aozora2html 0.7.0 → 2.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.github/workflows/ruby.yml +34 -0
- data/.gitignore +8 -3
- data/.rubocop.yml +227 -0
- data/.travis.yml +5 -0
- data/CHANGELOG.md +33 -0
- data/LICENSE +116 -0
- data/README.md +16 -11
- data/aozora2html.gemspec +6 -6
- data/bin/aozora2html +6 -54
- data/lib/aozora2html/accent_parser.rb +91 -0
- data/lib/aozora2html/error.rb +16 -0
- data/lib/aozora2html/header.rb +139 -0
- data/lib/aozora2html/i18n.rb +28 -0
- data/lib/aozora2html/ruby_buffer.rb +81 -0
- data/lib/aozora2html/style_stack.rb +27 -0
- data/lib/aozora2html/tag/accent.rb +39 -0
- data/lib/aozora2html/tag/block.rb +19 -0
- data/lib/aozora2html/tag/chitsuki.rb +15 -0
- data/lib/aozora2html/tag/dakuten_katakana.rb +23 -0
- data/lib/aozora2html/tag/decorate.rb +18 -0
- data/lib/aozora2html/tag/dir.rb +15 -0
- data/lib/aozora2html/tag/editor_note.rb +16 -0
- data/lib/aozora2html/tag/embed_gaiji.rb +48 -0
- data/lib/aozora2html/tag/font_size.rb +17 -0
- data/lib/aozora2html/tag/gaiji.rb +11 -0
- data/lib/aozora2html/tag/img.rb +21 -0
- data/lib/aozora2html/tag/indent.rb +8 -0
- data/lib/aozora2html/tag/inline.rb +13 -0
- data/lib/aozora2html/tag/inline_caption.rb +15 -0
- data/lib/aozora2html/tag/inline_font_size.rb +18 -0
- data/lib/aozora2html/tag/inline_keigakomi.rb +15 -0
- data/lib/aozora2html/tag/inline_yokogumi.rb +16 -0
- data/lib/aozora2html/tag/jisage.rb +15 -0
- data/lib/aozora2html/tag/jizume.rb +16 -0
- data/lib/aozora2html/tag/kaeriten.rb +15 -0
- data/lib/aozora2html/tag/keigakomi.rb +13 -0
- data/lib/aozora2html/tag/kunten.rb +12 -0
- data/lib/aozora2html/tag/midashi.rb +18 -0
- data/lib/aozora2html/tag/multiline.rb +6 -0
- data/lib/aozora2html/tag/multiline_caption.rb +15 -0
- data/lib/aozora2html/tag/multiline_chitsuki.rb +8 -0
- data/lib/aozora2html/tag/multiline_jisage.rb +8 -0
- data/lib/aozora2html/tag/multiline_midashi.rb +22 -0
- data/lib/aozora2html/tag/multiline_style.rb +17 -0
- data/lib/aozora2html/tag/multiline_yokogumi.rb +17 -0
- data/lib/aozora2html/tag/okurigana.rb +15 -0
- data/lib/aozora2html/tag/oneline_chitsuki.rb +9 -0
- data/lib/aozora2html/tag/oneline_indent.rb +2 -0
- data/lib/aozora2html/tag/oneline_jisage.rb +7 -0
- data/lib/aozora2html/tag/reference_mentioned.rb +46 -0
- data/lib/aozora2html/tag/ruby.rb +98 -0
- data/lib/aozora2html/tag/un_embed_gaiji.rb +24 -0
- data/lib/aozora2html/tag.rb +55 -0
- data/lib/aozora2html/tag_parser.rb +53 -0
- data/lib/aozora2html/utils.rb +93 -0
- data/lib/aozora2html/version.rb +1 -1
- data/lib/aozora2html/yaml_loader.rb +31 -0
- data/lib/aozora2html.rb +0 -4
- data/lib/extensions.rb +44 -0
- data/lib/jstream.rb +68 -0
- data/lib/t2hs.rb +837 -1765
- data/test/test_aozora2html.rb +320 -43
- data/test/test_aozora_accent_parser.rb +13 -2
- data/test/test_command_parse.rb +213 -0
- data/test/test_dakuten_katakana_tag.rb +5 -4
- data/test/test_decorate_tag.rb +5 -4
- data/test/test_dir_tag.rb +5 -4
- data/test/test_editor_note_tag.rb +4 -4
- data/test/test_exception.rb +4 -4
- data/test/test_font_size_tag.rb +15 -7
- data/test/test_gaiji_tag.rb +14 -7
- data/test/test_header.rb +60 -0
- data/test/test_i18n.rb +23 -0
- data/test/test_img_tag.rb +5 -4
- data/test/test_inline_caption_tag.rb +5 -4
- data/test/test_inline_font_size_tag.rb +7 -6
- data/test/test_inline_keigakomi_tag.rb +5 -4
- data/test/test_inline_yokogumi_tag.rb +5 -4
- data/test/test_jizume_tag.rb +7 -6
- data/test/test_jstream.rb +5 -5
- data/test/test_kaeriten_tag.rb +5 -4
- data/test/test_keigakomi_tag.rb +8 -7
- data/test/test_midashi_tag.rb +38 -0
- data/test/test_multiline_caption_tag.rb +7 -6
- data/test/test_multiline_midashi_tag.rb +24 -7
