Fixed mozillazg#290

修复 ``pypinyin.contrib.tone_convert`` 中 ``to_`` 开头的转换函数
没有正确处理输入的拼音包含 ``5`` 的场景（当包含 ``5`` 时会导致返回的格式不符合函数预期的返回格式）
以及修复没有正确处理部分拼音中的 ``ü`` 或 ``v`` 的问题
（当 ``v_to_u=False`` 时返回结果需要将 ``ü`` 替换为 ``v``）

>>> to_tone('lve')
'lve'
>>> to_tone2('lün5')
'lv5n'
>>> to_tone3('lün5')
'lv5n'
>>> to_tone2('lvn5')
'lv5n'
>>> to_tone3('lvn5')
'lv5n'

>>> to_tone('lve')
'lüe'
>>> to_tone2('lün5')
'lvn'
>>> to_tone3('lün5')
'lvn'
>>> to_tone2('lvn5')
'lvn'
>>> to_tone3('lvn5')
'lvn'
>>> to_tone2('lvn5', v_to_u=True)
'lün'
>>> to_tone3('lvn5', v_to_u=True)
'lün'
>>> to_tone2('lvn', neutral_tone_with_five=True)
'lv5n'
>>> to_tone3('lvn', neutral_tone_with_five=True)
'lvn5'

CHANGELOG.rst

@@ -2,10 +2,54 @@ Changelog
 ---------
 
 
+`0.48.0`_ (2023-mm-dd)
++++++++++++++++++++++++++
+
+* **[Bugfixed]** 修复 ``pypinyin.contrib.tone_convert`` 中 ``to_`` 开头的转换函数
+  没有正确处理输入的拼音包含 ``5`` 的场景（当包含 ``5`` 时会导致返回的格式不符合函数预期的返回格式）
+  以及修复没有正确处理部分拼音中的 ``ü`` 或 ``v`` 的问题
+  （当 ``v_to_u=False`` 时返回结果需要将 ``ü`` 替换为 ``v``） Fixed `#290`_ :
+
+  .. code-block:: python
+
+      # 修复前
+      >>> to_tone('lve')
+      'lve'
+      >>> to_tone2('lün5')
+      'lv5n'
+      >>> to_tone3('lün5')
+      'lv5n'
+      >>> to_tone2('lvn5')
+      'lv5n'
+      >>> to_tone3('lvn5')
+      'lv5n'
+
+      # 修复后
+      >>> to_tone('lve')
+      'lüe'
+      >>> to_tone2('lün5')
+      'lvn'
+      >>> to_tone3('lün5')
+      'lvn'
+      >>> to_tone2('lvn5')
+      'lvn'
+      >>> to_tone3('lvn5')
+      'lvn'
+      >>> to_tone2('lvn5', v_to_u=True)
+      'lün'
+      >>> to_tone3('lvn5', v_to_u=True)
+      'lün'
+      >>> to_tone2('lvn', neutral_tone_with_five=True)
+      'lv5n'
+      >>> to_tone3('lvn', neutral_tone_with_five=True)
+      'lvn5'
+
+
 `0.47.1`_ (2022-08-21)
 +++++++++++++++++++++++++
 
-* **[Bugfixed]** 修复无声母和韵母的场景下指定 neutral_tone_with_five=True 会返回 ``5`` 作为拼音的问题:
+* **[Bugfixed]** 修复无声母和韵母的场景下指定 neutral_tone_with_five=True 会返回
+  ``5`` 作为拼音的问题（`#284`_）:
 
