Python analyse.ChineseAnalyzer方法代碼示例

本文整理匯總了Python中jieba.analyse.ChineseAnalyzer方法的典型用法代碼示例。如果您正苦於以下問題：Python analyse.ChineseAnalyzer方法的具體用法？Python analyse.ChineseAnalyzer怎麽用？Python analyse.ChineseAnalyzer使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類jieba.analyse的用法示例。

在下文中一共展示了analyse.ChineseAnalyzer方法的8個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: init

# 需要導入模塊: from jieba import analyse [as 別名]
# 或者: from jieba.analyse import ChineseAnalyzer [as 別名]
def __init__(self, app=None, db=None, analyzer=None):
        """
        You can custom analyzer by::

            from jieba.analyse import ChineseAnalyzer
            search = Search(analyzer = ChineseAnalyzer)
        """
        self._signal = None
        self._indexs = dict()
        self.db = db
        self.analyzer = analyzer
        if app is not None:
            self.init_app(app)

開發者ID:honmaple，項目名稱:flask-msearch，代碼行數:15，代碼來源:backends.py

示例2: init

# 需要導入模塊: from jieba import analyse [as 別名]
# 或者: from jieba.analyse import ChineseAnalyzer [as 別名]
def __init__(self, app=None, db=None, analyzer=None):
        """
        You can custom analyzer by::

            from jieba.analyse import ChineseAnalyzer
            search = Search(analyzer = ChineseAnalyzer)
        """
        self.db = db
        self.analyzer = analyzer
        if app is not None:
            self.init_app(app)

開發者ID:honmaple，項目名稱:flask-msearch，代碼行數:13，代碼來源:__init__.py

示例3: setUp

# 需要導入模塊: from jieba import analyse [as 別名]
# 或者: from jieba.analyse import ChineseAnalyzer [as 別名]
def setUp(self):
        class TestConfig(object):
            SQLALCHEMY_TRACK_MODIFICATIONS = True
            SQLALCHEMY_DATABASE_URI = 'sqlite://'
            DEBUG = True
            TESTING = True
            MSEARCH_INDEX_NAME = mkdtemp()
            MSEARCH_BACKEND = 'whoosh'

        self.app = Flask(__name__)
        self.app.config.from_object(TestConfig())
        self.db = SQLAlchemy(self.app)
        self.search = Search(self.app, db=self.db, analyzer=ChineseAnalyzer())

        db = self.db

        class Post(db.Model, ModelSaveMixin):
            __tablename__ = 'basic_posts'
            __searchable__ = ['title', 'content']

            id = db.Column(db.Integer, primary_key=True)
            title = db.Column(db.String(49))
            content = db.Column(db.Text)

            def __repr__(self):
                return '<Post:{}>'.format(self.title)

        self.Post = Post

        with self.app.test_request_context():
            self.db.create_all()
            for (i, title) in enumerate(titles, 1):
                post = self.Post(title=title, content='content%d' % i)
                post.save(self.db)

開發者ID:honmaple，項目名稱:flask-msearch，代碼行數:36，代碼來源:test_jieba.py

示例4: init

# 需要導入模塊: from jieba import analyse [as 別名]
# 或者: from jieba.analyse import ChineseAnalyzer [as 別名]
def __init__(self, *args, **kwargs):
        # 為中文分詞，修改默認的分詞器為結巴分詞器
        kwargs['analyzer'] = ChineseAnalyzer()
        super().__init__(*args, **kwargs)

開發者ID:Arianxx，項目名稱:BookForum，代碼行數:6，代碼來源:whoosh_cn_backend.py

示例5: build_schema

# 需要導入模塊: from jieba import analyse [as 別名]
# 或者: from jieba.analyse import ChineseAnalyzer [as 別名]
def build_schema(self, fields):
        schema_fields = {
            ID: WHOOSH_ID(stored=True, unique=True),
            DJANGO_CT: WHOOSH_ID(stored=True),
            DJANGO_ID: WHOOSH_ID(stored=True),
        }
        # Grab the number of keys that are hard-coded into Haystack.
        # We'll use this to (possibly) fail slightly more gracefully later.
        initial_key_count = len(schema_fields)
        content_field_name = ''

