From ffe7c28f315589e2ba44c1ef27eb4564646a03ef Mon Sep 17 00:00:00 2001 From: Kirill Date: Tue, 2 Sep 2008 21:36:49 -0400 Subject: [PATCH] Bring mingw_spawn* into Cheetah The relative paths from one file to another was preserved to reduce modifications to the "borrowed" files. --- compat/mingw.c | 1042 +++++++++++++++++++++++ compat/mingw.h | 238 ++++++ compat/mmap.c | 42 + compat/pread.c | 18 + compat/strlcpy.c | 13 + compat/winansi.c | 345 ++++++++ date.c | 860 +++++++++++++++++++ hash.h | 43 + sha1_file.c | 2479 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ strbuf.c | 310 +++++++ strbuf.h | 128 +++ usage.c | 96 +++ wrapper.c | 198 +++++ 13 files changed, 5812 insertions(+) create mode 100644 compat/mingw.c create mode 100644 compat/mingw.h create mode 100644 compat/mmap.c create mode 100644 compat/pread.c create mode 100644 compat/strlcpy.c create mode 100644 compat/winansi.c create mode 100644 date.c create mode 100644 hash.h create mode 100644 sha1_file.c create mode 100644 strbuf.c create mode 100644 strbuf.h create mode 100644 usage.c create mode 100644 wrapper.c diff --git a/compat/mingw.c b/compat/mingw.c new file mode 100644 index 0000000..4cdc5f6 --- /dev/null +++ b/compat/mingw.c @@ -0,0 +1,1042 @@ +#include "../git-compat-util.h" +#include "../strbuf.h" + +unsigned int _CRT_fmode = _O_BINARY; + +#undef open +int mingw_open (const char *filename, int oflags, ...) +{ + va_list args; + unsigned mode; + va_start(args, oflags); + mode = va_arg(args, int); + va_end(args); + + if (!strcmp(filename, "/dev/null")) + filename = "nul"; + int fd = open(filename, oflags, mode); + if (fd < 0 && (oflags & O_CREAT) && errno == EACCES) { + DWORD attrs = GetFileAttributes(filename); + if (attrs != INVALID_FILE_ATTRIBUTES && (attrs & FILE_ATTRIBUTE_DIRECTORY)) + errno = EISDIR; + } + return fd; +} + +static inline time_t filetime_to_time_t(const FILETIME *ft) +{ + long long winTime = ((long long)ft->dwHighDateTime << 32) + ft->dwLowDateTime; + winTime -= 116444736000000000LL; /* Windows to Unix Epoch conversion */ + winTime /= 10000000; /* Nano to seconds resolution */ + return (time_t)winTime; +} + +static inline size_t size_to_blocks(size_t s) +{ + return (s+511)/512; +} + +extern int _getdrive( void ); +/* We keep the do_lstat code in a separate function to avoid recursion. + * When a path ends with a slash, the stat will fail with ENOENT. In + * this case, we strip the trailing slashes and stat again. + */ +static int do_lstat(const char *file_name, struct stat *buf) +{ + WIN32_FILE_ATTRIBUTE_DATA fdata; + + if (GetFileAttributesExA(file_name, GetFileExInfoStandard, &fdata)) { + int fMode = S_IREAD; + if (fdata.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY) + fMode |= S_IFDIR; + else + fMode |= S_IFREG; + if (!(fdata.dwFileAttributes & FILE_ATTRIBUTE_READONLY)) + fMode |= S_IWRITE; + + buf->st_ino = 0; + buf->st_gid = 0; + buf->st_uid = 0; + buf->st_mode = fMode; + buf->st_size = fdata.nFileSizeLow; /* Can't use nFileSizeHigh, since it's not a stat64 */ + buf->st_blocks = size_to_blocks(buf->st_size); + buf->st_dev = _getdrive() - 1; + buf->st_atime = filetime_to_time_t(&(fdata.ftLastAccessTime)); + buf->st_mtime = filetime_to_time_t(&(fdata.ftLastWriteTime)); + buf->st_ctime = filetime_to_time_t(&(fdata.ftCreationTime)); + errno = 0; + return 0; + } + + switch (GetLastError()) { + case ERROR_ACCESS_DENIED: + case ERROR_SHARING_VIOLATION: + case ERROR_LOCK_VIOLATION: + case ERROR_SHARING_BUFFER_EXCEEDED: + errno = EACCES; + break; + case ERROR_BUFFER_OVERFLOW: + errno = ENAMETOOLONG; + break; + case ERROR_NOT_ENOUGH_MEMORY: + errno = ENOMEM; + break; + default: + errno = ENOENT; + break; + } + return -1; +} + +/* We provide our own lstat/fstat functions, since the provided + * lstat/fstat functions are so slow. These stat functions are + * tailored for Git's usage (read: fast), and are not meant to be + * complete. Note that Git stat()s are redirected to mingw_lstat() + * too, since Windows doesn't really handle symlinks that well. + */ +int mingw_lstat(const char *file_name, struct mingw_stat *buf) +{ + int namelen; + static char alt_name[PATH_MAX]; + + if (!do_lstat(file_name, buf)) + return 0; + + /* if file_name ended in a '/', Windows returned ENOENT; + * try again without trailing slashes + */ + if (errno != ENOENT) + return -1; + + namelen = strlen(file_name); + if (namelen && file_name[namelen-1] != '/') + return -1; + while (namelen && file_name[namelen-1] == '/') + --namelen; + if (!namelen || namelen >= PATH_MAX) + return -1; + + memcpy(alt_name, file_name, namelen); + alt_name[namelen] = 0; + return do_lstat(alt_name, buf); +} + +#undef fstat +#undef stat +int mingw_fstat(int fd, struct mingw_stat *buf) +{ + HANDLE fh = (HANDLE)_get_osfhandle(fd); + BY_HANDLE_FILE_INFORMATION fdata; + + if (fh == INVALID_HANDLE_VALUE) { + errno = EBADF; + return -1; + } + /* direct non-file handles to MS's fstat() */ + if (GetFileType(fh) != FILE_TYPE_DISK) { + struct stat st; + if (fstat(fd, &st)) + return -1; + buf->st_ino = st.st_ino; + buf->st_gid = st.st_gid; + buf->st_uid = st.st_uid; + buf->st_mode = st.st_mode; + buf->st_size = st.st_size; + buf->st_blocks = size_to_blocks(buf->st_size); + buf->st_dev = st.st_dev; + buf->st_atime = st.st_atime; + buf->st_mtime = st.st_mtime; + buf->st_ctime = st.st_ctime; + return 0; + } + + if (GetFileInformationByHandle(fh, &fdata)) { + int fMode = S_IREAD; + if (fdata.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY) + fMode |= S_IFDIR; + else + fMode |= S_IFREG; + if (!(fdata.dwFileAttributes & FILE_ATTRIBUTE_READONLY)) + fMode |= S_IWRITE; + + buf->st_ino = 0; + buf->st_gid = 0; + buf->st_uid = 0; + buf->st_mode = fMode; + buf->st_size = fdata.nFileSizeLow; /* Can't use nFileSizeHigh, since it's not a stat64 */ + buf->st_blocks = size_to_blocks(buf->st_size); + buf->st_dev = _getdrive() - 1; + buf->st_atime = filetime_to_time_t(&(fdata.ftLastAccessTime)); + buf->st_mtime = filetime_to_time_t(&(fdata.ftLastWriteTime)); + buf->st_ctime = filetime_to_time_t(&(fdata.ftCreationTime)); + return 0; + } + errno = EBADF; + return -1; +} + +static inline void time_t_to_filetime(time_t t, FILETIME *ft) +{ + long long winTime = t * 10000000LL + 116444736000000000LL; + ft->dwLowDateTime = winTime; + ft->dwHighDateTime = winTime >> 32; +} + +int mingw_utime (const char *file_name, const struct utimbuf *times) +{ + FILETIME mft, aft; + int fh, rc; + + /* must have write permission */ + if ((fh = open(file_name, O_RDWR | O_BINARY)) < 0) + return -1; + + time_t_to_filetime(times->modtime, &mft); + time_t_to_filetime(times->actime, &aft); + if (!SetFileTime((HANDLE)_get_osfhandle(fh), NULL, &aft, &mft)) { + errno = EINVAL; + rc = -1; + } else + rc = 0; + close(fh); + return rc; +} + +unsigned int sleep (unsigned int seconds) +{ + Sleep(seconds*1000); + return 0; +} + +int mkstemp(char *template) +{ + char *filename = mktemp(template); + if (filename == NULL) + return -1; + return open(filename, O_RDWR | O_CREAT, 0600); +} + +int gettimeofday(struct timeval *tv, void *tz) +{ + SYSTEMTIME st; + struct tm tm; + GetSystemTime(&st); + tm.tm_year = st.wYear-1900; + tm.tm_mon = st.wMonth-1; + tm.tm_mday = st.wDay; + tm.tm_hour = st.wHour; + tm.tm_min = st.wMinute; + tm.tm_sec = st.wSecond; + tv->tv_sec = tm_to_time_t(&tm); + if (tv->tv_sec < 0) + return -1; + tv->tv_usec = st.wMilliseconds*1000; + return 0; +} + +int pipe(int filedes[2]) +{ + int fd; + HANDLE h[2], parent; + + if (_pipe(filedes, 8192, 0) < 0) + return -1; + + parent = GetCurrentProcess(); + + if (!DuplicateHandle (parent, (HANDLE)_get_osfhandle(filedes[0]), + parent, &h[0], 0, FALSE, DUPLICATE_SAME_ACCESS)) { + close(filedes[0]); + close(filedes[1]); + return -1; + } + if (!DuplicateHandle (parent, (HANDLE)_get_osfhandle(filedes[1]), + parent, &h[1], 0, FALSE, DUPLICATE_SAME_ACCESS)) { + close(filedes[0]); + close(filedes[1]); + CloseHandle(h[0]); + return -1; + } + fd = _open_osfhandle((int)h[0], O_NOINHERIT); + if (fd < 0) { + close(filedes[0]); + close(filedes[1]); + CloseHandle(h[0]); + CloseHandle(h[1]); + return -1; + } + close(filedes[0]); + filedes[0] = fd; + fd = _open_osfhandle((int)h[1], O_NOINHERIT); + if (fd < 0) { + close(filedes[0]); + close(filedes[1]); + CloseHandle(h[1]); + return -1; + } + close(filedes[1]); + filedes[1] = fd; + return 0; +} + +int poll(struct pollfd *ufds, unsigned int nfds, int timeout) +{ + int i, pending; + + if (timeout != -1) + return errno = EINVAL, error("poll timeout not supported"); + + /* When there is only one fd to wait for, then we pretend that + * input is available and let the actual wait happen when the + * caller invokes read(). + */ + if (nfds == 1) { + if (!(ufds[0].events & POLLIN)) + return errno = EINVAL, error("POLLIN not set"); + ufds[0].revents = POLLIN; + return 0; + } + +repeat: + pending = 0; + for (i = 0; i < nfds; i++) { + DWORD avail = 0; + HANDLE h = (HANDLE) _get_osfhandle(ufds[i].fd); + if (h == INVALID_HANDLE_VALUE) + return -1; /* errno was set */ + + if (!(ufds[i].events & POLLIN)) + return errno = EINVAL, error("POLLIN not set"); + + /* this emulation works only for pipes */ + if (!PeekNamedPipe(h, NULL, 0, NULL, &avail, NULL)) { + int err = GetLastError(); + if (err == ERROR_BROKEN_PIPE) { + ufds[i].revents = POLLHUP; + pending++; + } else { + errno = EINVAL; + return error("PeekNamedPipe failed," + " GetLastError: %u", err); + } + } else if (avail) { + ufds[i].revents = POLLIN; + pending++; + } else + ufds[i].revents = 0; + } + if (!pending) { + /* The only times that we spin here is when the process + * that is connected through the pipes is waiting for + * its own input data to become available. But since + * the process (pack-objects) is itself CPU intensive, + * it will happily pick up the time slice that we are + * relinguishing here. + */ + Sleep(0); + goto repeat; + } + return 0; +} + +struct tm *gmtime_r(const time_t *timep, struct tm *result) +{ + /* gmtime() in MSVCRT.DLL is thread-safe, but not reentrant */ + memcpy(result, gmtime(timep), sizeof(struct tm)); + return result; +} + +struct tm *localtime_r(const time_t *timep, struct tm *result) +{ + /* localtime() in MSVCRT.DLL is thread-safe, but not reentrant */ + memcpy(result, localtime(timep), sizeof(struct tm)); + return result; +} + +#undef getcwd +char *mingw_getcwd(char *pointer, int len) +{ + int i; + char *ret = getcwd(pointer, len); + if (!ret) + return ret; + for (i = 0; pointer[i]; i++) + if (pointer[i] == '\\') + pointer[i] = '/'; + return ret; +} + +#undef getenv +char *mingw_getenv(const char *name) +{ + char *result = getenv(name); + if (!result && !strcmp(name, "TMPDIR")) { + /* on Windows it is TMP and TEMP */ + result = getenv("TMP"); + if (!result) + result = getenv("TEMP"); + } + return result; +} + +/* + * See http://msdn2.microsoft.com/en-us/library/17w5ykft(vs.71).aspx + * (Parsing C++ Command-Line Arguments) + */ +static const char *quote_arg(const char *arg) +{ + /* count chars to quote */ + int len = 0, n = 0; + int force_quotes = 0; + char *q, *d; + const char *p = arg; + if (!*p) force_quotes = 1; + while (*p) { + if (isspace(*p) || *p == '*' || *p == '?' || *p == '{') + force_quotes = 1; + else if (*p == '"') + n++; + else if (*p == '\\') { + int count = 0; + while (*p == '\\') { + count++; + p++; + len++; + } + if (*p == '"') + n += count*2 + 1; + continue; + } + len++; + p++; + } + if (!force_quotes && n == 0) + return arg; + + /* insert \ where necessary */ + d = q = xmalloc(len+n+3); + *d++ = '"'; + while (*arg) { + if (*arg == '"') + *d++ = '\\'; + else if (*arg == '\\') { + int count = 0; + while (*arg == '\\') { + count++; + *d++ = *arg++; + } + if (*arg == '"') { + while (count-- > 0) + *d++ = '\\'; + *d++ = '\\'; + } + } + *d++ = *arg++; + } + *d++ = '"'; + *d++ = 0; + return q; +} + +static const char *parse_interpreter(const char *cmd) +{ + static char buf[100]; + char *p, *opt; + int n, fd; + + /* don't even try a .exe */ + n = strlen(cmd); + if (n >= 4 && !strcasecmp(cmd+n-4, ".exe")) + return NULL; + + fd = open(cmd, O_RDONLY); + if (fd < 0) + return NULL; + n = read(fd, buf, sizeof(buf)-1); + close(fd); + if (n < 4) /* at least '#!/x' and not error */ + return NULL; + + if (buf[0] != '#' || buf[1] != '!') + return NULL; + buf[n] = '\0'; + p = buf + strcspn(buf, "\r\n"); + if (!*p) + return NULL; + + *p = '\0'; + if (!(p = strrchr(buf+2, '/')) && !(p = strrchr(buf+2, '\\'))) + return NULL; + /* strip options */ + if ((opt = strchr(p+1, ' '))) + *opt = '\0'; + return p+1; +} + +/* + * Splits the PATH into parts. + */ +static char **get_path_split(void) +{ + char *p, **path, *envpath = getenv("PATH"); + int i, n = 0; + + if (!envpath || !*envpath) + return NULL; + + envpath = xstrdup(envpath); + p = envpath; + while (p) { + char *dir = p; + p = strchr(p, ';'); + if (p) *p++ = '\0'; + if (*dir) { /* not earlier, catches series of ; */ + ++n; + } + } + if (!n) + return NULL; + + path = xmalloc((n+1)*sizeof(char*)); + p = envpath; + i = 0; + do { + if (*p) + path[i++] = xstrdup(p); + p = p+strlen(p)+1; + } while (i < n); + path[i] = NULL; + + free(envpath); + + return path; +} + +static void free_path_split(char **path) +{ + if (!path) + return; + + char **p = path; + while (*p) + free(*p++); + free(path); +} + +/* + * exe_only means that we only want to detect .exe files, but not scripts + * (which do not have an extension) + */ +static char *lookup_prog(const char *dir, const char *cmd, int isexe, int exe_only) +{ + char path[MAX_PATH]; + snprintf(path, sizeof(path), "%s/%s.exe", dir, cmd); + + if (!isexe && access(path, F_OK) == 0) + return xstrdup(path); + path[strlen(path)-4] = '\0'; + if ((!exe_only || isexe) && access(path, F_OK) == 0) + if (!(GetFileAttributes(path) & FILE_ATTRIBUTE_DIRECTORY)) + return xstrdup(path); + return NULL; +} + +/* + * Determines the absolute path of cmd using the the split path in path. + * If cmd contains a slash or backslash, no lookup is performed. + */ +static char *path_lookup(const char *cmd, char **path, int exe_only) +{ + char *prog = NULL; + int len = strlen(cmd); + int isexe = len >= 4 && !strcasecmp(cmd+len-4, ".exe"); + + if (strchr(cmd, '/') || strchr(cmd, '\\')) + prog = xstrdup(cmd); + + while (!prog && *path) + prog = lookup_prog(*path++, cmd, isexe, exe_only); + + return prog; +} + +static int env_compare(const void *a, const void *b) +{ + char *const *ea = a; + char *const *eb = b; + return strcasecmp(*ea, *eb); +} + +static pid_t mingw_spawnve(const char *cmd, const char **argv, char **env, + int prepend_cmd) +{ + STARTUPINFO si; + PROCESS_INFORMATION pi; + struct strbuf envblk, args; + unsigned flags; + BOOL ret; + + /* Determine whether or not we are associated to a console */ + HANDLE cons = CreateFile("CONOUT$", GENERIC_WRITE, + FILE_SHARE_WRITE, NULL, OPEN_EXISTING, + FILE_ATTRIBUTE_NORMAL, NULL); + if (cons == INVALID_HANDLE_VALUE) { + /* There is no console associated with this process. + * Since the child is a console process, Windows + * would normally create a console window. But + * since we'll be redirecting std streams, we do + * not need the console. + */ + flags = CREATE_NO_WINDOW; + } else { + /* There is already a console. If we specified + * CREATE_NO_WINDOW here, too, Windows would + * disassociate the child from the console. + * Go figure! + */ + flags = 0; + CloseHandle(cons); + } + memset(&si, 0, sizeof(si)); + si.cb = sizeof(si); + si.dwFlags = STARTF_USESTDHANDLES; + si.hStdInput = (HANDLE) _get_osfhandle(0); + si.hStdOutput = (HANDLE) _get_osfhandle(1); + si.hStdError = (HANDLE) _get_osfhandle(2); + + /* concatenate argv, quoting args as we go */ + strbuf_init(&args, 0); + if (prepend_cmd) { + char *quoted = (char *)quote_arg(cmd); + strbuf_addstr(&args, quoted); + if (quoted != cmd) + free(quoted); + } + for (; *argv; argv++) { + char *quoted = (char *)quote_arg(*argv); + if (*args.buf) + strbuf_addch(&args, ' '); + strbuf_addstr(&args, quoted); + if (quoted != *argv) + free(quoted); + } + + if (env) { + int count = 0; + char **e, **sorted_env; + + for (e = env; *e; e++) + count++; + + /* environment must be sorted */ + sorted_env = xmalloc(sizeof(*sorted_env) * (count + 1)); + memcpy(sorted_env, env, sizeof(*sorted_env) * (count + 1)); + qsort(sorted_env, count, sizeof(*sorted_env), env_compare); + + strbuf_init(&envblk, 0); + for (e = sorted_env; *e; e++) { + strbuf_addstr(&envblk, *e); + strbuf_addch(&envblk, '\0'); + } + free(sorted_env); + } + + memset(&pi, 0, sizeof(pi)); + ret = CreateProcess(cmd, args.buf, NULL, NULL, TRUE, flags, + env ? envblk.buf : NULL, NULL, &si, &pi); + + if (env) + strbuf_release(&envblk); + strbuf_release(&args); + + if (!ret) { + errno = ENOENT; + return -1; + } + CloseHandle(pi.hThread); + return (pid_t)pi.hProcess; +} + +pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env) +{ + pid_t pid; + char **path = get_path_split(); + char *prog = path_lookup(cmd, path, 0); + + if (!prog) { + errno = ENOENT; + pid = -1; + } + else { + const char *interpr = parse_interpreter(prog); + + if (interpr) { + const char *argv0 = argv[0]; + char *iprog = path_lookup(interpr, path, 1); + argv[0] = prog; + if (!iprog) { + errno = ENOENT; + pid = -1; + } + else { + pid = mingw_spawnve(iprog, argv, env, 1); + free(iprog); + } + argv[0] = argv0; + } + else + pid = mingw_spawnve(prog, argv, env, 0); + free(prog); + } + free_path_split(path); + return pid; +} + +static int try_shell_exec(const char *cmd, char *const *argv, char **env) +{ + const char *interpr = parse_interpreter(cmd); + char **path; + char *prog; + int pid = 0; + + if (!interpr) + return 0; + path = get_path_split(); + prog = path_lookup(interpr, path, 1); + if (prog) { + int argc = 0; + const char **argv2; + while (argv[argc]) argc++; + argv2 = xmalloc(sizeof(*argv) * (argc+1)); + argv2[0] = (char *)cmd; /* full path to the script file */ + memcpy(&argv2[1], &argv[1], sizeof(*argv) * argc); + pid = mingw_spawnve(prog, argv2, env, 1); + if (pid >= 0) { + int status; + if (waitpid(pid, &status, 0) < 0) + status = 255; + exit(status); + } + pid = 1; /* indicate that we tried but failed */ + free(prog); + free(argv2); + } + free_path_split(path); + return pid; +} + +static void mingw_execve(const char *cmd, char *const *argv, char *const *env) +{ + /* check if git_command is a shell script */ + if (!try_shell_exec(cmd, argv, (char **)env)) { + int pid, status; + + pid = mingw_spawnve(cmd, (const char **)argv, (char **)env, 0); + if (pid < 0) + return; + if (waitpid(pid, &status, 0) < 0) + status = 255; + exit(status); + } +} + +void mingw_execvp(const char *cmd, char *const *argv) +{ + char **path = get_path_split(); + char *prog = path_lookup(cmd, path, 0); + + if (prog) { + mingw_execve(prog, argv, environ); + free(prog); + } else + errno = ENOENT; + + free_path_split(path); +} + +char **copy_environ() +{ + char **env; + int i = 0; + while (environ[i]) + i++; + env = xmalloc((i+1)*sizeof(*env)); + for (i = 0; environ[i]; i++) + env[i] = xstrdup(environ[i]); + env[i] = NULL; + return env; +} + +void free_environ(char **env) +{ + int i; + for (i = 0; env[i]; i++) + free(env[i]); + free(env); +} + +static int lookup_env(char **env, const char *name, size_t nmln) +{ + int i; + + for (i = 0; env[i]; i++) { + if (0 == strncmp(env[i], name, nmln) + && '=' == env[i][nmln]) + /* matches */ + return i; + } + return -1; +} + +/* + * If name contains '=', then sets the variable, otherwise it unsets it + */ +char **env_setenv(char **env, const char *name) +{ + char *eq = strchrnul(name, '='); + int i = lookup_env(env, name, eq-name); + + if (i < 0) { + if (*eq) { + for (i = 0; env[i]; i++) + ; + env = xrealloc(env, (i+2)*sizeof(*env)); + env[i] = xstrdup(name); + env[i+1] = NULL; + } + } + else { + free(env[i]); + if (*eq) + env[i] = xstrdup(name); + else + for (; env[i]; i++) + env[i] = env[i+1]; + } + return env; +} + +/* this is the first function to call into WS_32; initialize it */ +#undef gethostbyname +struct hostent *mingw_gethostbyname(const char *host) +{ + WSADATA wsa; + + if (WSAStartup(MAKEWORD(2,2), &wsa)) + die("unable to initialize winsock subsystem, error %d", + WSAGetLastError()); + atexit((void(*)(void)) WSACleanup); + return gethostbyname(host); +} + +int mingw_socket(int domain, int type, int protocol) +{ + int sockfd; + SOCKET s = WSASocket(domain, type, protocol, NULL, 0, 0); + if (s == INVALID_SOCKET) { + /* + * WSAGetLastError() values are regular BSD error codes + * biased by WSABASEERR. + * However, strerror() does not know about networking + * specific errors, which are values beginning at 38 or so. + * Therefore, we choose to leave the biased error code + * in errno so that _if_ someone looks up the code somewhere, + * then it is at least the number that are usually listed. + */ + errno = WSAGetLastError(); + return -1; + } + /* convert into a file descriptor */ + if ((sockfd = _open_osfhandle(s, O_RDWR|O_BINARY)) < 0) { + closesocket(s); + return error("unable to make a socket file descriptor: %s", + strerror(errno)); + } + return sockfd; +} + +#undef connect +int mingw_connect(int sockfd, struct sockaddr *sa, size_t sz) +{ + SOCKET s = (SOCKET)_get_osfhandle(sockfd); + return connect(s, sa, sz); +} + +#undef rename +int mingw_rename(const char *pold, const char *pnew) +{ + /* + * Try native rename() first to get errno right. + * It is based on MoveFile(), which cannot overwrite existing files. + */ + if (!rename(pold, pnew)) + return 0; + if (errno != EEXIST) + return -1; + if (MoveFileEx(pold, pnew, MOVEFILE_REPLACE_EXISTING)) + return 0; + /* TODO: translate more errors */ + if (GetLastError() == ERROR_ACCESS_DENIED) { + DWORD attrs = GetFileAttributes(pnew); + if (attrs != INVALID_FILE_ATTRIBUTES && (attrs & FILE_ATTRIBUTE_DIRECTORY)) { + errno = EISDIR; + return -1; + } + } + errno = EACCES; + return -1; +} + +struct passwd *getpwuid(int uid) +{ + static char user_name[100]; + static struct passwd p; + + DWORD len = sizeof(user_name); + if (!GetUserName(user_name, &len)) + return NULL; + p.pw_name = user_name; + p.pw_gecos = "unknown"; + p.pw_dir = NULL; + return &p; +} + +static HANDLE timer_event; +static HANDLE timer_thread; +static int timer_interval; +static int one_shot; +static sig_handler_t timer_fn = SIG_DFL; + +/* The timer works like this: + * The thread, ticktack(), is a trivial routine that most of the time + * only waits to receive the signal to terminate. The main thread tells + * the thread to terminate by setting the timer_event to the signalled + * state. + * But ticktack() interrupts the wait state after the timer's interval + * length to call the signal handler. + */ + +static __stdcall unsigned ticktack(void *dummy) +{ + while (WaitForSingleObject(timer_event, timer_interval) == WAIT_TIMEOUT) { + if (timer_fn == SIG_DFL) + die("Alarm"); + if (timer_fn != SIG_IGN) + timer_fn(SIGALRM); + if (one_shot) + break; + } + return 0; +} + +static int start_timer_thread(void) +{ + timer_event = CreateEvent(NULL, FALSE, FALSE, NULL); + if (timer_event) { + timer_thread = (HANDLE) _beginthreadex(NULL, 0, ticktack, NULL, 0, NULL); + if (!timer_thread ) + return errno = ENOMEM, + error("cannot start timer thread"); + } else + return errno = ENOMEM, + error("cannot allocate resources for timer"); + return 0; +} + +static void stop_timer_thread(void) +{ + if (timer_event) + SetEvent(timer_event); /* tell thread to terminate */ + if (timer_thread) { + int rc = WaitForSingleObject(timer_thread, 1000); + if (rc == WAIT_TIMEOUT) + error("timer thread did not terminate timely"); + else if (rc != WAIT_OBJECT_0) + error("waiting for timer thread failed: %lu", + GetLastError()); + CloseHandle(timer_thread); + } + if (timer_event) + CloseHandle(timer_event); + timer_event = NULL; + timer_thread = NULL; +} + +static inline int is_timeval_eq(const struct timeval *i1, const struct timeval *i2) +{ + return i1->tv_sec == i2->tv_sec && i1->tv_usec == i2->tv_usec; +} + +int setitimer(int type, struct itimerval *in, struct itimerval *out) +{ + static const struct timeval zero; + static int atexit_done; + + if (out != NULL) + return errno = EINVAL, + error("setitimer param 3 != NULL not implemented"); + if (!is_timeval_eq(&in->it_interval, &zero) && + !is_timeval_eq(&in->it_interval, &in->it_value)) + return errno = EINVAL, + error("setitimer: it_interval must be zero or eq it_value"); + + if (timer_thread) + stop_timer_thread(); + + if (is_timeval_eq(&in->it_value, &zero) && + is_timeval_eq(&in->it_interval, &zero)) + return 0; + + timer_interval = in->it_value.tv_sec * 1000 + in->it_value.tv_usec / 1000; + one_shot = is_timeval_eq(&in->it_interval, &zero); + if (!atexit_done) { + atexit(stop_timer_thread); + atexit_done = 1; + } + return start_timer_thread(); +} + +int sigaction(int sig, struct sigaction *in, struct sigaction *out) +{ + if (sig != SIGALRM) + return errno = EINVAL, + error("sigaction only implemented for SIGALRM"); + if (out != NULL) + return errno = EINVAL, + error("sigaction: param 3 != NULL not implemented"); + + timer_fn = in->sa_handler; + return 0; +} + +#undef signal +sig_handler_t mingw_signal(int sig, sig_handler_t handler) +{ + if (sig != SIGALRM) + return signal(sig, handler); + sig_handler_t old = timer_fn; + timer_fn = handler; + return old; +} + +static const char *make_backslash_path(const char *path) +{ + static char buf[PATH_MAX + 1]; + char *c; + + if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) + die("Too long path: %.*s", 60, path); + + for (c = buf; *c; c++) { + if (*c == '/') + *c = '\\'; + } + return buf; +} + +void mingw_open_html(const char *unixpath) +{ + const char *htmlpath = make_backslash_path(unixpath); + printf("Launching default browser to display HTML ...\n"); + ShellExecute(NULL, "open", htmlpath, NULL, "\\", 0); +} diff --git a/compat/mingw.h b/compat/mingw.h new file mode 100644 index 0000000..a52e657 --- /dev/null +++ b/compat/mingw.h @@ -0,0 +1,238 @@ +#include + +/* + * things that are not available in header files + */ + +typedef int pid_t; +#define hstrerror strerror + +#define S_IFLNK 0120000 /* Symbolic link */ +#define S_ISLNK(x) (((x) & S_IFMT) == S_IFLNK) +#define S_ISSOCK(x) 0 +#define S_IRGRP 0 +#define S_IWGRP 0 +#define S_IXGRP 0 +#define S_ISGID 0 +#define S_IROTH 0 +#define S_IXOTH 0 + +#define WIFEXITED(x) ((unsigned)(x) < 259) /* STILL_ACTIVE */ +#define WEXITSTATUS(x) ((x) & 0xff) +#define WIFSIGNALED(x) ((unsigned)(x) > 259) + +#define SIGKILL 0 +#define SIGCHLD 0 +#define SIGPIPE 0 +#define SIGHUP 0 +#define SIGQUIT 0 +#define SIGALRM 100 + +#define F_GETFD 1 +#define F_SETFD 2 +#define FD_CLOEXEC 0x1 + +struct passwd { + char *pw_name; + char *pw_gecos; + char *pw_dir; +}; + +struct pollfd { + int fd; /* file descriptor */ + short events; /* requested events */ + short revents; /* returned events */ +}; +#define POLLIN 1 +#define POLLHUP 2 + +typedef void (__cdecl *sig_handler_t)(int); +struct sigaction { + sig_handler_t sa_handler; + unsigned sa_flags; +}; +#define sigemptyset(x) (void)0 +#define SA_RESTART 0 + +struct itimerval { + struct timeval it_value, it_interval; +}; +#define ITIMER_REAL 0 + +/* + * trivial stubs + */ + +static inline int readlink(const char *path, char *buf, size_t bufsiz) +{ errno = ENOSYS; return -1; } +static inline int symlink(const char *oldpath, const char *newpath) +{ errno = ENOSYS; return -1; } +static inline int link(const char *oldpath, const char *newpath) +{ errno = ENOSYS; return -1; } +static inline int fchmod(int fildes, mode_t mode) +{ errno = ENOSYS; return -1; } +static inline int fork(void) +{ errno = ENOSYS; return -1; } +static inline unsigned int alarm(unsigned int seconds) +{ return 0; } +static inline int fsync(int fd) +{ return 0; } +static inline int getppid(void) +{ return 1; } +static inline void sync(void) +{} +static inline int getuid() +{ return 1; } +static inline struct passwd *getpwnam(const char *name) +{ return NULL; } +static inline int fcntl(int fd, int cmd, long arg) +{ + if (cmd == F_GETFD || cmd == F_SETFD) + return 0; + errno = EINVAL; + return -1; +} + +/* + * simple adaptors + */ + +static inline int mingw_mkdir(const char *path, int mode) +{ + return mkdir(path); +} +#define mkdir mingw_mkdir + +static inline int mingw_unlink(const char *pathname) +{ + /* read-only files cannot be removed */ + chmod(pathname, 0666); + return unlink(pathname); +} +#define unlink mingw_unlink + +static inline int waitpid(pid_t pid, unsigned *status, unsigned options) +{ + if (options == 0) + return _cwait(status, pid, 0); + errno = EINVAL; + return -1; +} + +/* + * implementations of missing functions + */ + +int pipe(int filedes[2]); +unsigned int sleep (unsigned int seconds); +int mkstemp(char *template); +int gettimeofday(struct timeval *tv, void *tz); +int poll(struct pollfd *ufds, unsigned int nfds, int timeout); +struct tm *gmtime_r(const time_t *timep, struct tm *result); +struct tm *localtime_r(const time_t *timep, struct tm *result); +int getpagesize(void); /* defined in MinGW's libgcc.a */ +struct passwd *getpwuid(int uid); +int setitimer(int type, struct itimerval *in, struct itimerval *out); +int sigaction(int sig, struct sigaction *in, struct sigaction *out); + +/* + * replacements of existing functions + */ + +int mingw_open (const char *filename, int oflags, ...); +#define open mingw_open + +char *mingw_getcwd(char *pointer, int len); +#define getcwd mingw_getcwd + +char *mingw_getenv(const char *name); +#define getenv mingw_getenv + +struct hostent *mingw_gethostbyname(const char *host); +#define gethostbyname mingw_gethostbyname + +int mingw_socket(int domain, int type, int protocol); +#define socket mingw_socket + +int mingw_connect(int sockfd, struct sockaddr *sa, size_t sz); +#define connect mingw_connect + +int mingw_rename(const char*, const char*); +#define rename mingw_rename + +/* Use mingw_lstat() instead of lstat()/stat() and + * mingw_fstat() instead of fstat() on Windows. + * struct stat is redefined because it lacks the st_blocks member. + */ +struct mingw_stat { + unsigned st_mode; + time_t st_mtime, st_atime, st_ctime; + unsigned st_dev, st_ino, st_uid, st_gid; + size_t st_size; + size_t st_blocks; +}; +int mingw_lstat(const char *file_name, struct mingw_stat *buf); +int mingw_fstat(int fd, struct mingw_stat *buf); +#define fstat mingw_fstat +#define lstat mingw_lstat +#define stat mingw_stat +static inline int mingw_stat(const char *file_name, struct mingw_stat *buf) +{ return mingw_lstat(file_name, buf); } + +int mingw_utime(const char *file_name, const struct utimbuf *times); +#define utime mingw_utime + +pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env); +void mingw_execvp(const char *cmd, char *const *argv); +#define execvp mingw_execvp + +static inline unsigned int git_ntohl(unsigned int x) +{ return (unsigned int)ntohl(x); } +#define ntohl git_ntohl + +sig_handler_t mingw_signal(int sig, sig_handler_t handler); +#define signal mingw_signal + +/* + * ANSI emulation wrappers + */ + +int winansi_fputs(const char *str, FILE *stream); +int winansi_printf(const char *format, ...) __attribute__((format (printf, 1, 2))); +int winansi_fprintf(FILE *stream, const char *format, ...) __attribute__((format (printf, 2, 3))); +#define fputs winansi_fputs +#define printf(...) winansi_printf(__VA_ARGS__) +#define fprintf(...) winansi_fprintf(__VA_ARGS__) + +/* + * git specific compatibility + */ + +#define has_dos_drive_prefix(path) (isalpha(*(path)) && (path)[1] == ':') +#define is_dir_sep(c) ((c) == '/' || (c) == '\\') +#define PATH_SEP ';' +#define PRIuMAX "I64u" + +void mingw_open_html(const char *path); +#define open_html mingw_open_html + +/* + * helpers + */ + +char **copy_environ(void); +void free_environ(char **env); +char **env_setenv(char **env, const char *name); + +/* + * A replacement of main() that ensures that argv[0] has a path + */ + +#define main(c,v) dummy_decl_mingw_main(); \ +static int mingw_main(); \ +int main(int argc, const char **argv) \ +{ \ + argv[0] = xstrdup(_pgmptr); \ + return mingw_main(argc, argv); \ +} \ +static int mingw_main(c,v) diff --git a/compat/mmap.c b/compat/mmap.c new file mode 100644 index 0000000..c9d46d1 --- /dev/null +++ b/compat/mmap.c @@ -0,0 +1,42 @@ +#include "../git-compat-util.h" + +void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t offset) +{ + size_t n = 0; + + if (start != NULL || !(flags & MAP_PRIVATE)) + die("Invalid usage of mmap when built with NO_MMAP"); + + start = xmalloc(length); + if (start == NULL) { + errno = ENOMEM; + return MAP_FAILED; + } + + while (n < length) { + ssize_t count = pread(fd, (char *)start + n, length - n, offset + n); + + if (count == 0) { + memset((char *)start+n, 0, length-n); + break; + } + + if (count < 0) { + if (errno == EAGAIN || errno == EINTR) + continue; + free(start); + errno = EACCES; + return MAP_FAILED; + } + + n += count; + } + + return start; +} + +int git_munmap(void *start, size_t length) +{ + free(start); + return 0; +} diff --git a/compat/pread.c b/compat/pread.c new file mode 100644 index 0000000..978cac4 --- /dev/null +++ b/compat/pread.c @@ -0,0 +1,18 @@ +#include "../git-compat-util.h" + +ssize_t git_pread(int fd, void *buf, size_t count, off_t offset) +{ + off_t current_offset; + ssize_t rc; + + current_offset = lseek(fd, 0, SEEK_CUR); + + if (lseek(fd, offset, SEEK_SET) < 0) + return -1; + + rc = read_in_full(fd, buf, count); + + if (current_offset != lseek(fd, current_offset, SEEK_SET)) + return -1; + return rc; +} diff --git a/compat/strlcpy.c b/compat/strlcpy.c new file mode 100644 index 0000000..4024c36 --- /dev/null +++ b/compat/strlcpy.c @@ -0,0 +1,13 @@ +#include "../git-compat-util.h" + +size_t gitstrlcpy(char *dest, const char *src, size_t size) +{ + size_t ret = strlen(src); + + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + memcpy(dest, src, len); + dest[len] = '\0'; + } + return ret; +} diff --git a/compat/winansi.c b/compat/winansi.c new file mode 100644 index 0000000..e2d96df --- /dev/null +++ b/compat/winansi.c @@ -0,0 +1,345 @@ +/* + * Copyright 2008 Peter Harris + */ + +#include +#include "../git-compat-util.h" + +/* + Functions to be wrapped: +*/ +#undef printf +#undef fprintf +#undef fputs +/* TODO: write */ + +/* + ANSI codes used by git: m, K + + This file is git-specific. Therefore, this file does not attempt + to implement any codes that are not used by git. + + TODO: K +*/ + +static HANDLE console; +static WORD plain_attr; +static WORD attr; +static int negative; + +static void init(void) +{ + CONSOLE_SCREEN_BUFFER_INFO sbi; + + static int initialized = 0; + if (initialized) + return; + + console = GetStdHandle(STD_OUTPUT_HANDLE); + if (console == INVALID_HANDLE_VALUE) + console = NULL; + + if (!console) + return; + + GetConsoleScreenBufferInfo(console, &sbi); + attr = plain_attr = sbi.wAttributes; + negative = 0; + + initialized = 1; +} + + +#define FOREGROUND_ALL (FOREGROUND_RED | FOREGROUND_GREEN | FOREGROUND_BLUE) +#define BACKGROUND_ALL (BACKGROUND_RED | BACKGROUND_GREEN | BACKGROUND_BLUE) + +static void set_console_attr(void) +{ + WORD attributes = attr; + if (negative) { + attributes &= ~FOREGROUND_ALL; + attributes &= ~BACKGROUND_ALL; + + /* This could probably use a bitmask + instead of a series of ifs */ + if (attr & FOREGROUND_RED) + attributes |= BACKGROUND_RED; + if (attr & FOREGROUND_GREEN) + attributes |= BACKGROUND_GREEN; + if (attr & FOREGROUND_BLUE) + attributes |= BACKGROUND_BLUE; + + if (attr & BACKGROUND_RED) + attributes |= FOREGROUND_RED; + if (attr & BACKGROUND_GREEN) + attributes |= FOREGROUND_GREEN; + if (attr & BACKGROUND_BLUE) + attributes |= FOREGROUND_BLUE; + } + SetConsoleTextAttribute(console, attributes); +} + +static const char *set_attr(const char *str) +{ + const char *func; + size_t len = strspn(str, "0123456789;"); + func = str + len; + + switch (*func) { + case 'm': + do { + long val = strtol(str, (char **)&str, 10); + switch (val) { + case 0: /* reset */ + attr = plain_attr; + negative = 0; + break; + case 1: /* bold */ + attr |= FOREGROUND_INTENSITY; + break; + case 2: /* faint */ + case 22: /* normal */ + attr &= ~FOREGROUND_INTENSITY; + break; + case 3: /* italic */ + /* Unsupported */ + break; + case 4: /* underline */ + case 21: /* double underline */ + /* Wikipedia says this flag does nothing */ + /* Furthermore, mingw doesn't define this flag + attr |= COMMON_LVB_UNDERSCORE; */ + break; + case 24: /* no underline */ + /* attr &= ~COMMON_LVB_UNDERSCORE; */ + break; + case 5: /* slow blink */ + case 6: /* fast blink */ + /* We don't have blink, but we do have + background intensity */ + attr |= BACKGROUND_INTENSITY; + break; + case 25: /* no blink */ + attr &= ~BACKGROUND_INTENSITY; + break; + case 7: /* negative */ + negative = 1; + break; + case 27: /* positive */ + negative = 0; + break; + case 8: /* conceal */ + case 28: /* reveal */ + /* Unsupported */ + break; + case 30: /* Black */ + attr &= ~FOREGROUND_ALL; + break; + case 31: /* Red */ + attr &= ~FOREGROUND_ALL; + attr |= FOREGROUND_RED; + break; + case 32: /* Green */ + attr &= ~FOREGROUND_ALL; + attr |= FOREGROUND_GREEN; + break; + case 33: /* Yellow */ + attr &= ~FOREGROUND_ALL; + attr |= FOREGROUND_RED | FOREGROUND_GREEN; + break; + case 34: /* Blue */ + attr &= ~FOREGROUND_ALL; + attr |= FOREGROUND_BLUE; + break; + case 35: /* Magenta */ + attr &= ~FOREGROUND_ALL; + attr |= FOREGROUND_RED | FOREGROUND_BLUE; + break; + case 36: /* Cyan */ + attr &= ~FOREGROUND_ALL; + attr |= FOREGROUND_GREEN | FOREGROUND_BLUE; + break; + case 37: /* White */ + attr |= FOREGROUND_RED | + FOREGROUND_GREEN | + FOREGROUND_BLUE; + break; + case 38: /* Unknown */ + break; + case 39: /* reset */ + attr &= ~FOREGROUND_ALL; + attr |= (plain_attr & FOREGROUND_ALL); + break; + case 40: /* Black */ + attr &= ~BACKGROUND_ALL; + break; + case 41: /* Red */ + attr &= ~BACKGROUND_ALL; + attr |= BACKGROUND_RED; + break; + case 42: /* Green */ + attr &= ~BACKGROUND_ALL; + attr |= BACKGROUND_GREEN; + break; + case 43: /* Yellow */ + attr &= ~BACKGROUND_ALL; + attr |= BACKGROUND_RED | BACKGROUND_GREEN; + break; + case 44: /* Blue */ + attr &= ~BACKGROUND_ALL; + attr |= BACKGROUND_BLUE; + break; + case 45: /* Magenta */ + attr &= ~BACKGROUND_ALL; + attr |= BACKGROUND_RED | BACKGROUND_BLUE; + break; + case 46: /* Cyan */ + attr &= ~BACKGROUND_ALL; + attr |= BACKGROUND_GREEN | BACKGROUND_BLUE; + break; + case 47: /* White */ + attr |= BACKGROUND_RED | + BACKGROUND_GREEN | + BACKGROUND_BLUE; + break; + case 48: /* Unknown */ + break; + case 49: /* reset */ + attr &= ~BACKGROUND_ALL; + attr |= (plain_attr & BACKGROUND_ALL); + break; + default: + /* Unsupported code */ + break; + } + str++; + } while (*(str-1) == ';'); + + set_console_attr(); + break; + case 'K': + /* TODO */ + break; + default: + /* Unsupported code */ + break; + } + + return func + 1; +} + +static int ansi_emulate(const char *str, FILE *stream) +{ + int rv = 0; + const char *pos = str; + + while (*pos) { + pos = strstr(str, "\033["); + if (pos) { + size_t len = pos - str; + + if (len) { + size_t out_len = fwrite(str, 1, len, stream); + rv += out_len; + if (out_len < len) + return rv; + } + + str = pos + 2; + rv += 2; + + fflush(stream); + + pos = set_attr(str); + rv += pos - str; + str = pos; + } else { + rv += strlen(str); + fputs(str, stream); + return rv; + } + } + return rv; +} + +int winansi_fputs(const char *str, FILE *stream) +{ + int rv; + + if (!isatty(fileno(stream))) + return fputs(str, stream); + + init(); + + if (!console) + return fputs(str, stream); + + rv = ansi_emulate(str, stream); + + if (rv >= 0) + return 0; + else + return EOF; +} + +static int winansi_vfprintf(FILE *stream, const char *format, va_list list) +{ + int len, rv; + char small_buf[256]; + char *buf = small_buf; + va_list cp; + + if (!isatty(fileno(stream))) + goto abort; + + init(); + + if (!console) + goto abort; + + va_copy(cp, list); + len = vsnprintf(small_buf, sizeof(small_buf), format, cp); + va_end(cp); + + if (len > sizeof(small_buf) - 1) { + buf = malloc(len + 1); + if (!buf) + goto abort; + + len = vsnprintf(buf, len + 1, format, list); + } + + rv = ansi_emulate(buf, stream); + + if (buf != small_buf) + free(buf); + return rv; + +abort: + rv = vfprintf(stream, format, list); + return rv; +} + +int winansi_fprintf(FILE *stream, const char *format, ...) +{ + va_list list; + int rv; + + va_start(list, format); + rv = winansi_vfprintf(stream, format, list); + va_end(list); + + return rv; +} + +int winansi_printf(const char *format, ...) +{ + va_list list; + int rv; + + va_start(list, format); + rv = winansi_vfprintf(stdout, format, list); + va_end(list); + + return rv; +} diff --git a/date.c b/date.c new file mode 100644 index 0000000..35a5257 --- /dev/null +++ b/date.c @@ -0,0 +1,860 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + */ + +#include "cache.h" + +/* + * This is like mktime, but without normalization of tm_wday and tm_yday. + */ +time_t tm_to_time_t(const struct tm *tm) +{ + static const int mdays[] = { + 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334 + }; + int year = tm->tm_year - 70; + int month = tm->tm_mon; + int day = tm->tm_mday; + + if (year < 0 || year > 129) /* algo only works for 1970-2099 */ + return -1; + if (month < 0 || month > 11) /* array bounds */ + return -1; + if (month < 2 || (year + 2) % 4) + day--; + return (year * 365 + (year + 1) / 4 + mdays[month] + day) * 24*60*60UL + + tm->tm_hour * 60*60 + tm->tm_min * 60 + tm->tm_sec; +} + +static const char *month_names[] = { + "January", "February", "March", "April", "May", "June", + "July", "August", "September", "October", "November", "December" +}; + +static const char *weekday_names[] = { + "Sundays", "Mondays", "Tuesdays", "Wednesdays", "Thursdays", "Fridays", "Saturdays" +}; + +static time_t gm_time_t(unsigned long time, int tz) +{ + int minutes; + + minutes = tz < 0 ? -tz : tz; + minutes = (minutes / 100)*60 + (minutes % 100); + minutes = tz < 0 ? -minutes : minutes; + return time + minutes * 60; +} + +/* + * The "tz" thing is passed in as this strange "decimal parse of tz" + * thing, which means that tz -0100 is passed in as the integer -100, + * even though it means "sixty minutes off" + */ +static struct tm *time_to_tm(unsigned long time, int tz) +{ + time_t t = gm_time_t(time, tz); + return gmtime(&t); +} + +/* + * What value of "tz" was in effect back then at "time" in the + * local timezone? + */ +static int local_tzoffset(unsigned long time) +{ + time_t t, t_local; + struct tm tm; + int offset, eastwest; + + t = time; + localtime_r(&t, &tm); + t_local = tm_to_time_t(&tm); + + if (t_local < t) { + eastwest = -1; + offset = t - t_local; + } else { + eastwest = 1; + offset = t_local - t; + } + offset /= 60; /* in minutes */ + offset = (offset % 60) + ((offset / 60) * 100); + return offset * eastwest; +} + +const char *show_date(unsigned long time, int tz, enum date_mode mode) +{ + struct tm *tm; + static char timebuf[200]; + + if (mode == DATE_RELATIVE) { + unsigned long diff; + struct timeval now; + gettimeofday(&now, NULL); + if (now.tv_sec < time) + return "in the future"; + diff = now.tv_sec - time; + if (diff < 90) { + snprintf(timebuf, sizeof(timebuf), "%lu seconds ago", diff); + return timebuf; + } + /* Turn it into minutes */ + diff = (diff + 30) / 60; + if (diff < 90) { + snprintf(timebuf, sizeof(timebuf), "%lu minutes ago", diff); + return timebuf; + } + /* Turn it into hours */ + diff = (diff + 30) / 60; + if (diff < 36) { + snprintf(timebuf, sizeof(timebuf), "%lu hours ago", diff); + return timebuf; + } + /* We deal with number of days from here on */ + diff = (diff + 12) / 24; + if (diff < 14) { + snprintf(timebuf, sizeof(timebuf), "%lu days ago", diff); + return timebuf; + } + /* Say weeks for the past 10 weeks or so */ + if (diff < 70) { + snprintf(timebuf, sizeof(timebuf), "%lu weeks ago", (diff + 3) / 7); + return timebuf; + } + /* Say months for the past 12 months or so */ + if (diff < 360) { + snprintf(timebuf, sizeof(timebuf), "%lu months ago", (diff + 15) / 30); + return timebuf; + } + /* Else fall back on absolute format.. */ + } + + if (mode == DATE_LOCAL) + tz = local_tzoffset(time); + + tm = time_to_tm(time, tz); + if (!tm) + return NULL; + if (mode == DATE_SHORT) + sprintf(timebuf, "%04d-%02d-%02d", tm->tm_year + 1900, + tm->tm_mon + 1, tm->tm_mday); + else if (mode == DATE_ISO8601) + sprintf(timebuf, "%04d-%02d-%02d %02d:%02d:%02d %+05d", + tm->tm_year + 1900, + tm->tm_mon + 1, + tm->tm_mday, + tm->tm_hour, tm->tm_min, tm->tm_sec, + tz); + else if (mode == DATE_RFC2822) + sprintf(timebuf, "%.3s, %d %.3s %d %02d:%02d:%02d %+05d", + weekday_names[tm->tm_wday], tm->tm_mday, + month_names[tm->tm_mon], tm->tm_year + 1900, + tm->tm_hour, tm->tm_min, tm->tm_sec, tz); + else + sprintf(timebuf, "%.3s %.3s %d %02d:%02d:%02d %d%c%+05d", + weekday_names[tm->tm_wday], + month_names[tm->tm_mon], + tm->tm_mday, + tm->tm_hour, tm->tm_min, tm->tm_sec, + tm->tm_year + 1900, + (mode == DATE_LOCAL) ? 0 : ' ', + tz); + return timebuf; +} + +/* + * Check these. And note how it doesn't do the summer-time conversion. + * + * In my world, it's always summer, and things are probably a bit off + * in other ways too. + */ +static const struct { + const char *name; + int offset; + int dst; +} timezone_names[] = { + { "IDLW", -12, 0, }, /* International Date Line West */ + { "NT", -11, 0, }, /* Nome */ + { "CAT", -10, 0, }, /* Central Alaska */ + { "HST", -10, 0, }, /* Hawaii Standard */ + { "HDT", -10, 1, }, /* Hawaii Daylight */ + { "YST", -9, 0, }, /* Yukon Standard */ + { "YDT", -9, 1, }, /* Yukon Daylight */ + { "PST", -8, 0, }, /* Pacific Standard */ + { "PDT", -8, 1, }, /* Pacific Daylight */ + { "MST", -7, 0, }, /* Mountain Standard */ + { "MDT", -7, 1, }, /* Mountain Daylight */ + { "CST", -6, 0, }, /* Central Standard */ + { "CDT", -6, 1, }, /* Central Daylight */ + { "EST", -5, 0, }, /* Eastern Standard */ + { "EDT", -5, 1, }, /* Eastern Daylight */ + { "AST", -3, 0, }, /* Atlantic Standard */ + { "ADT", -3, 1, }, /* Atlantic Daylight */ + { "WAT", -1, 0, }, /* West Africa */ + + { "GMT", 0, 0, }, /* Greenwich Mean */ + { "UTC", 0, 0, }, /* Universal (Coordinated) */ + + { "WET", 0, 0, }, /* Western European */ + { "BST", 0, 1, }, /* British Summer */ + { "CET", +1, 0, }, /* Central European */ + { "MET", +1, 0, }, /* Middle European */ + { "MEWT", +1, 0, }, /* Middle European Winter */ + { "MEST", +1, 1, }, /* Middle European Summer */ + { "CEST", +1, 1, }, /* Central European Summer */ + { "MESZ", +1, 1, }, /* Middle European Summer */ + { "FWT", +1, 0, }, /* French Winter */ + { "FST", +1, 1, }, /* French Summer */ + { "EET", +2, 0, }, /* Eastern Europe, USSR Zone 1 */ + { "EEST", +2, 1, }, /* Eastern European Daylight */ + { "WAST", +7, 0, }, /* West Australian Standard */ + { "WADT", +7, 1, }, /* West Australian Daylight */ + { "CCT", +8, 0, }, /* China Coast, USSR Zone 7 */ + { "JST", +9, 0, }, /* Japan Standard, USSR Zone 8 */ + { "EAST", +10, 0, }, /* Eastern Australian Standard */ + { "EADT", +10, 1, }, /* Eastern Australian Daylight */ + { "GST", +10, 0, }, /* Guam Standard, USSR Zone 9 */ + { "NZT", +12, 0, }, /* New Zealand */ + { "NZST", +12, 0, }, /* New Zealand Standard */ + { "NZDT", +12, 1, }, /* New Zealand Daylight */ + { "IDLE", +12, 0, }, /* International Date Line East */ +}; + +static int match_string(const char *date, const char *str) +{ + int i = 0; + + for (i = 0; *date; date++, str++, i++) { + if (*date == *str) + continue; + if (toupper(*date) == toupper(*str)) + continue; + if (!isalnum(*date)) + break; + return 0; + } + return i; +} + +static int skip_alpha(const char *date) +{ + int i = 0; + do { + i++; + } while (isalpha(date[i])); + return i; +} + +/* +* Parse month, weekday, or timezone name +*/ +static int match_alpha(const char *date, struct tm *tm, int *offset) +{ + int i; + + for (i = 0; i < 12; i++) { + int match = match_string(date, month_names[i]); + if (match >= 3) { + tm->tm_mon = i; + return match; + } + } + + for (i = 0; i < 7; i++) { + int match = match_string(date, weekday_names[i]); + if (match >= 3) { + tm->tm_wday = i; + return match; + } + } + + for (i = 0; i < ARRAY_SIZE(timezone_names); i++) { + int match = match_string(date, timezone_names[i].name); + if (match >= 3) { + int off = timezone_names[i].offset; + + /* This is bogus, but we like summer */ + off += timezone_names[i].dst; + + /* Only use the tz name offset if we don't have anything better */ + if (*offset == -1) + *offset = 60*off; + + return match; + } + } + + if (match_string(date, "PM") == 2) { + tm->tm_hour = (tm->tm_hour % 12) + 12; + return 2; + } + + if (match_string(date, "AM") == 2) { + tm->tm_hour = (tm->tm_hour % 12) + 0; + return 2; + } + + /* BAD CRAP */ + return skip_alpha(date); +} + +static int is_date(int year, int month, int day, struct tm *now_tm, time_t now, struct tm *tm) +{ + if (month > 0 && month < 13 && day > 0 && day < 32) { + struct tm check = *tm; + struct tm *r = (now_tm ? &check : tm); + time_t specified; + + r->tm_mon = month - 1; + r->tm_mday = day; + if (year == -1) { + if (!now_tm) + return 1; + r->tm_year = now_tm->tm_year; + } + else if (year >= 1970 && year < 2100) + r->tm_year = year - 1900; + else if (year > 70 && year < 100) + r->tm_year = year; + else if (year < 38) + r->tm_year = year + 100; + else + return 0; + if (!now_tm) + return 1; + + specified = tm_to_time_t(r); + + /* Be it commit time or author time, it does not make + * sense to specify timestamp way into the future. Make + * sure it is not later than ten days from now... + */ + if (now + 10*24*3600 < specified) + return 0; + tm->tm_mon = r->tm_mon; + tm->tm_mday = r->tm_mday; + if (year != -1) + tm->tm_year = r->tm_year; + return 1; + } + return 0; +} + +static int match_multi_number(unsigned long num, char c, const char *date, char *end, struct tm *tm) +{ + time_t now; + struct tm now_tm; + struct tm *refuse_future; + long num2, num3; + + num2 = strtol(end+1, &end, 10); + num3 = -1; + if (*end == c && isdigit(end[1])) + num3 = strtol(end+1, &end, 10); + + /* Time? Date? */ + switch (c) { + case ':': + if (num3 < 0) + num3 = 0; + if (num < 25 && num2 >= 0 && num2 < 60 && num3 >= 0 && num3 <= 60) { + tm->tm_hour = num; + tm->tm_min = num2; + tm->tm_sec = num3; + break; + } + return 0; + + case '-': + case '/': + case '.': + now = time(NULL); + refuse_future = NULL; + if (gmtime_r(&now, &now_tm)) + refuse_future = &now_tm; + + if (num > 70) { + /* yyyy-mm-dd? */ + if (is_date(num, num2, num3, refuse_future, now, tm)) + break; + /* yyyy-dd-mm? */ + if (is_date(num, num3, num2, refuse_future, now, tm)) + break; + } + /* Our eastern European friends say dd.mm.yy[yy] + * is the norm there, so giving precedence to + * mm/dd/yy[yy] form only when separator is not '.' + */ + if (c != '.' && + is_date(num3, num, num2, refuse_future, now, tm)) + break; + /* European dd.mm.yy[yy] or funny US dd/mm/yy[yy] */ + if (is_date(num3, num2, num, refuse_future, now, tm)) + break; + /* Funny European mm.dd.yy */ + if (c == '.' && + is_date(num3, num, num2, refuse_future, now, tm)) + break; + return 0; + } + return end - date; +} + +/* + * We've seen a digit. Time? Year? Date? + */ +static int match_digit(const char *date, struct tm *tm, int *offset, int *tm_gmt) +{ + int n; + char *end; + unsigned long num; + + num = strtoul(date, &end, 10); + + /* + * Seconds since 1970? We trigger on that for any numbers with + * more than 8 digits. This is because we don't want to rule out + * numbers like 20070606 as a YYYYMMDD date. + */ + if (num >= 100000000) { + time_t time = num; + if (gmtime_r(&time, tm)) { + *tm_gmt = 1; + return end - date; + } + } + + /* + * Check for special formats: num[-.:/]num[same]num + */ + switch (*end) { + case ':': + case '.': + case '/': + case '-': + if (isdigit(end[1])) { + int match = match_multi_number(num, *end, date, end, tm); + if (match) + return match; + } + } + + /* + * None of the special formats? Try to guess what + * the number meant. We use the number of digits + * to make a more educated guess.. + */ + n = 0; + do { + n++; + } while (isdigit(date[n])); + + /* Four-digit year or a timezone? */ + if (n == 4) { + if (num <= 1400 && *offset == -1) { + unsigned int minutes = num % 100; + unsigned int hours = num / 100; + *offset = hours*60 + minutes; + } else if (num > 1900 && num < 2100) + tm->tm_year = num - 1900; + return n; + } + + /* + * NOTE! We will give precedence to day-of-month over month or + * year numbers in the 1-12 range. So 05 is always "mday 5", + * unless we already have a mday.. + * + * IOW, 01 Apr 05 parses as "April 1st, 2005". + */ + if (num > 0 && num < 32 && tm->tm_mday < 0) { + tm->tm_mday = num; + return n; + } + + /* Two-digit year? */ + if (n == 2 && tm->tm_year < 0) { + if (num < 10 && tm->tm_mday >= 0) { + tm->tm_year = num + 100; + return n; + } + if (num >= 70) { + tm->tm_year = num; + return n; + } + } + + if (num > 0 && num < 32) { + tm->tm_mday = num; + } else if (num > 1900) { + tm->tm_year = num - 1900; + } else if (num > 70) { + tm->tm_year = num; + } else if (num > 0 && num < 13) { + tm->tm_mon = num-1; + } + + return n; +} + +static int match_tz(const char *date, int *offp) +{ + char *end; + int offset = strtoul(date+1, &end, 10); + int min, hour; + int n = end - date - 1; + + min = offset % 100; + hour = offset / 100; + + /* + * Don't accept any random crap.. At least 3 digits, and + * a valid minute. We