2grep: -F implemented. Passes test.
This commit is contained in:
Ole Tange
parent
157e498d6b
commit
dbf36dfd17
|
|
@ -8,119 +8,136 @@
|
|||
|
||||
=head1 SYNOPSIS
|
||||
|
||||
B<2search> [-nrfHB] file string [string...]
|
||||
B<2search> [-nrfHB] inputfile string [string...]
|
||||
|
||||
B<2search> --grep [-nrfH] file string [string...]
|
||||
B<2search> --grep [-nrfH] inputfile string [string...]
|
||||
|
||||
B<2grep> [-nrfH] file string [string...]
|
||||
B<2grep> [-nrfH] inputfile string [string...]
|
||||
|
||||
... | B<2search> [-nrfHB] file
|
||||
... | B<2search> [-nrfHB] inputfile
|
||||
|
||||
... | B<2search> --grep [-nrfH] file
|
||||
... | B<2search> --grep [-nrfH] inputfile
|
||||
|
||||
... | B<2grep> [-nrfH] file
|
||||
... | B<2grep> [-nrfH] inputfile
|
||||
|
||||
=head1 DESCRIPTION
|
||||
|
||||
B<2search> searches a sorted file for a string. It outputs the
|
||||
following line or the byte position of this line, which is where the
|
||||
string would have been if it had been in the sorted file.
|
||||
B<2search> searches a sorted file for lines starting with a string. It
|
||||
outputs the following line or the byte position of this line, which is
|
||||
where the string would have been if it had been in the sorted file.
|
||||
|
||||
B<2grep> output all lines starting with a given string. The file must
|
||||
be sorted.
|
||||
|
||||
By using B<-k> the same way as in B<sort> you can instead search for
|
||||
strings in columns, if the file is sorted using the B<-k> syntax.
|
||||
|
||||
|
||||
=over 9
|
||||
|
||||
=item B<--ignore-leading-blanks>
|
||||
|
||||
=item B<-b>
|
||||
|
||||
ignore leading blanks
|
||||
Ignore leading blanks. Used if I<inputfile> is sorted with B<sort
|
||||
--ignore-leading-blanks>.
|
||||
|
||||
|
||||
=item B<--byte-offset>
|
||||
|
||||
=item B<-B>
|
||||
|
||||
print byte position where string would have been
|
||||
Print byte position where string would have been.
|
||||
|
||||
|
||||
=item B<--dictionary-order> (not implemented)
|
||||
|
||||
=item B<-d>
|
||||
|
||||
consider only blanks and alphanumeric characters
|
||||
Consider only blanks and alphanumeric characters. Used if I<inputfile>
|
||||
is sorted with B<sort --dictionary-order>.
|
||||
|
||||
|
||||
=item B<--debug>
|
||||
|
||||
=item B<-D>
|
||||
|
||||
annotate the part of the line used to sort to stderr
|
||||
Show debugging information.
|
||||
|
||||
|
||||
=item B<--ignore-case>
|
||||
|
||||
=item B<-f>
|
||||
|
||||
fold lower case to upper case characters
|
||||
Fold lower case to upper case characters. Used if I<inputfile> is
|
||||
sorted with B<sort --ignore-case>.
|
||||
|
||||
|
||||
=item B<-F>
|
||||
|
||||
Fixed string. The search string 'foo' will not match 'foobar'.
|
||||
|
||||
|
||||
=item B<--file> I<file>
|
||||
|
||||
=item B<-F> I<file>
|
||||
|
||||
search for all lines in I<file>
|
||||
Search for all lines in I<file>.
|
||||
|
||||
|
||||
=item B<--general-numeric-sort> (not implemented)
|
||||
|
||||
=item B<-g>
|
||||
|
||||
compare according to general numerical value
|
||||
Compare according to general numerical value. Used if I<inputfile> is
|
||||
sorted with B<sort --general-numeric-sort>.
|
||||
|
||||
|
||||
=item B<--header>
|
||||
|
||||
=item B<-H>
|
||||
|
||||
treat the first line in I<file> as a header
|
||||
Treat the first line in I<file> as a header. Ignore it when searching
|
||||
and print it once in the output.
|
||||
|
||||
|
||||
=item B<--ignore-nonprinting> (not implemented)
|
||||
|
||||
=item B<-i>
|
||||
|
||||
consider only printable characters
|
||||
Consider only printable characters. Used if I<inputfile> is
|
||||
sorted with B<sort --ignore-nonprinting>.
|
||||
|
||||
|
||||
=item B<--month-sort>
|
||||
|
||||
=item B<-M>
|
||||
|
||||
compare (unknown) < 'JAN' < ... < 'DEC'
|
||||
Compare (unknown) < 'JAN' < ... < 'DEC'. Used if I<inputfile> is
|
||||
sorted with B<sort --month-sort>.
