mirror of
git://git.sv.gnu.org/coreutils.git
synced 2026-02-20 06:12:14 +02:00
md5sum, sha*sum: add --tag to output a format indicating the algorithm
The format used is the BSD traditional format which looks like: MD5 (/dev/null) = d41d8cd98f00b204e9800998ecf8427e * NEWS: Add new feature info. * doc/coreutils.texi (md5sum invocation): Add detailed information about the new --tag option. * src/md5sum.c: Add the new --tag option for BSD-style output. (bsd_split_3): Add ESCAPED_FILENAME parameter. (print_filename): New function refactored from main(). (filename_unescape): New function refactored from split_3(). * tests/misc/md5sum-bsd: Add tests for the new feature.
This commit is contained in:
committed by
Pádraig Brady
parent
dd22da8e95
commit
c9f4c32322
6
NEWS
6
NEWS
@@ -2,6 +2,12 @@ GNU coreutils NEWS -*- outline -*-
|
||||
|
||||
* Noteworthy changes in release ?.? (????-??-??) [?]
|
||||
|
||||
** New features
|
||||
|
||||
md5sum now accepts the --tag option to print BSD-style output with GNU
|
||||
file name escaping. This also affects sha1sum, sha224sum, sha256sum,
|
||||
sha384sum and sha512sum.
|
||||
|
||||
** Bug fixes
|
||||
|
||||
du no longer emits a "disk-corrupted"-style diagnostic when it detects
|
||||
|
||||
@@ -3705,6 +3705,17 @@ If all listed files are readable and are consistent with the associated
|
||||
MD5 checksums, exit successfully. Otherwise exit with a status code
|
||||
indicating there was a failure.
|
||||
|
||||
@item --tag
|
||||
@opindex --tag
|
||||
@cindex BSD output
|
||||
Output BSD style checksums, which indicate the checksum algorithm used.
|
||||
As a @acronym{GNU} extension, file names with problematic characters
|
||||
are escaped as described above, with the same escaping indicator of @samp{\}
|
||||
at the start of the line, being used.
|
||||
The @option{--tag} option implies binary mode, and is disallowed with
|
||||
@option{--text} mode as supporting that would unnecessarily complicate
|
||||
the output format, while providing little benefit.
|
||||
|
||||
@item -t
|
||||
@itemx --text
|
||||
@opindex -t
|
||||
@@ -3715,7 +3726,7 @@ outputting a @samp{ } flag. This is the inverse of @option{--binary}.
|
||||
This option is the default on systems like @acronym{GNU} that do not
|
||||
distinguish between binary and text files. On other systems, it is
|
||||
the default for reading standard input when standard input is a
|
||||
terminal.
|
||||
terminal. This mode is never defaulted to if @option{--tag} is used.
|
||||
|
||||
@item -w
|
||||
@itemx --warn
|
||||
|
||||
216
src/md5sum.c
216
src/md5sum.c
@@ -135,7 +135,8 @@ enum
|
||||
{
|
||||
STATUS_OPTION = CHAR_MAX + 1,
|
||||
QUIET_OPTION,
|
||||
STRICT_OPTION
|
||||
STRICT_OPTION,
|
||||
TAG_OPTION
|
||||
};
|
||||
|
||||
static struct option const long_options[] =
|
||||
@@ -147,6 +148,7 @@ static struct option const long_options[] =
|
||||
{ "text", no_argument, NULL, 't' },
|
||||
{ "warn", no_argument, NULL, 'w' },
|
||||
{ "strict", no_argument, NULL, STRICT_OPTION },
|
||||
{ "tag", no_argument, NULL, TAG_OPTION },
|
||||
{ GETOPT_HELP_OPTION_DECL },
|
||||
{ GETOPT_VERSION_OPTION_DECL },
|
||||
{ NULL, 0, NULL, 0 }
|
||||
@@ -179,6 +181,9 @@ With no FILE, or when FILE is -, read standard input.\n\
|
||||
printf (_("\
|
||||
-c, --check read %s sums from the FILEs and check them\n"),
|
||||
DIGEST_TYPE_STRING);
|
||||
fputs (_("\
|
||||
--tag create a BSD-style checksum\n\
|
||||
"), stdout);
|
||||
if (O_BINARY)
|
||||
fputs (_("\
|
||||
-t, --text read in text mode (default if reading tty stdin)\n\
|
||||
@@ -215,23 +220,73 @@ space for text), and name for each FILE.\n"),
|
||||
|
||||
#define ISWHITE(c) ((c) == ' ' || (c) == '\t')
|
||||
|
||||
/* Given a file name, S of length S_LEN, that is not NUL-terminated,
|
||||
modify it in place, performing the equivalent of this sed substitution:
|
||||
's/\\n/\n/g;s/\\\\/\\/g' i.e., replacing each "\\n" string with a newline
|
||||
and each "\\\\" with a single backslash, NUL-terminate it and return S.