might want to check that the minutes + * are divisible by 30 or something too. + */ + if (min < 60 && n > 2) { + offset = hour*60+min; + if (*date == '-') + offset = -offset; + + *offp = offset; + } + return end - date; +} + +static int date_string(unsigned long date, int offset, char *buf, int len) +{ + int sign = '+'; + + if (offset < 0) { + offset = -offset; + sign = '-'; + } + return snprintf(buf, len, "%lu %c%02d%02d", date, sign, offset / 60, offset % 60); +} + +/* Gr. strptime is crap for this; it doesn't have a way to require RFC2822 + (i.e. English) day/month names, and it doesn't work correctly with %z. */ +int parse_date(const char *date, char *result, int maxlen) +{ + struct tm tm; + int offset, tm_gmt; + time_t then; + + memset(&tm, 0, sizeof(tm)); + tm.tm_year = -1; + tm.tm_mon = -1; + tm.tm_mday = -1; + tm.tm_isdst = -1; + offset = -1; + tm_gmt = 0; + + for (;;) { + int match = 0; + unsigned char c = *date; + + /* Stop at end of string or newline */ + if (!c || c == '\n') + break; + + if (isalpha(c)) + match = match_alpha(date, &tm, &offset); + else if (isdigit(c)) + match = match_digit(date, &tm, &offset, &tm_gmt); + else if ((c == '-' || c == '+') && isdigit(date[1])) + match = match_tz(date, &offset); + + if (!match) { + /* BAD CRAP */ + match = 1; + } + + date += match; + } + + /* mktime uses local timezone */ + then = tm_to_time_t(&tm); + if (offset == -1) + offset = (then - mktime(&tm)) / 60; + + if (then == -1) + return -1; + + if (!tm_gmt) + then -= offset * 60; + return date_string(then, offset, result, maxlen); +} + +enum date_mode parse_date_format(const char *format) +{ + if (!strcmp(format, "relative")) + return DATE_RELATIVE; + else if (!strcmp(format, "iso8601") || + !strcmp(format, "iso")) + return DATE_ISO8601; + else if (!strcmp(format, "rfc2822") || + !strcmp(format, "rfc")) + return DATE_RFC2822; + else if (!strcmp(format, "short")) + return DATE_SHORT; + else if (!strcmp(format, "local")) + return DATE_LOCAL; + else if (!strcmp(format, "default")) + return DATE_NORMAL; + else + die("unknown date format %s", format); +} + +void datestamp(char *buf, int bufsize) +{ + time_t now; + int offset; + + time(&now); + + offset = tm_to_time_t(localtime(&now)) - now; + offset /= 60; + + date_string(now, offset, buf, bufsize); +} + +static void update_tm(struct tm *tm, unsigned long sec) +{ + time_t n = mktime(tm) - sec; + localtime_r(&n, tm); +} + +static void date_yesterday(struct tm *tm, int *num) +{ + update_tm(tm, 24*60*60); +} + +static void date_time(struct tm *tm, int hour) +{ + if (tm->tm_hour < hour) + date_yesterday(tm, NULL); + tm->tm_hour = hour; + tm->tm_min = 0; + tm->tm_sec = 0; +} + +static void date_midnight(struct tm *tm, int *num) +{ + date_time(tm, 0); +} + +static void date_noon(struct tm *tm, int *num) +{ + date_time(tm, 12); +} + +static void date_tea(struct tm *tm, int *num) +{ + date_time(tm, 17); +} + +static void date_pm(struct tm *tm, int *num) +{ + int hour, n = *num; + *num = 0; + + hour = tm->tm_hour; + if (n) { + hour = n; + tm->tm_min = 0; + tm->tm_sec = 0; + } + tm->tm_hour = (hour % 12) + 12; +} + +static void date_am(struct tm *tm, int *num) +{ + int hour, n = *num; + *num = 0; + + hour = tm->tm_hour; + if (n) { + hour = n; + tm->tm_min = 0; + tm->tm_sec = 0; + } + tm->tm_hour = (hour % 12); +} + +static void date_never(struct tm *tm, int *num) +{ + time_t n = 0; + localtime_r(&n, tm); +} + +static const struct special { + const char *name; + void (*fn)(struct tm *, int *); +} special[] = { + { "yesterday", date_yesterday }, + { "noon", date_noon }, + { "midnight", date_midnight }, + { "tea", date_tea }, + { "PM", date_pm }, + { "AM", date_am }, + { "never", date_never }, + { NULL } +}; + +static const char *number_name[] = { + "zero", "one", "two", "three", "four", + "five", "six", "seven", "eight", "nine", "ten", +}; + +static const struct typelen { + const char *type; + int length; +} typelen[] = { + { "seconds", 1 }, + { "minutes", 60 }, + { "hours", 60*60 }, + { "days", 24*60*60 }, + { "weeks", 7*24*60*60 }, + { NULL } +}; + +static const char *approxidate_alpha(const char *date, struct tm *tm, int *num) +{ + const struct typelen *tl; + const struct special *s; + const char *end = date; + int i; + + while (isalpha(*++end)); + ; + + for (i = 0; i < 12; i++) { + int match = match_string(date, month_names[i]); + if (match >= 3) { + tm->tm_mon = i; + return end; + } + } + + for (s = special; s->name; s++) { + int len = strlen(s->name); + if (match_string(date, s->name) == len) { + s->fn(tm, num); + return end; + } + } + + if (!*num) { + for (i = 1; i < 11; i++) { + int len = strlen(number_name[i]); + if (match_string(date, number_name[i]) == len) { + *num = i; + return end; + } + } + if (match_string(date, "last") == 4) + *num = 1; + return end; + } + + tl = typelen; + while (tl->type) { + int len = strlen(tl->type); + if (match_string(date, tl->type) >= len-1) { + update_tm(tm, tl->length * *num); + *num = 0; + return end; + } + tl++; + } + + for (i = 0; i < 7; i++) { + int match = match_string(date, weekday_names[i]); + if (match >= 3) { + int diff, n = *num -1; + *num = 0; + + diff = tm->tm_wday - i; + if (diff <= 0) + n++; + diff += 7*n; + + update_tm(tm, diff * 24 * 60 * 60); + return end; + } + } + + if (match_string(date, "months") >= 5) { + int n = tm->tm_mon - *num; + *num = 0; + while (n < 0) { + n += 12; + tm->tm_year--; + } + tm->tm_mon = n; + return end; + } + + if (match_string(date, "years") >= 4) { + tm->tm_year -= *num; + *num = 0; + return end; + } + + return end; +} + +static const char *approxidate_digit(const char *date, struct tm *tm, int *num) +{ + char *end; + unsigned long number = strtoul(date, &end, 10); + + switch (*end) { + case ':': + case '.': + case '/': + case '-': + if (isdigit(end[1])) { + int match = match_multi_number(number, *end, date, end, tm); + if (match) + return date + match; + } + } + + *num = number; + return end; +} + +unsigned long approxidate(const char *date) +{ + int number = 0; + struct tm tm, now; + struct timeval tv; + char buffer[50]; + + if (parse_date(date, buffer, sizeof(buffer)) > 0) + return strtoul(buffer, NULL, 10); + + gettimeofday(&tv, NULL); + localtime_r(&tv.tv_sec, &tm); + now = tm; + for (;;) { + unsigned char c = *date; + if (!c) + break; + date++; + if (isdigit(c)) { + date = approxidate_digit(date-1, &tm, &number); + continue; + } + if (isalpha(c)) + date = approxidate_alpha(date-1, &tm, &number); + } + if (number > 0 && number < 32) + tm.tm_mday = number; + if (tm.tm_mon > now.tm_mon && tm.tm_year == now.tm_year) + tm.tm_year--; + return mktime(&tm); +} diff --git a/hash.h b/hash.h new file mode 100644 index 0000000..69e33a4 --- /dev/null +++ b/hash.h @@ -0,0 +1,43 @@ +#ifndef HASH_H +#define HASH_H + +/* + * These are some simple generic hash table helper functions. + * Not necessarily suitable for all users, but good for things + * where you want to just keep track of a list of things, and + * have a good hash to use on them. + * + * It keeps the hash table at roughly 50-75% free, so the memory + * cost of the hash table itself is roughly + * + * 3 * 2*sizeof(void *) * nr_of_objects + * + * bytes. + * + * FIXME: on 64-bit architectures, we waste memory. It would be + * good to have just 32-bit pointers, requiring a special allocator + * for hashed entries or something. + */ +struct hash_table_entry { + unsigned int hash; + void *ptr; +}; + +struct hash_table { + unsigned int size, nr; + struct hash_table_entry *array; +}; + +extern void *lookup_hash(unsigned int hash, const struct hash_table *table); +extern void **insert_hash(unsigned int hash, void *ptr, struct hash_table *table); +extern int for_each_hash(const struct hash_table *table, int (*fn)(void *)); +extern void free_hash(struct hash_table *table); + +static inline void init_hash(struct hash_table *table) +{ + table->size = 0; + table->nr = 0; + table->array = NULL; +} + +#endif diff --git a/sha1_file.c b/sha1_file.c new file mode 100644 index 0000000..32e4664 --- /dev/null +++ b/sha1_file.c @@ -0,0 +1,2479 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + * + * This handles basic git sha1 object files - packing, unpacking, + * creation etc. + */ +#include "cache.h" +#include "delta.h" +#include "pack.h" +#include "blob.h" +#include "commit.h" +#include "tag.h" +#include "tree.h" +#include "refs.h" +#include "pack-revindex.h" +#include "sha1-lookup.h" + +#ifndef O_NOATIME +#if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) +#define O_NOATIME 01000000 +#else +#define O_NOATIME 0 +#endif +#endif + +#ifdef NO_C99_FORMAT +#define SZ_FMT "lu" +static unsigned long sz_fmt(size_t s) { return (unsigned long)s; } +#else +#define SZ_FMT "zu" +static size_t sz_fmt(size_t s) { return s; } +#endif + +const unsigned char null_sha1[20]; + +const signed char hexval_table[256] = { + -1, -1, -1, -1, -1, -1, -1, -1, /* 00-07 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 08-0f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 10-17 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 18-1f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 20-27 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 28-2f */ + 0, 1, 2, 3, 4, 5, 6, 7, /* 30-37 */ + 8, 9, -1, -1, -1, -1, -1, -1, /* 38-3f */ + -1, 10, 11, 12, 13, 14, 15, -1, /* 40-47 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 48-4f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 50-57 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 58-5f */ + -1, 10, 11, 12, 13, 14, 15, -1, /* 60-67 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 68-67 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 70-77 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 78-7f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 80-87 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 88-8f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 90-97 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 98-9f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* a0-a7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* a8-af */ + -1, -1, -1, -1, -1, -1, -1, -1, /* b0-b7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* b8-bf */ + -1, -1, -1, -1, -1, -1, -1, -1, /* c0-c7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* c8-cf */ + -1, -1, -1, -1, -1, -1, -1, -1, /* d0-d7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* d8-df */ + -1, -1, -1, -1, -1, -1, -1, -1, /* e0-e7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* e8-ef */ + -1, -1, -1, -1, -1, -1, -1, -1, /* f0-f7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* f8-ff */ +}; + +int get_sha1_hex(const char *hex, unsigned char *sha1) +{ + int i; + for (i = 0; i < 20; i++) { + unsigned int val = (hexval(hex[0]) << 4) | hexval(hex[1]); + if (val & ~0xff) + return -1; + *sha1++ = val; + hex += 2; + } + return 0; +} + +static inline int offset_1st_component(const char *path) +{ + if (has_dos_drive_prefix(path)) + return 2 + (path[2] == '/'); + return *path == '/'; +} + +int safe_create_leading_directories(char *path) +{ + char *pos = path + offset_1st_component(path); + struct stat st; + + while (pos) { + pos = strchr(pos, '/'); + if (!pos) + break; + *pos = 0; + if (!stat(path, &st)) { + /* path exists */ + if (!S_ISDIR(st.st_mode)) { + *pos = '/'; + return -3; + } + } + else if (mkdir(path, 0777)) { + *pos = '/'; + return -1; + } + else if (adjust_shared_perm(path)) { + *pos = '/'; + return -2; + } + *pos++ = '/'; + } + return 0; +} + +int safe_create_leading_directories_const(const char *path) +{ + /* path points to cache entries, so xstrdup before messing with it */ + char *buf = xstrdup(path); + int result = safe_create_leading_directories(buf); + free(buf); + return result; +} + +char *sha1_to_hex(const unsigned char *sha1) +{ + static int bufno; + static char hexbuffer[4][50]; + static const char hex[] = "0123456789abcdef"; + char *buffer = hexbuffer[3 & ++bufno], *buf = buffer; + int i; + + for (i = 0; i < 20; i++) { + unsigned int val = *sha1++; + *buf++ = hex[val >> 4]; + *buf++ = hex[val & 0xf]; + } + *buf = '\0'; + + return buffer; +} + +static void fill_sha1_path(char *pathbuf, const unsigned char *sha1) +{ + int i; + for (i = 0; i < 20; i++) { + static char hex[] = "0123456789abcdef"; + unsigned int val = sha1[i]; + char *pos = pathbuf + i*2 + (i > 0); + *pos++ = hex[val >> 4]; + *pos = hex[val & 0xf]; + } +} + +/* + * NOTE! This returns a statically allocated buffer, so you have to be + * careful about using it. Do an "xstrdup()" if you need to save the + * filename. + * + * Also note that this returns the location for creating. Reading + * SHA1 file can happen from any alternate directory listed in the + * DB_ENVIRONMENT environment variable if it is not found in + * the primary object database. + */ +char *sha1_file_name(const unsigned char *sha1) +{ + static char *name, *base; + + if (!base) { + const char *sha1_file_directory = get_object_directory(); + int len = strlen(sha1_file_directory); + base = xmalloc(len + 60); + memcpy(base, sha1_file_directory, len); + memset(base+len, 0, 60); + base[len] = '/'; + base[len+3] = '/'; + name = base + len + 1; + } + fill_sha1_path(name, sha1); + return base; +} + +static char *sha1_get_pack_name(const unsigned char *sha1, + char **name, char **base, const char *which) +{ + static const char hex[] = "0123456789abcdef"; + char *buf; + int i; + + if (!*base) { + const char *sha1_file_directory = get_object_directory(); + int len = strlen(sha1_file_directory); + *base = xmalloc(len + 60); + sprintf(*base, "%s/pack/pack-1234567890123456789012345678901234567890.%s", + sha1_file_directory, which); + *name = *base + len + 11; + } + + buf = *name; + + for (i = 0; i < 20; i++) { + unsigned int val = *sha1++; + *buf++ = hex[val >> 4]; + *buf++ = hex[val & 0xf]; + } + + return *base; +} + +char *sha1_pack_name(const unsigned char *sha1) +{ + static char *name, *base; + + return sha1_get_pack_name(sha1, &name, &base, "pack"); +} + +char *sha1_pack_index_name(const unsigned char *sha1) +{ + static char *name, *base; + + return sha1_get_pack_name(sha1, &name, &base, "idx"); +} + +struct alternate_object_database *alt_odb_list; +static struct alternate_object_database **alt_odb_tail; + +static void read_info_alternates(const char * alternates, int depth); + +/* + * Prepare alternate object database registry. + * + * The variable alt_odb_list points at the list of struct + * alternate_object_database. The elements on this list come from + * non-empty elements from colon separated ALTERNATE_DB_ENVIRONMENT + * environment variable, and $GIT_OBJECT_DIRECTORY/info/alternates, + * whose contents is similar to that environment variable but can be + * LF separated. Its base points at a statically allocated buffer that + * contains "/the/directory/corresponding/to/.git/objects/...", while + * its name points just after the slash at the end of ".git/objects/" + * in the example above, and has enough space to hold 40-byte hex + * SHA1, an extra slash for the first level indirection, and the + * terminating NUL. + */ +static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth) +{ + struct stat st; + const char *objdir = get_object_directory(); + struct alternate_object_database *ent; + struct alternate_object_database *alt; + /* 43 = 40-byte + 2 '/' + terminating NUL */ + int pfxlen = len; + int entlen = pfxlen + 43; + int base_len = -1; + + if (!is_absolute_path(entry) && relative_base) { + /* Relative alt-odb */ + if (base_len < 0) + base_len = strlen(relative_base) + 1; + entlen += base_len; + pfxlen += base_len; + } + ent = xmalloc(sizeof(*ent) + entlen); + + if (!is_absolute_path(entry) && relative_base) { + memcpy(ent->base, relative_base, base_len - 1); + ent->base[base_len - 1] = '/'; + memcpy(ent->base + base_len, entry, len); + } + else + memcpy(ent->base, entry, pfxlen); + + ent->name = ent->base + pfxlen + 1; + ent->base[pfxlen + 3] = '/'; + ent->base[pfxlen] = ent->base[entlen-1] = 0; + + /* Detect cases where alternate disappeared */ + if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) { + error("object directory %s does not exist; " + "check .git/objects/info/alternates.", + ent->base); + free(ent); + return -1; + } + + /* Prevent the common mistake of listing the same + * thing twice, or object directory itself. + */ + for (alt = alt_odb_list; alt; alt = alt->next) { + if (!memcmp(ent->base, alt->base, pfxlen)) { + free(ent); + return -1; + } + } + if (!memcmp(ent->base, objdir, pfxlen)) { + free(ent); + return -1; + } + + /* add the alternate entry */ + *alt_odb_tail = ent; + alt_odb_tail = &(ent->next); + ent->next = NULL; + + /* recursively add alternates */ + read_info_alternates(ent->base, depth + 1); + + ent->base[pfxlen] = '/'; + + return 0; +} + +static void link_alt_odb_entries(const char *alt, const char *ep, int sep, + const char *relative_base, int depth) +{ + const char *cp, *last; + + if (depth > 5) { + error("%s: ignoring alternate object stores, nesting too deep.", + relative_base); + return; + } + + last = alt; + while (last < ep) { + cp = last; + if (cp < ep && *cp == '#') { + while (cp < ep && *cp != sep) + cp++; + last = cp + 1; + continue; + } + while (cp < ep && *cp != sep) + cp++; + if (last != cp) { + if (!is_absolute_path(last) && depth) { + error("%s: ignoring relative alternate object store %s", + relative_base, last); + } else { + link_alt_odb_entry(last, cp - last, + relative_base, depth); + } + } + while (cp < ep && *cp == sep) + cp++; + last = cp; + } +} + +static void read_info_alternates(const char * relative_base, int depth) +{ + char *map; + size_t mapsz; + struct stat st; + const char alt_file_name[] = "info/alternates"; + /* Given that relative_base is no longer than PATH_MAX, + ensure that "path" has enough