spaCy/spacy/tests/serialize/test_serialize_tokenizer.py

145 lines
5.3 KiB
Python
Raw Normal View History

import pickle
import re
import pytest
from spacy.attrs import ENT_IOB, ENT_TYPE
from spacy.lang.en import English
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
from spacy.tokenizer import Tokenizer
from spacy.tokens import Doc
from spacy.util import compile_infix_regex, compile_prefix_regex
from spacy.util import compile_suffix_regex, get_lang_class, load_model
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
from ..util import assert_packed_msg_equal, make_tempdir
2017-06-03 14:26:34 +03:00
def load_tokenizer(b):
Refactor pipeline components, config and language data (#5759) * Update with WIP * Update with WIP * Update with pipeline serialization * Update types and pipe factories * Add deep merge, tidy up and add tests * Fix pipe creation from config * Don't validate default configs on load * Update spacy/language.py Co-authored-by: Ines Montani <ines@ines.io> * Adjust factory/component meta error * Clean up factory args and remove defaults * Add test for failing empty dict defaults * Update pipeline handling and methods * provide KB as registry function instead of as object * small change in test to make functionality more clear * update example script for EL configuration * Fix typo * Simplify test * Simplify test * splitting pipes.pyx into separate files * moving default configs to each component file * fix batch_size type * removing default values from component constructors where possible (TODO: test 4725) * skip instead of xfail * Add test for config -> nlp with multiple instances * pipeline.pipes -> pipeline.pipe * Tidy up, document, remove kwargs * small cleanup/generalization for Tok2VecListener * use DEFAULT_UPSTREAM field * revert to avoid circular imports * Fix tests * Replace deprecated arg * Make model dirs require config * fix pickling of keyword-only arguments in constructor * WIP: clean up and integrate full config * Add helper to handle function args more reliably Now also includes keyword-only args * Fix config composition and serialization * Improve config debugging and add visual diff * Remove unused defaults and fix type * Remove pipeline and factories from meta * Update spacy/default_config.cfg Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/default_config.cfg * small UX edits * avoid printing stack trace for debug CLI commands * Add support for language-specific factories * specify the section of the config which holds the model to debug * WIP: add Language.from_config * Update with language data refactor WIP * Auto-format * Add backwards-compat handling for Language.factories * Update morphologizer.pyx * Fix morphologizer * Update and simplify lemmatizers * Fix Japanese tests * Port over tagger changes * Fix Chinese and tests * Update to latest Thinc * WIP: xfail first Russian lemmatizer test * Fix component-specific overrides * fix nO for output layers in debug_model * Fix default value * Fix tests and don't pass objects in config * Fix deep merging * Fix lemma lookup data registry Only load the lookups if an entry is available in the registry (and if spacy-lookups-data is installed) * Add types * Add Vocab.from_config * Fix typo * Fix tests * Make config copying more elegant * Fix pipe analysis * Fix lemmatizers and is_base_form * WIP: move language defaults to config * Fix morphology type * Fix vocab * Remove comment * Update to latest Thinc * Add morph rules to config * Tidy up * Remove set_morphology option from tagger factory * Hack use_gpu * Move [pipeline] to top-level block and make [nlp.pipeline] list Allows separating component blocks from component order – otherwise, ordering the config would mean a changed component order, which is bad. Also allows initial config to define more components and not use all of them * Fix use_gpu and resume in CLI * Auto-format * Remove resume from config * Fix formatting and error * [pipeline] -> [components] * Fix types * Fix tagger test: requires set_morphology? Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
2020-07-22 14:42:59 +03:00
tok = get_lang_class("en")().tokenizer
tok.from_bytes(b)
return tok
@pytest.mark.issue(2833)
def test_issue2833(en_vocab):
"""Test that a custom error is raised if a token or span is pickled."""
doc = Doc(en_vocab, words=["Hello", "world"])
with pytest.raises(NotImplementedError):
pickle.dumps(doc[0])
with pytest.raises(NotImplementedError):
pickle.dumps(doc[0:2])
@pytest.mark.issue(3012)
def test_issue3012(en_vocab):
"""Test that the is_tagged attribute doesn't get overwritten when we from_array
without tag information."""
words = ["This", "is", "10", "%", "."]
tags = ["DT", "VBZ", "CD", "NN", "."]
