X-Git-Url: https://git.gag.com/?a=blobdiff_plain;f=gzip.c;h=0d0953cda2e2cb4b642dd5191faff2b63f8189e7;hb=31831d686bc445a6715366487b9ca88d28929194;hp=a013540c4960609e3dae62f9741afaba4ac00da3;hpb=2725db10000bae65e311a9329973b11053b86f1a;p=debian%2Fgzip diff --git a/gzip.c b/gzip.c index a013540..0d0953c 100644 --- a/gzip.c +++ b/gzip.c @@ -43,7 +43,7 @@ static char const *const license_msg[] = { * or stdout with -c option or if stdin used as input. * If the output file name had to be truncated, the original name is kept * in the compressed file. - * On MSDOS, file.tmp -> file.tmz. On VMS, file.tmp -> file.tmp-gz. + * On MSDOS, file.tmp -> file.tmz. * * Using gz on MSDOS would create too many file name conflicts. For * example, foo.txt -> foo.tgz (.tgz must be reserved as shorthand for @@ -59,10 +59,10 @@ static char const *const license_msg[] = { #include #include #include +#include #include #include -#include "closein.h" #include "tailor.h" #include "gzip.h" #include "intprops.h" @@ -70,7 +70,9 @@ static char const *const license_msg[] = { #include "revision.h" #include "timespec.h" -#include "fcntl-safer.h" +#include "dirname.h" +#include "dosname.h" +#include "fcntl--.h" #include "getopt.h" #include "ignore-value.h" #include "stat-time.h" @@ -79,7 +81,6 @@ static char const *const license_msg[] = { /* configuration */ -#include #include #include #include @@ -97,8 +98,6 @@ static char const *const license_msg[] = { # include #endif -#define RW_USER (S_IRUSR | S_IWUSR) /* creation mode for open() */ - #ifndef MAX_PATH_LEN # define MAX_PATH_LEN 1024 /* max pathname length */ #endif @@ -160,6 +159,14 @@ DECLARE(uch, window, 2L*WSIZE); is deliberately not documented, and only for testing. */ static bool presume_input_tty; +/* If true, transfer output data to the output file's storage device + when supported. Otherwise, if the system crashes around the time + gzip is run, the user might lose both input and output data. See: + Pillai TS et al. All file systems are not created equal: on the + complexity of crafting crash-consistent applications. OSDI'14. 2014:433-48. + https://www.usenix.org/conference/osdi14/technical-sessions/presentation/pillai */ +static bool synchronous; + static int ascii = 0; /* convert end-of-lines to local OS conventions */ int to_stdout = 0; /* output to stdout (-c) */ static int decompress = 0; /* decompress (-d) */ @@ -199,18 +206,23 @@ static int volatile exiting_signal; /* If nonnegative, close this file descriptor and unlink ofname on error. */ static int volatile remove_ofname_fd = -1; +static bool stdin_was_read; + off_t bytes_in; /* number of input bytes */ off_t bytes_out; /* number of output bytes */ static off_t total_in; /* input bytes for all files */ static off_t total_out; /* output bytes for all files */ char ifname[MAX_PATH_LEN]; /* input file name */ char ofname[MAX_PATH_LEN]; /* output file name */ +static char dfname[MAX_PATH_LEN]; /* name of dir containing output file */ static struct stat istat; /* status for input file */ int ifd; /* input file descriptor */ int ofd; /* output file descriptor */ +static int dfd = -1; /* output directory file descriptor */ unsigned insize; /* valid bytes in inbuf */ unsigned inptr; /* index of next byte to be processed in inbuf */ unsigned outcnt; /* bytes in output buffer */ +int rsync = 0; /* make ryncable chunks */ static int handled_sig[] = { @@ -239,6 +251,8 @@ static int handled_sig[] = enum { PRESUME_INPUT_TTY_OPTION = CHAR_MAX + 1, + RSYNCABLE_OPTION, + SYNCHRONOUS_OPTION, /* A value greater than all valid long options, used as a flag to distinguish options derived from the GZIP environment variable. */ @@ -267,6 +281,7 @@ static const struct option longopts[] = {"-presume-input-tty", no_argument, NULL, PRESUME_INPUT_TTY_OPTION}, {"quiet", 0, 0, 'q'}, /* quiet mode */ {"silent", 0, 0, 'q'}, /* quiet mode */ + {"synchronous",0, 0, SYNCHRONOUS_OPTION}, {"recursive", 0, 0, 'r'}, /* recurse through directories */ {"suffix", 1, 0, 'S'}, /* use given suffix instead of .gz */ {"test", 0, 0, 't'}, /* test compressed file integrity */ @@ -277,7 +292,7 @@ static const struct option longopts[] = {"best", 0, 0, '9'}, /* compress better */ {"lzw", 0, 0, 'Z'}, /* make output compatible with old compress */ {"bits", 1, 0, 'b'}, /* max number of bits per code (implies -Z) */ - + {"rsyncable", 0, 0, RSYNCABLE_OPTION}, /* make rsync-friendly archive */ { 0, 0, 0, 0 } }; @@ -304,6 +319,7 @@ local void install_signal_handlers (void); local void remove_output_file (void); local RETSIGTYPE abort_gzip_signal (int); local void do_exit (int exitcode) ATTRIBUTE_NORETURN; +static void finish_out (void); int main (int argc, char **argv); static int (*work) (int infile, int outfile) = zip; /* function to call */ @@ -351,7 +367,9 @@ local void help() #if ! NO_DIR " -r, --recursive operate recursively on directories", #endif + " --rsyncable make rsync-friendly archive", " -S, --suffix=SUF use suffix SUF on compressed files", + " --synchronous synchronous output (safer if system crashes, but slower)", " -t, --test test compressed file integrity", " -v, --verbose verbose mode", " -V, --version display version number", @@ -412,9 +430,7 @@ int main (int argc, char **argv) program_name = gzip_base_name (argv[0]); proglen = strlen (program_name); - atexit (close_stdin); - - /* Suppress .exe for MSDOS, OS/2 and VMS: */ + /* Suppress .exe for MSDOS and OS/2: */ if (4 < proglen && strequ (program_name + proglen - 4, ".exe")) program_name[proglen - 4] = '\0'; @@ -432,7 +448,7 @@ int main (int argc, char **argv) * gzip even if it is invoked under the name gunzip or zcat. * * Systems which do not support links can still use -d or -dc. - * Ignore an .exe extension for MSDOS, OS/2 and VMS. + * Ignore an .exe extension for MSDOS and OS/2. */ if (strncmp (program_name, "un", 2) == 0 /* ungzip, uncompress */ || strncmp (program_name, "gun", 3) == 0) /* gunzip */ @@ -512,13 +528,13 @@ int main (int argc, char **argv) case 'f': force++; break; case 'h': case 'H': - help(); do_exit(OK); break; + help (); finish_out (); break; case 'k': keep = 1; break; case 'l': list = decompress = to_stdout = 1; break; case 'L': - license(); do_exit(OK); break; + license (); finish_out (); break; case 'm': /* undocumented, may change later */ no_time = 1; break; case 'M': /* undocumented, may change later */ @@ -543,6 +559,11 @@ int main (int argc, char **argv) recursive = 1; #endif break; + + case RSYNCABLE_OPTION: + case RSYNCABLE_OPTION + ENV_OPTION: + rsync = 1; + break; case 'S': #ifdef NO_MULTIPLE_DOTS if (*optarg == '.') optarg++; @@ -550,6 +571,9 @@ int main (int argc, char **argv) z_len = strlen(optarg); z_suffix = optarg; break; + case SYNCHRONOUS_OPTION: + synchronous = true; + break; case 't': test = decompress = to_stdout = 1; break; @@ -557,7 +581,7 @@ int main (int argc, char **argv) case 'v' + ENV_OPTION: verbose++; quiet = 0; break; case 'V': - version(); do_exit(OK); break; + version (); finish_out (); break; case 'Z': #ifdef LZW do_lzw = 1; break; @@ -633,7 +657,7 @@ int main (int argc, char **argv) /* And get to work */ if (file_count != 0) { if (to_stdout && !test && !list && (!decompress || !ascii)) { - SET_BINARY_MODE(fileno(stdout)); + SET_BINARY_MODE (STDOUT_FILENO); } while (optind < argc) { treat_file(argv[optind++]); @@ -641,9 +665,25 @@ int main (int argc, char **argv) } else { /* Standard input */ treat_stdin(); } - if (list && !quiet && file_count > 1) { - do_list(-1, -1); /* print totals */ - } + if (stdin_was_read && close (STDIN_FILENO) != 0) + { + strcpy (ifname, "stdin"); + read_error (); + } + if (list) + { + /* Output any totals, and check for output errors. */ + if (!quiet && 1 < file_count) + do_list (-1, -1); + if (fflush (stdout) != 0) + write_error (); + } + if (to_stdout + && ((synchronous + && fdatasync (STDOUT_FILENO) != 0 && errno != EINVAL) + || close (STDOUT_FILENO) != 0) + && errno != EBADF) + write_error (); do_exit(exit_code); return exit_code; /* just to avoid lint warning */ } @@ -674,7 +714,7 @@ local void treat_stdin() { if (!force && !list && (presume_input_tty - || isatty(fileno((FILE *)(decompress ? stdin : stdout))))) { + || isatty (decompress ? STDIN_FILENO : STDOUT_FILENO))) { /* Do not send compressed data to the terminal or read it from * the terminal. We get here when user invoked the program * without parameters, so be helpful. According to the GNU standards: @@ -700,16 +740,16 @@ local void treat_stdin() } if (decompress || !ascii) { - SET_BINARY_MODE(fileno(stdin)); + SET_BINARY_MODE (STDIN_FILENO); } if (!test && !list && (!decompress || !ascii)) { - SET_BINARY_MODE(fileno(stdout)); + SET_BINARY_MODE (STDOUT_FILENO); } strcpy(ifname, "stdin"); strcpy(ofname, "stdout"); /* Get the file's time stamp and size. */ - if (fstat (fileno (stdin), &istat) != 0) + if (fstat (STDIN_FILENO, &istat) != 0) { progerror ("standard input"); do_exit (ERROR); @@ -727,7 +767,8 @@ local void treat_stdin() clear_bufs(); /* clear input and output buffers */ to_stdout = 1; part_nb = 0; - ifd = fileno(stdin); + ifd = STDIN_FILENO; + stdin_was_read = true; if (decompress) { method = get_method(ifd); @@ -743,7 +784,8 @@ local void treat_stdin() /* Actually do the compression/decompression. Loop over zipped members. */ for (;;) { - if ((*work)(fileno(stdin), fileno(stdout)) != OK) return; + if (work (STDIN_FILENO, STDOUT_FILENO) != OK) + return; if (input_eof ()) break; @@ -769,6 +811,48 @@ local void treat_stdin() } } +static char const dot = '.'; + +/* True if the cached directory for calls to openat etc. is DIR, with + length DIRLEN. DIR need not be null-terminated. DIRLEN must be + less than MAX_PATH_LEN. */ +static bool +atdir_eq (char const *dir, ptrdiff_t dirlen) +{ + if (dirlen == 0) + dir = &dot, dirlen = 1; + return memcmp (dfname, dir, dirlen) == 0 && !dfname[dirlen]; +} + +/* Set the directory used for calls to openat etc. to be the directory + DIR, with length DIRLEN. DIR need not be null-terminated. + DIRLEN must be less than MAX_PATH_LEN. Return a file descriptor for + the directory, or -1 if one could not be obtained. */ +static int +atdir_set (char const *dir, ptrdiff_t dirlen) +{ + /* Don't bother opening directories on older systems that + lack openat and unlinkat. It's not worth the porting hassle. */ + #if HAVE_OPENAT && HAVE_UNLINKAT + enum { try_opening_directories = true }; + #else + enum { try_opening_directories = false }; + #endif + + if (try_opening_directories && ! atdir_eq (dir, dirlen)) + { + if (0 <= dfd) + close (dfd); + if (dirlen == 0) + dir = &dot, dirlen = 1; + memcpy (dfname, dir, dirlen); + dfname[dirlen] = '\0'; + dfd = open (dfname, O_SEARCH | O_DIRECTORY); + } + + return dfd; +} + /* ======================================================================== * Compress or decompress the given file */ @@ -888,7 +972,7 @@ local void treat_file(iname) * a new ofname and save the original name in the compressed file. */ if (to_stdout) { - ofd = fileno(stdout); + ofd = STDOUT_FILENO; /* Keep remove_ofname_fd negative. */ } else { if (create_outfile() != OK) return; @@ -926,19 +1010,26 @@ local void treat_file(iname) if (!to_stdout) { - copy_stat (&istat); - if (close (ofd) != 0) + + if ((synchronous + && ((0 <= dfd && fdatasync (dfd) != 0 && errno != EINVAL) + || (fsync (ofd) != 0 && errno != EINVAL))) + || close (ofd) != 0) write_error (); if (!keep) { sigset_t oldset; int unlink_errno; + char *ifbase = last_component (ifname); + int ufd = atdir_eq (ifname, ifbase - ifname) ? dfd : -1; + int res; sigprocmask (SIG_BLOCK, &caught_signals, &oldset); remove_ofname_fd = -1; - unlink_errno = xunlink (ifname) == 0 ? 0 : errno; + res = ufd < 0 ? xunlink (ifname) : unlinkat (ufd, ifbase, 0); + unlink_errno = res == 0 ? 0 : errno; sigprocmask (SIG_SETMASK, &oldset, NULL); if (unlink_errno) @@ -989,6 +1080,19 @@ local int create_outfile() int name_shortened = 0; int flags = (O_WRONLY | O_CREAT | O_EXCL | (ascii && decompress ? 0 : O_BINARY)); + char const *base = ofname; + int atfd = AT_FDCWD; + + if (!keep) + { + char const *b = last_component (ofname); + int f = atdir_set (ofname, b - ofname); + if (0 <= f) + { + base = b; + atfd = f; + } + } for (;;) { @@ -996,7 +1100,7 @@ local int create_outfile() sigset_t oldset; sigprocmask (SIG_BLOCK, &caught_signals, &oldset); - remove_ofname_fd = ofd = OPEN (ofname, flags, RW_USER); + remove_ofname_fd = ofd = openat (atfd, base, flags, S_IRUSR | S_IWUSR); open_errno = errno; sigprocmask (SIG_SETMASK, &oldset, NULL); @@ -1046,8 +1150,6 @@ local int create_outfile() * also accepted suffixes. For Unix, we do not want to accept any * .??z suffix as indicating a compressed file; some people use .xyz * to denote volume data. - * On systems allowing multiple versions of the same file (such as VMS), - * this function removes any version suffix in the given name. */ local char *get_suffix(name) char *name; @@ -1079,13 +1181,6 @@ local char *get_suffix(name) : 0] = z_suffix; suf = known_suffixes + suffix_of_builtin; -#ifdef SUFFIX_SEP - /* strip a version number from the file name */ - { - char *v = strrchr(name, SUFFIX_SEP); - if (v != NULL) *v = '\0'; - } -#endif nlen = strlen(name); if (nlen <= MAX_SUFFIX+2) { strcpy(suffix, name); @@ -1096,7 +1191,7 @@ local char *get_suffix(name) slen = strlen(suffix); do { int s = strlen(*suf); - if (slen > s && suffix[slen-s-1] != PATH_SEP + if (slen > s && ! ISSLASH (suffix[slen - s - 1]) && strequ(suffix + slen - s, *suf)) { return name+nlen-s; } @@ -1106,13 +1201,15 @@ local char *get_suffix(name) } -/* Open file NAME with the given flags and mode and store its status +/* Open file NAME with the given flags and store its status into *ST. Return a file descriptor to the newly opened file, or -1 (setting errno) on failure. */ static int -open_and_stat (char *name, int flags, mode_t mode, struct stat *st) +open_and_stat (char *name, int flags, struct stat *st) { int fd; + int atfd = AT_FDCWD; + char const *base = name; /* Refuse to follow symbolic links unless -c or -f. */ if (!to_stdout && !force) @@ -1121,7 +1218,7 @@ open_and_stat (char *name, int flags, mode_t mode, struct stat *st) flags |= O_NOFOLLOW; else { -#if HAVE_LSTAT || defined lstat +#ifdef S_ISLNK if (lstat (name, st) != 0) return -1; else if (S_ISLNK (st->st_mode)) @@ -1133,7 +1230,18 @@ open_and_stat (char *name, int flags, mode_t mode, struct stat *st) } } - fd = OPEN (name, flags, mode); + if (!keep) + { + char const *b = last_component (name); + int f = atdir_set (name, b - name); + if (0 <= f) + { + base = b; + atfd = f; + } + } + + fd = openat (atfd, base, flags); if (0 <= fd && fstat (fd, st) != 0) { int e = errno; @@ -1177,7 +1285,7 @@ open_input_file (iname, sbuf) strcpy(ifname, iname); /* If input file exists, return OK. */ - fd = open_and_stat (ifname, open_flags, RW_USER, sbuf); + fd = open_and_stat (ifname, open_flags, sbuf); if (0 <= fd) return fd; @@ -1185,9 +1293,7 @@ open_input_file (iname, sbuf) progerror(ifname); return -1; } - /* file.ext doesn't exist, try adding a suffix (after removing any - * version number for VMS). - */ + /* File.ext doesn't exist. Try adding a suffix. */ s = get_suffix(ifname); if (s != NULL) { progerror(ifname); /* ifname already has z suffix and does not exist */ @@ -1218,7 +1324,7 @@ open_input_file (iname, sbuf) if (sizeof ifname <= ilen + strlen (s)) goto name_too_long; strcat(ifname, s); - fd = open_and_stat (ifname, open_flags, RW_USER, sbuf); + fd = open_and_stat (ifname, open_flags, sbuf); if (0 <= fd) return fd; if (errno != ENOENT) @@ -1394,7 +1500,7 @@ local int get_method(in) method = -1; /* unknown yet */ part_nb++; /* number of parts in gzip file */ header_bytes = 0; - last_member = RECORD_IO; + last_member = 0; /* assume multiple members in gzip file except for record oriented I/O */ if (memcmp(magic, GZIP_MAGIC, 2) == 0 @@ -1548,7 +1654,7 @@ local int get_method(in) inptr--; last_member = 1; if (imagic0 != EOF) { - write_buf(fileno(stdout), magic, 1); + write_buf (STDOUT_FILENO, magic, 1); bytes_out++; } } @@ -1637,7 +1743,7 @@ local void do_list(ifd, method) bytes_out = -1L; bytes_in = ifile_size; - if (!RECORD_IO && method == DEFLATED && !last_member) { + if (method == DEFLATED && !last_member) { /* Get the crc and uncompressed size for gzip'ed (not zip'ed) files. * If the lseek fails, we could use read() to get to the end, but * --list is used to get quick results. @@ -1658,12 +1764,13 @@ local void do_list(ifd, method) if (verbose) { + static char const month_abbr[][4] + = { "Jan", "Feb", "Mar", "Apr", "May", "Jun", + "Jul", "Aug", "Sep", "Oct", "Nov", "Dec" }; struct tm *tm = localtime (&time_stamp.tv_sec); printf ("%5s %08lx ", methods[method], crc); if (tm) - printf ("%s%3d %02d:%02d ", - ("Jan\0Feb\0Mar\0Apr\0May\0Jun\0Jul\0Aug\0Sep\0Oct\0Nov\0Dec" - + 4 * tm->tm_mon), + printf ("%s%3d %02d:%02d ", month_abbr[tm->tm_mon], tm->tm_mday, tm->tm_hour, tm->tm_min); else printf ("??? ?? ??:?? "); @@ -1728,8 +1835,7 @@ local void shorten_name(name) * 1234.678.012.gz -> 123.678.012.gz */ do { - p = strrchr(name, PATH_SEP); - p = p ? p+1 : name; + p = last_component (name); while (*p) { plen = strcspn(p, PART_SEP); p += plen; @@ -1762,7 +1868,7 @@ local int check_ofname() if (!force) { int ok = 0; fprintf (stderr, "%s: %s already exists;", program_name, ofname); - if (foreground && (presume_input_tty || isatty(fileno(stdin)))) { + if (foreground && (presume_input_tty || isatty (STDIN_FILENO))) { fprintf(stderr, " do you wish to overwrite (y or n)? "); fflush(stderr); ok = yesno(); @@ -1896,16 +2002,8 @@ local void treat_dir (fd, dir) continue; if (len + entrylen < MAX_PATH_LEN - 2) { strcpy(nbuf,dir); - if (len != 0 /* dir = "" means current dir on Amiga */ -#ifdef PATH_SEP2 - && dir[len-1] != PATH_SEP2 -#endif -#ifdef PATH_SEP3 - && dir[len-1] != PATH_SEP3 -#endif - ) { - nbuf[len++] = PATH_SEP; - } + if (*last_component (nbuf) && !ISSLASH (nbuf[len - 1])) + nbuf[len++] = '/'; strcpy (nbuf + len, entry); treat_file(nbuf); } else { @@ -1985,6 +2083,14 @@ local void do_exit(exitcode) exit(exitcode); } +static void +finish_out (void) +{ + if (fclose (stdout) != 0) + write_error (); + do_exit (OK); +} + /* ======================================================================== * Close and unlink the output file. */