Removed polyglots unicode_type usage

ebook_converter/ebooks/oeb/polish/container.py

@@ -49,7 +49,7 @@ from ebook_converter.utils.ipc.simple_worker import WorkerError, fork_job
 from ebook_converter.utils.logging import default_log
 from ebook_converter.utils.xml_parse import safe_xml_fromstring
 from ebook_converter.utils.zipfile import ZipFile
-from ebook_converter.polyglot.builtins import iteritems, unicode_type
+from ebook_converter.polyglot.builtins import iteritems
 
 exists, join, relpath = os.path.exists, os.path.join, os.path.relpath
 
@@ -163,7 +163,7 @@ class ContainerBase(object):  # {{{
         """
         def fix_data(d):
             return d.replace('\r\n', '\n').replace('\r', '\n')
-        if isinstance(data, unicode_type):
+        if isinstance(data, str):
             return fix_data(data)
         bom_enc = None
         if data[:4] in {b'\0\0\xfe\xff', b'\xff\xfe\0\0'}:
@@ -681,7 +681,7 @@ class Container(ContainerBase):  # {{{
         ''' The names of all manifest items whose media-type matches predicate.
         `predicate` can be a set, a list, a string or a function taking a single
         argument, which will be called with the media-type. '''
-        if isinstance(predicate, unicode_type):
+        if isinstance(predicate, str):
             predicate = predicate.__eq__
         elif hasattr(predicate, '__contains__'):
             predicate = predicate.__contains__

ebook_converter/ebooks/oeb/polish/css.py

@@ -10,7 +10,7 @@ from ebook_converter.ebooks.oeb.normalize_css import normalize_filter_css, norma
 from ebook_converter.ebooks.oeb.polish.pretty import pretty_script_or_style, pretty_xml_tree, serialize
 from ebook_converter.utils.icu import numeric_sort_key
 from ebook_converter.css_selectors import Select, SelectorError
-from ebook_converter.polyglot.builtins import iteritems, itervalues, unicode_type
+from ebook_converter.polyglot.builtins import iteritems, itervalues
 
 
 __license__ = 'GPL v3'
@@ -342,10 +342,10 @@ def sort_sheet(container, sheet_or_text):
     ''' Sort the rules in a stylesheet. Note that in the general case this can
     change the effective styles, but for most common sheets, it should be safe.
     '''
-    sheet = container.parse_css(sheet_or_text) if isinstance(sheet_or_text, unicode_type) else sheet_or_text
+    sheet = container.parse_css(sheet_or_text) if isinstance(sheet_or_text, str) else sheet_or_text
 
     def text_sort_key(x):
-        return numeric_sort_key(unicode_type(x or ''))
+        return numeric_sort_key(str(x or ''))
 
     def selector_sort_key(x):
         return (x.specificity, text_sort_key(x.selectorText))

ebook_converter/ebooks/oeb/polish/parsing.py

@@ -7,7 +7,6 @@ from ebook_converter import xml_replace_entities
 from ebook_converter.utils.xml_parse import safe_xml_fromstring
 from ebook_converter.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
 from ebook_converter.utils.cleantext import clean_xml_chars
-from ebook_converter.polyglot.builtins import unicode_type
 
 
 __license__ = 'GPL v3'
@@ -81,7 +80,7 @@ def parse(raw, decoder=None, log=None, line_numbers=True, linenumber_attribute=N
         if linenumber_attribute:
             for elem in ans.iter(LxmlElement):
                 if elem.sourceline is not None:
-                    elem.set(linenumber_attribute, unicode_type(elem.sourceline))
+                    elem.set(linenumber_attribute, str(elem.sourceline))
         return ans
     except Exception:
         if log is not None:

ebook_converter/ebooks/oeb/polish/split.py

@@ -6,7 +6,7 @@ from ebook_converter.ebooks.oeb.base import barename, XPNSMAP, XPath, OPF, XHTML
 from ebook_converter.ebooks.oeb.polish.errors import MalformedMarkup
 from ebook_converter.ebooks.oeb.polish.toc import node_from_loc
 from ebook_converter.ebooks.oeb.polish.replace import LinkRebaser
-from ebook_converter.polyglot.builtins import iteritems, unicode_type
+from ebook_converter.polyglot.builtins import iteritems
 
