From: Mischa POSLAWSKY <perl@shiar.org>
Date: Fri, 2 Dec 2022 20:41:32 +0000 (+0100)
Subject: count option providing improved uniq -c
X-Git-Tag: v1.10~14
X-Git-Url: http://git.shiar.nl/barcat.git/commitdiff_plain/6672fed2b85ccecb6c34aa019b1e87b8d31b8172

count option providing improved uniq -c
---

diff --git a/barcat b/barcat
index 0cfdb2d..3b73b67 100755
--- a/barcat
+++ b/barcat
@@ -26,6 +26,7 @@ GetOptions(\%opt,
 			$opt{anchor} = qr/$_/;
 		} or die $@ =~ s/(?:\ at\ \N+)?\Z/ for option $_[0]/r;
 	},
+	'count|c!',
 	'human-readable|H!',
 	'sexagesimal!',
 	'reformat!',
@@ -189,7 +190,7 @@ $opt{'value-format'} = $opt{sexagesimal} ? sub {
 $opt{'value-format'} ||= sub { sprintf '%.8g', $_[0] };
 
 
-my (@lines, @values, @order);
+my (@lines, @values, @order, %uniq);
 
 $SIG{$_} = \&show_stat for $opt{'signal-stat'} || ();
 $SIG{ALRM} = sub {
@@ -212,6 +213,14 @@ my $float = qr<[0-9]* [.]? [0-9]+ (?: e[+-]?[0-9]+ )?>; # positive numberish
 my $valmatch = qr< $opt{anchor} ( \h* -? $float |) >x;
 while (defined ($_ = $opt{input} ? shift @{ $opt{input} } : readline)) {
 	s/\r?\n\z//;
+	if ($opt{count}) {
+		my ($valnum) = m/(\S*)/;
+		$valnum //= '';
+		$uniq{$valnum}++ and next;
+		push @lines, "\n " . $_;
+		push @values, $valnum;
+		next;
+	}
 	s/\A\h*// unless $opt{unmodified};
 	my $valnum = s/$valmatch/\n/ && $1;
 	push @values, $valnum;
@@ -247,6 +256,11 @@ state $nr = $opt{hidemin} ? $opt{hidemin}->($#lines) : 0;
 
 my $limit = $opt{hidemax} ? $opt{hidemax}->($#lines, $nr) : $#lines;
 
+if ($opt{count}) {
+	$_ = $uniq{$_} for @values;
+	@order = @values;
+}
+
 @order = sort { $b <=> $a } @order unless tied @order;
 my $maxval = $opt{maxval} // (
 	$opt{hidemax} ? max grep { length } @values[$nr .. $limit] :
@@ -438,6 +452,8 @@ Usage:                                               /\_/\
 Options:
   -a, --[no-]ascii         Restrict user interface to ASCII characters
   -C, --[no-]color         Force colored output of values and bar markers
+  -c, --count              Omit repetitions and count the number of
+                           occurrences
   -f, --field=([+]N|REGEXP)
                            Compare values after a given number of whitespace
                            separators
@@ -509,6 +525,12 @@ disabled otherwise such as when piped or redirected.
 Can also be disabled by setting B<-M>
 or the I<NO_COLOR> environment variable.
 
+=item B<-c>, B<--count>
+
+Omit repetitions and count the number of occurrences.
+Similar to piping input to C<sort | uniq -c>
+but keeping the order of first appearances.
+
 =item B<-f>, B<--field>=([B<+>]I<number> | I<regexp>)
 
 Compare values after a given number of whitespace separators,
@@ -742,16 +764,16 @@ Monitor network latency from prefixed results:
 
     ping google.com | barcat -f'time=\K' -t
 
-Commonly used after counting, for example users on the current server:
-
-    users | tr ' ' '\n' | sort | uniq -c | barcat
-
-Letter frequencies in text files:
+Commonly used after counting, eg letter frequencies in text files:
 
     cat /usr/share/games/fortunes/*.u8 |
     perl -CS -nE 'say for grep length, split /\PL*/, uc' |
     sort | uniq -c | barcat
 
+Users on the current server while preserving order:
+
+    users | tr ' ' '\n' | barcat -c
+
 Number of HTTP requests per day:
 
     cat httpd/access.log | cut -d\  -f4 | cut -d: -f1 | uniq -c | barcat
diff --git a/t/input/duplicates.txt b/t/input/duplicates.txt
new file mode 100644
index 0000000..124b263
--- /dev/null
+++ b/t/input/duplicates.txt
@@ -0,0 +1,20 @@
+thrice
+twice
+thrice
+once
+twice
+most
+thrice
+most
+most
+most
+most
+most
+most
+
+most
+ indented
+different
+  different
+most
+most
diff --git a/t/t0002-usage.out b/t/t0002-usage.out
index 55ac83f..a9ff9d7 100644
--- a/t/t0002-usage.out
+++ b/t/t0002-usage.out
@@ -1,2 +1,2 @@
 barcat -h |wc -l
-36
+38
diff --git a/t/t1662-uniq_words.out b/t/t1662-uniq_words.out
new file mode 100644
index 0000000..737a885
--- /dev/null
+++ b/t/t1662-uniq_words.out
@@ -0,0 +1,7 @@
+barcat --count input/duplicates.txt
+ 3 thrice    ----<+->
+ 2 twice     ----<
+ 1 once      ---
+10 most      ----<+->=------------------
+ 3           ----<+->
+ 1 different ---