pos = ["DET", "VERB", "NUM", "NOUN", "PUNCT"]
ents = ["O", "O", "B-PERCENT", "I-PERCENT", "O"]
doc = Doc(en_vocab, words=words, tags=tags, pos=pos, ents=ents)
assert doc.has_annotation("TAG")
expected = ("10", "NUM", "CD", "PERCENT")
assert (doc[2].text, doc[2].pos_, doc[2].tag_, doc[2].ent_type_) == expected
header = [ENT_IOB, ENT_TYPE]
ent_array = doc.to_array(header)
doc.from_array(header, ent_array)
assert (doc[2].text, doc[2].pos_, doc[2].tag_, doc[2].ent_type_) == expected
# Serializing then deserializing
doc_bytes = doc.to_bytes()
doc2 = Doc(en_vocab).from_bytes(doc_bytes)
assert (doc2[2].text, doc2[2].pos_, doc2[2].tag_, doc2[2].ent_type_) == expected
@pytest.mark.issue(4190)
def test_issue4190():
def customize_tokenizer(nlp):
prefix_re = compile_prefix_regex(nlp.Defaults.prefixes)
suffix_re = compile_suffix_regex(nlp.Defaults.suffixes)
infix_re = compile_infix_regex(nlp.Defaults.infixes)
# Remove all exceptions where a single letter is followed by a period (e.g. 'h.')
exceptions = {
k: v
for k, v in dict(nlp.Defaults.tokenizer_exceptions).items()
if not (len(k) == 2 and k[1] == ".")
}
new_tokenizer = Tokenizer(
nlp.vocab,
exceptions,
prefix_search=prefix_re.search,
suffix_search=suffix_re.search,
infix_finditer=infix_re.finditer,
token_match=nlp.tokenizer.token_match,
faster_heuristics=False,
)
nlp.tokenizer = new_tokenizer
test_string = "Test c."
# Load default language
nlp_1 = English()
doc_1a = nlp_1(test_string)
result_1a = [token.text for token in doc_1a] # noqa: F841
# Modify tokenizer
customize_tokenizer(nlp_1)
doc_1b = nlp_1(test_string)
result_1b = [token.text for token in doc_1b]
# Save and Reload
with make_tempdir() as model_dir:
nlp_1.to_disk(model_dir)
nlp_2 = load_model(model_dir)
# This should be the modified tokenizer
doc_2 = nlp_2(test_string)
result_2 = [token.text for token in doc_2]
assert result_1b == result_2
assert nlp_2.tokenizer.faster_heuristics is False
def test_serialize_custom_tokenizer(en_vocab, en_tokenizer):
"""Test that custom tokenizer with not all functions defined or empty
properties can be serialized and deserialized correctly (see #2494,
#4991)."""
tokenizer = Tokenizer(en_vocab, suffix_search=en_tokenizer.suffix_search)
tokenizer_bytes = tokenizer.to_bytes()
2018-11-30 19:43:08 +03:00
Tokenizer(en_vocab).from_bytes(tokenizer_bytes)
# test that empty/unset values are set correctly on deserialization
tokenizer = get_lang_class("en")().tokenizer
tokenizer.token_match = re.compile("test").match
assert tokenizer.rules != {}
assert tokenizer.token_match is not None
assert tokenizer.url_match is not None
assert tokenizer.prefix_search is not None
assert tokenizer.infix_finditer is not None
tokenizer.from_bytes(tokenizer_bytes)
assert tokenizer.rules == {}
assert tokenizer.token_match is None
assert tokenizer.url_match is None
assert tokenizer.prefix_search is None
assert tokenizer.infix_finditer is None
2020-03-25 14:28:12 +03:00
tokenizer = Tokenizer(en_vocab, rules={"ABC.": [{"ORTH": "ABC"}, {"ORTH": "."}]})
tokenizer.rules = {}
tokenizer_bytes = tokenizer.to_bytes()
tokenizer_reloaded = Tokenizer(en_vocab).from_bytes(tokenizer_bytes)
assert tokenizer_reloaded.rules == {}
@pytest.mark.parametrize("text", ["I💜you", "theyre", "“hello”"])
2017-06-03 14:26:34 +03:00
def test_serialize_tokenizer_roundtrip_bytes(en_tokenizer, text):
tokenizer = en_tokenizer
new_tokenizer = load_tokenizer(tokenizer.to_bytes())
assert_packed_msg_equal(new_tokenizer.to_bytes(), tokenizer.to_bytes())
2018-07-06 13:40:28 +03:00
assert new_tokenizer.to_bytes() == tokenizer.to_bytes()
doc1 = tokenizer(text)
2017-06-03 14:26:34 +03:00
doc2 = new_tokenizer(text)
assert [token.text for token in doc1] == [token.text for token in doc2]
def test_serialize_tokenizer_roundtrip_disk(en_tokenizer):
tokenizer = en_tokenizer
with make_tempdir() as d:
file_path = d / "tokenizer"
2017-06-03 14:26:34 +03:00
tokenizer.to_disk(file_path)
tokenizer_d = en_tokenizer.from_disk(file_path)
assert tokenizer.to_bytes() == tokenizer_d.to_bytes()