本文整理汇总了Python中whoosh.filedb.filestore.FileStorage.writer方法的典型用法代码示例。如果您正苦于以下问题：Python FileStorage.writer方法的具体用法？Python FileStorage.writer怎么用？Python FileStorage.writer使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类whoosh.filedb.filestore.FileStorage的用法示例。
在下文中一共展示了FileStorage.writer方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: TranslationMemory
# 需要导入模块: from whoosh.filedb.filestore import FileStorage [as 别名]
# 或者: from whoosh.filedb.filestore.FileStorage import writer [as 别名]
class TranslationMemory(object):
def __init__(self):
self.index = FileStorage(data_dir('memory')).open_index()
self.parser = qparser.QueryParser(
'source',
schema=self.index.schema,
group=qparser.OrGroup.factory(0.9),
termclass=query.FuzzyTerm,
)
self.searcher = None
self.comparer = Comparer()
def __del__(self):
self.close()
def open_searcher(self):
if self.searcher is None:
self.searcher = self.index.searcher()
def doc_count(self):
self.open_searcher()
return self.searcher.doc_count()
def close(self):
if self.searcher is not None:
self.searcher.close()
self.searcher = None
@contextlib.contextmanager
def writer(self):
writer = self.index.writer()
try:
yield writer
finally:
writer.commit()
def get_language_code(self, code, langmap):
language = Language.objects.auto_get_or_create(code)
if langmap and language.code in langmap:
language = Language.objects.auto_get_or_create(
langmap[language.code]
)
return language.code
def import_tmx(self, fileobj, langmap=None):
origin = force_text(os.path.basename(fileobj.name))
storage = tmxfile.parsefile(fileobj)
header = next(
storage.document.getroot().iterchildren(
storage.namespaced("header")
)
)
source_language_code = header.get('srclang')
source_language = self.get_language_code(source_language_code, langmap)
languages = {}
with self.writer() as writer:
for unit in storage.units:
# Parse translations (translate-toolkit does not care about
# languages here, it just picks first and second XML elements)
translations = {}
for node in unit.getlanguageNodes():
lang, text = get_node_data(unit, node)
translations[lang] = text
if lang not in languages:
languages[lang] = self.get_language_code(lang, langmap)
try:
source = translations.pop(source_language_code)
except KeyError:
# Skip if source language is not present
continue
for lang, text in translations.items():
writer.add_document(
source_language=source_language,
target_language=languages[lang],
source=source,
target=text,
origin=origin,
category=CATEGORY_FILE,
)
def lookup(self, source_language, target_language, text):
langfilter = query.And([
query.Term('source_language', source_language),
query.Term('target_language', target_language),
])
self.open_searcher()
text_query = self.parser.parse(text)
matches = self.searcher.search(
text_query, filter=langfilter, limit=20000
)
for match in matches:
similarity = self.comparer.similarity(text, match['source'])
if similarity < 30:
continue
yield (
match['source'], match['target'], similarity, match['origin']
#.........这里部分代码省略.........