py3 porting cleanup: drop str proxy

We don't need unicode_type anymore, because the str/unicode split
disappeared.

In addition to converting all unicode_type to str, there are some cases
where string literals were converted to unicode_type, e.g. for r''
strings, since ur'' didn't work. These can now be dropped entirely.

src/calibre/__init__.py

@@ -5,7 +5,7 @@ __copyright__ = '2008, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
 import sys, os, re, time, random, warnings
-from polyglot.builtins import codepoint_to_chr, unicode_type, hasenv, native_string_type
+from polyglot.builtins import codepoint_to_chr, hasenv, native_string_type
 from math import floor
 from functools import partial
 
@@ -71,7 +71,7 @@ def get_types_map():
 
 
 def to_unicode(raw, encoding='utf-8', errors='strict'):
-    if isinstance(raw, unicode_type):
+    if isinstance(raw, str):
         return raw
     return raw.decode(encoding, errors)
 
@@ -259,7 +259,7 @@ def get_parsed_proxy(typ='http', debug=True):
                     traceback.print_exc()
             else:
                 if debug:
-                    prints('Using http proxy', unicode_type(ans))
+                    prints('Using http proxy', str(ans))
                 return ans
 
 
@@ -419,7 +419,7 @@ def strftime(fmt, t=None):
         fmt = fmt.decode('mbcs' if iswindows else 'utf-8', 'replace')
     ans = time.strftime(fmt, t)
     if early_year:
-        ans = ans.replace('_early year hack##', unicode_type(orig_year))
+        ans = ans.replace('_early year hack##', str(orig_year))
     return ans
 
 
@@ -531,7 +531,7 @@ def force_unicode(obj, enc=preferred_encoding):
 def as_unicode(obj, enc=preferred_encoding):
     if not isbytestring(obj):
         try:
-            obj = unicode_type(obj)
+            obj = str(obj)
         except Exception:
             try:
                 obj = native_string_type(obj)
@@ -554,7 +554,7 @@ def human_readable(size, sep=' '):
         if size < (1 << ((i + 1) * 10)):
             divisor, suffix = (1 << (i * 10)), candidate
             break
-    size = unicode_type(float(size)/divisor)
+    size = str(float(size)/divisor)
     if size.find(".") > -1:
         size = size[:size.find(".")+2]
     if size.endswith('.0'):

src/calibre/constants.py

@@ -1,12 +1,12 @@
 #!/usr/bin/env python
 # vim:fileencoding=utf-8
 # License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
-from polyglot.builtins import unicode_type, environ_item, hasenv
+from polyglot.builtins import environ_item, hasenv
 import sys, locale, codecs, os, collections, collections.abc
 
 __appname__   = 'calibre'
 numeric_version = (5, 29, 0)
-__version__   = '.'.join(map(unicode_type, numeric_version))
+__version__   = '.'.join(map(str, numeric_version))
 git_version   = None
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 

src/calibre/customize/__init__.py

@@ -6,7 +6,6 @@ import os, sys, zipfile, importlib, enum
 
 from calibre.constants import numeric_version, iswindows, ismacos
 from calibre.ptempfile import PersistentTemporaryFile
-from polyglot.builtins import unicode_type
 
 if iswindows:
     platform = 'windows'
@@ -207,7 +206,7 @@ class Plugin:  # {{{
             config_dialog.exec_()
 
             if config_dialog.result() == QDialog.DialogCode.Accepted:
-                sc = unicode_type(sc.text()).strip()
+                sc = str(sc.text()).strip()
                 customize_plugin(self, sc)
 
         geom = bytearray(config_dialog.saveGeometry())

src/calibre/customize/conversion.py

@@ -7,7 +7,6 @@ import re, os, shutil, numbers
 
 from calibre import CurrentDir
 from calibre.customize import Plugin
-from polyglot.builtins import unicode_type
 
 
 class ConversionOption:
@@ -81,7 +80,7 @@ class OptionRecommendation:
                                                     self.option.choices:
             raise ValueError('OpRec: %s: Recommended value not in choices'%
                              self.option.name)
-        if not (isinstance(self.recommended_value, (numbers.Number, bytes, unicode_type)) or self.recommended_value is None):
+        if not (isinstance(self.recommended_value, (numbers.Number, bytes, str)) or self.recommended_value is None):
             raise ValueError('OpRec: %s:'%self.option.name + repr(
                 self.recommended_value) + ' is not a string or a number')
 
@@ -342,7 +341,7 @@ class OutputFormatPlugin(Plugin):
     @property
     def is_periodical(self):
         return self.oeb.metadata.publication_type and \
-            unicode_type(self.oeb.metadata.publication_type[0]).startswith('periodical:')
+            str(self.oeb.metadata.publication_type[0]).startswith('periodical:')
 
     def specialize_options(self, log, opts, input_fmt):
         '''

src/calibre/customize/ui.py

@@ -22,7 +22,7 @@ from calibre.utils.config import (make_config_dir, Config, ConfigProxy,
                                  plugin_dir, OptionParser)
 from calibre.ebooks.metadata.sources.base import Source
 from calibre.constants import DEBUG, numeric_version, system_plugins_loc
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from polyglot.builtins import iteritems, itervalues
 
 builtin_names = frozenset(p.name for p in builtin_plugins)
 BLACKLISTED_PLUGINS = frozenset({'Marvin XD', 'iOS reader applications'})
@@ -781,7 +781,7 @@ def build_plugin(path):
     from calibre import prints
     from calibre.ptempfile import PersistentTemporaryFile
     from calibre.utils.zipfile import ZipFile, ZIP_STORED
-    path = unicode_type(path)
+    path = str(path)
     names = frozenset(os.listdir(path))
     if '__init__.py' not in names:
         prints(path, ' is not a valid plugin')

src/calibre/customize/zipplugin.py

@@ -22,7 +22,7 @@ from calibre import as_unicode
 from calibre.customize import (
     InvalidPlugin, Plugin, PluginNotFound, numeric_version, platform
 )
-from polyglot.builtins import itervalues, reload, string_or_bytes, unicode_type
+from polyglot.builtins import itervalues, reload, string_or_bytes
 
 # PEP 302 based plugin loading mechanism, works around the bug in zipimport in
 # python 2.x that prevents importing from zip files in locations whose paths
@@ -307,7 +307,7 @@ class CalibrePluginFinder:
             if ans.minimum_calibre_version > numeric_version:
                 raise InvalidPlugin(
                     'The plugin at %s needs a version of calibre >= %s' %
-                    (as_unicode(path_to_zip_file), '.'.join(map(unicode_type,
+                    (as_unicode(path_to_zip_file), '.'.join(map(str,
                         ans.minimum_calibre_version))))
 
             if platform not in ans.supported_platforms:

src/calibre/db/adding.py

@@ -16,7 +16,7 @@ from calibre import prints
 from calibre.constants import filesystem_encoding, ismacos, iswindows
 from calibre.ebooks import BOOK_EXTENSIONS
 from calibre.utils.filenames import make_long_path_useable
-from polyglot.builtins import itervalues, unicode_type
+from polyglot.builtins import itervalues
 
 
 def splitext(path):
@@ -71,7 +71,7 @@ def metadata_extensions():
     # but not actually added)
     global _metadata_extensions
     if _metadata_extensions is None:
-        _metadata_extensions =  frozenset(map(unicode_type, BOOK_EXTENSIONS)) | {'opf'}
+        _metadata_extensions =  frozenset(BOOK_EXTENSIONS) | {'opf'}
     return _metadata_extensions
 
 
@@ -146,7 +146,7 @@ def find_books_in_directory(dirpath, single_book_per_directory, compiled_rules=(
         for path in listdir_impl(dirpath, sort_by_mtime=True):
             key, ext = splitext(path)
             if allow_path(path, ext, compiled_rules):
-                books[icu_lower(key) if isinstance(key, unicode_type) else key.lower()][ext] = path
+                books[icu_lower(key) if isinstance(key, str) else key.lower()][ext] = path
 
         for formats in itervalues(books):
             if formats_ok(formats):

src/calibre/db/backend.py

@@ -50,8 +50,7 @@ from calibre.utils.formatter_functions import (
 from calibre.utils.icu import sort_key
 from calibre.utils.img import save_cover_data_to
 from polyglot.builtins import (
-    cmp, iteritems, itervalues, native_string_type, reraise, string_or_bytes,
-    unicode_type
+    cmp, iteritems, itervalues, native_string_type, reraise, string_or_bytes
 )
 
 # }}}
@@ -108,7 +107,7 @@ class DBPrefs(dict):  # {{{
             dict.__setitem__(self, key, val)
 
     def raw_to_object(self, raw):
-        if not isinstance(raw, unicode_type):
+        if not isinstance(raw, str):
             raw = raw.decode(preferred_encoding)
         return json.loads(raw, object_hook=from_json)
 
@@ -352,7 +351,7 @@ class Connection(apsw.Connection):  # {{{
         self.createscalarfunction('title_sort', title_sort, 1)
         self.createscalarfunction('author_to_author_sort',
                 _author_to_author_sort, 1)
-        self.createscalarfunction('uuid4', lambda: unicode_type(uuid.uuid4()),
+        self.createscalarfunction('uuid4', lambda: str(uuid.uuid4()),
                 0)
 
         # Dummy functions for dynamically created filters
@@ -646,10 +645,10 @@ class DB:
                 prints('found user category case overlap', catmap[uc])
                 cat = catmap[uc][0]
                 suffix = 1
-                while icu_lower((cat + unicode_type(suffix))) in catmap:
+                while icu_lower((cat + str(suffix))) in catmap:
                     suffix += 1
-                prints('Renaming user category %s to %s'%(cat, cat+unicode_type(suffix)))
-                user_cats[cat + unicode_type(suffix)] = user_cats[cat]
+                prints('Renaming user category %s to %s'%(cat, cat+str(suffix)))
+                user_cats[cat + str(suffix)] = user_cats[cat]
                 del user_cats[cat]
                 cats_changed = True
         if cats_changed:
@@ -755,25 +754,25 @@ class DB:
             if d['is_multiple']:
                 if x is None:
                     return []
-                if isinstance(x, (unicode_type, bytes)):
+                if isinstance(x, (str, bytes)):
                     x = x.split(d['multiple_seps']['ui_to_list'])
                 x = [y.strip() for y in x if y.strip()]
                 x = [y.decode(preferred_encoding, 'replace') if not isinstance(y,
-                    unicode_type) else y for y in x]
+                    str) else y for y in x]
                 return [u' '.join(y.split()) for y in x]
             else:
-                return x if x is None or isinstance(x, unicode_type) else \
+                return x if x is None or isinstance(x, str) else \
                         x.decode(preferred_encoding, 'replace')
 
         def adapt_datetime(x, d):
-            if isinstance(x, (unicode_type, bytes)):
+            if isinstance(x, (str, bytes)):
                 if isinstance(x, bytes):
                     x = x.decode(preferred_encoding, 'replace')
                 x = parse_date(x, assume_utc=False, as_utc=False)
             return x
 
         def adapt_bool(x, d):
-            if isinstance(x, (unicode_type, bytes)):
+            if isinstance(x, (str, bytes)):
                 if isinstance(x, bytes):
                     x = x.decode(preferred_encoding, 'replace')
                 x = x.lower()
@@ -796,7 +795,7 @@ class DB:
         def adapt_number(x, d):
             if x is None:
                 return None
-            if isinstance(x, (unicode_type, bytes)):
+            if isinstance(x, (str, bytes)):
                 if isinstance(x, bytes):
                     x = x.decode(preferred_encoding, 'replace')
                 if x.lower() == 'none':
@@ -888,7 +887,7 @@ class DB:
                 # account for the series index column. Field_metadata knows that
                 # the series index is one larger than the series. If you change
                 # it here, be sure to change it there as well.
-                self.FIELD_MAP[unicode_type(data['num'])+'_index'] = base = base+1
+                self.FIELD_MAP[str(data['num'])+'_index'] = base = base+1
                 self.field_metadata.set_field_record_index(label_+'_index', base,
                             prefer_custom=True)
 
@@ -1311,7 +1310,7 @@ class DB:
         if getattr(self, '_library_id_', None) is None:
             ans = self.conn.get('SELECT uuid FROM library_id', all=False)
             if ans is None:
-                ans = unicode_type(uuid.uuid4())
+                ans = str(uuid.uuid4())
                 self.library_id = ans
             else:
                 self._library_id_ = ans
@@ -1319,7 +1318,7 @@ class DB:
 
     @library_id.setter
     def library_id(self, val):
-        self._library_id_ = unicode_type(val)
+        self._library_id_ = str(val)
         self.execute('''
                 DELETE FROM library_id;
                 INSERT INTO library_id (uuid) VALUES (?);
@@ -2026,7 +2025,7 @@ class DB:
         def map_data(x):
             if not isinstance(x, string_or_bytes):
                 x = native_string_type(x)
-            x = x.encode('utf-8') if isinstance(x, unicode_type) else x
+            x = x.encode('utf-8') if isinstance(x, str) else x
             x = pickle_binary_string(x)
             return x
         options = [(book_id, fmt.upper(), map_data(data)) for book_id, data in iteritems(options)]
@@ -2067,7 +2066,7 @@ class DB:
                 copyfile_using_links(src, dest, dest_is_dir=False)
                 old_files.add(src)
             x = path_map[x]
-            if not isinstance(x, unicode_type):
+            if not isinstance(x, str):
                 x = x.decode(filesystem_encoding, 'replace')
             progress(x, i+1, total)
 

src/calibre/db/cache.py

@@ -47,7 +47,7 @@ from calibre.utils.config import prefs, tweaks
 from calibre.utils.date import UNDEFINED_DATE, now as nowf, utcnow
 from calibre.utils.icu import sort_key
 from calibre.utils.localization import canonicalize_lang
-from polyglot.builtins import cmp, iteritems, itervalues, string_or_bytes, unicode_type
+from polyglot.builtins import cmp, iteritems, itervalues, string_or_bytes
 
 
 def api(f):
@@ -579,14 +579,14 @@ class Cache:
     @read_api
     def get_item_id(self, field, item_name):
         ' Return the item id for item_name (case-insensitive) '
-        rmap = {icu_lower(v) if isinstance(v, unicode_type) else v:k for k, v in iteritems(self.fields[field].table.id_map)}
-        return rmap.get(icu_lower(item_name) if isinstance(item_name, unicode_type) else item_name, None)
+        rmap = {icu_lower(v) if isinstance(v, str) else v:k for k, v in iteritems(self.fields[field].table.id_map)}
+        return rmap.get(icu_lower(item_name) if isinstance(item_name, str) else item_name, None)
 
     @read_api
     def get_item_ids(self, field, item_names):
         ' Return the item id for item_name (case-insensitive) '
-        rmap = {icu_lower(v) if isinstance(v, unicode_type) else v:k for k, v in iteritems(self.fields[field].table.id_map)}
-        return {name:rmap.get(icu_lower(name) if isinstance(name, unicode_type) else name, None) for name in item_names}
+        rmap = {icu_lower(v) if isinstance(v, str) else v:k for k, v in iteritems(self.fields[field].table.id_map)}
+        return {name:rmap.get(icu_lower(name) if isinstance(name, str) else name, None) for name in item_names}
 
     @read_api
     def author_data(self, author_ids=None):

src/calibre/db/categories.py

@@ -8,7 +8,7 @@ __docformat__ = 'restructuredtext en'
 
 import copy
 from functools import partial
-from polyglot.builtins import iteritems, unicode_type, native_string_type
+from polyglot.builtins import iteritems, native_string_type
 
 from calibre.ebooks.metadata import author_to_author_sort
 from calibre.utils.config_base import tweaks
@@ -101,8 +101,8 @@ def clean_user_categories(dbcache):
         if len(comps) == 0:
             i = 1
             while True:
-                if unicode_type(i) not in user_cats:
-                    new_cats[unicode_type(i)] = user_cats[k]
+                if str(i) not in user_cats:
+                    new_cats[str(i)] = user_cats[k]
                     break
                 i += 1
         else:

src/calibre/db/cli/cmd_add.py

@@ -21,7 +21,6 @@ from calibre.ptempfile import TemporaryDirectory
 from calibre.srv.changes import books_added, formats_added
 from calibre.utils.localization import canonicalize_lang
 from calibre.utils.short_uuid import uuid4
-from polyglot.builtins import unicode_type
 
 readonly = False
 version = 0  # change this if you change signature of implementation()
@@ -296,9 +295,9 @@ def do_add(
                     prints('   ', path)
 
         if added_ids:
-            prints(_('Added book ids: %s') % (', '.join(map(unicode_type, added_ids))))
+            prints(_('Added book ids: %s') % (', '.join(map(str, added_ids))))
         if merged_ids:
-            prints(_('Merged book ids: %s') % (', '.join(map(unicode_type, merged_ids))))
+            prints(_('Merged book ids: %s') % (', '.join(map(str, merged_ids))))
 
 
 def option_parser(get_parser, args):

src/calibre/db/cli/cmd_list.py

@@ -11,7 +11,7 @@ from textwrap import TextWrapper
 from calibre.db.cli.utils import str_width
 from calibre.ebooks.metadata import authors_to_string
 from calibre.utils.date import isoformat
-from polyglot.builtins import as_bytes, iteritems, unicode_type
+from polyglot.builtins import as_bytes, iteritems
 
 readonly = True
 version = 0  # change this if you change signature of implementation()
@@ -123,10 +123,10 @@ def prepare_output_table(fields, book_ids, data, metadata):
         ans.append(row)
         for field in fields:
             if field == 'id':
-                row.append(unicode_type(book_id))
+                row.append(str(book_id))
                 continue
             val = data.get(field.replace('*', '#'), {}).get(book_id)
-            row.append(unicode_type(val).replace('\n', ' '))
+            row.append(str(val).replace('\n', ' '))
     return ans
 
 
@@ -308,7 +308,7 @@ List the books available in the calibre database.
 def main(opts, args, dbctx):
     afields = set(FIELDS) | {'id'}
     if opts.fields.strip():
-        fields = [unicode_type(f.strip().lower()) for f in opts.fields.split(',')]
+        fields = [str(f.strip().lower()) for f in opts.fields.split(',')]
     else:
         fields = []
 

src/calibre/db/cli/cmd_list_categories.py

@@ -8,7 +8,7 @@ import sys
 from textwrap import TextWrapper
 
 from calibre import prints
-from polyglot.builtins import as_bytes, unicode_type
+from polyglot.builtins import as_bytes
 
 readonly = True
 version = 0  # change this if you change signature of implementation()
@@ -78,7 +78,7 @@ def do_list(fields, data, opts):
     widths = list(map(lambda x: 0, fields))
     for i in data:
         for j, field in enumerate(fields):
-            widths[j] = max(widths[j], max(len(field), len(unicode_type(i[field]))))
+            widths[j] = max(widths[j], max(len(field), len(str(i[field]))))
 
     screen_width = geometry()[0]
     if not screen_width:
@@ -109,7 +109,7 @@ def do_list(fields, data, opts):
 
     for record in data:
         text = [
-            wrappers[i].wrap(unicode_type(record[field]))
+            wrappers[i].wrap(str(record[field]))
             for i, field in enumerate(fields)
         ]
         lines = max(map(len, text))
@@ -167,11 +167,11 @@ def main(opts, args, dbctx):
             is_rating = category_metadata(category)['datatype'] == 'rating'
             for tag in category_data[category]:
                 if is_rating:
-                    tag.name = unicode_type(len(tag.name))
+                    tag.name = str(len(tag.name))
                 data.append({
                     'category': category,
                     'tag_name': tag.name,
-                    'count': unicode_type(tag.count),
+                    'count': str(tag.count),
                     'rating': fmtr(tag.avg_rating),
                 })
     else:
@@ -179,7 +179,7 @@ def main(opts, args, dbctx):
             data.append({
                 'category': category,
                 'tag_name': _('CATEGORY ITEMS'),
-                'count': unicode_type(len(category_data[category])),
+                'count': str(len(category_data[category])),
                 'rating': ''
             })
 

src/calibre/db/cli/cmd_set_metadata.py

@@ -10,7 +10,7 @@ from calibre.ebooks.metadata.book.base import field_from_string
 from calibre.ebooks.metadata.book.serialize import read_cover
 from calibre.ebooks.metadata.opf import get_metadata
 from calibre.srv.changes import metadata
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 
 readonly = False
 version = 0  # change this if you change signature of implementation()
@@ -181,5 +181,5 @@ def main(opts, args, dbctx):
         if not final_mi:
             raise SystemExit(_('No book with id: %s in the database') % book_id)
 
-    prints(unicode_type(final_mi))
+    prints(str(final_mi))
     return 0

src/calibre/db/cli/cmd_show_metadata.py

@@ -8,7 +8,6 @@ import sys
 
 from calibre import prints
 from calibre.ebooks.metadata.opf2 import OPFCreator
-from polyglot.builtins import unicode_type
 
 readonly = True
 version = 0  # change this if you change signature of implementation()
@@ -53,6 +52,6 @@ def main(opts, args, dbctx):
         mi = OPFCreator(os.getcwd(), mi)
         mi.render(stdout)
     else:
-        prints(unicode_type(mi))
+        prints(str(mi))
 
     return 0

src/calibre/db/fields.py

@@ -18,7 +18,7 @@ from calibre.utils.config_base import tweaks
 from calibre.utils.icu import sort_key
 from calibre.utils.date import UNDEFINED_DATE, clean_date_for_sort, parse_date
 from calibre.utils.localization import calibre_langcode_to_name
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 
 
 def bool_sort_key(bools_are_tristate):
@@ -85,7 +85,7 @@ class Field:
             self._sort_key = lambda x: sort_key(author_to_author_sort(x))
             self.sort_sort_key = False
         self.default_value = {} if name == 'identifiers' else () if self.is_multiple else None
-        self.category_formatter = unicode_type
+        self.category_formatter = str
         if dt == 'rating':
             if self.metadata['display'].get('allow_half_stars', False):
                 self.category_formatter = lambda x: rating_to_stars(x, True)

src/calibre/db/lazy.py

@@ -14,7 +14,7 @@ from copy import deepcopy
 from calibre.ebooks.metadata.book.base import Metadata, SIMPLE_GET, TOP_LEVEL_IDENTIFIERS, NULL_VALUES, ALL_METADATA_FIELDS
 from calibre.ebooks.metadata.book.formatter import SafeFormat
 from calibre.utils.date import utcnow
-from polyglot.builtins import unicode_type, native_string_type
+from polyglot.builtins import native_string_type
 
 # Lazy format metadata retrieval {{{
 '''
@@ -46,7 +46,7 @@ class MutableBase:
 
     @resolved
     def __unicode__(self):
-        return unicode_type(self._values)
+        return str(self._values)
 
     @resolved
     def __len__(self):

src/calibre/db/schema_upgrades.py

@@ -10,7 +10,7 @@ import os
 
 from calibre import prints
 from calibre.utils.date import isoformat, DEFAULT_DATE
-from polyglot.builtins import itervalues, unicode_type
+from polyglot.builtins import itervalues
 
 
 class SchemaUpgrade:
@@ -598,10 +598,10 @@ class SchemaUpgrade:
                 existing = frozenset(map(int, custom_recipes))
                 if id_ in existing:
                     id_ = max(existing) + 1000
-                id_ = unicode_type(id_)
+                id_ = str(id_)
                 fname = custom_recipe_filename(id_, title)
                 custom_recipes[id_] = (title, fname)
-                if isinstance(script, unicode_type):
+                if isinstance(script, str):
                     script = script.encode('utf-8')
                 with open(os.path.join(bdir, fname), 'wb') as f:
                     f.write(script)

src/calibre/db/search.py

@@ -18,7 +18,7 @@ from calibre.utils.date import parse_date, UNDEFINED_DATE, now, dt_as_local
 from calibre.utils.icu import primary_contains, sort_key
 from calibre.utils.localization import lang_map, canonicalize_lang
 from calibre.utils.search_query_parser import SearchQueryParser, ParseException
-from polyglot.builtins import iteritems, unicode_type, string_or_bytes
+from polyglot.builtins import iteritems, string_or_bytes
 