- data/test/test_multiline_style_tag.rb +7 -6
- data/test/test_multiline_yokogumi_tag.rb +7 -6
- data/test/test_okurigana_tag.rb +5 -4
- data/test/test_ruby_parse.rb +130 -0
- data/test/test_ruby_tag.rb +5 -4
- data/test/test_tag_parser.rb +10 -10
- data/vendor/jis2ucs/README.md +3 -6
- data/yml/accent_table.yml +240 -0
- data/yml/command_table.yml +61 -0
- data/yml/jis2ucs.yml +11234 -0
- metadata +74 -42
- data/appveyor.yml +0 -19
- data/lib/accent_tag.rb +0 -23
- data/lib/aozora2html/jis2ucs.rb +0 -11237
- data/lib/embed_gaiji_tag.rb +0 -34
data/test/test_aozora2html.rb
CHANGED
@@ -6,6 +6,9 @@ require 'tmpdir'
|
|
6
6
|
|
7
7
|
class Aozora2HtmlTest < Test::Unit::TestCase
|
8
8
|
def setup
|
9
|
+
input = StringIO.new("abc\r\n")
|
10
|
+
output = StringIO.new
|
11
|
+
@parser = Aozora2Html.new(input, output)
|
9
12
|
end
|
10
13
|
|
11
14
|
def test_aozora2html_new
|
@@ -22,7 +25,7 @@ class Aozora2HtmlTest < Test::Unit::TestCase
|
|
22
25
|
end
|
23
26
|
end
|
24
27
|
|
25
|
-
def
|
28
|
+
def test_line_number
|
26
29
|
Dir.mktmpdir do |dir|
|
27
30
|
input = File.join(dir,'dummy.txt')
|
28
31
|
output = File.join(dir,'dummy2.txt')
|
@@ -30,73 +33,347 @@ class Aozora2HtmlTest < Test::Unit::TestCase
|
|
30
33
|
parser = Aozora2Html.new(input, output)
|
31
34
|
|
32
35
|
begin
|
33
|
-
assert_equal 0, parser.
|
36
|
+
assert_equal 0, parser.line_number
|
34
37
|
ch = parser.read_char
|
35
38
|
assert_equal "a",ch
|
36
|
-
assert_equal 1, parser.
|
39
|
+
assert_equal 1, parser.line_number
|
37
40
|
ch = parser.read_char
|
38
41
|
assert_equal "\r\n",ch
|
39
|
-
assert_equal 1, parser.
|
42
|
+
assert_equal 1, parser.line_number
|
40
43
|
ch = parser.read_char
|
41
44
|
assert_equal "b",ch
|
42
|
-
assert_equal 2, parser.
|
45
|
+
assert_equal 2, parser.line_number
|
43
46
|
ch = parser.read_char
|
44
47
|
assert_equal "\r\n",ch
|
45
|
-
assert_equal 2, parser.
|
48
|
+
assert_equal 2, parser.line_number
|
46
49
|
ch = parser.read_char
|
47
50
|
assert_equal "c",ch
|
48
|
-
assert_equal 3, parser.
|
51
|
+
assert_equal 3, parser.line_number
|
49
52
|
ensure
|
50
53
|
parser.close
|
51
54
|
end
|
52
55
|
end
|
53
56
|
end
|
54
57
|
|
58
|
+
def test_line_number_2
|
59
|
+
input = StringIO.new("a\r\nb\r\nc\r\n")
|
60
|
+
output = StringIO.new
|
61
|
+
parser = Aozora2Html.new(input, output)
|
62
|
+
assert_equal 0, parser.line_number
|
63
|
+
ch = parser.read_char
|
64
|
+
assert_equal "a",ch
|
65
|
+
assert_equal 1, parser.line_number
|
66
|
+
ch = parser.read_char
|
67
|
+
assert_equal "\r\n",ch
|
68
|
+
assert_equal 1, parser.line_number
|
69
|
+
ch = parser.read_char
|
70
|
+
assert_equal "b",ch
|
71
|
+
assert_equal 2, parser.line_number
|
72
|
+
ch = parser.read_char
|
73
|
+
assert_equal "\r\n",ch
|
74
|
+
assert_equal 2, parser.line_number
|
75
|
+
ch = parser.read_char
|
76
|
+
assert_equal "c",ch
|
77
|
+
assert_equal 3, parser.line_number
|
78
|
+
end
|
79
|
+
|
55
80
|
def test_read_line
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
begin
|
62
|
-
parsed = parser.read_line
|
63
|
-
assert_equal "ab", parsed
|
64
|
-
ensure
|
65
|
-
parser.close
|
66
|
-
end
|
67
|
-
end
|
81
|
+
input = StringIO.new("ab\r\nc\r\n")
|
82
|
+
output = StringIO.new
|
83
|
+
parser = Aozora2Html.new(input, output)
|
84
|
+
parsed = parser.read_line
|
85
|
+
assert_equal "ab", parsed
|
68
86
|
end
|
69
87
|
|
70
88
|
def test_char_type
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
89
|
+
assert_equal :kanji, @parser.char_type(Aozora2Html::Tag::EmbedGaiji.new(nil,"foo","1-2-3","name"))
|
90
|
+
assert_equal :kanji, @parser.char_type(Aozora2Html::Tag::UnEmbedGaiji.new(nil,"foo"))
|
91
|
+
