Add pythainlp.util.rhyme

Author: wannaphong

docs/api/util.rst

@@ -38,6 +38,7 @@ Modules
 .. autofunction:: remove_tonemark
 .. autofunction:: remove_zw
 .. autofunction:: reorder_vowels
+.. autofunction:: rhyme
 .. autofunction:: sound_syllable
 .. autofunction:: syllable_length
 .. autofunction:: syllable_open_close_detector

pythainlp/util/__init__.py

@@ -45,6 +45,7 @@
     "remove_tonemark",
     "remove_zw",
     "reorder_vowels",
+    "rhyme",
     "text_to_arabic_digit",
     "text_to_thai_digit",
     "thai_digit_to_arabic_digit",
@@ -127,3 +128,4 @@
 from pythainlp.util.encoding import tis620_to_utf8
 import pythainlp.util.spell_words as spell_words
 from pythainlp.util.abbreviation import abbreviation_to_full_text
+from pythainlp.util.pronounce import rhyme

pythainlp/util/pronounce.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+# Copyright (C) 2016-2023 PyThaiNLP Project
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from typing import List
+
+from pythainlp.corpus import thai_words
+from pythainlp.tokenize import syllable_tokenize
+from pythainlp.khavee import KhaveeVerifier
+
+
+kv = KhaveeVerifier()
+all_thai_words_dict = [i for i in list(thai_words()) if len(syllable_tokenize(i))==1]
+
+
+def rhyme(word: str)->List[str]:
+    """
+    Find Thai rhyme
+
+    :param str word: A Thai word
+    :return: All list Thai rhyme words
+    :rtype: List[str]
+
+    :Example:
+    ::
+        from pythainlp.util import rhyme
+
+        print(rhyme("จีบ"))
+        # output: ['กลีบ', 'กีบ', 'ครีบ', ...]
+    """
+    list_sumpus=[]
+    for i in all_thai_words_dict:
+        if kv.is_sumpus(word,i) and i!=word:
+            list_sumpus.append(i)
+    return sorted(list_sumpus)

tests/test_util.py

@@ -36,6 +36,7 @@
     remove_dup_spaces,
     remove_tonemark,
     remove_zw,
+    rhyme,
     text_to_arabic_digit,
     text_to_thai_digit,
     thaiword_to_date,
@@ -853,5 +854,9 @@ def test_spell_word(self):
         self.assertEqual(spell_word("คน"),['คอ', 'นอ', 'คน'])
         self.assertEqual(spell_word("คนดี"),['คอ', 'นอ', 'คน', 'ดอ', 'อี', 'ดี', 'คนดี'])
 
+    def test_rhyme(self):
+        self.assertIsInstance(rhyme("แมว"), list)
+        self.assertTrue(len(rhyme("แมว")) > 2)
+
     # def test_abbreviation_to_full_text(self):
     #     self.assertIsInstance(abbreviation_to_full_text("รร.ของเราน่าอยู่", list))