 CONTAINS_MATCH = 0
 EQUALS_MATCH   = 1
@@ -149,7 +149,7 @@ class DateSearch:  # {{{
 
         if query == 'false':
             for v, book_ids in field_iter():
-                if isinstance(v, (bytes, unicode_type)):
+                if isinstance(v, (bytes, str)):
                     if isinstance(v, bytes):
                         v = v.decode(preferred_encoding, 'replace')
                     v = parse_date(v)
@@ -159,7 +159,7 @@ class DateSearch:  # {{{
 
         if query == 'true':
             for v, book_ids in field_iter():
-                if isinstance(v, (bytes, unicode_type)):
+                if isinstance(v, (bytes, str)):
                     if isinstance(v, bytes):
                         v = v.decode(preferred_encoding, 'replace')
                     v = parse_date(v)
@@ -413,7 +413,7 @@ class SavedSearchQueries:  # {{{
         return self._db()
 
     def force_unicode(self, x):
-        if not isinstance(x, unicode_type):
+        if not isinstance(x, str):
             x = x.decode(preferred_encoding, 'replace')
         return x
 

src/calibre/db/tests/base.py

@@ -9,7 +9,6 @@ __docformat__ = 'restructuredtext en'
 import unittest, os, shutil, tempfile, atexit, gc, time
 from functools import partial
 from io import BytesIO
-from polyglot.builtins import unicode_type
 
 rmtree = partial(shutil.rmtree, ignore_errors=True)
 
@@ -82,7 +81,7 @@ class BaseTest(unittest.TestCase):
             atexit.register(rmtree, self.clone_dir)
             self.clone_count = 0
         self.clone_count += 1
-        dest = os.path.join(self.clone_dir, unicode_type(self.clone_count))
+        dest = os.path.join(self.clone_dir, str(self.clone_count))
         shutil.copytree(library_path, dest)
         return dest
 

src/calibre/db/tests/legacy.py

@@ -12,7 +12,7 @@ from operator import itemgetter
 
 from calibre.library.field_metadata import fm_as_dict
 from calibre.db.tests.base import BaseTest
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 from polyglot import reprlib
 
 # Utils {{{
@@ -116,7 +116,7 @@ class LegacyTest(BaseTest):
             for label, loc in iteritems(db.FIELD_MAP):
                 if isinstance(label, numbers.Integral):
                     label = '#'+db.custom_column_num_map[label]['label']
-                label = unicode_type(label)
+                label = str(label)
                 ans[label] = tuple(db.get_property(i, index_is_id=True, loc=loc)
                                    for i in db.all_ids())
                 if label in ('id', 'title', '#tags'):
@@ -282,7 +282,7 @@ class LegacyTest(BaseTest):
         old = db.get_data_as_dict(prefix='test-prefix')
         new = ndb.get_data_as_dict(prefix='test-prefix')
         for o, n in zip(old, new):
-            o = {unicode_type(k) if isinstance(k, bytes) else k:set(v) if isinstance(v, list) else v for k, v in iteritems(o)}
+            o = {str(k) if isinstance(k, bytes) else k:set(v) if isinstance(v, list) else v for k, v in iteritems(o)}
             n = {k:set(v) if isinstance(v, list) else v for k, v in iteritems(n)}
             self.assertEqual(o, n)
 

src/calibre/db/tests/writing.py

@@ -15,7 +15,7 @@ from calibre.ebooks.metadata.book.base import Metadata
 from calibre.utils.date import UNDEFINED_DATE
 from calibre.db.tests.base import BaseTest, IMG
 from calibre.db.backend import FTSQueryError
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from polyglot.builtins import iteritems, itervalues
 
 
 class WritingTest(BaseTest):
@@ -664,11 +664,11 @@ class WritingTest(BaseTest):
     def test_set_author_data(self):  # {{{
         cache = self.init_cache()
         adata = cache.author_data()
-        ldata = {aid:unicode_type(aid) for aid in adata}
+        ldata = {aid:str(aid) for aid in adata}
         self.assertEqual({1,2,3}, cache.set_link_for_authors(ldata))
         for c in (cache, self.init_cache()):
             self.assertEqual(ldata, {aid:d['link'] for aid, d in iteritems(c.author_data())})
-        self.assertEqual({3}, cache.set_link_for_authors({aid:'xxx' if aid == max(adata) else unicode_type(aid) for aid in adata}),
+        self.assertEqual({3}, cache.set_link_for_authors({aid:'xxx' if aid == max(adata) else str(aid) for aid in adata}),
                          'Setting the author link to the same value as before, incorrectly marked some books as dirty')
         sdata = {aid:'%s, changed' % aid for aid in adata}
         self.assertEqual({1,2,3}, cache.set_sort_for_authors(sdata))

src/calibre/db/utils.py

@@ -8,7 +8,7 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 import os, errno, sys, re
 from locale import localeconv
 from collections import OrderedDict, namedtuple
-from polyglot.builtins import iteritems, itervalues, unicode_type, string_or_bytes
+from polyglot.builtins import iteritems, itervalues, string_or_bytes
 from threading import Lock
 
 from calibre import as_unicode, prints
@@ -18,7 +18,7 @@ from calibre.utils.localization import canonicalize_lang
 
 
 def force_to_bool(val):
-    if isinstance(val, (bytes, unicode_type)):
+    if isinstance(val, (bytes, str)):
         if isinstance(val, bytes):
             val = val.decode(preferred_encoding, 'replace')
         try:
@@ -227,7 +227,7 @@ class ThumbnailCache:
     def _write_order(self):
         if hasattr(self, 'items'):
             try:
-                data = '\n'.join(group_id + ' ' + unicode_type(book_id) for (group_id, book_id) in self.items)
+                data = '\n'.join(group_id + ' ' + str(book_id) for (group_id, book_id) in self.items)
                 with lopen(os.path.join(self.location, 'order'), 'wb') as f:
                     f.write(data.encode('utf-8'))
             except EnvironmentError as err:

src/calibre/db/view.py

@@ -8,7 +8,7 @@ __docformat__ = 'restructuredtext en'
 
 import weakref, operator, numbers
 from functools import partial
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from polyglot.builtins import iteritems, itervalues
 
 from calibre.ebooks.metadata import title_sort
 from calibre.utils.config_base import tweaks, prefs
@@ -376,7 +376,7 @@ class View:
             self.marked_ids = dict.fromkeys(id_dict, u'true')
         else:
             # Ensure that all the items in the dict are text
-            self.marked_ids = {k: unicode_type(v) for k, v in iteritems(id_dict)}
+            self.marked_ids = {k: str(v) for k, v in iteritems(id_dict)}
         # This invalidates all searches in the cache even though the cache may
         # be shared by multiple views. This is not ideal, but...
         cmids = set(self.marked_ids)

src/calibre/db/write.py

@@ -9,7 +9,7 @@ __docformat__ = 'restructuredtext en'
 import re
 from functools import partial
 from datetime import datetime
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from polyglot.builtins import iteritems, itervalues
 
 from calibre.constants import preferred_encoding
 from calibre.ebooks.metadata import author_to_author_sort, title_sort
@@ -30,7 +30,7 @@ def sqlite_datetime(x):
 def single_text(x):
     if x is None:
         return x
-    if not isinstance(x, unicode_type):
+    if not isinstance(x, str):
         x = x.decode(preferred_encoding, 'replace')
     x = x.strip()
     return x if x else None
@@ -58,7 +58,7 @@ def multiple_text(sep, ui_sep, x):
         return ()
     if isinstance(x, bytes):
         x = x.decode(preferred_encoding, 'replace')
-    if isinstance(x, unicode_type):
+    if isinstance(x, str):
         x = x.split(sep)
     else:
         x = (y.decode(preferred_encoding, 'replace') if isinstance(y, bytes)
@@ -70,7 +70,7 @@ def multiple_text(sep, ui_sep, x):
 
 
 def adapt_datetime(x):
-    if isinstance(x, (unicode_type, bytes)):
+    if isinstance(x, (str, bytes)):
         x = parse_date(x, assume_utc=False, as_utc=False)
     if x and is_date_undefined(x):
         x = UNDEFINED_DATE
@@ -78,7 +78,7 @@ def adapt_datetime(x):
 
 
 def adapt_date(x):
-    if isinstance(x, (unicode_type, bytes)):
+    if isinstance(x, (str, bytes)):
         x = parse_only_date(x)
     if x is None or is_date_undefined(x):
         x = UNDEFINED_DATE
@@ -88,7 +88,7 @@ def adapt_date(x):
 def adapt_number(typ, x):
     if x is None:
         return None
-    if isinstance(x, (unicode_type, bytes)):
+    if isinstance(x, (str, bytes)):
         if isinstance(x, bytes):
             x = x.decode(preferred_encoding, 'replace')
         if not x or x.lower() == 'none':
@@ -97,7 +97,7 @@ def adapt_number(typ, x):
 
 
 def adapt_bool(x):
-    if isinstance(x, (unicode_type, bytes)):
+    if isinstance(x, (str, bytes)):
         if isinstance(x, bytes):
             x = x.decode(preferred_encoding, 'replace')
         x = x.lower()

src/calibre/debug.py

@@ -12,7 +12,7 @@ from calibre.utils.config import OptionParser
 from calibre.constants import iswindows
 from calibre import prints
 from calibre.startup import get_debug_executable
-from polyglot.builtins import exec_path, unicode_type
+from polyglot.builtins import exec_path
 
 
 def run_calibre_debug(*args, **kw):
@@ -204,7 +204,7 @@ def print_basic_debug_info(out=None):
             out('Linux:', platform.linux_distribution())
     except:
         pass
-    out('Interface language:', unicode_type(set_translators.lang))
+    out('Interface language:', str(set_translators.lang))
     from calibre.customize.ui import has_external_plugins, initialized_plugins
     if has_external_plugins():
         from calibre.customize import PluginInstallationType

src/calibre/devices/__init__.py

@@ -8,7 +8,6 @@ Device drivers.
 
 import sys, time, pprint
 from functools import partial
-from polyglot.builtins import unicode_type
 
 DAY_MAP   = dict(Sun=0, Mon=1, Tue=2, Wed=3, Thu=4, Fri=5, Sat=6)
 MONTH_MAP = dict(Jan=1, Feb=2, Mar=3, Apr=4, May=5, Jun=6, Jul=7, Aug=8, Sep=9, Oct=10, Nov=11, Dec=12)
@@ -19,8 +18,8 @@ INVERSE_MONTH_MAP = dict(zip(MONTH_MAP.values(), MONTH_MAP.keys()))
 def strptime(src):
     src = src.strip()
     src = src.split()
-    src[0] = unicode_type(DAY_MAP[src[0][:-1]])+','
-    src[2] = unicode_type(MONTH_MAP[src[2]])
+    src[0] = str(DAY_MAP[src[0][:-1]])+','
+    src[2] = str(MONTH_MAP[src[2]])
     return time.strptime(' '.join(src), '%w, %d %m %Y %H:%M:%S %Z')
 
 

src/calibre/devices/cli.py

@@ -17,7 +17,6 @@ from calibre.devices.errors import ArgumentError, DeviceError, DeviceLocked
 from calibre.customize.ui import device_plugins
 from calibre.devices.scanner import DeviceScanner
 from calibre.utils.config import device_prefs
-from polyglot.builtins import unicode_type
 from polyglot.io import PolyglotStringIO
 
 MINIMUM_COL_WIDTH = 12  # : Minimum width of columns in ls output
@@ -125,7 +124,7 @@ def ls(dev, path, recurse=False, human_readable_size=False, ll=False, cols=0):
         maxlen = 0
         if ll:  # Calculate column width for size column
             for file in files:
-                size = len(unicode_type(file.size))
+                size = len(str(file.size))
                 if human_readable_size:
                     file = FileFormatter(file)
                     size = len(file.human_readable_size)
@@ -137,10 +136,10 @@ def ls(dev, path, recurse=False, human_readable_size=False, ll=False, cols=0):
             lsoutput.append(name)
             lscoloutput.append(name)
             if ll:
-                size = unicode_type(file.size)
+                size = str(file.size)
                 if human_readable_size:
                     size = file.human_readable_size
-                prints(file.mode_string, ("%"+unicode_type(maxlen)+"s")%size, file.modification_time, name, file=output)
+                prints(file.mode_string, ("%"+str(maxlen)+"s")%size, file.modification_time, name, file=output)
         if not ll and len(lsoutput) > 0:
             trytable = []
             for colwidth in range(MINIMUM_COL_WIDTH, cols):
@@ -244,7 +243,7 @@ def main():
             print("Filesystem\tSize \tUsed \tAvail \tUse%")
             for i in range(3):
                 print("%-10s\t%s\t%s\t%s\t%s"%(where[i], human_readable(total[i]), human_readable(total[i]-free[i]), human_readable(free[i]),
-                                                                            unicode_type(0 if total[i]==0 else int(100*(total[i]-free[i])/(total[i]*1.)))+"%"))
+                                                                            str(0 if total[i]==0 else int(100*(total[i]-free[i])/(total[i]*1.)))+"%"))
         elif command == 'eject':
             dev.eject()
         elif command == "books":

src/calibre/devices/errors.py

@@ -8,7 +8,6 @@ Defines the errors that the device drivers generate.
 G{classtree ProtocolError}
 """
 
-from polyglot.builtins import unicode_type
 
 
 class ProtocolError(Exception):
@@ -95,7 +94,7 @@ class DeviceBusy(ProtocolError):
     def __init__(self, uerr=""):
         ProtocolError.__init__(
             self, "Device is in use by another application:"
-            "\nUnderlying error:" + unicode_type(uerr)
+            "\nUnderlying error:" + str(uerr)
         )
 
 
@@ -138,9 +137,9 @@ class ControlError(ProtocolError):
     def __str__(self):
         if self.query and self.response:
             return "Got unexpected response:\n" + \
-           "query:\n"+unicode_type(self.query.query)+"\n"+\
-           "expected:\n"+unicode_type(self.query.response)+"\n" +\
-           "actual:\n"+unicode_type(self.response)
+           "query:\n"+str(self.query.query)+"\n"+\
+           "expected:\n"+str(self.query.response)+"\n" +\
+           "actual:\n"+str(self.response)
         if self.desc:
             return self.desc
         return "Unknown control error occurred"

src/calibre/devices/jetbook/driver.py

@@ -15,7 +15,6 @@ import re
 from calibre.constants import filesystem_encoding
 from calibre.devices.usbms.driver import USBMS
 from calibre.ebooks.metadata import string_to_authors
-from polyglot.builtins import unicode_type
 
 
 class JETBOOK(USBMS):
@@ -65,7 +64,7 @@ class JETBOOK(USBMS):
     def metadata_from_path(cls, path):
 
         def check_unicode(txt):
-            if not isinstance(txt, unicode_type):
+            if not isinstance(txt, str):
                 txt = txt.decode(filesystem_encoding, 'replace')
             txt = txt.replace('_', ' ')
             return txt

src/calibre/devices/kindle/apnx.py

@@ -18,7 +18,7 @@ from calibre.ebooks.mobi.reader.headers import MetadataHeader
 from calibre.utils.logging import default_log
 from calibre import prints, fsync
 from calibre.constants import DEBUG
-from polyglot.builtins import as_unicode, as_bytes, unicode_type
+from polyglot.builtins import as_unicode, as_bytes
 
 
 class APNXBuilder:
@@ -33,7 +33,7 @@ class APNXBuilder:
         using either the fast or accurate algorithm.
         '''
         import uuid
-        apnx_meta = {'guid': unicode_type(uuid.uuid4()).replace('-', '')[:8], 'asin':
+        apnx_meta = {'guid': str(uuid.uuid4()).replace('-', '')[:8], 'asin':
                 '', 'cdetype': 'EBOK', 'format': 'MOBI_7', 'acr': ''}
 
         with lopen(mobi_file_path, 'rb') as mf:
@@ -53,11 +53,11 @@ class APNXBuilder:
             if mh.exth is None or not mh.exth.cdetype:
                 apnx_meta['cdetype'] = 'EBOK'
             else:
-                apnx_meta['cdetype'] = unicode_type(mh.exth.cdetype)
+                apnx_meta['cdetype'] = str(mh.exth.cdetype)
             if mh.exth is None or not mh.exth.uuid:
                 apnx_meta['asin'] = ''
             else:
-                apnx_meta['asin'] = unicode_type(mh.exth.uuid)
+                apnx_meta['asin'] = str(mh.exth.uuid)
 
         # Get the pages depending on the chosen parser
         pages = []

src/calibre/devices/kindle/driver.py

@@ -15,7 +15,7 @@ from calibre.constants import DEBUG, filesystem_encoding
 from calibre.devices.kindle.bookmark import Bookmark
 from calibre.devices.usbms.driver import USBMS
 from calibre import strftime, fsync, prints
-from polyglot.builtins import unicode_type, as_bytes, as_unicode
+from polyglot.builtins import as_bytes, as_unicode
 
 '''
 Notes on collections:
@@ -610,7 +610,7 @@ class KINDLE2(KINDLE):
                 cust_col_name = opts.extra_customization[self.OPT_APNX_METHOD_COL]
                 if cust_col_name:
                     try:
-                        temp = unicode_type(metadata.get(cust_col_name)).lower()
+                        temp = str(metadata.get(cust_col_name)).lower()
                         if temp in self.EXTRA_CUSTOMIZATION_CHOICES[self.OPT_APNX_METHOD]:
                             method = temp
                         else:

src/calibre/devices/kobo/driver.py

@@ -33,7 +33,7 @@ from calibre import prints, fsync
 from calibre.ptempfile import PersistentTemporaryFile, better_mktemp
 from calibre.constants import DEBUG
 from calibre.utils.config_base import prefs
-from polyglot.builtins import iteritems, itervalues, unicode_type, string_or_bytes
+from polyglot.builtins import iteritems, itervalues, string_or_bytes
 
 EPUB_EXT  = '.epub'
 KEPUB_EXT = '.kepub'
@@ -47,7 +47,7 @@ def qhash(inputstr):
     instr = b""
     if isinstance(inputstr, bytes):
         instr = inputstr
-    elif isinstance(inputstr, unicode_type):
+    elif isinstance(inputstr, str):
         instr = inputstr.encode("utf8")
     else:
         return -1
@@ -377,7 +377,7 @@ class KOBO(USBMS):
             try:
                 cursor.execute(query)
             except Exception as e:
-                err = unicode_type(e)
+                err = str(e)
                 if not (any_in(err, '___ExpirationStatus', 'FavouritesIndex', 'Accessibility', 'IsDownloaded')):
                     raise
                 query= ('select Title, Attribution, DateCreated, ContentID, MimeType, ContentType, '
@@ -483,13 +483,13 @@ class KOBO(USBMS):
                     cursor.execute('update content set ReadStatus=0, FirstTimeReading = \'true\', ___PercentRead=0, ___ExpirationStatus=3 '
                         'where BookID is Null and ContentID =?',t)
                 except Exception as e:
-                    if 'no such column' not in unicode_type(e):
+                    if 'no such column' not in str(e):
                         raise
                     try:
                         cursor.execute('update content set ReadStatus=0, FirstTimeReading = \'true\', ___PercentRead=0 '
                             'where BookID is Null and ContentID =?',t)
                     except Exception as e:
-                        if 'no such column' not in unicode_type(e):
+                        if 'no such column' not in str(e):
                             raise
                         cursor.execute('update content set ReadStatus=0, FirstTimeReading = \'true\' '
                             'where BookID is Null and ContentID =?',t)
@@ -833,7 +833,7 @@ class KOBO(USBMS):
             cursor.execute(query)
         except Exception as e:
             debug_print('    Database Exception:  Unable to reset Shortlist list')
-            if 'no such column' not in unicode_type(e):
+            if 'no such column' not in str(e):
                 raise
         finally:
             cursor.close()
@@ -847,7 +847,7 @@ class KOBO(USBMS):
             cursor.execute('update content set FavouritesIndex=1 where BookID is Null and ContentID = ?', t)
         except Exception as e:
             debug_print('    Database Exception:  Unable set book as Shortlist')
-            if 'no such column' not in unicode_type(e):
+            if 'no such column' not in str(e):
                 raise
         finally:
             cursor.close()
@@ -1808,7 +1808,7 @@ class KOBOTOUCH(KOBO):
                                 debug_print('KoboTouch:update_booklist - book file does not exist. ContentID="%s"'%ContentID)
 
                     except Exception as e:
-                        debug_print("KoboTouch:update_booklist - exception creating book: '%s'"%unicode_type(e))
+                        debug_print("KoboTouch:update_booklist - exception creating book: '%s'"%str(e))
                         debug_print("        prefix: ", prefix, "lpath: ", lpath, "title: ", title, "authors: ", authors,
                                     "MimeType: ", MimeType, "DateCreated: ", DateCreated, "ContentType: ", ContentType, "ImageID: ", ImageID)
                         raise
@@ -1870,7 +1870,7 @@ class KOBOTOUCH(KOBO):
                 bookshelves.append(row['ShelfName'])
 
             cursor.close()
-#            debug_print("KoboTouch:get_bookshelvesforbook - count bookshelves=" + unicode_type(count_bookshelves))
+#            debug_print("KoboTouch:get_bookshelvesforbook - count bookshelves=" + str(count_bookshelves))
             return bookshelves
 
         self.debug_index = 0
@@ -1963,7 +1963,7 @@ class KOBOTOUCH(KOBO):
             try:
                 cursor.execute(query)
             except Exception as e:
-                err = unicode_type(e)
+                err = str(e)
                 if not (any_in(err, '___ExpirationStatus', 'FavouritesIndex', 'Accessibility', 'IsDownloaded', 'Series', 'ExternalId')):
                     raise
                 query= ('SELECT Title, Attribution, DateCreated, ContentID, MimeType, ContentType, '
@@ -2174,7 +2174,7 @@ class KOBOTOUCH(KOBO):
 
                     cursor.close()
             except Exception as e:
-                debug_print('KoboTouch:upload_books - Exception:  %s'%unicode_type(e))
+                debug_print('KoboTouch:upload_books - Exception:  %s'%str(e))
 
         return result
 
@@ -2318,7 +2318,7 @@ class KOBOTOUCH(KOBO):
                     debug_print('KoboTouch:delete_via_sql: finished SQL')
                 debug_print('KoboTouch:delete_via_sql: After SQL, no exception')
             except Exception as e:
-                debug_print('KoboTouch:delete_via_sql - Database Exception:  %s'%unicode_type(e))
+                debug_print('KoboTouch:delete_via_sql - Database Exception:  %s'%str(e))
 
         debug_print('KoboTouch:delete_via_sql: imageId="%s"'%imageId)
         if imageId is None:
@@ -2451,7 +2451,7 @@ class KOBOTOUCH(KOBO):
 
             if self.manage_collections:
                 if collections:
-                    # debug_print("KoboTouch:update_device_database_collections - length collections=" + unicode_type(len(collections)))
+                    # debug_print("KoboTouch:update_device_database_collections - length collections=" + str(len(collections)))
 
                     # Need to reset the collections outside the particular loops
                     # otherwise the last item will not be removed
@@ -2621,7 +2621,7 @@ class KOBOTOUCH(KOBO):
                 self.keep_cover_aspect, self.letterbox_fs_covers, self.png_covers,
                 letterbox_color=self.letterbox_fs_covers_color)
         except Exception as e:
-            debug_print('KoboTouch: FAILED to upload cover=%s Exception=%s'%(filepath, unicode_type(e)))
+            debug_print('KoboTouch: FAILED to upload cover=%s Exception=%s'%(filepath, str(e)))
 
     def imageid_from_contentid(self, ContentID):
         ImageID = ContentID.replace('/', '_')
@@ -2831,7 +2831,7 @@ class KOBOTOUCH(KOBO):
                                 f.write(data)
                                 fsync(f)
         except Exception as e:
-            err = unicode_type(e)
+            err = str(e)
             debug_print("KoboTouch:_upload_cover - Exception string: %s"%err)
             raise
 
@@ -2978,7 +2978,7 @@ class KOBOTOUCH(KOBO):
 #            count_bookshelves = i + 1
 
         cursor.close()
-#        debug_print("KoboTouch:get_bookshelflist - count bookshelves=" + unicode_type(count_bookshelves))
+#        debug_print("KoboTouch:get_bookshelflist - count bookshelves=" + str(count_bookshelves))
 
         return bookshelves
 
@@ -3062,7 +3062,7 @@ class KOBOTOUCH(KOBO):
             cursor.execute(addquery, add_values)
         elif result['_IsDeleted'] == 'true':
             debug_print("KoboTouch:check_for_bookshelf - Shelf '%s' is deleted - undeleting. result['_IsDeleted']='%s'" % (
-                bookshelf_name, unicode_type(result['_IsDeleted'])))
+                bookshelf_name, str(result['_IsDeleted'])))
             cursor.execute(updatequery, test_values)
 
         cursor.close()

src/calibre/devices/kobo/kobotouch_config.py

@@ -16,7 +16,6 @@ from calibre.devices.usbms.driver import debug_print
 from calibre.gui2 import error_dialog
 from calibre.gui2.widgets2 import ColorButton
 from calibre.gui2.dialogs.template_dialog import TemplateDialog
-from polyglot.builtins import unicode_type
 
 
 def wrap_msg(msg):
@@ -128,7 +127,7 @@ class KOBOTOUCHConfig(TabbedDeviceConfig):
 
         p['support_newer_firmware'] = self.support_newer_firmware
         p['debugging_title'] = self.debugging_title
-        p['driver_version'] = '.'.join([unicode_type(i) for i in self.device.version])
+        p['driver_version'] = '.'.join([str(i) for i in self.device.version])
 
         return p
 
@@ -480,7 +479,7 @@ class AdvancedGroupBox(DeviceOptionsGroupBox):
                               'to perform full read-write functionality - Here be Dragons!! '
                               'Enable only if you are comfortable with restoring your kobo '
                               'to factory defaults and testing software. '
-                              'This driver supports firmware V2.x.x and DBVersion up to ') + unicode_type(
+                              'This driver supports firmware V2.x.x and DBVersion up to ') + str(
                                   device.supported_dbversion), device.get_pref('support_newer_firmware')
                              )
 