assert_equal :hankaku, @parser.char_type(Aozora2Html::Tag::Accent.new(nil,123,"abc"))
|
92
|
+
assert_equal :else, @parser.char_type(Aozora2Html::Tag::Okurigana.new(nil,"abc"))
|
93
|
+
assert_equal :else, @parser.char_type(Aozora2Html::Tag::InlineKeigakomi.new(nil,"abc"))
|
94
|
+
assert_equal :katakana, @parser.char_type(Aozora2Html::Tag::DakutenKatakana.new(nil,1,"abc"))
|
76
95
|
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
+
assert_equal :hiragana, @parser.char_type("あ".encode("shift_jis"))
|
97
|
+
assert_equal :hiragana, @parser.char_type("っ".encode("shift_jis"))
|
98
|
+
assert_equal :katakana, @parser.char_type("ヴ".encode("shift_jis"))
|
99
|
+
assert_equal :katakana, @parser.char_type("ー".encode("shift_jis"))
|
100
|
+
assert_equal :zenkaku, @parser.char_type("A".encode("shift_jis"))
|
101
|
+
assert_equal :zenkaku, @parser.char_type("w".encode("shift_jis"))
|
102
|
+
assert_equal :hankaku, @parser.char_type("z".encode("shift_jis"))
|
103
|
+
assert_equal :kanji, @parser.char_type("漢".encode("shift_jis"))
|
104
|
+
assert_equal :hankaku_terminate, @parser.char_type("!".encode("shift_jis"))
|
105
|
+
assert_equal :else, @parser.char_type("?".encode("shift_jis"))
|
106
|
+
assert_equal :else, @parser.char_type("Å".encode("shift_jis"))
|
107
|
+
end
|
108
|
+
|
109
|
+
def test_read_char
|
110
|
+
input = StringIO.new("/\\r\n".encode("shift_jis"))
|
111
|
+
output = StringIO.new
|
112
|
+
parser = Aozora2Html.new(input, output)
|
113
|
+
char = parser.read_char
|
114
|
+
assert_equal "/".encode("shift_jis"), char
|
115
|
+
assert_equal Aozora2Html::KU, char
|
116
|
+
end
|
117
|
+
|
118
|
+
def test_illegal_char_check
|
119
|
+
input = StringIO.new("abc\r\n")
|
120
|
+
output = StringIO.new
|
121
|
+
parser = Aozora2Html.new(input, output)
|
122
|
+
out = StringIO.new
|
123
|
+
$stdout = out
|
124
|
+
begin
|
125
|
+
parser.illegal_char_check("#", 123)
|
126
|
+
outstr = out.string
|
127
|
+
assert_equal "警告(123行目):1バイトの「#」が使われています\n", outstr.encode("utf-8")
|
128
|
+
ensure
|
129
|
+
$stdout = STDOUT
|
130
|
+
end
|
131
|
+
end
|
132
|
+
|
133
|
+
def test_illegal_char_check_sharp
|
134
|
+
input = StringIO.new("abc\r\n")
|
135
|
+
output = StringIO.new
|
136
|
+
parser = Aozora2Html.new(input, output)
|
137
|
+
out = StringIO.new
|
138
|
+
$stdout = out
|
139
|
+
begin
|
140
|
+
parser.illegal_char_check("♯".encode("shift_jis"), 123)
|
141
|
+
outstr = out.string
|
142
|
+
assert_equal "警告(123行目):注記記号の誤用の可能性がある、「♯」が使われています\n", outstr.encode("utf-8")
|
143
|
+
ensure
|
144
|
+
$stdout = STDOUT
|
145
|
+
end
|
146
|
+
end
|
147
|
+
|
148
|
+
def test_illegal_char_check_notjis
|
149
|
+
input = StringIO.new("abc\r\n")
|
150
|
+
output = StringIO.new
|
151
|
+
parser = Aozora2Html.new(input, output)
|
152
|
+
out = StringIO.new
|
153
|
+
$stdout = out
|
154
|
+
begin
|
155
|
+
parser.illegal_char_check("①".encode("cp932").force_encoding("shift_jis"), 123)
|
156
|
+
outstr = out.string
|
157
|
+
assert_equal "警告(123行目):JIS外字「①」が使われています\n", outstr.force_encoding("cp932").encode("utf-8")
|
158
|
+
ensure
|
159
|
+
$stdout = STDOUT
|
160
|
+
end
|
161
|
+
end
|
162
|
+
|
163
|
+
def test_illegal_char_check_ok
|
164
|
+
input = StringIO.new("abc\r\n")
|
165
|
+
output = StringIO.new
|
166
|
+
parser = Aozora2Html.new(input, output)
|
167
|
+
out = StringIO.new
|
168
|
+
$stdout = out
|
169
|
+
begin
|
170
|
+
parser.illegal_char_check("あ".encode("shift_jis"), 123)
|
171
|
+
outstr = output.string
|
172
|
+
assert_equal "", outstr
|
173
|
+
ensure
|
174
|
+
$stdout = STDOUT
|
175
|
+
end
|
176
|
+
end
|
177
|
+
|
178
|
+
def test_convert_japanese_number
|
179
|
+
assert_equal "3字下げ",
|
180
|
+
