Merge remote-tracking branch 'origin/develop'

.pre-commit-config.yaml

@@ -1,5 +1,5 @@
 repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks.git
+  - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v3.4.0
     hooks:
       - id: check-merge-conflict
@@ -11,7 +11,7 @@ repos:
         exclude: '.bumpversion.cfg'
       - id: requirements-txt-fixer
       - id: trailing-whitespace
-  - repo: https://gitlab.com/pycqa/flake8
+  - repo: https://github.com/pycqa/flake8
     rev: 3.8.4
     hooks:
       - id: flake8

.readthedocs.yaml

@@ -0,0 +1,35 @@
+# Read the Docs configuration file for Sphinx projects
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.12"
+    # You can also specify other tool versions:
+    # nodejs: "20"
+    # rust: "1.70"
+    # golang: "1.20"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+  # You can configure Sphinx to use a different builder, for instance use the dirhtml builder for simpler URLs
+  # builder: "dirhtml"
+  # Fail on all warnings to avoid broken references
+  # fail_on_warning: true
+
+# Optionally build your docs in additional formats such as PDF and ePub
+# formats:
+#   - pdf
+#   - epub
+
+# Optional but recommended, declare the Python requirements required
+# to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+# python:
+#   install:
+#     - requirements: docs/requirements.txt

CHANGELOG.rst

@@ -1,6 +1,38 @@
 Changelog
 ---------
 
+`0.51.0`_ (2024-03-10)
++++++++++++++++++++++++++
+
+* **[New]** 新增一个用于转换拼音风格的命令行辅助工具::
+
+    $ python -m pypinyin.tools.toneconvert to-tone 'zhong4 xin1'
+    zhòng xīn
+
+    $ python -m pypinyin.tools.toneconvert to-tone2 'zhòng xīn'
+    zho4ng xi1n
+
+    $ python -m pypinyin.tools.toneconvert to-tone3 'zhòng xīn'
+    zhong4 xin1
+
+    $ python -m pypinyin.tools.toneconvert to-normal 'zhòng xīn'
+    zhong xin
+
+* **[New]** ``pypinyin`` 命令行工具支持接受空格间隔的多个汉字词语作为输入（无需引号包裹）(via `#318`_ Thanks `@Freed-Wu`_) ::
+
+      # 老版本
+      $ pypinyin 我 是 小明
+      pypinyin: error: unrecognized arguments: 是 小明
+
+      # 新版本
+      $ pypinyin 我 是 小明
+      wǒ
+      shì
+      xiǎo míng
+
+* **[Improved]** 使用 `phrase-pinyin-data`_ v0.17.0 的词语拼音数据。
+
+
 `0.50.0`_ (2023-12-11)
 +++++++++++++++++++++++++
 
@@ -980,8 +1012,10 @@ __ https://github.com/mozillazg/python-pinyin/issues/8
 .. _#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
+.. _#318: https://github.com/mozillazg/python-pinyin/pull/318
 .. _@hanabi1224: https://github.com/hanabi1224
 .. _@yangwe1: https://github.com/yangwe1
+.. _@Freed-Wu: https://github.com/Freed-Wu
 .. _变调规则: https://en.wikipedia.org/wiki/Standard_Chinese_phonology#Tone_sandhi
 
 .. _0.2.0: https://github.com/mozillazg/python-pinyin/compare/v0.1.0...v0.2.0
@@ -1074,3 +1108,4 @@ __ https://github.com/mozillazg/python-pinyin/issues/8
 .. _0.48.0: https://github.com/mozillazg/python-pinyin/compare/v0.47.1...v0.48.0
 .. _0.49.0: https://github.com/mozillazg/python-pinyin/compare/v0.48.0...v0.49.0
 .. _0.50.0: https://github.com/mozillazg/python-pinyin/compare/v0.49.0...v0.50.0
+.. _0.51.0: https://github.com/mozillazg/python-pinyin/compare/v0.50.0...v0.51.0

README.rst

@@ -37,8 +37,6 @@
 使用示例
 --------
 
-Python 3(Python 2 下把 ``'中心'`` 替换为 ``u'中心'`` 即可):
-
 .. code-block:: python
 
     >>> from pypinyin import pinyin, lazy_pinyin, Style
@@ -80,7 +78,9 @@ Python 3(Python 2 下把 ``'中心'`` 替换为 ``u'中心'`` 即可):
 
     $ pypinyin 音乐
     yīn yuè
-    $ pypinyin -h
+
+    $ python -m pypinyin.tools.toneconvert to-tone 'zhong4 xin1'
+    zhòng xīn
 
 
 文档

docs/usage.rst

@@ -213,6 +213,10 @@
 命令行工具
 ------------
 
+
+pypinyin
+~~~~~~~~~~~
+
 程序内置了一个命令行工具 ``pypinyin`` :
 