        for field_name, field_class in fields.items():
            if field_class.is_multivalued:
                if field_class.indexed is False:
                    schema_fields[field_class.index_fieldname] = IDLIST(stored=True, field_boost=field_class.boost)
                else:
                    schema_fields[field_class.index_fieldname] = KEYWORD(stored=True, commas=True, scorable=True, field_boost=field_class.boost)
            elif field_class.field_type in ['date', 'datetime']:
                schema_fields[field_class.index_fieldname] = DATETIME(stored=field_class.stored, sortable=True)
            elif field_class.field_type == 'integer':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=int, field_boost=field_class.boost)
            elif field_class.field_type == 'float':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=float, field_boost=field_class.boost)
            elif field_class.field_type == 'boolean':
                # Field boost isn't supported on BOOLEAN as of 1.8.2.
                schema_fields[field_class.index_fieldname] = BOOLEAN(stored=field_class.stored)
            elif field_class.field_type == 'ngram':
                schema_fields[field_class.index_fieldname] = NGRAM(minsize=3, maxsize=15, stored=field_class.stored, field_boost=field_class.boost)
            elif field_class.field_type == 'edge_ngram':
                schema_fields[field_class.index_fieldname] = NGRAMWORDS(minsize=2, maxsize=15, at='start', stored=field_class.stored, field_boost=field_class.boost)
            else:
                # schema_fields[field_class.index_fieldname] = TEXT(stored=True, analyzer=StemmingAnalyzer(), field_boost=field_class.boost, sortable=True)
                schema_fields[field_class.index_fieldname] = TEXT(stored=True, 
                    analyzer=ChineseAnalyzer(), 
                    field_boost=field_class.boost, 
                    sortable=True)

            if field_class.document is True:
                content_field_name = field_class.index_fieldname
                schema_fields[field_class.index_fieldname].spelling = True

        # Fail more gracefully than relying on the backend to die if no fields
        # are found.
        if len(schema_fields) <= initial_key_count:
            raise SearchBackendError("No fields were found in any search_indexes. Please correct this before attempting to search.")

        return (content_field_name, Schema(**schema_fields))

開發者ID:infinity1207，項目名稱:thirtylol，代碼行數:49，代碼來源:whoosh_cn_backend.py

示例6: build_schema

# 需要導入模塊: from jieba import analyse [as 別名]
# 或者: from jieba.analyse import ChineseAnalyzer [as 別名]
def build_schema(self, fields):
        schema_fields = {
            ID: WHOOSH_ID(stored=True, unique=True),
            DJANGO_CT: WHOOSH_ID(stored=True),
            DJANGO_ID: WHOOSH_ID(stored=True),
        }
        # Grab the number of keys that are hard-coded into Haystack.
        # We'll use this to (possibly) fail slightly more gracefully later.
        initial_key_count = len(schema_fields)
        content_field_name = ''

        for field_name, field_class in fields.items():
            if field_class.is_multivalued:
                if field_class.indexed is False:
                    schema_fields[field_class.index_fieldname] = IDLIST(stored=True, field_boost=field_class.boost)
                else:
                    schema_fields[field_class.index_fieldname] = KEYWORD(stored=True, commas=True, scorable=True,
                                                                         field_boost=field_class.boost)
            elif field_class.field_type in ['date', 'datetime']:
                schema_fields[field_class.index_fieldname] = DATETIME(stored=field_class.stored, sortable=True)
            elif field_class.field_type == 'integer':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=int,
                                                                     field_boost=field_class.boost)
            elif field_class.field_type == 'float':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=float,
                                                                     field_boost=field_class.boost)
            elif field_class.field_type == 'boolean':
                # Field boost isn't supported on BOOLEAN as of 1.8.2.
                schema_fields[field_class.index_fieldname] = BOOLEAN(stored=field_class.stored)
            elif field_class.field_type == 'ngram':
                schema_fields[field_class.index_fieldname] = NGRAM(minsize=3, maxsize=15, stored=field_class.stored,
                                                                   field_boost=field_class.boost)
            elif field_class.field_type == 'edge_ngram':
                schema_fields[field_class.index_fieldname] = NGRAMWORDS(minsize=2, maxsize=15, at='start',
                                                                        stored=field_class.stored,
                                                                        field_boost=field_class.boost)
            else:  # StemmingAnalyzer->ChineseAnalyzer
                schema_fields[field_class.index_fieldname] = TEXT(stored=True, analyzer=ChineseAnalyzer(),
                                                                  field_boost=field_class.boost, sortable=True)

            if field_class.document is True:
                content_field_name = field_class.index_fieldname
                schema_fields[field_class.index_fieldname].spelling = True

        # Fail more gracefully than relying on the backend to die if no fields
        # are found.
        if len(schema_fields) <= initial_key_count:
            raise SearchBackendError(
                "No fields were found in any search_indexes. Please correct this before attempting to search.")

        return (content_field_name, Schema(**schema_fields))

