Skip to content

Commit e5f77b9

Browse files
committed
added factory: one2one unicode mapping
1 parent 5db310d commit e5f77b9

File tree

2 files changed

+35
-35
lines changed

2 files changed

+35
-35
lines changed

text_normalizer/factory/strip.py

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -23,7 +23,7 @@ def __init__(
2323
):
2424
if direction not in ['both', 'left', 'right']:
2525
raise ValueError(
26-
'WRONG direction input! '
26+
'Not Supported Yet!!'
2727
'Direction has three options [both, left, right]',
2828
'Your input is {}'.format(direction),
2929
)
@@ -77,17 +77,17 @@ def normalize(
7777
backward_annotations=backward_annotations,
7878
)
7979
return output_str, {
80-
'for': forward_annotations,
81-
'back': backward_annotations,
80+
'forward': forward_annotations,
81+
'backward': backward_annotations,
8282
}
8383

8484
def denormalize(
8585
self,
8686
sentence: str,
8787
meta: dict,
8888
) -> str:
89-
forward_annotations = meta['for']
90-
backward_annotations = meta['back']
89+
forward_annotations = meta['forward']
90+
backward_annotations = meta['backward']
9191
output_str = transform(
9292
input_str=sentence,
9393
forward_annotations=backward_annotations,

text_normalizer/factory/test/test_strip.py

Lines changed: 30 additions & 30 deletions
Original file line numberDiff line numberDiff line change
@@ -47,40 +47,40 @@ def setUpClass(cls):
4747
'input': ' \n\t\n HAHA\t \t \n \n ',
4848
'output': 'HAHA',
4949
'meta': {
50-
'for': [(0, 6, ' \n\t\n H'), (8, 17, 'A\t \t \n \n ')],
51-
'back': [(0, 1, 'H'), (3, 4, 'A')],
50+
'forward': [(0, 6, ' \n\t\n H'), (8, 17, 'A\t \t \n \n ')],
51+
'backward': [(0, 1, 'H'), (3, 4, 'A')],
5252
},
5353
},
5454
{
5555
'input': ' \n \t \t \n',
5656
'output': '',
5757
'meta': {
58-
'for': [(0, 8, ' \n \t \t \n')],
59-
'back': [(0, 0, '')],
58+
'forward': [(0, 8, ' \n \t \t \n')],
59+
'backward': [(0, 0, '')],
6060
},
6161
},
6262
{
6363
'input': '黃金曼特寧好苦QAQ\t\t\n\n ',
6464
'output': '黃金曼特寧好苦QAQ',
6565
'meta': {
66-
'for': [(9, 15, 'Q\t\t\n\n ')],
67-
'back': [(9, 10, 'Q')],
66+
'forward': [(9, 15, 'Q\t\t\n\n ')],
67+
'backward': [(9, 10, 'Q')],
6868
},
6969
},
7070
{
7171
'input': '\t\t \n\n我的空白在前面ㄏㄏ',
7272
'output': '我的空白在前面ㄏㄏ',
7373
'meta': {
74-
'for': [(0, 8, '\t\t \n\n我')],
75-
'back': [(0, 1, '我')],
74+
'forward': [(0, 8, '\t\t \n\n我')],
75+
'backward': [(0, 1, '我')],
7676
},
7777
},
7878
{
7979
'input': '隼興大大是專業HR',
8080
'output': '隼興大大是專業HR',
8181
'meta': {
82-
'for': [],
83-
'back': [],
82+
'forward': [],
83+
'backward': [],
8484
},
8585
},
8686
]
@@ -96,40 +96,40 @@ def setUpClass(cls):
9696
'input': ' \n\t\n HAHA\t \t \n \n ',
9797
'output': 'HAHA\t \t \n \n ',
9898
'meta': {
99-
'for': [(0, 6, ' \n\t\n H')],
100-
'back': [(0, 1, 'H')],
99+
'forward': [(0, 6, ' \n\t\n H')],
100+
'backward': [(0, 1, 'H')],
101101
},
102102
},
103103
{
104104
'input': ' \n \t \t \n',
105105
'output': '',
106106
'meta': {
107-
'for': [(0, 8, ' \n \t \t \n')],
108-
'back': [(0, 0, '')],
107+
'forward': [(0, 8, ' \n \t \t \n')],
108+
'backward': [(0, 0, '')],
109109
},
110110
},
111111
{
112112
'input': '黃金曼特寧好苦QAQ\t\t\n\n ',
113113
'output': '黃金曼特寧好苦QAQ\t\t\n\n ',
114114
'meta': {
115-
'for': [],
116-
'back': [],
115+
'forward': [],
116+
'backward': [],
117117
},
118118
},
119119
{
120120
'input': '\t\t \n\n我的空白在前面ㄏㄏ',
121121
'output': '我的空白在前面ㄏㄏ',
122122
'meta': {
123-
'for': [(0, 8, '\t\t \n\n我')],
124-
'back': [(0, 1, '我')],
123+
'forward': [(0, 8, '\t\t \n\n我')],
124+
'backward': [(0, 1, '我')],
125125
},
126126
},
127127
{
128128
'input': '隼興大大是專業HR',
129129
'output': '隼興大大是專業HR',
130130
'meta': {
131-
'for': [],
132-
'back': [],
131+
'forward': [],
132+
'backward': [],
133133
},
134134
},
135135
]
@@ -145,40 +145,40 @@ def setUpClass(cls):
145145
'input': ' \n\t\n HAHA\t \t \n \n ',
146146
'output': ' \n\t\n HAHA',
147147
'meta': {
148-
'for': [(8, 17, 'A\t \t \n \n ')],
149-
'back': [(8, 9, 'A')],
148+
'forward': [(8, 17, 'A\t \t \n \n ')],
149+
'backward': [(8, 9, 'A')],
150150
},
151151
},
152152
{
153153
'input': ' \n \t \t \n',
154154
'output': '',
155155
'meta': {
156-
'for': [(0, 8, ' \n \t \t \n')],
157-
'back': [(0, 0, '')],
156+
'forward': [(0, 8, ' \n \t \t \n')],
157+
'backward': [(0, 0, '')],
158158
},
159159
},
160160
{
161161
'input': '黃金曼特寧好苦QAQ\t\t\n\n ',
162162
'output': '黃金曼特寧好苦QAQ',
163163
'meta': {
164-
'for': [(9, 15, 'Q\t\t\n\n ')],
165-
'back': [(9, 10, 'Q')],
164+
'forward': [(9, 15, 'Q\t\t\n\n ')],
165+
'backward': [(9, 10, 'Q')],
166166
},
167167
},
168168
{
169169
'input': '\t\t \n\n我的空白在前面ㄏㄏ',
170170
'output': '\t\t \n\n我的空白在前面ㄏㄏ',
171171
'meta': {
172-
'for': [],
173-
'back': [],
172+
'forward': [],
173+
'backward': [],
174174
},
175175
},
176176
{
177177
'input': '隼興大大是專業HR',
178178
'output': '隼興大大是專業HR',
179179
'meta': {
180-
'for': [],
181-
'back': [],
180+
'forward': [],
181+
'backward': [],
182182
},
183183
},
184184
]

0 commit comments

Comments
 (0)