Dependencies: Upgrade Underthesea to 6.7.0

BLKSerene · Aug 6, 2023 · d1a3303 · d1a3303
1 parent 5917e37
commit d1a3303
Show file tree

Hide file tree

Showing 7 changed files with 8 additions and 7 deletions.
diff --git a/ACKNOWLEDGMENTS.md b/ACKNOWLEDGMENTS.md
@@ -52,5 +52,5 @@ As Wordless stands on the shoulders of giants, I hereby extend my sincere gratit
 27|[stopword](https://github.com/fergiemcdowall/stopword)             |2.0.5 |Fergus McDowall|[MIT](https://github.com/fergiemcdowall/stopword/blob/master/LICENSE)
 28|[SudachiPy](https://github.com/WorksApplications/sudachi.rs)       |0.6.7 |Works Applications Co., Ltd.|[Apache-2.0](https://github.com/WorksApplications/sudachi.rs/blob/develop/LICENSE)
 29|[TextBlob](https://github.com/sloria/TextBlob)                     |0.17.1|Steven Loria|[MIT](https://github.com/sloria/TextBlob/blob/dev/LICENSE)
-30|[Underthesea](https://undertheseanlp.com/)                         |6.2.0 |Vu Anh|[GPL-3.0-or-later](https://github.com/undertheseanlp/underthesea/blob/main/LICENSE)
+30|[Underthesea](https://undertheseanlp.com/)                         |6.7.0 |Vu Anh|[GPL-3.0-or-later](https://github.com/undertheseanlp/underthesea/blob/main/LICENSE)
 31|[wordcloud](https://github.com/amueller/word_cloud)                |1.9.2 |Andreas Christian Müller|[MIT](https://github.com/amueller/word_cloud/blob/main/LICENSE)
diff --git a/ACKNOWLEDGMENTS_zho_cn.md b/ACKNOWLEDGMENTS_zho_cn.md
@@ -52,5 +52,5 @@
 27|[stopword](https://github.com/fergiemcdowall/stopword)             |2.0.5 |Fergus McDowall|[MIT](https://github.com/fergiemcdowall/stopword/blob/master/LICENSE)
 28|[SudachiPy](https://github.com/WorksApplications/sudachi.rs)       |0.6.7 |Works Applications Co., Ltd.|[Apache-2.0](https://github.com/WorksApplications/sudachi.rs/blob/develop/LICENSE)
 29|[TextBlob](https://github.com/sloria/TextBlob)                     |0.17.1|Steven Loria|[MIT](https://github.com/sloria/TextBlob/blob/dev/LICENSE)
-30|[Underthesea](https://undertheseanlp.com/)                         |6.2.0 |Vu Anh|[GPL-3.0-or-later](https://github.com/undertheseanlp/underthesea/blob/main/LICENSE)
+30|[Underthesea](https://undertheseanlp.com/)                         |6.7.0 |Vu Anh|[GPL-3.0-or-later](https://github.com/undertheseanlp/underthesea/blob/main/LICENSE)
 31|[wordcloud](https://github.com/amueller/word_cloud)                |1.9.2 |Andreas Christian Müller|[MIT](https://github.com/amueller/word_cloud/blob/main/LICENSE)
diff --git a/ACKNOWLEDGMENTS_zho_tw.md b/ACKNOWLEDGMENTS_zho_tw.md
@@ -52,5 +52,5 @@
 27|[stopword](https://github.com/fergiemcdowall/stopword)             |2.0.5 |Fergus McDowall|[MIT](https://github.com/fergiemcdowall/stopword/blob/master/LICENSE)
 28|[SudachiPy](https://github.com/WorksApplications/sudachi.rs)       |0.6.7 |Works Applications Co., Ltd.|[Apache-2.0](https://github.com/WorksApplications/sudachi.rs/blob/develop/LICENSE)
 29|[TextBlob](https://github.com/sloria/TextBlob)                     |0.17.1|Steven Loria|[MIT](https://github.com/sloria/TextBlob/blob/dev/LICENSE)
-30|[Underthesea](https://undertheseanlp.com/)                         |6.2.0 |Vu Anh|[GPL-3.0-or-later](https://github.com/undertheseanlp/underthesea/blob/main/LICENSE)
+30|[Underthesea](https://undertheseanlp.com/)                         |6.7.0 |Vu Anh|[GPL-3.0-or-later](https://github.com/undertheseanlp/underthesea/blob/main/LICENSE)
 31|[wordcloud](https://github.com/amueller/word_cloud)                |1.9.2 |Andreas Christian Müller|[MIT](https://github.com/amueller/word_cloud/blob/main/LICENSE)
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -48,6 +48,7 @@
 - Dependencies: Upgrade PyThaiNLP to 4.0.2
 - Dependencies: Upgrade Requests to 2.31.0
 - Dependencies: Upgrade spaCy to 3.6.0
+- Dependencies: Upgrade Underthesea to 6.7.0
 - Dependencies: Upgrade wordcloud to 1.9.2
 
 ## [3.2.0](https://github.com/BLKSerene/Wordless/releases/tag/3.2.0) - 03/20/2023

diff --git a/requirements_tests.txt b/requirements_tests.txt
@@ -29,7 +29,7 @@ pythainlp == 4.0.2
 sacremoses == 0.0.53
 simplemma == 0.9.1
 textblob == 0.17.1
-underthesea == 6.2.0
+underthesea == 6.7.0
 