開發者ID:enjoy-binbin，項目名稱:Django-blog，代碼行數:53，代碼來源:whoosh_cn_backend.py

示例7: build_schema

# 需要導入模塊: from jieba import analyse [as 別名]
# 或者: from jieba.analyse import ChineseAnalyzer [as 別名]
def build_schema(self, fields):
        schema_fields = {
            ID: WHOOSH_ID(stored=True, unique=True),
            DJANGO_CT: WHOOSH_ID(stored=True),
            DJANGO_ID: WHOOSH_ID(stored=True),
        }
        # Grab the number of keys that are hard-coded into Haystack.
        # We'll use this to (possibly) fail slightly more gracefully later.
        initial_key_count = len(schema_fields)
        content_field_name = ''

        for field_name, field_class in fields.items():
            if field_class.is_multivalued:
                if field_class.indexed is False:
                    schema_fields[field_class.index_fieldname] = IDLIST(stored=True, field_boost=field_class.boost)
                else:
                    schema_fields[field_class.index_fieldname] = KEYWORD(stored=True, commas=True, scorable=True, field_boost=field_class.boost)
            elif field_class.field_type in ['date', 'datetime']:
                schema_fields[field_class.index_fieldname] = DATETIME(stored=field_class.stored, sortable=True)
            elif field_class.field_type == 'integer':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=int, field_boost=field_class.boost)
            elif field_class.field_type == 'float':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=float, field_boost=field_class.boost)
            elif field_class.field_type == 'boolean':
                # Field boost isn't supported on BOOLEAN as of 1.8.2.
                schema_fields[field_class.index_fieldname] = BOOLEAN(stored=field_class.stored)
            elif field_class.field_type == 'ngram':
                schema_fields[field_class.index_fieldname] = NGRAM(minsize=3, maxsize=15, stored=field_class.stored, field_boost=field_class.boost)
            elif field_class.field_type == 'edge_ngram':
                schema_fields[field_class.index_fieldname] = NGRAMWORDS(minsize=2, maxsize=15, at='start', stored=field_class.stored, field_boost=field_class.boost)
            else:
                # 調用結巴分詞
                schema_fields[field_class.index_fieldname] = TEXT(stored=True, analyzer=ChineseAnalyzer(), field_boost=field_class.boost, sortable=True)

            if field_class.document is True:
                content_field_name = field_class.index_fieldname
                schema_fields[field_class.index_fieldname].spelling = True

        # Fail more gracefully than relying on the backend to die if no fields
        # are found.
        if len(schema_fields) <= initial_key_count:
            raise SearchBackendError("No fields were found in any search_indexes. Please correct this before attempting to search.")

        return (content_field_name, Schema(**schema_fields))

開發者ID:stormsha，項目名稱:blog，代碼行數:46，代碼來源:whoosh_cn_backend.py

示例8: build_schema

# 需要導入模塊: from jieba import analyse [as 別名]
# 或者: from jieba.analyse import ChineseAnalyzer [as 別名]
def build_schema(self, fields):
        schema_fields = {
            ID: WHOOSH_ID(stored=True, unique=True),
            DJANGO_CT: WHOOSH_ID(stored=True),
            DJANGO_ID: WHOOSH_ID(stored=True),
        }
        # Grab the number of keys that are hard-coded into Haystack.
        # We'll use this to (possibly) fail slightly more gracefully later.
        initial_key_count = len(schema_fields)
        content_field_name = ''

        for field_name, field_class in fields.items():
            if field_class.is_multivalued:
                if field_class.indexed is False:
                    schema_fields[field_class.index_fieldname] = IDLIST(stored=True, field_boost=field_class.boost)
                else:
                    schema_fields[field_class.index_fieldname] = KEYWORD(stored=True, commas=True, scorable=True, field_boost=field_class.boost)
            elif field_class.field_type in ['date', 'datetime']:
                schema_fields[field_class.index_fieldname] = DATETIME(stored=field_class.stored, sortable=True)
            elif field_class.field_type == 'integer':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=int, field_boost=field_class.boost)
            elif field_class.field_type == 'float':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=float, field_boost=field_class.boost)
            elif field_class.field_type == 'boolean':
                # Field boost isn't supported on BOOLEAN as of 1.8.2.
                schema_fields[field_class.index_fieldname] = BOOLEAN(stored=field_class.stored)
            elif field_class.field_type == 'ngram':
                schema_fields[field_class.index_fieldname] = NGRAM(minsize=3, maxsize=15, stored=field_class.stored, field_boost=field_class.boost)
            elif field_class.field_type == 'edge_ngram':
                schema_fields[field_class.index_fieldname] = NGRAMWORDS(minsize=2, maxsize=15, at='start', stored=field_class.stored, field_boost=field_class.boost)
            else:
                schema_fields[field_class.index_fieldname] = TEXT(stored=True, analyzer=ChineseAnalyzer(), field_boost=field_class.boost, sortable=True)

            if field_class.document is True:
                content_field_name = field_class.index_fieldname
                schema_fields[field_class.index_fieldname].spelling = True

        # Fail more gracefully than relying on the backend to die if no fields
        # are found.
        if len(schema_fields) <= initial_key_count:
            raise SearchBackendError("No fields were found in any search_indexes. Please correct this before attempting to search.")

        return (content_field_name, Schema(**schema_fields))

開發者ID:Hopetree，項目名稱:izone，代碼行數:45，代碼來源:whoosh_cn_backend.py

注：本文中的jieba.analyse.ChineseAnalyzer方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。

示例1: __init__

示例2: __init__