@@ -638,7 +637,7 @@ class TemplateConfig(QWidget):  # {{{
 
     @property
     def template(self):
-        return unicode_type(self.t.text()).strip()
+        return str(self.t.text()).strip()
 
     @template.setter
     def template(self, template):
@@ -660,7 +659,7 @@ class TemplateConfig(QWidget):  # {{{
         except Exception as err:
             error_dialog(self, _('Invalid template'),
                     '<p>'+_('The template "%s" is invalid:')%tmpl +
-                    '<br>'+unicode_type(err), show=True)
+                    '<br>'+str(err), show=True)
 
             return False
 # }}}

src/calibre/devices/mtp/driver.py

@@ -16,7 +16,7 @@ from calibre.devices.mtp.base import debug
 from calibre.devices.mtp.defaults import DeviceDefaults
 from calibre.ptempfile import SpooledTemporaryFile, PersistentTemporaryDirectory
 from calibre.utils.filenames import shorten_components_to
-from polyglot.builtins import iteritems, itervalues, unicode_type, as_bytes
+from polyglot.builtins import iteritems, itervalues, as_bytes
 
 BASE = importlib.import_module('calibre.devices.mtp.%s.driver'%(
     'windows' if iswindows else 'unix')).MTP_DEVICE
@@ -76,7 +76,7 @@ class MTP_DEVICE(BASE):
 
     def is_folder_ignored(self, storage_or_storage_id, path,
                           ignored_folders=None):
-        storage_id = unicode_type(getattr(storage_or_storage_id, 'object_id',
+        storage_id = str(getattr(storage_or_storage_id, 'object_id',
                              storage_or_storage_id))
         lpath = tuple(icu_lower(name) for name in path)
         if ignored_folders is None:
@@ -168,14 +168,14 @@ class MTP_DEVICE(BASE):
                 traceback.print_exc()
                 dinfo = {}
         if dinfo.get('device_store_uuid', None) is None:
-            dinfo['device_store_uuid'] = unicode_type(uuid.uuid4())
+            dinfo['device_store_uuid'] = str(uuid.uuid4())
         if dinfo.get('device_name', None) is None:
             dinfo['device_name'] = self.current_friendly_name
         if name is not None:
             dinfo['device_name'] = name
         dinfo['location_code'] = location_code
         dinfo['last_library_uuid'] = getattr(self, 'current_library_uuid', None)
-        dinfo['calibre_version'] = '.'.join([unicode_type(i) for i in numeric_version])
+        dinfo['calibre_version'] = '.'.join([str(i) for i in numeric_version])
         dinfo['date_last_connected'] = isoformat(now())
         dinfo['mtp_prefix'] = storage.storage_prefix
         raw = as_bytes(json.dumps(dinfo, default=to_json))

src/calibre/devices/mtp/filesystem_cache.py

@@ -9,7 +9,7 @@ __docformat__ = 'restructuredtext en'
 import weakref, sys, json
 from collections import deque
 from operator import attrgetter
-from polyglot.builtins import itervalues, unicode_type
+from polyglot.builtins import itervalues
 from datetime import datetime
 
 from calibre import human_readable, prints, force_unicode
@@ -73,7 +73,7 @@ class FileOrFolder:
     def __repr__(self):
         name = 'Folder' if self.is_folder else 'File'
         try:
-            path = unicode_type(self.full_path)
+            path = str(self.full_path)
         except:
             path = ''
         datum = 'size=%s'%(self.size)

src/calibre/devices/mtp/unix/driver.py

@@ -15,7 +15,6 @@ from calibre.constants import islinux, ismacos
 from calibre.ptempfile import SpooledTemporaryFile
 from calibre.devices.errors import OpenFailed, DeviceError, BlacklistedDevice, OpenActionNeeded
 from calibre.devices.mtp.base import MTPDeviceBase, synchronous, debug
-from polyglot.builtins import unicode_type
 
 MTPDevice = namedtuple('MTPDevice', 'busnum devnum vendor_id product_id '
         'bcd serial manufacturer product')
@@ -222,7 +221,7 @@ class MTP_DEVICE(MTPDeviceBase):
         try:
             storage = sorted(self.dev.storage_info, key=operator.itemgetter('id'))
         except self.libmtp.MTPError as e:
-            if "The device has no storage information." in unicode_type(e):
+            if "The device has no storage information." in str(e):
                 # This happens on newer Android devices while waiting for
                 # the user to allow access. Apparently what happens is
                 # that when the user clicks allow, the device disconnects
@@ -317,7 +316,7 @@ class MTP_DEVICE(MTPDeviceBase):
                     storage.append({'id':sid, 'size':capacity,
                         'is_folder':True, 'name':name, 'can_delete':False,
                         'is_system':True})
-                    self._currently_getting_sid = unicode_type(sid)
+                    self._currently_getting_sid = str(sid)
                     items, errs = self.dev.get_filesystem(sid,
                             partial(self._filesystem_callback, {}))
                     all_items.extend(items), all_errs.extend(errs)

src/calibre/devices/mtp/windows/driver.py

@@ -8,7 +8,7 @@ __docformat__ = 'restructuredtext en'
 
 import time, threading, traceback
 from functools import wraps, partial
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from polyglot.builtins import iteritems, itervalues
 from itertools import chain
 
 from calibre import as_unicode, prints, force_unicode
@@ -268,7 +268,7 @@ class MTP_DEVICE(MTPDeviceBase):
                         break
                 storage = {'id':storage_id, 'size':capacity, 'name':name,
                         'is_folder':True, 'can_delete':False, 'is_system':True}
-                self._currently_getting_sid = unicode_type(storage_id)
+                self._currently_getting_sid = str(storage_id)
                 id_map = self.dev.get_filesystem(storage_id, partial(
                         self._filesystem_callback, {}))
                 for x in itervalues(id_map):

src/calibre/devices/prs505/sony_cache.py

@@ -17,7 +17,6 @@ from calibre.ebooks.chardet import xml_to_unicode
 from calibre.ebooks.metadata import authors_to_string, title_sort, \
                                     authors_to_sort_string
 from polyglot.binary import from_base64_bytes
-from polyglot.builtins import unicode_type
 
 '''
 cacheExt.xml
@@ -66,8 +65,8 @@ INVERSE_MONTH_MAP = dict(zip(MONTH_MAP.values(), MONTH_MAP.keys()))
 def strptime(src):
     src = src.strip()
     src = src.split()
-    src[0] = unicode_type(DAY_MAP[src[0][:-1]])+','
-    src[2] = unicode_type(MONTH_MAP[src[2]])
+    src[0] = str(DAY_MAP[src[0][:-1]])+','
+    src[2] = str(MONTH_MAP[src[2]])
     return time.strptime(' '.join(src), '%w, %d %m %Y %H:%M:%S %Z')
 
 
@@ -84,7 +83,7 @@ def strftime(epoch, zone=time.localtime):
 
 def uuid():
     from uuid import uuid4
-    return unicode_type(uuid4()).replace('-', '', 1).upper()
+    return str(uuid4()).replace('-', '', 1).upper()
 
 # }}}
 
@@ -197,8 +196,8 @@ class XMLCache:
                     playlist.set('title', title)
                 if title in seen:
                     for i in range(2, 1000):
-                        if title+unicode_type(i) not in seen:
-                            title = title+unicode_type(i)
+                        if title+str(i) not in seen:
+                            title = title+str(i)
                             playlist.set('title', title)
                             seen.add(title)
                             break
@@ -271,7 +270,7 @@ class XMLCache:
                 nsmap=root.nsmap, attrib={
                     'uuid' : uuid(),
                     'title': title,
-                    'id'   : unicode_type(self.max_id(root)+1),
+                    'id'   : str(self.max_id(root)+1),
                     'sourceid': '1'
                     })
         root.append(ans)
@@ -310,13 +309,13 @@ class XMLCache:
         def ensure_media_xml_base_ids(root):
             for num, tag in enumerate(('library', 'watchSpecial')):
                 for x in root.xpath('//*[local-name()="%s"]'%tag):
-                    x.set('id', unicode_type(num))
+                    x.set('id', str(num))
 
         def rebase_ids(root, base, sourceid, pl_sourceid):
             'Rebase all ids and also make them consecutive'
             for item in root.xpath('//*[@sourceid]'):
                 sid = pl_sourceid if item.tag.endswith('playlist') else sourceid
-                item.set('sourceid', unicode_type(sid))
+                item.set('sourceid', str(sid))
             # Only rebase ids of nodes that are immediate children of the
             # record root (that way playlist/itemnodes are unaffected
             items = root.xpath('child::*[@id]')
@@ -326,8 +325,8 @@ class XMLCache:
                 old = int(item.get('id'))
                 new = base + i
                 if old != new:
-                    item.set('id', unicode_type(new))
-                    idmap[unicode_type(old)] = unicode_type(new)
+                    item.set('id', str(new))
+                    idmap[str(old)] = str(new)
             return idmap
 
         self.prune_empty_playlists()
@@ -356,7 +355,7 @@ class XMLCache:
 
         last_bl = max(self.roots.keys())
         max_id = self.max_id(self.roots[last_bl])
-        self.roots[0].set('nextID', unicode_type(max_id+1))
+        self.roots[0].set('nextID', str(max_id+1))
         debug_print('Finished running fix_ids()')
 
     # }}}
@@ -513,7 +512,7 @@ class XMLCache:
             # Ensure each book has an ID.
             for rec in records:
                 if rec.get('id', None) is None:
-                    rec.set('id', unicode_type(self.max_id(root)+1))
+                    rec.set('id', str(self.max_id(root)+1))
             ids = [x.get('id', None) for x in records]
             # Given that we set the ids, there shouldn't be any None's. But
             # better to be safe...
@@ -570,7 +569,7 @@ class XMLCache:
         id_ = self.max_id(root)+1
         attrib = {
                 'page':'0', 'part':'0','pageOffset':'0','scale':'0',
-                'id':unicode_type(id_), 'sourceid':'1', 'path':lpath}
+                'id':str(id_), 'sourceid':'1', 'path':lpath}
         ans = root.makeelement('{%s}text'%namespace, attrib=attrib, nsmap=root.nsmap)
         root.append(ans)
         return ans
@@ -589,7 +588,7 @@ class XMLCache:
         if thumbnail and thumbnail[-1]:
             ans.text = '\n' + '\t\t'
             t = root.makeelement('{%s}thumbnail'%namespace,
-                attrib={'width':unicode_type(thumbnail[0]), 'height':unicode_type(thumbnail[1])},
+                attrib={'width':str(thumbnail[0]), 'height':str(thumbnail[1])},
                 nsmap=root.nsmap)
             t.text = 'main_thumbnail.jpg'
             ans.append(t)
@@ -658,7 +657,7 @@ class XMLCache:
             date = strftime(timestamp, zone=tz)
             record.set('date', clean(date))
         try:
-            record.set('size', clean(unicode_type(os.stat(path).st_size)))
+            record.set('size', clean(str(os.stat(path).st_size)))
         except:
             record.set('size', '0')
         title = book.title if book.title else _('Unknown')
@@ -688,7 +687,7 @@ class XMLCache:
             record.set('sourceid', '1')
         if 'id' not in record.attrib:
             num = self.max_id(record.getroottree().getroot())
-            record.set('id', unicode_type(num+1))
+            record.set('id', str(num+1))
         return (gtz_count, ltz_count, use_tz_var)
     # }}}
 

src/calibre/devices/prst1/driver.py

@@ -23,7 +23,7 @@ from calibre.devices.usbms.books import CollectionsBookList
 from calibre.devices.usbms.books import BookList
 from calibre.ebooks.metadata import authors_to_sort_string, authors_to_string
 from calibre.constants import islinux
-from polyglot.builtins import unicode_type, long_type
+from polyglot.builtins import long_type
 
 DBPATH = 'Sony_Reader/database/books.db'
 THUMBPATH = 'Sony_Reader/database/cache/books/%s/thumbnail/main_thumbnail.jpg'
@@ -170,7 +170,7 @@ class PRST1(USBMS):
 
         with closing(sqlite.connect(dbpath)) as connection:
             # Replace undecodable characters in the db instead of erroring out
-            connection.text_factory = lambda x: x if isinstance(x, unicode_type) else x.decode('utf-8', 'replace')
+            connection.text_factory = lambda x: x if isinstance(x, str) else x.decode('utf-8', 'replace')
 
             cursor = connection.cursor()
             # Query collections

src/calibre/devices/smart_device_app/driver.py

@@ -47,7 +47,7 @@ from calibre.utils.mdns import (
 )
 from calibre.utils.socket_inheritance import set_socket_inherit
 from polyglot import queue
-from polyglot.builtins import as_bytes, iteritems, itervalues, unicode_type
+from polyglot.builtins import as_bytes, iteritems, itervalues
 
 
 def synchronous(tlockname):
@@ -125,13 +125,13 @@ class ConnectionListener(Thread):
                             content_server_port = ''
                             try:
                                 from calibre.srv.opts import server_config
-                                content_server_port = unicode_type(server_config().port)
+                                content_server_port = str(server_config().port)
                             except Exception:
                                 pass
                             message = (self.driver.ZEROCONF_CLIENT_STRING + ' (on ' +
-                                            unicode_type(socket.gethostname().partition('.')[0]) +
+                                            str(socket.gethostname().partition('.')[0]) +
                                             ');' + content_server_port +
-                                            ',' + unicode_type(self.driver.port)).encode('utf-8')
+                                            ',' + str(self.driver.port)).encode('utf-8')
                             self.driver._debug('received broadcast', packet, message)
                             self.driver.broadcast_socket.sendto(message, remote)
                         except:
@@ -414,7 +414,7 @@ class SMART_DEVICE_APP(DeviceConfig, DevicePlugin):
                     if isinstance(a, dict):
                         printable = {}
                         for k,v in iteritems(a):
-                            if isinstance(v, (bytes, unicode_type)) and len(v) > 50:
+                            if isinstance(v, (bytes, str)) and len(v) > 50:
                                 printable[k] = 'too long'
                             else:
                                 printable[k] = v
@@ -436,14 +436,14 @@ class SMART_DEVICE_APP(DeviceConfig, DevicePlugin):
         if not isinstance(dinfo, dict):
             dinfo = {}
         if dinfo.get('device_store_uuid', None) is None:
-            dinfo['device_store_uuid'] = unicode_type(uuid.uuid4())
+            dinfo['device_store_uuid'] = str(uuid.uuid4())
         if dinfo.get('device_name') is None:
             dinfo['device_name'] = self.get_gui_name()
         if name is not None:
             dinfo['device_name'] = name
         dinfo['location_code'] = location_code
         dinfo['last_library_uuid'] = getattr(self, 'current_library_uuid', None)
-        dinfo['calibre_version'] = '.'.join([unicode_type(i) for i in numeric_version])
+        dinfo['calibre_version'] = '.'.join([str(i) for i in numeric_version])
         dinfo['date_last_connected'] = isoformat(now())
         dinfo['prefix'] = self.PREFIX
         return dinfo
@@ -495,9 +495,9 @@ class SMART_DEVICE_APP(DeviceConfig, DevicePlugin):
 
         from calibre.library.save_to_disk import config, get_components
         opts = config().parse()
-        if not isinstance(template, unicode_type):
+        if not isinstance(template, str):
             template = template.decode('utf-8')
-        app_id = unicode_type(getattr(mdata, 'application_id', ''))
+        app_id = str(getattr(mdata, 'application_id', ''))
         id_ = mdata.get('id', fname)
         extra_components = get_components(template, mdata, id_,
                 timefmt=opts.send_timefmt, length=maxlen-len(app_id)-1,
@@ -747,7 +747,7 @@ class SMART_DEVICE_APP(DeviceConfig, DevicePlugin):
         from calibre.utils.date import now, parse_date
         try:
             key = self._make_metadata_cache_key(uuid, ext_or_lpath)
-            if isinstance(lastmod, unicode_type):
+            if isinstance(lastmod, str):
                 if lastmod == 'None':
                     return None
                 lastmod = parse_date(lastmod)
@@ -1909,7 +1909,7 @@ class SMART_DEVICE_APP(DeviceConfig, DevicePlugin):
                             'between 50 and 99. Forced to be %d.')%self.DEFAULT_THUMBNAIL_COMPRESSION_QUALITY
                 self._debug(message)
                 self.set_option('thumbnail_compression_quality',
-                                unicode_type(self.DEFAULT_THUMBNAIL_COMPRESSION_QUALITY))
+                                str(self.DEFAULT_THUMBNAIL_COMPRESSION_QUALITY))
 
             try:
                 self.listen_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

src/calibre/devices/usbms/deviceconfig.py

@@ -6,7 +6,6 @@ __copyright__ = '2009, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
 from calibre.utils.config_base import Config, ConfigProxy
-from polyglot.builtins import unicode_type
 
 
 class DeviceConfig:
@@ -109,15 +108,15 @@ class DeviceConfig:
                     if hasattr(config_widget.opt_extra_customization[i], 'isChecked'):
                         ec.append(config_widget.opt_extra_customization[i].isChecked())
                     elif hasattr(config_widget.opt_extra_customization[i], 'currentText'):
-                        ec.append(unicode_type(config_widget.opt_extra_customization[i].currentText()).strip())
+                        ec.append(str(config_widget.opt_extra_customization[i].currentText()).strip())
                     else:
-                        ec.append(unicode_type(config_widget.opt_extra_customization[i].text()).strip())
+                        ec.append(str(config_widget.opt_extra_customization[i].text()).strip())
             else:
-                ec = unicode_type(config_widget.opt_extra_customization.text()).strip()
+                ec = str(config_widget.opt_extra_customization.text()).strip()
                 if not ec:
                     ec = None
             proxy['extra_customization'] = ec
-        st = unicode_type(config_widget.opt_save_template.text())
+        st = str(config_widget.opt_save_template.text())
         proxy['save_template'] = st
 
     @classmethod

src/calibre/devices/usbms/driver.py

@@ -21,7 +21,7 @@ from calibre.devices.usbms.cli import CLI
 from calibre.devices.usbms.device import Device
 from calibre.devices.usbms.books import BookList, Book
 from calibre.ebooks.metadata.book.json_codec import JsonCodec
-from polyglot.builtins import itervalues, unicode_type, string_or_bytes
+from polyglot.builtins import itervalues, string_or_bytes
 
 
 def debug_print(*args, **kw):
@@ -107,14 +107,14 @@ class USBMS(CLI, Device):
         if not isinstance(dinfo, dict):
             dinfo = {}
         if dinfo.get('device_store_uuid', None) is None:
-            dinfo['device_store_uuid'] = unicode_type(uuid.uuid4())
+            dinfo['device_store_uuid'] = str(uuid.uuid4())
         if dinfo.get('device_name', None) is None:
             dinfo['device_name'] = self.get_gui_name()
         if name is not None:
             dinfo['device_name'] = name
         dinfo['location_code'] = location_code
         dinfo['last_library_uuid'] = getattr(self, 'current_library_uuid', None)
-        dinfo['calibre_version'] = '.'.join([unicode_type(i) for i in numeric_version])
+        dinfo['calibre_version'] = '.'.join([str(i) for i in numeric_version])
         dinfo['date_last_connected'] = isoformat(now())
         dinfo['prefix'] = prefix.replace('\\', '/')
         return dinfo

src/calibre/devices/utils.py

@@ -10,7 +10,6 @@ import os, time, re
 from functools import partial
 
 from calibre.devices.errors import DeviceError, WrongDestinationError, FreeSpaceError
-from polyglot.builtins import unicode_type
 
 
 def sanity_check(on_card, files, card_prefixes, free_space):
@@ -97,9 +96,9 @@ def create_upload_path(mdata, fname, template, sanitize,
     ext = path_type.splitext(fname)[1]
 
     opts = config().parse()
-    if not isinstance(template, unicode_type):
+    if not isinstance(template, str):
         template = template.decode('utf-8')
-    app_id = unicode_type(getattr(mdata, 'application_id', ''))
+    app_id = str(getattr(mdata, 'application_id', ''))
     id_ = mdata.get('id', fname)
     extra_components = get_components(template, mdata, id_,
             timefmt=opts.send_timefmt, length=maxlen-len(app_id)-1,

src/calibre/ebooks/BeautifulSoup.py

@@ -9,13 +9,12 @@ from bs4 import (  # noqa
     SoupStrainer, Tag, __version__
 )
 
-from polyglot.builtins import unicode_type
 
 
 def parse_html(markup):
     from calibre.ebooks.chardet import strip_encoding_declarations, xml_to_unicode, substitute_entites
     from calibre.utils.cleantext import clean_xml_chars
-    if isinstance(markup, unicode_type):
+    if isinstance(markup, str):
         markup = strip_encoding_declarations(markup)
         markup = substitute_entites(markup)
     else:

src/calibre/ebooks/__init__.py

@@ -11,7 +11,6 @@ from various formats.
 import os, re, numbers, sys
 from calibre import prints
 from calibre.ebooks.chardet import xml_to_unicode
-from polyglot.builtins import unicode_type
 
 
 class ConversionError(Exception):
@@ -82,7 +81,7 @@ def extract_calibre_cover(raw, base, log):
     if matches is None:
         body = soup.find('body')
         if body is not None:
-            text = u''.join(map(unicode_type, body.findAll(text=True)))
+            text = u''.join(map(str, body.findAll(text=True)))
             if text.strip():
                 # Body has text, abort
                 return
@@ -152,7 +151,7 @@ def check_ebook_format(stream, current_guess):
 
 
 def normalize(x):
-    if isinstance(x, unicode_type):
+    if isinstance(x, str):
         import unicodedata
         x = unicodedata.normalize('NFC', x)
     return x

src/calibre/ebooks/chardet.py

@@ -7,7 +7,6 @@ __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
 import re, codecs, sys
-from polyglot.builtins import unicode_type
 
 _encoding_pats = (
     # XML declaration
@@ -140,7 +139,7 @@ def force_encoding(raw, verbose, assume_utf8=False):
 
 
 def detect_xml_encoding(raw, verbose=False, assume_utf8=False):
-    if not raw or isinstance(raw, unicode_type):
+    if not raw or isinstance(raw, str):
         return raw, None
     for x in ('utf8', 'utf-16-le', 'utf-16-be'):
         bom = getattr(codecs, 'BOM_'+x.upper().replace('-16', '16').replace(
@@ -184,7 +183,7 @@ def xml_to_unicode(raw, verbose=False, strip_encoding_pats=False,
         return '', None
     raw, encoding = detect_xml_encoding(raw, verbose=verbose,
             assume_utf8=assume_utf8)
-    if not isinstance(raw, unicode_type):
+    if not isinstance(raw, str):
         raw = raw.decode(encoding, 'replace')
 
     if strip_encoding_pats:

src/calibre/ebooks/chm/reader.py

@@ -13,7 +13,7 @@ from calibre.ebooks.BeautifulSoup import BeautifulSoup, NavigableString
 from calibre.ebooks.chardet import xml_to_unicode
 from calibre.ebooks.metadata.toc import TOC
 from chm.chm import CHMFile, chmlib
-from polyglot.builtins import as_unicode, unicode_type
+from polyglot.builtins import as_unicode
 
 
 def match_string(s1, s2_already_lowered):
@@ -43,7 +43,7 @@ class CHMReader(CHMFile):
 
     def __init__(self, input, log, input_encoding=None):
         CHMFile.__init__(self)
-        if isinstance(input, unicode_type):
+        if isinstance(input, str):
             enc = 'mbcs' if iswindows else filesystem_encoding
             try:
                 input = input.encode(enc)
@@ -192,7 +192,7 @@ class CHMReader(CHMFile):
             with lopen(lpath, 'r+b') as f:
                 data = f.read()
                 data = self._reformat(data, lpath)
-                if isinstance(data, unicode_type):
+                if isinstance(data, str):
                     data = data.encode('utf-8')
                 f.seek(0)
                 f.truncate()

src/calibre/ebooks/comic/input.py

@@ -16,7 +16,6 @@ from calibre.ptempfile import PersistentTemporaryDirectory
 from calibre.utils.icu import numeric_sort_key
 from calibre.utils.ipc.server import Server
 from calibre.utils.ipc.job import ParallelJob
-from polyglot.builtins import unicode_type
 from polyglot.queue import Empty
 
