From 20f67f157c2284057328e6391d10e329b088f8d2 Mon Sep 17 00:00:00 2001
From: Rob Landley <rob@landley.net>
Date: Thu, 30 Jun 2016 10:39:41 -0500
Subject: Teach wc to do -cm together. Fix testsuite so TEST_HOST passes too.

---
 tests/wc.test   | 13 +++++-----
 toys/posix/wc.c | 73 +++++++++++++++++++++++++++++++--------------------------
 2 files changed, 46 insertions(+), 40 deletions(-)

diff --git a/tests/wc.test b/tests/wc.test
index abb237e8..d227b9c0 100755
--- a/tests/wc.test
+++ b/tests/wc.test
@@ -12,16 +12,14 @@ lines
 EOF
 
 testing "wc" "wc >/dev/null && echo yes" "yes\n" "" ""
-testing "empty file" "wc" "0 0 0\n" "" ""
-testing "standard input" "wc" "1 3 5\n" "" "a b\nc"
+testing "empty file" "wc" "      0       0       0\n" "" ""
+testing "standard input" "wc" "      1       3       5\n" "" "a b\nc"
 testing "-c" "wc -c file1" "26 file1\n" "" ""
 testing "-l" "wc -l file1" "4 file1\n" "" ""
 testing "-w" "wc -w file1" "5 file1\n" "" ""
-testing "format" "wc file1" "4 5 26 file1\n" "" ""
+NOSPACE=1 testing "format" "wc file1" " 4 5 26 file1\n" "" ""
 testing "multiple files" "wc input - file1" \
-        "1 2 3 input\n0 2 3 -\n4 5 26 file1\n5 9 32 total\n" "a\nb" "a b"
-
-optional TOYBOX_I18N
+        "      1       2       3 input\n      0       2       3 -\n      4       5      26 file1\n      5       9      32 total\n" "a\nb" "a b"
 
 #Tests for wc -m
 if printf "%s" "$LANG" | grep -q UTF-8
@@ -33,13 +31,14 @@ do
   printf "ü" >> file1
 done
 testing "-m" "wc -m file1" "8193 file1\n" "" ""
+testing "-m 2" 'cat "$FILES/utf8/test2.txt" | wc -m' "169\n" "" ""
 printf " " > file1
 for i in $(seq 1 8192)
 do
   printf "ü" >> file1
 done
 testing "-m (invalid chars)" "wc -m file1" "8193 file1\n" "" ""
-testing "-mlw" "wc -mlw input" "1 2 11 input\n" "hello, 世界!\n" ""
+NOSPACE=1 testing "-mlw" "wc -mlw input" " 1 2 11 input\n" "hello, 世界!\n" ""
 
 else
 printf "skipping tests for wc -m"
diff --git a/toys/posix/wc.c b/toys/posix/wc.c
index e7afc813..a8c3e452 100644
--- a/toys/posix/wc.c
+++ b/toys/posix/wc.c
@@ -4,7 +4,7 @@
  *
  * See http://opengroup.org/onlinepubs/9699919799/utilities/wc.html
 
-USE_WC(NEWTOY(wc, USE_TOYBOX_I18N("m")"cwl[!cm]", TOYFLAG_USR|TOYFLAG_BIN|TOYFLAG_LOCALE))
+USE_WC(NEWTOY(wc, "mcwl", TOYFLAG_USR|TOYFLAG_BIN|TOYFLAG_LOCALE))
 
 config WC
   bool "wc"
@@ -28,68 +28,75 @@ config WC
 #include "toys.h"
 
 GLOBALS(
-  unsigned long totals[3];
+  unsigned long totals[4];
 )
 
 static void show_lengths(unsigned long *lengths, char *name)
 {
-  int i, nospace = 1;
-  for (i=0; i<3; i++) {
-    if (!toys.optflags || (toys.optflags&(1<<i))) {
-      xprintf(" %ld"+nospace, lengths[i]);
-      nospace = 0;
+  int i, space = 7, first = 1;
+
+  for (i = 0; i<4; i++) if (toys.optflags == (1<<i)) space = 0;
+  for (i = 0; i<4; i++) {
+    if (toys.optflags&(1<<i)) {
+      printf(" %*ld"+first, space, lengths[i]);
+      first = 0;
     }
     TT.totals[i] += lengths[i];
   }
-  if (*toys.optargs) xprintf(" %s", name);
+  if (*toys.optargs) printf(" %s", name);
   xputc('\n');
 }
 
 static void do_wc(int fd, char *name)
 {
-  int i, len, clen=1, space;
-  unsigned long word=0, lengths[]={0,0,0};
+  int len = 0, clen = 1, space = 0;
+  unsigned long word = 0, lengths[] = {0,0,0,0};
 
+  // Speed up common case: wc -c normalfile is file length.
   if (toys.optflags == FLAG_c) {
     struct stat st;
 
     // On Linux, files in /proc often report their size as 0.
-    if (!fstat(fd, &st) && S_ISREG(st.st_mode) && st.st_size > 0) {
+    if (!fstat(fd, &st) && S_ISREG(st.st_mode) && st.st_size) {
       lengths[2] = st.st_size;
       goto show;
     }
   }
 
   for (;;) {
-    len = read(fd, toybuf, sizeof(toybuf));
-    if (len<0) perror_msg_raw(name);
-    if (len<1) break;
-    if (toys.optflags == FLAG_c) {
-      lengths[2] += len;
-      continue;
-    }
-    for (i=0; i<len; i+=clen) {
-      wchar_t wchar;
-
-      if (CFG_TOYBOX_I18N && (toys.optflags&FLAG_m)) {
-        clen = mbrtowc(&wchar, toybuf+i, len-i, 0);
-        if (clen == -1) {
-          clen = 1;
-          continue;
+    int pos, done = 0, len2 = read(fd, toybuf+len, sizeof(toybuf)-len);
+
+    if (len2<0) perror_msg_raw(name);
+    else len += len2;
+    if (len2<1) done++;
+
+    for (pos = 0; pos<len; pos++) {
+      if (toybuf[pos]=='\n') lengths[0]++;
+      lengths[2]++;
+      if (toys.optflags&FLAG_m) {
+        // If we've consumed next wide char
+        if (--clen<1) {
+          wchar_t wchar;
+
+          // next wide size, don't count invalid, fetch more data if necessary
+          clen = mbrtowc(&wchar, toybuf+pos, len-pos, 0);
+          if (clen == -1) continue;
+          if (clen == -2 && !done) break;
+
+          lengths[3]++;
+          space = iswspace(wchar);
         }
-        if (clen == -2) break;
-        if (clen == 0) clen=1;
-        space = iswspace(wchar);
-      } else space = isspace(toybuf[i]);
+      } else space = isspace(toybuf[pos]);
 
-      if (toybuf[i]==10) lengths[0]++;
       if (space) word=0;
       else {
         if (!word) lengths[1]++;
         word=1;
       }
-      lengths[2]++;
     }
+    if (done) break;
+    if (pos != len) memmove(toybuf, toybuf+pos, len-pos);
+    len -= pos;
   }
 
 show:
@@ -98,7 +105,7 @@ show:
 
 void wc_main(void)
 {
-  toys.optflags |= (toys.optflags&8)>>1;
+  if (!toys.optflags) toys.optflags = FLAG_l|FLAG_w|FLAG_c;
   loopfiles(toys.optargs, do_wc);
   if (toys.optc>1) show_lengths(TT.totals, "total");
 }
-- 
cgit v1.2.3