Aozora2Html::Utils.convert_japanese_number("三字下げ".encode("shift_jis")).encode("utf-8")
|
181
|
+
assert_equal "10字下げ",
|
182
|
+
Aozora2Html::Utils.convert_japanese_number("十字下げ".encode("shift_jis")).encode("utf-8")
|
183
|
+
assert_equal "12字下げ",
|
184
|
+
Aozora2Html::Utils.convert_japanese_number("十二字下げ".encode("shift_jis")).encode("utf-8")
|
185
|
+
assert_equal "20字下げ",
|
186
|
+
Aozora2Html::Utils.convert_japanese_number("二十字下げ".encode("shift_jis")).encode("utf-8")
|
187
|
+
assert_equal "20字下げ",
|
188
|
+
Aozora2Html::Utils.convert_japanese_number("二〇字下げ".encode("shift_jis")).encode("utf-8")
|
189
|
+
assert_equal "23字下げ",
|
190
|
+
Aozora2Html::Utils.convert_japanese_number("二十三字下げ".encode("shift_jis")).encode("utf-8")
|
191
|
+
assert_equal "2字下げ",
|
192
|
+
Aozora2Html::Utils.convert_japanese_number("2字下げ".encode("shift_jis")).encode("utf-8")
|
193
|
+
|
194
|
+
end
|
195
|
+
|
196
|
+
def test_kuten2png
|
197
|
+
assert_equal %q|<img src="../../../gaiji/1-84/1-84-77.png" alt="※(「てへん+劣」、第3水準1-84-77)" class="gaiji" />|,
|
198
|
+
@parser.kuten2png("#「てへん+劣」、第3水準1-84-77".encode("shift_jis")).to_s.encode("utf-8")
|
199
|
+
assert_equal %q|<img src="../../../gaiji/1-02/1-02-22.png" alt="※(二の字点、1-2-22)" class="gaiji" />|,
|
200
|
+
@parser.kuten2png("#二の字点、1-2-22".encode("shift_jis")).to_s.encode("utf-8")
|
201
|
+
assert_equal %q|<img src="../../../gaiji/1-06/1-06-57.png" alt="※(ファイナルシグマ、1-6-57)" class="gaiji" />|,
|
202
|
+
@parser.kuten2png("#ファイナルシグマ、1-6-57".encode("shift_jis")).to_s.encode("utf-8")
|
203
|
+
assert_equal %q|#「口+世」、151-23|,
|
204
|
+
@parser.kuten2png("#「口+世」、151-23".encode("shift_jis")).to_s.encode("utf-8")
|
205
|
+
end
|
206
|
+
|
207
|
+
def test_terpri?
|
208
|
+
assert_equal true, @parser.terpri?([])
|
209
|
+
assert_equal true, @parser.terpri?([""])
|
210
|
+
assert_equal true, @parser.terpri?(["a"])
|
211
|
+
tag = Aozora2Html::Tag::MultilineMidashi.new(@parser,"小".encode("shift_jis"),:normal)
|
212
|
+
assert_equal false, @parser.terpri?([tag])
|
213
|
+
assert_equal false, @parser.terpri?([tag,tag])
|
214
|
+
assert_equal false, @parser.terpri?([tag,"",""])
|
215
|
+
assert_equal false, @parser.terpri?(["",tag,""])
|
216
|
+
assert_equal true, @parser.terpri?([tag,"a"])
|
217
|
+
assert_equal true, @parser.terpri?(["a",tag])
|
218
|
+
end
|
219
|
+
|
220
|
+
def test_new_midashi_id
|
221
|
+
midashi_id = @parser.new_midashi_id(1)
|
222
|
+
assert_equal midashi_id + 1, @parser.new_midashi_id(1)
|
223
|
+
assert_equal midashi_id + 2, @parser.new_midashi_id("小".encode("shift_jis"))
|
224
|
+
assert_equal midashi_id + 12, @parser.new_midashi_id("中".encode("shift_jis"))
|
225
|
+
assert_equal midashi_id + 112, @parser.new_midashi_id("大".encode("shift_jis"))
|
226
|
+
assert_raise(Aozora2Html::Error) do
|
227
|
+
@parser.new_midashi_id("?".encode("shift_jis"))
|
228
|
+
end
|
229
|
+
end
|
230
|
+
|
231
|
+
def test_multiply
|
232
|
+
bouki = @parser.multiply("x", 5)
|
233
|
+
assert_equal "x x x x x", bouki
|
234
|
+
end
|
235
|
+
|
236
|
+
def test_apply_midashi
|
237
|
+
midashi = @parser.apply_midashi("中見出し".encode("shift_jis"))
|
238
|
+
assert_equal %Q|<h4 class="naka-midashi"><a class="midashi_anchor" id="midashi10">|, midashi.to_s
|
239
|
+
midashi = @parser.apply_midashi("大見出し".encode("shift_jis"))
|
240
|
+
assert_equal %Q|<h3 class="o-midashi"><a class="midashi_anchor" id="midashi110">|, midashi.to_s
|
241
|
+
end
|
242
|
+
|
243
|
+
def test_detect_command_mode
|
244
|
+
command = "字下げ終わり".encode("shift_jis")
|
245
|
+
assert_equal :jisage, @parser.detect_command_mode(command)
|
246
|
+
command = "地付き終わり".encode("shift_jis")
|
247
|
+
assert_equal :chitsuki, @parser.detect_command_mode(command)
