class _DefaultSearchSchema(SchemaClass):
"""
General search schema
"""
object_key = ID(stored=True, unique=True)
id = NUMERIC(numtype=int, bits=64, signed=False, stored=True, unique=False)
object_type = ID(stored=True, unique=False)
creator = ID(stored=True)
owner = ID(stored=True)
#: security index. This list roles and user/group ids allowed to *see* this
#: content
allowed_roles_and_users = KEYWORD(stored=True)
#: tags indexing
tag_ids = KEYWORD(stored=True)
tag_text = TEXT(stored=False, analyzer=accent_folder)
# hierarchical index of ids path ('/' is the separator)
parent_ids = FieldType(format=Existence(),
analyzer=PathTokenizer(),
stored=True,
unique=False)
name = TEXT(stored=True, analyzer=accent_folder)
slug = ID(stored=True)
description = TEXT(stored=True, analyzer=accent_folder)
text = TEXT(stored=False, analyzer=accent_folder)
def _schema(self):
# Creates a schema given this object's mingram and maxgram attributes.
from whoosh.fields import Schema, FieldType, ID, STORED
from whoosh.formats import Frequency
from whoosh.analysis import SimpleAnalyzer
idtype = ID()
freqtype = FieldType(Frequency(), SimpleAnalyzer())
fls = [("word", STORED), ("score", STORED)]
for size in xrange(self.mingram, self.maxgram + 1):
fls.extend([("start%s" % size, idtype), ("end%s" % size, idtype),
("gram%s" % size, freqtype)])
return Schema(**dict(fls))
FieldType, DATETIME)
# CUSTOM ANALYZER wordsplit + lowercase filter for case insensitive search
ANALYZER = RegexTokenizer(expression=r"\w+") | LowercaseFilter()
# FILE INDEX SCHEMA DEFINITION
FILE_INDEX_NAME = 'FILE_INDEX'
FILE_SCHEMA = Schema(
fileid=ID(unique=True), # Path
repository=ID(stored=True),
repository_id=NUMERIC(unique=True, stored=True), # Numeric id of repo
repo_name=TEXT(stored=True),
owner=TEXT(),
path=TEXT(stored=True),
content=FieldType(format=Characters(),
analyzer=ANALYZER,
scorable=True,
stored=True),
modtime=STORED(),
md5=STORED(),
extension=ID(stored=True),
commit_id=TEXT(stored=True),
size=NUMERIC(stored=True),
mimetype=TEXT(stored=True),
lines=NUMERIC(stored=True),
)
# COMMIT INDEX SCHEMA
COMMIT_INDEX_NAME = 'COMMIT_INDEX'
COMMIT_SCHEMA = Schema(
commit_id=ID(unique=True, stored=True),
repository=ID(unique=True, stored=True),