Merge pull request #1025 from PyThaiNLP/5.0.4

PyThaiNLP v5.0.4

Author: wannaphong

CITATION.cff

@@ -1,4 +1,4 @@
-cff-version: 1.1.0
+cff-version: "1.2.0"
 message: "If you use this software, please cite it as below."
 authors:
 - family-names: "Phatthiyaphaibun"
@@ -20,5 +20,6 @@ authors:
   given-names: "Pattarawat"
   orcid: "https://orcid.org/0000-0000-0000-0000"
 title: "PyThaiNLP: Thai Natural Language Processing in Python"
-version: v5.0.3
-date-released: 2024-05-12
+version: v5.0.4
+license: Apache-2.0
+date-released: 2024-06-02

README.md

@@ -23,7 +23,7 @@ PyThaiNLP เป็นไลบารีภาษาไพทอนสำหร
 
 | Version | Description | Status |
 |:------:|:--:|:------:|
-| [5.0.3](https://github.com/PyThaiNLP/pythainlp/releases) | Stable | [Change Log](https://github.com/PyThaiNLP/pythainlp/issues/788) |
+| [5.0.4](https://github.com/PyThaiNLP/pythainlp/releases) | Stable | [Change Log](https://github.com/PyThaiNLP/pythainlp/issues/788) |
 | [`dev`](https://github.com/PyThaiNLP/pythainlp/tree/dev) | Release Candidate for 5.1 | [Change Log](https://github.com/PyThaiNLP/pythainlp/issues/900) |
 
 ## Getting Started

README_TH.md

@@ -20,7 +20,7 @@ PyThaiNLP เป็นไลบารีภาษาไพทอนสำหร
 
 | รุ่น | คำอธิบาย | สถานะ |
 |:------:|:--:|:------:|
-| [5.0.3](https://github.com/PyThaiNLP/pythainlp/releases) | Stable | [Change Log](https://github.com/PyThaiNLP/pythainlp/issues/788) |
+| [5.0.4](https://github.com/PyThaiNLP/pythainlp/releases) | Stable | [Change Log](https://github.com/PyThaiNLP/pythainlp/issues/788) |
 | [`dev`](https://github.com/PyThaiNLP/pythainlp/tree/dev) | Release Candidate for 5.1  | [Change Log](https://github.com/PyThaiNLP/pythainlp/issues/900) |
 
 ติดตามพวกเราบน [PyThaiNLP Facebook page](https://www.facebook.com/pythainlp/) เพื่อรับข่าวสารเพิ่มเติม

pythainlp/__init__.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
 # SPDX-License-Identifier: Apache-2.0
-__version__ = "5.0.3"
+__version__ = "5.0.4"
 
 thai_consonants = "กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรลวศษสหฬอฮ"  # 44 chars
 

pythainlp/tag/thainer.py

@@ -83,7 +83,7 @@ class ThaiNameTagger:
     :Example:
     ::
 
-        from pythainlp.tag.named_entity import ThaiNameTagger
+        from pythainlp.tag.thainer import ThaiNameTagger
 
         thainer14 = ThaiNameTagger(version="1.4")
         thainer14.get_ner("วันที่ 15 ก.ย. 61 ทดสอบระบบเวลา 14:49 น.")
@@ -133,7 +133,7 @@ def get_ner(
 
         :Example:
 
-            >>> from pythainlp.tag.named_entity import ThaiNameTagger
+            >>> from pythainlp.tag.thainer import ThaiNameTagger
             >>>
             >>> ner = ThaiNameTagger()
             >>> ner.get_ner("วันที่ 15 ก.ย. 61 ทดสอบระบบเวลา 14:49 น.")

pythainlp/util/normalize.py

@@ -283,9 +283,12 @@ def maiyamok(sent: Union[str, List[str]]) -> List[str]:
         if "ๆ" == text:
             text = _list_word[i - 1]
         elif "ๆ" in text:
-            text = text.replace("ๆ", "")
-            _list_word.append(text)
+            count = text.count("ๆ")
+            text = _list_word[i - 1]
+            for _ in range(count):
+                _list_word.append(text)
             i += 1
+            continue
         _list_word.append(text)
         i += 1
     return _list_word

setup.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 5.0.3
+current_version = 5.0.4
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?

setup.py

@@ -161,7 +161,7 @@
 
 setup(
     name="pythainlp",
-    version="5.0.3",
+    version="5.0.4",
     description="Thai Natural Language Processing library",
     long_description=readme,
     long_description_content_type="text/markdown",

tests/test_util.py

@@ -531,6 +531,10 @@ def test_normalize(self):
             maiyamok("เด็กๆชอบไปโรงเรียน"),
             ["เด็ก", "เด็ก", "ชอบ", "ไป", "โรงเรียน"],
         )
+        self.assertEqual(
+            maiyamok("เด็กๆๆชอบไปโรงเรียน"),
+            ['เด็ก', 'เด็ก', 'เด็ก', 'ชอบ', 'ไป', 'โรงเรียน'],
+        ) # 914
         self.assertEqual(
             maiyamok(
                 ["ทำไม", "คน", "ดี", " ", "ๆ", "ๆ", " ", "ถึง", "ทำ", "ไม่ได้"]