Moved xml_entity_to_unicode partial to utils.entities module.

ebook_converter/__init__.py

@@ -27,12 +27,6 @@ class CurrentDir(object):
 
 
 _ent_pat = re.compile(r'&(\S+?);')
-xml_entity_to_unicode = partial(entities.entity_to_unicode,
-                                result_exceptions={'"': '"',
-                                                   "'": ''',
-                                                   '<': '&lt;',
-                                                   '>': '&gt;',
-                                                   '&': '&amp;'})
 
 
 def replace_entities(raw, encoding='cp1252'):
@@ -41,7 +35,8 @@ def replace_entities(raw, encoding='cp1252'):
 
 
 def xml_replace_entities(raw, encoding='cp1252'):
-    return _ent_pat.sub(partial(xml_entity_to_unicode, encoding=encoding), raw)
+    return _ent_pat.sub(partial(entities.xml_entity_to_unicode,
+                                encoding=encoding), raw)
 
 
 def prepare_string_for_xml(raw, attribute=False):

ebook_converter/ebooks/chardet.py

@@ -1,9 +1,8 @@
-import re, codecs
+import codecs
+import re
 
+from ebook_converter.utils import entities
 
-__license__ = 'GPL v3'
-__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
-__docformat__ = 'restructuredtext en'
 
 _encoding_pats = (
     # XML declaration
@@ -94,8 +93,7 @@ def find_declared_encoding(raw, limit=50*1024):
 
 
 def substitute_entites(raw):
-    from ebook_converter import xml_entity_to_unicode
-    return ENTITY_PATTERN.sub(xml_entity_to_unicode, raw)
+    return ENTITY_PATTERN.sub(entities.xml_entity_to_unicode, raw)
 
 
 _CHARSET_ALIASES = {"macintosh" : "mac-roman",

ebook_converter/ebooks/conversion/plugins/txt_input.py

@@ -1,13 +1,11 @@
 import os
 
-from ebook_converter import _ent_pat, xml_entity_to_unicode
-from ebook_converter.customize.conversion import InputFormatPlugin, OptionRecommendation
+from ebook_converter import _ent_pat
+from ebook_converter.customize.conversion import InputFormatPlugin
+from ebook_converter.customize.conversion import OptionRecommendation
+from ebook_converter.utils import entities
 
 
-__license__ = 'GPL 3'
-__copyright__ = '2009, John Schember <john@nachtimwald.com>'
-__docformat__ = 'restructuredtext en'
-
 MD_EXTENSIONS = {
     'abbr': 'Abbreviations',
     'admonition': 'Support admonitions',
@@ -200,7 +198,7 @@ class TXTInput(InputFormatPlugin):
         txt = txt.decode(ienc, 'replace')
 
         # Replace entities
-        txt = _ent_pat.sub(xml_entity_to_unicode, txt)
+        txt = _ent_pat.sub(entities.xml_entity_to_unicode, txt)
 
         # Normalize line endings
         txt = normalize_line_endings(txt)

ebook_converter/ebooks/mobi/reader/mobi6.py

@@ -9,7 +9,6 @@ import textwrap
 
 from lxml import html, etree
 
-from ebook_converter import xml_entity_to_unicode
 from ebook_converter.utils.cleantext import clean_ascii_chars, clean_xml_chars
 from ebook_converter.ebooks import DRMError, unit_convert
 from ebook_converter.ebooks.chardet import strip_encoding_declarations
@@ -183,7 +182,8 @@ class MobiReader(object):
                                      self.processed_html)
 
         self.processed_html = strip_encoding_declarations(self.processed_html)
-        self.processed_html = re.sub(r'&(\S+?);', xml_entity_to_unicode,
+        self.processed_html = re.sub(r'&(\S+?);',
+                                     entities.xml_entity_to_unicode,
                                      self.processed_html)
         image_name_map = self.extract_images(processed_records, output_dir)
         self.replace_page_breaks()