v2.0.0 upload

Author: ThanatosDi

allow_setting.json

@@ -3,16 +3,18 @@
 import mimetypes
 import os
 import re
+import shutil
 import sys
+import time
 import zipfile
-import chardet
-import logging
+from configparser import ConfigParser
 
 from modules.console import Console
-from modules.utils.error import FileTypeError, FileUnzipError, ConfigError
 from modules.logger import Logger
 from modules.opencc import OpenCC
-from modules.utils.tools import get_key, resource_path
+from modules.utils.error import (ConfigError, FileTypeError, FileUnzipError,
+                                 ZhConvertError)
+from modules.utils.tools import encoding, get_key, resource_path
 from modules.zhconvert import ZhConvert
 
 
@@ -26,14 +28,15 @@ def __init__(self):
         Objects:
             logger -- log記錄檔物件
             workpath -- 本程式所在的絕對路徑
-            config -- 讀取本程式路徑底下的 config.json 設定檔內容
+            cfg -- 讀取本程式路徑底下的 config.ini 設定檔內容
             convert_file_list -- 執行 unzip 方法後取得 EPub 中需要轉換的檔案之絕對路徑清單(list)
             new_filename -- 轉換後的 EPub 檔案的檔案名稱
         """
-        self.logger = Logger(name='EPUB')
         self.workpath = os.path.abspath(
             os.path.join(sys.argv[0], os.path.pardir))
-        self.config = self._read_config(f'{self.workpath}/config.json')
+        self.logger = Logger(
+            name='EPUB', workpath=self.workpath)
+        self.cfg = self._read_config(f'{self.workpath}/config.ini')
         self.convert_file_list = None
         self.file_path = None
 
@@ -45,21 +48,23 @@ def _read_config(self, config):
         """
         if os.path.exists(config):
             self.logger.info('_read_config', 'read config')
-            with open(config, 'r', encoding='utf-8') as r_c:
-                config = json.loads(r_c.read())
+            cfg = ConfigParser()
+            cfg_encoding = encoding(config)['encoding']
+            self.logger.info('_read_config encoding',encoding(config)['encoding'])
+            cfg.read(config, encoding=cfg_encoding)
             self.logger.info(
-                '_read_config', f"Aleady read config\nengine: {config['engine']}\nconverter: {config['converter']}\nformat: {config['format']}")
-            return config
+                '_read_config', f"already read config\nengine: {cfg['setting']['engine']}\nconverter: {cfg['setting']['converter']}\nformat: {cfg['setting']['format']}")
+            return cfg
         else:
-            print('error')
+            self.logger.info(f'_read_config', f'can\'t find "config.ini", please check config file.')
+
+    """ def _read_allow_setting(self, config):
+        '''讀取允許設定
 
-    def _read_allow_setting(self, config):
-        """讀取允許設定
-        
         Arguments:
             config {str} -- allow_setting.json path
-        """
-        print(resource_path('allow_setting.json'))
+        '''
+        print(resource_path('allow_setting.json')) """
 
     @property
     def _zip(self):
@@ -103,6 +108,7 @@ def convert(self, epub_file_path):
         """
         try:
             self.file_path = epub_file_path
+            self.logger.info('convert', f'file path: {self.file_path}')
             self._check(epub_file_path)
             self._unzip(epub_file_path)
             if self.convert_file_list:
@@ -111,10 +117,10 @@ def convert(self, epub_file_path):
                 self._convert_content(self.convert_file_list)
                 self._rename(self.convert_file_list)
                 self._zip
-                # self._clean
+                self._clean
+            self.logger.info('convert', f'success convert {os.path.basename(epub_file_path)}')
         except Exception as e:
             self.logger.error('convert', f'{str(e)}')
-            os.system('pause')
 
