UCW: Renamed 'UTF-8' tests to 'Unicode' (I am going to add some UTF-16 test cases).

diff --git a/lib/Makefile b/lib/Makefile
index ed6a3a7972fa70afafa5538fa7a14f5ad65c220e..f579a34399e65ab0ef9470a466268b3b26995d6f 100644 (file)
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -19,7 +19,7 @@ LIBUCW_MODS= \
        profile \
        fastbuf ff-binary ff-string ff-printf ff-unicode \
        fb-file carefulio fb-mem fb-temp fb-mmap fb-limfd fb-buffer fb-grow fb-pool fb-atomic fb-param \
-       str_ctype str_upper str_lower unicode-utf8 stkstring \
+       str_ctype str_upper str_lower unicode stkstring \
        wildmatch wordsplit ctmatch patimatch patmatch regex \
        prime primetable random timer randomkey \
        bit-ffs bit-fls \
@@ -99,11 +99,11 @@ $(o)/lib/lizard-test: $(o)/lib/lizard-test.o $(LIBUCW)
 $(o)/lib/kmp-test: $(o)/lib/kmp-test.o $(LIBUCW) $(LIBCHARSET)
 $(o)/lib/ipaccess-test: $(o)/lib/ipaccess-test.o $(LIBUCW)
 
-TESTS+=$(addprefix $(o)/lib/,regex.test unicode-utf8.test hash-test.test mempool.test stkstring.test \
+TESTS+=$(addprefix $(o)/lib/,regex.test unicode.test hash-test.test mempool.test stkstring.test \
     slists.test kmp-test.test bbuf.test getopt.test fastbuf.test eltpool.test)
 
 $(o)/lib/regex.test: $(o)/lib/regex-t
-$(o)/lib/unicode-utf8.test: $(o)/lib/unicode-utf8-t
+$(o)/lib/unicode.test: $(o)/lib/unicode-t
 $(o)/lib/hash-test.test: $(o)/lib/hash-test
 $(o)/lib/mempool.test: $(o)/lib/mempool-t $(o)/lib/mempool-fmt-t $(o)/lib/mempool-str-t
 $(o)/lib/stkstring.test: $(o)/lib/stkstring-t

diff --git a/lib/unicode-utf8.c b/lib/unicode-utf8.c
deleted file mode 100644 (file)
index e4a33af..0000000
--- a/lib/unicode-utf8.c
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- *     UCW Library -- UTF-8 Functions
- *
- *     (c) 1997--2004 Martin Mares <mj@ucw.cz>
- *     (c) 2003 Robert Spalek <robert@ucw.cz>
- *
- *     This software may be freely distributed and used according to the terms
- *     of the GNU Lesser General Public License.
- */
-
-#include "lib/lib.h"
-#include "lib/unicode.h"
-
-uns
-utf8_strlen(const byte *str)
-{
-  uns len = 0;
-  while (*str)
-    {
-      UTF8_SKIP(str);
-      len++;
-    }
-  return len;
-}
-
-uns
-utf8_strnlen(const byte *str, uns n)
-{
-  uns len = 0;
-  const byte *end = str + n;
-  while (str < end)
-    {
-      UTF8_SKIP(str);
-      len++;
-    }
-  return len;
-}
-
-#ifdef TEST
-#include <string.h>
-#include <stdio.h>
-int main(int argc, char **argv)
-{
-  byte buf[256];
-  if (argc > 1 && !strncmp(argv[1], "get", 3))
-    {
-      int f32 = !strcmp(argv[1], "get32");
-      byte *p = buf;
-      uns u;
-      while (scanf("%x", &u) == 1)
-       *p++ = u;
-      *p = 0;
-      p = buf;
-      while (*p)
-       {
-         if (p != buf)
-           putchar(' ');
-         if (f32)
-           GET_UTF8_32(p, u);
-         else
-           GET_UTF8(p, u);
-         printf("%04x", u);
-       }
-      putchar('\n');
-    }
-  else if (argc > 1 && !strncmp(argv[1], "put", 3))
-    {
-      uns u, i=0;
-      int f32 = !strcmp(argv[1], "put32");
-      while (scanf("%x", &u) == 1)
-       {
-         byte *p = buf;
-         if (f32)
-           PUT_UTF8_32(p, u);
-         else
-           PUT_UTF8(p, u);
-         *p = 0;
-         for (p=buf; *p; p++)
-           {
-             if (i++)
-               putchar(' ');
-             printf("%02x", *p);
-           }
-       }
-      putchar('\n');
-    }
-  else
-    puts("?");
-  return 0;
-}
-#endif

