1 files changed, 66 insertions, 0 deletions

diff --git a/v_windows/v/vlib/encoding/utf8/utf8_util_test.v b/v_windows/v/vlib/encoding/utf8/utf8_util_test.v
new file mode 100644
index 0000000..f09cb76
--- /dev/null
+++ b/v_windows/v/vlib/encoding/utf8/utf8_util_test.v
@@ -0,0 +1,66 @@
+import encoding.utf8
+
+fn test_utf8_util() {
+	// string test
+	src := 'ăĂ ôÔ testo 怔' //_\u1E5A\u1E5B<=>\u1F49\u1F41<=>\u0128\u012a\u012c" // len 29 runes, raw 49 bytes
+	src_upper := 'ĂĂ ÔÔ TESTO Æ€”' //_\u1E5A\u1E5A<=>\u1F49\u1F49<=>\u0128\u012A\u012C"
+	src_lower := 'ăă ôô testo 怔' //_\u1E5B\u1E5B<=>\u1F41\u1F41<=>\u0129\u012B\u012D"
+	upper := utf8.to_upper(src)
+	lower := utf8.to_lower(src)
+	assert upper == src_upper
+	assert lower == src_lower
+
+	assert utf8.to_upper('абвёabc12｛') == 'АБВЁABC12｛'
+	assert utf8.to_lower('АБВЁABC12｛') == 'абвёabc12｛'
+
+	// test len function
+	assert utf8.len('') == 0
+	assert utf8.len('pippo') == 5
+	assert utf8.len(src) == 15 // 29
+	assert src.len == 24 // 49
+
+	// western punctuation
+	a := '.abc?abcòàè.'
+	assert utf8.is_punct(a, 0) == true
+	assert utf8.is_punct('b', 0) == false
+	assert utf8.is_uchar_punct(0x002E) == true
+	assert utf8.is_punct(a, 4) == true // ?
+	assert utf8.is_punct(a, 14) == true // last .
+	assert utf8.is_punct(a, 12) == false // è
+	println('OK western')
+
+	// global punctuation
+	b := '.ĂĂa. ÔÔ TESTO Æ€'
+	assert utf8.is_global_punct(b, 0) == true
+	assert utf8.is_global_punct('.', 0) == true
+	assert utf8.is_uchar_punct(0x002E) == true
+	assert utf8.is_global_punct(b, 6) == true // .
+	assert utf8.is_global_punct(b, 1) == false // a
+
+	// test utility functions
+	assert utf8.get_uchar(b, 0) == 0x002E
+}
+
+fn test_raw_indexing() {
+	a := '我是V Lang!'
+
+	// test non ascii characters
+	assert utf8.raw_index(a, 0) == '我'
+	assert utf8.raw_index(a, 1) == '是'
+
+	// test ascii characters
+	assert utf8.raw_index(a, 2) == 'V'
+	assert utf8.raw_index(a, 3) == ' '
+	assert utf8.raw_index(a, 4) == 'L'
+	assert utf8.raw_index(a, 5) == 'a'
+	assert utf8.raw_index(a, 6) == 'n'
+	assert utf8.raw_index(a, 7) == 'g'
+	assert utf8.raw_index(a, 8) == '!'
+}
+
+fn test_reversed() {
+	a := '我是V Lang!'
+	b := '你好世界hello world'
+	assert utf8.reverse(a) == '!gnaL V是我'
+	assert utf8.reverse(b) == 'dlrow olleh界世好你'
+}