   .. code-block:: python
 
@@ -915,6 +959,8 @@ __ https://github.com/mozillazg/python-pinyin/issues/8
 .. _#251: https://github.com/mozillazg/python-pinyin/issues/251
 .. _#266: https://github.com/mozillazg/python-pinyin/issues/266
 .. _#80: https://github.com/mozillazg/python-pinyin/issues/80
+.. _#284: https://github.com/mozillazg/python-pinyin/issues/284
+.. _#290: https://github.com/mozillazg/python-pinyin/issues/290
 .. _#164: https://github.com/mozillazg/python-pinyin/pull/164
 .. _#176: https://github.com/mozillazg/python-pinyin/pull/176
 .. _#279: https://github.com/mozillazg/python-pinyin/pull/279
@@ -1009,3 +1055,4 @@ __ https://github.com/mozillazg/python-pinyin/issues/8
 .. _0.46.0: https://github.com/mozillazg/python-pinyin/compare/v0.45.0...v0.46.0
 .. _0.47.0: https://github.com/mozillazg/python-pinyin/compare/v0.46.0...v0.47.0
 .. _0.47.1: https://github.com/mozillazg/python-pinyin/compare/v0.47.0...v0.47.1
+.. _0.48.0: https://github.com/mozillazg/python-pinyin/compare/v0.47.1...v0.48.0

docs/contrib.rst

@@ -17,33 +17,3 @@ contrib
 .. autofunction:: pypinyin.contrib.tone_convert.to_finals_tone
 .. autofunction:: pypinyin.contrib.tone_convert.to_finals_tone2
 .. autofunction:: pypinyin.contrib.tone_convert.to_finals_tone3
-
-.. autofunction:: pypinyin.contrib.tone_convert.tone_to_normal
-.. autofunction:: pypinyin.contrib.tone_convert.tone_to_tone2
-.. autofunction:: pypinyin.contrib.tone_convert.tone_to_tone3
-
-.. autofunction:: pypinyin.contrib.tone_convert.tone2_to_normal
-.. autofunction:: pypinyin.contrib.tone_convert.tone2_to_tone
-.. autofunction:: pypinyin.contrib.tone_convert.tone2_to_tone3
-
-.. autofunction:: pypinyin.contrib.tone_convert.tone3_to_normal
-.. autofunction:: pypinyin.contrib.tone_convert.tone3_to_tone
-.. autofunction:: pypinyin.contrib.tone_convert.tone3_to_tone2
-
-
-.. V2UMixin
-.. ---------
-
-.. .. autoclass:: pypinyin.contrib.uv.V2UMixin
-
-
-.. NeutralToneWith5Mixin
-.. -----------------------
-
-.. .. autoclass:: pypinyin.contrib.neutral_tone.NeutralToneWith5Mixin
-
-
-.. ToneSandhiMixin
-.. ----------------
-
-.. .. autoclass:: pypinyin.contrib.tone_sandhi.ToneSandhiMixin

pypinyin/style/_constants.py

@@ -88,9 +88,9 @@
 )
 
 # 匹配使用数字标识声调的字符的正则表达式
-RE_TONE2 = re.compile(r'([aeoiuvnmê])([1-5])$')
+RE_TONE2 = re.compile(r'([aeoiuvnmêü])([1-5])$')
 # 匹配 TONE2 中标识韵母声调的正则表达式
-RE_TONE3 = re.compile(r'^([a-zê]+)([1-5])([a-zê]*)$')
+RE_TONE3 = re.compile(r'^([a-zêü]+)([1-5])([a-zêü]*)$')
 
 # 匹配单个数字
 RE_NUMBER = re.compile(r'\d')

pypinyin/style/_tone_convert.py

@@ -63,6 +63,7 @@ def to_tone(pinyin):
       >>> to_tone('zhong1')
       'zhōng'
     """
+    pinyin = pinyin.replace('v', 'ü')
     if not _re_number.search(pinyin):
         return pinyin
 
