Subject: Re: base64 tool?
Newsgroups: gmane.comp.gnu.core-utils.bugs
Date: 2005-06-25 13:32:35 GMT (4 years, 1 week, 1 day, 15 hours and 30 minutes ago)
Simon Josefsson <jas <at> extundo.com> writes:
> Jim Meyering <jim <at> meyering.net> writes:
>
>> Simon Josefsson <jas <at> extundo.com> wrote:
>> ...
>>> I'll volunteer to submit a patch and documentation for the tool if you
>>> think it could be added.
>>
>> Ok. That sounds fair.
>> If you can add some tests too, that'd be great.
>> If so, please use something like coreutils/tests/md5sum/basic-1 as a model.
>
> Great! My package contain several self tests, they can probably be
> adapted easily.
Initial patch below; review is especially needed for the
coreutils.texi part. Self tests after lunch...
/ChangeLog:
2005-06-25 Simon Josefsson <jas <at> extundo.com>
* AUTHORS: Mention base64.
* NEWS: Likewise.
* man/Makefile.am: Build base64.1.
* man/base64.x: New file.
* src/Makefile.am (bin_PROGRAMS): Add base64.
* src/base64.c: New file.
doc/ChangeLog:
2005-06-25 Simon Josefsson <jas <at> extundo.com>
* coreutils.texi: Add base64 section.
lib/ChangeLog:
2005-06-25 Simon Josefsson <jas <at> extundo.com>
* base64.h, base64.c: New files.
* Makefile.am (libcoreutils_a_SOURCES): Add base64.h and base64.c.
Index: AUTHORS
===================================================================
RCS file: /cvsroot/coreutils/coreutils/AUTHORS,v
retrieving revision 1.7
diff -u -p -r1.7 AUTHORS
--- AUTHORS 3 Nov 2004 23:10:50 -0000 1.7
+++ AUTHORS 25 Jun 2005 13:28:38 -0000
@@ -1,6 +1,7 @@
Here are the names of the programs in this package,
each followed by the name(s) of its author(s).
+base64: Simon Josefsson
basename: FIXME unknown
cat: Torbjorn Granlund, Richard M. Stallman
chgrp: David MacKenzie, Jim Meyering
Index: NEWS
===================================================================
RCS file: /cvsroot/coreutils/coreutils/NEWS,v
retrieving revision 1.299
diff -u -p -r1.299 NEWS
--- NEWS 23 Jun 2005 22:37:33 -0000 1.299
+++ NEWS 25 Jun 2005 13:28:40 -0000
@@ -167,6 +167,11 @@ GNU coreutils NEWS
stat -f's default output format has been changed to output this size as well.
stat -f recognizes file systems of type XFS and JFS
+** New programs
+
+ base64 is a new tool that provide base64 encoding and decoding
+ functionality.
+
* Major changes in release 5.3.0 (2005-01-08) [unstable]
** Bug fixes
Index: README
===================================================================
RCS file: /cvsroot/coreutils/coreutils/README,v
retrieving revision 1.18
diff -u -p -r1.18 README
--- README 8 Jan 2005 09:00:08 -0000 1.18
+++ README 25 Jun 2005 13:28:40 -0000
@@ -7,13 +7,14 @@ arbitrary limits.
The programs that can be built with this package are:
- [ basename cat chgrp chmod chown chroot cksum comm cp csplit cut date dd
- df dir dircolors dirname du echo env expand expr factor false fmt fold
- ginstall groups head hostid hostname id join kill link ln logname ls
- md5sum mkdir mkfifo mknod mv nice nl nohup od paste pathchk pinky pr
- printenv printf ptx pwd readlink rm rmdir seq sha1sum shred sleep sort
- split stat stty su sum sync tac tail tee test touch tr true tsort tty
- uname unexpand uniq unlink uptime users vdir wc who whoami yes
+ [ base64 basename cat chgrp chmod chown chroot cksum comm cp csplit
+ cut date dd df dir dircolors dirname du echo env expand expr factor
+ false fmt fold ginstall groups head hostid hostname id join kill
+ link ln logname ls md5sum mkdir mkfifo mknod mv nice nl nohup od
+ paste pathchk pinky pr printenv printf ptx pwd readlink rm rmdir seq
+ sha1sum shred sleep sort split stat stty su sum sync tac tail tee
+ test touch tr true tsort tty uname unexpand uniq unlink uptime users
+ vdir wc who whoami yes
See the file NEWS for a list of major changes in the current release.
Index: doc/coreutils.texi
===================================================================
RCS file: /cvsroot/coreutils/coreutils/doc/coreutils.texi,v
retrieving revision 1.269
diff -u -p -r1.269 coreutils.texi
--- doc/coreutils.texi 24 Jun 2005 08:05:51 -0000 1.269
+++ doc/coreutils.texi 25 Jun 2005 13:28:44 -0000
@@ -36,6 +36,7 @@
@dircategory Individual utilities
@direntry
+* base64: (coreutils)base64 invocation. Base64 encode/decode data.