|
||||
|
||||
|
||||
=item B<--human-numeric-sort>
|
||||
|
||||
=item B<-h>
|
||||
|
||||
compare human readable numbers (e.g., 2K 1G)
|
||||
Compare human readable numbers (e.g., 2K 1G). Used if I<inputfile> is
|
||||
sorted with B<sort --human-numeric-sort>.
|
||||
|
||||
|
||||
=item B<--key=KEYDEF> (not implemented)
|
||||
=item B<--key=KEYDEF>
|
||||
|
||||
=item B<-k>
|
||||
|
||||
sort via a key; KEYDEF gives location and type
|
||||
Sort via a key; KEYDEF gives location and type. Used if I<inputfile>
|
||||
is sorted with B<sort --key=KEYDEF>.
|
||||
|
||||
|
||||
=item B<--numeric-sort>
|
||||
|
||||
=item B<-n>
|
||||
|
||||
compare according to string numerical value. If numerical values are
|
||||
the same: compare as strings.
|
||||
Compare according to string numerical value. If numerical values are
|
||||
the same: compare as strings. Used if I<inputfile> is sorted with
|
||||
B<sort --numeric-sort>.
|
||||
|
||||
|
||||
=item B<--numascii>
|
||||
|
|
@ -140,19 +157,20 @@ This is simiar to B<--version-sort>, but without the exceptions.
|
|||
|
||||
=item B<-R>
|
||||
|
||||
sort by random hash of keys
|
||||
Sort by random hash of keys.
|
||||
|
||||
|
||||
=item B<--reverse>
|
||||
|
||||
=item B<-r>
|
||||
|
||||
reverse the result of comparisons
|
||||
Reverse the result of comparisons. Used if I<inputfile> is sorted with
|
||||
B<sort --reverse>.
|
||||
|
||||
|
||||
=item B<--sort=WORD> (not implemented)
|
||||
|
||||
sort according to WORD: general-numeric B<-g>, human-numeric B<-h>, month
|
||||
Sort according to WORD: general-numeric B<-g>, human-numeric B<-h>, month
|
||||
B<-M>, numeric B<-n>, random B<-R>, version B<-V>
|
||||
|
||||
|
||||
|
|
@ -160,14 +178,14 @@ B<-M>, numeric B<-n>, random B<-R>, version B<-V>
|
|||
|
||||
=item B<--field-separator=SEP>
|
||||
|
||||
use I<SEP> instead of blanks (\s+). I<SEP> is a regexp.
|
||||
Use I<SEP> instead of blanks (\s+). I<SEP> is a regexp.
|
||||
|
||||
|
||||
=item B<-z>
|
||||
|
||||
=item B<--zero-terminated>
|
||||
|
||||
end lines with 0 byte, not newline
|
||||
End lines with 0 (NUL) byte, not newline.
|
||||
|
||||
|
||||
=back
|
||||
|
|
@ -262,7 +280,7 @@ To solve this sort the input with B<LC_ALL=C sort ...>.
|
|||
|
||||
=head1 REPORTING BUGS
|
||||
|
||||
B<2search> is part of tangetools. Report bugs on
|
||||
B<2search> and B<2grep> are part of tangetools. Report bugs on
|
||||
https://gitlab.com/ole.tange/tangetools/-/issues
|
||||
|
||||
|
||||
|
|
@ -401,7 +419,8 @@ GetOptions(
|
|||
"f|ignore-case" => \$opt::ignore_case,
|
||||
"g|general-numeric-sort" => \$opt::general_numeric_sort,
|
||||
"G|grep" => \$opt::grep,
|
||||
"F|file=s" => \$opt::file,
|
||||
"F|fixed-strings" => \$opt::fixed_strings,
|
||||
"file=s" => \$opt::file,
|
||||
"i|ignore-nonprinting" => \$opt::ignore_nonprinting,
|
||||
"M|month-sort" => \$opt::month_sort,
|
||||
"h|human-numeric-sort" => \$opt::human_numeric_sort,
|
||||
|
|
@ -523,9 +542,11 @@ sub bgrep {
|
|||
exit 1;
|
||||
}
|
||||
seek($fh,$startpos,0) or die;
|
||||
# Allow for partial matches in grep (4 mathes 40, A matches Aaa)
|
||||
for my $keydef (@Global::keydefs) {
|
||||
$keydef->{'partial_match'} = 1;
|
||||
if(not $opt::fixed_strings) {
|
||||
# Allow for partial matches in grep (4 mathes 40, A matches Aaa)
|
||||
for my $keydef (@Global::keydefs) {
|
||||
$keydef->{'partial_match'} = 1;
|
||||
}
|
||||
}
|
||||
my $line;
|
||||
while($line = <$fh>
|
||||
|
|
|
|||
|
|
@ -8,119 +8,136 @@
|
|||
|
||||
=head1 SYNOPSIS
|
||||
|
||||
B<2search> [-nrfHB] file string [string...]