space to append "/", the + file name, "info/alternates", and a trailing NUL. */ + char path[PATH_MAX + 1 + sizeof alt_file_name]; + int fd; + + sprintf(path, "%s/%s", relative_base, alt_file_name); + fd = open(path, O_RDONLY); + if (fd < 0) + return; + if (fstat(fd, &st) || (st.st_size == 0)) { + close(fd); + return; + } + mapsz = xsize_t(st.st_size); + map = xmmap(NULL, mapsz, PROT_READ, MAP_PRIVATE, fd, 0); + close(fd); + + link_alt_odb_entries(map, map + mapsz, '\n', relative_base, depth); + + munmap(map, mapsz); +} + +void add_to_alternates_file(const char *reference) +{ + struct lock_file *lock = xcalloc(1, sizeof(struct lock_file)); + int fd = hold_lock_file_for_append(lock, git_path("objects/info/alternates"), 1); + char *alt = mkpath("%s/objects\n", reference); + write_or_die(fd, alt, strlen(alt)); + if (commit_lock_file(lock)) + die("could not close alternates file"); + if (alt_odb_tail) + link_alt_odb_entries(alt, alt + strlen(alt), '\n', NULL, 0); +} + +void prepare_alt_odb(void) +{ + const char *alt; + + if (alt_odb_tail) + return; + + alt = getenv(ALTERNATE_DB_ENVIRONMENT); + if (!alt) alt = ""; + + alt_odb_tail = &alt_odb_list; + link_alt_odb_entries(alt, alt + strlen(alt), PATH_SEP, NULL, 0); + + read_info_alternates(get_object_directory(), 0); +} + +static int has_loose_object(const unsigned char *sha1) +{ + char *name = sha1_file_name(sha1); + struct alternate_object_database *alt; + + if (!access(name, F_OK)) + return 1; + prepare_alt_odb(); + for (alt = alt_odb_list; alt; alt = alt->next) { + name = alt->name; + fill_sha1_path(name, sha1); + if (!access(alt->base, F_OK)) + return 1; + } + return 0; +} + +static unsigned int pack_used_ctr; +static unsigned int pack_mmap_calls; +static unsigned int peak_pack_open_windows; +static unsigned int pack_open_windows; +static size_t peak_pack_mapped; +static size_t pack_mapped; +struct packed_git *packed_git; + +void pack_report(void) +{ + fprintf(stderr, + "pack_report: getpagesize() = %10" SZ_FMT "\n" + "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n" + "pack_report: core.packedGitLimit = %10" SZ_FMT "\n", + sz_fmt(getpagesize()), + sz_fmt(packed_git_window_size), + sz_fmt(packed_git_limit)); + fprintf(stderr, + "pack_report: pack_used_ctr = %10u\n" + "pack_report: pack_mmap_calls = %10u\n" + "pack_report: pack_open_windows = %10u / %10u\n" + "pack_report: pack_mapped = " + "%10" SZ_FMT " / %10" SZ_FMT "\n", + pack_used_ctr, + pack_mmap_calls, + pack_open_windows, peak_pack_open_windows, + sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped)); +} + +static int check_packed_git_idx(const char *path, struct packed_git *p) +{ + void *idx_map; + struct pack_idx_header *hdr; + size_t idx_size; + uint32_t version, nr, i, *index; + int fd = open(path, O_RDONLY); + struct stat st; + + if (fd < 0) + return -1; + if (fstat(fd, &st)) { + close(fd); + return -1; + } + idx_size = xsize_t(st.st_size); + if (idx_size < 4 * 256 + 20 + 20) { + close(fd); + return error("index file %s is too small", path); + } + idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0); + close(fd); + + hdr = idx_map; + if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) { + version = ntohl(hdr->idx_version); + if (version < 2 || version > 2) { + munmap(idx_map, idx_size); + return error("index file %s is version %"PRIu32 + " and is not supported by this binary" + " (try upgrading GIT to a newer version)", + path, version); + } + } else + version = 1; + + nr = 0; + index = idx_map; + if (version > 1) + index += 2; /* skip index header */ + for (i = 0; i < 256; i++) { + uint32_t n = ntohl(index[i]); + if (n < nr) { + munmap(idx_map, idx_size); + return error("non-monotonic index %s", path); + } + nr = n; + } + + if (version == 1) { + /* + * Total size: + * - 256 index entries 4 bytes each + * - 24-byte entries * nr (20-byte sha1 + 4-byte offset) + * - 20-byte SHA1 of the packfile + * - 20-byte SHA1 file checksum + */ + if (idx_size != 4*256 + nr * 24 + 20 + 20) { + munmap(idx_map, idx_size); + return error("wrong index v1 file size in %s", path); + } + } else if (version == 2) { + /* + * Minimum size: + * - 8 bytes of header + * - 256 index entries 4 bytes each + * - 20-byte sha1 entry * nr + * - 4-byte crc entry * nr + * - 4-byte offset entry * nr + * - 20-byte SHA1 of the packfile + * - 20-byte SHA1 file checksum + * And after the 4-byte offset table might be a + * variable sized table containing 8-byte entries + * for offsets larger than 2^31. + */ + unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20; + unsigned long max_size = min_size; + if (nr) + max_size += (nr - 1)*8; + if (idx_size < min_size || idx_size > max_size) { + munmap(idx_map, idx_size); + return error("wrong index v2 file size in %s", path); + } + if (idx_size != min_size && + /* + * make sure we can deal with large pack offsets. + * 31-bit signed offset won't be enough, neither + * 32-bit unsigned one will be. + */ + (sizeof(off_t) <= 4)) { + munmap(idx_map, idx_size); + return error("pack too large for current definition of off_t in %s", path); + } + } + + p->index_version = version; + p->index_data = idx_map; + p->index_size = idx_size; + p->num_objects = nr; + return 0; +} + +int open_pack_index(struct packed_git *p) +{ + char *idx_name; + int ret; + + if (p->index_data) + return 0; + + idx_name = xstrdup(p->pack_name); + strcpy(idx_name + strlen(idx_name) - strlen(".pack"), ".idx"); + ret = check_packed_git_idx(idx_name, p); + free(idx_name); + return ret; +} + +static void scan_windows(struct packed_git *p, + struct packed_git **lru_p, + struct pack_window **lru_w, + struct pack_window **lru_l) +{ + struct pack_window *w, *w_l; + + for (w_l = NULL, w = p->windows; w; w = w->next) { + if (!w->inuse_cnt) { + if (!*lru_w || w->last_used < (*lru_w)->last_used) { + *lru_p = p; + *lru_w = w; + *lru_l = w_l; + } + } + w_l = w; + } +} + +static int unuse_one_window(struct packed_git *current, int keep_fd) +{ + struct packed_git *p, *lru_p = NULL; + struct pack_window *lru_w = NULL, *lru_l = NULL; + + if (current) + scan_windows(current, &lru_p, &lru_w, &lru_l); + for (p = packed_git; p; p = p->next) + scan_windows(p, &lru_p, &lru_w, &lru_l); + if (lru_p) { + munmap(lru_w->base, lru_w->len); + pack_mapped -= lru_w->len; + if (lru_l) + lru_l->next = lru_w->next; + else { + lru_p->windows = lru_w->next; + if (!lru_p->windows && lru_p->pack_fd != keep_fd) { + close(lru_p->pack_fd); + lru_p->pack_fd = -1; + } + } + free(lru_w); + pack_open_windows--; + return 1; + } + return 0; +} + +void release_pack_memory(size_t need, int fd) +{ + size_t cur = pack_mapped; + while (need >= (cur - pack_mapped) && unuse_one_window(NULL, fd)) + ; /* nothing */ +} + +void close_pack_windows(struct packed_git *p) +{ + while (p->windows) { + struct pack_window *w = p->windows; + + if (w->inuse_cnt) + die("pack '%s' still has open windows to it", + p->pack_name); + munmap(w->base, w->len); + pack_mapped -= w->len; + pack_open_windows--; + p->windows = w->next; + free(w); + } +} + +void unuse_pack(struct pack_window **w_cursor) +{ + struct pack_window *w = *w_cursor; + if (w) { + w->inuse_cnt--; + *w_cursor = NULL; + } +} + +/* + * Do not call this directly as this leaks p->pack_fd on error return; + * call open_packed_git() instead. + */ +static int open_packed_git_1(struct packed_git *p) +{ + struct stat st; + struct pack_header hdr; + unsigned char sha1[20]; + unsigned char *idx_sha1; + long fd_flag; + + if (!p->index_data && open_pack_index(p)) + return error("packfile %s index unavailable", p->pack_name); + + p->pack_fd = open(p->pack_name, O_RDONLY); + if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) + return -1; + + /* If we created the struct before we had the pack we lack size. */ + if (!p->pack_size) { + if (!S_ISREG(st.st_mode)) + return error("packfile %s not a regular file", p->pack_name); + p->pack_size = st.st_size; + } else if (p->pack_size != st.st_size) + return error("packfile %s size changed", p->pack_name); + + /* We leave these file descriptors open with sliding mmap; + * there is no point keeping them open across exec(), though. + */ + fd_flag = fcntl(p->pack_fd, F_GETFD, 0); + if (fd_flag < 0) + return error("cannot determine file descriptor flags"); + fd_flag |= FD_CLOEXEC; + if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1) + return error("cannot set FD_CLOEXEC"); + + /* Verify we recognize this pack file format. */ + if (read_in_full(p->pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr)) + return error("file %s is far too short to be a packfile", p->pack_name); + if (hdr.hdr_signature != htonl(PACK_SIGNATURE)) + return error("file %s is not a GIT packfile", p->pack_name); + if (!pack_version_ok(hdr.hdr_version)) + return error("packfile %s is version %"PRIu32" and not" + " supported (try upgrading GIT to a newer version)", + p->pack_name, ntohl(hdr.hdr_version)); + + /* Verify the pack matches its index. */ + if (p->num_objects != ntohl(hdr.hdr_entries)) + return error("packfile %s claims to have %"PRIu32" objects" + " while index indicates %"PRIu32" objects", + p->pack_name, ntohl(hdr.hdr_entries), + p->num_objects); + if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1) + return error("end of packfile %s is unavailable", p->pack_name); + if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1)) + return error("packfile %s signature is unavailable", p->pack_name); + idx_sha1 = ((unsigned char *)p->index_data) + p->index_size - 40; + if (hashcmp(sha1, idx_sha1)) + return error("packfile %s does not match index", p->pack_name); + return 0; +} + +static int open_packed_git(struct packed_git *p) +{ + if (!open_packed_git_1(p)) + return 0; + if (p->pack_fd != -1) { + close(p->pack_fd); + p->pack_fd = -1; + } + return -1; +} + +static int in_window(struct pack_window *win, off_t offset) +{ + /* We must promise at least 20 bytes (one hash) after the + * offset is available from this window, otherwise the offset + * is not actually in this window and a different window (which + * has that one hash excess) must be used. This is to support + * the object header and delta base parsing routines below. + */ + off_t win_off = win->offset; + return win_off <= offset + && (offset + 20) <= (win_off + win->len); +} + +unsigned char* use_pack(struct packed_git *p, + struct pack_window **w_cursor, + off_t offset, + unsigned int *left) +{ + struct pack_window *win = *w_cursor; + + if (p->pack_fd == -1 && open_packed_git(p)) + die("packfile %s cannot be accessed", p->pack_name); + + /* Since packfiles end in a hash of their content and its + * pointless to ask for an offset into the middle of that + * hash, and the in_window function above wouldn't match + * don't allow an offset too close to the end of the file. + */ + if (offset > (p->pack_size - 20)) + die("offset beyond end of packfile (truncated pack?)"); + + if (!win || !in_window(win, offset)) { + if (win) + win->inuse_cnt--; + for (win = p->windows; win; win = win->next) { + if (in_window(win, offset)) + break; + } + if (!win) { + size_t window_align = packed_git_window_size / 2; + off_t len; + win = xcalloc(1, sizeof(*win)); + win->offset = (offset / window_align) * window_align; + len = p->pack_size - win->offset; + if (len > packed_git_window_size) + len = packed_git_window_size; + win->len = (size_t)len; + pack_mapped += win->len; + while (packed_git_limit < pack_mapped + && unuse_one_window(p, p->pack_fd)) + ; /* nothing */ + win->base = xmmap(NULL, win->len, + PROT_READ, MAP_PRIVATE, + p->pack_fd, win->offset); + if (win->base == MAP_FAILED) + die("packfile %s cannot be mapped: %s", + p->pack_name, + strerror(errno)); + pack_mmap_calls++; + pack_open_windows++; + if (pack_mapped > peak_pack_mapped) + peak_pack_mapped = pack_mapped; + if (pack_open_windows > peak_pack_open_windows) + peak_pack_open_windows = pack_open_windows; + win->next = p->windows; + p->windows = win; + } + } + if (win != *w_cursor) { + win->last_used = pack_used_ctr++; + win->inuse_cnt++; + *w_cursor = win; + } + offset -= win->offset; + if (left) + *left = win->len - xsize_t(offset); + return win->base + offset; +} + +static struct packed_git *alloc_packed_git(int extra) +{ + struct packed_git *p = xmalloc(sizeof(*p) + extra); + memset(p, 0, sizeof(*p)); + p->pack_fd = -1; + return p; +} + +struct packed_git *add_packed_git(const char *path, int path_len, int local) +{ + struct stat st; + struct packed_git *p = alloc_packed_git(path_len + 2); + + /* + * Make sure a corresponding .pack file exists and that + * the index looks sane. + */ + path_len -= strlen(".idx"); + if (path_len < 1) { + free(p); + return NULL; + } + memcpy(p->pack_name, path, path_len); + strcpy(p->pack_name + path_len, ".pack"); + if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) { + free(p); + return NULL; + } + + /* ok, it looks sane as far as we can check without + * actually mapping the pack file. + */ + p->pack_size = st.st_size; + p->pack_local = local; + p->mtime = st.st_mtime; + if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1)) + hashclr(p->sha1); + return p; +} + +struct packed_git *parse_pack_index(unsigned char *sha1) +{ + const char *idx_path = sha1_pack_index_name(sha1); + const char *path = sha1_pack_name(sha1); + struct packed_git *p = alloc_packed_git(strlen(path) + 1); + + strcpy(p->pack_name, path); + hashcpy(p->sha1, sha1); + if (check_packed_git_idx(idx_path, p)) { + free(p); + return NULL; + } + + return p; +} + +void install_packed_git(struct packed_git *pack) +{ + pack->next = packed_git; + packed_git = pack; +} + +static void prepare_packed_git_one(char *objdir, int local) +{ + /* Ensure that this buffer is large enough so that we can + append "/pack/" without clobbering the stack even if + strlen(objdir) were PATH_MAX. */ + char path[PATH_MAX + 1 + 4 + 1 + 1]; + int len; + DIR *dir; + struct dirent *de; + + sprintf(path, "%s/pack", objdir); + len = strlen(path); + dir = opendir(path); + if (!dir) { + if (errno != ENOENT) + error("unable to open object pack directory: %s: %s", + path, strerror(errno)); + return; + } + path[len++] = '/'; + while ((de = readdir(dir)) != NULL) { + int namelen = strlen(de->d_name); + struct packed_git *p; + + if (!has_extension(de->d_name, ".idx")) + continue; + + if (len + namelen + 1 > sizeof(path)) + continue; + + /* Don't reopen a pack we already have. */ + strcpy(path + len, de->d_name); + for (p = packed_git; p; p = p->next) { + if (!memcmp(path, p->pack_name, len + namelen - 4)) + break; + } + if (p) + continue; + /* See if it really is a valid .idx file with corresponding + * .pack file that we can map. + */ + p = add_packed_git(path, len + namelen, local); + if (!p) + continue; + install_packed_git(p); + } + closedir(dir); +} + +static int sort_pack(const void *a_, const void *b_) +{ + struct packed_git *a = *((struct packed_git **)a_); + struct packed_git *b = *((struct packed_git **)b_); + int st; + + /* + * Local packs tend to contain objects specific to our + * variant of the project than remote ones. In addition, + * remote ones could be on a network mounted filesystem. + * Favor local ones for these reasons. + */ + st = a->pack_local - b->pack_local; + if (st) + return -st; + + /* + * Younger packs tend to contain more recent objects, + * and more recent objects tend to get accessed more + * often. + */ + if (a->mtime < b->mtime) + return 1; + else if (a->mtime == b->mtime) + return 0; + return -1; +} + +static void rearrange_packed_git(void) +{ + struct packed_git **ary, *p; + int i, n; + + for (n = 0, p = packed_git; p; p = p->next) + n++; + if (n < 2) + return; + + /* prepare an array of packed_git for easier sorting */ + ary = xcalloc(n, sizeof(struct packed_git *)); + for (n = 0, p = packed_git; p; p = p->next) + ary[n++] = p; + + qsort(ary, n, sizeof(struct packed_git *), sort_pack); + + /* link them back again */ + for (i = 0; i < n - 1; i++) + ary[i]->next = ary[i + 1]; + ary[n - 1]->next = NULL; + packed_git = ary[0]; + + free(ary); +} + +static int prepare_packed_git_run_once = 0; +void prepare_packed_git(void) +{ + struct alternate_object_database *alt; + + if (prepare_packed_git_run_once) + return; + prepare_packed_git_one(get_object_directory(), 1); + prepare_alt_odb(); + for (alt = alt_odb_list; alt; alt = alt->next) { + alt->name[-1] = 0; + prepare_packed_git_one(alt->base, 0); + alt->name[-1] = '/'; + } + rearrange_packed_git(); + prepare_packed_git_run_once = 1; +} + +void reprepare_packed_git(void) +{ + prepare_packed_git_run_once = 0; + prepare_packed_git(); +} + +static void mark_bad_packed_object(struct packed_git *p, + const unsigned char *sha1) +{ + unsigned i; + for (i = 0; i < p->num_bad_objects; i++) + if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) + return; + p->bad_object_sha1 = xrealloc(p->bad_object_sha1, 20 * (p->num_bad_objects + 1)); + hashcpy(p->bad_object_sha1 + 20 * p->num_bad_objects, sha1); + p->num_bad_objects++; +} + +static int has_packed_and_bad(const unsigned char *sha1) +{ + struct packed_git *p; + unsigned i; + + for (p = packed_git; p; p = p->next) + for (i = 0; i < p->num_bad_objects; i++) + if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) + return 1; + return 0; +} + +int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type) +{ + unsigned char real_sha1[20]; + hash_sha1_file(map, size, type, real_sha1); + return hashcmp(sha1, real_sha1) ? -1 : 0; +} + +static int git_open_noatime(const char *name) +{ + static int sha1_file_open_flag = O_NOATIME; + int fd = open(name, O_RDONLY | sha1_file_open_flag); + + /* Might the failure be due to O_NOATIME? */ + if (fd < 0 && errno != ENOENT && sha1_file_open_flag) { + fd = open(name, O_RDONLY); + if (fd >= 0) + sha1_file_open_flag = 0; + } + return fd; +} + +static int open_sha1_file(const unsigned char *sha1) +{ + int fd; + char *name = sha1_file_name(sha1); + struct alternate_object_database *alt; + + fd = git_open_noatime(name); + if (fd >= 0) + return fd; + + prepare_alt_odb(); + errno = ENOENT; + for (alt = alt_odb_list; alt; alt = alt->next) { + name = alt->name; + fill_sha1_path(name, sha1); + fd = git_open_noatime(alt->base); + if (fd >= 0) + return fd; + } + return -1; +} + +static void *map_sha1_file(const unsigned char *sha1, unsigned long *size) +{ + void *map; + int fd; + + fd = open_sha1_file(sha1); + map = NULL; + if (fd >= 0) { + struct stat st; + + if (!fstat(fd, &st)) { + *size = xsize_t(st.st_size); + map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0); + } + close(fd); + } + return map; +} + +static int legacy_loose_object(unsigned char *map) +{ + unsigned int word; + + /* + * Is it a zlib-compressed buffer? If so, the first byte + * must be 0x78 (15-bit window size, deflated), and the + * first 16-bit word is evenly divisible by 31 + */ + word = (map[0] << 8) + map[1]; + if (map[0] == 0x78 && !