Hello, Am Sunday, den 21. April 2002 13:13:16 schrieb berberic: > I appended a patch for cat.c.
I'm very sorry, but as I just noticed the patch was not against the
original sources, but against a patched version of the sources from my
linux-distribution. This time I attached the (hopefully) correct patch.
(I repeat the explanation:)
cat -v prints every character out of 32..127 as ^ or M- notation. This
might be sufficient for the english speaking world, but is an anoyance
for europeans, because it destroys text strings containing accented
charakters, umlauts, etc. I added a new option (-p or
--show-locale-chars) that does not change characters that are
printable in the actual locale (using isprint).
This is quite usefull for non-english-speaking peoples because it
allows to "strip" control-chars from a "text"-stream without
destroying accented characters, umlauts, ...
MfG
bmg
--
"Des is völlig wurscht, was heut beschlos- | M G Berberich
sen wird: I bin sowieso dagegn!" | [EMAIL PROTECTED]
(SPD-Stadtrat Kurt Schindler; Regensburg) |
diff -Naur textutils-2.0/po/de.po textutils-2.0-isprint/po/de.po
--- textutils-2.0/po/de.po Fri Aug 6 22:56:36 1999
+++ textutils-2.0-isprint/po/de.po Sun Apr 21 14:53:45 2002
@@ -42,6 +43,8 @@
" -T, --show-tabs display TAB characters as ^I\n"
" -u (ignored)\n"
" -v, --show-nonprinting use ^ and M- notation, except for LFD and TAB\n"
+" -p, --show-locale-chars don't use ^ and M- notation for characters\n"
+" that are printable in the current locale\n"
" --help display this help and exit\n"
" --version output version information and exit\n"
"\n"
@@ -59,6 +59,8 @@
" -T, --show-tabs gib TAB-Zeichen als ^I aus\n"
" -u (ignoriert)\n"
" -v, --show-nonprinting benutze ^ und M- Notation, außer für LFD und TAB\n"
+" -p, --show-locale-chars benutze keine ^ und M- Notation für Zeichen\n"
+" die in der eingestellten Sprache druckbar sind.\n"
" --help gib diese Hilfe aus und beende das Programm\n"
" --version gib Versionsinformation aus und beende das "
"Programm\n"
diff -Naur textutils-2.0/src/cat.c textutils-2.0-isprint/src/cat.c
--- textutils-2.0/src/cat.c Tue May 18 16:12:03 1999
+++ textutils-2.0-isprint/src/cat.c Sun Apr 21 14:54:44 2002
@@ -102,6 +102,8 @@
-T, --show-tabs display TAB characters as ^I\n\
-u (ignored)\n\
-v, --show-nonprinting use ^ and M- notation, except for LFD and TAB\n\
+ -p, --show-locale-chars don't use ^ and M- notation for characters\n\
+ that are printable in the current locale\n\
--help display this help and exit\n\
--version output version information and exit\n\
\n\
@@ -199,6 +201,7 @@
/* Variables that have values according to the specified options. */
int quote,
+ int printable,
int output_tabs,
int numbers,
int numbers_at_empty_lines,
@@ -395,35 +398,33 @@
{
for (;;)
{
- if (ch >= 32)
+ if ((!printable && ch >= 32 && ch < 127) ||
+ (printable && isprint(ch)))
+ *bpout++ = ch;
+ else if (ch == 127)
{
- if (ch < 127)
- *bpout++ = ch;
- else if (ch == 127)
- {
- *bpout++ = '^';
- *bpout++ = '?';
- }
- else
+ *bpout++ = '^';
+ *bpout++ = '?';
+ }
+ else if (ch > 127)
+ {
+ *bpout++ = 'M';
+ *bpout++ = '-';
+ if (ch >= 128 + 32)
{
- *bpout++ = 'M';
- *bpout++ = '-';
- if (ch >= 128 + 32)
- {
- if (ch < 128 + 127)
- *bpout++ = ch - 128;
- else
- {
- *bpout++ = '^';
- *bpout++ = '?';
- }
- }
+ if (ch < 128 + 127)
+ *bpout++ = ch - 128;
else
{
*bpout++ = '^';
- *bpout++ = ch - 128 + 64;
+ *bpout++ = '?';
}
}
+ else
+ {
+ *bpout++ = '^';
+ *bpout++ = ch - 128 + 64;
+ }
}
else if (ch == '\t' && output_tabs)
*bpout++ = '\t';
@@ -437,7 +438,7 @@
*bpout++ = '^';
*bpout++ = ch + 64;
}
-
+
ch = *bpin++;
}
}
@@ -505,6 +506,7 @@
int squeeze_empty_lines = 0;
int mark_line_ends = 0;
int quote = 0;
+ int printable = 0;
int output_tabs = 1;
#if O_BINARY
int binary_files = 0;
@@ -521,6 +523,7 @@
{"number", no_argument, NULL, 'n'},
{"squeeze-blank", no_argument, NULL, 's'},
{"show-nonprinting", no_argument, NULL, 'v'},
+ {"show-locale-chars", no_argument, NULL, 'p'},
{"show-ends", no_argument, NULL, 'E'},
{"show-tabs", no_argument, NULL, 'T'},
{"show-all", no_argument, NULL, 'A'},
@@ -541,9 +544,9 @@
while ((c = getopt_long (argc, argv,
#if O_BINARY
- "benstuvABET"
+ "benpstuvABET"
#else
- "benstuvAET"
+ "benpstuvAET"
#endif
, long_options, NULL)) != -1)
{
@@ -569,6 +572,11 @@
numbers = 1;
break;
+ case 'p':
+ ++options;
+ printable = 1;
+ break;
+
case 's':
++options;
squeeze_empty_lines = 1;
@@ -796,7 +804,7 @@
outbuf = (unsigned char *) xmalloc (outsize - 1 + insize * 4 + 13);
- cat (inbuf, insize, outbuf, outsize, quote,
+ cat (inbuf, insize, outbuf, outsize, quote, printable,
output_tabs, numbers, numbers_at_empty_lines, mark_line_ends,
squeeze_empty_lines);
msg00784/pgp00000.pgp
Description: PGP signature
