From 8ab096d2a4213d9676f9531474afda0c73a7c04a Mon Sep 17 00:00:00 2001
From: FRIGN <dev@frign.de>
Date: Sun, 1 Feb 2015 03:01:11 +0100
Subject: [PATCH] Finish up wc(1)

Use size_t for all counts, fix the manpage and refactor the code.
Here's yet another place where GNU coreutils fail:

sbase:
$ echo "GNU/Turd sucks" | wc -cm
    15

coreutils:
$ echo "GNU/Turd sucks" | wc -cm
     15      15

Take a bloody guess which behaviour is correct[0].

[0]: http://pubs.opengroup.org/onlinepubs/009604499/utilities/wc.html
---
 README |  2 +-
 wc.1   | 35 +++++++++++----------
 wc.c   | 97 ++++++++++++++++++++++++++++------------------------------
 3 files changed, 66 insertions(+), 68 deletions(-)

diff --git a/README b/README
index f465574..12ffd9c 100644
--- a/README
+++ b/README
@@ -82,7 +82,7 @@ The following tools are implemented ('*' == finished, '#' == UTF-8 support,
 =  sha1sum         non-posix                       none
 =  sha256sum       non-posix                       none
 =  sha512sum       non-posix                       none
-   wc              yes                             none
+#* wc              yes                             none
 =  xargs           no                              -I, -L, -p, -s, -t, -x
 =* yes             non-posix                       none
 
diff --git a/wc.1 b/wc.1
index 772d814..c18b210 100644
--- a/wc.1
+++ b/wc.1
@@ -1,4 +1,4 @@
-.Dd January 30, 2015
+.Dd February 1, 2015
 .Dt WC 1
 .Os sbase
 .Sh NAME
@@ -6,26 +6,27 @@
 .Nd word count
 .Sh SYNOPSIS
 .Nm
-.Op Fl clmw
+.Op Fl c | Fl m
+.Op Fl lw
 .Op Ar file ...
 .Sh DESCRIPTION
 .Nm
-prints the number of lines, words, and bytes in each file. If any flags are
-given,
+prints the number of lines, words and bytes in each
+.Ar file ,
+unless set differently with flags.
+If no
+.Ar file
+is given
 .Nm
-will print only the requested information. If no
-.Ar files
-are given,
-.Nm
-reads stdin.
+reads from stdin.
 .Sh OPTIONS
 .Bl -tag -width Ds
-.It Fl c
-print the number of bytes.
-.It Fl l
-print the number of lines.
-.It Fl m
-print the number of characters, not bytes.
-.It Fl w
-print the number of words.
+.It Fl c | Fl l | Fl m | Fl w
+Print the number of bytes | lines | characters | words.
 .El
+.Sh STANDARDS
+The
+.Nm
+utility is compliant with the
+.St -p1003.1-2008
+specification.
diff --git a/wc.c b/wc.c
index f2a7206..f283e1b 100644
--- a/wc.c
+++ b/wc.c
@@ -6,18 +6,58 @@
 
 #include "util.h"
 
-static void output(const char *, long, long, long);
-static void wc(FILE *, const char *);
+static int    lflag = 0;
+static int    wflag = 0;
+static char   cmode = 0;
+static size_t tc = 0, tl = 0, tw = 0;
 
-static int lflag = 0;
-static int wflag = 0;
-static char cmode = 0;
-static long tc = 0, tl = 0, tw = 0;
+void
+output(const char *str, size_t nc, size_t nl, size_t nw)
+{
+	int noflags = !cmode && !lflag && !wflag;
+
+	if (lflag || noflags)
+		printf(" %5zu", nl);
+	if (wflag || noflags)
+		printf(" %5zu", nw);
+	if (cmode || noflags)
+		printf(" %5zu", nc);
+	if (str)
+		printf(" %s", str);
+	putchar('\n');
+}
+
+void
+wc(FILE *fp, const char *str)
+{
+	int word = 0;
+	int c;
+	size_t nc = 0, nl = 0, nw = 0;
+
+	while ((c = getc(fp)) != EOF) {
+		if (cmode != 'm' || UTF8_POINT(c))
+			nc++;
+		if (c == '\n')
+			nl++;
+		if (!isspace(c))
+			word = 1;
+		else if (word) {
+			word = 0;
+			nw++;
+		}
+	}
+	if (word)
+		nw++;
+	tc += nc;
+	tl += nl;
+	tw += nw;
+	output(str, nc, nl, nw);
+}
 
 static void
 usage(void)
 {
-	eprintf("usage: %s [-clmw] [files...]\n", argv0);
+	eprintf("usage: %s [-c | -m] [-lw] [file ...]\n", argv0);
 }
 
 int
@@ -59,46 +99,3 @@ main(int argc, char *argv[])
 	}
 	return 0;
 }
-
-void
-output(const char *str, long nc, long nl, long nw)
-{
-	int noflags = !cmode && !lflag && !wflag;
-
-	if (lflag || noflags)
-		printf(" %5ld", nl);
-	if (wflag || noflags)
-		printf(" %5ld", nw);
-	if (cmode || noflags)
-		printf(" %5ld", nc);
-	if (str)
-		printf(" %s", str);
-	putchar('\n');
-}
-
-void
-wc(FILE *fp, const char *str)
-{
-	int word = 0;
-	int c;
-	long nc = 0, nl = 0, nw = 0;
-
-	while ((c = getc(fp)) != EOF) {
-		if (cmode != 'm' || UTF8_POINT(c))
-			nc++;
-		if (c == '\n')
-			nl++;
-		if (!isspace(c))
-			word = 1;
-		else if (word) {
-			word = 0;
-			nw++;
-		}
-	}
-	if (word)
-		nw++;
-	tc += nc;
-	tl += nl;
-	tw += nw;
-	output(str, nc, nl, nw);
-}