 # If the specified screen has either dimension larger than this value, no image
@@ -29,7 +28,7 @@ def extract_comic(path_to_comic_file):
     Un-archive the comic file.
     '''
     tdir = PersistentTemporaryDirectory(suffix='_comic_extract')
-    if not isinstance(tdir, unicode_type):
+    if not isinstance(tdir, str):
         # Needed in case the zip file has wrongly encoded unicode file/dir
         # names
         tdir = tdir.decode(filesystem_encoding)

src/calibre/ebooks/conversion/config.py

@@ -13,7 +13,6 @@ from calibre.utils.lock import ExclusiveFile
 from calibre import sanitize_file_name
 from calibre.customize.conversion import OptionRecommendation
 from calibre.customize.ui import available_output_formats
-from polyglot.builtins import unicode_type
 
 
 config_dir = os.path.join(config_dir, 'conversion')
@@ -90,7 +89,7 @@ class GuiRecommendations(dict):
 
     def serialize(self):
         ans = json.dumps(self, indent=2, ensure_ascii=False)
-        if isinstance(ans, unicode_type):
+        if isinstance(ans, str):
             ans = ans.encode('utf-8')
         return b'json:' + ans
 

src/calibre/ebooks/conversion/plugins/chm_input.py

@@ -10,7 +10,7 @@ import os
 from calibre.customize.conversion import InputFormatPlugin
 from calibre.ptempfile import TemporaryDirectory
 from calibre.constants import filesystem_encoding
-from polyglot.builtins import unicode_type, as_bytes
+from polyglot.builtins import as_bytes
 
 
 class CHMInput(InputFormatPlugin):
@@ -37,7 +37,7 @@ class CHMInput(InputFormatPlugin):
 
         log.debug('Processing CHM...')
         with TemporaryDirectory('_chm2oeb') as tdir:
-            if not isinstance(tdir, unicode_type):
+            if not isinstance(tdir, str):
                 tdir = tdir.decode(filesystem_encoding)
             html_input = plugin_for_input_format('html')
             for opt in html_input.options:
@@ -128,7 +128,7 @@ class CHMInput(InputFormatPlugin):
         base = os.path.dirname(os.path.abspath(htmlpath))
 
         def unquote(x):
-            if isinstance(x, unicode_type):
+            if isinstance(x, str):
                 x = x.encode('utf-8')
             return _unquote(x).decode('utf-8')
 

src/calibre/ebooks/conversion/plugins/epub_output.py

@@ -12,7 +12,7 @@ from calibre.customize.conversion import (OutputFormatPlugin,
         OptionRecommendation)
 from calibre.ptempfile import TemporaryDirectory
 from calibre import CurrentDir
-from polyglot.builtins import unicode_type, as_bytes
+from polyglot.builtins import as_bytes
 
 block_level_tags = (
       'address',
@@ -225,15 +225,15 @@ class EPUBOutput(OutputFormatPlugin):
         identifiers = oeb.metadata['identifier']
         uuid = None
         for x in identifiers:
-            if x.get(OPF('scheme'), None).lower() == 'uuid' or unicode_type(x).startswith('urn:uuid:'):
-                uuid = unicode_type(x).split(':')[-1]
+            if x.get(OPF('scheme'), None).lower() == 'uuid' or str(x).startswith('urn:uuid:'):
+                uuid = str(x).split(':')[-1]
                 break
         encrypted_fonts = getattr(input_plugin, 'encrypted_fonts', [])
 
         if uuid is None:
             self.log.warn('No UUID identifier found')
             from uuid import uuid4
-            uuid = unicode_type(uuid4())
+            uuid = str(uuid4())
             oeb.metadata.add('identifier', uuid, scheme='uuid', id=uuid)
 
         if encrypted_fonts and not uuid.startswith('urn:uuid:'):
@@ -241,7 +241,7 @@ class EPUBOutput(OutputFormatPlugin):
             # for some absurd reason, or it will throw a hissy fit and refuse
             # to use the obfuscated fonts.
             for x in identifiers:
-                if unicode_type(x) == uuid:
+                if str(x) == uuid:
                     x.content = 'urn:uuid:'+uuid
 
         with TemporaryDirectory('_epub_output') as tdir:
@@ -336,7 +336,7 @@ class EPUBOutput(OutputFormatPlugin):
                         f.write(bytes(bytearray(data[i] ^ key[i%16] for i in range(1024))))
                     else:
                         self.log.warn('Font', path, 'is invalid, ignoring')
-                if not isinstance(uri, unicode_type):
+                if not isinstance(uri, str):
                     uri = uri.decode('utf-8')
                 fonts.append('''
                 <enc:EncryptedData>

src/calibre/ebooks/conversion/plugins/html_input.py

@@ -17,7 +17,7 @@ from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation
 from calibre.utils.filenames import ascii_filename
 from calibre.utils.imghdr import what
 from calibre.utils.localization import get_lang
-from polyglot.builtins import as_unicode, unicode_type
+from polyglot.builtins import as_unicode
 
 
 def sanitize_file_name(x):
@@ -144,7 +144,7 @@ class HTMLInput(InputFormatPlugin):
         if not metadata.title:
             oeb.logger.warn('Title not specified')
             metadata.add('title', self.oeb.translate(__('Unknown')))
-        bookid = unicode_type(uuid.uuid4())
+        bookid = str(uuid.uuid4())
         metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
         for ident in metadata.identifier:
             if 'id' in ident.attrib:
@@ -233,7 +233,7 @@ class HTMLInput(InputFormatPlugin):
 
     def link_to_local_path(self, link_, base=None):
         from calibre.ebooks.html.input import Link
-        if not isinstance(link_, unicode_type):
+        if not isinstance(link_, str):
             try:
                 link_ = link_.decode('utf-8', 'error')
             except:
@@ -298,7 +298,7 @@ class HTMLInput(InputFormatPlugin):
             # bhref refers to an already existing file. The read() method of
             # DirContainer will call unquote on it before trying to read the
             # file, therefore we quote it here.
-            if isinstance(bhref, unicode_type):
+            if isinstance(bhref, str):
                 bhref = bhref.encode('utf-8')
             item.html_input_href = as_unicode(quote(bhref))
             if is_stylesheet:

src/calibre/ebooks/conversion/plugins/html_output.py

@@ -10,7 +10,6 @@ from os.path import dirname, abspath, relpath as _relpath, exists, basename
 from calibre.customize.conversion import OutputFormatPlugin, OptionRecommendation
 from calibre import CurrentDir
 from calibre.ptempfile import PersistentTemporaryDirectory
-from polyglot.builtins import unicode_type
 
 
 def relpath(*args):
@@ -140,7 +139,7 @@ class HTMLOutput(OutputFormatPlugin):
                     toc=html_toc, meta=meta, nextLink=nextLink,
                     tocUrl=tocUrl, cssLink=cssLink,
                     firstContentPageLink=nextLink)
-            if isinstance(t, unicode_type):
+            if isinstance(t, str):
                 t = t.encode('utf-8')
             f.write(t)
 

src/calibre/ebooks/conversion/plugins/htmlz_output.py

@@ -11,7 +11,6 @@ import os
 from calibre.customize.conversion import OutputFormatPlugin, \
     OptionRecommendation
 from calibre.ptempfile import TemporaryDirectory
-from polyglot.builtins import unicode_type
 
 
 class HTMLZOutput(OutputFormatPlugin):
@@ -80,9 +79,9 @@ class HTMLZOutput(OutputFormatPlugin):
             fname = u'index'
             if opts.htmlz_title_filename:
                 from calibre.utils.filenames import shorten_components_to
-                fname = shorten_components_to(100, (ascii_filename(unicode_type(oeb_book.metadata.title[0])),))[0]
+                fname = shorten_components_to(100, (ascii_filename(str(oeb_book.metadata.title[0])),))[0]
             with open(os.path.join(tdir, fname+u'.html'), 'wb') as tf:
-                if isinstance(html, unicode_type):
+                if isinstance(html, str):
                     html = html.encode('utf-8')
                 tf.write(html)
 

src/calibre/ebooks/conversion/plugins/lrf_output.py

@@ -10,7 +10,6 @@ import sys, os
 
 from calibre.customize.conversion import OutputFormatPlugin
 from calibre.customize.conversion import OptionRecommendation
-from polyglot.builtins import unicode_type
 
 
 class LRFOptions:
@@ -18,7 +17,7 @@ class LRFOptions:
     def __init__(self, output, opts, oeb):
         def f2s(f):
             try:
-                return unicode_type(f[0])
+                return str(f[0])
             except:
                 return ''
         m = oeb.metadata
@@ -32,13 +31,13 @@ class LRFOptions:
         self.title_sort = self.author_sort = ''
         for x in m.creator:
             if x.role == 'aut':
-                self.author = unicode_type(x)
-                fa = unicode_type(getattr(x, 'file_as', ''))
+                self.author = str(x)
+                fa = str(getattr(x, 'file_as', ''))
                 if fa:
                     self.author_sort = fa
         for x in m.title:
-            if unicode_type(x.file_as):
-                self.title_sort = unicode_type(x.file_as)
+            if str(x.file_as):
+                self.title_sort = str(x.file_as)
         self.freetext = f2s(m.description)
         self.category = f2s(m.subject)
         self.cover = None

src/calibre/ebooks/conversion/plugins/mobi_input.py

@@ -7,7 +7,6 @@ __docformat__ = 'restructuredtext en'
 import os
 
 from calibre.customize.conversion import InputFormatPlugin
-from polyglot.builtins import unicode_type
 
 
 class MOBIInput(InputFormatPlugin):
@@ -51,7 +50,7 @@ class MOBIInput(InputFormatPlugin):
 
         raw = parse_cache.pop('calibre_raw_mobi_markup', False)
         if raw:
-            if isinstance(raw, unicode_type):
+            if isinstance(raw, str):
                 raw = raw.encode('utf-8')
             with lopen('debug-raw.html', 'wb') as f:
                 f.write(raw)

src/calibre/ebooks/conversion/plugins/mobi_output.py

@@ -8,7 +8,6 @@ __docformat__ = 'restructuredtext en'
 
 from calibre.customize.conversion import (OutputFormatPlugin,
         OptionRecommendation)
-from polyglot.builtins import unicode_type
 
 
 def remove_html_cover(oeb, log):
@@ -122,7 +121,7 @@ class MOBIOutput(OutputFormatPlugin):
         if not found:
             from calibre.ebooks import generate_masthead
             self.oeb.log.debug('No masthead found in manifest, generating default mastheadImage...')
-            raw = generate_masthead(unicode_type(self.oeb.metadata['title'][0]))
+            raw = generate_masthead(str(self.oeb.metadata['title'][0]))
             id, href = self.oeb.manifest.generate('masthead', 'masthead')
             self.oeb.manifest.add(id, href, 'image/gif', data=raw)
             self.oeb.guide.add('masthead', 'Masthead Image', href)
@@ -166,7 +165,7 @@ class MOBIOutput(OutputFormatPlugin):
                     sec.nodes.remove(a)
 
             root = TOC(klass='periodical', href=self.oeb.spine[0].href,
-                    title=unicode_type(self.oeb.metadata.title[0]))
+                    title=str(self.oeb.metadata.title[0]))
 
             for s in sections:
                 if articles[id(s)]:

src/calibre/ebooks/conversion/plugins/pdf_output.py

@@ -14,7 +14,7 @@ import glob, os
 from calibre.customize.conversion import (OutputFormatPlugin,
     OptionRecommendation)
 from calibre.ptempfile import TemporaryDirectory
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 
 UNITS = ('millimeter', 'centimeter', 'point', 'inch' , 'pica' , 'didot',
         'cicero', 'devicepixel')
@@ -193,8 +193,8 @@ class PDFOutput(OutputFormatPlugin):
 
     def get_cover_data(self):
         oeb = self.oeb
-        if (oeb.metadata.cover and unicode_type(oeb.metadata.cover[0]) in oeb.manifest.ids):
-            cover_id = unicode_type(oeb.metadata.cover[0])
+        if (oeb.metadata.cover and str(oeb.metadata.cover[0]) in oeb.manifest.ids):
+            cover_id = str(oeb.metadata.cover[0])
             item = oeb.manifest.ids[cover_id]
             if isinstance(item.data, bytes):
                 self.cover_data = item.data

src/calibre/ebooks/conversion/plugins/pml_output.py

@@ -10,7 +10,6 @@ import os, io
 from calibre.customize.conversion import (OutputFormatPlugin,
         OptionRecommendation)
 from calibre.ptempfile import TemporaryDirectory
-from polyglot.builtins import unicode_type
 
 
 class PMLOutput(OutputFormatPlugin):
@@ -42,7 +41,7 @@ class PMLOutput(OutputFormatPlugin):
 
         with TemporaryDirectory('_pmlz_output') as tdir:
             pmlmlizer = PMLMLizer(log)
-            pml = unicode_type(pmlmlizer.extract_content(oeb_book, opts))
+            pml = str(pmlmlizer.extract_content(oeb_book, opts))
             with lopen(os.path.join(tdir, 'index.pml'), 'wb') as out:
                 out.write(pml.encode(opts.pml_output_encoding, 'replace'))
 

src/calibre/ebooks/conversion/plugins/recipe_input.py

@@ -11,7 +11,6 @@ import os
 from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation
 from calibre.constants import numeric_version
 from calibre import walk
-from polyglot.builtins import unicode_type
 
 
 class RecipeDisabled(Exception):
@@ -164,6 +163,6 @@ class RecipeInput(InputFormatPlugin):
 
     def save_download(self, zf):
         raw = self.recipe_source
-        if isinstance(raw, unicode_type):
+        if isinstance(raw, str):
             raw = raw.encode('utf-8')
         zf.writestr('download.recipe', raw)

src/calibre/ebooks/conversion/plugins/snb_input.py

@@ -10,7 +10,6 @@ import os
 from calibre.customize.conversion import InputFormatPlugin
 from calibre.ptempfile import TemporaryDirectory
 from calibre.utils.filenames import ascii_filename
-from polyglot.builtins import unicode_type
 
 HTML_TEMPLATE = '<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/><title>%s</title></head><body>\n%s\n</body></html>'
 
@@ -75,7 +74,7 @@ class SNBInput(InputFormatPlugin):
             if d['cover'] != '':
                 oeb.guide.add('cover', 'Cover', d['cover'])
 
-        bookid = unicode_type(uuid.uuid4())
+        bookid = str(uuid.uuid4())
         oeb.metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
         for ident in oeb.metadata.identifier:
             if 'id' in ident.attrib:

src/calibre/ebooks/conversion/plugins/snb_output.py

@@ -10,7 +10,6 @@ import os
 from calibre.customize.conversion import OutputFormatPlugin, OptionRecommendation
 from calibre.ptempfile import TemporaryDirectory
 from calibre.constants import __appname__, __version__
-from polyglot.builtins import unicode_type
 
 
 class SNBOutput(OutputFormatPlugin):
@@ -75,20 +74,20 @@ class SNBOutput(OutputFormatPlugin):
             # Process Meta data
             meta = oeb_book.metadata
             if meta.title:
-                title = unicode_type(meta.title[0])
+                title = str(meta.title[0])
             else:
                 title = ''
-            authors = [unicode_type(x) for x in meta.creator if x.role == 'aut']
+            authors = [str(x) for x in meta.creator if x.role == 'aut']
             if meta.publisher:
-                publishers = unicode_type(meta.publisher[0])
+                publishers = str(meta.publisher[0])
             else:
                 publishers = ''
             if meta.language:
-                lang = unicode_type(meta.language[0]).upper()
+                lang = str(meta.language[0]).upper()
             else:
                 lang = ''
             if meta.description:
-                abstract = unicode_type(meta.description[0])
+                abstract = str(meta.description[0])
             else:
                 abstract = ''
 

src/calibre/ebooks/conversion/plumber.py

@@ -20,7 +20,7 @@ from calibre.utils.zipfile import ZipFile
 from calibre import (extract, walk, isbytestring, filesystem_encoding,
         get_types_map)
 from calibre.constants import __version__
-from polyglot.builtins import unicode_type, string_or_bytes
+from polyglot.builtins import string_or_bytes
 
 DEBUG_README=b'''
 This debug folder contains snapshots of the e-book as it passes through the
@@ -794,7 +794,7 @@ OptionRecommendation(name='search_replace',
     def unarchive(self, path, tdir):
         extract(path, tdir)
         files = list(walk(tdir))
-        files = [f if isinstance(f, unicode_type) else f.decode(filesystem_encoding)
+        files = [f if isinstance(f, str) else f.decode(filesystem_encoding)
                 for f in files]
         from calibre.customize.ui import available_input_formats
         fmts = set(available_input_formats())
@@ -847,7 +847,7 @@ OptionRecommendation(name='search_replace',
         rec = self.get_option_by_name(name)
         help = getattr(rec, 'help', None)
         if help is not None:
-            return help.replace('%default', unicode_type(rec.recommended_value))
+            return help.replace('%default', str(rec.recommended_value))
 
     def get_all_help(self):
         ans = {}
@@ -915,7 +915,7 @@ OptionRecommendation(name='search_replace',
                     try:
                         val = parse_date(val, assume_utc=x=='timestamp')
                     except:
-                        self.log.exception(_('Failed to parse date/time') + ' ' + unicode_type(val))
+                        self.log.exception(_('Failed to parse date/time') + ' ' + str(val))
                         continue
                 setattr(mi, x, val)
 

src/calibre/ebooks/conversion/preprocess.py

@@ -10,7 +10,6 @@ import functools, re, json
 from math import ceil
 
 from calibre import entity_to_unicode, as_unicode
-from polyglot.builtins import unicode_type
 
 XMLDECL_RE    = re.compile(r'^\s*<[?]xml.*?[?]>')
 SVG_NS       = 'http://www.w3.org/2000/svg'
@@ -75,8 +74,8 @@ def smarten_punctuation(html, log=None):
     from calibre.ebooks.conversion.utils import HeuristicProcessor
     preprocessor = HeuristicProcessor(log=log)
     from uuid import uuid4
-    start = 'calibre-smartypants-'+unicode_type(uuid4())
-    stop = 'calibre-smartypants-'+unicode_type(uuid4())
+    start = 'calibre-smartypants-'+str(uuid4())
+    stop = 'calibre-smartypants-'+str(uuid4())
     html = html.replace('<!--', start)
     html = html.replace('-->', stop)
     html = preprocessor.fix_nbsp_indents(html)
@@ -152,20 +151,20 @@ class DocAnalysis:
         maxLineLength=1900  # Discard larger than this to stay in range
         buckets=20  # Each line is divided into a bucket based on length
 
-        # print("there are "+unicode_type(len(lines))+" lines")
+        # print("there are "+str(len(lines))+" lines")
         # max = 0
         # for line in self.lines:
         #    l = len(line)
         #    if l > max:
         #        max = l
-        # print("max line found is "+unicode_type(max))
+        # print("max line found is "+str(max))
         # Build the line length histogram
         hRaw = [0 for i in range(0,buckets)]
         for line in self.lines:
             l = len(line)
             if l > minLineLength and l < maxLineLength:
                 l = int(l // 100)
-                # print("adding "+unicode_type(l))
+                # print("adding "+str(l))
                 hRaw[l]+=1
 
         # Normalize the histogram into percents
@@ -174,8 +173,8 @@ class DocAnalysis:
             h = [float(count)/totalLines for count in hRaw]
         else:
             h = []
-        # print("\nhRaw histogram lengths are: "+unicode_type(hRaw))
-        # print("              percents are: "+unicode_type(h)+"\n")
+        # print("\nhRaw histogram lengths are: "+str(hRaw))
+        # print("              percents are: "+str(h)+"\n")
 
         # Find the biggest bucket
         maxValue = 0
@@ -187,7 +186,7 @@ class DocAnalysis:
             # print("Line lengths are too variable. Not unwrapping.")
             return False
         else:
-            # print(unicode_type(maxValue)+" of the lines were in one bucket")
+            # print(str(maxValue)+" of the lines were in one bucket")
             return True
 
 
@@ -223,8 +222,8 @@ class Dehyphenator:
             wraptags = match.group('wraptags')
         except:
             wraptags = ''
-        hyphenated = unicode_type(firsthalf) + "-" + unicode_type(secondhalf)
-        dehyphenated = unicode_type(firsthalf) + unicode_type(secondhalf)
+        hyphenated = str(firsthalf) + "-" + str(secondhalf)
+        dehyphenated = str(firsthalf) + str(secondhalf)
         if self.suffixes.match(secondhalf) is None:
             lookupword = self.removesuffixes.sub('', dehyphenated)
         else:
@@ -330,7 +329,7 @@ class CSSPreProcessor:
         # are commented lines before the first @import or @charset rule. Since
         # the conversion will remove all stylesheets anyway, we don't lose
         # anything
-        data = re.sub(unicode_type(r'/\*.*?\*/'), '', data, flags=re.DOTALL)
+        data = re.sub(r'/\*.*?\*/', '', data, flags=re.DOTALL)
 
         ans, namespaced = [], False
         for line in data.splitlines():
@@ -538,7 +537,7 @@ class HTMLPreProcessor:
             docanalysis = DocAnalysis('pdf', html)
             length = docanalysis.line_length(getattr(self.extra_opts, 'unwrap_factor'))
             if length:
-                # print("The pdf line length returned is " + unicode_type(length))
+                # print("The pdf line length returned is " + str(length))
                 # unwrap em/en dashes
                 end_rules.append((re.compile(
                     r'(?<=.{%i}[–—])\s*<p>\s*(?=[\[a-z\d])' % length), lambda match: ''))

src/calibre/ebooks/conversion/utils.py

@@ -11,7 +11,6 @@ from math import ceil
 from calibre.ebooks.conversion.preprocess import DocAnalysis, Dehyphenator
 from calibre.utils.logging import default_log
 from calibre.utils.wordcount import get_wordcount_obj
-from polyglot.builtins import unicode_type
 
 
 class HeuristicProcessor:
@@ -54,8 +53,8 @@ class HeuristicProcessor:
         title = match.group('title')
         if not title:
             self.html_preprocess_sections = self.html_preprocess_sections + 1
-            self.log.debug("marked " + unicode_type(self.html_preprocess_sections) +
-                    " chapters. - " + unicode_type(chap))
+            self.log.debug("marked " + str(self.html_preprocess_sections) +
+                    " chapters. - " + str(chap))
             return '<h2>'+chap+'</h2>\n'
         else:
             delete_whitespace = re.compile('^\\s*(?P<c>.*?)\\s*$')
@@ -63,16 +62,16 @@ class HeuristicProcessor:
             txt_chap = delete_quotes.sub('', delete_whitespace.sub('\\g<c>', html2text(chap)))
             txt_title = delete_quotes.sub('', delete_whitespace.sub('\\g<c>', html2text(title)))
             self.html_preprocess_sections = self.html_preprocess_sections + 1
-            self.log.debug("marked " + unicode_type(self.html_preprocess_sections) +
-                    " chapters & titles. - " + unicode_type(chap) + ", " + unicode_type(title))
+            self.log.debug("marked " + str(self.html_preprocess_sections) +
+                    " chapters & titles. - " + str(chap) + ", " + str(title))
             return '<h2 title="'+txt_chap+', '+txt_title+'">'+chap+'</h2>\n<h3 class="sigilNotInTOC">'+title+'</h3>\n'
 
     def chapter_break(self, match):
         chap = match.group('section')
         styles = match.group('styles')
         self.html_preprocess_sections = self.html_preprocess_sections + 1
-        self.log.debug("marked " + unicode_type(self.html_preprocess_sections) +
-                " section markers based on punctuation. - " + unicode_type(chap))
+        self.log.debug("marked " + str(self.html_preprocess_sections) +
+                " section markers based on punctuation. - " + str(chap))
         return '<'+styles+' style="page-break-before:always">'+chap
 
     def analyze_title_matches(self, match):
@@ -115,8 +114,8 @@ class HeuristicProcessor:
         line_end = line_end_ere.findall(raw)
         tot_htm_ends = len(htm_end)
         tot_ln_fds = len(line_end)
-        # self.log.debug("There are " + unicode_type(tot_ln_fds) + " total Line feeds, and " +
-        #        unicode_type(tot_htm_ends) + " marked up endings")
+        # self.log.debug("There are " + str(tot_ln_fds) + " total Line feeds, and " +
+        #        str(tot_htm_ends) + " marked up endings")
 
         if percent > 1:
             percent = 1
@@ -124,7 +123,7 @@ class HeuristicProcessor:
             percent = 0
 
         min_lns = tot_ln_fds * percent
-        # self.log.debug("There must be fewer than " + unicode_type(min_lns) + " unmarked lines to add markup")
+        # self.log.debug("There must be fewer than " + str(min_lns) + " unmarked lines to add markup")
         return min_lns > tot_htm_ends
 
     def dump(self, raw, where):
@@ -161,17 +160,17 @@ class HeuristicProcessor:
         ]
 
