bogofilter -- Fast Bayesian Spam Filter

Update of /cvsroot/bogofilter/bogofilter
In directory usw-pr-cvs1:/tmp/cvs-serv9808

Modified Files:
	bogoutil.c 
Log Message:
Expanded the "-w path" option for displaying words from a word list.  Words
are now read from stdin or they can be specified on the command line.
If the path is the name of a wordlist, the words will be looked up in
that wordlist.  If the path is a directory, the words will be looked up in
path/spamlist.db and path/goodlist.db.


Index: bogoutil.c
===================================================================
RCS file: /cvsroot/bogofilter/bogofilter/bogoutil.c,v
retrieving revision 1.16
retrieving revision 1.17
diff -C2 -d -r1.16 -r1.17
*** bogoutil.c	27 Oct 2002 00:29:47 -0000	1.16
--- bogoutil.c	27 Oct 2002 21:42:28 -0000	1.17
***************
*** 17,20 ****
--- 17,22 ----
  #include <ctype.h>
  #include <db.h>
+ #include <errno.h>
+ #include <sys/stat.h>
  
  #include "version.h"
***************
*** 153,182 ****
  }
  
! int display_words(char *db_file)
  {
-     dbh_t *dbh;
-     char buf[BUFSIZE];
      char *p;
      int rv = 0;
      size_t len;
  
!     memset(buf, '\0', BUFSIZE);
! 
!     if ((dbh = db_open(db_file, db_file, DB_READ)) == NULL) {
! 	rv = 2;
!     }
!     else {
!       db_lock_reader(dbh);
!       for (;;) {
! 	if (fgets(buf, BUFSIZE, stdin) == NULL) {
! 	  if (ferror(stdin)) {
  	    perror(PROGNAME);
  	    rv = 2;
- 	  }
- 	  break;
  	}
  	len = strlen(buf);
  	p = &buf[len - 1];
! 
  	if (*(p--) != '\n') {
  	    fprintf(stderr,
--- 155,184 ----
  }
  
! dbh_t *db_open_and_lock_file( const char *db_file, const char *name, dbmode_t mode)
! {
!     dbh_t *dbh = db_open(db_file, db_file, DB_READ);
!     if (dbh != NULL)
! 	db_lock_reader(dbh);
!     return dbh;
! }
! 
! int get_token(char *buf, size_t bufsize, FILE *fp)
  {
      char *p;
      int rv = 0;
      size_t len;
  
!     if (fgets(buf, bufsize, fp) == NULL) {
! 	if (ferror(fp)) {
  	    perror(PROGNAME);
  	    rv = 2;
  	}
+ 	else
+ 	    rv = 1;
+     }
+     else {
  	len = strlen(buf);
  	p = &buf[len - 1];
! 	
  	if (*(p--) != '\n') {
  	    fprintf(stderr,
***************
*** 185,200 ****
  		    buf);
  	    rv = 1;
- 	    break;
  	}
  	*(p + 1) = '\0';
  
! 	printf("%s %ld\n", buf, db_getvalue(dbh, buf));
!       }
!       db_lock_release(dbh);
      }
  
      return rv;
  }
  
  double compute_robx( dbh_t *dbh_spam, dbh_t *dbh_good )
  {
--- 187,287 ----
  		    buf);
  	    rv = 1;
  	}
  	*(p + 1) = '\0';
+     }
+     return rv;
+ }
  
! int words_from_list(char *db_file, int argc, char **argv)
! {
!     dbh_t *dbh;
!     int rv = 0;
! 
!     dbh = db_open_and_lock_file(db_file, db_file, DB_READ);
!     if ( dbh == NULL )
! 	return 2;
! 
!     if ( argc == 0)
!     {
! 	char buf[BUFSIZE];
! 	while (get_token(buf, BUFSIZE, stdin) == 0) {
! 	    printf("%s %ld\n", buf, db_getvalue(dbh, buf));
! 	}
!     }
!     else
!     {
! 	while (argc-- > 0) {
! 	    char *token = *++argv;
! 	    printf("%s %ld\n", token, db_getvalue(dbh, token));
! 	}
      }
  