diff --git a/lib/unicode-utf8.t b/lib/unicode-utf8.t
deleted file mode 100644 (file)
index 132bbbd..0000000
--- a/lib/unicode-utf8.t
+++ /dev/null
@@ -1,41 +0,0 @@
-# Tests for the Unicode UTF-8 module
-
-Name:  put1
-Run:   ../obj/lib/unicode-utf8-t put
-In:    0041 0048 004f 004a
-Out:   41 48 4f 4a
-
-Name:  put2
-Run:   ../obj/lib/unicode-utf8-t put
-In:    00aa 01aa 02a5 05a5 0a5a 15a5 2a5a 5a5a a5a5
-Out:   c2 aa c6 aa ca a5 d6 a5 e0 a9 9a e1 96 a5 e2 a9 9a e5 a9 9a ea 96 a5
-
-Name:  get1
-Run:   ../obj/lib/unicode-utf8-t get
-In:    41 48 4f 4a
-Out:   0041 0048 004f 004a
-
-Name:  get2
-Run:   ../obj/lib/unicode-utf8-t get
-In:    c2 aa c6 aa ca a5 d6 a5 e0 a9 9a e1 96 a5 e2 a9 9a e5 a9 9a ea 96 a5
-Out:   00aa 01aa 02a5 05a5 0a5a 15a5 2a5a 5a5a a5a5
-
-Name:  get3
-Run:   ../obj/lib/unicode-utf8-t get
-In:    84 ff f9 f8 c2 aa 41
-Out:   fffc fffc fffc fffc 00aa 0041
-
-Name:  put32
-Run:   ../obj/lib/unicode-utf8-t put32
-In:    15a5a 2a5a5 5a5a5 a5a5a 15a5a5 2a5a5a 5a5a5a a5a5a5 15a5a5a 2a5a5a5 5a5a5a5 a5a5a5a 15a5a5a5 2a5a5a5a 5a5a5a5a
-Out:   f0 95 a9 9a f0 aa 96 a5 f1 9a 96 a5 f2 a5 a9 9a f5 9a 96 a5 f8 8a a5 a9 9a f8 96 a5 a9 9a f8 a9 9a 96 a5 f9 96 a5 a9 9a fa a9 9a 96 a5 fc 85 a9 9a 96 a5 fc 8a 96 a5 a9 9a fc 95 a9 9a 96 a5 fc aa 96 a5 a9 9a fd 9a 96 a5 a9 9a
-
-Name:  get32a
-Run:   ../obj/lib/unicode-utf8-t get32
-In:    f0 95 a9 9a f0 aa 96 a5 f1 9a 96 a5 f2 a5 a9 9a f5 9a 96 a5 f8 8a a5 a9 9a f8 96 a5 a9 9a f8 a9 9a 96 a5 f9 96 a5 a9 9a fa a9 9a 96 a5 fc 85 a9 9a 96 a5 fc 8a 96 a5 a9 9a fc 95 a9 9a 96 a5 fc aa 96 a5 a9 9a fd 9a 96 a5 a9 9a
-Out:   15a5a 2a5a5 5a5a5 a5a5a 15a5a5 2a5a5a 5a5a5a a5a5a5 15a5a5a 2a5a5a5 5a5a5a5 a5a5a5a 15a5a5a5 2a5a5a5a 5a5a5a5a
-
-Name:  get32b
-Run:   ../obj/lib/unicode-utf8-t get32
-In:    fe 83 81
-Out:   fffc fffc fffc

diff --git a/lib/unicode.c b/lib/unicode.c
new file mode 100644 (file)
index 0000000..e4a33af
--- /dev/null
+++ b/lib/unicode.c
@@ -0,0 +1,91 @@
+/*
+ *     UCW Library -- UTF-8 Functions
+ *
+ *     (c) 1997--2004 Martin Mares <mj@ucw.cz>
+ *     (c) 2003 Robert Spalek <robert@ucw.cz>
+ *
+ *     This software may be freely distributed and used according to the terms
+ *     of the GNU Lesser General Public License.
+ */
+
+#include "lib/lib.h"
+#include "lib/unicode.h"
+
+uns
+utf8_strlen(const byte *str)
+{
+  uns len = 0;
+  while (*str)
+    {
+      UTF8_SKIP(str);
+      len++;
+    }
+  return len;
+}
+
+uns
+utf8_strnlen(const byte *str, uns n)
+{
+  uns len = 0;
+  const byte *end = str + n;
+  while (str < end)
+    {
+      UTF8_SKIP(str);
+      len++;
+    }
+  return len;
+}
+
+#ifdef TEST
+#include <string.h>
+#include <stdio.h>
+int main(int argc, char **argv)
+{
+  byte buf[256];
+  if (argc > 1 && !strncmp(argv[1], "get", 3))
+    {
+      int f32 = !strcmp(argv[1], "get32");
+      byte *p = buf;
+      uns u;
+      while (scanf("%x", &u) == 1)
+       *p++ = u;
+      *p = 0;
+      p = buf;
+      while (*p)
+       {
+         if (p != buf)
+           putchar(' ');
+         if (f32)
+           GET_UTF8_32(p, u);
+         else
+           GET_UTF8(p, u);
+         printf("%04x", u);
+       }
+      putchar('\n');
+    }
+  else if (argc > 1 && !strncmp(argv[1], "put", 3))
+    {
+      uns u, i=0;
+      int f32 = !strcmp(argv[1], "put32");
+      while (scanf("%x", &u) == 1)
+       {
+         byte *p = buf;
+         if (f32)
+           PUT_UTF8_32(p, u);
+         else
+           PUT_UTF8(p, u);
+         *p = 0;
+         for (p=buf; *p; p++)
+           {
+             if (i++)
+               putchar(' ');
+             printf("%02x", *p);
+           }
+       }
+      putchar('\n');
+    }
+  else
+    puts("?");
+  return 0;
+}
+#endif