|
248
|
+
command = "中見出し終わり".encode("shift_jis")
|
249
|
+
assert_equal :midashi, @parser.detect_command_mode(command)
|
250
|
+
command = "ここで太字終わり".encode("shift_jis")
|
251
|
+
assert_equal :futoji, @parser.detect_command_mode(command)
|
252
|
+
end
|
253
|
+
|
254
|
+
def test_tcy
|
255
|
+
input = StringIO.new("[#縦中横](※[#ローマ数字1、1-13-21])\r\n".encode("shift_jis"))
|
256
|
+
output = StringIO.new
|
257
|
+
parser = Aozora2Html.new(input, output)
|
258
|
+
out = StringIO.new
|
259
|
+
$stdout = out
|
260
|
+
message = nil
|
261
|
+
begin
|
262
|
+
parser.parse_body
|
263
|
+
parser.general_output
|
264
|
+
rescue Aozora2Html::Error => e
|
265
|
+
message = e.message.encode("utf-8")
|
266
|
+
ensure
|
267
|
+
$stdout = STDOUT
|
268
|
+
assert_equal "エラー(0行目):縦中横中に改行されました。改行をまたぐ要素にはブロック表記を用いてください. \r\n処理を停止します", message
|
269
|
+
end
|
270
|
+
end
|
271
|
+
|
272
|
+
def test_ensure_close
|
273
|
+
input = StringIO.new("[#ここから5字下げ]\r\n底本: test\r\n".encode("shift_jis"))
|
274
|
+
output = StringIO.new
|
275
|
+
parser = Aozora2Html.new(input, output)
|
276
|
+
out = StringIO.new
|
277
|
+
$stdout = out
|
278
|
+
message = nil
|
279
|
+
begin
|
280
|
+
parser.parse_body
|
281
|
+
parser.parse_body
|
282
|
+
parser.parse_body
|
283
|
+
parser.general_output
|
284
|
+
rescue Aozora2Html::Error => e
|
285
|
+
message = e.message.encode("utf-8")
|
286
|
+
ensure
|
287
|
+
$stdout = STDOUT
|
288
|
+
assert_equal "エラー(0行目):字下げ中に本文が終了しました. \r\n処理を停止します", message
|
289
|
+
end
|
290
|
+
end
|
291
|
+
|
292
|
+
def test_ending_check
|
293
|
+
input = StringIO.new("本文\r\n\r\n底本:test\r\n".encode("shift_jis"))
|
294
|
+
output = StringIO.new
|
295
|
+
parser = Aozora2Html.new(input, output)
|
296
|
+
out = StringIO.new
|
297
|
+
$stdout = out
|
298
|
+
_message = nil
|
299
|
+
begin
|
300
|
+
parser.parse_body
|
301
|
+
parser.parse_body
|
302
|
+
parser.parse_body
|
303
|
+
parser.parse_body
|
304
|
+
parser.parse_body
|
305
|
+
rescue Aozora2Html::Error => e
|
306
|
+
_message = e.message.encode("utf-8")
|
307
|
+
ensure
|
308
|
+
$stdout = STDOUT
|
309
|
+
output.seek(0)
|
310
|
+
out_text = output.read
|
311
|
+
assert_equal "本文<br />\r\n<br />\r\n</div>\r\n<div class=\"bibliographical_information\">\r\n<hr />\r\n<br />\r\n", out_text
|
312
|
+
end
|
313
|
+
end
|
314
|
+
|
315
|
+
def test_invalid_closing
|
316
|
+
input = StringIO.new("[#ここで太字終わり]\r\n".encode("shift_jis"))
|
317
|
+
output = StringIO.new
|
318
|
+
parser = Aozora2Html.new(input, output)
|
319
|
+
out = StringIO.new
|
320
|
+
$stdout = out
|
321
|
+
message = nil
|
322
|
+
begin
|
323
|
+
parser.parse_body
|
324
|
+
rescue Aozora2Html::Error => e
|
325
|
+
message = e.message.encode("utf-8")
|
326
|
+
ensure
|
327
|
+
$stdout = STDOUT
|
328
|
+
assert_equal "エラー(0行目):太字を閉じようとしましたが、太字中ではありません. \r\n処理を停止します", message
|
329
|
+
end
|
330
|
+
end
|
331
|
+
|
332
|
+
def test_invalid_nest
|
333
|
+
input = StringIO.new("[#太字][#傍線]あ[#太字終わり]\r\n".encode("shift_jis"))
|
334
|
+
output = StringIO.new
|
335
|
+
parser = Aozora2Html.new(input, output)
|
336
|
+
out = StringIO.new
|
337
|
+
$stdout = out
|
338
|
+
message = nil
|
339
|
+
begin
|
340
|
+
parser.parse_body
|
341
|
+
parser.parse_body
|
342
|
+
parser.parse_body
|
343
|
+
parser.parse_body
|
344
|
+
parser.parse_body
|
345
|
+
parser.parse_body
|
346
|
+
parser.parse_body
|
347
|
+
rescue Aozora2Html::Error => e
|
348
|
+
message = e.message.encode("utf-8")
|
349
|
+
ensure
|
350
|
+
$stdout = STDOUT
|
351
|
+
assert_equal "エラー(0行目):太字を終了しようとしましたが、傍線中です. \r\n処理を停止します", message
|
352
|
+
end
|
353
|
+
end
|
354
|
+
|
355
|
+
def test_command_do
|
356
|
+
