From 3f93db90876689f3b3db9fe3233046feb2501c56 Mon Sep 17 00:00:00 2001
From: Michael Mikonos <127171689+mknos@users.noreply.github.com>
Date: Tue, 13 Feb 2024 01:23:14 +0800
Subject: [PATCH] wc: unexpected counts for -w flag (#457)

* As noted earlier, word count output in wc did not match GNU version
* A word is one or more non-space characters, surrounded by whitespace (including newline)
* The old code seemed to count the spaces in between words, but I couldn't follow it
* To test this I built the OpenBSD version of wc on my linux system, then compared total word count for a set of files between OpenBSD, GNU and perl

%$wc_obsd -w s*
wc: s: Is a directory
       0 s
     524 seq
     330 shar
     319 shar2
     225 sleep
    4098 sort
    1789 spell
     895 split
wc: sssss: Is a directory
       0 sssss
     444 strings
    1116 sum
    9740 total
%perl wc -w s*
wc: 's' is a directory
       524 seq
       330 shar
       319 shar2
       225 sleep
      4098 sort
      1789 spell
       895 split
wc: 'sssss' is a directory
       444 strings
      1116 sum
      9740 total
%/usr/bin/wc -w s*
/usr/bin/wc: s: Is a directory
      0 s
    524 seq
    330 shar
    319 shar2
    225 sleep
   4098 sort
   1789 spell
    895 split
/usr/bin/wc: sssss: Is a directory
      0 sssss
    444 strings
   1116 sum
   9740 total
---
 bin/wc | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/bin/wc b/bin/wc
index fd9114f3..32934c55 100755
--- a/bin/wc
+++ b/bin/wc
@@ -169,8 +169,9 @@ sub wc_fh {
             }
         }
         if ($opt{'w'}) {
-            @words = split(/\w+/,$_);
-            $words += $#words;
+            s/\A\s+//;
+            @words = split /\s+/;
+            $words += scalar @words;
         }
         if ($opt{'m'}) {
             @chars = m/$encoding/gox;
@@ -181,7 +182,6 @@ sub wc_fh {
         }
     }
     if ($paras > 1) { $paras--; }
-    if ($words > 1) { $words--; }
     $total_paras += $paras;
     $total_lines += $lines; $total_words += $words;
     $total_chars += $chars; $total_bytes += $bytes;