Merge remote-tracking branch 'origin/develop'

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks.git
-    rev: v2.0.0
+    rev: v3.4.0
     hooks:
       - id: check-merge-conflict
       - id: debug-statements
@@ -11,5 +11,13 @@ repos:
         exclude: '.bumpversion.cfg'
       - id: requirements-txt-fixer
       - id: trailing-whitespace
+  - repo: https://gitlab.com/pycqa/flake8
+    rev: 3.8.4
+    hooks:
       - id: flake8
         exclude: 'tools|pypinyin/(phrases_dict.py|pinyin_dict.py|phonetic_symbol.py)|(docs/conf.py)'
+  # - repo: https://github.com/pre-commit/mirrors-mypy
+  #   rev: 'v0.812'
+  #   hooks:
+  #     - id: mypy
+  #       files: 'pypinyin/'

.whitesource

@@ -0,0 +1,12 @@
+{
+  "scanSettings": {
+    "baseBranches": []
+  },
+  "checkRunSettings": {
+    "vulnerableCheckRunConclusionLevel": "failure",
+    "displayMode": "diff"
+  },
+  "issueSettings": {
+    "minSeverityLevel": "LOW"
+  }
+}

CHANGELOG.rst

@@ -1,6 +1,15 @@
 Changelog
 ---------
 
+`0.41.0`_ (2021-03-13)
+++++++++++++++++++++++++
+
+* **[New]** 新增 ``pypinyin.contrib.tone_convert`` 模块，用于
+  ``Style.TONE`` 、 ``Style.TONE2`` 、 ``Style.TONE3`` 、 ``Style.NORMAL`` 风格的拼音之间互相转换。
+  详见 `文档 <https://pypinyin.readthedocs.io/zh_CN/develop/contrib.html#tone-convert>`__
+* **[Improved]** 使用 `pinyin-data`_ v0.10.2 的拼音数据。
+
+
 `0.40.0`_ (2020-11-22)
 ++++++++++++++++++++++++
 
@@ -891,3 +900,4 @@ __ https://github.com/mozillazg/python-pinyin/issues/8
 .. _0.39.0: https://github.com/mozillazg/python-pinyin/compare/v0.38.1...v0.39.0
 .. _0.39.1: https://github.com/mozillazg/python-pinyin/compare/v0.39.0...v0.39.1
 .. _0.40.0: https://github.com/mozillazg/python-pinyin/compare/v0.39.1...v0.40.0
+.. _0.41.0: https://github.com/mozillazg/python-pinyin/compare/v0.40.0...v0.41.0

Makefile

@@ -16,7 +16,11 @@ help:
 .PHONY: test
 test: lint
 	@echo "run test"
-	py.test --cov pypinyin tests/
+	make testonly
+
+.PHONY: testonly
+testonly:
+	py.test --random-order --cov pypinyin tests/ pypinyin/
 
 .PHONY: publish
 publish: clean

README.rst

@@ -106,6 +106,17 @@ FAQ
 
 详见 `文档 <https://pypinyin.readthedocs.io/zh_CN/master/usage.html#custom-dict>`__ 。
 
+如果是分词导致的拼音有误的话，可以先使用其他的分词模块对数据进行分词处理，
+然后将分词后的词组结果列表作为函数的参数即可:
+
+.. code-block:: python
+
+    >>> # 使用其他分词模块分词，比如 jieba 之类，
+    >>> #或者基于 phrases_dict.py 里的词语数据使用其他分词算法分词
+    >>> words = list(jieba.cut('每股24.67美元的确定性协议'))
+    >>> pinyin(words)
+
+
 为什么没有 y, w, yu 几个声母？
 ++++++++++++++++++++++++++++++++++++++++++++
 

docs/contrib.rst

@@ -3,6 +3,28 @@
 contrib
 ========
 
+.. _tone_convert:
+
+拼音转换
+--------
+
+.. autofunction:: pypinyin.contrib.tone_convert.to_normal
+.. autofunction:: pypinyin.contrib.tone_convert.to_tone
+.. autofunction:: pypinyin.contrib.tone_convert.to_tone2
+.. autofunction:: pypinyin.contrib.tone_convert.to_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
 ---------

docs/usage.rst

@@ -148,7 +148,8 @@
     Out[7]: ['ū']
 
 
-当 ``strict=True`` 时根据 `《汉语拼音方案》`_ 的如下规则处理声母、在韵母相关风格下还原正确的韵母：
+当 ``strict=True`` 时根据 `《汉语拼音方案》`_ 的如下规则处理声母、在韵母相关风格下还原正确的韵母
+（只对只获取声母或只获取韵母相关拼音风格有效，不影响其他获取完整拼音信息的拼音风格的结果）：
 
 * 21 个声母： ``b p m f d t n l g k h j q x zh ch sh r z c s`` （**y, w 不是声母**）
 * i行的韵母，前面没有声母的时候，写成yi(衣)，ya(呀)，ye(耶)，yao(腰)，you(忧)，yan(烟)，

pypinyin/contrib/_tone_rule.py

@@ -23,23 +23,23 @@
 """
 
 
-def right_mark_index(pinyin_no_number):
+def right_mark_index(pinyin_no_tone):
     # 有 ɑ 不放过, 没 ɑ 找 o、e
     for c in ['a', 'o', 'e']:
-        if c in pinyin_no_number:
-            return pinyin_no_number.index(c)
+        if c in pinyin_no_tone:
+            return pinyin_no_tone.index(c)
 
     # i、u 若是连在一起，谁在后面就标谁
     for c in ['iu', 'ui']:
-        if c in pinyin_no_number:
-            return pinyin_no_number.index(c) + 1
+        if c in pinyin_no_tone:
+            return pinyin_no_tone.index(c) + 1
 
     # ɑ、o、e、i、u、ü
     for c in ['i', 'u', 'v', 'ü']:
-        if c in pinyin_no_number:
-            return pinyin_no_number.index(c)
+        if c in pinyin_no_tone:
+            return pinyin_no_tone.index(c)
 
     # n, m, ê
     for c in ['n', 'm', 'ê']:
-        if c in pinyin_no_number:
-            return pinyin_no_number.index(c)
+        if c in pinyin_no_tone:
+            return pinyin_no_tone.index(c)

pypinyin/contrib/_tone_rule.pyi

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-from typing import Text
+from typing import Text, Optional
 
 
-def right_mark_index(pinyin_no_number: Text) -> int: ...
+def right_mark_index(pinyin_no_number: Text) -> Optional[int]: ...