input = StringIO.new("[#ここから太字]\r\nテスト。\r\n[#ここで太字終わり]\r\n".encode("shift_jis"))
|
357
|
+
output = StringIO.new
|
358
|
+
parser = Aozora2Html.new(input, output)
|
359
|
+
out = StringIO.new
|
360
|
+
$stdout = out
|
361
|
+
_message = nil
|
362
|
+
begin
|
363
|
+
9.times do
|
364
|
+
parser.parse_body
|
96
365
|
end
|
366
|
+
rescue Aozora2Html::Error => e
|
367
|
+
_message = e.message.encode("utf-8")
|
368
|
+
ensure
|
369
|
+
$stdout = STDOUT
|
370
|
+
output.seek(0)
|
371
|
+
out_text = output.read
|
372
|
+
assert_equal "<div class=\"futoji\">\r\nテスト。<br />\r\n</div>\r\n", out_text
|
97
373
|
end
|
98
374
|
end
|
99
375
|
|
376
|
+
|
100
377
|
def teardown
|
101
378
|
end
|
102
379
|
end
|
@@ -2,7 +2,7 @@
|
|
2
2
|
require 'test_helper'
|
3
3
|
require 'aozora2html'
|
4
4
|
|
5
|
-
class
|
5
|
+
class Aozora2HtmlAccentParserTest < Test::Unit::TestCase
|
6
6
|
def setup
|
7
7
|
end
|
8
8
|
|
@@ -10,11 +10,22 @@ class Aozora2HtmlTest < Test::Unit::TestCase
|
|
10
10
|
str = "〔e'tiquette〕\r\n".encode("shift_jis")
|
11
11
|
strio = StringIO.new(str)
|
12
12
|
stream = Jstream.new(strio)
|
13
|
-
parsed =
|
13
|
+
parsed = Aozora2Html::AccentParser.new(stream,"〕".encode("shift_jis"),{},[]).process
|
14
14
|
expected = "〔<img src=\"../../../gaiji/1-09/1-09-63.png\" alt=\"※(アキュートアクセント付きE小文字)\" class=\"gaiji\" />tiquette"
|
15
15
|
assert_equal expected, parsed.to_s.encode("utf-8")
|
16
16
|
end
|
17
17
|
|
18
|
+
def test_use_jisx0213
|
19
|
+
Aozora2Html::Tag::Accent.use_jisx0213 = true
|
20
|
+
str = "〔e'tiquette〕\r\n".encode("shift_jis")
|
21
|
+
strio = StringIO.new(str)
|
22
|
+
stream = Jstream.new(strio)
|
23
|
+
parsed = Aozora2Html::AccentParser.new(stream,"〕".encode("shift_jis"),{},[]).process
|
24
|
+
expected = "〔étiquette"
|
25
|
+
assert_equal expected, parsed.to_s.encode("utf-8")
|
26
|
+
end
|
27
|
+
|
18
28
|
def teardown
|
29
|
+
Aozora2Html::Tag::Accent.use_jisx0213 = nil
|
19
30
|
end
|
20
31
|
end
|
@@ -0,0 +1,213 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require 'test_helper'
|
3
|
+
require 'aozora2html'
|
4
|
+
|
5
|
+
class CommandParseTest < Test::Unit::TestCase
|
6
|
+
def setup
|
7
|
+
end
|
8
|
+
|
9
|
+
def test_parse_command1
|
10
|
+
src = "デボルド―※[#濁点付き片仮名ワ、1-7-82]ルモオル\r\n"
|
11
|
+
parsed = parse_text(src)
|
12
|
+
expected = "デボルド—<img src=\"../../../gaiji/1-07/1-07-82.png\" alt=\"※(濁点付き片仮名ワ、1-7-82)\" class=\"gaiji\" />ルモオル<br />\r\n"
|
13
|
+
assert_equal expected, parsed
|
14
|
+
end
|
15
|
+
|
16
|
+
def test_parse_command2
|
17
|
+
src = "繁雑な日本の 〔e'tiquette〕 も、\r\n"
|
18
|
+
parsed = parse_text(src)
|
19
|
+
expected = %Q|繁雑な日本の <img src="../../../gaiji/1-09/1-09-63.png" alt="※(アキュートアクセント付きE小文字)" class="gaiji" />tiquette も、<br />\r\n|
|
20
|
+
assert_equal expected, parsed
|
21
|
+
end
|
22
|
+
|
23
|
+
def test_parse_command3
|
24
|
+
src = "〔Sito^t qu'on le touche il re'sonne.〕\r\n"
|
25
|
+
parsed = parse_text(src)
|
26
|
+
expected = %Q|Sit<img src="../../../gaiji/1-09/1-09-74.png" alt="※(サーカムフレックスアクセント付きO小文字)" class="gaiji" />t q<img src="../../../gaiji/1-09/1-09-79.png" alt="※(アキュートアクセント付きU小文字)" class="gaiji" />on le touche il r<img src="../../../gaiji/1-09/1-09-63.png" alt="※(アキュートアクセント付きE小文字)" class="gaiji" />sonne.<br />\r\n|
|
27
|
+
assert_equal expected, parsed
|
28
|
+
end
|
29
|
+
|
30
|
+
def test_parse_command4
|
31
|
+
src = "presqu'〔i^le〕\r\n"
|
32
|
+
parsed = parse_text(src)
|
33
|
+
expected = %Q|presqu'<img src="../../../gaiji/1-09/1-09-68.png" alt="※(サーカムフレックスアクセント付きI小文字)" class="gaiji" />le<br />\r\n|
|
34
|
+
assert_equal expected, parsed
|
35
|
+
end
|
36
|
+
|
37
|
+
def test_parse_command5
|
38
|
+
src = "[二十歳の 〔E'tude〕]\r\n"
|
39
|
+
parsed = parse_text(src)
|
40
|
+