(word % 31)) + return 1; + else + return 0; +} + +unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep) +{ + unsigned shift; + unsigned char c; + unsigned long size; + unsigned long used = 0; + + c = buf[used++]; + *type = (c >> 4) & 7; + size = c & 15; + shift = 4; + while (c & 0x80) { + if (len <= used) + return 0; + if (sizeof(long) * 8 <= shift) + return 0; + c = buf[used++]; + size += (c & 0x7f) << shift; + shift += 7; + } + *sizep = size; + return used; +} + +static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz) +{ + unsigned long size, used; + static const char valid_loose_object_type[8] = { + 0, /* OBJ_EXT */ + 1, 1, 1, 1, /* "commit", "tree", "blob", "tag" */ + 0, /* "delta" and others are invalid in a loose object */ + }; + enum object_type type; + + /* Get the data stream */ + memset(stream, 0, sizeof(*stream)); + stream->next_in = map; + stream->avail_in = mapsize; + stream->next_out = buffer; + stream->avail_out = bufsiz; + + if (legacy_loose_object(map)) { + inflateInit(stream); + return inflate(stream, 0); + } + + + /* + * There used to be a second loose object header format which + * was meant to mimic the in-pack format, allowing for direct + * copy of the object data. This format turned up not to be + * really worth it and we don't write it any longer. But we + * can still read it. + */ + used = unpack_object_header_gently(map, mapsize, &type, &size); + if (!used || !valid_loose_object_type[type]) + return -1; + map += used; + mapsize -= used; + + /* Set up the stream for the rest.. */ + stream->next_in = map; + stream->avail_in = mapsize; + inflateInit(stream); + + /* And generate the fake traditional header */ + stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu", + typename(type), size); + return 0; +} + +static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1) +{ + int bytes = strlen(buffer) + 1; + unsigned char *buf = xmalloc(1+size); + unsigned long n; + int status = Z_OK; + + n = stream->total_out - bytes; + if (n > size) + n = size; + memcpy(buf, (char *) buffer + bytes, n); + bytes = n; + if (bytes <= size) { + /* + * The above condition must be (bytes <= size), not + * (bytes < size). In other words, even though we + * expect no more output and set avail_out to zer0, + * the input zlib stream may have bytes that express + * "this concludes the stream", and we *do* want to + * eat that input. + * + * Otherwise we would not be able to test that we + * consumed all the input to reach the expected size; + * we also want to check that zlib tells us that all + * went well with status == Z_STREAM_END at the end. + */ + stream->next_out = buf + bytes; + stream->avail_out = size - bytes; + while (status == Z_OK) + status = inflate(stream, Z_FINISH); + } + buf[size] = 0; + if (status == Z_STREAM_END && !stream->avail_in) { + inflateEnd(stream); + return buf; + } + + if (status < 0) + error("corrupt loose object '%s'", sha1_to_hex(sha1)); + else if (stream->avail_in) + error("garbage at end of loose object '%s'", + sha1_to_hex(sha1)); + free(buf); + return NULL; +} + +/* + * We used to just use "sscanf()", but that's actually way + * too permissive for what we want to check. So do an anal + * object header parse by hand. + */ +static int parse_sha1_header(const char *hdr, unsigned long *sizep) +{ + char type[10]; + int i; + unsigned long size; + + /* + * The type can be at most ten bytes (including the + * terminating '\0' that we add), and is followed by + * a space. + */ + i = 0; + for (;;) { + char c = *hdr++; + if (c == ' ') + break; + type[i++] = c; + if (i >= sizeof(type)) + return -1; + } + type[i] = 0; + + /* + * The length must follow immediately, and be in canonical + * decimal format (ie "010" is not valid). + */ + size = *hdr++ - '0'; + if (size > 9) + return -1; + if (size) { + for (;;) { + unsigned long c = *hdr - '0'; + if (c > 9) + break; + hdr++; + size = size * 10 + c; + } + } + *sizep = size; + + /* + * The length must be followed by a zero byte + */ + return *hdr ? -1 : type_from_string(type); +} + +static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1) +{ + int ret; + z_stream stream; + char hdr[8192]; + + ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)); + if (ret < Z_OK || (*type = parse_sha1_header(hdr, size)) < 0) + return NULL; + + return unpack_sha1_rest(&stream, hdr, *size, sha1); +} + +unsigned long get_size_from_delta(struct packed_git *p, + struct pack_window **w_curs, + off_t curpos) +{ + const unsigned char *data; + unsigned char delta_head[20], *in; + z_stream stream; + int st; + + memset(&stream, 0, sizeof(stream)); + stream.next_out = delta_head; + stream.avail_out = sizeof(delta_head); + + inflateInit(&stream); + do { + in = use_pack(p, w_curs, curpos, &stream.avail_in); + stream.next_in = in; + st = inflate(&stream, Z_FINISH); + curpos += stream.next_in - in; + } while ((st == Z_OK || st == Z_BUF_ERROR) && + stream.total_out < sizeof(delta_head)); + inflateEnd(&stream); + if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) + die("delta data unpack-initial failed"); + + /* Examine the initial part of the delta to figure out + * the result size. + */ + data = delta_head; + + /* ignore base size */ + get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); + + /* Read the result size */ + return get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); +} + +static off_t get_delta_base(struct packed_git *p, + struct pack_window **w_curs, + off_t *curpos, + enum object_type type, + off_t delta_obj_offset) +{ + unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL); + off_t base_offset; + + /* use_pack() assured us we have [base_info, base_info + 20) + * as a range that we can look at without walking off the + * end of the mapped window. Its actually the hash size + * that is assured. An OFS_DELTA longer than the hash size + * is stupid, as then a REF_DELTA would be smaller to store. + */ + if (type == OBJ_OFS_DELTA) { + unsigned used = 0; + unsigned char c = base_info[used++]; + base_offset = c & 127; + while (c & 128) { + base_offset += 1; + if (!base_offset || MSB(base_offset, 7)) + return 0; /* overflow */ + c = base_info[used++]; + base_offset = (base_offset << 7) + (c & 127); + } + base_offset = delta_obj_offset - base_offset; + if (base_offset >= delta_obj_offset) + return 0; /* out of bound */ + *curpos += used; + } else if (type == OBJ_REF_DELTA) { + /* The base entry _must_ be in the same pack */ + base_offset = find_pack_entry_one(base_info, p); + *curpos += 20; + } else + die("I am totally screwed"); + return base_offset; +} + +/* forward declaration for a mutually recursive function */ +static int packed_object_info(struct packed_git *p, off_t offset, + unsigned long *sizep); + +static int packed_delta_info(struct packed_git *p, + struct pack_window **w_curs, + off_t curpos, + enum object_type type, + off_t obj_offset, + unsigned long *sizep) +{ + off_t base_offset; + + base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset); + type = packed_object_info(p, base_offset, NULL); + + /* We choose to only get the type of the base object and + * ignore potentially corrupt pack file that expects the delta + * based on a base with a wrong size. This saves tons of + * inflate() calls. + */ + if (sizep) + *sizep = get_size_from_delta(p, w_curs, curpos); + + return type; +} + +static int unpack_object_header(struct packed_git *p, + struct pack_window **w_curs, + off_t *curpos, + unsigned long *sizep) +{ + unsigned char *base; + unsigned int left; + unsigned long used; + enum object_type type; + + /* use_pack() assures us we have [base, base + 20) available + * as a range that we can look at at. (Its actually the hash + * size that is assured.) With our object header encoding + * the maximum deflated object size is 2^137, which is just + * insane, so we know won't exceed what we have been given. + */ + base = use_pack(p, w_curs, *curpos, &left); + used = unpack_object_header_gently(base, left, &type, sizep); + if (!used) + die("object offset outside of pack file"); + *curpos += used; + + return type; +} + +const char *packed_object_info_detail(struct packed_git *p, + off_t obj_offset, + unsigned long *size, + unsigned long *store_size, + unsigned int *delta_chain_length, + unsigned char *base_sha1) +{ + struct pack_window *w_curs = NULL; + off_t curpos; + unsigned long dummy; + unsigned char *next_sha1; + enum object_type type; + struct revindex_entry *revidx; + + *delta_chain_length = 0; + curpos = obj_offset; + type = unpack_object_header(p, &w_curs, &curpos, size); + + revidx = find_pack_revindex(p, obj_offset); + *store_size = revidx[1].offset - obj_offset; + + for (;;) { + switch (type) { + default: + die("pack %s contains unknown object type %d", + p->pack_name, type); + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + unuse_pack(&w_curs); + return typename(type); + case OBJ_OFS_DELTA: + obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset); + if (!obj_offset) + die("pack %s contains bad delta base reference of type %s", + p->pack_name, typename(type)); + if (*delta_chain_length == 0) { + revidx = find_pack_revindex(p, obj_offset); + hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr)); + } + break; + case OBJ_REF_DELTA: + next_sha1 = use_pack(p, &w_curs, curpos, NULL); + if (*delta_chain_length == 0) + hashcpy(base_sha1, next_sha1); + obj_offset = find_pack_entry_one(next_sha1, p); + break; + } + (*delta_chain_length)++; + curpos = obj_offset; + type = unpack_object_header(p, &w_curs, &curpos, &dummy); + } +} + +static int packed_object_info(struct packed_git *p, off_t obj_offset, + unsigned long *sizep) +{ + struct pack_window *w_curs = NULL; + unsigned long size; + off_t curpos = obj_offset; + enum object_type type; + + type = unpack_object_header(p, &w_curs, &curpos, &size); + + switch (type) { + case OBJ_OFS_DELTA: + case OBJ_REF_DELTA: + type = packed_delta_info(p, &w_curs, curpos, + type, obj_offset, sizep); + break; + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + if (sizep) + *sizep = size; + break; + default: + die("pack %s contains unknown object type %d", + p->pack_name, type); + } + unuse_pack(&w_curs); + return type; +} + +static void *unpack_compressed_entry(struct packed_git *p, + struct pack_window **w_curs, + off_t curpos, + unsigned long size) +{ + int st; + z_stream stream; + unsigned char *buffer, *in; + + buffer = xmalloc(size + 1); + buffer[size] = 0; + memset(&stream, 0, sizeof(stream)); + stream.next_out = buffer; + stream.avail_out = size; + + inflateInit(&stream); + do { + in = use_pack(p, w_curs, curpos, &stream.avail_in); + stream.next_in = in; + st = inflate(&stream, Z_FINISH); + curpos += stream.next_in - in; + } while (st == Z_OK || st == Z_BUF_ERROR); + inflateEnd(&stream); + if ((st != Z_STREAM_END) || stream.total_out != size) { + free(buffer); + return NULL; + } + + return buffer; +} + +#define MAX_DELTA_CACHE (256) + +static size_t delta_base_cached; + +static struct delta_base_cache_lru_list { + struct delta_base_cache_lru_list *prev; + struct delta_base_cache_lru_list *next; +} delta_base_cache_lru = { &delta_base_cache_lru, &delta_base_cache_lru }; + +static struct delta_base_cache_entry { + struct delta_base_cache_lru_list lru; + void *data; + struct packed_git *p; + off_t base_offset; + unsigned long size; + enum object_type type; +} delta_base_cache[MAX_DELTA_CACHE]; + +static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset) +{ + unsigned long hash; + + hash = (unsigned long)p + (unsigned long)base_offset; + hash += (hash >> 8) + (hash >> 16); + return hash % MAX_DELTA_CACHE; +} + +static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset, + unsigned long *base_size, enum object_type *type, int keep_cache) +{ + void *ret; + unsigned long hash = pack_entry_hash(p, base_offset); + struct delta_base_cache_entry *ent = delta_base_cache + hash; + + ret = ent->data; + if (ret && ent->p == p && ent->base_offset == base_offset) + goto found_cache_entry; + return unpack_entry(p, base_offset, type, base_size); + +found_cache_entry: + if (!keep_cache) { + ent->data = NULL; + ent->lru.next->prev = ent->lru.prev; + ent->lru.prev->next = ent->lru.next; + delta_base_cached -= ent->size; + } else { + ret = xmemdupz(ent->data, ent->size); + } + *type = ent->type; + *base_size = ent->size; + return ret; +} + +static inline void release_delta_base_cache(struct delta_base_cache_entry *ent) +{ + if (ent->data) { + free(ent->data); + ent->data = NULL; + ent->lru.next->prev = ent->lru.prev; + ent->lru.prev->next = ent->lru.next; + delta_base_cached -= ent->size; + } +} + +static void add_delta_base_cache(struct packed_git *p, off_t base_offset, + void *base, unsigned long base_size, enum object_type type) +{ + unsigned long hash = pack_entry_hash(p, base_offset); + struct delta_base_cache_entry *ent = delta_base_cache + hash; + struct delta_base_cache_lru_list *lru; + + release_delta_base_cache(ent); + delta_base_cached += base_size; + + for (lru = delta_base_cache_lru.next; + delta_base_cached > delta_base_cache_limit + && lru != &delta_base_cache_lru; + lru = lru->next) { + struct delta_base_cache_entry *f = (void *)lru; + if (f->type == OBJ_BLOB) + release_delta_base_cache(f); + } + for (lru = delta_base_cache_lru.next; + delta_base_cached > delta_base_cache_limit + && lru != &delta_base_cache_lru; + lru = lru->next) { + struct delta_base_cache_entry *f = (void *)lru; + release_delta_base_cache(f); + } + + ent->p = p; + ent->base_offset = base_offset; + ent->type = type; + ent->data = base; + ent->size = base_size; + ent->lru.next = &delta_base_cache_lru; + ent->lru.prev = delta_base_cache_lru.prev; + delta_base_cache_lru.prev->next = &ent->lru; + delta_base_cache_lru.prev = &ent->lru; +} + +static void *unpack_delta_entry(struct packed_git *p, + struct pack_window **w_curs, + off_t curpos, + unsigned long delta_size, + off_t obj_offset, + enum object_type *type, + unsigned long *sizep) +{ + void *delta_data, *result, *base; + unsigned long base_size; + off_t base_offset; + + base_offset = get_delta_base(p, w_curs, &curpos, *type, obj_offset); + if (!base_offset) { + error("failed to validate delta base reference " + "at offset %"PRIuMAX" from %s", + (uintmax_t)curpos, p->pack_name); + return NULL; + } + unuse_pack(w_curs); + base = cache_or_unpack_entry(p, base_offset, &base_size, type, 0); + if (!base) { + /* + * We're probably in deep shit, but let's try to fetch + * the required base anyway from another pack or loose. + * This is costly but should happen only in the presence + * of a corrupted pack, and is better than failing outright. + */ + struct revindex_entry *revidx = find_pack_revindex(p, base_offset); + const unsigned char *base_sha1 = + nth_packed_object_sha1(p, revidx->nr); + error("failed to read delta base object %s" + " at offset %"PRIuMAX" from %s", + sha1_to_hex(base_sha1), (uintmax_t)base_offset, + p->pack_name); + mark_bad_packed_object(p, base_sha1); + base = read_object(base_sha1, type, &base_size); + if (!base) + return NULL; + } + + delta_data = unpack_compressed_entry(p, w_curs, curpos, delta_size); + if (!delta_data) { + error("failed to unpack compressed delta " + "at offset %"PRIuMAX" from %s", + (uintmax_t)curpos, p->pack_name); + free(base); + return NULL; + } + result = patch_delta(base, base_size, + delta_data, delta_size, + sizep); + if (!result) + die("failed to apply delta"); + free(delta_data); + add_delta_base_cache(p, base_offset, base, base_size, *type); + return result; +} + +void *unpack_entry(struct packed_git *p, off_t obj_offset, + enum object_type *type, unsigned long *sizep) +{ + struct pack_window *w_curs = NULL; + off_t curpos = obj_offset; + void *data; + + *type = unpack_object_header(p, &w_curs, &curpos, sizep); + switch (*type) { + case OBJ_OFS_DELTA: + case OBJ_REF_DELTA: + data = unpack_delta_entry(p, &w_curs, curpos, *sizep, + obj_offset, type, sizep); + break; + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + data = unpack_compressed_entry(p, &w_curs, curpos, *sizep); + break; + default: + data = NULL; + error("unknown object type %i at offset %"PRIuMAX" in %s", + *type, (uintmax_t)obj_offset, p->pack_name); + } + unuse_pack(&w_curs); + return data; +} + +const unsigned char *nth_packed_object_sha1(struct packed_git *p, + uint32_t n) +{ + const unsigned char *index = p->index_data; + if (!index) { + if (open_pack_index(p)) + return NULL; + index = p->index_data; + } + if (n >= p->num_objects) + return NULL; + index += 4 * 256; + if (p->index_version == 1) { + return index + 24 * n + 4; + } else { + index += 8; + return index + 20 * n; + } +} + +off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n) +{ + const unsigned char *index = p->index_data; + index += 4 * 256; + if (p->index_version == 1) { + return ntohl(*((uint32_t *)(index + 24 * n))); + } else { + uint32_t off; + index += 8 + p->num_objects * (20 + 4); + off = ntohl(*((uint32_t *)(index + 4 * n))); + if (!