wc

commit 496cd811a1fb586b2834b79b629383fdb6a89974
parent aec062db2e9525927fb8690a21fbf16ef53488c5
Author: NunoSempere <nuno.sempere@protonmail.com>
Date:   Sat,  9 Sep 2023 16:21:03 +0200

small readability reorder

Thought a bit about whether having OR instead of AND
changes performance, and concluded it probably didn't.

In particular, think about when it jumps to the inner
part of the if/else condition

Diffstat:
M
README.md
 | 
2
+-
M
ww
 | 
0

M
ww.c
 | 
22
++++++++--------------

3 files changed, 9 insertions(+), 15 deletions(-)
diff --git a/README.md b/README.md
@@ -11,7 +11,7 @@
 
 ## Comparison with wc.
 
-The GNU utils version ([github](https://github.com/coreutils/coreutils/tree/master/src/wc.c), [savannah](http://git.savannah.gnu.org/gitweb/?p=coreutils.git;a=blob;f=src/wc.c;hb=HEAD)) is a bit over 1K lines of C. It does many things and checks many possible failure modes.
+The GNU utils version ([github](https://github.com/coreutils/coreutils/tree/master/src/wc.c), [savannah](http://git.savannah.gnu.org/gitweb/?p=coreutils.git;a=blob;f=src/wc.c;hb=HEAD)) is a bit over 1K lines of C. It does many things and checks many possible failure modes. I think it detects whether it should be reading from stdin using some very wrapped fstat. 
 
 The busybox version ([git.busybox.net](https://git.busybox.net/busybox/tree/coreutils/wc.c)) of wc is much shorter, at 257 lines, while striving to be [POSIX-compliant](https://pubs.opengroup.org/onlinepubs/9699919799/), meaning it has flags.
 
diff --git a/ww b/ww
Binary files differ.
diff --git a/ww.c b/ww.c
@@ -4,25 +4,19 @@
 int wc(FILE* fp)
 {
     char c[1];
-    int seen_word = 0, seen_sep_after_word = 0, num_words = 0;
+    int word = 0, num_words = 0;
 	  int fn = fileno(fp);
     while (read(fn, c, sizeof(c)) > 0) {
-        if (*c == '\n' || *c == ' ' || *c == '\t') {
-            if (seen_word) {
-                seen_sep_after_word = 1;
-            }
+        if (*c != ' ' && *c != '\n' && *c != '\t') {
+            word = 1;
         } else {
-            seen_word = 1;
-        }
-        // exercise: what happens if you only track seen_sep,
-        // instead of seen_sep_after_word?
-        // test with: $ echo "	hello world" | ./wc
-        if (seen_word && seen_sep_after_word) {
-            num_words++;
-            seen_sep_after_word = seen_word = 0;
+            if (word) {
+              num_words++;
+              word = 0;
+            }
         }
     }
-		num_words+=seen_word;
+		num_words+=word;
     printf("%i\n", num_words);
     return 0;
 }