remove stanford

data.py

@@ -14,7 +14,6 @@
 from hazm.corpus_readers.peykare_reader import \
     coarse_pos_e as peykare_coarse_pos_e
 from hazm.dependency_parser import MaltParser, TurboParser
-from hazm.pos_tagger import StanfordPOSTagger
 
 
 def create_words_file(dic_file="tests/files/persian.dic", output="hazm/data/words.dat"):
@@ -381,48 +380,4 @@ def train_turboparser(
             "LAS;UAS",
         ]
     ).wait()
-
-
-def train_stanford_postagger(
-    peykare_root="tests/files/peykare",
-    path_to_model="tests/files/persian.tagger",
-    path_to_jar="tests/files/stanford_postagger.jar",
-    properties_file="tests/files/stanford-postagger.props",
-    memory_min="-Xms1g",
-    memory_max="-Xmx6g",
-    test_size=0.1,
-    pos_map=peykare_coarse_pos_e,
-):
-    peykare = PeykareReader(peykare_root, pos_map=pos_map)
-    train_file = "tests/files/tagger_train_data.txt"
-    train, test = train_test_split(
-        list(peykare.sents()), test_size=test_size, random_state=0
-    )
-
-    output = open(train_file, "w", "utf8")
-    for sentence in train:
-        print(*(["/".join(w).replace(" ", "_") for w in sentence]), file=output)
-    subprocess.Popen(
-        [
-            "java",
-            memory_min,
-            memory_max,
-            "-classpath",
-            path_to_jar,
-            "edu.stanford.nlp.tagger.maxent.MaxentTagger",
-            "-prop",
-            properties_file,
-            "-model",
-            path_to_model,
-            "-trainFile",
-            train_file,
-            "-tagSeparator",
-            "/",
-            "-search",
-            "owlqn2",
-        ]
-    ).wait()
-
-    tagger = StanfordPOSTagger(path_to_jar=path_to_jar, path_to_model=path_to_model)
-    print(tagger.evaluate(test))    
 

hazm/__init__.py

@@ -19,7 +19,6 @@
 from hazm.sequence_tagger import SequenceTagger
 
 from hazm.pos_tagger import POSTagger
-from hazm.pos_tagger import StanfordPOSTagger
 
 from hazm.stemmer import Stemmer
 from hazm.word_tokenizer import WordTokenizer

hazm/pos_tagger.py

@@ -1,7 +1,5 @@
 """این ماژول شامل کلاس‌ها و توابعی برای برچسب‌گذاری توکن‌هاست."""
 
-from nltk.tag import stanford
-
 from hazm import SequenceTagger
 
 punctuation_list = [
@@ -155,38 +153,3 @@ def tag_sents(self: "POSTagger", sentences):
             if self.__is_universal
             else tagged_sents
         )
-
-
-class StanfordPOSTagger(stanford.StanfordPOSTagger):
-    """StanfordPOSTagger."""
-
-    def __init__(
-        self: "StanfordPOSTagger",
-        model_filename: "str",
-        path_to_jar: str,
-        *args, # noqa: ANN002
-        **kwargs, # noqa: ANN003
-    ) -> None:
-        self._SEPARATOR = "/"
-        super(stanford.StanfordPOSTagger, self).__init__(
-            model_filename=model_filename,
-            path_to_jar=path_to_jar,
-            *args,  # noqa: B026
-            **kwargs,
-        )
-
-    def tag(self: "StanfordPOSTagger", tokens):
-        """tag.
-
-        Examples:
-            >>> tagger = StanfordPOSTagger(model_filename='persian.tagger', path_to_jar='stanford_postagger.jar')
-            >>> tagger.tag(['من', 'به', 'مدرسه', 'رفته_بودم', '.'])
-            [('من', 'PRO'), ('به', 'P'), ('مدرسه', 'N'), ('رفته_بودم', 'V'), ('.', 'PUNC')]
-
-        """
-        return self.tag_sents([tokens])[0]
-
-    def tag_sents(self: "StanfordPOSTagger", sentences):
-        """tag_sents."""
-        refined = ([w.replace(" ", "_") for w in s] for s in sentences)
-        return super(stanford.StanfordPOSTagger, self).tag_sents(refined)

tests/conftest.py

@@ -9,7 +9,6 @@
 from hazm import RuleBasedChunker
 from hazm import SentEmbedding
 from hazm import SentenceTokenizer
-from hazm import StanfordPOSTagger
 from hazm import Stemmer
 from hazm import TokenSplitter
 from hazm import WordEmbedding
@@ -48,10 +47,6 @@ def pos_tagger():
 def universal_pos_tagger():
     return POSTagger(model="tests/files/pos_tagger.model",universal_tag=True)
 
-@pytest.fixture(scope="session")
-def stanford_pos_tagger():
-    return StanfordPOSTagger(model_filename="tests/files/persian.tagger", path_to_jar="tests/files/stanford_postagger.jar")
-
 @pytest.fixture(scope="session")
 def token_splitter():
     return TokenSplitter()

tests/test_pos_tagger.py

@@ -19,9 +19,3 @@ def test_tag_sents_universal(self:"TestPOSTagger", universal_pos_tagger):
         actual = universal_pos_tagger.tag_sents([["من", "به", "مدرسه", "ایران", "رفته_بودم", "."]])
         expected = [[("من", "PRON"), ("به", "ADP"), ("مدرسه", "NOUN"), ("ایران", "NOUN"), ("رفته_بودم", "VERB"), (".", "PUNCT")]]
         assert actual == expected
-
-class TestStanfordPOSTagger:
-    def test_data_maker(self:"TestPOSTagger", stanford_pos_tagger):
-        actual = stanford_pos_tagger.tag(["من", "به", "مدرسه", "رفته_بودم", "."])
-        expected = [("من", "PRO"), ("به", "P"), ("مدرسه", "N"), ("رفته_بودم", "V"), (".", "PUNC")]
-        assert actual == expected