1// Copyright 2015 The Go Authors. All rights reserved.
2// Use of this source code is governed by a BSD-style
3// license that can be found in the LICENSE file.
4
5package korean
6
7import (
8	"strings"
9	"testing"
10
11	"golang.org/x/text/encoding"
12	"golang.org/x/text/encoding/internal"
13	"golang.org/x/text/encoding/internal/enctest"
14	"golang.org/x/text/transform"
15)
16
17func dec(e encoding.Encoding) (dir string, t transform.Transformer, err error) {
18	return "Decode", e.NewDecoder(), nil
19}
20func enc(e encoding.Encoding) (dir string, t transform.Transformer, err error) {
21	return "Encode", e.NewEncoder(), internal.ErrASCIIReplacement
22}
23
24func TestNonRepertoire(t *testing.T) {
25	// Pick n large enough to cause an overflow in the destination buffer of
26	// transform.String.
27	const n = 10000
28	testCases := []struct {
29		init      func(e encoding.Encoding) (string, transform.Transformer, error)
30		e         encoding.Encoding
31		src, want string
32	}{
33		{dec, EUCKR, "\xfe\xfe", "\ufffd"},
34		// {dec, EUCKR, "א", "\ufffd"}, // TODO: why is this different?
35
36		{enc, EUCKR, "א", ""},
37		{enc, EUCKR, "aא", "a"},
38		{enc, EUCKR, "\uac00א", "\xb0\xa1"},
39		// TODO: should we also handle Jamo?
40
41		{dec, EUCKR, "\x80", "\ufffd"},
42		{dec, EUCKR, "\xff", "\ufffd"},
43		{dec, EUCKR, "\x81", "\ufffd"},
44		{dec, EUCKR, "\xb0\x40", "\ufffd@"},
45		{dec, EUCKR, "\xb0\xff", "\ufffd"},
46		{dec, EUCKR, "\xd0\x20", "\ufffd "},
47		{dec, EUCKR, "\xd0\xff", "\ufffd"},
48
49		{dec, EUCKR, strings.Repeat("\x81", n), strings.Repeat("걖", n/2)},
50	}
51	for _, tc := range testCases {
52		dir, tr, wantErr := tc.init(tc.e)
53
54		dst, _, err := transform.String(tr, tc.src)
55		if err != wantErr {
56			t.Errorf("%s %v(%q): got %v; want %v", dir, tc.e, tc.src, err, wantErr)
57		}
58		if got := string(dst); got != tc.want {
59			t.Errorf("%s %v(%q):\ngot  %q\nwant %q", dir, tc.e, tc.src, got, tc.want)
60		}
61	}
62}
63
64func TestBasics(t *testing.T) {
65	// The encoded forms can be verified by the iconv program:
66	// $ echo 月日は百代 | iconv -f UTF-8 -t SHIFT-JIS | xxd
67	testCases := []struct {
68		e       encoding.Encoding
69		encoded string
70		utf8    string
71	}{{
72		// Korean tests.
73		//
74		// "A\uac02\uac35\uac56\ud401B\ud408\ud620\ud624C\u4f3d\u8a70D" is a
75		// nonsense string that contains ASCII, Hangul and CJK ideographs.
76		//
77		// "세계야, 안녕" translates as "Hello, world".
78		e:       EUCKR,
79		encoded: "A\x81\x41\x81\x61\x81\x81\xc6\xfeB\xc7\xa1\xc7\xfe\xc8\xa1C\xca\xa1\xfd\xfeD",
80		utf8:    "A\uac02\uac35\uac56\ud401B\ud408\ud620\ud624C\u4f3d\u8a70D",
81	}, {
82		e:       EUCKR,
83		encoded: "\xbc\xbc\xb0\xe8\xbe\xdf\x2c\x20\xbe\xc8\xb3\xe7",
84		utf8:    "세계야, 안녕",
85	}}
86
87	for _, tc := range testCases {
88		enctest.TestEncoding(t, tc.e, tc.encoded, tc.utf8, "", "")
89	}
90}
91
92func TestFiles(t *testing.T) { enctest.TestFile(t, EUCKR) }
93
94func BenchmarkEncoding(b *testing.B) { enctest.Benchmark(b, EUCKR) }
95