|
||||
If S is not a valid escaped file name, i.e., if it ends with an odd number
|
||||
of backslashes or if it contains a backslash followed by anything other
|
||||
than "n" or another backslash, return NULL. */
|
||||
|
||||
static char *
|
||||
filename_unescape (char *s, size_t s_len)
|
||||
{
|
||||
char *dst = s;
|
||||
|
||||
for (size_t i = 0; i < s_len; i++)
|
||||
{
|
||||
switch (s[i])
|
||||
{
|
||||
case '\\':
|
||||
if (i == s_len - 1)
|
||||
{
|
||||
/* File name ends with an unescaped backslash: invalid. */
|
||||
return NULL;
|
||||
}
|
||||
++i;
|
||||
switch (s[i])
|
||||
{
|
||||
case 'n':
|
||||
*dst++ = '\n';
|
||||
break;
|
||||
case '\\':
|
||||
*dst++ = '\\';
|
||||
break;
|
||||
default:
|
||||
/* Only '\' or 'n' may follow a backslash. */
|
||||
return NULL;
|
||||
}
|
||||
break;
|
||||
|
||||
case '\0':
|
||||
/* The file name may not contain a NUL. */
|
||||
return NULL;
|
||||
|
||||
default:
|
||||
*dst++ = s[i];
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (dst < s + s_len)
|
||||
*dst = '\0';
|
||||
|
||||
return s;
|
||||
}
|
||||
|
||||
/* Split the checksum string S (of length S_LEN) from a BSD 'md5' or
|
||||
'sha1' command into two parts: a hexadecimal digest, and the file
|
||||
name. S is modified. Return true if successful. */
|
||||
|
||||
static bool
|
||||
bsd_split_3 (char *s, size_t s_len, unsigned char **hex_digest,
|
||||
char **file_name)
|
||||
char **file_name, bool escaped_filename)
|
||||
{
|
||||
size_t i;
|
||||
|
||||
if (s_len == 0)
|
||||
return false;
|
||||
|
||||
*file_name = s;
|
||||
|
||||
/* Find end of filename. The BSD 'md5' and 'sha1' commands do not escape
|
||||
filenames, so search backwards for the last ')'. */
|
||||
/* Find end of filename. */
|
||||
i = s_len - 1;
|
||||
while (i && s[i] != ')')
|
||||
i--;
|
||||
@@ -239,6 +294,11 @@ bsd_split_3 (char *s, size_t s_len, unsigned char **hex_digest,
|
||||
if (s[i] != ')')
|
||||
return false;
|
||||
|
||||
*file_name = s;
|
||||
|
||||
if (escaped_filename && filename_unescape (s, i) == NULL)
|
||||
return false;
|
||||
|
||||
s[i++] = '\0';
|
||||
|
||||
while (ISWHITE (s[i]))
|
||||
@@ -271,7 +331,14 @@ split_3 (char *s, size_t s_len,
|
||||
while (ISWHITE (s[i]))
|
||||
++i;
|
||||
|
||||
if (s[i] == '\\')
|
||||
{
|
||||
++i;
|
||||
escaped_filename = true;
|
||||
}
|
||||
|
||||
/* Check for BSD-style checksum line. */
|
||||
|
||||
algo_name_len = strlen (DIGEST_TYPE_STRING);
|
||||
if (STREQ_LEN (s + i, DIGEST_TYPE_STRING, algo_name_len))
|
||||
{
|
||||
@@ -282,7 +349,7 @@ split_3 (char *s, size_t s_len,
|
||||
*binary = 0;
|
||||
return bsd_split_3 (s + i + algo_name_len + 1,
|
||||
s_len - (i + algo_name_len + 1),
|
||||
hex_digest, file_name);
|
||||
hex_digest, file_name, escaped_filename);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -293,11 +360,6 @@ split_3 (char *s, size_t s_len,
|
||||