@@ -104,6 +105,7 @@ def to_tone2(pinyin, v_to_u=False, neutral_tone_with_five=False, **kwargs):
     """
     if kwargs.get('neutral_tone_with_5', None) is not None:
         neutral_tone_with_five = kwargs['neutral_tone_with_5']
+    pinyin = pinyin.replace('5', '')
     s = tone_to_tone3(
         pinyin, v_to_u=True, neutral_tone_with_five=neutral_tone_with_five)
     s = tone3_to_tone2(s)
@@ -143,6 +145,7 @@ def to_tone3(pinyin, v_to_u=False, neutral_tone_with_five=False, **kwargs):
     """
     if kwargs.get('neutral_tone_with_5', None) is not None:
         neutral_tone_with_five = kwargs['neutral_tone_with_5']
+    pinyin = pinyin.replace('5', '')
     s = tone_to_tone2(
         pinyin, v_to_u=True, neutral_tone_with_five=neutral_tone_with_five)
     s = tone2_to_tone3(s)
@@ -255,6 +258,7 @@ def to_finals_tone2(pinyin, strict=True, v_to_u=False,
       'o1ng'
 
     """
+    pinyin = pinyin.replace('5', '')
     finals = to_finals_tone3(pinyin, strict=strict, v_to_u=v_to_u,
                              neutral_tone_with_five=neutral_tone_with_five)
 
@@ -287,6 +291,7 @@ def to_finals_tone3(pinyin, strict=True, v_to_u=False,
       'ong1'
 
     """
+    pinyin = pinyin.replace('5', '')
     finals = to_finals(pinyin, strict=strict, v_to_u=v_to_u)
     if not finals:
         return finals

