unstructured

Форк
0
139 строк · 2.6 Кб
1
EXPECTED_TABLE = """<table border="1" class="dataframe">
2
  <tbody>
3
    <tr>
4
      <td>Stanley Cups</td>
5
      <td></td>
6
      <td></td>
7
    </tr>
8
    <tr>
9
      <td>Team</td>
10
      <td>Location</td>
11
      <td>Stanley Cups</td>
12
    </tr>
13
    <tr>
14
      <td>Blues</td>
15
      <td>STL</td>
16
      <td>1</td>
17
    </tr>
18
    <tr>
19
      <td>Flyers</td>
20
      <td>PHI</td>
21
      <td>2</td>
22
    </tr>
23
    <tr>
24
      <td>Maple Leafs</td>
25
      <td>TOR</td>
26
      <td>13</td>
27
    </tr>
28
  </tbody>
29
</table>"""
30

31
EXPECTED_TABLE_XLSX = """<table border="1" class="dataframe">
32
  <tbody>
33
    <tr>
34
      <td>Team</td>
35
      <td>Location</td>
36
      <td>Stanley Cups</td>
37
    </tr>
38
    <tr>
39
      <td>Blues</td>
40
      <td>STL</td>
41
      <td>1</td>
42
    </tr>
43
    <tr>
44
      <td>Flyers</td>
45
      <td>PHI</td>
46
      <td>2</td>
47
    </tr>
48
    <tr>
49
      <td>Maple Leafs</td>
50
      <td>TOR</td>
51
      <td>13</td>
52
    </tr>
53
  </tbody>
54
</table>"""
55

56
EXPECTED_TITLE = "Stanley Cups"
57

58
EXPECTED_TEXT = (
59
    "Stanley Cups Team Location Stanley Cups Blues STL 1 Flyers PHI 2 Maple Leafs TOR 13"
60
)
61

62
EXPECTED_TEXT_XLSX = "Team Location Stanley Cups Blues STL 1 Flyers PHI 2 Maple Leafs TOR 13"
63

64
EXPECTED_TEXT_WITH_EMOJI = (
65
    "Stanley Cups "
66
    "Team Location Stanley Cups Blues STL 1 Flyers PHI 2 Maple Leafs TOR 13 👨\\U+1F3FB🔧 TOR 15"
67
)
68

69
EXPECTED_TEXT_SEMICOLON_DELIMITER = (
70
    "Year Month Revenue Costs 2022 1 123 -123 2023 2 143,1 -814,38 2024 3 215,32 -11,08"
71
)
72

73
EXPECTED_TABLE_SEMICOLON_DELIMITER = """<table border="1" class="dataframe">
74
  <tbody>
75
    <tr>
76
      <td>Year</td>
77
      <td>Month</td>
78
      <td>Revenue</td>
79
      <td>Costs</td>
80
      <td></td>
81
    </tr>
82
    <tr>
83
      <td>2022</td>
84
      <td>1</td>
85
      <td>123</td>
86
      <td>-123</td>
87
      <td></td>
88
    </tr>
89
    <tr>
90
      <td>2023</td>
91
      <td>2</td>
92
      <td>143,1</td>
93
      <td>-814,38</td>
94
      <td></td>
95
    </tr>
96
    <tr>
97
      <td>2024</td>
98
      <td>3</td>
99
      <td>215,32</td>
100
      <td>-11,08</td>
101
      <td></td>
102
    </tr>
103
  </tbody>
104
</table>"""
105

106
EXPECTED_TABLE_WITH_EMOJI = """<table border="1" class="dataframe">
107
  <tbody>
108
    <tr>
109
      <td>Stanley Cups</td>
110
      <td></td>
111
      <td></td>
112
    </tr>
113
    <tr>
114
      <td>Team</td>
115
      <td>Location</td>
116
      <td>Stanley Cups</td>
117
    </tr>
118
    <tr>
119
      <td>Blues</td>
120
      <td>STL</td>
121
      <td>1</td>
122
    </tr>
123
    <tr>
124
      <td>Flyers</td>
125
      <td>PHI</td>
126
      <td>2</td>
127
    </tr>
128
    <tr>
129
      <td>Maple Leafs</td>
130
      <td>TOR</td>
131
      <td>13</td>
132
    </tr>
133
    <tr>
134
      <td>👨\\U+1F3FB🔧</td>
135
      <td>TOR</td>
136
      <td>15</td>
137
    </tr>
138
  </tbody>
139
</table>"""
140

Использование cookies

Мы используем файлы cookie в соответствии с Политикой конфиденциальности и Политикой использования cookies.

Нажимая кнопку «Принимаю», Вы даете АО «СберТех» согласие на обработку Ваших персональных данных в целях совершенствования нашего веб-сайта и Сервиса GitVerse, а также повышения удобства их использования.

Запретить использование cookies Вы можете самостоятельно в настройках Вашего браузера.