if (s_len - i < min_digest_line_length + (s[i] == '\\'))
|
||||
return false;
|
||||
|
||||
if (s[i] == '\\')
|
||||
{
|
||||
++i;
|
||||
escaped_filename = true;
|
||||
}
|
||||
*hex_digest = (unsigned char *) &s[i];
|
||||
|
||||
/* The first field has to be the n-character hexadecimal
|
||||
@@ -333,49 +395,8 @@ split_3 (char *s, size_t s_len,
|
||||
*file_name = &s[i];
|
||||
|
||||
if (escaped_filename)
|
||||
{
|
||||
/* Translate each '\n' string in the file name to a NEWLINE,
|
||||
and each '\\' string to a backslash. */
|
||||
return filename_unescape (&s[i], s_len - i) != NULL;
|
||||
|
||||
char *dst = &s[i];
|
||||
|
||||
while (i < s_len)
|
||||
{
|
||||
switch (s[i])
|
||||
{
|
||||
case '\\':
|
||||
if (i == s_len - 1)
|
||||
{
|
||||
/* A valid line does not end with a backslash. */
|
||||
return false;
|
||||
}
|
||||
++i;
|
||||
switch (s[i++])
|
||||
{
|
||||
case 'n':
|
||||
*dst++ = '\n';
|
||||
break;
|
||||
case '\\':
|
||||
*dst++ = '\\';
|
||||
break;
|
||||
default:
|
||||
/* Only '\' or 'n' may follow a backslash. */
|
||||
return false;
|
||||
}
|
||||
break;
|
||||
|
||||
case '\0':
|
||||
/* The file name may not contain a NUL. */
|
||||
return false;
|
||||
break;
|
||||
|
||||
default:
|
||||
*dst++ = s[i++];
|
||||
break;
|
||||
}
|
||||
}
|
||||
*dst = '\0';
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -636,6 +657,31 @@ digest_check (const char *checkfile_name)
|
||||
&& (!strict || n_improperly_formatted_lines == 0));
|
||||
}
|
||||
|
||||
static void
|
||||
print_filename (char const *file)
|
||||
{
|
||||
/* Translate each NEWLINE byte to the string, "\\n",
|
||||
and each backslash to "\\\\". */
|
||||
while (*file)
|
||||
{
|
||||
switch (*file)
|
||||
{
|
||||
case '\n':
|
||||
fputs ("\\n", stdout);
|
||||
break;
|
||||
|
||||
case '\\':
|
||||
fputs ("\\\\", stdout);
|
||||
break;
|
||||
|
||||
default:
|
||||
putchar (*file);
|
||||
break;
|
||||
}
|
||||
file++;
|
||||
}
|
||||
}
|
||||
|
||||
int
|
||||
main (int argc, char **argv)
|
||||
{
|
||||
@@ -646,6 +692,7 @@ main (int argc, char **argv)
|
||||
int opt;
|
||||
bool ok = true;
|
||||
int binary = -1;
|
||||
bool prefix_tag = false;
|
||||
|
||||
/* Setting values of global variables. */
|
||||
initialize_main (&argc, &argv);
|
||||
@@ -690,6 +737,10 @@ main (int argc, char **argv)
|
||||
case STRICT_OPTION:
|
||||
strict = true;
|
||||
break;
|
||||
case TAG_OPTION:
|
||||
prefix_tag = true;
|
||||
binary = 1;
|
||||
break;
|
||||
case_GETOPT_HELP_CHAR;
|
||||
case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);
|
||||
default:
|
||||
@@ -699,6 +750,24 @@ main (int argc, char **argv)
|
||||
min_digest_line_length = MIN_DIGEST_LINE_LENGTH;
|
||||
digest_hex_bytes = DIGEST_HEX_BYTES;
|
||||
|
||||
if (prefix_tag && !binary)
|
||||
{
|
||||
/* This could be supported in a backwards compatible way
|
||||
by prefixing the output line with a space in text mode.
