using third party python pinyin

third_party/phkit/phkit/__init__.py

@@ -100,7 +100,7 @@ readme_docs = [__doc__, version_doc,
 
 from .chinese import text_to_sequence as chinese_text_to_sequence, sequence_to_text as chinese_sequence_to_text
 from .english import text_to_sequence as english_text_to_sequence, sequence_to_text as english_sequence_to_text
-from .pinyinkit import lazy_pinyin, pinyin, slug, initialize
+from .pinyinkit import lazy_pinyin
 
 # 兼容0.1.0之前的版本，python3.7以上版本支持。
 from .chinese import convert, number, phoneme, sequence, symbol, style

third_party/phkit/phkit/chinese/convert.py

@@ -8,9 +8,9 @@
 
 全角半角转换，简体繁体转换。
 """
-from hanziconv import hanziconv
+from .hanziconv import HanziConv
 
-hc = hanziconv.HanziConv()
+hc = HanziConv()
 
 # 繁体转简体
 fan2jian = hc.toSimplified

third_party/phkit/phkit/chinese/hanziconv.py

@@ -0,0 +1,99 @@
+# Copyright 2014 Bernard Yue
+#
+# 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.
+#
+
+__doc__ = """
+Hanzi Converter 繁簡轉換器 | 繁简转换器
+This module provides functions converting chinese text between simplified and
+traditional characters.  It returns unicode represnetation of the text.
+Class HanziConv is the main entry point of the module, you can import the
+class by doing:
+    >>> from hanziconv import HanziConv
+"""
+
+import os
+from zhon import cedict
+
+class HanziConv():
+    """This class supports hanzi (漢字) convention between simplified and
+    traditional format"""
+    __traditional_charmap = cedict.traditional
+    __simplified_charmap = cedict.simplified
+
+    @classmethod
+    def __convert(cls, text, toTraditional=True):
+        """Convert `text` to Traditional characters if `toTraditional` is
+        True, else convert to simplified characters
+        :param text:           data to convert
+        :param toTraditional:  True -- convert to traditional text
+                               False -- covert to simplified text
+        :returns:              converted 'text`
+        """
+        if isinstance(text, bytes):
+            text = text.decode('utf-8')
+
+        fromMap = cls.__simplified_charmap
+        toMap = cls.__traditional_charmap
+        if not toTraditional:
+            fromMap = cls.__traditional_charmap
+            toMap = cls.__simplified_charmap
+
+        final = []
+        for c in text:
+            index = fromMap.find(c)
+            if index != -1:
+                final.append(toMap[index])
+            else:
+                final.append(c)
+        return ''.join(final)
+
+    @classmethod
+    def toSimplified(cls, text):
+        """Convert `text` to simplified character string.  Assuming text is
+        traditional character string
+        :param text:  text to convert
+        :returns:     converted UTF-8 characters
+        >>> from hanziconv import HanziConv
+        >>> print(HanziConv.toSimplified('繁簡轉換器'))
+        繁简转换器
+        """
+        return cls.__convert(text, toTraditional=False)
+
+    @classmethod
+    def toTraditional(cls, text):
+        """Convert `text` to traditional character string.  Assuming text is
+        simplified character string
+        :param text:  text to convert
+        :returns:     converted UTF-8 characters
+        >>> from hanziconv import HanziConv
+        >>> print(HanziConv.toTraditional('繁简转换器'))
+        繁簡轉換器
+        """
+        return cls.__convert(text, toTraditional=True)
+
+    @classmethod
+    def same(cls, text1, text2):
+        """Return True if text1 and text2 meant literally the same, False
+        otherwise
+        :param text1: string to compare to ``text2``
+        :param text2: string to compare to ``text1``
+        :returns:     **True**  -- ``text1`` and ``text2`` are the same in meaning,
+                      **False** -- otherwise
+        >>> from hanziconv import HanziConv
+        >>> print(HanziConv.same('繁简转换器', '繁簡轉換器'))
+        True
+        """
+        t1 = cls.toSimplified(text1)
+        t2 = cls.toSimplified(text2)
+        return t1 == t2

third_party/phkit/phkit/chinese/number.py

@@ -19,6 +19,14 @@ _number_group_re = re.compile(r"([0-9]+)")
 
 
 def say_digit(num: str):
+    """123 -> 一二三
+
+    Args:
+        num (str): [description]
+
+    Returns:
+        [type]: [description]
+    """
     outs = []
     for zi in num:
         outs.append(_number_cn[int(zi)])
@@ -31,6 +39,7 @@ def say_number(num: str):
         return _number_cn[0]
     elif len(x) > 16:
         return num
+    
     length = len(x)
     outs = []
     for num, zi in enumerate(x):