expected = %Q|[二十歳の <img src="../../../gaiji/1-09/1-09-32.png" alt="※(アキュートアクセント付きE)" class="gaiji" />tude]<br />\r\n|
|
41
|
+
assert_equal expected, parsed
|
42
|
+
end
|
43
|
+
|
44
|
+
def test_parse_command6
|
45
|
+
src = "責[#「責」に白ゴマ傍点]空文庫\r\n"
|
46
|
+
parsed = parse_text(src)
|
47
|
+
expected = %Q|<em class="white_sesame_dot">責</em>空文庫<br />\r\n|
|
48
|
+
assert_equal expected, parsed
|
49
|
+
end
|
50
|
+
|
51
|
+
def test_parse_command7
|
52
|
+
src = "[#丸傍点]青空文庫で読書しよう[#丸傍点終わり]。\r\n"
|
53
|
+
parsed = parse_text(src)
|
54
|
+
expected = %Q|<em class="black_circle">青空文庫で読書しよう</em>。<br />\r\n|
|
55
|
+
assert_equal expected, parsed
|
56
|
+
end
|
57
|
+
|
58
|
+
def test_parse_command8
|
59
|
+
src = "この形は傍線[#「傍線」に傍線]と書いてください。\r\n"
|
60
|
+
parsed = parse_text(src)
|
61
|
+
expected = %Q|この形は<em class="underline_solid">傍線</em>と書いてください。<br />\r\n|
|
62
|
+
assert_equal expected, parsed
|
63
|
+
end
|
64
|
+
|
65
|
+
def test_parse_command9
|
66
|
+
src = "[#左に鎖線]青空文庫で読書しよう[#左に鎖線終わり]。\r\n"
|
67
|
+
parsed = parse_text(src)
|
68
|
+
expected = %Q|<em class="overline_dotted">青空文庫で読書しよう</em>。<br />\r\n|
|
69
|
+
assert_equal expected, parsed
|
70
|
+
end
|
71
|
+
|
72
|
+
def test_parse_command10
|
73
|
+
src = "「クリス、宇宙航行委員会が選考[#「選考」は太字]するんだ。きみは志願できない。待つ[#「待つ」は太字]んだ」\r\n"
|
74
|
+
parsed = parse_text(src)
|
75
|
+
expected = %Q|「クリス、宇宙航行委員会が<span class="futoji">選考</span>するんだ。きみは志願できない。<span class="futoji">待つ</span>んだ」<br />\r\n|
|
76
|
+
assert_equal expected, parsed
|
77
|
+
end
|
78
|
+
|
79
|
+
def test_parse_command11
|
80
|
+
src = "Which, teaching us, hath this exordium: Nothing from nothing ever yet was born.[#「Nothing from nothing ever yet was born.」は斜体]\r\n"
|
81
|
+
parsed = parse_text(src)
|
82
|
+
expected = %Q|Which, teaching us, hath this exordium: <span class="shatai">Nothing from nothing ever yet was born.</span><br />\r\n|
|
83
|
+
assert_equal expected, parsed
|
84
|
+
end
|
85
|
+
|
86
|
+
def test_parse_command_warichu
|
87
|
+
src = "[#割り注]価は四百円であった。[#割り注終わり]\r\n"
|
88
|
+
parsed = parse_text(src)
|
89
|
+
expected = %Q|<span class="warichu">(価は四百円であった。)</span><br />\r\n|
|
90
|
+
assert_equal expected, parsed
|
91
|
+
end
|
92
|
+
|
93
|
+
def test_parse_command_warichu2
|
94
|
+
src = "飽海郡南平田村大字飛鳥[#割り注]東は字大林四三七[#改行]西は字神内一一一ノ一[#割り注終わり]\r\n"
|
95
|
+
parsed = parse_text(src)
|
96
|
+
expected = %Q|飽海郡南平田村大字飛鳥<span class="warichu">(東は字大林四三七<span class="notes">[#改行]</span>西は字神内一一一ノ一)</span><br />\r\n|
|
97
|
+
assert_equal expected, parsed
|
98
|
+
end
|
99
|
+
|
100
|
+
def test_parse_command_unicode
|
101
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
102
|
+
src = "※[#「衄のへん+卩」、U+5379、287-2]\r\n"
|
103
|
+
parsed = parse_text(src)
|
104
|
+
expected = "卹<br />\r\n"
|
105
|
+
assert_equal expected, parsed
|
106
|
+
end
|
107
|
+
|
108
|
+
def test_parse_command_teisei1
|
109
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
110
|
+
src = "吹喋[#「喋」に「ママ」の注記]\r\n"
|
111
|
+
parsed = parse_text(src)
|
112
|
+
expected = "吹<ruby><rb>喋</rb><rp>(</rp><rt>ママ</rt><rp>)</rp></ruby><br />\r\n"
|
113
|
+
assert_equal expected, parsed
|
114
|
+
end
|
115
|
+
|
116
|
+
def test_parse_command_teisei2
|
117
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
118
|
+
src = "紋附だとか[#「紋附だとか」は底本では「絞附だとか」]\r\n"
|
119
|
+
parsed = parse_text(src)
|
120
|
+
expected = %Q|紋附だとか<span class="notes">[#「紋附だとか」は底本では「絞附だとか」]</span><br />\r\n|
|
121
|
+
assert_equal expected, parsed
|
122
|
+
end
|
123
|
+
|
124
|
+
def test_parse_command_teisei3
|
125
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
126
|
+
src = "私は籠《ざる》[#ルビの「ざる」は底本では「さる」]をさげ\r\n"
|
127
|
+
parsed = parse_text(src)
|
128
|
+