         ITALICIZE_STYLE_PATS = [
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])_\*/(?P<words>[^\*_]+)/\*_'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])~~(?P<words>[^~]+)~~'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])_/(?P<words>[^/_]+)/_'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])_\*(?P<words>[^\*_]+)\*_'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])\*/(?P<words>[^/\*]+)/\*'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])/:(?P<words>[^:/]+):/'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])\|:(?P<words>[^:\|]+):\|'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])\*(?P<words>[^\*]+)\*'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])~(?P<words>[^~]+)~'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])/(?P<words>[^/\*><]+)/'),
-            unicode_type(r'(?msu)(?<=[\s>"“\'‘])_(?P<words>[^_]+)_'),
+            r'(?msu)(?<=[\s>"“\'‘])_\*/(?P<words>[^\*_]+)/\*_',
+            r'(?msu)(?<=[\s>"“\'‘])~~(?P<words>[^~]+)~~',
+            r'(?msu)(?<=[\s>"“\'‘])_/(?P<words>[^/_]+)/_',
+            r'(?msu)(?<=[\s>"“\'‘])_\*(?P<words>[^\*_]+)\*_',
+            r'(?msu)(?<=[\s>"“\'‘])\*/(?P<words>[^/\*]+)/\*',
+            r'(?msu)(?<=[\s>"“\'‘])/:(?P<words>[^:/]+):/',
+            r'(?msu)(?<=[\s>"“\'‘])\|:(?P<words>[^:\|]+):\|',
+            r'(?msu)(?<=[\s>"“\'‘])\*(?P<words>[^\*]+)\*',
+            r'(?msu)(?<=[\s>"“\'‘])~(?P<words>[^~]+)~',
+            r'(?msu)(?<=[\s>"“\'‘])/(?P<words>[^/\*><]+)/',
+            r'(?msu)(?<=[\s>"“\'‘])_(?P<words>[^_]+)_',
         ]
 
         for word in ITALICIZE_WORDS:
@@ -181,10 +180,10 @@ class HeuristicProcessor:
         search_text = re.sub(r'<[^>]*>', '', search_text)
         for pat in ITALICIZE_STYLE_PATS:
             for match in re.finditer(pat, search_text):
-                ital_string = unicode_type(match.group('words'))
-                # self.log.debug("italicising "+unicode_type(match.group(0))+"    with <i>"+ital_string+"</i>")
+                ital_string = str(match.group('words'))
+                # self.log.debug("italicising "+str(match.group(0))+"    with <i>"+ital_string+"</i>")
                 try:
-                    html = re.sub(re.escape(unicode_type(match.group(0))), '<i>%s</i>' % ital_string, html)
+                    html = re.sub(re.escape(str(match.group(0))), '<i>%s</i>' % ital_string, html)
                 except OverflowError:
                     # match.group(0) was too large to be compiled into a regex
                     continue
@@ -209,10 +208,10 @@ class HeuristicProcessor:
             if wordcount > 200000:
                 typical_chapters = 15000.
             self.min_chapters = int(ceil(wordcount / typical_chapters))
-        self.log.debug("minimum chapters required are: "+unicode_type(self.min_chapters))
+        self.log.debug("minimum chapters required are: "+str(self.min_chapters))
         heading = re.compile('<h[1-3][^>]*>', re.IGNORECASE)
         self.html_preprocess_sections = len(heading.findall(html))
-        self.log.debug("found " + unicode_type(self.html_preprocess_sections) + " pre-existing headings")
+        self.log.debug("found " + str(self.html_preprocess_sections) + " pre-existing headings")
 
         # Build the Regular Expressions in pieces
         init_lookahead = "(?=<(p|div))"
@@ -302,7 +301,7 @@ class HeuristicProcessor:
                 if n_lookahead_req:
                     n_lookahead = re.sub("(ou|in|cha)", "lookahead_", full_chapter_line)
                 if not analyze:
-                    self.log.debug("Marked " + unicode_type(self.html_preprocess_sections) + " headings, " + log_message)
+                    self.log.debug("Marked " + str(self.html_preprocess_sections) + " headings, " + log_message)
 
                 chapter_marker = arg_ignorecase+init_lookahead+full_chapter_line+blank_lines+lp_n_lookahead_open+n_lookahead+lp_n_lookahead_close+ \
                     lp_opt_title_open+title_line_open+title_header_open+lp_title+title_header_close+title_line_close+lp_opt_title_close
@@ -316,10 +315,10 @@ class HeuristicProcessor:
                             title_req = True
                             strict_title = False
                         self.log.debug(
-                                unicode_type(type_name)+" had "+unicode_type(hits)+
-                                " hits - "+unicode_type(self.chapters_no_title)+" chapters with no title, "+
-                                unicode_type(self.chapters_with_title)+" chapters with titles, "+
-                                unicode_type(float(self.chapters_with_title) / float(hits))+" percent. ")
+                                str(type_name)+" had "+str(hits)+
+                                " hits - "+str(self.chapters_no_title)+" chapters with no title, "+
+                                str(self.chapters_with_title)+" chapters with titles, "+
+                                str(float(self.chapters_with_title) / float(hits))+" percent. ")
                         if type_name == 'common':
                             analysis_result.append([chapter_type, n_lookahead_req, strict_title, ignorecase, title_req, log_message, type_name])
                         elif self.min_chapters <= hits < max_chapters or self.min_chapters < 3 > hits:
@@ -336,8 +335,8 @@ class HeuristicProcessor:
         words_per_chptr = wordcount
         if words_per_chptr > 0 and self.html_preprocess_sections > 0:
             words_per_chptr = wordcount // self.html_preprocess_sections
-        self.log.debug("Total wordcount is: "+ unicode_type(wordcount)+", Average words per section is: "+
-                       unicode_type(words_per_chptr)+", Marked up "+unicode_type(self.html_preprocess_sections)+" chapters")
+        self.log.debug("Total wordcount is: "+ str(wordcount)+", Average words per section is: "+
+                       str(words_per_chptr)+", Marked up "+str(self.html_preprocess_sections)+" chapters")
         return html
 
     def punctuation_unwrap(self, length, content, format):
@@ -367,8 +366,8 @@ class HeuristicProcessor:
 
         # define the pieces of the regex
         # (?<!\&\w{4});) is a semicolon not part of an entity
-        lookahead = "(?<=.{"+unicode_type(length)+r"}([a-zა-ჰäëïöüàèìòùáćéíĺóŕńśúýâêîôûçąężıãõñæøþðßěľščťžňďřů,:)\\IAß]|(?<!\&\w{4});))"
-        em_en_lookahead = "(?<=.{"+unicode_type(length)+"}[\u2013\u2014])"
+        lookahead = "(?<=.{"+str(length)+r"}([a-zა-ჰäëïöüàèìòùáćéíĺóŕńśúýâêîôûçąężıãõñæøþðßěľščťžňďřů,:)\\IAß]|(?<!\&\w{4});))"
+        em_en_lookahead = "(?<=.{"+str(length)+"}[\u2013\u2014])"
         soft_hyphen = "\xad"
         line_ending = "\\s*(?P<style_close></(span|[iub])>)?\\s*(</(p|div)>)?"
         blanklines = "\\s*(?P<up2threeblanks><(p|span|div)[^>]*>\\s*(<(p|span|div)[^>]*>\\s*</(span|p|div)>\\s*)</(span|p|div)>\\s*){0,3}\\s*"
@@ -428,18 +427,18 @@ class HeuristicProcessor:
         return html
 
     def fix_nbsp_indents(self, html):
-        txtindent = re.compile(unicode_type(r'<(?P<tagtype>p|div)(?P<formatting>[^>]*)>\s*(?P<span>(<span[^>]*>\s*)+)?\s*(\u00a0){2,}'), re.IGNORECASE)
+        txtindent = re.compile(r'<(?P<tagtype>p|div)(?P<formatting>[^>]*)>\s*(?P<span>(<span[^>]*>\s*)+)?\s*(\u00a0){2,}', re.IGNORECASE)
         html = txtindent.sub(self.insert_indent, html)
         if self.found_indents > 1:
-            self.log.debug("replaced "+unicode_type(self.found_indents)+ " nbsp indents with inline styles")
+            self.log.debug("replaced "+str(self.found_indents)+ " nbsp indents with inline styles")
         return html
 
     def cleanup_markup(self, html):
         # remove remaining non-breaking spaces
-        html = re.sub(unicode_type(r'\u00a0'), ' ', html)
+        html = re.sub(r'\u00a0', ' ', html)
         # Get rid of various common microsoft specific tags which can cause issues later
         # Get rid of empty <o:p> tags to simplify other processing
-        html = re.sub(unicode_type(r'\s*<o:p>\s*</o:p>'), ' ', html)
+        html = re.sub(r'\s*<o:p>\s*</o:p>', ' ', html)
         # Delete microsoft 'smart' tags
         html = re.sub('(?i)</?st1:\\w+>', '', html)
         # Re-open self closing paragraph tags
@@ -479,8 +478,8 @@ class HeuristicProcessor:
         blanklines = self.blankreg.findall(html)
         lines = self.linereg.findall(html)
         if len(lines) > 1:
-            self.log.debug("There are " + unicode_type(len(blanklines)) + " blank lines. " +
-                    unicode_type(float(len(blanklines)) / float(len(lines))) + " percent blank")
+            self.log.debug("There are " + str(len(blanklines)) + " blank lines. " +
+                    str(float(len(blanklines)) / float(len(lines))) + " percent blank")
 
             if float(len(blanklines)) / float(len(lines)) > 0.40:
                 return True
@@ -502,11 +501,11 @@ class HeuristicProcessor:
             lines = float(len(self.single_blank.findall(to_merge))) - 1.
             em = base_em + (em_per_line * lines)
             if to_merge.find('whitespace'):
-                newline = self.any_multi_blank.sub('\n<p class="whitespace'+unicode_type(int(em * 10))+
-                                                   '" style="text-align:center; margin-top:'+unicode_type(em)+'em"> </p>', match.group(0))
+                newline = self.any_multi_blank.sub('\n<p class="whitespace'+str(int(em * 10))+
+                                                   '" style="text-align:center; margin-top:'+str(em)+'em"> </p>', match.group(0))
             else:
-                newline = self.any_multi_blank.sub('\n<p class="softbreak'+unicode_type(int(em * 10))+
-                                                   '" style="text-align:center; margin-top:'+unicode_type(em)+'em"> </p>', match.group(0))
+                newline = self.any_multi_blank.sub('\n<p class="softbreak'+str(int(em * 10))+
+                                                   '" style="text-align:center; margin-top:'+str(em)+'em"> </p>', match.group(0))
             return newline
 
         html = self.any_multi_blank.sub(merge_matches, html)
@@ -530,9 +529,9 @@ class HeuristicProcessor:
             top_margin = ''
             bottom_margin = ''
             if initblanks is not None:
-                top_margin = 'margin-top:'+unicode_type(len(self.single_blank.findall(initblanks)))+'em;'
+                top_margin = 'margin-top:'+str(len(self.single_blank.findall(initblanks)))+'em;'
             if endblanks is not None:
-                bottom_margin = 'margin-bottom:'+unicode_type(len(self.single_blank.findall(endblanks)))+'em;'
+                bottom_margin = 'margin-bottom:'+str(len(self.single_blank.findall(endblanks)))+'em;'
 
             if initblanks is None and endblanks is None:
                 return content
@@ -609,7 +608,7 @@ class HeuristicProcessor:
                     else:
                         replacement_break = re.sub('(?i)(width=\\d+\\%?|width:\\s*\\d+(\\%|px|pt|em)?;?)', '', replacement_break)
                         divpercent = (100 - width) // 2
-                        hr_open = re.sub('45', unicode_type(divpercent), hr_open)
+                        hr_open = re.sub('45', str(divpercent), hr_open)
                         scene_break = hr_open+replacement_break+'</div>'
                 else:
                     scene_break = hr_open+'<hr style="height: 3px; background:#505050" /></div>'
@@ -669,12 +668,12 @@ class HeuristicProcessor:
             else:
                 styles = match.group('styles').split(';')
                 is_paragraph = self.check_paragraph(content)
-                # print "styles for this line are: "+unicode_type(styles)
+                # print "styles for this line are: "+str(styles)
                 split_styles = []
                 for style in styles:
-                    # print "style is: "+unicode_type(style)
+                    # print "style is: "+str(style)
                     newstyle = style.split(':')
-                    # print "newstyle is: "+unicode_type(newstyle)
+                    # print "newstyle is: "+str(newstyle)
                     split_styles.append(newstyle)
                 styles = split_styles
                 for style, setting in styles:
@@ -685,7 +684,7 @@ class HeuristicProcessor:
                         if 9 < setting < 14:
                             text_indent = indented_text
                         else:
-                            text_indent = style+':'+unicode_type(setting)+'pt;'
+                            text_indent = style+':'+str(setting)+'pt;'
                     if style == 'padding':
                         setting = re.sub('pt', '', setting).split(' ')
                         if int(setting[1]) < 16 and int(setting[3]) < 16:
@@ -706,23 +705,23 @@ class HeuristicProcessor:
                             blockquote_open_loop = blockquote_open
                         if debugabby:
                             self.log.debug('\n\n******\n')
-                            self.log.debug('padding top is: '+unicode_type(setting[0]))
-                            self.log.debug('padding right is:' +unicode_type(setting[1]))
-                            self.log.debug('padding bottom is: ' + unicode_type(setting[2]))
-                            self.log.debug('padding left is: ' +unicode_type(setting[3]))
+                            self.log.debug('padding top is: '+str(setting[0]))
+                            self.log.debug('padding right is:' +str(setting[1]))
+                            self.log.debug('padding bottom is: ' + str(setting[2]))
+                            self.log.debug('padding left is: ' +str(setting[3]))
 
-                # print "text-align is: "+unicode_type(text_align)
-                # print "\n***\nline is:\n     "+unicode_type(match.group(0))+'\n'
+                # print "text-align is: "+str(text_align)
+                # print "\n***\nline is:\n     "+str(match.group(0))+'\n'
                 if debugabby:
-                    # print "this line is a paragraph = "+unicode_type(is_paragraph)+", previous line was "+unicode_type(self.previous_was_paragraph)
+                    # print "this line is a paragraph = "+str(is_paragraph)+", previous line was "+str(self.previous_was_paragraph)
                     self.log.debug("styles for this line were:", styles)
                     self.log.debug('newline is:')
                     self.log.debug(blockquote_open_loop+blockquote_close_loop+
                             paragraph_before+'<p style="'+text_indent+text_align+
                             '">'+content+'</p>'+paragraph_after+'\n\n\n\n\n')
-                # print "is_paragraph is "+unicode_type(is_paragraph)+", previous_was_paragraph is "+unicode_type(self.previous_was_paragraph)
+                # print "is_paragraph is "+str(is_paragraph)+", previous_was_paragraph is "+str(self.previous_was_paragraph)
                 self.previous_was_paragraph = is_paragraph
-                # print "previous_was_paragraph is now set to "+unicode_type(self.previous_was_paragraph)+"\n\n\n"
+                # print "previous_was_paragraph is now set to "+str(self.previous_was_paragraph)+"\n\n\n"
                 return blockquote_open_loop+blockquote_close_loop+paragraph_before+'<p style="'+text_indent+text_align+'">'+content+'</p>'+paragraph_after
 
         html = abbyy_line.sub(convert_styles, html)
@@ -805,12 +804,12 @@ class HeuristicProcessor:
         # more of the lines break in the same region of the document then unwrapping is required
         docanalysis = DocAnalysis(format, html)
         hardbreaks = docanalysis.line_histogram(.50)
-        self.log.debug("Hard line breaks check returned "+unicode_type(hardbreaks))
+        self.log.debug("Hard line breaks check returned "+str(hardbreaks))
 
         # Calculate Length
         unwrap_factor = getattr(self.extra_opts, 'html_unwrap_factor', 0.4)
         length = docanalysis.line_length(unwrap_factor)
-        self.log.debug("Median line length is " + unicode_type(length) + ", calculated with " + format + " format")
+        self.log.debug("Median line length is " + str(length) + ", calculated with " + format + " format")
 
         # ##### Unwrap lines ######
         if getattr(self.extra_opts, 'unwrap_lines', False):
@@ -832,7 +831,7 @@ class HeuristicProcessor:
         # If still no sections after unwrapping mark split points on lines with no punctuation
         if self.html_preprocess_sections < self.min_chapters and getattr(self.extra_opts, 'markup_chapter_headings', False):
             self.log.debug("Looking for more split points based on punctuation,"
-                    " currently have " + unicode_type(self.html_preprocess_sections))
+                    " currently have " + str(self.html_preprocess_sections))
             chapdetect3 = re.compile(
                 r'<(?P<styles>(p|div)[^>]*)>\s*(?P<section>(<span[^>]*>)?\s*(?!([\W]+\s*)+)'
                 r'(<[ibu][^>]*>){0,2}\s*(<span[^>]*>)?\s*(<[ibu][^>]*>){0,2}\s*(<span[^>]*>)?\s*'

src/calibre/ebooks/css_transform_rules.py

@@ -12,7 +12,7 @@ from css_parser.css import Property, CSSRule
 from calibre import force_unicode
 from calibre.ebooks import parse_css_length
 from calibre.ebooks.oeb.normalize_css import normalizers, safe_parser
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 
 
 def compile_pat(pat):
@@ -161,7 +161,7 @@ def transform_number(val, op, raw):
     v = op(v, val)
     if int(v) == v:
         v = int(v)
-    return unicode_type(v) + u
+    return str(v) + u
 
 
 class Rule:
@@ -379,7 +379,7 @@ def test(return_tests=False):  # {{{
         r = Rule(**rule)
         decl = StyleDeclaration(safe_parser().parseStyle(style))
         r.process_declaration(decl)
-        return unicode_type(decl)
+        return str(decl)
 
     class TestTransforms(unittest.TestCase):
         longMessage = True

src/calibre/ebooks/docx/footnotes.py

@@ -6,7 +6,7 @@ __license__ = 'GPL v3'
 __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 
 from collections import OrderedDict
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 
 
 class Note:
@@ -52,8 +52,8 @@ class Footnotes:
         if note is not None and note.type == 'normal':
             self.counter += 1
             anchor = 'note_%d' % self.counter
-            self.notes[anchor] = (unicode_type(self.counter), note)
-            return anchor, unicode_type(self.counter)
+            self.notes[anchor] = (str(self.counter), note)
+            return anchor, str(self.counter)
         return None, None
 
     def __iter__(self):

src/calibre/ebooks/docx/numbering.py

@@ -14,7 +14,7 @@ from lxml.html.builder import OL, UL, SPAN
 from calibre.ebooks.docx.block_styles import ParagraphStyle
 from calibre.ebooks.docx.char_styles import RunStyle, inherit
 from calibre.ebooks.metadata import roman
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 
 STYLE_MAP = {
     'aiueo': 'hiragana',
@@ -291,7 +291,7 @@ class Numbering:
                     seen_instances.add(num_id)
                     p.tag = 'li'
                     p.set('value', '%s' % counter[ilvl])
-                    p.set('list-lvl', unicode_type(ilvl))
+                    p.set('list-lvl', str(ilvl))
                     p.set('list-id', num_id)
                     if lvl.num_template is not None:
                         val = lvl.format_template(counter, ilvl, lvl.num_template)

src/calibre/ebooks/docx/tables.py

@@ -9,7 +9,7 @@ from lxml.html.builder import TABLE, TR, TD
 
 from calibre.ebooks.docx.block_styles import inherit, read_shd as rs, read_border, binary_property, border_props, ParagraphStyle, border_to_css
 from calibre.ebooks.docx.char_styles import RunStyle
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from polyglot.builtins import iteritems, itervalues
 
 # Read from XML {{{
 read_shd = rs
@@ -646,9 +646,9 @@ class Table:
                 td = TD()
                 style_map[td] = s = self.style_map[tc]
                 if s.col_span is not inherit:
-                    td.set('colspan', unicode_type(s.col_span))
+                    td.set('colspan', str(s.col_span))
                 if s.row_span is not inherit:
-                    td.set('rowspan', unicode_type(s.row_span))
+                    td.set('rowspan', str(s.row_span))
                 td.tail = '\n\t\t\t'
                 tr.append(td)
                 for x in self.namespace.XPath('./w:p|./w:tbl')(tc):

src/calibre/ebooks/docx/to_html.py

@@ -28,7 +28,7 @@ from calibre.ebooks.docx.fields import Fields
 from calibre.ebooks.docx.settings import Settings
 from calibre.ebooks.metadata.opf2 import OPFCreator
 from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from polyglot.builtins import iteritems, itervalues
 
 
 NBSP = '\xa0'
@@ -480,7 +480,7 @@ class Convert:
                 current_hyperlink = x
             elif x.tag.endswith('}instrText') and x.text and x.text.strip().startswith('TOC '):
                 old_anchor = current_anchor
-                anchor = unicode_type(uuid.uuid4())
+                anchor = str(uuid.uuid4())
                 self.anchor_map[anchor] = current_anchor = generate_anchor('toc', frozenset(itervalues(self.anchor_map)))
                 self.toc_anchor = current_anchor
                 if old_anchor is not None:
@@ -507,7 +507,7 @@ class Convert:
         if m is not None:
             n = min(6, max(1, int(m.group(1))))
             dest.tag = 'h%d' % n
-            dest.set('data-heading-level', unicode_type(n))
+            dest.set('data-heading-level', str(n))
 
         if style.bidi is True:
             dest.set('dir', 'rtl')

src/calibre/ebooks/docx/writer/container.py

@@ -18,7 +18,7 @@ from calibre.ebooks.pdf.render.common import PAPER_SIZES
 from calibre.utils.date import utcnow
 from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
 from calibre.utils.zipfile import ZipFile
-from polyglot.builtins import iteritems, unicode_type, native_string_type
+from polyglot.builtins import iteritems, native_string_type
 
 
 def xml2str(root, pretty_print=False, with_tail=False):
@@ -65,9 +65,9 @@ def create_skeleton(opts, namespaces=None):
 
     def margin(which):
         val = page_margin(opts, which)
-        return w(which), unicode_type(int(val * 20))
+        return w(which), str(int(val * 20))
     body.append(E.sectPr(
-        E.pgSz(**{w('w'):unicode_type(width), w('h'):unicode_type(height)}),
+        E.pgSz(**{w('w'):str(width), w('h'):str(height)}),
         E.pgMar(**dict(map(margin, 'left top right bottom'.split()))),
         E.cols(**{w('space'):'720'}),
         E.docGrid(**{w('linePitch'):"360"}),

src/calibre/ebooks/docx/writer/from_html.py

@@ -18,7 +18,7 @@ from calibre.ebooks.docx.writer.lists import ListsManager
 from calibre.ebooks.oeb.stylizer import Stylizer as Sz, Style as St
 from calibre.ebooks.oeb.base import XPath, barename
 from calibre.utils.localization import lang_as_iso639_1
-from polyglot.builtins import unicode_type, string_or_bytes
+from polyglot.builtins import string_or_bytes
 
 
 def lang_for_tag(tag):
@@ -108,7 +108,7 @@ class TextRun:
         for text, preserve_whitespace, bookmark in self.texts:
             if bookmark is not None:
                 bid = links_manager.bookmark_id
-                makeelement(r, 'w:bookmarkStart', w_id=unicode_type(bid), w_name=bookmark)
+                makeelement(r, 'w:bookmarkStart', w_id=str(bid), w_name=bookmark)
             if text is None:
                 makeelement(r, 'w:br', w_clear=preserve_whitespace)
             elif hasattr(text, 'xpath'):
@@ -123,7 +123,7 @@ class TextRun:
                 else:
                     add_text('', preserve_whitespace)
             if bookmark is not None:
-                makeelement(r, 'w:bookmarkEnd', w_id=unicode_type(bid))
+                makeelement(r, 'w:bookmarkEnd', w_id=str(bid))
 
     def __repr__(self):
         return repr(self.texts)
@@ -139,7 +139,7 @@ class TextRun:
     def style_weight(self):
         ans = 0
         for text, preserve_whitespace, bookmark in self.texts:
-            if isinstance(text, unicode_type):
+            if isinstance(text, str):
                 ans += len(text)
         return ans
 
