->abbrev = 0; + opt->diff = 1; + argc = setup_revisions(argc, argv, opt, NULL); + + while (--argc > 0) { + const char *arg = *++argv; + + if (!strcmp(arg, "--stdin")) { + read_stdin = 1; + continue; + } + usage(diff_tree_usage); + } + + /* + * NOTE! "setup_revisions()" will have inserted the revisions + * it parsed in reverse order. So if you do + * + * git-diff-tree a b + * + * the commit list will be "b" -> "a" -> NULL, so we reverse + * the order of the objects if the first one is not marked + * UNINTERESTING. + */ + nr_sha1 = 0; + list = opt->pending_objects; + if (list) { + nr_sha1++; + tree1 = list->item; + list = list->next; + if (list) { + nr_sha1++; + tree2 = tree1; + tree1 = list->item; + if (list->next) + usage(diff_tree_usage); + /* Switch them around if the second one was uninteresting.. */ + if (tree2->flags & UNINTERESTING) { + struct object *tmp = tree2; + tree2 = tree1; + tree1 = tmp; + } + } + } + + switch (nr_sha1) { + case 0: + if (!read_stdin) + usage(diff_tree_usage); + break; + case 1: + diff_tree_commit_sha1(tree1->sha1); + break; + case 2: + diff_tree_sha1(tree1->sha1, + tree2->sha1, + "", &opt->diffopt); + log_tree_diff_flush(opt); + break; + } + + if (!read_stdin) + return 0; + + if (opt->diffopt.detect_rename) + opt->diffopt.setup |= (DIFF_SETUP_USE_SIZE_CACHE | + DIFF_SETUP_USE_CACHE); + while (fgets(line, sizeof(line), stdin)) + if (line[0] == '\n') + fflush(stdout); + else + diff_tree_stdin(line); + + return 0; +} diff --git a/builtin.h b/builtin.h index 01882ec..7620984 100644 --- a/builtin.h +++ b/builtin.h @@ -34,5 +34,10 @@ extern int cmd_read_tree(int argc, const char **argv, char **envp); extern int cmd_commit_tree(int argc, const char **argv, char **envp); extern int cmd_apply(int argc, const char **argv, char **envp); extern int cmd_show_branch(int argc, const char **argv, char **envp); +extern int cmd_diff_files(int argc, const char **argv, char **envp); +extern int cmd_diff_index(int argc, const char **argv, char **envp); +extern int cmd_diff_stages(int argc, const char **argv, char **envp); +extern int cmd_diff_tree(int argc, const char **argv, char **envp); + #endif diff --git a/diff-files.c b/diff-files.c deleted file mode 100644 index b9d193d..0000000 --- a/diff-files.c +++ /dev/null @@ -1,54 +0,0 @@ -/* - * GIT - The information manager from hell - * - * Copyright (C) Linus Torvalds, 2005 - */ -#include "cache.h" -#include "diff.h" -#include "commit.h" -#include "revision.h" - -static const char diff_files_usage[] = -"git-diff-files [-q] [-0/-1/2/3 |-c|--cc] [] [...]" -COMMON_DIFF_OPTIONS_HELP; - -int main(int argc, const char **argv) -{ - struct rev_info rev; - int silent = 0; - - git_config(git_diff_config); - init_revisions(&rev); - rev.abbrev = 0; - - argc = setup_revisions(argc, argv, &rev, NULL); - while (1 < argc && argv[1][0] == '-') { - if (!strcmp(argv[1], "--base")) - rev.max_count = 1; - else if (!strcmp(argv[1], "--ours")) - rev.max_count = 2; - else if (!strcmp(argv[1], "--theirs")) - rev.max_count = 3; - else if (!strcmp(argv[1], "-q")) - silent = 1; - else - usage(diff_files_usage); - argv++; argc--; - } - /* - * Make sure there are NO revision (i.e. pending object) parameter, - * rev.max_count is reasonable (0 <= n <= 3), - * there is no other revision filtering parameters. - */ - if (rev.pending_objects || - rev.min_age != -1 || rev.max_age != -1) - usage(diff_files_usage); - /* - * Backward compatibility wart - "diff-files -s" used to - * defeat the common diff option "-s" which asked for - * DIFF_FORMAT_NO_OUTPUT. - */ - if (rev.diffopt.output_format == DIFF_FORMAT_NO_OUTPUT) - rev.diffopt.output_format = DIFF_FORMAT_RAW; - return run_diff_files(&rev, silent); -} diff --git a/diff-index.c