* basename: (coreutils)basename invocation. Strip directory and suffix.
* cat: (coreutils)cat invocation. Concatenate and write files.
* chgrp: (coreutils)chgrp invocation. Change file groups.
@@ -217,6 +218,7 @@ Output of entire files
* tac invocation:: Concatenate and write files in reverse.
* nl invocation:: Number lines and write files.
* od invocation:: Write files in octal or other formats.
+* base64 invocation:: Transform data into printable data.
Formatting file contents
@@ -1183,6 +1185,7 @@ in some way.
* tac invocation:: Concatenate and write files in reverse.
* nl invocation:: Number lines and write files.
* od invocation:: Write files in octal or other formats.
+* base64 invocation:: Transform data into printable data.
@end menu
@node cat invocation
@@ -1764,6 +1767,64 @@ address.
@exitstatus
+@node base64 invocation
+@section @command{base64}: Transform data into printable data.
+
+@pindex base64
+@cindex base64 encoding
+
+@command{base64} transform data read from standard input, or the
+string given as argument, into (or from) base64 encoded form. The
+base64 encoded form uses printable @acronym{ASCII} characters to
+represent binary data, see
+@uref{ftp://ftp.rfc-editor.org/in-notes/rfc3548.txt, RFC 3548}.
+Synopses:
+
+@smallexample
+base64 [@var{option}]@dots{} [@var{string}]
+base64 --decode [@var{option}]@dots{} [@var{string}]
+@end smallexample
+
+The base64 encoding expand data to roughly 133% of the original.
+
+The program accepts the following options. Also see @ref{Common options}.
+
+@table @samp
+
+@item -w[@var{COLS}]
+@itemx --wrap[=@var{COLS}]
+@opindex -w
+@opindex --wrap
+@cindex wrap data
+@cindex column to wrap data after
+During encoding, wrap lines after @var{COLS} characters. This must be
+a positive number.
+
+If this option is not given at all, no line wrapping will be
+performed. If @var{COLS} is omitted, the default is 76.
+
+@item -d
+@itemx --decode
+@opindex -d
+@opindex --decode
+@cindex Decode base64 data
+@cindex Base64 decoding
+Change the mode of operation, from the default of encoding data, to
+decoding data. Input is expected to be base64 encoded data, and the
+output will be the original data.
+
+@item -i
+@itemx --ignore-garbage
+@opindex -i
+@opindex --ignore-garbage
+@cindex Ignore garbage in base64 stream
+During decoding, ignore unrecognized characters (including newline),
+to permit distorted data to be decoded.
+
+@end table
+
+@exitstatus
+
@node Formatting file contents
@chapter Formatting file contents
Index: lib/Makefile.am
===================================================================
RCS file: /cvsroot/coreutils/coreutils/lib/Makefile.am,v
retrieving revision 1.223
diff -u -p -r1.223 Makefile.am
--- lib/Makefile.am 23 Jun 2005 18:41:48 -0000 1.223
+++ lib/Makefile.am 25 Jun 2005 13:28:45 -0000
@@ -27,6 +27,7 @@ DEFS += -DLIBDIR=\"$(libdir)\"
libcoreutils_a_SOURCES = \
allocsa.c allocsa.h \
+ base64.c base64.h \
dev-ino.h \
diacrit.c diacrit.h \
euidaccess.h \
Index: lib/base64.c
===================================================================
RCS file: lib/base64.c
diff -N lib/base64.c
--- /dev/null 1 Jan 1970 00:00:00 -0000
+++ lib/base64.c 25 Jun 2005 13:28:45 -0000
@@ -0,0 +1,403 @@
+/* base64.c -- Encode binary data using printable characters.
+ Copyright (C) 1999, 2000, 2001, 2004 Free Software Foundation, Inc.
+
+ 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 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, write to the Free Software Foundation,
+ Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
+
+/* Written by Simon Josefsson. Partially adapted from GNU MailUtils
+ * (mailbox/filter_trans.c, as of 2004-11-28). Improved by review
+ * from Paul Eggert, Bruno Haible, and Stepan Kasal.
+ *
+ * See also RFC 3548 <http://www.ietf.org/rfc/rfc3548.txt>.
+ *
+ * Be careful with error checking. Here is how you would typically
+ * use these functions:
+ *
+ * bool ok = base64_decode_alloc (in, inlen, &out, &outlen);
+ * if (!ok)
+ * FAIL: input was not valid base64
+ * if (out == NULL)
+ * FAIL: memory allocation error
+ * OK: data in OUT/OUTLEN
+ *
+ * size_t outlen = base64_encode_alloc (in, inlen, &out);
+ * if (out == NULL && outlen == 0 && inlen != 0)
+ * FAIL: input too long
+ * if (out == NULL)
+ * FAIL: memory allocation error
+ * OK: data in OUT/LEN.
