/usr/share/pyshared/carquinyol/indexstore.py is in python-carquinyol-0.84 0.84.1-3build1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 | # Copyright (C) 2008, One Laptop Per Child
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
import logging
import os
import gobject
import xapian
from xapian import WritableDatabase, Document, Enquire, Query, QueryParser
from carquinyol import layoutmanager
from carquinyol.layoutmanager import MAX_QUERY_LIMIT
_VALUE_UID = 0
_VALUE_TIMESTAMP = 1
_PREFIX_UID = 'Q'
_PREFIX_ACTIVITY = 'A'
_PREFIX_ACTIVITY_ID = 'I'
_PREFIX_MIME_TYPE = 'M'
_PREFIX_KEEP = 'K'
# Force a flush every _n_ changes to the db
_FLUSH_THRESHOLD = 20
# Force a flush after _n_ seconds since the last change to the db
_FLUSH_TIMEOUT = 60
_PROPERTIES_NOT_TO_INDEX = ['timestamp', 'activity_id', 'keep', 'preview']
_MAX_RESULTS = int(2 ** 31 - 1)
class IndexStore(object):
"""Index metadata and provide rich query facilities on it.
"""
def __init__(self):
self._database = None
self._flush_timeout = None
self._pending_writes = 0
def open_index(self):
index_path = layoutmanager.get_instance().get_index_path()
self._database = WritableDatabase(index_path, xapian.DB_CREATE_OR_OPEN)
def close_index(self):
self._database.flush()
self._database = None
def remove_index(self):
index_path = layoutmanager.get_instance().get_index_path()
if not os.path.exists(index_path):
return
for f in os.listdir(index_path):
os.remove(os.path.join(index_path, f))
def contains(self, uid):
postings = self._database.postlist(_PREFIX_UID + uid)
try:
postlist_item = postings.next()
except StopIteration:
return False
return True
def store(self, uid, properties):
document = Document()
document.add_term(_PREFIX_UID + uid)
document.add_term(_PREFIX_ACTIVITY + properties.get('activity', ''))
document.add_term(_PREFIX_MIME_TYPE + properties.get('mime_type', ''))
document.add_term(_PREFIX_ACTIVITY_ID +
properties.get('activity_id', ''))
document.add_term(_PREFIX_KEEP + str(properties.get('keep', 0)))
document.add_value(_VALUE_UID, uid)
document.add_value(_VALUE_TIMESTAMP, str(properties['timestamp']))
term_generator = xapian.TermGenerator()
# TODO: we should do stemming, but in which language?
#if language is not None:
# term_generator.set_stemmer(_xapian.Stem(language))
# TODO: we should use a stopper
#if stop is not None:
# stopper = _xapian.SimpleStopper()
# for term in stop:
# stopper.add (term)
# term_generator.set_stopper (stopper)
term_generator.set_document(document)
term_generator.index_text_without_positions(
self._extract_text(properties), 1, '')
if not self.contains(uid):
self._database.add_document(document)
else:
self._database.replace_document(_PREFIX_UID + uid, document)
self._flush()
def _extract_text(self, properties):
text = ''
for key, value in properties.items():
if key not in _PROPERTIES_NOT_TO_INDEX:
if text:
text += ' '
if isinstance(value, unicode):
value = value.encode('utf-8')
elif not isinstance(value, basestring):
value = str(value)
text += value
return text
def find(self, query):
enquire = Enquire(self._database)
enquire.set_query(self._parse_query(query))
offset = query.get('offset', 0)
limit = query.get('limit', MAX_QUERY_LIMIT)
# This will assure that the results count is exact.
check_at_least = offset + limit + 1
enquire.set_sort_by_value(_VALUE_TIMESTAMP, True)
query_result = enquire.get_mset(offset, limit, check_at_least)
total_count = query_result.get_matches_estimated()
uids = []
for hit in query_result:
uids.append(hit.document.get_value(_VALUE_UID))
return (uids, total_count)
def _parse_query(self, query_dict):
logging.debug('_parse_query %r' % query_dict)
queries = []
query_str = query_dict.pop('query', None)
if query_str is not None:
query_parser = QueryParser()
query_parser.set_database(self._database)
#query_parser.set_default_op(Query.OP_AND)
# TODO: we should do stemming, but in which language?
#query_parser.set_stemmer(_xapian.Stem(lang))
#query_parser.set_stemming_strategy(qp.STEM_SOME)
query = query_parser.parse_query(
query_str,
QueryParser.FLAG_PHRASE |
QueryParser.FLAG_BOOLEAN |
QueryParser.FLAG_LOVEHATE |
QueryParser.FLAG_WILDCARD,
'')
queries.append(query)
timestamp = query_dict.pop('timestamp', None)
if timestamp is not None:
start = str(timestamp.pop('start', 0))
end = str(timestamp.pop('end', _MAX_RESULTS))
query = Query(Query.OP_VALUE_RANGE, _VALUE_TIMESTAMP, start, end)
queries.append(query)
uid = query_dict.pop('uid', None)
if uid is not None:
queries.append(Query(_PREFIX_UID + uid))
activity = query_dict.pop('activity', None)
if activity is not None:
queries.append(Query(_PREFIX_ACTIVITY + activity))
activity_id = query_dict.pop('activity_id', None)
if activity_id is not None:
query = Query(_PREFIX_ACTIVITY_ID + activity_id)
queries.append(query)
keep = query_dict.pop('keep', None)
if keep is not None:
query = Query(_PREFIX_KEEP + str(keep))
queries.append(query)
mime_type = query_dict.pop('mime_type', None)
if mime_type is not None:
mime_queries = []
for mime_type in mime_type:
mime_queries.append(Query(_PREFIX_MIME_TYPE + mime_type))
queries.append(Query(Query.OP_OR, mime_queries))
if not queries:
queries.append(Query(''))
if query_dict:
logging.warning('Unknown term(s): %r' % query_dict)
return Query(Query.OP_AND, queries)
def delete(self, uid):
self._database.delete_document(_PREFIX_UID + uid)
def get_activities(self):
activities = []
for term in self._database.allterms(_PREFIX_ACTIVITY):
activities.append(term.term[len(_PREFIX_ACTIVITY):])
return activities
def _flush_timeout_cb(self):
self._flush(True)
return False
def _flush(self, force=False):
"""Called after any database mutation"""
logging.debug('IndexStore.flush: %r %r' % (force, self._pending_writes))
if self._flush_timeout is not None:
gobject.source_remove(self._flush_timeout)
self._flush_timeout = None
self._pending_writes += 1
if force or self._pending_writes > _FLUSH_THRESHOLD:
self._database.flush()
self._pending_writes = 0
else:
self._flush_timeout = gobject.timeout_add_seconds(_FLUSH_TIMEOUT,
self._flush_timeout_cb)
|