third_party/phkit/phkit/pinyinkit/__init__.py

@@ -3,8 +3,61 @@
 文本转拼音的模块，依赖python-pinyin，jieba，phrase-pinyin-data模块。
 """
 import re
-from .core import lazy_pinyin, pinyin, slug, Style, initialize
+#from .core import lazy_pinyin, Style
-from pypinyin.style import convert
+from .core import lazy_pinyin as lazy_pinyin_local
+from pypinyin import lazy_pinyin, Style, load_phrases_dict, load_phrases_dict
+
+
+def parse_pinyin_txt(inpath):
+    # U+4E2D: zhōng,zhòng  # 中
+    outs = []
+    with open(inpath, encoding="utf8") as fin:
+        for line in tqdm(fin, desc='load pinyin', ncols=80, mininterval=1):
+            if line.startswith("#"):
+                continue
+            res = _ziyin_re.search(line)
+            if res:
+                zi = res.group(3).strip()
+                if len(zi) == 1:
+                    outs.append([zi, res.group(2).strip().split(",")])
+                else:
+                    print(line)
+            elif line.strip():
+                print(line)
+    return {ord(z): ','.join(p) for z, p in outs}
+
+
+def parse_phrase_txt(inpath):
+    # 一一对应: yī yī duì yìng
+    outs = []
+    with open(inpath, encoding="utf8") as fin:
+        for line in tqdm(fin, desc='load phrase', ncols=80, mininterval=1):
+            if line.startswith("#"):
+                continue
+            parts = line.split(":")
+            zs = parts[0].strip()
+            ps = parts[1].strip().split()
+            if len(parts) == 2 and len(zs) == len(ps) and len(zs) >= 2:
+                outs.append([zs, ps])
+            elif line.strip():
+                print(line)
+    return {zs: [[p] for p in ps] for zs, ps in outs}
+
+
+def initialize():
+    # 导入数据
+    inpath = Path(__file__).absolute().parent.joinpath('phrase_pinyin.txt.py')
+    _phrases_dict = parse_phrase_txt(inpath)
+    load_phrases_dict(_phrases_dict)  # big:398815 small:36776
+
+    inpath = Path(__file__).absolute().parent.joinpath('single_pinyin.txt.py')
+    _pinyin_dict = parse_pinyin_txt(inpath)
+    load_single_dict(_pinyin_dict)  # 41451
+
+    jieba.initialize()
+    # for word, _ in tqdm(_phrases_dict.items(), desc='jieba add word', ncols=80, mininterval=1):
+    #     jieba.add_word(word)
+
 
 # 兼容0.1.0之前的版本。
 # 音调：5为轻声
@@ -21,6 +74,8 @@ def text2pinyin(text, errors=None, **kwargs):
     if errors is None:
         errors = default_errors
     pin = lazy_pinyin(text, style=Style.TONE3, errors=errors, strict=True, neutral_tone_with_five=True, **kwargs)
+    pino = lazy_pinyin_local(text, style=Style.TONE3, errors=errors, strict=True, neutral_tone_with_five=True, **kwargs)
+    assert pin == pino
     return pin
 
 

third_party/phkit/phkit/pinyinkit/core.py

@@ -6,11 +6,8 @@
 Base on python-pinyin(pypinyin), phrase-pinyin-data, pinyin-data and jieba.
 """
 
-from __future__ import unicode_literals
-
 from itertools import chain
 
-from pypinyin.compat import text_type
 from pypinyin.constants import (
     PHRASES_DICT, PINYIN_DICT, Style
 )
@@ -29,7 +26,6 @@ _true_pin_re = re.compile(r"[^a-zA-Z]+")
 
 is_initialized = False
 
-
 def load_single_dict(pinyin_dict, style='default'):
     """载入用户自定义的单字拼音库
 
@@ -152,7 +148,7 @@ class Pinyin(object):
 
         """
         # 对字符串进行分词处理
-        if isinstance(hans, text_type):
+        if isinstance(hans, str):
             han_list = self.seg(hans)
         else:
             han_list = chain(*(self.seg(x) for x in hans))

third_party/phkit/requirements.txt

@@ -1,5 +1,3 @@
-pypinyin
-hanziconv
 jieba
 inflect
 unidecode

third_party/phkit/setup.py

@@ -28,7 +28,7 @@ import logging
 
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(os.path.splitext(os.path.basename(__name__))[0])
-install_requires = ['pypinyin>=0.41.0', 'hanziconv', 'jieba>=0.42.1', 'tqdm', 'inflect', 'unidecode']
+install_requires = ['jieba>=0.42.1', 'tqdm', 'inflect', 'unidecode']
 requires = install_requires