+ *
+ */
+
+#ifdef HAVE_CONFIG_H
+# include <config.h>
+#endif
+
+/* Get prototype. */
+#include "base64.h"
+
+/* Get malloc. */
+#include <stdlib.h>
+
+/* C89 compliant way to cast 'char' to 'unsigned char'. */
+static inline unsigned char
+to_uchar (char ch)
+{
+ return ch;
+}
+
+/* Base64 encode IN array of size INLEN into OUT array of size OUTLEN.
+ If OUTLEN is less than BASE64_LENGTH(INLEN), write as many bytes as
+ possible. If OUTLEN is larger than BASE64_LENGTH(INLEN), also zero
+ terminate the output buffer. */
+void
+base64_encode (const char *restrict in, size_t inlen,
+ char *restrict out, size_t outlen)
+{
+ const char b64[64] =
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
+
+ while (inlen && outlen)
+ {
+ *out++ = b64[to_uchar (in[0]) >> 2];
+ if (!--outlen)
+ break;
+ *out++ = b64[((to_uchar (in[0]) << 4)
+ + (--inlen ? to_uchar (in[1]) >> 4 : 0)) & 0x3f];
+ if (!--outlen)
+ break;
+ *out++ =
+ (inlen
+ ? b64[((to_uchar (in[1]) << 2)
+ + (--inlen ? to_uchar (in[2]) >> 6 : 0)) & 0x3f] : '=');
+ if (!--outlen)
+ break;
+ *out++ = inlen ? b64[to_uchar (in[2]) & 0x3f] : '=';
+ if (!--outlen)
+ break;
+ if (inlen)
+ inlen--;
+ in += 3;
+ }
+
+ if (outlen)
+ *out = '\0';
+}
+
+/* Allocate a buffer and store zero terminated base64 encoded data
+ from array IN of size INLEN, returning BASE64_LENGTH(INLEN), i.e.,
+ the length of the encoded data, excluding the terminating zero. On
+ return, the OUT variable will hold a pointer to newly allocated
+ memory that must be deallocated by the caller. If output string
+ length would overflow, 0 is returned and OUT is set to NULL. If
+ memory allocation fail, OUT is set to NULL, and the return value
+ indicate length of the requested memory block, i.e.,
+ BASE64_LENGTH(inlen) + 1. */
+size_t
+base64_encode_alloc (const char *in, size_t inlen, char **out)
+{
+ size_t outlen = 1 + BASE64_LENGTH (inlen);
+
+ /* Check for overflow in outlen computation.
+ *
+ * If there is no overflow, outlen >= inlen.
+ *
+ * If the operation (inlen + 2) overflows then it yields at most +1, so
+ * outlen is 0.
+ *
+ * If the multiplication overflows, we lose at least half of the
+ * correct value, so the result is < ((inlen + 2) / 3) * 2, which is
+ * less than (inlen + 2) * 0.66667, which is less than inlen as soon as
+ * (inlen > 4).
+ */
+ if (inlen > outlen)
+ {
+ *out = NULL;
+ return 0;
+ }
+
+ *out = malloc (outlen);
+ if (*out)
+ base64_encode (in, inlen, *out, outlen);
+
+ return outlen - 1;
+}
+
+/* With this approach this file works independent of the charset used
+ (think EBCDIC). However, it does assume that the characters in the
+ Base64 alphabet (A-Za-z0-9+/) are encoded in 0..255. POSIX
+ 1003.1-2001 require that char and unsigned char are 8-bit
+ quantities, though, taking care of that problem. But this may be a
+ potential problem on non-POSIX C99 platforms. */
+#define B64(x) \
+ ((x) == 'A' ? 0 \
+ : (x) == 'B' ? 1 \
+ : (x) == 'C' ? 2 \
+ : (x) == 'D' ? 3 \
+ : (x) == 'E' ? 4 \
+ : (x) == 'F' ? 5 \
+ : (x) == 'G' ? 6 \
+ : (x) == 'H' ? 7 \
+ : (x) == 'I' ? 8 \
+ : (x) == 'J' ? 9 \
+ : (x) == 'K' ? 10 \
+ : (x) == 'L' ? 11 \
+ : (x) == 'M' ? 12 \
+ : (x) == 'N' ? 13 \
+ : (x) == 'O' ? 14 \
+ : (x) == 'P' ? 15 \
+ : (x) == 'Q' ? 16 \
+ : (x) == 'R' ? 17 \
+ : (x) == 'S' ? 18 \
+ : (x) == 'T' ? 19 \
+ : (x) == 'U' ? 20 \
+ : (x) == 'V' ? 21 \
+ : (x) == 'W' ? 22 \
+ : (x) == 'X' ? 23 \
+ : (x) == 'Y' ? 24 \
+ : (x) == 'Z' ? 25 \
+ : (x) == 'a' ? 26 \
+ : (x) == 'b' ? 27 \