@@ -219,7 +219,7 @@ class Block:
         p = makeelement(body, 'w:p')
         end_bookmarks = []
         for bmark in self.bookmarks:
-            end_bookmarks.append(unicode_type(self.links_manager.bookmark_id))
+            end_bookmarks.append(str(self.links_manager.bookmark_id))
             makeelement(p, 'w:bookmarkStart', w_id=end_bookmarks[-1], w_name=bmark)
         if self.block_lang:
             rpr = makeelement(p, 'w:rPr')
@@ -232,8 +232,8 @@ class Block:
             self.float_spec.serialize(self, ppr)
         if self.numbering_id is not None:
             numpr = makeelement(ppr, 'w:numPr')
-            makeelement(numpr, 'w:ilvl', w_val=unicode_type(self.numbering_id[1]))
-            makeelement(numpr, 'w:numId', w_val=unicode_type(self.numbering_id[0]))
+            makeelement(numpr, 'w:ilvl', w_val=str(self.numbering_id[1]))
+            makeelement(numpr, 'w:numId', w_val=str(self.numbering_id[0]))
         if self.linked_style is not None:
             makeelement(ppr, 'w:pStyle', w_val=self.linked_style.id)
         elif self.style.id:
@@ -453,8 +453,8 @@ class Convert:
         if self.add_toc:
             self.links_manager.process_toc_links(self.oeb)
 
-        if self.add_cover and self.oeb.metadata.cover and unicode_type(self.oeb.metadata.cover[0]) in self.oeb.manifest.ids:
-            cover_id = unicode_type(self.oeb.metadata.cover[0])
+        if self.add_cover and self.oeb.metadata.cover and str(self.oeb.metadata.cover[0]) in self.oeb.manifest.ids:
+            cover_id = str(self.oeb.metadata.cover[0])
             item = self.oeb.manifest.ids[cover_id]
             self.cover_img = self.images_manager.read_image(item.href)
 

src/calibre/ebooks/docx/writer/images.py

@@ -9,7 +9,7 @@ import os
 import posixpath
 from collections import namedtuple
 from functools import partial
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from polyglot.builtins import iteritems, itervalues
 
 from lxml import etree
 
@@ -34,7 +34,7 @@ def get_image_margins(style):
     ans = {}
     for edge in 'Left Right Top Bottom'.split():
         val = as_num(getattr(style, 'padding' + edge)) + as_num(getattr(style, 'margin' + edge))
-        ans['dist' + edge[0]] = unicode_type(pt_to_emu(val))
+        ans['dist' + edge[0]] = str(pt_to_emu(val))
     return ans
 
 
@@ -131,7 +131,7 @@ class ImagesManager:
             makeelement(parent, 'wp:simplePos', x='0', y='0')
             makeelement(makeelement(parent, 'wp:positionH', relativeFrom='margin'), 'wp:align').text = floating
             makeelement(makeelement(parent, 'wp:positionV', relativeFrom='line'), 'wp:align').text = 'top'
-        makeelement(parent, 'wp:extent', cx=unicode_type(width), cy=unicode_type(height))
+        makeelement(parent, 'wp:extent', cx=str(width), cy=str(height))
         if fake_margins:
             # DOCX does not support setting margins for inline images, so we
             # fake it by using effect extents to simulate margins
@@ -149,7 +149,7 @@ class ImagesManager:
 
     def create_docx_image_markup(self, parent, name, alt, img_rid, width, height):
         makeelement, namespaces = self.document_relationships.namespace.makeelement, self.document_relationships.namespace.namespaces
-        makeelement(parent, 'wp:docPr', id=unicode_type(self.count), name=name, descr=alt)
+        makeelement(parent, 'wp:docPr', id=str(self.count), name=name, descr=alt)
         makeelement(makeelement(parent, 'wp:cNvGraphicFramePr'), 'a:graphicFrameLocks', noChangeAspect="1")
         g = makeelement(parent, 'a:graphic')
         gd = makeelement(g, 'a:graphicData', uri=namespaces['pic'])
@@ -162,7 +162,7 @@ class ImagesManager:
         makeelement(makeelement(bf, 'a:stretch'), 'a:fillRect')
         spPr = makeelement(pic, 'pic:spPr')
         xfrm = makeelement(spPr, 'a:xfrm')
-        makeelement(xfrm, 'a:off', x='0', y='0'), makeelement(xfrm, 'a:ext', cx=unicode_type(width), cy=unicode_type(height))
+        makeelement(xfrm, 'a:off', x='0', y='0'), makeelement(xfrm, 'a:ext', cx=str(width), cy=str(height))
         makeelement(makeelement(spPr, 'a:prstGeom', prst='rect'), 'a:avLst')
 
     def create_filename(self, href, fmt):
@@ -173,7 +173,7 @@ class ImagesManager:
         base = fname
         while fname.lower() in self.seen_filenames:
             num += 1
-            fname = base + unicode_type(num)
+            fname = base + str(num)
         self.seen_filenames.add(fname.lower())
         fname += os.extsep + fmt.lower()
         return fname
@@ -208,7 +208,7 @@ class ImagesManager:
         makeelement(makeelement(parent, 'wp:positionH', relativeFrom='page'), 'wp:align').text = 'center'
         makeelement(makeelement(parent, 'wp:positionV', relativeFrom='page'), 'wp:align').text = 'center'
         width, height = map(pt_to_emu, (width, height))
-        makeelement(parent, 'wp:extent', cx=unicode_type(width), cy=unicode_type(height))
+        makeelement(parent, 'wp:extent', cx=str(width), cy=str(height))
         makeelement(parent, 'wp:effectExtent', l='0', r='0', t='0', b='0')
         makeelement(parent, 'wp:wrapTopAndBottom')
         self.create_docx_image_markup(parent, 'cover.jpg', _('Cover'), img.rid, width, height)

src/calibre/ebooks/docx/writer/links.py

@@ -10,7 +10,6 @@ from uuid import uuid4
 
 from calibre.ebooks.oeb.base import urlquote
 from calibre.utils.filenames import ascii_text
-from polyglot.builtins import unicode_type
 from polyglot.urllib import urlparse
 
 
@@ -37,7 +36,7 @@ class TOCItem:
         p = makeelement(body, 'w:p', append=False)
         ppr = makeelement(p, 'w:pPr')
         makeelement(ppr, 'w:pStyle', w_val="Normal")
-        makeelement(ppr, 'w:ind', w_left='0', w_firstLineChars='0', w_firstLine='0', w_leftChars=unicode_type(200 * self.level))
+        makeelement(ppr, 'w:ind', w_left='0', w_firstLineChars='0', w_firstLine='0', w_leftChars=str(200 * self.level))
         if self.is_first:
             makeelement(ppr, 'w:pageBreakBefore', w_val='off')
             r = makeelement(p, 'w:r')
@@ -71,7 +70,7 @@ class LinksManager:
         self.namespace = namespace
         self.log = log
         self.document_relationships = document_relationships
-        self.top_anchor = unicode_type(uuid4().hex)
+        self.top_anchor = str(uuid4().hex)
         self.anchor_map = {}
         self.used_bookmark_names = set()
         self.bmark_id = 0

src/calibre/ebooks/docx/writer/lists.py

@@ -8,7 +8,7 @@ __copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
 from collections import defaultdict
 from operator import attrgetter
 
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from polyglot.builtins import iteritems, itervalues
 
 LIST_STYLES = frozenset(
     'disc circle square decimal decimal-leading-zero lower-roman upper-roman'
@@ -83,7 +83,7 @@ class NumberingDefinition:
 
     def serialize(self, parent):
         makeelement = self.namespace.makeelement
-        an = makeelement(parent, 'w:abstractNum', w_abstractNumId=unicode_type(self.num_id))
+        an = makeelement(parent, 'w:abstractNum', w_abstractNumId=str(self.num_id))
         makeelement(an, 'w:multiLevelType', w_val='hybridMultilevel')
         makeelement(an, 'w:name', w_val='List %d' % (self.num_id + 1))
         for level in self.levels:
@@ -114,12 +114,12 @@ class Level:
         return hash((self.start, self.num_fmt, self.lvl_text))
 
     def serialize(self, parent, makeelement):
-        lvl = makeelement(parent, 'w:lvl', w_ilvl=unicode_type(self.ilvl))
-        makeelement(lvl, 'w:start', w_val=unicode_type(self.start))
+        lvl = makeelement(parent, 'w:lvl', w_ilvl=str(self.ilvl))
+        makeelement(lvl, 'w:start', w_val=str(self.start))
         makeelement(lvl, 'w:numFmt', w_val=self.num_fmt)
         makeelement(lvl, 'w:lvlText', w_val=self.lvl_text)
         makeelement(lvl, 'w:lvlJc', w_val='left')
-        makeelement(makeelement(lvl, 'w:pPr'), 'w:ind', w_hanging='360', w_left=unicode_type(1152 + self.ilvl * 360))
+        makeelement(makeelement(lvl, 'w:pPr'), 'w:ind', w_hanging='360', w_left=str(1152 + self.ilvl * 360))
         if self.num_fmt == 'bullet':
             ff = {'\uf0b7':'Symbol', '\uf0a7':'Wingdings'}.get(self.lvl_text, 'Courier New')
             makeelement(makeelement(lvl, 'w:rPr'), 'w:rFonts', w_ascii=ff, w_hAnsi=ff, w_hint="default")
@@ -165,5 +165,5 @@ class ListsManager:
             defn.serialize(parent)
         makeelement = self.namespace.makeelement
         for defn in self.definitions:
-            n = makeelement(parent, 'w:num', w_numId=unicode_type(defn.num_id + 1))
-            makeelement(n, 'w:abstractNumId', w_val=unicode_type(defn.num_id))
+            n = makeelement(parent, 'w:num', w_numId=str(defn.num_id + 1))
+            makeelement(n, 'w:abstractNumId', w_val=str(defn.num_id))

src/calibre/ebooks/docx/writer/styles.py

@@ -14,7 +14,7 @@ from lxml import etree
 from calibre.ebooks import parse_css_length
 from calibre.ebooks.docx.writer.utils import convert_color, int_or_zero
 from calibre.utils.localization import lang_as_iso639_1
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 from tinycss.css21 import CSS21Parser
 
 css_parser = CSS21Parser()
@@ -76,7 +76,7 @@ class CombinedStyle:
         pPr = makeelement(block, 'w:pPr')
         self.bs.serialize_properties(pPr, normal_style.bs)
         if self.outline_level is not None:
-            makeelement(pPr, 'w:outlineLvl', w_val=unicode_type(self.outline_level + 1))
+            makeelement(pPr, 'w:outlineLvl', w_val=str(self.outline_level + 1))
         rPr = makeelement(block, 'w:rPr')
         self.rs.serialize_properties(rPr, normal_style.rs)
 
@@ -109,16 +109,16 @@ class FloatSpec:
 
     def serialize(self, block, parent):
         if self.is_dropcaps:
-            attrs = dict(w_dropCap='drop', w_lines=unicode_type(self.dropcaps_lines), w_wrap='around', w_vAnchor='text', w_hAnchor='text')
+            attrs = dict(w_dropCap='drop', w_lines=str(self.dropcaps_lines), w_wrap='around', w_vAnchor='text', w_hAnchor='text')
         else:
             attrs = dict(
                 w_wrap='around', w_vAnchor='text', w_hAnchor='text', w_xAlign=self.x_align, w_y='1',
-                w_hSpace=unicode_type(self.h_space), w_vSpace=unicode_type(self.v_space), w_hRule=self.h_rule
+                w_hSpace=str(self.h_space), w_vSpace=str(self.v_space), w_hRule=self.h_rule
             )
             if self.w is not None:
-                attrs['w_w'] = unicode_type(self.w)
+                attrs['w_w'] = str(self.w)
             if self.h is not None:
-                attrs['w_h'] = unicode_type(self.h)
+                attrs['w_h'] = str(self.h)
         self.makeelement(parent, 'w:framePr', **attrs)
         # Margins are already applied by the frame style, so override them to
         # be zero on individual blocks
@@ -138,7 +138,7 @@ class FloatSpec:
             width = getattr(self, 'border_%s_width' % edge)
             bstyle = getattr(self, 'border_%s_style' % edge)
             self.makeelement(
-                bdr, 'w:'+edge, w_space=unicode_type(padding), w_val=bstyle, w_sz=unicode_type(width), w_color=getattr(self, 'border_%s_color' % edge))
+                bdr, 'w:'+edge, w_space=str(padding), w_val=bstyle, w_sz=str(width), w_color=getattr(self, 'border_%s_color' % edge))
 
 
 class DOCXStyle:
@@ -234,7 +234,7 @@ class TextStyle(DOCXStyle):
             self.spacing = None
         va = css.first_vertical_align
         if isinstance(va, numbers.Number):
-            self.vertical_align = unicode_type(int(va * 2))
+            self.vertical_align = str(int(va * 2))
         else:
             val = {
                 'top':'superscript', 'text-top':'superscript', 'sup':'superscript', 'super':'superscript',
@@ -290,9 +290,9 @@ class TextStyle(DOCXStyle):
         w = self.w
         is_normal_style = self is normal_style
         if is_normal_style or self.padding != normal_style.padding:
-            bdr.set(w('space'), unicode_type(self.padding))
+            bdr.set(w('space'), str(self.padding))
         if is_normal_style or self.border_width != normal_style.border_width:
-            bdr.set(w('sz'), unicode_type(self.border_width))
+            bdr.set(w('sz'), str(self.border_width))
         if is_normal_style or self.border_style != normal_style.border_style:
             bdr.set(w('val'), self.border_style)
         if is_normal_style or self.border_color != normal_style.border_color:
@@ -342,7 +342,7 @@ class TextStyle(DOCXStyle):
         if check_attr('shadow'):
             rPr.append(makeelement(rPr, 'shadow', val=bmap(self.shadow)))
         if check_attr('spacing'):
-            rPr.append(makeelement(rPr, 'spacing', val=unicode_type(self.spacing or 0)))
+            rPr.append(makeelement(rPr, 'spacing', val=str(self.spacing or 0)))
         if is_normal_style:
             rPr.append(makeelement(rPr, 'vertAlign', val=self.vertical_align if self.vertical_align in {'superscript', 'subscript'} else 'baseline'))
         elif self.vertical_align != normal_style.vertical_align:
@@ -380,7 +380,7 @@ class DescendantTextStyle:
         for name, attr in (('sz', 'font_size'), ('b', 'bold'), ('i', 'italic')):
             pval, cval = vals(attr)
             if pval != cval:
-                val = 'on' if attr in {'bold', 'italic'} else unicode_type(cval)  # bold, italic are toggle properties
+                val = 'on' if attr in {'bold', 'italic'} else str(cval)  # bold, italic are toggle properties
                 for suffix in ('', 'Cs'):
                     add(name + suffix, val=val)
 
@@ -401,7 +401,7 @@ class DescendantTextStyle:
         if check('shadow'):
             add('shadow', val='on')  # toggle property
         if check('spacing'):
-            add('spacing', val=unicode_type(child_style.spacing or 0))
+            add('spacing', val=str(child_style.spacing or 0))
         if check('vertical_align'):
             val = child_style.vertical_align
             if val in {'superscript', 'subscript', 'baseline'}:
@@ -411,9 +411,9 @@ class DescendantTextStyle:
 
         bdr = {}
         if check('padding'):
-            bdr['space'] = unicode_type(child_style.padding)
+            bdr['space'] = str(child_style.padding)
         if check('border_width'):
-            bdr['sz'] = unicode_type(child_style.border_width)
+            bdr['sz'] = str(child_style.border_width)
         if check('border_style'):
             bdr['val'] = child_style.border_style
         if check('border_color'):
@@ -537,14 +537,14 @@ class BlockStyle(DOCXStyle):
             e = bdr.makeelement(w(edge))
             padding = getattr(self, 'padding_' + edge)
             if (self is normal_style and padding > 0) or (padding != getattr(normal_style, 'padding_' + edge)):
-                e.set(w('space'), unicode_type(padding))
+                e.set(w('space'), str(padding))
             width = getattr(self, 'border_%s_width' % edge)
             bstyle = getattr(self, 'border_%s_style' % edge)
             if (self is normal_style and width > 0 and bstyle != 'none'
                     ) or width != getattr(normal_style, 'border_%s_width' % edge
                     ) or bstyle != getattr(normal_style, 'border_%s_style' % edge):
                 e.set(w('val'), bstyle)
-                e.set(w('sz'), unicode_type(width))
+                e.set(w('sz'), str(width))
                 e.set(w('color'), getattr(self, 'border_%s_color' % edge))
             if e.attrib:
                 bdr.append(e)
@@ -568,15 +568,15 @@ class BlockStyle(DOCXStyle):
             if css_unit in ('em', 'ex'):
                 lines = max(0, int(css_val * (50 if css_unit == 'ex' else 100)))
                 if (self is normal_style and lines > 0) or getter(self) != getter(normal_style):
-                    spacing.set(w(attr + 'Lines'), unicode_type(lines))
+                    spacing.set(w(attr + 'Lines'), str(lines))
             else:
                 getter = attrgetter('margin_' + edge)
                 val = getter(self)
                 if (self is normal_style and val > 0) or val != getter(normal_style):
-                    spacing.set(w(attr), unicode_type(val))
+                    spacing.set(w(attr), str(val))
 
         if self is normal_style or self.line_height != normal_style.line_height:
-            spacing.set(w('line'), unicode_type(self.line_height))
+            spacing.set(w('line'), str(self.line_height))
             spacing.set(w('lineRule'), 'atLeast')
 
         if spacing.attrib:
@@ -589,31 +589,31 @@ class BlockStyle(DOCXStyle):
             if css_unit in ('em', 'ex'):
                 chars = max(0, int(css_val * (50 if css_unit == 'ex' else 100)))
                 if (self is normal_style and chars > 0) or getter(self) != getter(normal_style):
-                    ind.set(w(edge + 'Chars'), unicode_type(chars))
+                    ind.set(w(edge + 'Chars'), str(chars))
             else:
                 getter = attrgetter('margin_' + edge)
                 val = getter(self)
                 if (self is normal_style and val > 0) or val != getter(normal_style):
-                    ind.set(w(edge), unicode_type(val))
+                    ind.set(w(edge), str(val))
                     ind.set(w(edge + 'Chars'), '0')  # This is needed to override any declaration in the parent style
         css_val, css_unit = parse_css_length(self.css_text_indent)
         if css_unit in ('em', 'ex'):
             chars = int(css_val * (50 if css_unit == 'ex' else 100))
             if css_val >= 0:
                 if (self is normal_style and chars > 0) or self.css_text_indent != normal_style.css_text_indent:
-                    ind.set(w('firstLineChars'), unicode_type(chars))
+                    ind.set(w('firstLineChars'), str(chars))
             else:
                 if (self is normal_style and chars < 0) or self.css_text_indent != normal_style.css_text_indent:
-                    ind.set(w('hangingChars'), unicode_type(abs(chars)))
+                    ind.set(w('hangingChars'), str(abs(chars)))
         else:
             val = self.text_indent
             if val >= 0:
                 if (self is normal_style and val > 0) or self.text_indent != normal_style.text_indent:
-                    ind.set(w('firstLine'), unicode_type(val))
+                    ind.set(w('firstLine'), str(val))
                     ind.set(w('firstLineChars'), '0')  # This is needed to override any declaration in the parent style
             else:
                 if (self is normal_style and val < 0) or self.text_indent != normal_style.text_indent:
-                    ind.set(w('hanging'), unicode_type(abs(val)))
+                    ind.set(w('hanging'), str(abs(val)))
                     ind.set(w('hangingChars'), '0')
         if ind.attrib:
             pPr.append(ind)
@@ -687,7 +687,7 @@ class StylesManager:
                 pure_block_styles.add(bs)
 
         self.pure_block_styles = sorted(pure_block_styles, key=block_counts.__getitem__)
-        bnum = len(unicode_type(max(1, len(pure_block_styles) - 1)))
+        bnum = len(str(max(1, len(pure_block_styles) - 1)))
         for i, bs in enumerate(self.pure_block_styles):
             bs.id = bs.name = '%0{}d Block'.format(bnum) % i
             bs.seq = i
@@ -707,7 +707,7 @@ class StylesManager:
                 heading_style = styles[-1]
                 heading_style.outline_level = i
 
-        snum = len(unicode_type(max(1, len(counts) - 1)))
+        snum = len(str(max(1, len(counts) - 1)))
         heading_styles = []
         for i, (style, count) in enumerate(counts.most_common()):
             if i == 0:
@@ -735,7 +735,7 @@ class StylesManager:
                         if run.descendant_style is None:
                             run.descendant_style = descendant_style_map[ds] = ds
                         ds_counts[run.descendant_style] += run.style_weight
-        rnum = len(unicode_type(max(1, len(ds_counts) - 1)))
+        rnum = len(str(max(1, len(ds_counts) - 1)))
         for i, (text_style, count) in enumerate(ds_counts.most_common()):
             text_style.id = 'Text%d' % i
             text_style.name = '%0{}d Text'.format(rnum) % i

src/calibre/ebooks/docx/writer/tables.py

@@ -9,7 +9,7 @@ from collections import namedtuple
 
 from calibre.ebooks.docx.writer.utils import convert_color
 from calibre.ebooks.docx.writer.styles import read_css_block_borders as rcbb, border_edges
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 
 
 class Dummy:
@@ -115,7 +115,7 @@ class Cell:
     def serialize(self, parent, makeelement):
         tc = makeelement(parent, 'w:tc')
         tcPr = makeelement(tc, 'w:tcPr')
-        makeelement(tcPr, 'w:tcW', w_type=self.width[0], w_w=unicode_type(self.width[1]))
+        makeelement(tcPr, 'w:tcW', w_type=self.width[0], w_w=str(self.width[1]))
         # For some reason, Word 2007 refuses to honor <w:shd> at the table or row
         # level, despite what the specs say, so we inherit and apply at the
         # cell level
@@ -126,7 +126,7 @@ class Cell:
         b = makeelement(tcPr, 'w:tcBorders', append=False)
         for edge, border in iteritems(self.borders):
             if border is not None and border.width > 0 and border.style != 'none':
-                makeelement(b, 'w:' + edge, w_val=border.style, w_sz=unicode_type(border.width), w_color=border.color)
+                makeelement(b, 'w:' + edge, w_val=border.style, w_sz=str(border.width), w_color=border.color)
         if len(b) > 0:
             tcPr.append(b)
 
@@ -136,7 +136,7 @@ class Cell:
             if edge in {'top', 'bottom'} or (edge == 'left' and self is self.row.first_cell) or (edge == 'right' and self is self.row.last_cell):
                 padding += getattr(self.row, 'padding_' + edge)
             if padding > 0:
-                makeelement(m, 'w:' + edge, w_type='dxa', w_w=unicode_type(int(padding * 20)))
+                makeelement(m, 'w:' + edge, w_type='dxa', w_w=str(int(padding * 20)))
         if len(m) > 0:
             tcPr.append(m)
 
@@ -356,14 +356,14 @@ class Table:
             return
         tbl = makeelement(parent, 'w:tbl')
         tblPr = makeelement(tbl, 'w:tblPr')
-        makeelement(tblPr, 'w:tblW', w_type=self.width[0], w_w=unicode_type(self.width[1]))
+        makeelement(tblPr, 'w:tblW', w_type=self.width[0], w_w=str(self.width[1]))
         if self.float in {'left', 'right'}:
             kw = {'w_vertAnchor':'text', 'w_horzAnchor':'text', 'w_tblpXSpec':self.float}
             for edge in border_edges:
                 val = getattr(self, 'margin_' + edge) or 0
                 if {self.float, edge} == {'left', 'right'}:
                     val = max(val, 2)
-                kw['w_' + edge + 'FromText'] = unicode_type(max(0, int(val *20)))
+                kw['w_' + edge + 'FromText'] = str(max(0, int(val *20)))
             makeelement(tblPr, 'w:tblpPr', **kw)
         if self.jc is not None:
             makeelement(tblPr, 'w:jc', w_val=self.jc)

src/calibre/ebooks/epub/cfi/tests.py

@@ -8,7 +8,7 @@ __copyright__ = '2014, Kovid Goyal <kovid at kovidgoyal.net>'
 import unittest, numbers
 
 from calibre.ebooks.epub.cfi.parse import parser, cfi_sort_key, decode_cfi
-from polyglot.builtins import iteritems, unicode_type
+from polyglot.builtins import iteritems
 
 
 class Tests(unittest.TestCase):
@@ -59,7 +59,7 @@ class Tests(unittest.TestCase):
             if after is not None:
                 ta['after'] = after
             if params:
-                ta['params'] = {unicode_type(k):(v,) if isinstance(v, unicode_type) else v for k, v in iteritems(params)}
+                ta['params'] = {str(k):(v,) if isinstance(v, str) else v for k, v in iteritems(params)}
             if ta:
                 step['text_assertion'] = ta
             return ans

src/calibre/ebooks/epub/pages.py

@@ -12,7 +12,6 @@ from itertools import count
 from calibre.ebooks.oeb.base import XHTML_NS
 from calibre.ebooks.oeb.base import OEBBook
 from lxml.etree import XPath
-from polyglot.builtins import unicode_type
 
