diff options
Diffstat (limited to 'locate/code.c')
| -rw-r--r-- | locate/code.c | 167 |
1 files changed, 47 insertions, 120 deletions
diff --git a/locate/code.c b/locate/code.c index f48885b6..d79e72ce 100644 --- a/locate/code.c +++ b/locate/code.c @@ -1,19 +1,19 @@ /* code -- bigram- and front-encode filenames for locate - Copyright (C) 1994, 2005, 2007 Free Software Foundation, Inc. + Copyright (C) 1994 Free Software Foundation, Inc. - This program is free software: you can redistribute it and/or modify + This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by - the Free Software Foundation, either version 3 of the License, or - (at your option) any later version. - + the Free Software Foundation; either version 2, or (at your option) + any later version. + This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - + You should have received a copy of the GNU General Public License - along with this program. If not, see <http://www.gnu.org/licenses/>. -*/ + along with this program; if not, write to the Free Software + Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ /* Compress a sorted list. Works with `find' to encode a filename database to save space @@ -37,54 +37,32 @@ 0-28 likeliest differential counts + offset (14) to make nonnegative 30 escape code for out-of-range count to follow in next halfword - 128-255 bigram codes (the 128 most common, as determined by `updatedb') - 32-127 single character (printable) ASCII remainder + 128-255 bigram codes (the 128 most common, as determined by `updatedb') + 32-127 single character (printable) ASCII remainder Written by James A. Woods <jwoods@adobe.com>. - Modified by David MacKenzie <djm@gnu.org>. */ + Modified by David MacKenzie <djm@gnu.ai.mit.edu>. */ #include <config.h> #include <stdio.h> #include <sys/types.h> -#include <string.h> -#include <errno.h> -#include <stdbool.h> +#if defined(HAVE_STRING_H) || defined(STDC_HEADERS) +#include <string.h> +#else +#include <strings.h> +#endif #ifdef STDC_HEADERS #include <stdlib.h> #endif -#if ENABLE_NLS -# include <libintl.h> -# define _(Text) gettext (Text) -#else -# define _(Text) Text -#define textdomain(Domain) -#define bindtextdomain(Package, Directory) -#endif -#ifdef gettext_noop -# define N_(String) gettext_noop (String) -#else -/* See locate.c for explanation as to why not use (String) */ -# define N_(String) String -#endif - #include "locatedb.h" -#include "closeout.h" -#include "xalloc.h" -#include "gnulib-version.h" -#include "progname.h" -#include "error.h" -#include "findutils-version.h" - -#ifndef ATTRIBUTE_NORETURN -# define ATTRIBUTE_NORETURN __attribute__ ((__noreturn__)) -#endif +char *xmalloc (); /* The name this program was run with. */ -const char *program_name; +char *program_name; /* The 128 most common bigrams in the file list, padded with NULs if there are fewer. */ @@ -93,7 +71,8 @@ static char bigrams[257] = {0}; /* Return the offset of PATTERN in STRING, or -1 if not found. */ static int -strindex (char *string, char *pattern) +strindex (string, pattern) + char *string, *pattern; { register char *s; @@ -113,7 +92,8 @@ strindex (char *string, char *pattern) /* Return the length of the longest common prefix of strings S1 and S2. */ static int -prefix_length (char *s1, char *s2) +prefix_length (s1, s2) + char *s1, *s2; { register char *start; @@ -122,41 +102,10 @@ prefix_length (char *s1, char *s2) return s1 - start; } -extern char *version_string; - -static void -usage (FILE *stream) -{ - fprintf (stream, _("\ -Usage: %s [--version | --help]\n\ -or %s most_common_bigrams < file-list > locate-database\n"), - program_name, program_name); - fputs (_("\nReport bugs to <bug-findutils@gnu.org>.\n"), stream); -} - - -static void inerr (const char *filename) ATTRIBUTE_NORETURN; -static void outerr(void) ATTRIBUTE_NORETURN; - -static void -inerr(const char *filename) -{ - error(1, errno, "%s", filename); - /*NOTREACHED*/ - abort(); -} - -static void -outerr(void) -{ - error(1, errno, _("write error")); - /*NOTREACHED*/ - abort(); -} - - -int -main (int argc, char **argv) +void +main (argc, argv) + int argc; + char **argv; { char *path; /* The current input entry. */ char *oldpath; /* The previous input entry. */ @@ -167,56 +116,41 @@ main (int argc, char **argv) FILE *fp; /* Most common bigrams file. */ int line_len; /* Length of input line. */ - set_program_name(argv[0]); - atexit (close_stdout); + program_name = argv[0]; bigram[2] = '\0'; if (argc != 2) { - usage(stderr); - return 2; - } - - if (0 == strcmp(argv[1], "--help")) - { - usage(stdout); - return 0; - } - else if (0 == strcmp(argv[1], "--version")) - { - display_findutils_version("code"); - return 0; + fprintf (stderr, "Usage: %s most_common_bigrams < list > coded_list\n", + argv[0]); + exit (2); } - + fp = fopen (argv[1], "r"); if (fp == NULL) { fprintf (stderr, "%s: ", argv[0]); perror (argv[1]); - return 1; + exit (1); } - - pathsize = oldpathsize = 1026; /* Increased as necessary by getline. */ + + pathsize = oldpathsize = 1026; /* Increased as necessary by getstr. */ path = xmalloc (pathsize); oldpath = xmalloc (oldpathsize); - /* Set to empty string, to force the first prefix count to 0. */ - oldpath[0] = '\0'; + /* Set to anything not starting with a slash, to force the first + prefix count to 0. */ + strcpy (oldpath, " "); oldcount = 0; /* Copy the list of most common bigrams to the output, padding with NULs if there are <128 of them. */ - if (NULL == fgets (bigrams, 257, fp)) - inerr(argv[1]); - - if (256 != fwrite (bigrams, 1, 256, stdout)) - outerr(); + fgets (bigrams, 257, fp); + fwrite (bigrams, 1, 256, stdout); + fclose (fp); - if (EOF == fclose (fp)) - inerr(argv[1]); - - while ((line_len = getline (&path, &pathsize, stdin)) > 0) + while ((line_len = getstr (&path, &pathsize, stdin, '\n', 0)) > 0) { char *pp; @@ -225,7 +159,8 @@ main (int argc, char **argv) /* Squelch unprintable chars in path so as not to botch decoding. */ for (pp = path; *pp != '\0'; pp++) { - if (!(*pp >= 040 && *pp < 0177)) + *pp &= 0177; + if (*pp < 040 || *pp == 0177) *pp = '?'; } @@ -236,19 +171,11 @@ main (int argc, char **argv) otherwise, two bytes plus a marker noting that fact. */ if (diffcount < -LOCATEDB_OLD_OFFSET || diffcount > LOCATEDB_OLD_OFFSET) { - if (EOF ==- putc (LOCATEDB_OLD_ESCAPE, stdout)) - outerr (); - - if (!putword (stdout, - diffcount+LOCATEDB_OLD_OFFSET, - GetwordEndianStateNative)) - outerr (); + putc (LOCATEDB_OLD_ESCAPE, stdout); + putw (diffcount + LOCATEDB_OLD_OFFSET, stdout); } else - { - if (EOF == putc (diffcount + LOCATEDB_OLD_OFFSET, stdout)) - outerr (); - } + putc (diffcount + LOCATEDB_OLD_OFFSET, stdout); /* Look for bigrams in the remainder of the path. */ for (pp = path + count; *pp != '\0'; pp += 2) @@ -283,5 +210,5 @@ main (int argc, char **argv) free (path); free (oldpath); - return 0; + exit (0); } |