+ : (x) == 'c' ? 28 \
+ : (x) == 'd' ? 29 \
+ : (x) == 'e' ? 30 \
+ : (x) == 'f' ? 31 \
+ : (x) == 'g' ? 32 \
+ : (x) == 'h' ? 33 \
+ : (x) == 'i' ? 34 \
+ : (x) == 'j' ? 35 \
+ : (x) == 'k' ? 36 \
+ : (x) == 'l' ? 37 \
+ : (x) == 'm' ? 38 \
+ : (x) == 'n' ? 39 \
+ : (x) == 'o' ? 40 \
+ : (x) == 'p' ? 41 \
+ : (x) == 'q' ? 42 \
+ : (x) == 'r' ? 43 \
+ : (x) == 's' ? 44 \
+ : (x) == 't' ? 45 \
+ : (x) == 'u' ? 46 \
+ : (x) == 'v' ? 47 \
+ : (x) == 'w' ? 48 \
+ : (x) == 'x' ? 49 \
+ : (x) == 'y' ? 50 \
+ : (x) == 'z' ? 51 \
+ : (x) == '0' ? 52 \
+ : (x) == '1' ? 53 \
+ : (x) == '2' ? 54 \
+ : (x) == '3' ? 55 \
+ : (x) == '4' ? 56 \
+ : (x) == '5' ? 57 \
+ : (x) == '6' ? 58 \
+ : (x) == '7' ? 59 \
+ : (x) == '8' ? 60 \
+ : (x) == '9' ? 61 \
+ : (x) == '+' ? 62 \
+ : (x) == '/' ? 63 \
+ : -1)
+
+static const signed char b64[0x100] = {
+ B64 (0), B64 (1), B64 (2), B64 (3),
+ B64 (4), B64 (5), B64 (6), B64 (7),
+ B64 (8), B64 (9), B64 (10), B64 (11),
+ B64 (12), B64 (13), B64 (14), B64 (15),
+ B64 (16), B64 (17), B64 (18), B64 (19),
+ B64 (20), B64 (21), B64 (22), B64 (23),
+ B64 (24), B64 (25), B64 (26), B64 (27),
+ B64 (28), B64 (29), B64 (30), B64 (31),
+ B64 (32), B64 (33), B64 (34), B64 (35),
+ B64 (36), B64 (37), B64 (38), B64 (39),
+ B64 (40), B64 (41), B64 (42), B64 (43),
+ B64 (44), B64 (45), B64 (46), B64 (47),
+ B64 (48), B64 (49), B64 (50), B64 (51),
+ B64 (52), B64 (53), B64 (54), B64 (55),
+ B64 (56), B64 (57), B64 (58), B64 (59),
+ B64 (60), B64 (61), B64 (62), B64 (63),
+ B64 (64), B64 (65), B64 (66), B64 (67),
+ B64 (68), B64 (69), B64 (70), B64 (71),
+ B64 (72), B64 (73), B64 (74), B64 (75),
+ B64 (76), B64 (77), B64 (78), B64 (79),
+ B64 (80), B64 (81), B64 (82), B64 (83),
+ B64 (84), B64 (85), B64 (86), B64 (87),
+ B64 (88), B64 (89), B64 (90), B64 (91),
+ B64 (92), B64 (93), B64 (94), B64 (95),
+ B64 (96), B64 (97), B64 (98), B64 (99),
+ B64 (100), B64 (101), B64 (102), B64 (103),
+ B64 (104), B64 (105), B64 (106), B64 (107),
+ B64 (108), B64 (109), B64 (110), B64 (111),
+ B64 (112), B64 (113), B64 (114), B64 (115),
+ B64 (116), B64 (117), B64 (118), B64 (119),
+ B64 (120), B64 (121), B64 (122), B64 (123),
+ B64 (124), B64 (125), B64 (126), B64 (127),
+ B64 (128), B64 (129), B64 (130), B64 (131),
+ B64 (132), B64 (133), B64 (134), B64 (135),
+ B64 (136), B64 (137), B64 (138), B64 (139),
+ B64 (140), B64 (141), B64 (142), B64 (143),
+ B64 (144), B64 (145), B64 (146), B64 (147),
+ B64 (148), B64 (149), B64 (150), B64 (151),
+ B64 (152), B64 (153), B64 (154), B64 (155),
+ B64 (156), B64 (157), B64 (158), B64 (159),
+ B64 (160), B64 (161), B64 (162), B64 (163),
+ B64 (164), B64 (165), B64 (166), B64 (167),
+ B64 (168), B64 (169), B64 (170), B64 (171),
+ B64 (172), B64 (173), B64 (174), B64 (175),
+ B64 (176), B64 (177), B64 (178), B64 (179),
+ B64 (180), B64 (181), B64 (182), B64 (183),
+ B64 (184), B64 (185), B64 (186), B64 (187),
+ B64 (188), B64 (189), B64 (190), B64 (191),
+ B64 (192), B64 (193), B64 (194), B64 (195),
+ B64 (196), B64 (197), B64 (198), B64 (199),
+ B64 (200), B64 (201), B64 (202), B64 (203),
+ B64 (204), B64 (205), B64 (206), B64 (207),
+ B64 (208), B64 (209), B64 (210), B64 (211),
+ B64 (212), B64 (213), B64 (214), B64 (215),
+ B64 (216), B64 (217), B64 (218), B64 (219),
+ B64 (220), B64 (221), B64 (222), B64 (223),
+ B64 (224), B64 (225), B64 (226), B64 (227),
+ B64 (228), B64 (229), B64 (230), B64 (231),
+ B64 (232), B64 (233), B64 (234), B64 (235),
+ B64 (236), B64 (237), B64 (238), B64 (239),