 NSMAP = {'h': XHTML_NS, 'html': XHTML_NS, 'xhtml': XHTML_NS}
 PAGE_RE = re.compile(r'page', re.IGNORECASE)
@@ -32,7 +31,7 @@ def filter_name(name):
 def build_name_for(expr):
     if not expr:
         counter = count(1)
-        return lambda elem: unicode_type(next(counter))
+        return lambda elem: str(next(counter))
     selector = XPath(expr, namespaces=NSMAP)
 
     def name_for(elem):

src/calibre/ebooks/epub/periodical.py

@@ -12,7 +12,6 @@ import time
 from calibre.constants import __appname__, __version__
 from calibre import strftime, prepare_string_for_xml as xml
 from calibre.utils.date import parse_date
-from polyglot.builtins import unicode_type
 
 SONY_METADATA = '''\
 <?xml version="1.0" encoding="utf-8"?>
@@ -83,21 +82,21 @@ SONY_ATOM_ENTRY = '''\
 
 def sony_metadata(oeb):
     m = oeb.metadata
-    title = short_title = unicode_type(m.title[0])
+    title = short_title = str(m.title[0])
     publisher = __appname__ + ' ' + __version__
     try:
-        pt = unicode_type(oeb.metadata.publication_type[0])
+        pt = str(oeb.metadata.publication_type[0])
         short_title = ':'.join(pt.split(':')[2:])
     except:
         pass
 
     try:
-        date = parse_date(unicode_type(m.date[0]),
+        date = parse_date(str(m.date[0]),
                 as_utc=False).strftime('%Y-%m-%d')
     except:
         date = strftime('%Y-%m-%d')
     try:
-        language = unicode_type(m.language[0]).replace('_', '-')
+        language = str(m.language[0]).replace('_', '-')
     except:
         language = 'en'
     short_title = xml(short_title, True)
@@ -115,9 +114,9 @@ def sony_metadata(oeb):
                 return True
 
     try:
-        base_id = unicode_type(list(filter(cal_id, m.identifier))[0])
+        base_id = str(list(filter(cal_id, m.identifier))[0])
     except:
-        base_id = unicode_type(uuid4())
+        base_id = str(uuid4())
 
     toc = oeb.toc
 
@@ -130,7 +129,7 @@ def sony_metadata(oeb):
         for x in toc:
             section.nodes.append(x)
         toc = TOC(klass='periodical', href=oeb.spine[2].href,
-                    title=unicode_type(oeb.metadata.title[0]))
+                    title=str(oeb.metadata.title[0]))
         toc.nodes.append(section)
 
     entries = []
@@ -145,7 +144,7 @@ def sony_metadata(oeb):
         d = 1
         bsectitle = sectitle
         while sectitle in seen_titles:
-            sectitle = bsectitle + ' ' + unicode_type(d)
+            sectitle = bsectitle + ' ' + str(d)
             d += 1
         seen_titles.add(sectitle)
         sectitle = xml(sectitle, True)
@@ -164,7 +163,7 @@ def sony_metadata(oeb):
             btitle = atitle
             d = 1
             while atitle in seen_titles:
-                atitle = btitle + ' ' + unicode_type(d)
+                atitle = btitle + ' ' + str(d)
                 d += 1
 
             auth = article.author if article.author else ''
@@ -181,7 +180,7 @@ def sony_metadata(oeb):
                 short_title=short_title,
                 section_title=sectitle,
                 href=article.href,
-                word_count=unicode_type(1),
+                word_count=str(1),
                 id=xml(base_id)+'/'+secid+'/'+aid
             ))
 

src/calibre/ebooks/fb2/fb2ml.py

@@ -20,7 +20,7 @@ from calibre.utils.localization import lang_as_iso639_1
 from calibre.utils.xml_parse import safe_xml_fromstring
 from calibre.utils.img import save_cover_data_to
 from calibre.ebooks.oeb.base import urlnormalize
-from polyglot.builtins import unicode_type, string_or_bytes
+from polyglot.builtins import string_or_bytes
 from polyglot.binary import as_base64_unicode
 from polyglot.urllib import urlparse
 
@@ -154,7 +154,7 @@ class FB2MLizer:
             metadata['author'] = '<author><first-name></first-name><last-name></last-name></author>'
 
         metadata['keywords'] = ''
-        tags = list(map(unicode_type, self.oeb_book.metadata.subject))
+        tags = list(map(str, self.oeb_book.metadata.subject))
         if tags:
             tags = ', '.join(prepare_string_for_xml(x) for x in tags)
             metadata['keywords'] = '<keywords>%s</keywords>'%tags
@@ -169,12 +169,12 @@ class FB2MLizer:
         year = publisher = isbn = ''
         identifiers = self.oeb_book.metadata['identifier']
         for x in identifiers:
-            if x.get(OPF('scheme'), None).lower() == 'uuid' or unicode_type(x).startswith('urn:uuid:'):
-                metadata['id'] = unicode_type(x).split(':')[-1]
+            if x.get(OPF('scheme'), None).lower() == 'uuid' or str(x).startswith('urn:uuid:'):
+                metadata['id'] = str(x).split(':')[-1]
                 break
         if metadata['id'] is None:
             self.log.warn('No UUID identifier found')
-            metadata['id'] = unicode_type(uuid.uuid4())
+            metadata['id'] = str(uuid.uuid4())
 
         try:
             date = self.oeb_book.metadata['date'][0]
@@ -236,7 +236,7 @@ class FB2MLizer:
             </description>''') % metadata
 
         # Remove empty lines.
-        return '\n'.join(filter(unicode_type.strip, header.splitlines()))
+        return '\n'.join(filter(str.strip, header.splitlines()))
 
     def fb2_footer(self):
         return '</FictionBook>'
@@ -247,8 +247,8 @@ class FB2MLizer:
         cover_href = None
 
         # Get the raster cover if it's available.
-        if self.oeb_book.metadata.cover and unicode_type(self.oeb_book.metadata.cover[0]) in self.oeb_book.manifest.ids:
-            id = unicode_type(self.oeb_book.metadata.cover[0])
+        if self.oeb_book.metadata.cover and str(self.oeb_book.metadata.cover[0]) in self.oeb_book.manifest.ids:
+            id = str(self.oeb_book.metadata.cover[0])
             cover_item = self.oeb_book.manifest.ids[id]
             if cover_item.media_type in OEB_RASTER_IMAGES:
                 cover_href = cover_item.href

src/calibre/ebooks/html/input.py

@@ -17,7 +17,6 @@ from calibre.ebooks.oeb.base import urlunquote
 from calibre.ebooks.chardet import detect_xml_encoding
 from calibre.constants import iswindows
 from calibre import unicode_path, as_unicode, replace_entities
-from polyglot.builtins import unicode_type
 from polyglot.urllib import urlparse, urlunparse
 
 
@@ -46,7 +45,7 @@ class Link:
         :param base: The base folder that relative URLs are with respect to.
                      Must be a unicode string.
         '''
-        assert isinstance(url, unicode_type) and isinstance(base, unicode_type)
+        assert isinstance(url, str) and isinstance(base, str)
         self.url         = url
         self.parsed_url  = urlparse(self.url)
         self.is_local    = self.parsed_url.scheme in ('', 'file')
@@ -155,7 +154,7 @@ class HTMLFile:
         return 'HTMLFile:%d:%s:%r'%(self.level, 'b' if self.is_binary else 'a', self.path)
 
     def __repr__(self):
-        return unicode_type(self)
+        return str(self)
 
     def find_links(self, src):
         for match in self.LINK_PAT.finditer(src):

src/calibre/ebooks/html/to_zip.py

@@ -10,7 +10,6 @@ import textwrap, os, glob
 
 from calibre.customize import FileTypePlugin
 from calibre.constants import numeric_version
-from polyglot.builtins import unicode_type
 
 
 class HTML2ZIP(FileTypePlugin):
@@ -114,7 +113,7 @@ every time you add an HTML file to the library.\
         config_dialog.exec_()
 
         if config_dialog.result() == QDialog.DialogCode.Accepted:
-            sc = unicode_type(sc.text()).strip()
+            sc = str(sc.text()).strip()
             if bf.isChecked():
                 sc += '|bf'
             customize_plugin(self, sc)

src/calibre/ebooks/htmlz/oeb2html.py

@@ -20,7 +20,7 @@ from calibre.ebooks.oeb.base import (
     XHTML, XHTML_NS, SVG_NS, barename, namespace, OEB_IMAGES, XLINK, rewrite_links, urlnormalize)
 from calibre.ebooks.oeb.stylizer import Stylizer
 from calibre.utils.logging import default_log
-from polyglot.builtins import unicode_type, string_or_bytes, as_unicode
+from polyglot.builtins import string_or_bytes, as_unicode
 from polyglot.urllib import urldefrag
 
 SELF_CLOSING_TAGS = {'area', 'base', 'basefont', 'br', 'hr', 'input', 'img', 'link', 'meta'}
@@ -46,7 +46,7 @@ class OEB2HTML:
         self.log.info('Converting OEB book to HTML...')
         self.opts = opts
         try:
-            self.book_title = unicode_type(oeb_book.metadata.title[0])
+            self.book_title = str(oeb_book.metadata.title[0])
         except Exception:
             self.book_title = _('Unknown')
         self.links = {}

src/calibre/ebooks/lit/reader.py

@@ -17,7 +17,7 @@ import calibre.ebooks.lit.mssha1 as mssha1
 from calibre.ebooks.oeb.base import urlnormalize, xpath
 from calibre.ebooks.oeb.reader import OEBReader
 from calibre.ebooks import DRMError
-from polyglot.builtins import codepoint_to_chr, unicode_type, string_or_bytes, itervalues
+from polyglot.builtins import codepoint_to_chr, string_or_bytes, itervalues
 from polyglot.urllib import unquote as urlunquote, urldefrag
 from calibre_extensions import lzx, msdes
 
@@ -121,7 +121,7 @@ def consume_sized_utf8_string(bytes, zpad=False):
 
 
 def encode(string):
-    return unicode_type(string).encode('ascii', 'xmlcharrefreplace')
+    return str(string).encode('ascii', 'xmlcharrefreplace')
 
 
 class UnBinary:
@@ -325,7 +325,7 @@ class UnBinary:
                             c = '"'
                         elif c == '<':
                             c = '&lt;'
-                        if isinstance(c, unicode_type):
+                        if isinstance(c, str):
                             c = c.encode('ascii', 'xmlcharrefreplace')
                         buf.write(c)
                     count -= 1

src/calibre/ebooks/lit/writer.py

@@ -29,7 +29,7 @@ from calibre.ebooks.lit.lzx import Compressor
 import calibre
 from calibre_extensions import msdes
 import calibre.ebooks.lit.mssha1 as mssha1
-from polyglot.builtins import codepoint_to_chr, unicode_type, string_or_bytes, native_string_type
+from polyglot.builtins import codepoint_to_chr, string_or_bytes, native_string_type
 from polyglot.urllib import urldefrag, unquote
 
 __all__ = ['LitWriter']
@@ -283,7 +283,7 @@ class ReBinary:
         data.write(codepoint_to_chr(len(self.anchors)).encode('utf-8'))
         for anchor, offset in self.anchors:
             data.write(codepoint_to_chr(len(anchor)).encode('utf-8'))
-            if isinstance(anchor, unicode_type):
+            if isinstance(anchor, str):
                 anchor = anchor.encode('utf-8')
             data.write(anchor)
             data.write(pack('<I', offset))
@@ -314,7 +314,7 @@ class LitWriter:
         oeb.metadata.add('calibre-version', calibre.__version__)
         cover = None
         if oeb.metadata.cover:
-            id = unicode_type(oeb.metadata.cover[0])
+            id = str(oeb.metadata.cover[0])
             cover = oeb.manifest.ids[id]
             for type, title in ALL_MS_COVER_TYPES:
                 if type not in oeb.guide:
@@ -486,7 +486,7 @@ class LitWriter:
                 data = rebin.content
                 name = name + '/content'
                 secnum = 1
-            elif isinstance(data, unicode_type):
+            elif isinstance(data, str):
                 data = data.encode('utf-8')
             elif hasattr(data, 'cssText'):
                 data = item.bytes_representation
@@ -521,9 +521,9 @@ class LitWriter:
                 item.offset = offset \
                     if state in ('linear', 'nonlinear') else 0
                 data.write(pack('<I', item.offset))
-                entry = [codepoint_to_chr(len(id)), unicode_type(id),
-                         codepoint_to_chr(len(href)), unicode_type(href),
-                         codepoint_to_chr(len(media_type)), unicode_type(media_type)]
+                entry = [codepoint_to_chr(len(id)), str(id),
+                         codepoint_to_chr(len(href)), str(href),
+                         codepoint_to_chr(len(media_type)), str(media_type)]
                 for value in entry:
                     data.write(value.encode('utf-8'))
                 data.write(b'\0')

src/calibre/ebooks/lrf/html/convert_from.py

@@ -32,7 +32,7 @@ from calibre.ebooks.lrf.pylrs.pylrs import (
     RuledLine, Span, Sub, Sup, TextBlock
 )
 from calibre.ptempfile import PersistentTemporaryFile
-from polyglot.builtins import itervalues, string_or_bytes, unicode_type
+from polyglot.builtins import itervalues, string_or_bytes
 from polyglot.urllib import unquote, urlparse
 
 """
@@ -278,7 +278,7 @@ class HTMLConverter:
                 update_css(npcss, self.override_pcss)
 
         paths = [os.path.abspath(path) for path in paths]
-        paths = [path.decode(sys.getfilesystemencoding()) if not isinstance(path, unicode_type) else path for path in paths]
+        paths = [path.decode(sys.getfilesystemencoding()) if not isinstance(path, str) else path for path in paths]
 
         while len(paths) > 0 and self.link_level <= self.link_levels:
             for path in paths:
@@ -358,7 +358,7 @@ class HTMLConverter:
                 os.makedirs(tdir)
             try:
                 with open(os.path.join(tdir, 'html2lrf-verbose.html'), 'wb') as f:
-                    f.write(unicode_type(soup).encode('utf-8'))
+                    f.write(str(soup).encode('utf-8'))
                     self.log.info(_('Written preprocessed HTML to ')+f.name)
             except:
                 pass
@@ -391,7 +391,7 @@ class HTMLConverter:
         self.log.info(_('\tConverting to BBeB...'))
         self.current_style = {}
         self.page_break_found = False
-        if not isinstance(path, unicode_type):
+        if not isinstance(path, str):
             path = path.decode(sys.getfilesystemencoding())
         self.target_prefix = path
         self.previous_text = '\n'
@@ -401,7 +401,7 @@ class HTMLConverter:
     def parse_css(self, style):
         """
         Parse the contents of a <style> tag or .css file.
-        @param style: C{unicode_type(style)} should be the CSS to parse.
+        @param style: C{str(style)} should be the CSS to parse.
         @return: A dictionary with one entry per selector where the key is the
         selector name and the value is a dictionary of properties
         """
@@ -589,7 +589,7 @@ class HTMLConverter:
             if isinstance(c, HTMLConverter.IGNORED_TAGS):
                 continue
             if isinstance(c, NavigableString):
-                text += unicode_type(c)
+                text += str(c)
             elif isinstance(c, Tag):
                 if c.name.lower() == 'img' and c.has_attr('alt'):
                     alt_text += c['alt']
@@ -644,7 +644,7 @@ class HTMLConverter:
             para, text, path, fragment = link['para'], link['text'], link['path'], link['fragment']
             ascii_text = text
 
-            if not isinstance(path, unicode_type):
+            if not isinstance(path, str):
                 path = path.decode(sys.getfilesystemencoding())
             if path in self.processed_files:
                 if path+fragment in self.targets.keys():
@@ -1087,7 +1087,7 @@ class HTMLConverter:
 
         s1, s2 = get('margin'), get('padding')
 
-        bl = unicode_type(self.current_block.blockStyle.attrs['blockwidth'])+'px'
+        bl = str(self.current_block.blockStyle.attrs['blockwidth'])+'px'
 
         def set(default, one, two):
             fval = None
@@ -1216,7 +1216,7 @@ class HTMLConverter:
                     ans = 120
             if ans is not None:
                 ans += int(self.font_delta * 20)
-                ans = unicode_type(ans)
+                ans = str(ans)
             return ans
 
         family, weight, style, variant = 'serif', 'normal', 'normal', None
@@ -1322,10 +1322,10 @@ class HTMLConverter:
     def text_properties(self, tag_css):
         indent = self.book.defaultTextStyle.attrs['parindent']
         if 'text-indent' in tag_css:
-            bl = unicode_type(self.current_block.blockStyle.attrs['blockwidth'])+'px'
+            bl = str(self.current_block.blockStyle.attrs['blockwidth'])+'px'
             if 'em' in tag_css['text-indent']:
                 bl = '10pt'
-            indent = self.unit_convert(unicode_type(tag_css['text-indent']), pts=True, base_length=bl)
+            indent = self.unit_convert(str(tag_css['text-indent']), pts=True, base_length=bl)
             if not indent:
                 indent = 0
             if indent > 0 and indent < 10 * self.minimum_indent:
@@ -1519,11 +1519,11 @@ class HTMLConverter:
                     elif not urlparse(tag['src'])[0]:
                         self.log.warn('Could not find image: '+tag['src'])
                 else:
-                    self.log.debug("Failed to process: %s"%unicode_type(tag))
+                    self.log.debug("Failed to process: %s"%str(tag))
             elif tagname in ['style', 'link']:
                 ncss, npcss = {}, {}
                 if tagname == 'style':
-                    text = ''.join([unicode_type(i) for i in tag.findAll(text=True)])
+                    text = ''.join([str(i) for i in tag.findAll(text=True)])
                     css, pcss = self.parse_css(text)
                     ncss.update(css)
                     npcss.update(pcss)
@@ -1555,7 +1555,7 @@ class HTMLConverter:
                 if tag.contents:
                     c = tag.contents[0]
                     if isinstance(c, NavigableString):
-                        c = unicode_type(c).replace('\r\n', '\n').replace('\r', '\n')
+                        c = str(c).replace('\r\n', '\n').replace('\r', '\n')
                         if c.startswith('\n'):
                             c = c[1:]
                             tag.contents[0] = NavigableString(c)
@@ -1613,7 +1613,7 @@ class HTMLConverter:
                             in_ol = parent.name.lower() == 'ol'
                             break
                         parent = parent.parent
-                    prepend = unicode_type(self.list_counter)+'. ' if in_ol else '\u2022' + ' '
+                    prepend = str(self.list_counter)+'. ' if in_ol else '\u2022' + ' '
                     self.current_para.append(Span(prepend))
                     self.process_children(tag, tag_css, tag_pseudo_css)
                     if in_ol:
@@ -1656,7 +1656,7 @@ class HTMLConverter:
 
                 if (self.anchor_ids and tag.has_attr('id')) or (self.book_designer and tag.get('class') in ('title', ['title'])):
                     if not tag.has_attr('id'):
-                        tag['id'] = __appname__+'_id_'+unicode_type(self.id_counter)
+                        tag['id'] = __appname__+'_id_'+str(self.id_counter)
                         self.id_counter += 1
 
                     tkey = self.target_prefix+tag['id']
@@ -1729,7 +1729,7 @@ class HTMLConverter:
                 except Exception as err:
                     self.log.warning(_('An error occurred while processing a table: %s. Ignoring table markup.')%repr(err))
                     self.log.exception('')
-                    self.log.debug(_('Bad table:\n%s')%unicode_type(tag)[:300])
+                    self.log.debug(_('Bad table:\n%s')%str(tag)[:300])
                     self.in_table = False
                     self.process_children(tag, tag_css, tag_pseudo_css)
                 finally:
@@ -1825,9 +1825,9 @@ def process_file(path, options, logger):
 
     for prop in ('author', 'author_sort', 'title', 'title_sort', 'publisher', 'freetext'):
         val = getattr(options, prop, None)
-        if val and not isinstance(val, unicode_type):
+        if val and not isinstance(val, str):
             soup = BeautifulSoup(val)
-            setattr(options, prop, unicode_type(soup))
+            setattr(options, prop, str(soup))
 
     title = (options.title, options.title_sort)
     author = (options.author, options.author_sort)
@@ -1871,7 +1871,7 @@ def process_file(path, options, logger):
     options.force_page_break = fpb
     options.link_exclude = le
     options.page_break = pb
-    if not isinstance(options.chapter_regex, unicode_type):
+    if not isinstance(options.chapter_regex, str):
         options.chapter_regex = options.chapter_regex.decode(preferred_encoding)
     options.chapter_regex = re.compile(options.chapter_regex, re.IGNORECASE)
     fpba = options.force_page_break_attr.split(',')

src/calibre/ebooks/lrf/input.py

@@ -12,7 +12,7 @@ from copy import deepcopy, copy
 from lxml import etree
 
 from calibre import guess_type
-from polyglot.builtins import as_bytes, unicode_type
+from polyglot.builtins import as_bytes
 
 
 class Canvas(etree.XSLTExtension):
@@ -70,9 +70,9 @@ class Canvas(etree.XSLTExtension):
         height = self.styles.to_num(block.get("ysize", None))
         img = div.makeelement('img')
         if width is not None:
-            img.set('width', unicode_type(int(width)))
+            img.set('width', str(int(width)))
         if height is not None:
-            img.set('height', unicode_type(int(height)))
+            img.set('height', str(int(height)))
         ref = block.get('refstream', None)
         if ref is not None:
             imstr = self.doc.xpath('//ImageStream[@objid="%s"]'%ref)
@@ -267,9 +267,9 @@ class TextBlock(etree.XSLTExtension):
             ysize = self.styles.to_num(child.get('ysize', None), 166/720)
             img = self.root.makeelement('img')
             if xsize is not None:
-                img.set('width', unicode_type(int(xsize)))
+                img.set('width', str(int(xsize)))
             if ysize is not None:
-                img.set('height', unicode_type(int(ysize)))
+                img.set('height', str(int(ysize)))
             ro = child.get('refobj', None)
             if ro in self.plot_map:
                 img.set('src', self.plot_map[ro])

src/calibre/ebooks/lrf/lrfparser.py

@@ -13,7 +13,7 @@ from calibre.utils.filenames import ascii_filename
 from calibre.ebooks.lrf.meta import LRFMetaFile
 from calibre.ebooks.lrf.objects import get_object, PageTree, StyleObject, \
                                          Font, Text, TOCObject, BookAttr, ruby_tags
-from polyglot.builtins import unicode_type, itervalues
+from polyglot.builtins import itervalues
 
 
 class LRFDocument(LRFMetaFile):
@@ -118,7 +118,7 @@ class LRFDocument(LRFMetaFile):
                 pages += '<PageTree objid="%d">\n'%(page_tree.id,)
                 close = '</PageTree>\n'
             for page in page_tree:
-                pages += unicode_type(page)
+                pages += str(page)
             pages += close
         traversed_objects = [int(i) for i in re.findall(r'objid="(\w+)"', pages)] + [pt_id]
 
@@ -131,9 +131,9 @@ class LRFDocument(LRFMetaFile):
             if isinstance(obj, (Font, Text, TOCObject)):
                 continue
             if isinstance(obj, StyleObject):
-                styles += unicode_type(obj)
+                styles += str(obj)
             else:
-                objects += unicode_type(obj)
+                objects += str(obj)
         styles += '</Style>\n'
         objects += '</Objects>\n'
         if write_files:

src/calibre/ebooks/lrf/lrs/convert_from.py

@@ -22,7 +22,7 @@ from calibre.ebooks.lrf.pylrs.pylrs import (
     TextStyle
 )
 from calibre.utils.config import OptionParser
-from polyglot.builtins import string_or_bytes, unicode_type
+from polyglot.builtins import string_or_bytes
 
 
 class LrsParser:
@@ -55,7 +55,7 @@ class LrsParser:
         for key, val in tag.attrs:
             if key in exclude:
                 continue
-            result[unicode_type(key)] = val
+            result[str(key)] = val
         return result
 
     def text_tag_to_element(self, tag):

src/calibre/ebooks/lrf/meta.py

@@ -22,7 +22,7 @@ from functools import wraps
 from calibre.ebooks.chardet import xml_to_unicode
 from calibre.utils.cleantext import clean_xml_chars
 from calibre.ebooks.metadata import MetaInformation, string_to_authors
-from polyglot.builtins import unicode_type, string_or_bytes
+from polyglot.builtins import string_or_bytes
 