|
||||
B<2search> [-nrfHB] inputfile string [string...]
|
||||
|
||||
B<2search> --grep [-nrfH] file string [string...]
|
||||
B<2search> --grep [-nrfH] inputfile string [string...]
|
||||
|
||||
B<2grep> [-nrfH] file string [string...]
|
||||
B<2grep> [-nrfH] inputfile string [string...]
|
||||
|
||||
... | B<2search> [-nrfHB] file
|
||||
... | B<2search> [-nrfHB] inputfile
|
||||
|
||||
... | B<2search> --grep [-nrfH] file
|
||||
... | B<2search> --grep [-nrfH] inputfile
|
||||
|
||||
... | B<2grep> [-nrfH] file
|
||||
... | B<2grep> [-nrfH] inputfile
|
||||
|
||||
=head1 DESCRIPTION
|
||||
|
||||
B<2search> searches a sorted file for a string. It outputs the
|
||||
following line or the byte position of this line, which is where the
|
||||
string would have been if it had been in the sorted file.
|
||||
B<2search> searches a sorted file for lines starting with a string. It
|
||||
outputs the following line or the byte position of this line, which is
|
||||
where the string would have been if it had been in the sorted file.
|
||||
|
||||
B<2grep> output all lines starting with a given string. The file must
|
||||
be sorted.
|
||||
|
||||
By using B<-k> the same way as in B<sort> you can instead search for
|
||||
strings in columns, if the file is sorted using the B<-k> syntax.
|
||||
|
||||
|
||||
=over 9
|
||||
|
||||
=item B<--ignore-leading-blanks>
|
||||
|
||||
=item B<-b>
|
||||
|
||||
ignore leading blanks
|
||||
Ignore leading blanks. Used if I<inputfile> is sorted with B<sort
|
||||
--ignore-leading-blanks>.
|
||||
|
||||
|
||||
=item B<--byte-offset>
|
||||
|
||||
=item B<-B>
|
||||
|
||||
print byte position where string would have been
|
||||
Print byte position where string would have been.
|
||||
|
||||
|
||||
=item B<--dictionary-order> (not implemented)
|
||||
|
||||
=item B<-d>
|
||||
|
||||
consider only blanks and alphanumeric characters
|
||||
Consider only blanks and alphanumeric characters. Used if I<inputfile>
|
||||
is sorted with B<sort --dictionary-order>.
|
||||
|
||||
|
||||
=item B<--debug>
|
||||
|
||||
=item B<-D>
|
||||
|
||||
annotate the part of the line used to sort to stderr
|
||||
Show debugging information.
|
||||
|
||||
|
||||
=item B<--ignore-case>
|
||||
|
||||
=item B<-f>
|
||||
|
||||
fold lower case to upper case characters
|
||||
Fold lower case to upper case characters. Used if I<inputfile> is
|
||||
sorted with B<sort --ignore-case>.
|
||||
|
||||
|
||||
=item B<-F>
|
||||
|
||||
Fixed string. The search string 'foo' will not match 'foobar'.
|
||||
|
||||
|
||||
=item B<--file> I<file>
|
||||
|
||||
=item B<-F> I<file>
|
||||
|
||||
search for all lines in I<file>
|
||||
Search for all lines in I<file>.
|
||||
|
||||
|
||||
=item B<--general-numeric-sort> (not implemented)
|
||||
|
||||
=item B<-g>
|
||||
|
||||
compare according to general numerical value
|
||||
Compare according to general numerical value. Used if I<inputfile> is
|
||||
sorted with B<sort --general-numeric-sort>.
|
||||
|
||||
|
||||
=item B<--header>
|
||||
|
||||
=item B<-H>
|
||||
|
||||
treat the first line in I<file> as a header
|
||||
Treat the first line in I<file> as a header. Ignore it when searching
|
||||
and print it once in the output.
|
||||
|
||||
|
||||
=item B<--ignore-nonprinting> (not implemented)
|
||||
|
||||
=item B<-i>
|
||||
|
||||
consider only printable characters
|
||||
Consider only printable characters. Used if I<inputfile> is
|
||||
sorted with B<sort --ignore-nonprinting>.
|
||||
|
||||
|
||||
=item B<--month-sort>
|
||||
|
||||
=item B<-M>
|
||||
|
||||
compare (unknown) < 'JAN' < ... < 'DEC'
|
||||
Compare (unknown) < 'JAN' < ... < 'DEC'. Used if I<inputfile> is
|
||||
sorted with B<sort --month-sort>.