+ B64 (240), B64 (241), B64 (242), B64 (243),
+ B64 (244), B64 (245), B64 (246), B64 (247),
+ B64 (248), B64 (249), B64 (250), B64 (251),
+ B64 (252), B64 (253), B64 (254), B64 (255)
+};
+
+bool
+isbase64 (char ch)
+{
+ return to_uchar (ch) <= 255 && 0 <= b64[to_uchar (ch)];
+}
+
+/* Decode base64 encoded input array IN of length INLEN to output
+ array OUT that can hold *OUTLEN bytes. Return true if decoding was
+ successful, i.e. if the input was valid base64 data, false
+ otherwise. If *OUTLEN is too small, as many bytes as possible will
+ be written to OUT. On return, *OUTLEN holds the length of decoded
+ bytes in OUT. Note that as soon as any non-alphabet characters are
+ encountered, decoding is stopped and false is returned. */
+bool
+base64_decode (const char *restrict in, size_t inlen,
+ char *restrict out, size_t * outlen)
+{
+ size_t outleft = *outlen;
+
+ while (inlen >= 2)
+ {
+ if (!isbase64 (in[0]) || !isbase64 (in[1]))
+ break;
+
+ if (outleft)
+ {
+ *out++ = ((b64[to_uchar (in[0])] << 2)
+ | (b64[to_uchar (in[1])] >> 4));
+ outleft--;
+ }
+
+ if (inlen == 2)
+ break;
+
+ if (in[2] == '=')
+ {
+ if (inlen != 4)
+ break;
+
+ if (in[3] != '=')
+ break;
+
+ }
+ else
+ {
+ if (!isbase64 (in[2]))
+ break;
+
+ if (outleft)
+ {
+ *out++ = (((b64[to_uchar (in[1])] << 4) & 0xf0)
+ | (b64[to_uchar (in[2])] >> 2));
+ outleft--;
+ }
+
+ if (inlen == 3)
+ break;
+
+ if (in[3] == '=')
+ {
+ if (inlen != 4)
+ break;
+ }
+ else
+ {
+ if (!isbase64 (in[3]))
+ break;
+
+ if (outleft)
+ {
+ *out++ = (((b64[to_uchar (in[2])] << 6) & 0xc0)
+ | b64[to_uchar (in[3])]);
+ outleft--;
+ }
+ }
+ }
+
+ in += 4;
+ inlen -= 4;
+ }
+
+ *outlen -= outleft;
+
+ if (inlen != 0)
+ return false;
+
+ return true;
+}
+
+/* Allocate an output buffer in *OUT, and decode the base64 encoded
+ data stored in IN of size INLEN to the *OUT buffer. On return, the
+ size of the decoded data is stored in *OUTLEN. OUTLEN may be NULL,
+ if the caller is not interested in the decoded length. *OUT may be
+ NULL to indicate an out of memory error, in which case *OUTLEN
+ contain the size of the memory block needed. The function return
+ true on successful decoding and memory allocation errors. (Use the
+ *OUT and *OUTLEN parameters to differentiate between successful
+ decoding and memory error.) The function return false if the input
+ was invalid, in which case *OUT is NULL and *OUTLEN is
+ undefined. */
+bool
+base64_decode_alloc (const char *in, size_t inlen, char **out,
+ size_t * outlen)
+{
+ /* This may allocate a few bytes too much, depending on input,
+ but it's not worth the extra CPU time to compute the exact amount.
+ The exact amount is 3 * inlen / 4, minus 1 if the input ends
+ with "=" and minus another 1 if the input ends with "==".
+ Dividing before multiplying avoids the possibility of overflow. */
+ size_t needlen = 3 * (inlen / 4) + 2;
+
+ *out = malloc (needlen);
+ if (!*out)
+ return true;
+
+ if (!base64_decode (in, inlen, *out, &needlen))
+ {
+ free (*out);
+ *out = NULL;
+ return false;
+ }
+
+ if (outlen)
+ *outlen = needlen;
+
+ return true;
+}
Index: lib/base64.h
===================================================================
RCS file: lib/base64.h
diff -N lib/base64.h
--- /dev/null 1 Jan 1970 00:00:00 -0000
+++ lib/base64.h 25 Jun 2005 13:28:45 -0000
@@ -0,0 +1,45 @@
+/* base64.h -- Encode binary data using printable characters.
+ Copyright (C) 2004 Free Software Foundation, Inc.
+ Written by Simon Josefsson.