expected = %Q|私は<ruby><rb>籠</rb><rp>(</rp><rt>ざる</rt><rp>)</rp></ruby><span class="notes">[#ルビの「ざる」は底本では「さる」]</span>をさげ<br />\r\n|
|
129
|
+
assert_equal expected, parsed
|
130
|
+
end
|
131
|
+
|
132
|
+
def test_parse_command_teisei4
|
133
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
134
|
+
src = "広場へに[#「広場へに」はママ]店でもだそう。\r\n"
|
135
|
+
parsed = parse_text(src)
|
136
|
+
expected = %Q|広場へに<span class="notes">[#「広場へに」はママ]</span>店でもだそう。<br />\r\n|
|
137
|
+
assert_equal expected, parsed
|
138
|
+
end
|
139
|
+
|
140
|
+
def test_parse_command_teisei5
|
141
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
142
|
+
src = "お湯《ゆう》[#ルビの「ゆう」はママ]\r\n"
|
143
|
+
parsed = parse_text(src)
|
144
|
+
expected = %Q|お<ruby><rb>湯</rb><rp>(</rp><rt>ゆう</rt><rp>)</rp></ruby><span class="notes">[#ルビの「ゆう」はママ]</span><br />\r\n|
|
145
|
+
assert_equal expected, parsed
|
146
|
+
end
|
147
|
+
|
148
|
+
def test_parse_command_tcy
|
149
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
150
|
+
src = "米機B29[#「29」は縦中横]の編隊は、\r\n"
|
151
|
+
parsed = parse_text(src)
|
152
|
+
expected = %Q|米機B<span dir="ltr">29</span>の編隊は、<br />\r\n|
|
153
|
+
assert_equal expected, parsed
|
154
|
+
end
|
155
|
+
|
156
|
+
def test_parse_command_tcy2
|
157
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
158
|
+
src = "[#縦中横](※[#ローマ数字1、1-13-21])[#縦中横終わり]\r\n"
|
159
|
+
parsed = parse_text(src)
|
160
|
+
expected = %Q|<span dir="ltr">(<img src="../../../gaiji/1-13/1-13-21.png" alt="※(ローマ数字1、1-13-21)" class="gaiji" />)</span><br />\r\n|
|
161
|
+
assert_equal expected, parsed
|
162
|
+
end
|
163
|
+
|
164
|
+
def test_parse_command_kogaki
|
165
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
166
|
+
src = "それ以上である。(5)[#「(5)」は行右小書き]\r\n"
|
167
|
+
parsed = parse_text(src)
|
168
|
+
expected = %Q|それ以上である。<sup class="superscript">(5)</sup><br />\r\n|
|
169
|
+
assert_equal expected, parsed
|
170
|
+
end
|
171
|
+
|
172
|
+
def test_parse_command_uetsuki
|
173
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
174
|
+
src = "22[#「2」は上付き小文字]\r\n"
|
175
|
+
parsed = parse_text(src)
|
176
|
+
expected = %Q|2<sup class="superscript">2</sup><br />\r\n|
|
177
|
+
assert_equal expected, parsed
|
178
|
+
end
|
179
|
+
|
180
|
+
def test_parse_command_bouki
|
181
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
182
|
+
src = "支部長の顔にさっと血が流れ[#「血が流れ」に「×」の傍記]た\r\n"
|
183
|
+
parsed = parse_text(src)
|
184
|
+
expected = %Q|支部長の顔にさっと<ruby><rb>血が流れ</rb><rp>(</rp><rt>× × × ×</rt><rp>)</rp></ruby>た<br />\r\n|
|
185
|
+
assert_equal expected, parsed
|
186
|
+
end
|
187
|
+
|
188
|
+
def test_parse_command_ruby
|
189
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = true
|
190
|
+
src = "グリーンランドの中央部八千尺の氷河地帯にあるといわれる、[#横組み]“Ser-mik-Suah《セルミク・シュアー》”[#横組み終わり]の冥路《よみじ》の国。\r\n"
|
191
|
+
parsed = parse_text(src)
|
192
|
+
expected = %Q|グリーンランドの中央部八千尺の氷河地帯にあるといわれる、<span class=\"yokogumi\">“<ruby><rb>Ser-mik-Suah</rb><rp>(</rp><rt>セルミク・シュアー</rt><rp>)</rp></ruby>”</span>の<ruby><rb>冥路</rb><rp>(</rp><rt>よみじ</rt><rp>)</rp></ruby>の国。<br />\r\n|
|
193
|
+
assert_equal expected, parsed
|
194
|
+
end
|
195
|
+
|
196
|
+
def parse_text(input_text)
|
197
|
+
input = StringIO.new(input_text.encode("shift_jis"))
|
198
|
+
output = StringIO.new
|
199
|
+
parser = Aozora2Html.new(input, output)
|
200
|
+
parser.instance_eval{@section=:tail}
|
201
|
+
catch(:terminate) do
|
202
|
+
loop do
|
203
|
+
parser.parse
|
204
|
+
end
|
205
|
+
end
|
206
|
+
output.string.encode("utf-8")
|
207
|
+
end
|
208
|
+
|
209
|
+
def teardown
|
210
|
+
Aozora2Html::Tag::EmbedGaiji.use_jisx0213 = false
|
211
|
+
Aozora2Html::Tag::EmbedGaiji.use_unicode = false
|
212
|
+
end
|
213
|
+
end
|