|
||||
However that's invasive enough that it was agreed to
|
||||
not support this mode with --tag, as --text use cases
|
||||
are adequately supported by the default output format. */
|
||||
error (0, 0, _("--tag does not support --text mode"));
|
||||
usage (EXIT_FAILURE);
|
||||
}
|
||||
|
||||
if (prefix_tag && do_check)
|
||||
{
|
||||
error (0, 0, _("the --tag option is meaningless when "
|
||||
"verifying checksums"));
|
||||
usage (EXIT_FAILURE);
|
||||
}
|
||||
|
||||
if (0 <= binary && do_check)
|
||||
{
|
||||
error (0, 0, _("the --binary and --text options are meaningless when "
|
||||
@@ -754,41 +823,36 @@ main (int argc, char **argv)
|
||||
ok = false;
|
||||
else
|
||||
{
|
||||
if (prefix_tag)
|
||||
{
|
||||
if (strchr (file, '\n') || strchr (file, '\\'))
|
||||
putchar ('\\');
|
||||
|
||||
fputs (DIGEST_TYPE_STRING, stdout);
|
||||
fputs (" (", stdout);
|
||||
print_filename (file);
|
||||
fputs (") = ", stdout);
|
||||
}
|
||||
|
||||
size_t i;
|
||||
|
||||
/* Output a leading backslash if the file name contains
|
||||
a newline or backslash. */
|
||||
if (strchr (file, '\n') || strchr (file, '\\'))
|
||||
if (!prefix_tag && (strchr (file, '\n') || strchr (file, '\\')))
|
||||
putchar ('\\');
|
||||
|
||||
for (i = 0; i < (digest_hex_bytes / 2); ++i)
|
||||
printf ("%02x", bin_buffer[i]);
|
||||
|
||||
putchar (' ');
|
||||
if (file_is_binary)
|
||||
putchar ('*');
|
||||
else
|
||||
putchar (' ');
|
||||
|
||||
/* Translate each NEWLINE byte to the string, "\\n",
|
||||
and each backslash to "\\\\". */
|
||||
for (i = 0; i < strlen (file); ++i)
|
||||
if (!prefix_tag)
|
||||
{
|
||||
switch (file[i])
|
||||
{
|
||||
case '\n':
|
||||
fputs ("\\n", stdout);
|
||||
break;
|
||||
putchar (' ');
|
||||
|
||||
case '\\':
|
||||
fputs ("\\\\", stdout);
|
||||
break;
|
||||
putchar (file_is_binary ? '*' : ' ');
|
||||
|
||||
default:
|
||||
putchar (file[i]);
|
||||
break;
|
||||
}
|
||||
print_filename (file);
|
||||
}
|
||||
|
||||
putchar ('\n');
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
#!/bin/sh
|
||||
# make sure 'md5sum -c' works for alternate BSD format (md5 -r)
|
||||
# 'md5sum' tests for generation and checking of
|
||||
# BSD traditional and alternate formats (md5 [-r])
|
||||
|
||||
# Copyright (C) 2011-2012 Free Software Foundation, Inc.
|
||||
|
||||
@@ -19,6 +20,9 @@
|
||||
. "${srcdir=.}/init.sh"; path_prepend_ ../src
|
||||
print_ver_ md5sum
|
||||
|
||||
## BSD alternate format tests ##
|
||||
|
||||
# Ensure we can --check BSD alternate format.
|
||||
# Note we start this list with a name
|
||||
# that's unambiguous in BSD format.
|
||||
# I.E. one not starting with ' ' or '*'
|
||||
@@ -38,4 +42,47 @@ md5sum --strict -c check.md5 || fail=1
|
||||
# an option to avoid the ambiguity.
|
||||
tail -n+2 check.md5 | md5sum --strict -c && fail=1
|
||||
|
||||
|
||||
## BSD traditional format tests (--tag option) ##
|
||||
|
||||
# Ensure --tag and --check are mutually exclusive
|
||||
md5sum --tag --check /dev/null && fail=1
|
||||
|
||||
# Ensure --tag and --text are mutually exclusive
|
||||
# We don't support --text with BSD tradition format,
|
||||
# as that would complicate the output format,
|
||||
# while providing little benefit over --text processing
|
||||
# available with the default md5sum output format.
|
||||
md5sum --tag --text /dev/null && fail=1
|
||||
|
||||
# Ensure we can --check BSD traditional format we produce
|
||||
rm check.md5
|
||||
for i in 'a' ' b' '*c' 'dd' ' '; do
|
||||
echo "$i" > "$i"
|
||||
md5sum --tag "$i" >> check.md5
|
||||
done
|
||||
md5sum --strict -c check.md5 || fail=1
|
||||
|
||||
# Ensure we can --check BSD traditional format we produce
|
||||
# with the GNU extension of escaped newlines
|
||||
nl='
|
||||
'
|
||||
tab=' '
|
||||
rm check.md5
|
||||
for i in 'a\b' 'a\' "a${nl}b" "a${tab}b"; do
|
||||
:> "$i"
|
||||
md5sum --tag "$i" >> check.md5
|
||||
done
|
||||
md5sum --strict -c check.md5 || fail=1
|
||||
|
||||
# Ensure BSD traditional format with GNU extension escapes
|
||||
# is in the expected format
|
||||
ex_file='test
|
||||
\\file'
|
||||
ex_output='\MD5 (test\n\\\\file) = d41d8cd98f00b204e9800998ecf8427e'
|
||||
touch "$ex_file"
|
||||
printf "%s\n" "$ex_output" > exp
|
||||
md5sum --tag "$ex_file" > out
|
||||
compare exp out || fail=1
|
||||
|
||||
Exit $fail
|
||||
|
||||
Reference in New Issue
Block a user