Merge pull request #875 from PyThaiNLP/add-thai_to_idn

Add pythainlp.util.to_idn

Author: wannaphong

docs/api/util.rst

@@ -218,6 +218,11 @@ Modules
 
     The `thai_to_eng` function is a text conversion tool for translating Thai text into its English transliterated form. This is beneficial for rendering Thai words and phrases in an English context.
 
+.. autofunction:: to_idna
+    :noindex:
+
+    The `to_idna` function is a text conversion tool for translating Thai text into its  International Domain Name (IDN) for Thai domain name.
+
 .. autofunction:: thai_word_tone_detector
     :noindex:
 

pythainlp/util/__init__.py

@@ -51,6 +51,7 @@
     "thai_strptime",
     "thai_strftime",
     "thai_to_eng",
+    "to_idna",
     "thai_word_tone_detector",
     "thaiword_to_date",
     "thaiword_to_num",
@@ -117,7 +118,7 @@
     syllable_open_close_detector,
 )
 from pythainlp.util.phoneme import nectec_to_ipa, ipa_to_rtgs, remove_tone_ipa
-from pythainlp.util.encoding import tis620_to_utf8
+from pythainlp.util.encoding import to_idna, tis620_to_utf8
 from pythainlp.util import spell_words
 from pythainlp.util.abbreviation import abbreviation_to_full_text
 from pythainlp.util.pronounce import rhyme

pythainlp/util/encoding.py

@@ -5,8 +5,8 @@ def tis620_to_utf8(text: str)->str:
     """
     Convert TIS-620 to UTF-8
 
-    :param str text: Text that uses TIS-620 encoding
-    :return: Text that uses UTF-8 encoding
+    :param str text: TIS-620 encoded text
+    :return: UTF-8 encoded text
     :rtype: str
 
     :Example:
@@ -18,3 +18,22 @@ def tis620_to_utf8(text: str)->str:
         # output: 'กระทรวงอุตสาหกรรม'
     """
     return text.encode("cp1252", "ignore").decode("tis-620")
+
+
+def to_idna(text: str) -> str:
+    """
+    Encode text with IDNA, as used in Internationalized Domain Name (IDN).
+
+    :param str text: Thai text
+    :return: IDNA-encoded text
+    :rtype: str
+
+    :Example:
+    ::
+
+        from pythainlp.util import to_idna
+
+        to_idna("คนละครึ่ง.com")
+        # output: 'xn--42caj4e6bk1f5b1j.com'
+    """
+    return text.encode("idna").decode("utf-8")

tests/test_util.py

@@ -45,6 +45,7 @@
     thaiword_to_time,
     time_to_thaiword,
     thai_to_eng,
+    to_idna,
     thaiword_to_num,
     thai_keyboard_dist,
     text_to_num,
@@ -780,6 +781,9 @@ def test_syllable_open_close_detector(self):
         self.assertEqual(syllable_open_close_detector("มาก"), "close")
         self.assertEqual(syllable_open_close_detector("คะ"), "open")
 
+    def test_to_idna(self):
+        self.assertEqual(to_idna("คนละครึ่ง.com"), "xn--42caj4e6bk1f5b1j.com")
+
     def test_thai_word_tone_detector(self):
         self.assertIsNotNone(thai_word_tone_detector("คนดี"))
         self.assertEqual(