Passed
Push — issue631-rest-api-language-det... ( 34c253...1cd800 )
by Osma
04:27
created

annif.simplemma_util.get_language_detector()   A

Complexity

Conditions 1

Size

Total Lines 2
Code Lines 2

Duplication

Lines 0
Ratio 0 %

Importance

Changes 0
Metric Value
cc 1
eloc 2
nop 1
dl 0
loc 2
rs 10
c 0
b 0
f 0
1
"""Wrapper code for using Simplemma functionality in Annif"""
2
3
from typing import Tuple, Union
4
5
from simplemma import LanguageDetector, Lemmatizer
6
from simplemma.strategies import DefaultStrategy
7
from simplemma.strategies.dictionaries import DefaultDictionaryFactory
8
9
LANG_CACHE_SIZE = 5  # How many language dictionaries to keep in memory at once (max)
10
11
_dictionary_factory = DefaultDictionaryFactory(cache_max_size=LANG_CACHE_SIZE)
12
_lemmatization_strategy = DefaultStrategy(dictionary_factory=_dictionary_factory)
13
lemmatizer = Lemmatizer(lemmatization_strategy=_lemmatization_strategy)
14
15
16
def get_language_detector(lang: Union[str, Tuple[str, ...]]) -> LanguageDetector:
17
    return LanguageDetector(lang, lemmatization_strategy=_lemmatization_strategy)
18