+
+ 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 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, write to the Free Software Foundation,
+ Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
+
+#ifndef BASE64_H
+# define BASE64_H
+
+/* Get size_t. */
+#include <stddef.h>
+
+/* Get bool. */
+#include <stdbool.h>
+
+/* This uses that the expression (n+(k-1))/k means the smallest
+ integer >= n/k, i.e., the ceiling of n/k. */
+#define BASE64_LENGTH(inlen) ((((inlen) + 2) / 3) * 4)
+
+extern bool isbase64 (char ch);
+
+extern void base64_encode (const char *restrict in, size_t inlen,
+ char *restrict out, size_t outlen);
+
+extern size_t base64_encode_alloc (const char *in, size_t inlen, char **out);
+
+extern bool base64_decode (const char *restrict in, size_t inlen,
+ char *restrict out, size_t * outlen);
+
+extern bool base64_decode_alloc (const char *in, size_t inlen,
+ char **out, size_t * outlen);
+
+#endif /* BASE64_H */
Index: man/.cvsignore
===================================================================
RCS file: /cvsroot/coreutils/coreutils/man/.cvsignore,v
retrieving revision 1.4
diff -u -p -r1.4 .cvsignore
--- man/.cvsignore 7 Aug 2003 08:04:52 -0000 1.4
+++ man/.cvsignore 25 Jun 2005 13:28:45 -0000
@@ -1,4 +1,5 @@
Makefile
+base64.1
basename.1
cat.1
chgrp.1
Index: man/Makefile.am
===================================================================
RCS file: /cvsroot/coreutils/coreutils/man/Makefile.am,v
retrieving revision 1.38
diff -u -p -r1.38 Makefile.am
--- man/Makefile.am 5 Apr 2005 22:21:14 -0000 1.38
+++ man/Makefile.am 25 Jun 2005 13:28:45 -0000
@@ -1,6 +1,6 @@
## Process this file with automake to produce Makefile.in -*-Makefile-*-
dist_man_MANS = \
- basename.1 cat.1 chgrp.1 chmod.1 chown.1 chroot.1 cksum.1 comm.1 \
+ base64.1 basename.1 cat.1 chgrp.1 chmod.1 chown.1 chroot.1 cksum.1 comm.1 \
cp.1 csplit.1 cut.1 date.1 dd.1 df.1 dir.1 dircolors.1 dirname.1 du.1 \
echo.1 env.1 expand.1 expr.1 factor.1 false.1 fmt.1 fold.1 groups.1 \
head.1 hostid.1 hostname.1 id.1 install.1 join.1 kill.1 \
@@ -20,6 +20,7 @@ MAINTAINERCLEANFILES = $(man_MANS)
# Depend on configure.ac to get version number changes.
common_dep = $(top_srcdir)/configure.ac
+base64.1: $(common_dep) $(srcdir)/base64.x ../src/base64.c
basename.1: $(common_dep) $(srcdir)/basename.x ../src/basename.c
cat.1: $(common_dep) $(srcdir)/cat.x ../src/cat.c
chgrp.1: $(common_dep) $(srcdir)/chgrp.x ../src/chgrp.c
Index: man/base64.x
===================================================================
RCS file: man/base64.x
diff -N man/base64.x
--- /dev/null 1 Jan 1970 00:00:00 -0000
+++ man/base64.x 25 Jun 2005 13:28:45 -0000
@@ -0,0 +1,4 @@
+[NAME]
+base64 \- base64 encode/decode data and print to standard output
+[DESCRIPTION]
+.\" Add any additional description here
Index: src/.cvsignore
===================================================================
RCS file: /cvsroot/coreutils/coreutils/src/.cvsignore,v
retrieving revision 1.11
diff -u -p -r1.11 .cvsignore
--- src/.cvsignore 27 Sep 2004 07:22:45 -0000 1.11
+++ src/.cvsignore 25 Jun 2005 13:29:23 -0000
@@ -2,6 +2,7 @@
.version
Makefile
[[]
+base64
basename
cat
chgrp
Index: src/Makefile.am
===================================================================
RCS file: /cvsroot/coreutils/coreutils/src/Makefile.am,v
retrieving revision 1.56
diff -u -p -r1.56 Makefile.am
--- src/Makefile.am 18 May 2005 19:32:11 -0000 1.56
+++ src/Makefile.am 25 Jun 2005 13:29:23 -0000
@@ -25,7 +25,7 @@ bin_PROGRAMS = [ chgrp chown chmod cp dd
mkfifo mknod mv nohup readlink rm rmdir shred stat sync touch unlink \
cat cksum comm csplit cut expand fmt fold head join md5sum \
nl od paste pr ptx sha1sum sort split sum tac tail tr tsort unexpand uniq wc \
- basename date dirname echo env expr factor false \
+ base64 basename date dirname echo env expr factor false \
hostname id kill logname pathchk printenv printf pwd seq sleep tee \
test true tty whoami yes \
$(OPTIONAL_BIN_PROGS) $(DF_PROG)
Index: src/base64.c
===================================================================
RCS file: src/base64.c
diff -N src/base64.c
--- /dev/null 1 Jan 1970 00:00:00 -0000
+++ src/base64.c 25 Jun 2005 13:29:23 -0000
@@ -0,0 +1,331 @@
+/* Base64 encode/decode strings or files.
