From 47ab3d4a42e9ab51c465c4322d2ec233f6324e6b Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 28 Apr 2024 15:16:40 +0200 Subject: Adding upstream version 1.18.10. Signed-off-by: Daniel Baumann --- src/mime/encodedword_test.go | 239 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 239 insertions(+) create mode 100644 src/mime/encodedword_test.go (limited to 'src/mime/encodedword_test.go') diff --git a/src/mime/encodedword_test.go b/src/mime/encodedword_test.go new file mode 100644 index 0000000..2a98794 --- /dev/null +++ b/src/mime/encodedword_test.go @@ -0,0 +1,239 @@ +// Copyright 2015 The Go Authors. All rights reserved. +// Use of this source code is governed by a BSD-style +// license that can be found in the LICENSE file. + +package mime + +import ( + "errors" + "io" + "strings" + "testing" +) + +func TestEncodeWord(t *testing.T) { + utf8, iso88591 := "utf-8", "iso-8859-1" + tests := []struct { + enc WordEncoder + charset string + src, exp string + }{ + {QEncoding, utf8, "François-Jérôme", "=?utf-8?q?Fran=C3=A7ois-J=C3=A9r=C3=B4me?="}, + {BEncoding, utf8, "Café", "=?utf-8?b?Q2Fmw6k=?="}, + {QEncoding, iso88591, "La Seleção", "=?iso-8859-1?q?La_Sele=C3=A7=C3=A3o?="}, + {QEncoding, utf8, "", ""}, + {QEncoding, utf8, "A", "A"}, + {QEncoding, iso88591, "a", "a"}, + {QEncoding, utf8, "123 456", "123 456"}, + {QEncoding, utf8, "\t !\"#$%&'()*+,-./ :;<>?@[\\]^_`{|}~", "\t !\"#$%&'()*+,-./ :;<>?@[\\]^_`{|}~"}, + {QEncoding, utf8, strings.Repeat("é", 10), "=?utf-8?q?" + strings.Repeat("=C3=A9", 10) + "?="}, + {QEncoding, utf8, strings.Repeat("é", 11), "=?utf-8?q?" + strings.Repeat("=C3=A9", 10) + "?= =?utf-8?q?=C3=A9?="}, + {QEncoding, iso88591, strings.Repeat("\xe9", 22), "=?iso-8859-1?q?" + strings.Repeat("=E9", 22) + "?="}, + {QEncoding, utf8, strings.Repeat("\x80", 22), "=?utf-8?q?" + strings.Repeat("=80", 21) + "?= =?utf-8?q?=80?="}, + {BEncoding, iso88591, strings.Repeat("\xe9", 45), "=?iso-8859-1?b?" + strings.Repeat("6enp", 15) + "?="}, + {BEncoding, utf8, strings.Repeat("\x80", 48), "=?utf-8?b?" + strings.Repeat("gICA", 15) + "?= =?utf-8?b?gICA?="}, + } + + for _, test := range tests { + if s := test.enc.Encode(test.charset, test.src); s != test.exp { + t.Errorf("Encode(%q) = %q, want %q", test.src, s, test.exp) + } + } +} + +func TestEncodedWordLength(t *testing.T) { + tests := []struct { + enc WordEncoder + src string + }{ + {QEncoding, strings.Repeat("à", 30)}, + {QEncoding, strings.Repeat("é", 60)}, + {BEncoding, strings.Repeat("ï", 25)}, + {BEncoding, strings.Repeat("ô", 37)}, + {BEncoding, strings.Repeat("\x80", 50)}, + {QEncoding, "{$firstname} Bienvendio a Apostolica, aquà inicia el camino de tu"}, + } + + for _, test := range tests { + s := test.enc.Encode("utf-8", test.src) + wordLen := 0 + for i := 0; i < len(s); i++ { + if s[i] == ' ' { + wordLen = 0 + continue + } + + wordLen++ + if wordLen > maxEncodedWordLen { + t.Errorf("Encode(%q) has more than %d characters: %q", + test.src, maxEncodedWordLen, s) + } + } + } +} + +func TestDecodeWord(t *testing.T) { + tests := []struct { + src, exp string + hasErr bool + }{ + {"=?UTF-8?Q?=C2=A1Hola,_se=C3=B1or!?=", "¡Hola, señor!", false}, + {"=?UTF-8?Q?Fran=C3=A7ois-J=C3=A9r=C3=B4me?=", "François-Jérôme", false}, + {"=?UTF-8?q?ascii?=", "ascii", false}, + {"=?utf-8?B?QW5kcsOp?=", "André", false}, + {"=?ISO-8859-1?Q?Rapha=EBl_Dupont?=", "Raphaël Dupont", false}, + {"=?utf-8?b?IkFudG9uaW8gSm9zw6kiIDxqb3NlQGV4YW1wbGUub3JnPg==?=", `"Antonio José" `, false}, + {"=?UTF-8?A?Test?=", "", true}, + {"=?UTF-8?Q?A=B?=", "", true}, + {"=?UTF-8?Q?=A?=", "", true}, + {"=?UTF-8?A?A?=", "", true}, + {"=????=", "", true}, + {"=?UTF-8???=", "", true}, + {"=?UTF-8?Q??