More tests for module uninorm/u8-normcmp.

[gnulib.git] / tests / uninorm / test-u8-normcmp.c

diff --git a/tests/uninorm/test-u8-normcmp.c b/tests/uninorm/test-u8-normcmp.c
index 6839750..ec47947 100644 (file)
--- a/tests/uninorm/test-u8-normcmp.c
+++ b/tests/uninorm/test-u8-normcmp.c
@@ -1,4 +1,4 @@
-/* Test of normalization insensitive comparison of UTF-32 strings.
+/* Test of normalization insensitive comparison of UTF-8 strings.
    Copyright (C) 2009 Free Software Foundation, Inc.
 
    This program is free software: you can redistribute it and/or modify
@@ -36,43 +36,11 @@
     }                                                                       \
   while (0)
 
-int
-main ()
-{
-  /* Empty string.  */
-  {
-    int cmp;
-
-    ASSERT (u8_normcmp (NULL, 0, NULL, 0, UNINORM_NFD, &cmp) == 0);
-    ASSERT (cmp == 0);
-  }
-  {
-    static const uint8_t input[] = { 'x', 'y' };
-    int cmp;
-
-    ASSERT (u8_normcmp (input, SIZEOF (input), NULL, 0, UNINORM_NFD, &cmp) == 0);
-    ASSERT (cmp == 1);
-
-    ASSERT (u8_normcmp (NULL, 0, input, SIZEOF (input), UNINORM_NFD, &cmp) == 0);
-    ASSERT (cmp == -1);
-
-    ASSERT (u8_normcmp (input, SIZEOF (input), input, SIZEOF (input), UNINORM_NFD, &cmp) == 0);
-    ASSERT (cmp == 0);
-  }
-
-  /* Shorter and longer strings.  */
-  {
-    static const uint8_t input1[] = { 'R', 'e', 'a', 'g', 'a', 'n' };
-    static const uint8_t input2[] = { 'R', 'e', 'a', 'g', 'a', 'n', 'o', 'm', 'i', 'c', 's' };
-    int cmp;
-
-    ASSERT (u8_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
-    ASSERT (cmp == -1);
-
-    ASSERT (u8_normcmp (input2, SIZEOF (input2), input1, SIZEOF (input1), UNINORM_NFD, &cmp) == 0);
-    ASSERT (cmp == 1);
-  }
+#include "test-u8-normcmp.h"
 
+static void
+test_nonascii (int (*my_normcmp) (const uint8_t *, size_t, const uint8_t *, size_t, uninorm_t, int *))
+{
   /* Normalization effects.  */
   {
     static const uint8_t input1[] = { 'H', 0xC3, 0xB6, 'h', 'l', 'e' };
@@ -82,30 +50,81 @@ main ()
     static const uint8_t input5[] = { 'H', 'u', 'r', 'z' };
     int cmp;
 
-    ASSERT (u8_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
+    ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
     ASSERT (cmp == 0);
 
-    ASSERT (u8_normcmp (input2, SIZEOF (input2), input1, SIZEOF (input1), UNINORM_NFD, &cmp) == 0);
+    ASSERT (my_normcmp (input2, SIZEOF (input2), input1, SIZEOF (input1), UNINORM_NFD, &cmp) == 0);
     ASSERT (cmp == 0);
 
-    ASSERT (u8_normcmp (input3, SIZEOF (input3), input4, SIZEOF (input4), UNINORM_NFD, &cmp) == 0);
+    ASSERT (my_normcmp (input3, SIZEOF (input3), input4, SIZEOF (input4), UNINORM_NFD, &cmp) == 0);
     ASSERT (cmp == 0);
 
-    ASSERT (u8_normcmp (input4, SIZEOF (input4), input3, SIZEOF (input3), UNINORM_NFD, &cmp) == 0);
+    ASSERT (my_normcmp (input4, SIZEOF (input4), input3, SIZEOF (input3), UNINORM_NFD, &cmp) == 0);
     ASSERT (cmp == 0);
 
-    ASSERT (u8_normcmp (input2, SIZEOF (input2), input3, SIZEOF (input3), UNINORM_NFD, &cmp) == 0);
+    ASSERT (my_normcmp (input2, SIZEOF (input2), input3, SIZEOF (input3), UNINORM_NFD, &cmp) == 0);
     ASSERT (cmp == -1);
 
-    ASSERT (u8_normcmp (input1, SIZEOF (input1), input4, SIZEOF (input4), UNINORM_NFD, &cmp) == 0);
+    ASSERT (my_normcmp (input1, SIZEOF (input1), input4, SIZEOF (input4), UNINORM_NFD, &cmp) == 0);
     ASSERT (cmp == -1);
 
-    ASSERT (u8_normcmp (input1, SIZEOF (input1), input5, SIZEOF (input5), UNINORM_NFD, &cmp) == 0);
+    ASSERT (my_normcmp (input1, SIZEOF (input1), input5, SIZEOF (input5), UNINORM_NFD, &cmp) == 0);
     ASSERT (cmp == -1);
 
-    ASSERT (u8_normcmp (input2, SIZEOF (input2), input5, SIZEOF (input5), UNINORM_NFD, &cmp) == 0);
+    ASSERT (my_normcmp (input2, SIZEOF (input2), input5, SIZEOF (input5), UNINORM_NFD, &cmp) == 0);
     ASSERT (cmp == -1);
   }
+  { /* LATIN CAPITAL LETTER A WITH DIAERESIS */
+    static const uint8_t input1[] = { 0xC3, 0x84 };
+    static const uint8_t input2[] = { 0x41, 0xCC, 0x88 };
+    int cmp;
+
+    ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
+    ASSERT (cmp == 0);
+  }
+  { /* LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON */
+    static const uint8_t input1[] = { 0xC7, 0x9E };
+    static const uint8_t input2[] = { 0x41, 0xCC, 0x88, 0xCC, 0x84 };
+    int cmp;
+
+    ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
+    ASSERT (cmp == 0);
+  }
+  { /* GREEK DIALYTIKA AND PERISPOMENI */
+    static const uint8_t input1[] = { 0xE1, 0xBF, 0x81 };
+    static const uint8_t input2[] = { 0xC2, 0xA8, 0xCD, 0x82 };
+    int cmp;
+
+    ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
+    ASSERT (cmp == 0);
+  }
+  { /* HANGUL SYLLABLE GEUL */
+    static const uint8_t input1[] = { 0xEA, 0xB8, 0x80 };
+    static const uint8_t input2[] = { 0xEA, 0xB7, 0xB8, 0xE1, 0x86, 0xAF };
+    static const uint8_t input3[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3, 0xE1, 0x86, 0xAF };
+    int cmp;
+
+    ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
+    ASSERT (cmp == 0);
+
+    ASSERT (my_normcmp (input1, SIZEOF (input1), input3, SIZEOF (input3), UNINORM_NFD, &cmp) == 0);
+    ASSERT (cmp == 0);
+  }
+  { /* HANGUL SYLLABLE GEU */
+    static const uint8_t input1[] = { 0xEA, 0xB7, 0xB8 };
+    static const uint8_t input2[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3 };
+    int cmp;
+
+    ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
+    ASSERT (cmp == 0);
+  }
+}
+
+int
+main ()
+{
+  test_ascii (u8_normcmp, UNINORM_NFD);
+  test_nonascii (u8_normcmp);
 
   return 0;
 }