+ Copyright (C) 2004, 2005 Free Software Foundation, Inc.
+
+ This file is part of Base64.
+
+ Base64 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 2, or (at your option)
+ any later version.
+
+ Base64 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 Base64; see the file COPYING. If not, write to the Free
+ Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301, USA. */
+
+/* Written by Simon Josefsson <simon <at> josefsson.org>. */
+
+#include <config.h>
+#include <getopt.h>
+
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <limits.h>
+#include <errno.h>
+
+#include "error.h"
+#include "xstrtol.h"
+#include "quote.h"
+#include "quotearg.h"
+#include "system.h"
+
+#include "base64.h"
+
+/* The official name of this program (e.g., no `g' prefix). */
+#define PROGRAM_NAME "base64"
+
+#define AUTHOR "Simon Josefsson"
+
+/* The invocation name of this program. */
+char *program_name;
+
+static const struct option long_options[] = {
+ {"decode", no_argument, 0, 'd'},
+ {"wrap", optional_argument, 0, 'w'},
+ {"ignore-garbage", no_argument, 0, 'i'},
+ {"help", no_argument, 0, GETOPT_HELP_CHAR},
+ {"version", no_argument, 0, GETOPT_VERSION_CHAR},
+
+ {GETOPT_HELP_OPTION_DECL},
+ {GETOPT_VERSION_OPTION_DECL},
+ {NULL, 0, NULL, 0}
+};
+
+static void
+usage (int status)
+{
+ if (status != EXIT_SUCCESS)
+ fprintf (stderr, _("Try `%s --help' for more information.\n"),
+ program_name);
+ else
+ {
+ printf (_("\
+Usage: %s [OPTION] [STRING]\n\
+Base64 encode or decode STRING, or standard input, to standard output.\n\
+\n"), program_name);
+ fputs (_("\
+ -w, --wrap[=COLS] Wrap encoded lines after COLS character (default 76).\n\
+\n\
+ -d, --decode Decode data.\n\
+ -i, --ignore-garbage When decoding, ignore non-alphabet characters.\n\
+\n\
+"), stdout);
+ fputs (_("\
+ --help Display this help and exit.\n\
+ --version Output version information and exit.\n"), stdout);
+ fputs (_("\
+\n\
+The data is encoded as described for the base64 alphabet in RFC 3548.\n\
+Decoding require compliant input by default, use --ignore-garbage to\n\
+attempt to recover from non-alphabet characters (such as newlines) in\n\
+the encoded stream.\n"), stdout);
+ printf (_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
+ }
+
+ exit (status);
+}
+
+/* Note that increasing this may decrease performance if --ignore-garbage
+ is used, because of the memmove operation below. */
+#define BLOCKSIZE 3072
+#define B64BLOCKSIZE BASE64_LENGTH (BLOCKSIZE)
+
+/* Ensure that BLOCKSIZE is a multiple of 3 and 4. */
+#if BLOCKSIZE % 12 != 0
+# error "invalid BLOCKSIZE"
+#endif
+
+static void
+wrap_write (const char *buffer, size_t len,
+ size_t wrap_column, size_t * current_column, FILE * out)
+{
+ size_t written;
+
+ if (wrap_column == 0)
+ {
+ /* Simple write. */
+ if (fwrite (buffer, 1, len, stdout) < len)
+ error (EXIT_FAILURE, errno, _("write error"));
+ }
+ else
+ for (written = 0; written < len;)
+ {
+ size_t to_write = wrap_column - *current_column;
+
+ if (written + to_write > len)
+ to_write = len - written;
+
+ if (to_write == 0
+ ? (fputs ("\n", out) < 0)
+ : (fwrite (buffer + written, 1, to_write, stdout) < to_write))
+ error (EXIT_FAILURE, errno, _("write error"));
+
+ written += to_write;
+ *current_column = to_write;
+ }
+}
+
+static void
+do_encode (FILE * in, FILE * out, size_t wrap_column)
+{
+ size_t current_column = 0;
+ char inbuf[BLOCKSIZE];
+ char outbuf[B64BLOCKSIZE];
+ size_t sum;
+
+ do
+ {
+ size_t n;
+
+ sum = 0;
+ do
+ {
+ n = fread (inbuf + sum, 1, BLOCKSIZE - sum, in);
+
+ if (n > BLOCKSIZE - sum)
+ error (EXIT_FAILURE, 0, _("read too much"));
