explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 01:48:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

Move string cleanup under a setting flag

Browse Source
This commit is contained in:
Matthew Honnibal 2017-11-23 12:19:18 +00:00
parent 5949777b12
commit 8fec7268eb
1 changed files with 18 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
spacy/language.py
View File

@ -547,22 +547,27 @@ class Language(object):
# in the string store.
recent_refs = weakref.WeakSet()
old_refs = weakref.WeakSet()
# If there is anything that we have inside — after iterations we should
# carefully get it back.
original_strings_data = list(self.vocab.strings)
# Keep track of the original string data, so that if we flush old strings,
# we can recover the original ones. However, we only want to do this if we're
# really adding strings, to save up-front costs.
original_strings_data = None
nr_seen = 0
for doc in docs:
yield doc
recent_refs.add(doc)
if nr_seen < 10000:
old_refs.add(doc)
nr_seen += 1
elif len(old_refs) == 0:
old_refs, recent_refs = recent_refs, old_refs
keys, strings = self.vocab.strings._cleanup_stale_strings(original_strings_data)
self.vocab._reset_cache(keys, strings)
self.tokenizer._reset_cache(keys)
nr_seen = 0
if cleanup:
recent_refs.add(doc)
if nr_seen < 10000:
old_refs.add(doc)
nr_seen += 1
elif len(old_refs) == 0:
old_refs, recent_refs = recent_refs, old_refs
if original_strings_data is None:
original_strings_data = list(self.vocab.strings)
else:
keys, strings = self.vocab.strings._cleanup_stale_strings(original_strings_data)
self.vocab._reset_cache(keys, strings)
self.tokenizer._reset_cache(keys)
nr_seen = 0
def to_disk(self, path, disable=tuple()):
"""Save the current state to a directory. If a model is loaded, this