#534 fix

arekit/common/context/terms_mapper.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 
 from arekit.common.context.token import Token
 from arekit.common.entities.base import Entity
@@ -10,7 +10,7 @@ class TextTermsMapper(object):
     def iter_mapped(self, terms):
         """ Performs mapping operation of each terms in a sequence
         """
-        assert(isinstance(terms, collections.Iterable))
+        assert(isinstance(terms, Iterable))
 
         self._before_mapping()
 

arekit/common/data/input/providers/rows/base.py

@@ -1,4 +1,5 @@
-import collections
+from collections import Counter
+from collections.abc import Iterable
 import logging
 
 from arekit.common.data.input.providers.contents import ContentsProvider
@@ -39,9 +40,9 @@ def __iter_rows(self, linked_data, idle_mode):
 
     def iter_by_rows(self, contents_provider, doc_ids_iter, idle_mode):
         assert(isinstance(contents_provider, ContentsProvider))
-        assert(isinstance(doc_ids_iter, collections.Iterable))
+        assert(isinstance(doc_ids_iter, Iterable))
 
-        self.__rows_counter = collections.Counter()
+        self.__rows_counter = Counter()
 
         for linked_data in contents_provider.from_doc_ids(doc_ids=doc_ids_iter, idle_mode=idle_mode):
             assert(isinstance(linked_data, LinkedDataWrapper))

arekit/common/docs/parsed/base.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 
 from arekit.common.entities.base import Entity
 from arekit.common.text.enums import TermFormat
@@ -25,7 +25,7 @@ def __init__(self, doc_id, parsed_sentences):
         parsed_sentences: iterable of ParsedSentence type
             NOTE: Considered sentences with labeled Entities in it!
         """
-        assert(isinstance(parsed_sentences, collections.Iterable))
+        assert(isinstance(parsed_sentences, Iterable))
 
         self.__doc_id = doc_id
         self.__parsed_sentences = list(parsed_sentences)

arekit/common/frames/variants/collection.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 from arekit.common.frames.variants.base import FrameVariant
 
 
@@ -23,7 +23,7 @@ def __register_frame(frames_dict, frames_list, id):
     # region public methods
 
     def fill_from_iterable(self, variants_with_id, overwrite_existed_variant, raise_error_on_existed_variant):
-        assert(isinstance(variants_with_id, collections.Iterable))
+        assert(isinstance(variants_with_id, Iterable))
         assert(isinstance(overwrite_existed_variant, bool))
         assert(isinstance(raise_error_on_existed_variant, bool))
         assert(len(self.__variants) == 0)

arekit/common/linkage/base.py

@@ -1,10 +1,10 @@
-import collections
+from collections.abc import Iterable
 
 
 class LinkedDataWrapper(object):
 
     def __init__(self, linked_data):
-        assert(isinstance(linked_data, collections.Iterable))
+        assert(isinstance(linked_data, Iterable))
         self.__linked_data = list(linked_data)
         self.__tag = None
 

arekit/common/opinions/collection.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 
 from arekit.common import log_utils
 from arekit.common.labels.base import Label
@@ -23,7 +23,7 @@ def __init__(self, synonyms,
         raise_exception_on_duplicates: bool
             denotes whether there is a need to fire exception for duplicates in opinions list.
         """
-        assert(isinstance(opinions, collections.Iterable) or isinstance(opinions, type(None)))
+        assert(isinstance(opinions, Iterable) or isinstance(opinions, type(None)))
         assert(isinstance(synonyms, SynonymsCollection))
         assert(isinstance(error_on_duplicates, bool))
         assert(isinstance(error_on_synonym_end_missed, bool))

arekit/common/synonyms/base.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 
 from arekit.common import log_utils
 
@@ -12,7 +12,7 @@ def __init__(self, iter_group_values_lists=None, is_read_only=True, debug=False)
             debug: bool
                 utilized for logging the salient information during usage.
         """
-        assert(isinstance(iter_group_values_lists, collections.Iterable) or iter_group_values_lists is None)
+        assert(isinstance(iter_group_values_lists, Iterable) or iter_group_values_lists is None)
         assert(isinstance(is_read_only, bool))
         assert(isinstance(debug, bool))
 

arekit/common/text/partitioning/str.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 
 from arekit.common.bound import Bound
 from arekit.common.text.partitioning.base import BasePartitioning
@@ -11,7 +11,7 @@ class StringPartitioning(BasePartitioning):
 
     def provide(self, text, parts_it):
         assert(isinstance(text, str))
-        assert(isinstance(parts_it, collections.Iterable))
+        assert(isinstance(parts_it, Iterable))
 
         start = 0
         parts = []

arekit/common/text/partitioning/terms.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 
 from arekit.common.bound import Bound
 from arekit.common.text.partitioning.base import BasePartitioning
@@ -11,7 +11,7 @@ class TermsPartitioning(BasePartitioning):
 
     def provide(self, text, parts_it):
         assert(isinstance(text, list))
-        assert(isinstance(parts_it, collections.Iterable))
+        assert(isinstance(parts_it, Iterable))
 
         start = 0
         parts = []

arekit/contrib/networks/embedding.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 import numpy as np
 
