From aa0dd79f521ba6df852ac2d09cbc98d5b9ad855c Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Sat, 16 Jan 2016 16:03:35 +0100 Subject: [PATCH] * Delete test_token_references, which checked a flakey strategy for preventing orphan tokens from a while ago. Now orphan tokens simply hold a reference to Pool, preventing the memory from being freed underneath them. This means that we don't need to run this slow test. --- spacy/tests/tokens/test_token_references.py | 54 --------------------- 1 file changed, 54 deletions(-) delete mode 100644 spacy/tests/tokens/test_token_references.py diff --git a/spacy/tests/tokens/test_token_references.py b/spacy/tests/tokens/test_token_references.py deleted file mode 100644 index 24639f141..000000000 --- a/spacy/tests/tokens/test_token_references.py +++ /dev/null @@ -1,54 +0,0 @@ -from __future__ import unicode_literals -import pytest -import gc - -from spacy.en import English -import os - -# Let this have its own instances, as we have to be careful about memory here -# that's the point, after all - -@pytest.mark.models -def get_orphan_token(text, i): - nlp = English() - tokens = nlp(text) - gc.collect() - token = tokens[i] - del tokens - return token - - -@pytest.mark.models -def test_orphan(): - orphan = get_orphan_token('An orphan token', 1) - gc.collect() - dummy = get_orphan_token('Load and flush the memory', 0) - dummy = get_orphan_token('Load again...', 0) - assert orphan.orth_ == 'orphan' - assert orphan.pos_ in ('ADJ', 'NOUN') - assert orphan.head.orth_ == 'token' - - -def _orphan_from_list(toks): - ''' Take the tokens from nlp(), append them to a list, return the list ''' - lst = [] - for tok in toks: - lst.append(tok) - return lst - - -@pytest.mark.models -def test_list_orphans(): - # Test case from NSchrading - nlp = English() - samples = ["a", "test blah wat okay"] - lst = [] - for sample in samples: - # Go through all the samples, call nlp() on each to get tokens, - # pass those tokens to the _orphan_from_list() function, get a list back - # and put all results in another list - lst.extend(_orphan_from_list(nlp(sample))) - # go through the list of all tokens and try to print orth_ - orths = ['a', 'test', 'blah', 'wat', 'okay'] - for i, l in enumerate(lst): - assert l.orth_ == orths[i]