 ## python-mecab-ko
 python-mecab-ko == 1.3.3

diff --git a/tests/wl_tests_nlp/test_pos_tagging.py b/tests/wl_tests_nlp/test_pos_tagging.py
@@ -227,8 +227,8 @@ def test_pos_tag(lang, pos_tagger):
         else:
             tests_lang_util_skipped = True
     elif lang == 'vie':
-        assert tokens_tagged == [('Tiếng', 'N'), ('Việt', 'Np'), (',', 'CH'), ('cũng', 'R'), ('gọi là', 'X'), ('tiếng', 'N'), ('Việt Nam', 'Np'), ('[', 'V'), ('9 ]', 'N'), ('hay', 'C'), ('Việt ngữ', 'V'), ('là', 'V'), ('ngôn ngữ', 'N'), ('của', 'E'), ('người', 'Nc'), ('Việt', 'Np'), ('và', 'C'), ('là', 'V'), ('ngôn ngữ', 'N'), ('chính thức', 'A'), ('tại', 'E'), ('Việt Nam', 'Np'), ('.', 'CH')]
-        assert tokens_tagged_universal == [('Tiếng', 'NOUN'), ('Việt', 'PROPN'), (',', 'PUNCT'), ('cũng', 'X'), ('gọi là', 'X'), ('tiếng', 'NOUN'), ('Việt Nam', 'PROPN'), ('[', 'VERB'), ('9 ]', 'NOUN'), ('hay', 'CCONJ'), ('Việt ngữ', 'VERB'), ('là', 'VERB'), ('ngôn ngữ', 'NOUN'), ('của', 'ADP'), ('người', 'NOUN'), ('Việt', 'PROPN'), ('và', 'CCONJ'), ('là', 'VERB'), ('ngôn ngữ', 'NOUN'), ('chính thức', 'ADJ'), ('tại', 'ADP'), ('Việt Nam', 'PROPN'), ('.', 'PUNCT')]
+        assert tokens_tagged == [('Tiếng', 'N'), ('Việt', 'Np'), (',', 'CH'), ('cũng', 'R'), ('gọi là', 'X'), ('tiếng', 'N'), ('Việt Nam', 'Np'), ('[', 'V'), ('9', 'M'), (']', 'CH'), ('hay', 'C'), ('Việt ngữ', 'V'), ('là', 'V'), ('ngôn ngữ', 'N'), ('của', 'E'), ('người', 'Nc'), ('Việt', 'Np'), ('và', 'C'), ('là', 'V'), ('ngôn ngữ', 'N'), ('chính thức', 'A'), ('tại', 'E'), ('Việt Nam', 'Np'), ('.', 'CH')]
+        assert tokens_tagged_universal == [('Tiếng', 'NOUN'), ('Việt', 'PROPN'), (',', 'PUNCT'), ('cũng', 'X'), ('gọi là', 'X'), ('tiếng', 'NOUN'), ('Việt Nam', 'PROPN'), ('[', 'VERB'), ('9', 'NUM'), (']', 'PUNCT'), ('hay', 'CCONJ'), ('Việt ngữ', 'VERB'), ('là', 'VERB'), ('ngôn ngữ', 'NOUN'), ('của', 'ADP'), ('người', 'NOUN'), ('Việt', 'PROPN'), ('và', 'CCONJ'), ('là', 'VERB'), ('ngôn ngữ', 'NOUN'), ('chính thức', 'ADJ'), ('tại', 'ADP'), ('Việt Nam', 'PROPN'), ('.', 'PUNCT')]
     else:
         raise wl_test_init.Wl_Exception_Tests_Lang_Skipped(lang)
 

diff --git a/tests/wl_tests_nlp/test_word_tokenization.py b/tests/wl_tests_nlp/test_word_tokenization.py
@@ -339,7 +339,7 @@ def test_word_tokenize(lang, word_tokenizer):
         if word_tokenizer == 'nltk_tok_tok':
             assert tokens == ['Tiếng', 'Việt', ',', 'cũng', 'gọi', 'là', 'tiếng', 'Việt', 'Nam[', '9', ']', 'hay', 'Việt', 'ngữ', 'là', 'ngôn', 'ngữ', 'của', 'người', 'Việt', 'và', 'là', 'ngôn', 'ngữ', 'chính', 'thức', 'tại', 'Việt', 'Nam', '.']
         elif word_tokenizer == 'underthesea_vie':
-            assert tokens == ['Tiếng', 'Việt', ',', 'cũng', 'gọi là', 'tiếng', 'Việt Nam', '[', '9 ]', 'hay', 'Việt ngữ', 'là', 'ngôn ngữ', 'của', 'người', 'Việt', 'và', 'là', 'ngôn ngữ', 'chính thức', 'tại', 'Việt Nam', '.']
+            assert tokens == ['Tiếng', 'Việt', ',', 'cũng', 'gọi là', 'tiếng', 'Việt Nam', '[', '9', ']', 'hay', 'Việt ngữ', 'là', 'ngôn ngữ', 'của', 'người', 'Việt', 'và', 'là', 'ngôn ngữ', 'chính thức', 'tại', 'Việt Nam', '.']
         else:
             tests_lang_util_skipped = True
     elif lang == 'yor':