(off & 0x80000000)) + return off; + index += p->num_objects * 4 + (off & 0x7fffffff) * 8; + return (((uint64_t)ntohl(*((uint32_t *)(index + 0)))) << 32) | + ntohl(*((uint32_t *)(index + 4))); + } +} + +off_t find_pack_entry_one(const unsigned char *sha1, + struct packed_git *p) +{ + const uint32_t *level1_ofs = p->index_data; + const unsigned char *index = p->index_data; + unsigned hi, lo, stride; + static int use_lookup = -1; + static int debug_lookup = -1; + + if (debug_lookup < 0) + debug_lookup = !!getenv("GIT_DEBUG_LOOKUP"); + + if (!index) { + if (open_pack_index(p)) + return 0; + level1_ofs = p->index_data; + index = p->index_data; + } + if (p->index_version > 1) { + level1_ofs += 2; + index += 8; + } + index += 4 * 256; + hi = ntohl(level1_ofs[*sha1]); + lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1])); + if (p->index_version > 1) { + stride = 20; + } else { + stride = 24; + index += 4; + } + + if (debug_lookup) + printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n", + sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects); + + if (use_lookup < 0) + use_lookup = !!getenv("GIT_USE_LOOKUP"); + if (use_lookup) { + int pos = sha1_entry_pos(index, stride, 0, + lo, hi, p->num_objects, sha1); + if (pos < 0) + return 0; + return nth_packed_object_offset(p, pos); + } + + do { + unsigned mi = (lo + hi) / 2; + int cmp = hashcmp(index + mi * stride, sha1); + + if (debug_lookup) + printf("lo %u hi %u rg %u mi %u\n", + lo, hi, hi - lo, mi); + if (!cmp) + return nth_packed_object_offset(p, mi); + if (cmp > 0) + hi = mi; + else + lo = mi+1; + } while (lo < hi); + return 0; +} + +int matches_pack_name(struct packed_git *p, const char *name) +{ + const char *last_c, *c; + + if (!strcmp(p->pack_name, name)) + return 1; + + for (c = p->pack_name, last_c = c; *c;) + if (*c == '/') + last_c = ++c; + else + ++c; + if (!strcmp(last_c, name)) + return 1; + + return 0; +} + +static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, const char **ignore_packed) +{ + static struct packed_git *last_found = (void *)1; + struct packed_git *p; + off_t offset; + + prepare_packed_git(); + if (!packed_git) + return 0; + p = (last_found == (void *)1) ? packed_git : last_found; + + do { + if (ignore_packed) { + const char **ig; + for (ig = ignore_packed; *ig; ig++) + if (matches_pack_name(p, *ig)) + break; + if (*ig) + goto next; + } + + if (p->num_bad_objects) { + unsigned i; + for (i = 0; i < p->num_bad_objects; i++) + if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) + goto next; + } + + offset = find_pack_entry_one(sha1, p); + if (offset) { + /* + * We are about to tell the caller where they can + * locate the requested object. We better make + * sure the packfile is still here and can be + * accessed before supplying that answer, as + * it may have been deleted since the index + * was loaded! + */ + if (p->pack_fd == -1 && open_packed_git(p)) { + error("packfile %s cannot be accessed", p->pack_name); + goto next; + } + e->offset = offset; + e->p = p; + hashcpy(e->sha1, sha1); + last_found = p; + return 1; + } + + next: + if (p == last_found) + p = packed_git; + else + p = p->next; + if (p == last_found) + p = p->next; + } while (p); + return 0; +} + +struct packed_git *find_sha1_pack(const unsigned char *sha1, + struct packed_git *packs) +{ + struct packed_git *p; + + for (p = packs; p; p = p->next) { + if (find_pack_entry_one(sha1, p)) + return p; + } + return NULL; + +} + +static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *sizep) +{ + int status; + unsigned long mapsize, size; + void *map; + z_stream stream; + char hdr[32]; + + map = map_sha1_file(sha1, &mapsize); + if (!map) + return error("unable to find %s", sha1_to_hex(sha1)); + if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) + status = error("unable to unpack %s header", + sha1_to_hex(sha1)); + else if ((status = parse_sha1_header(hdr, &size)) < 0) + status = error("unable to parse %s header", sha1_to_hex(sha1)); + else if (sizep) + *sizep = size; + inflateEnd(&stream); + munmap(map, mapsize); + return status; +} + +int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) +{ + struct pack_entry e; + int status; + + if (!find_pack_entry(sha1, &e, NULL)) { + /* Most likely it's a loose object. */ + status = sha1_loose_object_info(sha1, sizep); + if (status >= 0) + return status; + + /* Not a loose object; someone else may have just packed it. */ + reprepare_packed_git(); + if (!find_pack_entry(sha1, &e, NULL)) + return status; + } + return packed_object_info(e.p, e.offset, sizep); +} + +static void *read_packed_sha1(const unsigned char *sha1, + enum object_type *type, unsigned long *size) +{ + struct pack_entry e; + void *data; + + if (!find_pack_entry(sha1, &e, NULL)) + return NULL; + data = cache_or_unpack_entry(e.p, e.offset, size, type, 1); + if (!data) { + /* + * We're probably in deep shit, but let's try to fetch + * the required object anyway from another pack or loose. + * This should happen only in the presence of a corrupted + * pack, and is better than failing outright. + */ + error("failed to read object %s at offset %"PRIuMAX" from %s", + sha1_to_hex(sha1), (uintmax_t)e.offset, e.p->pack_name); + mark_bad_packed_object(e.p, sha1); + data = read_object(sha1, type, size); + } + return data; +} + +/* + * This is meant to hold a *small* number of objects that you would + * want read_sha1_file() to be able to return, but yet you do not want + * to write them into the object store (e.g. a browse-only + * application). + */ +static struct cached_object { + unsigned char sha1[20]; + enum object_type type; + void *buf; + unsigned long size; +} *cached_objects; +static int cached_object_nr, cached_object_alloc; + +static struct cached_object empty_tree = { + /* empty tree sha1: 4b825dc642cb6eb9a060e54bf8d69288fbee4904 */ + "\x4b\x82\x5d\xc6\x42\xcb\x6e\xb9\xa0\x60" + "\xe5\x4b\xf8\xd6\x92\x88\xfb\xee\x49\x04", + OBJ_TREE, + "", + 0 +}; + +static struct cached_object *find_cached_object(const unsigned char *sha1) +{ + int i; + struct cached_object *co = cached_objects; + + for (i = 0; i < cached_object_nr; i++, co++) { + if (!hashcmp(co->sha1, sha1)) + return co; + } + if (!hashcmp(sha1, empty_tree.sha1)) + return &empty_tree; + return NULL; +} + +int pretend_sha1_file(void *buf, unsigned long len, enum object_type type, + unsigned char *sha1) +{ + struct cached_object *co; + + hash_sha1_file(buf, len, typename(type), sha1); + if (has_sha1_file(sha1) || find_cached_object(sha1)) + return 0; + if (cached_object_alloc <= cached_object_nr) { + cached_object_alloc = alloc_nr(cached_object_alloc); + cached_objects = xrealloc(cached_objects, + sizeof(*cached_objects) * + cached_object_alloc); + } + co = &cached_objects[cached_object_nr++]; + co->size = len; + co->type = type; + co->buf = xmalloc(len); + memcpy(co->buf, buf, len); + hashcpy(co->sha1, sha1); + return 0; +} + +void *read_object(const unsigned char *sha1, enum object_type *type, + unsigned long *size) +{ + unsigned long mapsize; + void *map, *buf; + struct cached_object *co; + + co = find_cached_object(sha1); + if (co) { + *type = co->type; + *size = co->size; + return xmemdupz(co->buf, co->size); + } + + buf = read_packed_sha1(sha1, type, size); + if (buf) + return buf; + map = map_sha1_file(sha1, &mapsize); + if (map) { + buf = unpack_sha1_file(map, mapsize, type, size, sha1); + munmap(map, mapsize); + return buf; + } + reprepare_packed_git(); + return read_packed_sha1(sha1, type, size); +} + +void *read_sha1_file(const unsigned char *sha1, enum object_type *type, + unsigned long *size) +{ + void *data = read_object(sha1, type, size); + /* legacy behavior is to die on corrupted objects */ + if (!data && (has_loose_object(sha1) || has_packed_and_bad(sha1))) + die("object %s is corrupted", sha1_to_hex(sha1)); + return data; +} + +void *read_object_with_reference(const unsigned char *sha1, + const char *required_type_name, + unsigned long *size, + unsigned char *actual_sha1_return) +{ + enum object_type type, required_type; + void *buffer; + unsigned long isize; + unsigned char actual_sha1[20]; + + required_type = type_from_string(required_type_name); + hashcpy(actual_sha1, sha1); + while (1) { + int ref_length = -1; + const char *ref_type = NULL; + + buffer = read_sha1_file(actual_sha1, &type, &isize); + if (!buffer) + return NULL; + if (type == required_type) { + *size = isize; + if (actual_sha1_return) + hashcpy(actual_sha1_return, actual_sha1); + return buffer; + } + /* Handle references */ + else if (type == OBJ_COMMIT) + ref_type = "tree "; + else if (type == OBJ_TAG) + ref_type = "object "; + else { + free(buffer); + return NULL; + } + ref_length = strlen(ref_type); + + if (ref_length + 40 > isize || + memcmp(buffer, ref_type, ref_length) || + get_sha1_hex((char *) buffer + ref_length, actual_sha1)) { + free(buffer); + return NULL; + } + free(buffer); + /* Now we have the ID of the referred-to object in + * actual_sha1. Check again. */ + } +} + +static void write_sha1_file_prepare(const void *buf, unsigned long len, + const char *type, unsigned char *sha1, + char *hdr, int *hdrlen) +{ + SHA_CTX c; + + /* Generate the header */ + *hdrlen = sprintf(hdr, "%s %lu", type, len)+1; + + /* Sha1.. */ + SHA1_Init(&c); + SHA1_Update(&c, hdr, *hdrlen); + SHA1_Update(&c, buf, len); + SHA1_Final(sha1, &c); +} + +/* + * Move the just written object into its final resting place + */ +int move_temp_to_file(const char *tmpfile, const char *filename) +{ + int ret = link(tmpfile, filename); + + /* + * Coda hack - coda doesn't like cross-directory links, + * so we fall back to a rename, which will mean that it + * won't be able to check collisions, but that's not a + * big deal. + * + * The same holds for FAT formatted media. + * + * When this succeeds, we just return 0. We have nothing + * left to unlink. + */ + if (ret && ret != EEXIST) { + if (!rename(tmpfile, filename)) + return 0; + ret = errno; + } + unlink(tmpfile); + if (ret) { + if (ret != EEXIST) { + return error("unable to write sha1 filename %s: %s\n", filename, strerror(ret)); + } + /* FIXME!!! Collision check here ? */ + } + + return 0; +} + +static int write_buffer(int fd, const void *buf, size_t len) +{ + if (write_in_full(fd, buf, len) < 0) + return error("file write error (%s)", strerror(errno)); + return 0; +} + +int hash_sha1_file(const void *buf, unsigned long len, const char *type, + unsigned char *sha1) +{ + char hdr[32]; + int hdrlen; + write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen); + return 0; +} + +/* Finalize a file on disk, and close it. */ +static void close_sha1_file(int fd) +{ + if (fsync_object_files) + fsync_or_die(fd, "sha1 file"); + fchmod(fd, 0444); + if (close(fd) != 0) + die("unable to write sha1 file"); +} + +/* Size of directory component, including the ending '/' */ +static inline int directory_size(const char *filename) +{ + const char *s = strrchr(filename, '/'); + if (!s) + return 0; + return s - filename + 1; +} + +/* + * This creates a temporary file in the same directory as the final + * 'filename' + * + * We want to avoid cross-directory filename renames, because those + * can have problems on various filesystems (FAT, NFS, Coda). + */ +static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename) +{ + int fd, dirlen = directory_size(filename); + + if (dirlen + 20 > bufsiz) { + errno = ENAMETOOLONG; + return -1; + } + memcpy(buffer, filename, dirlen); + strcpy(buffer + dirlen, "tmp_obj_XXXXXX"); + fd = mkstemp(buffer); + if (fd < 0 && dirlen) { + /* Make sure the directory exists */ + memcpy(buffer, filename, dirlen); + buffer[dirlen-1] = 0; + if (mkdir(buffer, 0777) || adjust_shared_perm(buffer)) + return -1; + + /* Try again */ + strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX"); + fd = mkstemp(buffer); + } + return fd; +} + +static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, + void *buf, unsigned long len, time_t mtime) +{ + int fd, size, ret; + unsigned char *compressed; + z_stream stream; + char *filename; + static char tmpfile[PATH_MAX]; + + filename = sha1_file_name(sha1); + fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename); + if (fd < 0) { + if (errno == EPERM) + return error("insufficient permission for adding an object to repository database %s\n", get_object_directory()); + else + return error("unable to create temporary sha1 filename %s: %s\n", tmpfile, strerror(errno)); + } + + /* Set it up */ + memset(&stream, 0, sizeof(stream)); + deflateInit(&stream, zlib_compression_level); + size = 8 + deflateBound(&stream, len+hdrlen); + compressed = xmalloc(size); + + /* Compress it */ + stream.next_out = compressed; + stream.avail_out = size; + + /* First header.. */ + stream.next_in = (unsigned char *)hdr; + stream.avail_in = hdrlen; + while (deflate(&stream, 0) == Z_OK) + /* nothing */; + + /* Then the data itself.. */ + stream.next_in = buf; + stream.avail_in = len; + ret = deflate(&stream, Z_FINISH); + if (ret != Z_STREAM_END) + die("unable to deflate new object %s (%d)", sha1_to_hex(sha1), ret); + + ret = deflateEnd(&stream); + if (ret != Z_OK) + die("deflateEnd on object %s failed (%d)", sha1_to_hex(sha1), ret); + + size = stream.total_out; + + if (write_buffer(fd, compressed, size) < 0) + die("unable to write sha1 file"); + close_sha1_file(fd); + free(compressed); + + if (mtime) { + struct utimbuf utb; + utb.actime = mtime; + utb.modtime = mtime; + if (utime(tmpfile, &utb) < 0) + warning("failed utime() on %s: %s", + tmpfile, strerror(errno)); + } + + return move_temp_to_file(tmpfile, filename); +} + +int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1) +{ + unsigned char sha1[20]; + char hdr[32]; + int hdrlen; + + /* Normally if we have it in the pack then we do not bother writing + * it out into .git/objects/??/?{38} file. + */ + write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen); + if (returnsha1) + hashcpy(returnsha1, sha1); + if (has_sha1_file(sha1)) + return 0; + return write_loose_object(sha1, hdr, hdrlen, buf, len, 0); +} + +int force_object_loose(const unsigned char *sha1, time_t mtime) +{ + void *buf; + unsigned long len; + enum object_type type; + char hdr[32]; + int hdrlen; + + if (has_loose_object(sha1)) + return 0; + buf = read_packed_sha1(sha1, &type, &len); + if (!buf) + return error("cannot read sha1_file for %s", sha1_to_hex(sha1)); + hdrlen = sprintf(hdr, "%s %lu", typename(type), len) + 1; + return write_loose_object(sha1, hdr, hdrlen, buf, len, mtime); +} + +int has_pack_index(const unsigned char *sha1) +{ + struct stat st; + if (stat(sha1_pack_index_name(sha1), &st)) + return 0; + return 1; +} + +int has_pack_file(const unsigned char *sha1) +{ + struct stat st; + if (stat(sha1_pack_name(sha1), &st)) + return 0; + return 1; +} + +int has_sha1_pack(const unsigned char *sha1, const char **ignore_packed) +{ + struct pack_entry e; + return find_pack_entry(sha1, &e, ignore_packed); +} + +int has_sha1_file(const unsigned char *sha1) +{ + struct pack_entry e; + + if (find_pack_entry(sha1, &e, NULL)) + return 1; + return has_loose_object(sha1); +} + +int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object) +{ + struct strbuf buf; + int ret; + + strbuf_init(&buf, 0); + if (strbuf_read(&buf, fd, 4096) < 0) { + strbuf_release(&buf); + return -1; + } + + if (!type) + type = blob_type; + if (write_object) + ret = write_sha1_file(buf.buf, buf.len, type, sha1); + else + ret = hash_sha1_file(buf.buf, buf.len, type, sha1); + strbuf_release(&buf); + + return ret; +} + +int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, + enum object_type type, const char *path) +{ + size_t size = xsize_t(st->st_size); + void *buf = NULL; + int ret, re_allocated = 0; + + if (size) + buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); + close(fd); + + if (!type) + type = OBJ_BLOB; + + /* + * Convert blobs to git internal format + */ + if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) { + struct strbuf nbuf; + strbuf_init(&nbuf, 0); + if (convert_to_git(path, buf, size, &nbuf, + write_object ? safe_crlf : 0)) { + munmap(buf, size); + buf = strbuf_detach(&nbuf, &size); + re_allocated = 1; + } + } + + if (write_object) + ret = write_sha1_file(buf, size, typename(type), sha1); + else + ret = hash_sha1_file(buf, size, typename(type), sha1); + if (re_allocated) { + free(buf); + return ret; + } + if (size) + munmap(buf, size); + return ret; +} + +int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object) +{ + int fd; + char *target; + size_t len; + + switch (st->st_mode & S_IFMT) { + case S_IFREG: + fd = open(path, O_RDONLY); + if (fd < 0) + return error("open(\"%s\"): %s", path, + strerror(errno)); + if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path) < 0) + return error("%s: failed to insert into database", + path); + break; + case S_IFLNK: + len = xsize_t(st->st_size); + target = xmalloc(len + 1); + if (readlink(path, target, len + 1) != st->st_size) { + char *errstr = strerror(errno); + free(target); + return error("readlink(\"%s\"): %s", path, + errstr); + } + if (!write_object) + hash_sha1_file(target, len, blob_type, sha1); + else if (write_sha1_file(target, len, blob_type, sha1)) + return error("%s: failed to insert into database", + path); + free(target); + break; + case S_IFDIR: + return resolve_gitlink_ref(path, "HEAD", sha1); + default: + return error("%s: unsupported file type", path); + } + return 0; +} + +int read_pack_header(int fd, struct pack_header *header) +{ + if (read_in_full(fd, header, sizeof(*header)) < sizeof(*header)) + /* "eof before pack header was fully read" */ + return PH_ERROR_EOF; + + if (header->hdr_signature != htonl(PACK_SIGNATURE)) + /* "protocol error (pack signature mismatch detected)" */ + return PH_ERROR_PACK_SIGNATURE; + if (!pack_version_ok(header->hdr_version)) + /* "protocol error (pack version unsupported)" */ + return PH_ERROR_PROTOCOL; + return 0; +} diff --git a/strbuf.c b/strbuf.c new file mode 100644 index 0000000..720737d --- /dev/null +++ b/strbuf.c @@ -0,0 +1,310 @@ +#include "cache.h" + +int prefixcmp(const char *str, const char *prefix) +{ + for (; ; str++, prefix++) + if (!