b/diff-index.c deleted file mode 100644 index 8c9f601..0000000 --- a/diff-index.c +++ /dev/null @@ -1,38 +0,0 @@ -#include "cache.h" -#include "diff.h" -#include "commit.h" -#include "revision.h" - -static const char diff_cache_usage[] = -"git-diff-index [-m] [--cached] " -"[] [...]" -COMMON_DIFF_OPTIONS_HELP; - -int main(int argc, const char **argv) -{ - struct rev_info rev; - int cached = 0; - int i; - - git_config(git_diff_config); - init_revisions(&rev); - rev.abbrev = 0; - - argc = setup_revisions(argc, argv, &rev, NULL); - for (i = 1; i < argc; i++) { - const char *arg = argv[i]; - - if (!strcmp(arg, "--cached")) - cached = 1; - else - usage(diff_cache_usage); - } - /* - * Make sure there is one revision (i.e. pending object), - * and there is no revision filtering parameters. - */ - if (!rev.pending_objects || rev.pending_objects->next || - rev.max_count != -1 || rev.min_age != -1 || rev.max_age != -1) - usage(diff_cache_usage); - return run_diff_index(&rev, cached); -} diff --git a/diff-stages.c b/diff-stages.c deleted file mode 100644 index dcd20e7..0000000 --- a/diff-stages.c +++ /dev/null @@ -1,104 +0,0 @@ -/* - * Copyright (c) 2005 Junio C Hamano - */ - -#include "cache.h" -#include "diff.h" - -static struct diff_options diff_options; - -static const char diff_stages_usage[] = -"git-diff-stages [] [...]" -COMMON_DIFF_OPTIONS_HELP; - -static void diff_stages(int stage1, int stage2, const char **pathspec) -{ - int i = 0; - while (i < active_nr) { - struct cache_entry *ce, *stages[4] = { NULL, }; - struct cache_entry *one, *two; - const char *name; - int len, skip; - - ce = active_cache[i]; - skip = !ce_path_match(ce, pathspec); - len = ce_namelen(ce); - name = ce->name; - for (;;) { - int stage = ce_stage(ce); - stages[stage] = ce; - if (active_nr <= ++i) - break; - ce = active_cache[i]; - if (ce_namelen(ce) != len || - memcmp(name, ce->name, len)) - break; - } - one = stages[stage1]; - two = stages[stage2]; - - if (skip || (!one && !two)) - continue; - if (!one) - diff_addremove(&diff_options, '+', ntohl(two->ce_mode), - two->sha1, name, NULL); - else if (!two) - diff_addremove(&diff_options, '-', ntohl(one->ce_mode), - one->sha1, name, NULL); - else if (memcmp(one->sha1, two->sha1, 20) || - (one->ce_mode != two->ce_mode) || - diff_options.find_copies_harder) - diff_change(&diff_options, - ntohl(one->ce_mode), ntohl(two->ce_mode), - one->sha1, two->sha1, name, NULL); - } -} - -int main(int ac, const char **av) -{ - int stage1, stage2; - const char *prefix = setup_git_directory(); - const char **pathspec = NULL; - - git_config(git_diff_config); - read_cache(); - diff_setup(&diff_options); - while (1 < ac && av[1][0] == '-') { - const char *arg = av[1]; - if (!strcmp(arg, "-r")) - ; /* as usual */ - else { - int diff_opt_cnt; - diff_opt_cnt = diff_opt_parse(&diff_options, - av+1, ac-1); - if (diff_opt_cnt < 0) - usage(diff_stages_usage); - else if (diff_opt_cnt) { - av += diff_opt_cnt; - ac -= diff_opt_cnt; - continue; - } - else - usage(diff_stages_usage); - } - ac--; av++; - } - - if (ac < 3 || - sscanf(av[1], "%d", &stage1) != 1 || - ! (0 <= stage1 && stage1 <= 3) || - sscanf(av[2], "%d", &stage2) != 1 || - ! (0 <= stage2 && stage2 <= 3)) - usage(diff_stages_usage); - - av += 3; /* The rest from av[0] are for paths restriction. */ - pathspec = get_pathspec(prefix, av); - - if (diff_setup_done(&diff_options) < 0) - usage(diff_stages_usage); - - diff_stages(stage1, stage2, pathspec); - diffcore_std(&diff_options); - diff_flush(&diff_options); - return 0; -} diff --git a/diff-tree.c b/diff-tree.c deleted file mode 100644 index 69bb74b..0000000 --- a/diff-tree.c +++ /dev/null @@ -1,147 +0,0 @@ -#include "cache.h" -#include "diff.h" -#include "commit.h" -#include "log-tree.h" - -static struct rev_info log_tree_opt; - -static int diff_tree_commit_sha1(const unsigned char *sha1) -{ - struct commit *commit = lookup_commit_reference(sha1); - if (!commit) - return -1; - return log_tree_commit(&log_tree_opt, commit); -} - -static int diff_tree_stdin(char *line) -{ - int len = strlen(line); - unsigned char sha1[20]; - struct commit *commit; - - if (!len || line[len-1] != '\n') - return -1; - line[len-1] = 0; - if (get_sha1_hex(line, sha1)) - return -1; - commit = lookup_commit(sha1); - if (!commit || parse_commit(commit)) - return -1; - if (isspace(line[40]) && !get_sha1_hex(line+41, sha1)) { - /* Graft the fake parents locally to the commit */ - int pos = 41; - struct commit_list **pptr, *parents; - - /* Free the real parent list */ - for (parents = commit->parents; parents; ) { - struct commit_list *tmp = parents->next; - free(parents); - parents = tmp; - } - commit->parents = NULL; - pptr = &(commit->parents); - while (line[pos] && !get_sha1_hex(line + pos, sha1)) { - struct commit *parent = lookup_commit(sha1); - if (parent) { - pptr = &commit_list_insert(parent, pptr)->next; - } - pos += 41; - } - } - return log_tree_commit(&log_tree_opt, commit); -} - -static const char diff_tree_usage[] = -"git-diff-tree [--stdin] [-m] [-c] [--cc] [-s] [-v] [--pretty] [-t] [-r] [--root] " -"[] [] [...]\n" -" -r diff recursively\n" -" --root include the initial commit as diff against /dev/null\n" -COMMON_DIFF_OPTIONS_HELP; - -int main(int argc, const char **argv) -{ - int nr_sha1; - char line[1000]; - struct object *tree1, *tree2; - static struct rev_info *opt = &log_tree_opt; - struct object_list *list; - int read_stdin = 0; - - git_config(git_diff_config); - nr_sha1 = 0; - init_revisions(opt); - opt->abbrev = 0; - opt->diff = 1; - argc = setup_revisions(argc, argv, opt, NULL); - - while (--argc > 0) { - const char *arg = *++argv; - - if (!strcmp(arg, "--stdin")) { - read_stdin = 1; - continue; - } - usage(diff_tree_usage); - } - - /* - * NOTE! "setup_revisions()" will have inserted the revisions - * it parsed in reverse order. So if you do - * - * git-diff-tree a b - * - * the commit list will be "b" -> "a" -> NULL, so we reverse - * the order of the objects if the first one is not marked - * UNINTERESTING. - */ - nr_sha1 = 0; - list = opt->pending_objects; - if (list) { - nr_sha1++; - tree1 = list->item; - list = list->next; - if (list) { - nr_sha1++; - tree2 = tree1; - tree1 = list->item; - if (list->next) - usage(diff_tree_usage); - /* Switch them around if the second one was uninteresting.. */ - if (tree2->flags & UNINTERESTING) { - struct object *tmp = tree2; - tree2 = tree1; - tree1 = tmp; - } - } - } - - switch (nr_sha1) { - case 0: - if (!read_stdin) - usage(diff_tree_usage); - break; - case 1: - diff_tree_commit_sha1(tree1->sha1); - break; - case 2: - diff_tree_sha1(tree1->sha1, - tree2->sha1, - "", &opt->diffopt); - log_tree_diff_flush(opt); - break; - } - - if (!read_stdin) - return 0; - - if (opt->diffopt.detect_rename) - opt->diffopt.setup |= (DIFF_SETUP_USE_SIZE_CACHE | - DIFF_SETUP_USE_CACHE); - while (fgets(line, sizeof(line), stdin)) - if (line[0] == '\n') - fflush(stdout); - else - diff_tree_stdin(line); - - return 0; -} diff --git a/git.c b/git.c index d29505c..8749748 100644 --- a/git.c +++ b/git.c @@ -59,7 +59,11 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "read-tree", cmd_read_tree }, { "commit-tree", cmd_commit_tree }, { "apply", cmd_apply }, - { "show-branch", cmd_show_branch } + { "show-branch", cmd_show_branch }, + { "diff-files", cmd_diff_files }, + { "diff-index", cmd_diff_index }, + { "diff-stages", cmd_diff_stages }, + { "diff-tree", cmd_diff_tree } }; int i; -- cgit v0.10.2-6-g49f6