2017-01-02 23:51:19 +08:00
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from nl_processor import as_processor
|
|
|
|
|
|
|
|
|
|
_query_lang_matcher = [
|
2017-01-03 01:06:11 +08:00
|
|
|
|
re.compile('[把将]?[\s,.,。]?(.*?)[\s,.,。]?(?:这[个]?(?:词[组]?|句(?:子|话)?|短语))?翻译[成为到](\w+?[文语])(?![\s::,,.。])'),
|
|
|
|
|
re.compile('(\w+?)[\s,.,。]?(?:这[个]?(?:词[组]?|句(?:子|话)?|短语))?[的用](\w+?[文语])')
|
2017-01-02 23:51:19 +08:00
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
_lang_query_matcher = [
|
2017-01-03 01:06:11 +08:00
|
|
|
|
re.compile('.*[把将]?(?:(?:这[个]?|[下后][面]?)(?:词[组]?|句(?:子|话)?|短语))?翻译[成为到]\s*(\w+?[文语])[\s::,,](.*)'),
|
2017-01-02 23:51:19 +08:00
|
|
|
|
re.compile('[用]?(\w+[文语])\w+?(?:说|讲|表达|表示)(.*)(?:这[个]?(?:词[组]?|句(?:子|话)?|短语))'),
|
2017-01-03 01:06:11 +08:00
|
|
|
|
re.compile('[用]?(\w+[文语])\w+?(?:说|讲|表达|表示)(.*)'),
|
2017-01-02 23:51:19 +08:00
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@as_processor(keywords=('翻译(为|成|到)?', '.+(文|语)'))
|
|
|
|
|
def _processor(sentence, segmentation):
|
|
|
|
|
lang = None
|
|
|
|
|
query = None
|
|
|
|
|
for matcher in _query_lang_matcher + _lang_query_matcher:
|
|
|
|
|
m = matcher.match(sentence)
|
|
|
|
|
if m:
|
|
|
|
|
if matcher in _lang_query_matcher:
|
|
|
|
|
lang, query = m.group(1), m.group(2)
|
|
|
|
|
else:
|
|
|
|
|
lang, query = m.group(2), m.group(1)
|
|
|
|
|
break
|
|
|
|
|
if lang and query:
|
2017-01-03 01:06:11 +08:00
|
|
|
|
print('翻译: 目标语言:', lang, ', 待翻译文本:', query)
|
2017-01-02 23:51:19 +08:00
|
|
|
|
return 90, 'translate.translate_to', ' '.join((lang.strip(), query.strip(' ,,'))), None
|
|
|
|
|
return None
|