 .. code-block:: console
@@ -283,4 +287,32 @@ CYRILLIC_FIRST     :py:attr:`~pypinyin.Style.CYRILLIC_FIRST`
 ================== =========================================
 
 
+toneconvert
+~~~~~~~~~~~~~
+
+通过 ``python -m pypinyin.tools.toneconvert`` 命令可以运行一个辅助转换拼音风格的工具::
+
+
+    $ python -m pypinyin.tools.toneconvert to-tone 'zhong4 xin1'
+    zhòng xīn
+
+**注意**: 当输入包含多个拼音时，必须使用空格或英文逗号分隔，该工具不支持多个拼音连在一起的输入。
+
+该工具支持的命令如下::
+
+    $ python -m pypinyin.tools.toneconvert -h
+
+    usage: toneconvert.py [-h] {to-normal,to-tone,to-tone2,to-tone3} ...
+
+    options:
+      -h, --help            show this help message and exit
+
+    subcommands:
+      {to-normal,to-tone,to-tone2,to-tone3}
+        to-normal           call pypinyin.contrib.tone_convert.to_normal() with inputs
+        to-tone             call pypinyin.contrib.tone_convert.to_tone() with inputs
+        to-tone2            call pypinyin.contrib.tone_convert.to_tone2() with inputs
+        to-tone3            call pypinyin.contrib.tone_convert.to_tone3() with inputs
+
+
 .. _《汉语拼音方案》: http://www.moe.gov.cn/s78/A19/yxs_left/moe_810/s230/195802/t19580201_186000.html

