django公开项目博客

# encoding: utf-8 from __future__ import absolute_import, division, print_function, unicode_literals import json import os import re import shutil import threading import warnings import six from django.conf import settings from django.core.exceptions import ImproperlyConfigured from django.utils.datetime_safe import datetime from django.utils.encoding import force_str from haystack.backends import BaseEngine, BaseSearchBackend, BaseSearchQuery, EmptyResults, log_query from haystack.constants import DJANGO_CT, DJANGO_ID, ID from haystack.exceptions import MissingDependency, SearchBackendError, SkipDocument from haystack.inputs import Clean, Exact, PythonData, Raw from haystack.models import SearchResult from haystack.utils import get_identifier, get_model_ct from haystack.utils import log as logging from haystack.utils.app_loading import haystack_get_model from jieba.analyse import ChineseAnalyzer from whoosh import index from whoosh.analysis import StemmingAnalyzer from whoosh.fields import BOOLEAN, DATETIME, IDLIST, KEYWORD, NGRAM, NGRAMWORDS, NUMERIC, Schema, TEXT from whoosh.fields import ID as WHOOSH_ID from whoosh.filedb.filestore import FileStorage, RamStorage from whoosh.highlight import ContextFragmenter, HtmlFormatter from whoosh.highlight import highlight as whoosh_highlight from whoosh.qparser import QueryParser from whoosh.searching import ResultsPage from whoosh.writing import AsyncWriter try: import whoosh except ImportError: raise MissingDependency( "The 'whoosh' backend requires the installation of 'Whoosh'. Please refer to the documentation.") # Handle minimum requirement. if not hasattr(whoosh, '__version__') or whoosh.__version__ < (2, 5, 0): raise MissingDependency( "The 'whoosh' backend requires version 2.5.0 or greater.") # Bubble up the correct error. DATETIME_REGEX = re.compile( '^(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})T(?P<hour>\d{2}):(?P<minute>\d{2}):(?P<second>\d{2})(\.\d{3,6}Z?)?$') LOCALS = threading.local() LOCALS.RAM_STORE = None class WhooshHtmlFormatter(HtmlFormatter): """ This is a HtmlFormatter simpler than the whoosh.HtmlFormatter. We use it to have consistent results across backends. Specifically, Solr, Xapian and Elasticsearch are using this formatting. """ template = '<%(tag)s>%(t)s</%(tag)s>' class WhooshSearchBackend(BaseSearchBackend): # Word reserved by Whoosh for special use. RESERVED_WORDS = ( 'AND', 'NOT', 'OR', 'TO', ) # Characters reserved by Whoosh for special use. # The '\\' must come first, so as not to overwrite the other slash # replacements. RESERVED_CHARACTERS = ( '\\', '+', '-', '&&', '||', '!', '(', ')', '{', '}', '[', ']', '^', '"', '~', '*', '?', ':', '.', ) def __init__(self, connection_alias, **connection_options): super( WhooshSearchBackend, self).__init__( connection_alias, **connection_options) self.setup_complete = False self.use_file_storage = True self.post_limit = getattr( connection_options, 'POST_LIMIT', 128 * 1024 * 1024) self.path = connection_options.get('PATH') if connection_options.get('STORAGE', 'file') != 'file': self.use_file_storage = False if self.use_file_storage and not self.path: raise ImproperlyConfigured( "You must specify a 'PATH' in your settings for connection '%s'." % connection_alias) self.log = logging.getLogger('haystack') def setup(self): """ Defers loading until needed. """ from haystack import connections new_index = False # Make sure the index is there. if self.use_file_storage and not os.path.exists(self.path): os.makedirs(self.path) new_index = True if self.use_file_storage and not os.access(self.path, os.W_OK): raise IOError( "The path to your Whoosh index '%s' is not writable for the current user/group." % self.path) if self.use_file_storage: self.storage = FileStorage(self.path) else: global LOCALS if getattr(LOCALS, 'RAM_STORE', None) is None: LOCALS.RAM_STORE = RamStorage() self.storage = LOCALS.RAM_STORE self.content_field_name, self.schema = self.build_schema( connections[self.connection_alias].get_unified_index().all_searchfields()) self.parser = QueryParser(self.content_field_name, schema=self.schema) if new_index is True: self.index = self.storage.create_index(self.schema) else: try: self.index = self.storage.open_index(schema=self.schema) except index.EmptyIndexError: self.index = self.storage.create_index(self.schema) self.setup_complete = True 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 re