+
+ sum += n;
+ }
+ while (!feof (in) && !ferror (in) && sum < BLOCKSIZE);
+
+ if (sum > 0)
+ {
+ /* Process input one block at a time. Note that BLOCKSIZE %
+ 3 == 0, so that no base64 pads will appear in output. */
+ base64_encode (inbuf, sum, outbuf, BASE64_LENGTH (sum));
+
+ wrap_write (outbuf, BASE64_LENGTH (sum), wrap_column,
+ ¤t_column, out);
+ }
+ }
+ while (!feof (in) && !ferror (in) && sum == BLOCKSIZE);
+
+ /* When wrapping, terminate last line. */
+ if (wrap_column && fputs ("\n", out) < 0)
+ error (EXIT_FAILURE, errno, _("write error"));
+
+ if (ferror (in))
+ error (EXIT_FAILURE, errno, _("read error"));
+}
+
+static void
+do_decode (FILE * in, FILE * out, size_t ignore_garbage)
+{
+ char inbuf[B64BLOCKSIZE];
+ char outbuf[BLOCKSIZE];
+ size_t sum;
+
+ do
+ {
+ bool ok;
+ size_t n;
+
+ sum = 0;
+ do
+ {
+ n = fread (inbuf + sum, 1, B64BLOCKSIZE - sum, in);
+
+ if (n > B64BLOCKSIZE - sum)
+ error (EXIT_FAILURE, 0, _("read too much"));
+
+ if (ignore_garbage)
+ {
+ size_t i;
+ for (i = 0; n > 0 && i < n;)
+ if (isbase64 (inbuf[sum + i]) || inbuf[sum + i] == '=')
+ i++;
+ else
+ memmove (inbuf + sum + i, inbuf + sum + i + 1, --n - i);
+ }
+
+ sum += n;
+
+ if (ferror (in))
+ error (EXIT_FAILURE, errno, _("read error"));
+ }
+ while (sum < B64BLOCKSIZE && !feof (in));
+
+ n = BLOCKSIZE;
+ ok = base64_decode (inbuf, sum, outbuf, &n);
+
+ if (fwrite (outbuf, 1, n, stdout) < n)
+ error (EXIT_FAILURE, errno, _("write error"));
+
+ if (!ok)
+ error (EXIT_FAILURE, 0, _("invalid input"));
+ }
+ while (!feof (in));
+}
+
+int
+main (int argc, char **argv)
+{
+ int opt;
+ bool decode = false;
+ bool ignore_garbage = false;
+ size_t wrap_column = 0;
+
+ initialize_main (&argc, &argv);
+ program_name = argv[0];
+ setlocale (LC_ALL, "");
+ bindtextdomain (PACKAGE, LOCALEDIR);
+ textdomain (PACKAGE);
+
+ atexit (close_stdout);
+
+ while ((opt = getopt_long (argc, argv, "dqiw", long_options, NULL)) != -1)
+ switch (opt)
+ {
+ case 'd':
+ decode = true;
+ break;
+
+ case 'w':
+ if (optarg)
+ {
+ unsigned long int tmp_ulong;
+ if (xstrtoul (optarg, NULL, 0, &tmp_ulong, NULL) != LONGINT_OK
+ || SIZE_MAX < tmp_ulong || tmp_ulong == 0)
+ error (EXIT_FAILURE, 0, _("invalid wrap column: %s"),
+ quotearg (optarg));
+ wrap_column = tmp_ulong;
+ }
+ else
+ wrap_column = 76;
+ break;
+
+ case 'i':
+ ignore_garbage = true;
+ break;
+
+ case_GETOPT_HELP_CHAR;
+
+ case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHOR);
+
+ default:
+ usage (EXIT_FAILURE);
+ break;
+ }
+
+ if (argc - optind > 1)
+ {
+ error (0, 0, _("extra operand %s"), quote (argv[optind]));
+ usage (EXIT_FAILURE);
+ }
+
+ if (optind < argc)
+ {
+ const char *inbuf = argv[optind];
+ size_t inlen = strlen (argv[optind]);
+ char *out = NULL;
+ size_t outlen = 0;
+
+ if (decode)
+ {
+ if (!base64_decode_alloc (inbuf, inlen, &out, &outlen))
+ error (EXIT_FAILURE, 0, _("invalid input"));
+ if (out == NULL)
+ xalloc_die ();
+
+ if (fwrite (out, 1, outlen, stdout) < outlen)
+ error (EXIT_FAILURE, errno, _("write error"));
+
+ free (out);
+ }
+ else
+ {
+ size_t current_column = 0;
+
+ outlen = base64_encode_alloc (inbuf, inlen, &out);
+
+ if (out == NULL && outlen == 0 && inlen != 0)
+ error (EXIT_FAILURE, 0, "overlong input");
+ if (out == NULL)
+ xalloc_die ();
+
+ wrap_write (out, outlen, wrap_column, ¤t_column, stdout);
+
+ free (out);
+ }
+ }
+ else
+ {
+ if (decode)
+ do_decode (stdin, stdout, ignore_garbage);
+ else
+ do_encode (stdin, stdout, wrap_column);
+ }
+
+ if (fclose (stdin) == EOF)
+ error (EXIT_FAILURE, errno, _("standard input"));
+
+ exit (EXIT_SUCCESS);
+}