pypinyin/phrases_dict.py

@@ -75,6 +75,7 @@
     '一分一毫': [['yī'], ['fēn'], ['yī'], ['háo']],
     '一分为二': [['yī'], ['fēn'], ['wéi'], ['èr']],
     '一分子': [['yī'], ['fèn'], ['zi']],
+    '一分子甲烷': [['yī'], ['fēn'], ['zǐ'], ['jiǎ'], ['wán']],
     '一分钟': [['yì'], ['fēn'], ['zhōng']],
     '一切': [['yī'], ['qiè']],
     '一切万物': [['yī'], ['qiē'], ['wàn'], ['wù']],
@@ -3103,7 +3104,7 @@
     '九品中正': [['jiǔ'], ['pǐn'], ['zhōng'], ['zhèng']],
     '九回肠': [['jiǔ'], ['huí'], ['cháng']],
     '九垓八埏': [['jiǔ'], ['gāi'], ['bā'], ['yán']],
-    '九大行星': [['jiǔ'], ['dà'], ['háng'], ['xīng']],
+    '九大行星': [['jiǔ'], ['dà'], ['xíng'], ['xīng']],
     '九天九地': [['jiǔ'], ['tiān'], ['jiǔ'], ['dì']],
     '九天仙女': [['jiǔ'], ['tiān'], ['xiān'], ['nǚ']],
     '九头鸟': [['jiǔ'], ['tóu'], ['niǎo']],
@@ -5932,7 +5933,7 @@
     '克丁克卯': [['kè'], ['dīng'], ['kè'], ['mǎo']],
     '克什米尔': [['kè'], ['shí'], ['mǐ'], ['ěr']],
     '克传弓冶': [['kè'], ['chuán'], ['gōng'], ['yě']],
-    '克分子': [['kè'], ['fèn'], ['zǐ']],
+    '克分子': [['kè'], ['fēn'], ['zǐ']],
     '克尽厥职': [['kè'], ['jìn'], ['jué'], ['zhí']],
     '克尽职守': [['kè'], ['jìn'], ['zhí'], ['shǒu']],
     '克己慎行': [['kè'], ['jǐ'], ['shèn'], ['xíng']],
@@ -6063,6 +6064,7 @@
     '八卦教': [['bā'], ['guà'], ['jiào']],
     '八大山人': [['bā'], ['dà'], ['shān'], ['rén']],
     '八大胡同': [['bā'], ['dà'], ['hú'], ['tòng']],
+    '八大行星': [['bā'], ['dà'], ['xíng'], ['xīng']],
     '八字打开': [['bā'], ['zì'], ['dǎ'], ['kāi']],
     '八字没一撇': [['bā'], ['zì'], ['méi'], ['yī'], ['piě']],
     '八字没见一撇': [['bā'], ['zì'], ['méi'], ['jiàn'], ['yī'], ['piě']],
@@ -6111,6 +6113,7 @@
     '公共积累': [['gōng'], ['gòng'], ['jī'], ['lěi']],
     '公共课': [['gōng'], ['gòng'], ['kè']],
     '公分': [['gōng'], ['fēn']],
+    '公分子': [['gōng'], ['fēn'], ['zǐ']],
     '公切线': [['gōng'], ['qiē'], ['xiàn']],
     '公务员': [['gōng'], ['wù'], ['yuán']],
     '公助': [['gōng'], ['zhù']],
@@ -7318,13 +7321,20 @@
     '分头': [['fēn'], ['tóu']],
     '分娩': [['fēn'], ['miǎn']],
     '分子': [['fèn'], ['zǐ']],
-    '分子力': [['fèn'], ['zǐ'], ['lì']],
-    '分子式': [['fèn'], ['zǐ'], ['shì']],
-    '分子物理学': [['fèn'], ['zǐ'], ['wù'], ['lǐ'], ['xué']],
-    '分子生物学': [['fèn'], ['zǐ'], ['shēng'], ['wù'], ['xué']],
-    '分子筛': [['fèn'], ['zǐ'], ['shāi']],
-    '分子运动论': [['fèn'], ['zǐ'], ['yùn'], ['dòng'], ['lùn']],
-    '分子量': [['fèn'], ['zǐ'], ['liàng']],
+    '分子力': [['fēn'], ['zǐ'], ['lì']],
+    '分子和分母': [['fēn'], ['zǐ'], ['hé'], ['fēn'], ['mǔ']],
+    '分子式': [['fēn'], ['zǐ'], ['shì']],
+    '分子晶体': [['fēn'], ['zǐ'], ['jīng'], ['tǐ']],
+    '分子晶體': [['fēn'], ['zǐ'], ['jīng'], ['tǐ']],
+    '分子物理学': [['fēn'], ['zǐ'], ['wù'], ['lǐ'], ['xué']],
+    '分子生物学': [['fēn'], ['zǐ'], ['shēng'], ['wù'], ['xué']],
+    '分子生物學': [['fēn'], ['zǐ'], ['shēng'], ['wù'], ['xué']],
+    '分子筛': [['fēn'], ['zǐ'], ['shāi']],
+    '分子結構': [['fēn'], ['zǐ'], ['jié'], ['gòu']],
+    '分子结构': [['fēn'], ['zǐ'], ['jié'], ['gòu']],
+    '分子运动论': [['fēn'], ['zǐ'], ['yùn'], ['dòng'], ['lùn']],
+    '分子量': [['fēn'], ['zǐ'], ['liàng']],
+    '分子钟': [['fēn'], ['zǐ'], ['zhōng']],
     '分守要津': [['fēn'], ['shǒu'], ['yào'], ['jīn']],
     '分宜': [['fēn'], ['yí']],
     '分宵达曙': [['fēn'], ['xiāo'], ['dá'], ['shǔ']],
@@ -13820,7 +13830,7 @@
     '大藏经': [['dà'], ['zàng'], ['jīng']],
     '大虫': [['dà'], ['chóng']],
     '大行大市': [['dà'], ['háng'], ['dà'], ['shì']],
-    '大行星': [['dà'], ['háng'], ['xīng']],
+    '大行星': [['dà'], ['xíng'], ['xīng']],
     '大街': [['dà'], ['jiē']],
     '大街小巷': [['dà'], ['jiē'], ['xiǎo'], ['xiàng']],
     '大衣': [['dà'], ['yī']],
@@ -21217,6 +21227,7 @@
     '换约': [['huàn'], ['yuē']],
     '换脑筋': [['huàn'], ['nǎo'], ['jīn']],
     '换血': [['huàn'], ['xuè']],
+    '换行': [['huàn'], ['háng']],
     '换衣服': [['huàn'], ['yī'], ['fú']],
     '换骨夺胎': [['huàn'], ['gǔ'], ['duó'], ['tāi']],
     '换骨脱胎': [['huàn'], ['gǔ'], ['tuō'], ['tāi']],
@@ -21556,6 +21567,7 @@
     '揭露': [['jiē'], ['lù']],
     '援古刺今': [['yuán'], ['gǔ'], ['cì'], ['jīn']],
     '援款': [['yuán'], ['kuǎn']],
+    '援藏': [['yuán'], ['zàng']],
     '援鳖失龟': [['yuán'], ['biē'], ['shī'], ['guī']],
     '揽辔中原': [['lǎn'], ['pèi'], ['zhōng'], ['yuán']],
     '揽辔澄清': [['lǎn'], ['pèi'], ['chéng'], ['qīng']],
@@ -24783,6 +24795,7 @@
     '极少数': [['jí'], ['shǎo'], ['shù']],
     '极度': [['jí'], ['dù']],
     '极往知来': [['jí'], ['wǎng'], ['zhī'], ['lái']],
+    '极性分子': [['jí'], ['xìng'], ['fēn'], ['zǐ']],
     '极恶': [['jí'], ['è']],
     '极恶不赦': [['jí'], ['è'], ['bù'], ['shè']],
     '极恶穷凶': [['jí'], ['è'], ['qióng'], ['xiōng']],
@@ -25485,6 +25498,7 @@
     '楞头磕脑': [['léng'], ['tóu'], ['kē'], ['nǎo']],
     '楞眉横眼': [['lèng'], ['méi'], ['héng'], ['yǎn']],
     '楦头': [['xuàn'], ['tóu']],
+    '極性分子': [['jí'], ['xìng'], ['fēn'], ['zǐ']],
     '楷书': [['kǎi'], ['shū']],
     '楷体': [['kǎi'], ['tǐ']],
     '楷模': [['kǎi'], ['mó']],
@@ -28232,6 +28246,7 @@
     '漠不相关': [['mò'], ['bù'], ['xiāng'], ['guān']],
     '漠北': [['mò'], ['běi']],
     '漠南': [['mò'], ['nán']],
+    '漢藏': [['hàn'], ['zàng']],
     '漩涡': [['xuán'], ['wō']],
     '漫不加意': [['màn'], ['bù'], ['jiā'], ['yì']],
     '漫不经心': [['màn'], ['bù'], ['jīng'], ['xīn']],
@@ -39081,6 +39096,7 @@
     '超假': [['chāo'], ['jiǎ']],
     '超凡人圣': [['chāo'], ['fán'], ['rén'], ['shèng']],
     '超凡脱俗': [['chāo'], ['fán'], ['tuō'], ['sú']],
+    '超分子': [['chāo'], ['fēn'], ['zǐ']],
     '超员': [['chāo'], ['yuán']],
     '超导体': [['chāo'], ['dǎo'], ['tǐ']],
     '超市': [['chāo'], ['shì']],
@@ -44628,8 +44644,10 @@
     '高八度': [['gāo'], ['bā'], ['dù']],
     '高兴': [['gāo'], ['xìng']],
     '高冠博带': [['gāo'], ['guān'], ['bó'], ['dài']],
-    '高分子': [['gāo'], ['fèn'], ['zǐ']],
-    '高分子化合物': [['gāo'], ['fèn'], ['zǐ'], ['huà'], ['hé'], ['wù']],
+    '高分子': [['gāo'], ['fēn'], ['zǐ']],
+    '高分子功能材料': [['gāo'], ['fēn'], ['zǐ'], ['gōng'], ['néng'], ['cái'], ['liào']],
+    '高分子化合物': [['gāo'], ['fēn'], ['zǐ'], ['huà'], ['hé'], ['wù']],
+    '高分子化工': [['gāo'], ['fēn'], ['zǐ'], ['huà'], ['gōng']],
     '高压': [['gāo'], ['yā']],
     '高压电': [['gāo'], ['yā'], ['diàn']],
     '高压线': [['gāo'], ['yā'], ['xiàn']],