|
||||
|
||||
|
||||
=item B<--human-numeric-sort>
|
||||
|
||||
=item B<-h>
|
||||
|
||||
compare human readable numbers (e.g., 2K 1G)
|
||||
Compare human readable numbers (e.g., 2K 1G). Used if I<inputfile> is
|
||||
sorted with B<sort --human-numeric-sort>.
|
||||
|
||||
|
||||
=item B<--key=KEYDEF> (not implemented)
|
||||
=item B<--key=KEYDEF>
|
||||
|
||||
=item B<-k>
|
||||
|
||||
sort via a key; KEYDEF gives location and type
|
||||
Sort via a key; KEYDEF gives location and type. Used if I<inputfile>
|
||||
is sorted with B<sort --key=KEYDEF>.
|
||||
|
||||
|
||||
=item B<--numeric-sort>
|
||||
|
||||
=item B<-n>
|
||||
|
||||
compare according to string numerical value. If numerical values are
|
||||
the same: compare as strings.
|
||||
Compare according to string numerical value. If numerical values are
|
||||
the same: compare as strings. Used if I<inputfile> is sorted with
|
||||
B<sort --numeric-sort>.
|
||||
|
||||
|
||||
=item B<--numascii>
|
||||
|
|
@ -140,19 +157,20 @@ This is simiar to B<--version-sort>, but without the exceptions.
|
|||
|
||||
=item B<-R>
|
||||
|
||||
sort by random hash of keys
|
||||
Sort by random hash of keys.
|
||||
|
||||
|
||||
=item B<--reverse>
|
||||
|
||||
=item B<-r>
|
||||
|
||||
reverse the result of comparisons
|
||||
Reverse the result of comparisons. Used if I<inputfile> is sorted with
|
||||
B<sort --reverse>.
|
||||
|
||||
|
||||
=item B<--sort=WORD> (not implemented)
|
||||
|
||||
sort according to WORD: general-numeric B<-g>, human-numeric B<-h>, month
|
||||
Sort according to WORD: general-numeric B<-g>, human-numeric B<-h>, month
|
||||
B<-M>, numeric B<-n>, random B<-R>, version B<-V>
|
||||
|
||||
|
||||
|
|
@ -160,14 +178,14 @@ B<-M>, numeric B<-n>, random B<-R>, version B<-V>
|
|||
|
||||
=item B<--field-separator=SEP>
|
||||
|
||||
use I<SEP> instead of blanks (\s+). I<SEP> is a regexp.
|
||||
Use I<SEP> instead of blanks (\s+). I<SEP> is a regexp.
|
||||
|
||||
|
||||
=item B<-z>
|
||||
|
||||
=item B<--zero-terminated>
|
||||
|
||||
end lines with 0 byte, not newline
|
||||
End lines with 0 (NUL) byte, not newline.
|
||||
|
||||
|
||||
=back
|
||||
|
|
@ -262,7 +280,7 @@ To solve this sort the input with B<LC_ALL=C sort ...>.
|
|||
|
||||
=head1 REPORTING BUGS
|
||||
|
||||
B<2search> is part of tangetools. Report bugs on
|
||||
B<2search> and B<2grep> are part of tangetools. Report bugs on
|
||||
https://gitlab.com/ole.tange/tangetools/-/issues
|
||||
|
||||
|
||||
|
|
@ -401,7 +419,8 @@ GetOptions(
|
|||
"f|ignore-case" => \$opt::ignore_case,
|
||||
"g|general-numeric-sort" => \$opt::general_numeric_sort,
|
||||
"G|grep" => \$opt::grep,
|
||||
"F|file=s" => \$opt::file,
|
||||
"F|fixed-strings" => \$opt::fixed_strings,
|
||||
"file=s" => \$opt::file,
|
||||
"i|ignore-nonprinting" => \$opt::ignore_nonprinting,
|
||||
"M|month-sort" => \$opt::month_sort,
|
||||
"h|human-numeric-sort" => \$opt::human_numeric_sort,
|
||||
|
|
@ -523,9 +542,11 @@ sub bgrep {
|
|||
exit 1;
|
||||
}
|
||||
seek($fh,$startpos,0) or die;
|
||||
# Allow for partial matches in grep (4 mathes 40, A matches Aaa)
|
||||
for my $keydef (@Global::keydefs) {
|
||||
$keydef->{'partial_match'} = 1;
|
||||
if(not $opt::fixed_strings) {
|
||||
# Allow for partial matches in grep (4 mathes 40, A matches Aaa)
|
||||
for my $keydef (@Global::keydefs) {
|
||||
$keydef->{'partial_match'} = 1;
|
||||
}
|
||||
}
|
||||
my $line;
|
||||
while($line = <$fh>
|
||||
|
|
|
|||
Loading…
Reference in a new issue