 
@@ -31,7 +31,7 @@ def VocabularySize(self):
 
     @classmethod
     def from_word_embedding_pairs_iter(cls, word_embedding_pairs):
-        assert(isinstance(word_embedding_pairs, collections.Iterable))
+        assert(isinstance(word_embedding_pairs, Iterable))
 
         matrix = []
         words = []
@@ -51,7 +51,7 @@ def from_word_embedding_pairs_iter(cls, word_embedding_pairs):
 
     @classmethod
     def from_list_with_embedding_func(cls, words_iter, embedding_func):
-        assert(isinstance(words_iter, collections.Iterable))
+        assert(isinstance(words_iter, Iterable))
         assert(callable(embedding_func))
 
         matrix = []

arekit/contrib/utils/io_utils/utils.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 import logging
 from os.path import join, exists
 
@@ -25,7 +25,7 @@ def filename_template(data_type):
 
 
 def check_targets_existence(targets):
-    assert (isinstance(targets, collections.Iterable))
+    assert (isinstance(targets, Iterable))
 
     result = True
     for filepath in targets:

arekit/contrib/utils/pipelines/opinion_collections.py

@@ -1,4 +1,4 @@
-import collections
+from collections.abc import Iterable
 
 from arekit.common.labels.scaler.base import BaseLabelScaler
 from arekit.common.linkage.base import LinkedDataWrapper
@@ -18,7 +18,7 @@ def __create_labeled_opinion(item, label):
 
 
 def __linkages_to_opinions(linkages_iter, labels_helper, label_calc_mode):
-    assert(isinstance(linkages_iter, collections.Iterable))
+    assert(isinstance(linkages_iter, Iterable))
 
     for linkage in linkages_iter:
         assert(isinstance(linkage, LinkedDataWrapper))
@@ -31,7 +31,7 @@ def __linkages_to_opinions(linkages_iter, labels_helper, label_calc_mode):
 
 
 def __fill_opinion_collection(opinions_iter, collection, supported_labels):
-    assert(isinstance(opinions_iter, collections.Iterable))
+    assert(isinstance(opinions_iter, Iterable))
     assert(isinstance(collection, OpinionCollection))
     assert(isinstance(supported_labels, set) or supported_labels is None)
 

arekit/contrib/utils/serializer.py

@@ -1,6 +1,7 @@
-import collections
 import logging
 
+from collections.abc import Iterable
+
 from arekit.common.data.input.providers.columns.sample import SampleColumnsProvider
 from arekit.common.data.input.providers.rows.base import BaseRowProvider
 from arekit.common.data.input.repositories.base import BaseInputRepository
@@ -28,7 +29,7 @@ def create_samples_repo(keep_labels, rows_provider, storage):
     @staticmethod
     def fill_and_write(pipeline, repo, target, writer, doc_ids_iter, desc=""):
         assert(isinstance(pipeline, BasePipeline))
-        assert(isinstance(doc_ids_iter, collections.Iterable))
+        assert(isinstance(doc_ids_iter, Iterable))
         assert(isinstance(repo, BaseInputRepository))
 
         doc_ids = list(doc_ids_iter)

tests/text/test_nested_entities.py

@@ -0,0 +1,29 @@
+import unittest
+
+from arekit.common.text.parsed import BaseParsedText
+from arekit.common.text.parser import BaseTextParser
+from arekit.contrib.utils.pipelines.items.text.entities_default import TextEntitiesParser
+
+
+class TestNestedEntities(unittest.TestCase):
+
+    def test(self):
+        s = """24 марта президент [США] [Джо-Байден] провел переговоры с
+               лидерами стран [Евросоюза] в [Брюсселе] , вызвав внимание рынка и предположения о
+               том, что [Америке] удалось уговорить [ЕС] совместно бойкотировать российские нефть
+               и газ.  [[Европейский]-[Союз]] крайне зависим от [России] в плане поставок нефти и
+               газа."""
+
+        tep = TextEntitiesParser()
+
+        text_parser = BaseTextParser(pipeline=[
+            TextEntitiesParser(),
+        ])
+
+        parsed_text = text_parser.run(s.split())
+        assert(isinstance(parsed_text, BaseParsedText))
+        print(parsed_text._terms)
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/tutorials/test_tutorial_pipeline_sampling_bert.py

@@ -130,3 +130,7 @@ def test(self):
         source = join(self.__output_dir, "sample-train-0" + writer.extension())
         storage = reader.read(source)
         self.assertEqual(20, len(storage), "Amount of rows is non equal!")
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/tutorials/test_tutorial_pipeline_sampling_network.py

@@ -134,3 +134,7 @@ def test(self):
         source = join(self.__output_dir, "sample-train-0" + writer.extension())
         storage = reader.read(source)
         self.assertEqual(20, len(storage), "Amount of rows is non equal!")
+
+
+if __name__ == '__main__':
+    unittest.main()