pypinyin/runner.py

@@ -77,7 +77,7 @@ def get_parser():
     parser.add_argument('-m', '--heteronym', help='enable heteronym',
                         action='store_true')
     # 要查询的汉字
-    parser.add_argument('hans', help='chinese string')
+    parser.add_argument('hans', nargs='+', help='chinese string')
     return parser
 
 
@@ -98,7 +98,9 @@ def main():
     parser = get_parser()
     options = parser.parse_args(args)
     if PY2:
-        hans = options.hans.decode(sys.stdin.encoding or 'utf-8')
+        hans = [
+            han.decode(sys.stdin.encoding or 'utf-8') for han in options.hans
+        ]
     else:
         hans = options.hans
     func = getattr(pypinyin, options.func)
@@ -121,20 +123,21 @@ def main():
     # 不输出任何字符，防止污染命令行命令的输出结果
     # 其实主要是为了干掉 jieba 内的 print 语句 ;)
     sys.stdout = sys.stderr = NullWriter()
-    result = func(hans, style=style, **kwargs)
+    results = [func(han, style=style, **kwargs) for han in hans]
     # 恢复默认
     sys.stdout = sys.__stdout__
     sys.stderr = sys.__stderr__
 
-    if not result:
-        print('')
-    elif result and isinstance(result, (list, tuple)):
-        if isinstance(result[0], (list, tuple)):
-            print(' '.join([','.join(s) for s in result]))
+    for result in results:
+        if not result:
+            print('')
+        elif result and isinstance(result, (list, tuple)):
+            if isinstance(result[0], (list, tuple)):
+                print(' '.join([','.join(s) for s in result]))
+            else:
+                print(result)
         else:
             print(result)
-    else:
-        print(result)
 
 
 if __name__ == '__main__':