     def _rename(self, convert_file_list):
         """重新命名已轉換的檔案
@@ -132,7 +138,7 @@ def _filename(self):
             "s2t": ["s2t", "s2tw", "Traditional", "Taiwan", "WikiTraditional"],
             "t2s": ["t2s", "tw2s", "Simplified", "China", "WikiSimplified"]
         }
-        converter = get_key(converter_dict, self.config['converter'])
+        converter = get_key(converter_dict, self.cfg['setting']['converter'])
         openCC = OpenCC(converter)
         new_filename = openCC.convert(os.path.basename(self.file_path))
         return os.path.join(os.path.dirname(self.file_path), new_filename)
@@ -159,42 +165,65 @@ def _convert_content(self, convert_file_list):
             "format": ["Straight", "Horizontal"]
         }
         # 檢查設定檔是否有無錯誤
-        if self.config['engine'] not in setting['engine']:
-            raise ConfigError('Engine is not a right engine in "config.json"')
-        if self.config['converter'] not in setting['converter'][self.config['engine']]:
+        if self.cfg['setting']['engine'] not in setting['engine']:
+            raise ConfigError('Engine is not a right engine in "config.ini"')
+        if self.cfg['setting']['converter'] not in setting['converter'][self.cfg['setting']['engine']]:
             raise ConfigError(
-                'Converter is not a right converter in "config.json"')
-        if self.config['format'] not in setting['format']:
-            raise ConfigError('Format is not a right format in "config.json"')
+                'Converter is not a right converter in "config.ini"')
+        if self.cfg['setting']['format'] not in setting['format']:
+            raise ConfigError('Format is not a right format in "config.ini"')
         # 判斷轉換引擎並轉換
-        if self.config['engine'].lower() == 'opencc':
+        if self.cfg['setting']['engine'].lower() == 'opencc':
             self.logger.debug('convert_text', 'engine: opencc')
             for f in convert_file_list:
                 self.logger.debug(
                     'convert_text', f'now convert "{os.path.basename(f)}"')
                 self._content_opt_lang(f)
-                self._opencc(self.config['converter'], f)
-        if self.config['engine'].lower() == 'zhconvert':
+                self._opencc(self.cfg['setting']['converter'], f)
+        if self.cfg['setting']['engine'].lower() == 'zhconvert':
             self.logger.debug('convert_text', 'engine: zhconvert 繁化姬')
             for f in convert_file_list:
+                self.logger.debug(
+                    'convert_text', f'now convert "{os.path.basename(f)}"')
                 self._content_opt_lang(f)
+                self._zhconvert(self.cfg['setting']['converter'], f)
 
     def _opencc(self, converter, file):
-        """opencc 轉換作業
+        """opencc
 
         Arguments:
-            converter {str} -- config.json 中 converter 設定，轉換模式
+            converter {str} -- config.ini 中 converter 設定，轉換模式
             file {str} -- 欲進行文字轉換的內文文檔的絕對路徑
         """
         openCC = OpenCC(converter)
-        f_r = open(file, 'r', encoding='utf-8').readlines()
+        f_encoding = encoding(file)['encoding']
+        start_time = time.time()
+        f_r = open(file, 'r', encoding=f_encoding).readlines()
         with open(file + '.new', 'w', encoding='utf-8') as f_w:
             for line in f_r:
                 converted = openCC.convert(line)
                 f_w.write(converted)
+        end_time = time.time()
+        self.logger.info('_opencc', f'convert file: {os.path.basename(file)} cost {"{:.2f}".format(end_time-start_time)}s')
 
-    def _zhconvert(self, converter):
-        """  """
+    def _zhconvert(self, converter, file):
+        """zhconvert 繁化姬
+        
+        Arguments:
+            converter {str} -- config.ini 中 converter 設定，轉換模式
+            file {str} -- 欲進行文字轉換的內文文檔的絕對路徑
+        """
+        zhconvert = ZhConvert()
+        f_encoding = encoding(file)['encoding']
+        start_time = time.time()
+        with open(file, 'r', encoding=f_encoding) as f_r:
+            zhconvert.convert(text=f_r.read(), converter=converter)
+            with open(file + '.new', 'w', encoding='utf-8') as f_w:
+                if zhconvert.text is None:
+                    raise ZhConvertError()
+                f_w.write(zhconvert.text)
+        end_time = time.time()
+        self.logger.info('_zhconvert', f'convert file: {os.path.basename(file)} cost {"{:.2f}".format(end_time-start_time)}s')
 
     def _content_opt_lang(self, content_file_path):
         """修改 content.opf 中語言標籤的值
@@ -210,21 +239,51 @@ def _content_opt_lang(self, content_file_path):
             regex = re.compile(
                 r"<dc:language>[\S]*</dc:language>", re.IGNORECASE)
             fileline = open(content_file_path, encoding='utf-8').read()
-            if self.config['converter'] in converter["zh-TW"]:
+            if self.cfg['setting']['converter'] in converter["zh-TW"]:
                 self.logger.info('_content_lang', 'convert language to zh-TW')
                 modify = re.sub(
                     regex, f'<dc:language>zh-TW</dc:language>', fileline)
-            if self.config['converter'] in converter["zh-CN"]:
+            if self.cfg['setting']['converter'] in converter["zh-CN"]:
                 self.logger.info('_content_lang', 'convert language to zh-CN')
                 modify = re.sub(
                     regex, f'<dc:language>zh-CN</dc:language>', fileline)
             open(content_file_path, 'w', encoding='utf-8').write(modify)
 