+     db_close(dbh);
+ 
      return rv;
  }
  
+ int words_from_path(char *directory, int argc, char **argv)
+ {
+     dbh_t *dbh_good;
+     dbh_t *dbh_spam;
+     char filepath[PATH_LEN];
+ 
+     build_path(filepath, PATH_LEN, directory, GOODFILE);
+     if ((dbh_good = db_open_and_lock_file(filepath, GOODFILE, DB_READ)) == NULL)
+ 	return 2;
+ 
+     build_path(filepath, PATH_LEN, directory, SPAMFILE);
+     if ((dbh_spam = db_open_and_lock_file(filepath, SPAMFILE, DB_READ)) == NULL)
+ 	return 2;
+ 
+     printf("%-20s %6s %6s\n", "", "spam", "good");
+     if ( argc == 0)
+     {
+ 	char buf[BUFSIZE];
+ 	while (get_token(buf, BUFSIZE, stdin) == 0) {
+ 	    printf("%-20s %6ld %6ld\n", buf, db_getvalue(dbh_spam, buf), db_getvalue(dbh_good, buf));
+ 	}
+     }
+     else
+     {
+ 	while (argc-- > 0) {
+ 	    char *token = *argv++;
+ 	    printf("%-20s %6ld %6ld\n", token, db_getvalue(dbh_spam, token), db_getvalue(dbh_good, token));
+ 	}
+     }
+ 
+     db_close(dbh_good);
+     db_close(dbh_spam);
+ 
+     return 0;
+ }
+ 
+ int display_words(char *path, int argc, char **argv)
+ {
+     struct stat sb;
+     int rc = stat(path, &sb);
+ 
+     if (rc >= 0) 
+     {
+ 	if ( S_ISDIR(sb.st_mode))
+ 	    words_from_path(path, argc, argv);
+ 	else
+     	    words_from_list(path, argc, argv);
+     }
+     else
+     {
+ 	if (errno==ENOENT) {
+ 	    fprintf(stderr, "No such directory.\n");
+ 	    return 0;
+ 	}
+ 	else {
+ 	    perror("Error accessing directory");
+ 	    return -1;
+ 	}
+     }
+     return 0;
+ }
+ 
  double compute_robx( dbh_t *dbh_spam, dbh_t *dbh_good )
  {
***************
*** 419,423 ****
  
      /* Extra or missing parameters */
!     if (argc != optind) {
  	usage();
  	exit(1);
--- 506,510 ----
  
      /* Extra or missing parameters */
!     if (flag != WORD && argc != optind) {
  	usage();
  	exit(1);
***************
*** 430,434 ****
  	    return load_file(db_file);
  	case WORD:
! 	    return display_words(db_file);
  	case ROBX:
  	    return compute_robinson_x(db_file);
--- 517,523 ----
  	    return load_file(db_file);
  	case WORD:
! 	    argc -= optind;
! 	    argv += optind;
! 	    return display_words(db_file, argc, argv);
  	case ROBX:
  	    return compute_robinson_x(db_file);

2002	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep (92)	Oct (277)	Nov (500)	Dec (346)
2003	Jan (437)	Feb (277)	Mar (215)	Apr (220)	May (225)	Jun (119)	Jul (184)	Aug (306)	Sep (340)	Oct (231)	Nov (176)	Dec (232)
2004	Jan (202)	Feb (189)	Mar (111)	Apr (43)	May (99)	Jun (164)	Jul (71)	Aug (82)	Sep (61)	Oct (135)	Nov (208)	Dec (174)
2005	Jan (241)	Feb (99)	Mar (236)	Apr (112)	May (175)	Jun (178)	Jul (18)	Aug (31)	Sep (37)	Oct (60)	Nov (41)	Dec (69)
2006	Jan (34)	Feb (14)	Mar (16)	Apr (6)	May (20)	Jun (15)	Jul (64)	Aug (25)	Sep	Oct (2)	Nov (25)	Dec (13)
2007	Jan (36)	Feb (15)	Mar (3)	Apr (2)	May	Jun	Jul (25)	Aug (2)	Sep	Oct	Nov (12)	Dec (4)
2008	Jan (2)	Feb (12)	Mar (4)	Apr (14)	May (8)	Jun (4)	Jul (4)	Aug (5)	Sep	Oct (11)	Nov (1)	Dec
2009	Jan (15)	Feb (50)	Mar	Apr (2)	May (16)	Jun	Jul (13)	Aug (16)	Sep (1)	Oct (1)	Nov	Dec
2010	Jan (1)	Feb (7)	Mar (20)	Apr (5)	May	Jun	Jul (31)	Aug	Sep (1)	Oct (2)	Nov (1)	Dec (4)
2011	Jan (1)	Feb (3)	Mar (1)	Apr (1)	May (8)	Jun (2)	Jul	Aug	Sep	Oct	Nov	Dec
2012	Jan (6)	Feb	Mar	Apr (9)	May	Jun	Jul	Aug	Sep	Oct (2)	Nov (1)	Dec (12)
2013	Jan (2)	Feb	Mar	Apr	May	Jun (5)	Jul (4)	Aug	Sep	Oct	Nov (14)	Dec (1)
2014	Jan	Feb (3)	Mar	Apr	May	Jun	Jul (3)	Aug	Sep	Oct	Nov (2)	Dec
2015	Jan	Feb (10)	Mar (1)	Apr	May	Jun	Jul	Aug	Sep	Oct (11)	Nov	Dec
2016	Jan (4)	Feb	Mar	Apr	May	Jun	Jul (2)	Aug	Sep (2)	Oct (3)	Nov	Dec
2017	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep (4)	Oct	Nov	Dec
2018	Jan	Feb	Mar	Apr (1)	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec

S	M	T	W	T	F	S
		1	2 (7)	3 (2)	4 (28)	5 (1)
6 (7)	7 (6)	8 (3)	9 (5)	10 (4)	11 (17)	12 (1)
13 (5)	14 (2)	15 (11)	16	17 (3)	18 (1)	19 (16)
20 (5)	21 (10)	22 (13)	23 (12)	24 (6)	25 (17)	26 (23)
27 (9)	28 (17)	29 (18)	30 (17)	31 (11)

Thanks for helping keep SourceForge clean.

bogofilter -- Fast Bayesian Spam Filter

Fast Bayesian spam filter along lines suggested by Paul Graham

Brought to you by: m-a

bogofilter-cvs — For automated diffs from CVS commits