spaCy/spacy/lang/el/lemmatizer/__init__.py

79 lines
2.5 KiB
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
from ....symbols import NOUN, VERB, ADJ, PUNCT
Reduce size of language data (#4141) * Move Turkish lemmas to a json file Rather than a large dict in Python source, the data is now a big json file. This includes a method for loading the json file, falling back to a compressed file, and an update to MANIFEST.in that excludes json in the spacy/lang directory. This focuses on Turkish specifically because it has the most language data in core. * Transition all lemmatizer.py files to json This covers all lemmatizer.py files of a significant size (>500k or so). Small files were left alone. None of the affected files have logic, so this was pretty straightforward. One unusual thing is that the lemma data for Urdu doesn't seem to be used anywhere. That may require further investigation. * Move large lang data to json for fr/nb/nl/sv These are the languages that use a lemmatizer directory (rather than a single file) and are larger than English. For most of these languages there were many language data files, in which case only the large ones (>500k or so) were converted to json. It may or may not be a good idea to migrate the remaining Python files to json in the future. * Fix id lemmas.json The contents of this file were originally just copied from the Python source, but that used single quotes, so it had to be properly converted to json first. * Add .json.gz to gitignore This covers the json.gz files built as part of distribution. * Add language data gzip to build process Currently this gzip data on every build; it works, but it should be changed to only gzip when the source file has been updated. * Remove Danish lemmatizer.py Missed this when I added the json. * Update to match latest explosion/srsly#9 The way gzipped json is loaded/saved in srsly changed a bit. * Only compress language data if necessary If a .json.gz file exists and is newer than the corresponding json file, it's not recompressed. * Move en/el language data to json This only affected files >500kb, which was nouns for both languages and the generic lookup table for English. * Remove empty files in Norwegian tokenizer It's unclear why, but the Norwegian (nb) tokenizer had empty files for adj/adv/noun/verb lemmas. This may have been a result of copying the structure of the English lemmatizer. This removed the files, but still creates the empty sets in the lemmatizer. That may not actually be necessary. * Remove dubious entries in English lookup.json " furthest" and " skilled" - both prefixed with a space - were in the English lookup table. That seems obviously wrong so I have removed them. * Fix small issues with en/fr lemmatizers The en tokenizer was including the removed _nouns.py file, so that's removed. The fr tokenizer is unusual in that it has a lemmatizer directory with both __init__.py and lemmatizer.py. lemmatizer.py had not been converted to load the json language data, so that was fixed. * Auto-format * Auto-format * Update srsly pin * Consistently use pathlib paths
2019-08-20 12:54:11 +00:00
class GreekLemmatizer(object):
"""
Greek language lemmatizer applies the default rule based lemmatization
procedure with some modifications for better Greek language support.
Reduce size of language data (#4141) * Move Turkish lemmas to a json file Rather than a large dict in Python source, the data is now a big json file. This includes a method for loading the json file, falling back to a compressed file, and an update to MANIFEST.in that excludes json in the spacy/lang directory. This focuses on Turkish specifically because it has the most language data in core. * Transition all lemmatizer.py files to json This covers all lemmatizer.py files of a significant size (>500k or so). Small files were left alone. None of the affected files have logic, so this was pretty straightforward. One unusual thing is that the lemma data for Urdu doesn't seem to be used anywhere. That may require further investigation. * Move large lang data to json for fr/nb/nl/sv These are the languages that use a lemmatizer directory (rather than a single file) and are larger than English. For most of these languages there were many language data files, in which case only the large ones (>500k or so) were converted to json. It may or may not be a good idea to migrate the remaining Python files to json in the future. * Fix id lemmas.json The contents of this file were originally just copied from the Python source, but that used single quotes, so it had to be properly converted to json first. * Add .json.gz to gitignore This covers the json.gz files built as part of distribution. * Add language data gzip to build process Currently this gzip data on every build; it works, but it should be changed to only gzip when the source file has been updated. * Remove Danish lemmatizer.py Missed this when I added the json. * Update to match latest explosion/srsly#9 The way gzipped json is loaded/saved in srsly changed a bit. * Only compress language data if necessary If a .json.gz file exists and is newer than the corresponding json file, it's not recompressed. * Move en/el language data to json This only affected files >500kb, which was nouns for both languages and the generic lookup table for English. * Remove empty files in Norwegian tokenizer It's unclear why, but the Norwegian (nb) tokenizer had empty files for adj/adv/noun/verb lemmas. This may have been a result of copying the structure of the English lemmatizer. This removed the files, but still creates the empty sets in the lemmatizer. That may not actually be necessary. * Remove dubious entries in English lookup.json " furthest" and " skilled" - both prefixed with a space - were in the English lookup table. That seems obviously wrong so I have removed them. * Fix small issues with en/fr lemmatizers The en tokenizer was including the removed _nouns.py file, so that's removed. The fr tokenizer is unusual in that it has a lemmatizer directory with both __init__.py and lemmatizer.py. lemmatizer.py had not been converted to load the json language data, so that was fixed. * Auto-format * Auto-format * Update srsly pin * Consistently use pathlib paths
2019-08-20 12:54:11 +00:00
The first modification is that it checks if the word for lemmatization is
already a lemma and if yes, it just returns it.
The second modification is about removing the base forms function which is
not applicable for Greek language.
"""
@classmethod
def load(cls, path, index=None, exc=None, rules=None, lookup=None):
return cls(index, exc, rules, lookup)
def __init__(self, index=None, exceptions=None, rules=None, lookup=None):
self.index = index
self.exc = exceptions
self.rules = rules
self.lookup_table = lookup if lookup is not None else {}
def __call__(self, string, univ_pos, morphology=None):
if not self.rules:
return [self.lookup_table.get(string, string)]
if univ_pos in (NOUN, "NOUN", "noun"):
univ_pos = "noun"
elif univ_pos in (VERB, "VERB", "verb"):
univ_pos = "verb"
elif univ_pos in (ADJ, "ADJ", "adj"):
univ_pos = "adj"
elif univ_pos in (PUNCT, "PUNCT", "punct"):
univ_pos = "punct"
else:
return list(set([string.lower()]))
lemmas = lemmatize(
string,
self.index.get(univ_pos, {}),
self.exc.get(univ_pos, {}),
self.rules.get(univ_pos, []),
)
return lemmas
def lookup(self, string, orth=None):
key = orth if orth is not None else string
if key in self.lookup_table:
return self.lookup_table[key]
return string
def lemmatize(string, index, exceptions, rules):
string = string.lower()
forms = []
if string in index:
forms.append(string)
return forms
forms.extend(exceptions.get(string, []))
oov_forms = []
if not forms:
for old, new in rules:
if string.endswith(old):
form = string[: len(string) - len(old)] + new
if not form:
pass
elif form in index or not form.isalpha():
forms.append(form)
else:
oov_forms.append(form)
if not forms:
forms.extend(oov_forms)
if not forms:
forms.append(string)
return list(set(forms))