1 /* frcode -- front-compress a sorted list
2 Copyright (C) 1994 Free Software Foundation, Inc.
4 This program is free software; you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation; either version 2, or (at your option)
9 This program is distributed in the hope that it will be useful,
10 but WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 GNU General Public License for more details.
14 You should have received a copy of the GNU General Public License
15 along with this program; if not, write to the Free Software
16 Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */
18 /* Usage: frcode < sorted-list > compressed-list
20 Uses front compression (also known as incremental encoding);
21 see ";login:", March 1983, p. 8.
23 The input is a sorted list of NUL-terminated strings.
24 (FIXME newline-terminated, until we figure out how to sort
25 NUL-terminated strings.)
27 The output entries are in the same order as the input;
28 each entry consists of an offset-differential count byte
29 (the additional number of characters of prefix of the preceding entry to
30 use beyond the number that the preceding entry is using of its predecessor),
31 followed by a null-terminated ASCII remainder.
33 If the offset-differential count is larger than can be stored
34 in a byte (+/-127), the byte has the value LOCATEDB_ESCAPE
35 and the count follows in a 2-byte word, with the high byte first
40 Input, with NULs changed to newlines:
42 /usr/src/cmd/aardvark.c
43 /usr/src/cmd/armadillo.c
46 Length of the longest prefix of the preceding entry to share:
52 Output, with NULs changed to newlines and count bytes made printable:
59 (6 = 14 - 8, and -9 = 5 - 14)
61 Written by James A. Woods <jwoods@adobe.com>.
62 Modified by David MacKenzie <djm@gnu.ai.mit.edu>. */
66 #include <sys/types.h>
68 #if defined(HAVE_STRING_H) || defined(STDC_HEADERS)
82 /* The name this program was run with. */
85 /* Write out a 16-bit int, high byte first (network byte order). */
96 /* Return the length of the longest common prefix of strings S1 and S2. */
99 prefix_length (s1
, s2
)
102 register char *start
;
104 for (start
= s1
; *s1
== *s2
&& *s1
!= '\0'; s1
++, s2
++)
114 char *path
; /* The current input entry. */
115 char *oldpath
; /* The previous input entry. */
116 size_t pathsize
, oldpathsize
; /* Amounts allocated for them. */
117 int count
, oldcount
, diffcount
; /* Their prefix lengths & the difference. */
118 int line_len
; /* Length of input line. */
120 program_name
= argv
[0];
122 pathsize
= oldpathsize
= 1026; /* Increased as necessary by getstr. */
123 path
= xmalloc (pathsize
);
124 oldpath
= xmalloc (oldpathsize
);
126 /* Set to anything not starting with a slash, to force the first
127 prefix count to 0. */
128 strcpy (oldpath
, " ");
131 fwrite (LOCATEDB_MAGIC
, sizeof (LOCATEDB_MAGIC
), 1, stdout
);
133 /* FIXME temporary: change the \n to \0 when we figure out how to sort
134 null-terminated strings. */
135 while ((line_len
= getstr (&path
, &pathsize
, stdin
, '\n', 0)) > 0)
137 path
[line_len
- 1] = '\0'; /* FIXME temporary: nuke the newline. */
139 count
= prefix_length (oldpath
, path
);
140 diffcount
= count
- oldcount
;
142 /* If the difference is small, it fits in one byte;
143 otherwise, two bytes plus a marker noting that fact. */
144 if (diffcount
< -127 || diffcount
> 127)
146 putc (LOCATEDB_ESCAPE
, stdout
);
147 put_short (diffcount
, stdout
);
150 putc (diffcount
, stdout
);
152 fputs (path
+ count
, stdout
);
156 /* Swap path and oldpath and their sizes. */
157 char *tmppath
= oldpath
;
158 size_t tmppathsize
= oldpathsize
;
160 oldpathsize
= pathsize
;
162 pathsize
= tmppathsize
;