*prefix) + return 0; + else if (*str != *prefix) + return (unsigned char)*prefix - (unsigned char)*str; +} + +/* + * Used as the default ->buf value, so that people can always assume + * buf is non NULL and ->buf is NUL terminated even for a freshly + * initialized strbuf. + */ +char strbuf_slopbuf[1]; + +void strbuf_init(struct strbuf *sb, size_t hint) +{ + sb->alloc = sb->len = 0; + sb->buf = strbuf_slopbuf; + if (hint) + strbuf_grow(sb, hint); +} + +void strbuf_release(struct strbuf *sb) +{ + if (sb->alloc) { + free(sb->buf); + strbuf_init(sb, 0); + } +} + +char *strbuf_detach(struct strbuf *sb, size_t *sz) +{ + char *res = sb->alloc ? sb->buf : NULL; + if (sz) + *sz = sb->len; + strbuf_init(sb, 0); + return res; +} + +void strbuf_attach(struct strbuf *sb, void *buf, size_t len, size_t alloc) +{ + strbuf_release(sb); + sb->buf = buf; + sb->len = len; + sb->alloc = alloc; + strbuf_grow(sb, 0); + sb->buf[sb->len] = '\0'; +} + +void strbuf_grow(struct strbuf *sb, size_t extra) +{ + if (sb->len + extra + 1 <= sb->len) + die("you want to use way too much memory"); + if (!sb->alloc) + sb->buf = NULL; + ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc); +} + +void strbuf_trim(struct strbuf *sb) +{ + char *b = sb->buf; + while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1])) + sb->len--; + while (sb->len > 0 && isspace(*b)) { + b++; + sb->len--; + } + memmove(sb->buf, b, sb->len); + sb->buf[sb->len] = '\0'; +} +void strbuf_rtrim(struct strbuf *sb) +{ + while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1])) + sb->len--; + sb->buf[sb->len] = '\0'; +} + +void strbuf_ltrim(struct strbuf *sb) +{ + char *b = sb->buf; + while (sb->len > 0 && isspace(*b)) { + b++; + sb->len--; + } + memmove(sb->buf, b, sb->len); + sb->buf[sb->len] = '\0'; +} + +void strbuf_tolower(struct strbuf *sb) +{ + int i; + for (i = 0; i < sb->len; i++) + sb->buf[i] = tolower(sb->buf[i]); +} + +struct strbuf **strbuf_split(const struct strbuf *sb, int delim) +{ + int alloc = 2, pos = 0; + char *n, *p; + struct strbuf **ret; + struct strbuf *t; + + ret = xcalloc(alloc, sizeof(struct strbuf *)); + p = n = sb->buf; + while (n < sb->buf + sb->len) { + int len; + n = memchr(n, delim, sb->len - (n - sb->buf)); + if (pos + 1 >= alloc) { + alloc = alloc * 2; + ret = xrealloc(ret, sizeof(struct strbuf *) * alloc); + } + if (!n) + n = sb->buf + sb->len - 1; + len = n - p + 1; + t = xmalloc(sizeof(struct strbuf)); + strbuf_init(t, len); + strbuf_add(t, p, len); + ret[pos] = t; + ret[++pos] = NULL; + p = ++n; + } + return ret; +} + +void strbuf_list_free(struct strbuf **sbs) +{ + struct strbuf **s = sbs; + + while (*s) { + strbuf_release(*s); + free(*s++); + } + free(sbs); +} + +int strbuf_cmp(const struct strbuf *a, const struct strbuf *b) +{ + int cmp; + if (a->len < b->len) { + cmp = memcmp(a->buf, b->buf, a->len); + return cmp ? cmp : -1; + } else { + cmp = memcmp(a->buf, b->buf, b->len); + return cmp ? cmp : a->len != b->len; + } +} + +void strbuf_splice(struct strbuf *sb, size_t pos, size_t len, + const void *data, size_t dlen) +{ + if (pos + len < pos) + die("you want to use way too much memory"); + if (pos > sb->len) + die("`pos' is too far after the end of the buffer"); + if (pos + len > sb->len) + die("`pos + len' is too far after the end of the buffer"); + + if (dlen >= len) + strbuf_grow(sb, dlen - len); + memmove(sb->buf + pos + dlen, + sb->buf + pos + len, + sb->len - pos - len); + memcpy(sb->buf + pos, data, dlen); + strbuf_setlen(sb, sb->len + dlen - len); +} + +void strbuf_insert(struct strbuf *sb, size_t pos, const void *data, size_t len) +{ + strbuf_splice(sb, pos, 0, data, len); +} + +void strbuf_remove(struct strbuf *sb, size_t pos, size_t len) +{ + strbuf_splice(sb, pos, len, NULL, 0); +} + +void strbuf_add(struct strbuf *sb, const void *data, size_t len) +{ + strbuf_grow(sb, len); + memcpy(sb->buf + sb->len, data, len); + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len) +{ + strbuf_grow(sb, len); + memcpy(sb->buf + sb->len, sb->buf + pos, len); + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_addf(struct strbuf *sb, const char *fmt, ...) +{ + int len; + va_list ap; + + if (!strbuf_avail(sb)) + strbuf_grow(sb, 64); + va_start(ap, fmt); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + va_end(ap); + if (len < 0) + die("your vsnprintf is broken"); + if (len > strbuf_avail(sb)) { + strbuf_grow(sb, len); + va_start(ap, fmt); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + va_end(ap); + if (len > strbuf_avail(sb)) { + die("this should not happen, your snprintf is broken"); + } + } + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn, + void *context) +{ + for (;;) { + const char *percent; + size_t consumed; + + percent = strchrnul(format, '%'); + strbuf_add(sb, format, percent - format); + if (!*percent) + break; + format = percent + 1; + + consumed = fn(sb, format, context); + if (consumed) + format += consumed; + else + strbuf_addch(sb, '%'); + } +} + +size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) +{ + size_t res; + + strbuf_grow(sb, size); + res = fread(sb->buf + sb->len, 1, size, f); + if (res > 0) { + strbuf_setlen(sb, sb->len + res); + } + return res; +} + +ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint) +{ + size_t oldlen = sb->len; + + strbuf_grow(sb, hint ? hint : 8192); + for (;;) { + ssize_t cnt; + + cnt = xread(fd, sb->buf + sb->len, sb->alloc - sb->len - 1); + if (cnt < 0) { + strbuf_setlen(sb, oldlen); + return -1; + } + if (!cnt) + break; + sb->len += cnt; + strbuf_grow(sb, 8192); + } + + sb->buf[sb->len] = '\0'; + return sb->len - oldlen; +} + +int strbuf_getline(struct strbuf *sb, FILE *fp, int term) +{ + int ch; + + strbuf_grow(sb, 0); + if (feof(fp)) + return EOF; + + strbuf_reset(sb); + while ((ch = fgetc(fp)) != EOF) { + if (ch == term) + break; + strbuf_grow(sb, 1); + sb->buf[sb->len++] = ch; + } + if (ch == EOF && sb->len == 0) + return EOF; + + sb->buf[sb->len] = '\0'; + return 0; +} + +int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint) +{ + int fd, len; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -1; + len = strbuf_read(sb, fd, hint); + close(fd); + if (len < 0) + return -1; + + return len; +} diff --git a/strbuf.h b/strbuf.h new file mode 100644 index 0000000..eba7ba4 --- /dev/null +++ b/strbuf.h @@ -0,0 +1,128 @@ +#ifndef STRBUF_H +#define STRBUF_H + +/* + * Strbuf's can be use in many ways: as a byte array, or to store arbitrary + * long, overflow safe strings. + * + * Strbufs has some invariants that are very important to keep in mind: + * + * 1. the ->buf member is always malloc-ed, hence strbuf's can be used to + * build complex strings/buffers whose final size isn't easily known. + * + * It is NOT legal to copy the ->buf pointer away. + * `strbuf_detach' is the operation that detachs a buffer from its shell + * while keeping the shell valid wrt its invariants. + * + * 2. the ->buf member is a byte array that has at least ->len + 1 bytes + * allocated. The extra byte is used to store a '\0', allowing the ->buf + * member to be a valid C-string. Every strbuf function ensure this + * invariant is preserved. + * + * Note that it is OK to "play" with the buffer directly if you work it + * that way: + * + * strbuf_grow(sb, SOME_SIZE); + * ... Here, the memory array starting at sb->buf, and of length + * ... strbuf_avail(sb) is all yours, and you are sure that + * ... strbuf_avail(sb) is at least SOME_SIZE. + * strbuf_setlen(sb, sb->len + SOME_OTHER_SIZE); + * + * Of course, SOME_OTHER_SIZE must be smaller or equal to strbuf_avail(sb). + * + * Doing so is safe, though if it has to be done in many places, adding the + * missing API to the strbuf module is the way to go. + * + * XXX: do _not_ assume that the area that is yours is of size ->alloc - 1 + * even if it's true in the current implementation. Alloc is somehow a + * "private" member that should not be messed with. + */ + +#include + +extern char strbuf_slopbuf[]; +struct strbuf { + size_t alloc; + size_t len; + char *buf; +}; + +#define STRBUF_INIT { 0, 0, strbuf_slopbuf } + +/*----- strbuf life cycle -----*/ +extern void strbuf_init(struct strbuf *, size_t); +extern void strbuf_release(struct strbuf *); +extern char *strbuf_detach(struct strbuf *, size_t *); +extern void strbuf_attach(struct strbuf *, void *, size_t, size_t); +static inline void strbuf_swap(struct strbuf *a, struct strbuf *b) { + struct strbuf tmp = *a; + *a = *b; + *b = tmp; +} + +/*----- strbuf size related -----*/ +static inline size_t strbuf_avail(const struct strbuf *sb) { + return sb->alloc ? sb->alloc - sb->len - 1 : 0; +} + +extern void strbuf_grow(struct strbuf *, size_t); + +static inline void strbuf_setlen(struct strbuf *sb, size_t len) { + if (!sb->alloc) + strbuf_grow(sb, 0); + assert(len < sb->alloc); + sb->len = len; + sb->buf[len] = '\0'; +} +#define strbuf_reset(sb) strbuf_setlen(sb, 0) + +/*----- content related -----*/ +extern void strbuf_trim(struct strbuf *); +extern void strbuf_rtrim(struct strbuf *); +extern void strbuf_ltrim(struct strbuf *); +extern int strbuf_cmp(const struct strbuf *, const struct strbuf *); +extern void strbuf_tolower(struct strbuf *); + +extern struct strbuf **strbuf_split(const struct strbuf *, int delim); +extern void strbuf_list_free(struct strbuf **); + +/*----- add data in your buffer -----*/ +static inline void strbuf_addch(struct strbuf *sb, int c) { + strbuf_grow(sb, 1); + sb->buf[sb->len++] = c; + sb->buf[sb->len] = '\0'; +} + +extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t); +extern void strbuf_remove(struct strbuf *, size_t pos, size_t len); + +/* splice pos..pos+len with given data */ +extern void strbuf_splice(struct strbuf *, size_t pos, size_t len, + const void *, size_t); + +extern void strbuf_add(struct strbuf *, const void *, size_t); +static inline void strbuf_addstr(struct strbuf *sb, const char *s) { + strbuf_add(sb, s, strlen(s)); +} +static inline void strbuf_addbuf(struct strbuf *sb, const struct strbuf *sb2) { + strbuf_add(sb, sb2->buf, sb2->len); +} +extern void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len); + +typedef size_t (*expand_fn_t) (struct strbuf *sb, const char *placeholder, void *context); +extern void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn, void *context); + +__attribute__((format(printf,2,3))) +extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...); + +extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); +/* XXX: if read fails, any partial read is undone */ +extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint); +extern int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint); + +extern int strbuf_getline(struct strbuf *, FILE *, int); + +extern void stripspace(struct strbuf *buf, int skip_comments); +extern int launch_editor(const char *path, struct strbuf *buffer, const char *const *env); + +#endif /* STRBUF_H */ diff --git a/usage.c b/usage.c new file mode 100644 index 0000000..a5fc4ec --- /dev/null +++ b/usage.c @@ -0,0 +1,96 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + */ +#include "git-compat-util.h" + +static void report(const char *prefix, const char *err, va_list params) +{ + char msg[256]; + vsnprintf(msg, sizeof(msg), err, params); + fprintf(stderr, "%s%s\n", prefix, msg); +} + +static NORETURN void usage_builtin(const char *err) +{ + fprintf(stderr, "usage: %s\n", err); + exit(129); +} + +static NORETURN void die_builtin(const char *err, va_list params) +{ + report("fatal: ", err, params); + exit(128); +} + +static void error_builtin(const char *err, va_list params) +{ + report("error: ", err, params); +} + +static void warn_builtin(const char *warn, va_list params) +{ + report("warning: ", warn, params); +} + +/* If we are in a dlopen()ed .so write to a global variable would segfault + * (ugh), so keep things static. */ +static void (*usage_routine)(const char *err) NORETURN = usage_builtin; +static void (*die_routine)(const char *err, va_list params) NORETURN = die_builtin; +static void (*error_routine)(const char *err, va_list params) = error_builtin; +static void (*warn_routine)(const char *err, va_list params) = warn_builtin; + +void set_usage_routine(void (*routine)(const char *err) NORETURN) +{ + usage_routine = routine; +} + +void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN) +{ + die_routine = routine; +} + +void set_error_routine(void (*routine)(const char *err, va_list params)) +{ + error_routine = routine; +} + +void set_warn_routine(void (*routine)(const char *warn, va_list params)) +{ + warn_routine = routine; +} + + +void usage(const char *err) +{ + usage_routine(err); +} + +void die(const char *err, ...) +{ + va_list params; + + va_start(params, err); + die_routine(err, params); + va_end(params); +} + +int error(const char *err, ...) +{ + va_list params; + + va_start(params, err); + error_routine(err, params); + va_end(params); + return -1; +} + +void warning(const char *warn, ...) +{ + va_list params; + + va_start(params, warn); + warn_routine(warn, params); + va_end(params); +} diff --git a/wrapper.c b/wrapper.c new file mode 100644 index 0000000..93562f0 --- /dev/null +++ b/wrapper.c @@ -0,0 +1,198 @@ +/* + * Various trivial helper wrappers around standard functions + */ +#include "cache.h" + +char *xstrdup(const char *str) +{ + char *ret = strdup(str); + if (!ret) { + release_pack_memory(strlen(str) + 1, -1); + ret = strdup(str); + if (!ret) + die("Out of memory, strdup failed"); + } + return ret; +} + +void *xmalloc(size_t size) +{ + void *ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) { + release_pack_memory(size, -1); + ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) + die("Out of memory, malloc failed"); + } +#ifdef XMALLOC_POISON + memset(ret, 0xA5, size); +#endif + return ret; +} + +/* + * xmemdupz() allocates (len + 1) bytes of memory, duplicates "len" bytes of + * "data" to the allocated memory, zero terminates the allocated memory, + * and returns a pointer to the allocated memory. If the allocation fails, + * the program dies. + */ +void *xmemdupz(const void *data, size_t len) +{ + char *p = xmalloc(len + 1); + memcpy(p, data, len); + p[len] = '\0'; + return p; +} + +char *xstrndup(const char *str, size_t len) +{ + char *p = memchr(str, '\0', len); + return xmemdupz(str, p ? p - str : len); +} + +void *xrealloc(void *ptr, size_t size) +{ + void *ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) { + release_pack_memory(size, -1); + ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) + die("Out of memory, realloc failed"); + } + return ret; +} + +void *xcalloc(size_t nmemb, size_t size) +{ + void *ret = calloc(nmemb, size); + if (!ret && (!nmemb || !size)) + ret = calloc(1, 1); + if (!ret) { + release_pack_memory(nmemb * size, -1); + ret = calloc(nmemb, size); + if (!ret && (!nmemb || !size)) + ret = calloc(1, 1); + if (!ret) + die("Out of memory, calloc failed"); + } + return ret; +} + +void *xmmap(void *start, size_t length, + int prot, int flags, int fd, off_t offset) +{ + void *ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) { + if (!length) + return NULL; + release_pack_memory(length, fd); + ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) + die("Out of memory? mmap failed: %s", strerror(errno)); + } + return ret; +} + +/* + * xread() is the same a read(), but it automatically restarts read() + * operations with a recoverable error (EAGAIN and EINTR). xread() + * DOES NOT GUARANTEE that "len" bytes is read even if the data is available. + */ +ssize_t xread(int fd, void *buf, size_t len) +{ + ssize_t nr; + while (1) { + nr = read(fd, buf, len); + if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) + continue; + return nr; + } +} + +/* + * xwrite() is the same a write(), but it automatically restarts write() + * operations with a recoverable error (EAGAIN and EINTR). xwrite() DOES NOT + * GUARANTEE that "len" bytes is written even if the operation is successful. + */ +ssize_t xwrite(int fd, const void *buf, size_t len) +{ + ssize_t nr; + while (1) { + nr = write(fd, buf, len); + if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) + continue; + return nr; + } +} + +ssize_t read_in_full(int fd, void *buf, size_t count) +{ + char *p = buf; + ssize_t total = 0; + + while (count > 0) { + ssize_t loaded = xread(fd, p, count); + if (loaded <= 0) + return total ? total : loaded; + count -= loaded; + p += loaded; + total += loaded; + } + + return total; +} + +ssize_t write_in_full(int fd, const void *buf, size_t count) +{ + const char *p = buf; + ssize_t total = 0; + + while (count > 0) { + ssize_t written = xwrite(fd, p, count); + if (written < 0) + return -1; + if (!written) { + errno = ENOSPC; + return -1; + } + count -= written; + p += written; + total += written; + } + + return total; +} + +int xdup(int fd) +{ + int ret = dup(fd); + if (ret < 0) + die("dup failed: %s", strerror(errno)); + return ret; +} + +FILE *xfdopen(int fd, const char *mode) +{ + FILE *stream = fdopen(fd, mode); + if (stream == NULL) + die("Out of memory? fdopen failed: %s", strerror(errno)); + return stream; +} + +int xmkstemp(char *template) +{ + int fd; + + fd = mkstemp(template); + if (fd < 0) + die("Unable to create temporary file: %s", strerror(errno)); + return fd; +} -- 2.11.4.GIT