-    def _format(self):
-        """  """
+    # def _format(self, file_path):
+    #     """  """
+    #     modify_files = {}
+    #     opf_tmp = []
+    #     css_tmp = []
+    #     content_tmp = []
+    #     for root, _dirs, files in os.walk(f'{file_path}_files/'):
+    #         for filename in files:
+    #             if filename.endswith('opf'):
+    #                 opf_tmp.append(filename)
+    #             if filename.endswith('css'):
+    #                 css_tmp.append(filename)
+    #             if filename.endswith(('xhtml', 'html', 'htm')):
+    #                 content_tmp.append(filename)
+    #     modify_files['opf'] = opf_tmp
+    #     modify_files['css'] = css_tmp
+    #     modify_files['content'] = content_tmp
+    #     #橫式
+    #     if self.cfg['setting']['format'].lower() == 'horizontal':
+    #         self.logger.info('_format', 'set content to horizontal')
+    #         if not any(modify_files['css']):
+    #             print('css file not found')
+    #     #直式
+    #     if self.cfg['setting']['format'].lower() == 'straight':
+    #         self.logger.info('_format', 'set content to straight')
+    #         print('直式')
 
+    @property
     def _clean(self):
-        """  """
+        """ 清除解壓縮後的檔案 """
+        if os.path.isdir( f'{self.file_path}_files'):
+            self.logger.info('_clean', f'delete tmp files: {self.file_path}_files')
+            shutil.rmtree(f'{self.file_path}_files')
+        else:
+            self.logger.error('_clean', f'path: {self.file_path}_files not found.')
 
     def _check(self, file_path):
         """檢查檔案 MIME 格式
@@ -242,9 +301,8 @@ def _check(self, file_path):
 
 
 if __name__ == "__main__":
-    #epub = EPubConv()
-    # epub.convert('H:/VSCode/Python/epubconv/1.epub')
-    """ zh = ZhConvert()
-    zh.convert() """
-    #epub._read_allow_setting('allow_setting.json')
+    EPubConvert = EPubConv()
+    for epub in sys.argv[1:]:
+        EPubConvert.convert(epub)
+    os.system("pause")
     pass

app2.py

@@ -0,0 +1,4 @@
+[setting]
+engine=zhconvert
+converter=Traditional
+format=Horizontal

config.ini

@@ -0,0 +1,43 @@
+# UTF-8
+#
+# For more details about fixed file info 'ffi' see:
+# http://msdn.microsoft.com/en-us/library/ms646997.aspx
+VSVersionInfo(
+  ffi=FixedFileInfo(
+    # filevers and prodvers should be always a tuple with four items: (1, 2, 3, 4)
+    # Set not needed items to zero 0.
+    filevers=(2, 0, 0, 0),
+    prodvers=(2, 0, 0, 0),
+    # Contains a bitmask that specifies the valid bits 'flags'r
+    mask=0x3f,
+    # Contains a bitmask that specifies the Boolean attributes of the file.
+    flags=0x0,
+    # The operating system for which this file was designed.
+    # 0x4 - NT and there is no need to change it.
+    OS=0x40004,
+    # The general type of file.
+    # 0x1 - the file is an application.
+    fileType=0x1,
+    # The function of the file.
+    # 0x0 - the function is not defined for this fileType
+    subtype=0x0,
+    # Creation date and time stamp.
+    date=(0, 0)
+    ),
+  kids=[
+    StringFileInfo(
+      [
+      StringTable(
+        u'040904B0',
+        [StringStruct(u'CompanyName', u''),
+        StringStruct(u'FileDescription', u'EpubConv'),
+        StringStruct(u'FileVersion', u'2.0.0'),
+        StringStruct(u'InternalName', u'Epubconv'),
+        StringStruct(u'LegalCopyright', u''),
+        StringStruct(u'OriginalFilename', u'Epubconv.Exe'),
+        StringStruct(u'ProductName', u'Epubconv'),
+        StringStruct(u'ProductVersion', u'2.0.0')])
+      ]), 
+    VarFileInfo([VarStruct(u'Translation', [1033, 1200])])
+  ]
+)