diff --git a/lib/unicode.t b/lib/unicode.t
new file mode 100644 (file)
index 0000000..132bbbd
--- /dev/null
+++ b/lib/unicode.t
@@ -0,0 +1,41 @@
+# Tests for the Unicode UTF-8 module
+
+Name:  put1
+Run:   ../obj/lib/unicode-utf8-t put
+In:    0041 0048 004f 004a
+Out:   41 48 4f 4a
+
+Name:  put2
+Run:   ../obj/lib/unicode-utf8-t put
+In:    00aa 01aa 02a5 05a5 0a5a 15a5 2a5a 5a5a a5a5
+Out:   c2 aa c6 aa ca a5 d6 a5 e0 a9 9a e1 96 a5 e2 a9 9a e5 a9 9a ea 96 a5
+
+Name:  get1
+Run:   ../obj/lib/unicode-utf8-t get
+In:    41 48 4f 4a
+Out:   0041 0048 004f 004a
+
+Name:  get2
+Run:   ../obj/lib/unicode-utf8-t get
+In:    c2 aa c6 aa ca a5 d6 a5 e0 a9 9a e1 96 a5 e2 a9 9a e5 a9 9a ea 96 a5
+Out:   00aa 01aa 02a5 05a5 0a5a 15a5 2a5a 5a5a a5a5
+
+Name:  get3
+Run:   ../obj/lib/unicode-utf8-t get
+In:    84 ff f9 f8 c2 aa 41
+Out:   fffc fffc fffc fffc 00aa 0041
+
+Name:  put32
+Run:   ../obj/lib/unicode-utf8-t put32
+In:    15a5a 2a5a5 5a5a5 a5a5a 15a5a5 2a5a5a 5a5a5a a5a5a5 15a5a5a 2a5a5a5 5a5a5a5 a5a5a5a 15a5a5a5 2a5a5a5a 5a5a5a5a
+Out:   f0 95 a9 9a f0 aa 96 a5 f1 9a 96 a5 f2 a5 a9 9a f5 9a 96 a5 f8 8a a5 a9 9a f8 96 a5 a9 9a f8 a9 9a 96 a5 f9 96 a5 a9 9a fa a9 9a 96 a5 fc 85 a9 9a 96 a5 fc 8a 96 a5 a9 9a fc 95 a9 9a 96 a5 fc aa 96 a5 a9 9a fd 9a 96 a5 a9 9a
+
+Name:  get32a
+Run:   ../obj/lib/unicode-utf8-t get32
+In:    f0 95 a9 9a f0 aa 96 a5 f1 9a 96 a5 f2 a5 a9 9a f5 9a 96 a5 f8 8a a5 a9 9a f8 96 a5 a9 9a f8 a9 9a 96 a5 f9 96 a5 a9 9a fa a9 9a 96 a5 fc 85 a9 9a 96 a5 fc 8a 96 a5 a9 9a fc 95 a9 9a 96 a5 fc aa 96 a5 a9 9a fd 9a 96 a5 a9 9a
+Out:   15a5a 2a5a5 5a5a5 a5a5a 15a5a5 2a5a5a 5a5a5a a5a5a5 15a5a5a 2a5a5a5 5a5a5a5 a5a5a5a 15a5a5a5 2a5a5a5a 5a5a5a5a
+
+Name:  get32b
+Run:   ../obj/lib/unicode-utf8-t get32
+In:    fe 83 81
+Out:   fffc fffc fffc