 
 __license__ = 'GPL v3'
@@ -181,7 +181,7 @@ def split(container, name, loc_or_xpath, before=True, totals=None):
     '''
 
     root = container.parsed(name)
-    if isinstance(loc_or_xpath, unicode_type):
+    if isinstance(loc_or_xpath, str):
         split_point = root.xpath(loc_or_xpath)[0]
     else:
         try:
@@ -279,7 +279,7 @@ def multisplit(container, name, xpath, before=True):
             raise AbortError('Cannot split on the <body> tag')
 
     for i, tag in enumerate(nodes):
-        tag.set('calibre-split-point', unicode_type(i))
+        tag.set('calibre-split-point', str(i))
 
     current = name
     all_names = [name]

ebook_converter/ebooks/oeb/polish/toc.py

@@ -16,7 +16,7 @@ from ebook_converter.ebooks.oeb.polish.utils import guess_type, extract
 from ebook_converter.ebooks.oeb.polish.opf import set_guide_item, get_book_language
 from ebook_converter.ebooks.oeb.polish.pretty import pretty_html_tree
 from ebook_converter.utils.localization import get_lang, canonicalize_lang, lang_as_iso639_1
-from ebook_converter.polyglot.builtins import iteritems, unicode_type
+from ebook_converter.polyglot.builtins import iteritems
 
 
 __license__ = 'GPL v3'
@@ -170,11 +170,11 @@ def parse_ncx(container, ncx_name):
     toc_root.lang = toc_root.uid = None
     for attr, val in iteritems(root.attrib):
         if attr.endswith('lang'):
-            toc_root.lang = unicode_type(val)
+            toc_root.lang = str(val)
             break
     for uid in root.xpath('//*[calibre:lower-case(local-name()) = "meta" and @name="dtb:uid"]/@content'):
         if uid:
-            toc_root.uid = unicode_type(uid)
+            toc_root.uid = str(uid)
             break
     for pl in root.xpath('//*[calibre:lower-case(local-name()) = "pagelist"]'):
         for pt in pl.xpath('descendant::*[calibre:lower-case(local-name()) = "pagetarget"]'):
@@ -581,9 +581,9 @@ def create_ncx(toc, to_href, btitle, lang, uid):
         nsmap={None: NCX_NS})
     head = etree.SubElement(ncx, NCX('head'))
     etree.SubElement(head, NCX('meta'),
-        name='dtb:uid', content=unicode_type(uid))
+        name='dtb:uid', content=str(uid))
     etree.SubElement(head, NCX('meta'),
-        name='dtb:depth', content=unicode_type(toc.depth))
+        name='dtb:depth', content=str(toc.depth))
     generator = ''.join(['calibre (', __version__, ')'])
     etree.SubElement(head, NCX('meta'),
         name='dtb:generator', content=generator)
@@ -601,7 +601,7 @@ def create_ncx(toc, to_href, btitle, lang, uid):
         for child in toc_parent:
             play_order['c'] += 1
             point = etree.SubElement(xml_parent, NCX('navPoint'), id='num_%d' % play_order['c'],
-                            playOrder=unicode_type(play_order['c']))
+                            playOrder=str(play_order['c']))
             label = etree.SubElement(point, NCX('navLabel'))
             title = child.title
             if title:
@@ -770,7 +770,7 @@ def commit_nav_toc(container, toc, lang=None, landmarks=None, previous_nav=None)
         for entry in toc.page_list:
             if container.has_name(entry['dest']) and container.mime_map[entry['dest']] in OEB_DOCS:
                 a = create_li(ol, entry)
-                a.text = unicode_type(entry['pagenum'])
+                a.text = str(entry['pagenum'])
         pretty_xml_tree(nav)
         collapse_li(nav)
     container.replace(tocname, root)