tests/contrib/test_tone_convert.py

@@ -156,7 +156,6 @@ def test_tone_tone3_with_v_to_u(pinyin, v_to_u, result):
     ['a1', 'a1'],
     ['a', 'a'],
     ['shang', 'shang'],
-    ['sha5ng', 'shang5'],
 ])
 def test_tone2_tone3(pinyin, result):
     assert tone2_to_tone3(pinyin) == result
@@ -368,3 +367,148 @@ def test_tone_to_tone2_tone3_to_tone():
         tone3_2 = tone3_to_tone2(tone3)
         assert tone2_to_tone(tone3_2) == py
         assert to_tone(tone3_2) == py
+
+
+@mark.parametrize('input', [
+    'lün',
+    'lvn',
+
+    'lü5n',
+    'lün5',
+
+    'lv5n',
+    'lvn5',
+])
+def test_issue_290_1(input):
+    assert to_normal(input) == 'lvn'
+    assert to_normal(input, v_to_u=True) == 'lün'
+
+    assert to_tone(input) == 'lün'
+
+    assert to_tone2(input) == 'lvn'
+    assert to_tone2(input, neutral_tone_with_five=True) == 'lv5n'
+    assert to_tone2(input, v_to_u=True) == 'lün'
+    assert to_tone2(input, v_to_u=True, neutral_tone_with_five=True) == 'lü5n'
+
+    assert to_tone3(input) == 'lvn'
+    assert to_tone3(input, neutral_tone_with_five=True) == 'lvn5'
+    assert to_tone3(input, v_to_u=True) == 'lün'
+    assert to_tone3(input, v_to_u=True, neutral_tone_with_five=True) == 'lün5'
+
+    assert to_finals(input) == 'vn'
+    assert to_finals(input, v_to_u=True) == 'ün'
+
+    assert to_finals_tone(input) == 'ün'
+
+    assert to_finals_tone2(input) == 'vn'
+    assert to_finals_tone2(input, neutral_tone_with_five=True) == 'v5n'
+    assert to_finals_tone2(input, v_to_u=True) == 'ün'
+    assert to_finals_tone2(input, v_to_u=True,
+                           neutral_tone_with_five=True) == 'ü5n'
+
+    assert to_finals_tone3(input) == 'vn'
+    assert to_finals_tone3(input, neutral_tone_with_five=True) == 'vn5'
+    assert to_finals_tone3(input, v_to_u=True) == 'ün'
+    assert to_finals_tone3(input, v_to_u=True,
+                           neutral_tone_with_five=True) == 'ün5'
+
+
+@mark.parametrize('input', [
+    'lǘ',
+    'lü2',
+    'lv2',
+])
+def test_issue_290_2(input):
+    assert to_normal(input) == 'lv'
+    assert to_normal(input, v_to_u=True) == 'lü'
+
+    assert to_tone(input) == 'lǘ'
+
+    assert to_tone2(input) == 'lv2'
+    assert to_tone2(input, v_to_u=True) == 'lü2'
+
+    assert to_tone3(input) == 'lv2'
+    assert to_tone3(input, v_to_u=True) == 'lü2'
+
+    assert to_finals(input) == 'v'
+    assert to_finals(input, v_to_u=True) == 'ü'
+
+    assert to_finals_tone(input) == 'ǘ'
+
+    assert to_finals_tone2(input) == 'v2'
+    assert to_finals_tone2(input, v_to_u=True) == 'ü2'
+
+    assert to_finals_tone3(input) == 'v2'
+    assert to_finals_tone3(input, v_to_u=True) == 'ü2'
+
+
+@mark.parametrize('input', [
+    'lǘn',
+    'lü2n',
+    'lün2',
+    'lv2n',
+    'lvn2',
+])
+def test_issue_290_3(input):
+    assert to_normal(input) == 'lvn'
+    assert to_normal(input, v_to_u=True) == 'lün'
+
+    assert to_tone(input) == 'lǘn'
+
+    assert to_tone2(input) == 'lv2n'
+    assert to_tone2(input, v_to_u=True) == 'lü2n'
+
+    assert to_tone3(input) == 'lvn2'
+    assert to_tone3(input, v_to_u=True) == 'lün2'
+
+    assert to_finals(input) == 'vn'
+    assert to_finals(input, v_to_u=True) == 'ün'
+
+    assert to_finals_tone(input) == 'ǘn'
+
+    assert to_finals_tone2(input) == 'v2n'
+    assert to_finals_tone2(input, v_to_u=True) == 'ü2n'
+
+    assert to_finals_tone3(input) == 'vn2'
+    assert to_finals_tone3(input, v_to_u=True) == 'ün2'
+
+
+@mark.parametrize('input', [
+    'shang',
+    'sha5ng',
+    'shang5',
+])
+def test_issue_290_4(input):
+    assert to_normal(input) == 'shang'
+    assert to_normal(input, v_to_u=True) == 'shang'
+
+    assert to_tone(input) == 'shang'
+
+    assert to_tone2(input) == 'shang'
+    assert to_tone2(input, neutral_tone_with_five=True) == 'sha5ng'
+    assert to_tone2(input, v_to_u=True) == 'shang'
+    assert to_tone2(input, v_to_u=True,
+                    neutral_tone_with_five=True) == 'sha5ng'
+
+    assert to_tone3(input) == 'shang'
+    assert to_tone3(input, neutral_tone_with_five=True) == 'shang5'
+    assert to_tone3(input, v_to_u=True) == 'shang'
+    assert to_tone3(input, v_to_u=True,
+                    neutral_tone_with_five=True) == 'shang5'
+
+    assert to_finals(input) == 'ang'
+    assert to_finals(input, v_to_u=True) == 'ang'
+
+    assert to_finals_tone(input) == 'ang'
+
+    assert to_finals_tone2(input) == 'ang'
+    assert to_finals_tone2(input, neutral_tone_with_five=True) == 'a5ng'
+    assert to_finals_tone2(input, v_to_u=True) == 'ang'
+    assert to_finals_tone2(input, v_to_u=True,
+                           neutral_tone_with_five=True) == 'a5ng'
+
+    assert to_finals_tone3(input) == 'ang'
+    assert to_finals_tone3(input, neutral_tone_with_five=True) == 'ang5'
+    assert to_finals_tone3(input, v_to_u=True) == 'ang'
+    assert to_finals_tone3(input, v_to_u=True,
+                           neutral_tone_with_five=True) == 'ang5'