=", "", false}, + } + + for _, test := range tests { + dec := new(WordDecoder) + s, err := dec.Decode(test.src) + if test.hasErr && err == nil { + t.Errorf("Decode(%q) should return an error", test.src) + continue + } + if !test.hasErr && err != nil { + t.Errorf("Decode(%q): %v", test.src, err) + continue + } + if s != test.exp { + t.Errorf("Decode(%q) = %q, want %q", test.src, s, test.exp) + } + } +} + +func TestDecodeHeader(t *testing.T) { + tests := []struct { + src, exp string + }{ + {"=?UTF-8?Q?=C2=A1Hola,_se=C3=B1or!?=", "¡Hola, señor!"}, + {"=?UTF-8?Q?Fran=C3=A7ois-J=C3=A9r=C3=B4me?=", "François-Jérôme"}, + {"=?UTF-8?q?ascii?=", "ascii"}, + {"=?utf-8?B?QW5kcsOp?=", "André"}, + {"=?ISO-8859-1?Q?Rapha=EBl_Dupont?=", "Raphaël Dupont"}, + {"Jean", "Jean"}, + {"=?utf-8?b?IkFudG9uaW8gSm9zw6kiIDxqb3NlQGV4YW1wbGUub3JnPg==?=", `"Antonio José" `}, + {"=?UTF-8?A?Test?=", "=?UTF-8?A?Test?="}, + {"=?UTF-8?Q?A=B?=", "=?UTF-8?Q?A=B?="}, + {"=?UTF-8?Q?=A?=", "=?UTF-8?Q?=A?="}, + {"=?UTF-8?A?A?=", "=?UTF-8?A?A?="}, + // Incomplete words + {"=?", "=?"}, + {"=?UTF-8?", "=?UTF-8?"}, + {"=?UTF-8?=", "=?UTF-8?="}, + {"=?UTF-8?Q", "=?UTF-8?Q"}, + {"=?UTF-8?Q?", "=?UTF-8?Q?"}, + {"=?UTF-8?Q?=", "=?UTF-8?Q?="}, + {"=?UTF-8?Q?A", "=?UTF-8?Q?A"}, + {"=?UTF-8?Q?A?", "=?UTF-8?Q?A?"}, + // Tests from RFC 2047 + {"=?ISO-8859-1?Q?a?=", "a"}, + {"=?ISO-8859-1?Q?a?= b", "a b"}, + {"=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=", "ab"}, + {"=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=", "ab"}, + {"=?ISO-8859-1?Q?a?= \r\n\t =?ISO-8859-1?Q?b?=", "ab"}, + {"=?ISO-8859-1?Q?a_b?=", "a b"}, + } + + for _, test := range tests { + dec := new(WordDecoder) + s, err := dec.DecodeHeader(test.src) + if err != nil { + t.Errorf("DecodeHeader(%q): %v", test.src, err) + } + if s != test.exp { + t.Errorf("DecodeHeader(%q) = %q, want %q", test.src, s, test.exp) + } + } +} + +func TestCharsetDecoder(t *testing.T) { + tests := []struct { + src string + want string + charsets []string + content []string + }{ + {"=?utf-8?b?Q2Fmw6k=?=", "Café", nil, nil}, + {"=?ISO-8859-1?Q?caf=E9?=", "café", nil, nil}, + {"=?US-ASCII?Q?foo_bar?=", "foo bar", nil, nil}, + {"=?utf-8?Q?=?=", "=?utf-8?Q?=?=", nil, nil}, + {"=?utf-8?Q?=A?=", "=?utf-8?Q?=A?=", nil, nil}, + { + "=?ISO-8859-15?Q?f=F5=F6?= =?windows-1252?Q?b=E0r?=", + "f\xf5\xf6b\xe0r", + []string{"iso-8859-15", "windows-1252"}, + []string{"f\xf5\xf6", "b\xe0r"}, + }, + } + + for _, test := range tests { + i := 0 + dec := &WordDecoder{ + CharsetReader: func(charset string, input io.Reader) (io.Reader, error) { + if charset != test.charsets[i] { + t.Errorf("DecodeHeader(%q), got charset %q, want %q", test.src, charset, test.charsets[i]) + } + content, err := io.ReadAll(input) + if err != nil { + t.Errorf("DecodeHeader(%q), error in reader: %v", test.src, err) + } + got := string(content) + if got != test.content[i] { + t.Errorf("DecodeHeader(%q), got content %q, want %q", test.src, got, test.content[i]) + } + i++ + + return strings.NewReader(got), nil + }, + } + got, err := dec.DecodeHeader(test.src) + if err != nil { + t.Errorf("DecodeHeader(%q): %v", test.src, err) + } + if got != test.want { + t.Errorf("DecodeHeader(%q) = %q, want %q", test.src, got, test.want) + } + } +} + +func TestCharsetDecoderError(t *testing.T) { + dec := &WordDecoder{ + CharsetReader: func(charset string, input io.Reader) (io.Reader, error) { + return nil, errors.New("Test error") + }, + } + + if _, err := dec.DecodeHeader("=?charset?Q?foo?="); err == nil { + t.Error("DecodeHeader should return an error") + } +} + +func BenchmarkQEncodeWord(b *testing.B) { + for i := 0; i < b.N; i++ { + QEncoding.Encode("UTF-8", "¡Hola, señor!") + } +} + +func BenchmarkQDecodeWord(b *testing.B) { + dec := new(WordDecoder) + + for i := 0; i < b.N; i++ { + dec.Decode("=?utf-8?q?=C2=A1Hola,_se=C3=B1or!?=") + } +} + +func BenchmarkQDecodeHeader(b *testing.B) { + dec := new(WordDecoder) + + for i := 0; i < b.N; i++ { + dec.DecodeHeader("=?utf-8?q?=C2=A1Hola,_se=C3=B1or!?=") + } +} -- cgit v1.2.3