def __init__(self, stored=False, unique=False, field_boost=1.0):
"""
:param stored: Whether the value of this field is stored with the document.
"""
self.format = Existence(analyzer=IDAnalyzer(), field_boost=field_boost)
self.stored = stored
self.unique = unique
def __init__(self, stored = False, unique = False):
"""
:stored: Whether the value of this field is stored with the document.
"""
self.format = Existance(analyzer = IDAnalyzer())
self.stored = stored
self.unique = unique
def index(self, index_name='unified'):
types = self.get_requested_content_types()
from whoosh.fields import TEXT, ID, NGRAM, NUMERIC
from whoosh.analysis import StemmingAnalyzer, SimpleAnalyzer, IDAnalyzer
from whoosh.analysis.filters import LowercaseFilter
simp_ana = SimpleAnalyzer()
print 'Building %s index...' % index_name
# build a single schema from the fields exposed by the different search
# types
print '\tSchema:'
fields = {}
for type in types:
for info in type.get_fields_info().values():
if info['whoosh']['name'] not in fields and not info[
'whoosh'].get('ignore', False):
print '\t\t%s' % info
field_type = info['whoosh']['type']
if index_name == 'autocomplete':
# break the long text fields into terms, leave the
# others as single expression
if not (field_type.__class__ == NUMERIC):
if info.get('long_text', False):
field_type = TEXT(analyzer=simp_ana)
else:
field_type = ID(stored=True,
analyzer=IDAnalyzer()
| LowercaseFilter())
print '\t\t%s' % field_type
fields[info['whoosh']['name']] = field_type
# JIRA 508 - Add an ID counterpart to allow exact phrase search
# if info.get('long_text', False):
# fields[info['whoosh']['name']+'_iexact'] = ID(analyzer=IDAnalyzer(lowercase=True))
from whoosh.fields import Schema
schema = Schema(**fields)
# Create the index schema
index = self.recreate_index(index_name, schema)
# Add documents to the index
print '\tWrite indexes:'
writer = index.writer()
aci = {}
for type in types:
count = type.write_index(writer, self.is_verbose(), aci)
print '\t\t%s %s records indexed' % (count,
type.get_model().__name__)
# autocomplete
if index_name == 'unified':
f = open(types[0].get_autocomplete_path(True), 'w')
f.write((ur'|'.join(aci.keys())).encode('utf8'))
f.close()
writer.commit()
def __init__(self,
type=int,
stored=False,
unique=False,
field_boost=1.0,
decimal_places=0,
shift_step=4,
signed=True):
"""
:param type: the type of numbers that can be stored in this field: one
of ``int``, ``long``, ``float``, or ``Decimal``.
:param stored: Whether the value of this field is stored with the
document.
:param unique: Whether the value of this field is unique per-document.
:param decimal_places: specifies the number of decimal places to save
when storing Decimal instances as ``int`` or ``float``.
:param shift_steps: The number of bits of precision to shift away at
each tiered indexing level. Values should generally be 1-8. Lower
values yield faster searches but take up more space. A value
of `0` means no tiered indexing.
:param signed: Whether the numbers stored in this field may be
negative.
"""
self.type = type
if self.type is long_type:
# This will catch the Python 3 int type
self._to_text = long_to_text
self._from_text = text_to_long
self.sortable_typecode = "q" if signed else "Q"
elif self.type is int:
self._to_text = int_to_text
self._from_text = text_to_int
self.sortable_typecode = "i" if signed else "I"
elif self.type is float:
self._to_text = float_to_text
self._from_text = text_to_float
self.sortable_typecode = "f"
elif self.type is Decimal:
raise TypeError("To store Decimal instances, set type to int or "
"float and use the decimal_places argument")
else:
raise TypeError("%s field type can't store %r" %
(self.__class__, self.type))
self.stored = stored
self.unique = unique
self.decimal_places = decimal_places
self.shift_step = shift_step
self.signed = signed
self.analyzer = IDAnalyzer()
self.format = formats.Existence(field_boost=field_boost)
def __init__(self, type=int, stored=False, unique=False, field_boost=1.0):
self.type = type
self.stored = stored
self.unique = unique
self.format = Existence(analyzer=IDAnalyzer(), field_boost=field_boost)
