self.num_threads = num_threads
+ def has_pending(self):
+ """ Check if any data still needs indexing.
+ This function must only be used after the import has finished.
+ Otherwise it will be very expensive.
+ """
+ with connect(self.dsn) as conn:
+ with conn.cursor() as cur:
+ cur.execute("SELECT 'a' FROM placex WHERE indexed_status > 0 LIMIT 1")
+ return cur.rowcount > 0
+
+
def index_full(self, analyse=True):
- """ Index the complete database. This will first index boudnaries
+ """ Index the complete database. This will first index boundaries
followed by all other objects. When `analyse` is True, then the
database will be analysed at the appropriate places to
ensure that database statistics are updated.
with connect(self.dsn) as conn:
conn.autocommit = True
- if analyse:
- def _analyze():
+ def _analyze():
+ if analyse:
with conn.cursor() as cur:
cur.execute('ANALYZE')
- else:
- def _analyze():
- pass
self.index_by_rank(0, 4)
_analyze()
# And insert the curent batch
for idx in range(0, len(places), batch):
- part = places[idx:idx+batch]
+ part = places[idx:idx + batch]
LOG.debug("Processing places: %s", str(part))
runner.index_places(pool.next_free_worker(), part)
progress.add(len(part))