 BYTE      = "<B"  #: Unsigned char little endian encoded in 1 byte
 WORD      = "<H"  #: Unsigned short little endian encoded in 2 bytes
@@ -52,8 +52,8 @@ class field:
     def __repr__(self):
         typ = {DWORD: 'unsigned int', 'QWORD': 'unsigned long long', BYTE: 'unsigned char', WORD: 'unsigned short'}.get(self._fmt, '')
         return "An " + typ + " stored in " + \
-        unicode_type(struct.calcsize(self._fmt)) + \
-        " bytes starting at byte " + unicode_type(self._start)
+        str(struct.calcsize(self._fmt)) + \
+        " bytes starting at byte " + str(self._start)
 
 
 class versioned_field(field):
@@ -94,22 +94,22 @@ class fixed_stringfield:
         self._start = start
 
     def __get__(self, obj, typ=None):
-        length = unicode_type(self._length)
+        length = str(self._length)
         return obj.unpack(start=self._start, fmt="<"+length+"s")[0]
 
     def __set__(self, obj, val):
         if not isinstance(val, string_or_bytes):
-            val = unicode_type(val)
-        if isinstance(val, unicode_type):
+            val = str(val)
+        if isinstance(val, str):
             val = val.encode('utf-8')
         if len(val) != self._length:
             raise LRFException("Trying to set fixed_stringfield with a " +
                                "string of  incorrect length")
-        obj.pack(val, start=self._start, fmt="<"+unicode_type(len(val))+"s")
+        obj.pack(val, start=self._start, fmt="<"+str(len(val))+"s")
 
     def __repr__(self):
-        return "A string of length " + unicode_type(self._length) + \
-                " starting at byte " + unicode_type(self._start)
+        return "A string of length " + str(self._length) + \
+                " starting at byte " + str(self._start)
 
 
 class xml_attr_field:
@@ -196,7 +196,7 @@ class xml_field:
 
         if not val:
             val = ''
-        if not isinstance(val, unicode_type):
+        if not isinstance(val, str):
             val = val.decode('utf-8')
 
         elems = document.getElementsByTagName(self.tag_name)
@@ -726,8 +726,8 @@ def main(args=sys.argv):
     fields = LRFMetaFile.__dict__.items()
     fields.sort()
     for f in fields:
-        if "XML" in unicode_type(f):
-            print(unicode_type(f[1]) + ":", lrf.__getattribute__(f[0]).encode('utf-8'))
+        if "XML" in str(f):
+            print(str(f[1]) + ":", lrf.__getattribute__(f[0]).encode('utf-8'))
     if options.get_thumbnail:
         print("Thumbnail:", td)
     if options.get_cover:

src/calibre/ebooks/lrf/objects.py

@@ -7,7 +7,6 @@ import struct, array, zlib, io, collections, re
 from calibre.ebooks.lrf import LRFParseError, PRS500_PROFILE
 from calibre import entity_to_unicode, prepare_string_for_xml
 from calibre.ebooks.lrf.tags import Tag
-from polyglot.builtins import unicode_type
 
 ruby_tags = {
         0xF575: ['rubyAlignAndAdjust', 'W'],
@@ -83,7 +82,7 @@ class LRFObject:
             if h[1] != '' and h[0] != '':
                 setattr(self, h[0], val)
         else:
-            raise LRFParseError("Unknown tag in %s: %s" % (self.__class__.__name__, unicode_type(tag)))
+            raise LRFParseError("Unknown tag in %s: %s" % (self.__class__.__name__, str(tag)))
 
     def __iter__(self):
         for i in range(0):
@@ -121,13 +120,13 @@ class LRFContentObject(LRFObject):
     def handle_tag(self, tag):
         if tag.id in self.tag_map:
             action = self.tag_map[tag.id]
-            if isinstance(action, unicode_type):
+            if isinstance(action, str):
                 func, args = action, ()
             else:
                 func, args = action[0], (action[1],)
             getattr(self, func)(tag, *args)
         else:
-            raise LRFParseError("Unknown tag in %s: %s" % (self.__class__.__name__, unicode_type(tag)))
+            raise LRFParseError("Unknown tag in %s: %s" % (self.__class__.__name__, str(tag)))
 
     def __iter__(self):
         for i in self._contents:
@@ -270,7 +269,7 @@ class EmptyPageElement:
             yield i
 
     def __str__(self):
-        return unicode_type(self)
+        return str(self)
 
 
 class PageDiv(EmptyPageElement):
@@ -425,7 +424,7 @@ class Page(LRFStream):
     def __str__(self):
         s = '\n<Page pagestyle="%d" objid="%d">\n'%(self.style_id, self.id)
         for i in self:
-            s += unicode_type(i)
+            s += str(i)
         s += '\n</Page>\n'
         return s
 
@@ -470,7 +469,7 @@ class BlockAttr(StyleObject, LRFObject):
             return ans
 
         if hasattr(obj, 'sidemargin'):
-            margin = unicode_type(obj.sidemargin) + 'px'
+            margin = str(obj.sidemargin) + 'px'
             ans += item('margin-left: %(m)s; margin-right: %(m)s;'%dict(m=margin))
         if hasattr(obj, 'topskip'):
             ans += item('margin-top: %dpx;'%obj.topskip)
@@ -612,7 +611,7 @@ class Block(LRFStream, TextCSS):
             s += '%s="%s" '%(attr, self.attrs[attr])
         if self.name != 'ImageBlock':
             s = s.rstrip()+'>\n'
-            s += unicode_type(self.content)
+            s += str(self.content)
             s += '</%s>\n'%(self.name,)
             return s
         return s.rstrip() + ' />\n'
@@ -710,7 +709,7 @@ class Text(LRFStream):
     lineposition_map = {1:'before', 2:'after'}
 
     def add_text(self, text):
-        s = unicode_type(text, "utf-16-le")
+        s = str(text, "utf-16-le")
         if s:
             s = s.translate(self.text_map)
             self.content.append(self.entity_pattern.sub(entity_to_unicode, s))
@@ -850,7 +849,7 @@ class Text(LRFStream):
                 self.add_text(stream.read(tag.word))
             elif tag.id in self.__class__.text_tags:  # A Text tag
                 action = self.__class__.text_tags[tag.id]
-                if isinstance(action, unicode_type):
+                if isinstance(action, str):
                     getattr(self, action)(tag, stream)
                 else:
                     getattr(self, action[0])(tag, action[1])
@@ -874,14 +873,14 @@ class Text(LRFStream):
         s = ''
         open_containers = collections.deque()
         for c in self.content:
-            if isinstance(c, unicode_type):
+            if isinstance(c, str):
                 s += prepare_string_for_xml(c).replace('\0', '')
             elif c is None:
                 if open_containers:
                     p = open_containers.pop()
                     s += '</%s>'%(p.name,)
             else:
-                s += unicode_type(c)
+                s += str(c)
                 if not c.self_closing:
                     open_containers.append(c)
 
@@ -897,7 +896,7 @@ class Text(LRFStream):
         open_containers = collections.deque()
         in_p = False
         for c in self.content:
-            if isinstance(c, unicode_type):
+            if isinstance(c, str):
                 s += c
             elif c is None:
                 p = open_containers.pop()
@@ -992,7 +991,7 @@ class Canvas(LRFStream):
             s += '%s="%s" '%(attr, self.attrs[attr])
         s = s.rstrip() + '>\n'
         for po in self:
-            s += unicode_type(po) + '\n'
+            s += str(po) + '\n'
         s += '</%s>\n'%(self.__class__.__name__,)
         return s
 
@@ -1025,7 +1024,7 @@ class ImageStream(LRFStream):
 
     def end_stream(self, *args):
         LRFStream.end_stream(self, *args)
-        self.file = unicode_type(self.id) + '.' + self.encoding.lower()
+        self.file = str(self.id) + '.' + self.encoding.lower()
         if self._document is not None:
             self._document.image_map[self.id] = self
 
@@ -1189,7 +1188,7 @@ class BookAttr(StyleObject, LRFObject):
         s += '<BookSetting bindingdirection="%s" dpi="%s" screenwidth="%s" screenheight="%s" colordepth="%s" />\n'%\
         (self.binding_map[doc.binding], doc.dpi, doc.width, doc.height, doc.color_depth)
         for font in self._document.font_map.values():
-            s += unicode_type(font)
+            s += str(font)
         s += '</BookStyle>\n'
         return s
 
@@ -1230,7 +1229,7 @@ class TOCObject(LRFStream):
     def __str__(self):
         s = '<TOC>\n'
         for i in self:
-            s += unicode_type(i)
+            s += str(i)
         return s + '</TOC>\n'
 
 

src/calibre/ebooks/lrf/pylrs/elements.py

@@ -2,7 +2,7 @@
 
 """ elements.py -- replacements and helpers for ElementTree """
 
-from polyglot.builtins import unicode_type, string_or_bytes
+from polyglot.builtins import string_or_bytes
 
 
 class ElementWriter:
@@ -25,9 +25,9 @@ class ElementWriter:
         return text
 
     def _writeAttribute(self, f, name, value):
-        f.write(' %s="' % unicode_type(name))
+        f.write(' %s="' % str(name))
         if not isinstance(value, string_or_bytes):
-            value = unicode_type(value)
+            value = str(value)
         value = self._encodeCdata(value)
         value = value.replace('"', '"')
         f.write(value)
@@ -38,7 +38,7 @@ class ElementWriter:
         f.write(text)
 
     def _write(self, f, e):
-        f.write('<' + unicode_type(e.tag))
+        f.write('<' + str(e.tag))
 
         attributes = e.items()
         attributes.sort()

src/calibre/ebooks/lrf/pylrs/pylrf.py

@@ -12,7 +12,7 @@ import codecs
 import os
 
 from .pylrfopt import tagListOptimizer
-from polyglot.builtins import iteritems, string_or_bytes, unicode_type
+from polyglot.builtins import iteritems, string_or_bytes
 
 PYLRF_VERSION = "1.0"
 
@@ -85,7 +85,7 @@ def writeWord(f, word):
     if int(word) > 65535:
         raise LrfError('Cannot encode a number greater than 65535 in a word.')
     if int(word) < 0:
-        raise LrfError('Cannot encode a number < 0 in a word: '+unicode_type(word))
+        raise LrfError('Cannot encode a number < 0 in a word: '+str(word))
     f.write(struct.pack("<H", int(word)))
 
 
@@ -511,7 +511,7 @@ class LrfObject:
             raise LrfError("object name %s not recognized" % name)
 
     def __str__(self):
-        return 'LRFObject: ' + self.name + ", " + unicode_type(self.objId)
+        return 'LRFObject: ' + self.name + ", " + str(self.objId)
 
     def appendLrfTag(self, tag):
         self.tags.append(tag)

src/calibre/ebooks/lrf/pylrs/pylrs.py

@@ -54,7 +54,7 @@ DEFAULT_GENREADING      = "fs"          # default is yes to both lrf and lrs
 
 from calibre import __appname__, __version__
 from calibre import entity_to_unicode
-from polyglot.builtins import string_or_bytes, unicode_type, iteritems, native_string_type
+from polyglot.builtins import string_or_bytes, iteritems, native_string_type
 
 
 class LrsError(Exception):
@@ -229,7 +229,7 @@ class LrsAttributes:
                 raise LrsError("%s does not support setting %s" %
                         (self.__class__.__name__, name))
             if isinstance(value, int):
-                value = unicode_type(value)
+                value = str(value)
             self.attrs[name] = value
 
 
@@ -333,13 +333,13 @@ class LrsObject:
     def lrsObjectElement(self, name, objlabel="objlabel", labelName=None,
             labelDecorate=True, **settings):
         element = Element(name)
-        element.attrib["objid"] = unicode_type(self.objId)
+        element.attrib["objid"] = str(self.objId)
         if labelName is None:
             labelName = name
         if labelDecorate:
             label = "%s.%d" % (labelName, self.objId)
         else:
-            label = unicode_type(self.objId)
+            label = str(self.objId)
         element.attrib[objlabel] = label
         element.attrib.update(settings)
         return element
@@ -565,7 +565,7 @@ class Book(Delegator):
         factor = base_font_size / old_base_font_size
 
         def rescale(old):
-            return unicode_type(int(int(old) * factor))
+            return str(int(int(old) * factor))
 
         text_blocks = list(main.get_all(lambda x: isinstance(x, TextBlock)))
         for tb in text_blocks:
@@ -696,7 +696,7 @@ class TableOfContents:
     def addTocEntry(self, tocLabel, textBlock):
         if not isinstance(textBlock, (Canvas, TextBlock, ImageBlock, RuledLine)):
             raise LrsError("TOC destination must be a Canvas, TextBlock, ImageBlock or RuledLine"+
-                            " not a " + unicode_type(type(textBlock)))
+                            " not a " + str(type(textBlock)))
 
         if textBlock.parent is None:
             raise LrsError("TOC text block must be already appended to a page")
@@ -746,8 +746,8 @@ class TocLabel:
 
     def toElement(self, se):
         return ElementWithText("TocLabel", self.label,
-                 refobj=unicode_type(self.textBlock.objId),
-                 refpage=unicode_type(self.textBlock.parent.objId))
+                 refobj=str(self.textBlock.objId),
+                 refpage=str(self.textBlock.parent.objId))
 
 
 class BookInfo:
@@ -808,7 +808,7 @@ class DocInfo:
         self.thumbnail = None
         self.language = "en"
         self.creator  = None
-        self.creationdate = unicode_type(isoformat(date.today()))
+        self.creationdate = str(isoformat(date.today()))
         self.producer = "%s v%s"%(__appname__, __version__)
         self.numberofpages = "0"
 
@@ -832,7 +832,7 @@ class DocInfo:
         docInfo.append(ElementWithText("Creator", self.creator))
         docInfo.append(ElementWithText("CreationDate", self.creationdate))
         docInfo.append(ElementWithText("Producer", self.producer))
-        docInfo.append(ElementWithText("SumPage", unicode_type(self.numberofpages)))
+        docInfo.append(ElementWithText("SumPage", str(self.numberofpages)))
         return docInfo
 
 
@@ -1094,7 +1094,7 @@ class LrsStyle(LrsObject, LrsAttributes, LrsContainer):
         self.elementName = elementName
         self.objectsAppended = False
         # self.label = "%s.%d" % (elementName, self.objId)
-        # self.label = unicode_type(self.objId)
+        # self.label = str(self.objId)
         # self.parent = None
 
     def update(self, settings):
@@ -1104,11 +1104,11 @@ class LrsStyle(LrsObject, LrsAttributes, LrsContainer):
             self.attrs[name] = value
 
     def getLabel(self):
-        return unicode_type(self.objId)
+        return str(self.objId)
 
     def toElement(self, se):
         element = Element(self.elementName, stylelabel=self.getLabel(),
-                objid=unicode_type(self.objId))
+                objid=str(self.objId))
         element.attrib.update(self.attrs)
         return element
 
@@ -1236,14 +1236,14 @@ class PageStyle(LrsStyle):
             del settings[evenbase]
             if evenObj.parent is None:
                 parent.append(evenObj)
-            settings[evenbase + "id"] = unicode_type(evenObj.objId)
+            settings[evenbase + "id"] = str(evenObj.objId)
 
         if oddbase in settings:
             oddObj = settings[oddbase]
             del settings[oddbase]
             if oddObj.parent is None:
                 parent.append(oddObj)
-            settings[oddbase + "id"] = unicode_type(oddObj.objId)
+            settings[oddbase + "id"] = str(oddObj.objId)
 
     def appendReferencedObjects(self, parent):
         if self.objectsAppended:
@@ -1486,7 +1486,7 @@ class Paragraph(LrsContainer):
 
     def __init__(self, text=None):
         LrsContainer.__init__(self, [Text, CR, DropCaps, CharButton,
-                                     LrsSimpleChar1, bytes, unicode_type])
+                                     LrsSimpleChar1, bytes, str])
         if text is not None:
             if isinstance(text, string_or_bytes):
                 text = Text(text)
@@ -1521,7 +1521,7 @@ class Paragraph(LrsContainer):
 class LrsTextTag(LrsContainer):
 
     def __init__(self, text, validContents):
-        LrsContainer.__init__(self, [Text, bytes, unicode_type] + validContents)
+        LrsContainer.__init__(self, [Text, bytes, str] + validContents)
         if text is not None:
             self.append(text)
 
@@ -1580,7 +1580,7 @@ class DropCaps(LrsTextTag):
         return self.text is None or not self.text.strip()
 
     def toElement(self, se):
-        elem =  Element('DrawChar', line=unicode_type(self.line))
+        elem =  Element('DrawChar', line=str(self.line))
         appendTextElements(elem, self.contents, se)
         return elem
 
@@ -1656,7 +1656,7 @@ class JumpTo(LrsContainer):
         self.textBlock = textBlock
 
     def toElement(self, se):
-        return Element("JumpTo", refpage=unicode_type(self.textBlock.parent.objId), refobj=unicode_type(self.textBlock.objId))
+        return Element("JumpTo", refpage=str(self.textBlock.parent.objId), refobj=str(self.textBlock.objId))
 
 
 class Plot(LrsSimpleChar1, LrsContainer):
@@ -1688,8 +1688,8 @@ class Plot(LrsSimpleChar1, LrsContainer):
             parent.append(self.obj)
 
     def toElement(self, se):
-        elem =  Element('Plot', xsize=unicode_type(self.xsize), ysize=unicode_type(self.ysize),
-                                refobj=unicode_type(self.obj.objId))
+        elem =  Element('Plot', xsize=str(self.xsize), ysize=str(self.ysize),
+                                refobj=str(self.obj.objId))
         if self.adjustment:
             elem.set('adjustment', self.adjustment)
         return elem
@@ -1771,7 +1771,7 @@ class Space(LrsSimpleChar1, LrsContainer):
         if self.xsize == 0:
             return
 
-        return Element("Space", xsize=unicode_type(self.xsize))
+        return Element("Space", xsize=str(self.xsize))
 
     def toLrfContainer(self, lrfWriter, container):
         if self.xsize != 0:
@@ -1785,7 +1785,7 @@ class Box(LrsSimpleChar1, LrsContainer):
     """
 
     def __init__(self, linetype="solid"):
-        LrsContainer.__init__(self, [Text, bytes, unicode_type])
+        LrsContainer.__init__(self, [Text, bytes, str])
         if linetype not in LINE_TYPE_ENCODING:
             raise LrsError(linetype + " is not a valid line type")
         self.linetype = linetype
@@ -1805,7 +1805,7 @@ class Box(LrsSimpleChar1, LrsContainer):
 class Span(LrsSimpleChar1, LrsContainer):
 
     def __init__(self, text=None, **attrs):
-        LrsContainer.__init__(self, [LrsSimpleChar1, Text, bytes, unicode_type])
+        LrsContainer.__init__(self, [LrsSimpleChar1, Text, bytes, str])
         if text is not None:
             if isinstance(text, string_or_bytes):
                 text = Text(text)
@@ -1858,7 +1858,7 @@ class Span(LrsSimpleChar1, LrsContainer):
     def toElement(self, se):
         element = Element('Span')
         for (key, value) in self.attrs.items():
-            element.set(key, unicode_type(value))
+            element.set(key, str(value))
 
         appendTextElements(element, self.contents, se)
         return element
@@ -1871,9 +1871,9 @@ class EmpLine(LrsTextTag, LrsSimpleChar1):
     def __init__(self, text=None, emplineposition='before', emplinetype='solid'):
         LrsTextTag.__init__(self, text, [LrsSimpleChar1])
         if emplineposition not in self.__class__.emplinepositions:
-            raise LrsError('emplineposition for an EmpLine must be one of: '+unicode_type(self.__class__.emplinepositions))
+            raise LrsError('emplineposition for an EmpLine must be one of: '+str(self.__class__.emplinepositions))
         if emplinetype not in self.__class__.emplinetypes:
-            raise LrsError('emplinetype for an EmpLine must be one of: '+unicode_type(self.__class__.emplinetypes))
+            raise LrsError('emplinetype for an EmpLine must be one of: '+str(self.__class__.emplinetypes))
 
         self.emplinetype     = emplinetype
         self.emplineposition = emplineposition
@@ -1933,9 +1933,9 @@ class BlockSpace(LrsContainer):
         element = Element("BlockSpace")
 
         if self.xspace != 0:
-            element.attrib["xspace"] = unicode_type(self.xspace)
+            element.attrib["xspace"] = str(self.xspace)
         if self.yspace != 0:
-            element.attrib["yspace"] = unicode_type(self.yspace)
+            element.attrib["yspace"] = str(self.yspace)
 
         return element
 
@@ -1949,7 +1949,7 @@ class CharButton(LrsSimpleChar1, LrsContainer):
     """
 
     def __init__(self, button, text=None):
-        LrsContainer.__init__(self, [bytes, unicode_type, Text, LrsSimpleChar1])
+        LrsContainer.__init__(self, [bytes, str, Text, LrsSimpleChar1])
         self.button = None
         if button is not None:
             self.setButton(button)
@@ -1979,7 +1979,7 @@ class CharButton(LrsSimpleChar1, LrsContainer):
         container.appendLrfTag(LrfTag("CharButtonEnd"))
 
     def toElement(self, se):
-        cb = Element("CharButton", refobj=unicode_type(self.button.objId))
+        cb = Element("CharButton", refobj=str(self.button.objId))
         appendTextElements(cb, self.contents, se)
         return cb
 
@@ -2081,8 +2081,8 @@ class JumpButton(LrsObject, LrsContainer):
         b = self.lrsObjectElement("Button")
         pb = SubElement(b, "PushButton")
         SubElement(pb, "JumpTo",
-            refpage=unicode_type(self.textBlock.parent.objId),
-            refobj=unicode_type(self.textBlock.objId))
+            refpage=str(self.textBlock.parent.objId),
+            refobj=str(self.textBlock.objId))
         return b
 
 
@@ -2230,8 +2230,8 @@ class PutObj(LrsContainer):
             self.content.objId)))
 
     def toElement(self, se):
-        el = Element("PutObj", x1=unicode_type(self.x1), y1=unicode_type(self.y1),
-                    refobj=unicode_type(self.content.objId))
+        el = Element("PutObj", x1=str(self.x1), y1=str(self.y1),
+                    refobj=str(self.content.objId))
         return el
 
 
@@ -2313,9 +2313,9 @@ class Image(LrsObject, LrsContainer, LrsAttributes):
 
     def toElement(self, se):
         element = self.lrsObjectElement("Image", **self.attrs)
-        element.set("refstream", unicode_type(self.refstream.objId))
+        element.set("refstream", str(self.refstream.objId))
         for name in ["x0", "y0", "x1", "y1", "xsize", "ysize"]:
-            element.set(name, unicode_type(getattr(self, name)))
+            element.set(name, str(getattr(self, name)))
         return element
 
     def toLrf(self, lrfWriter):
@@ -2396,9 +2396,9 @@ class ImageBlock(LrsObject, LrsContainer, LrsAttributes):
 
     def toElement(self, se):
         element = self.lrsObjectElement("ImageBlock", **self.attrs)
-        element.set("refstream", unicode_type(self.refstream.objId))
+        element.set("refstream", str(self.refstream.objId))
         for name in ["x0", "y0", "x1", "y1", "xsize", "ysize"]:
-            element.set(name, unicode_type(getattr(self, name)))
+            element.set(name, str(getattr(self, name)))
         element.text = self.alttext
         return element
 

src/calibre/ebooks/lrf/tags.py

@@ -7,7 +7,6 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 import struct
 
 from calibre.ebooks.lrf import LRFParseError
-from polyglot.builtins import unicode_type
 
 
 class Tag:
@@ -198,7 +197,7 @@ class Tag:
         self.id = 0xF500 + tag_id[0]
 
         size, self.name = self.__class__.tags[tag_id[0]]
-        if isinstance(size, unicode_type):
+        if isinstance(size, str):
             parser = getattr(self, size + '_parser')
             self.contents = parser(stream)
         else:
@@ -241,7 +240,7 @@ class Tag:
     @classmethod
     def string_parser(self, stream):
         size = struct.unpack("<H", stream.read(2))[0]
-        return unicode_type(stream.read(size), "utf_16")
+        return str(stream.read(size), "utf_16")
 
     def type_one_parser(self, stream):
         cnt = struct.unpack("<H", stream.read(2))[0]

src/calibre/ebooks/metadata/__init__.py

@@ -14,7 +14,7 @@ from contextlib import suppress
 
 from calibre import relpath, guess_type, prints, force_unicode
 from calibre.utils.config_base import tweaks
-from polyglot.builtins import codepoint_to_chr, unicode_type, iteritems, as_unicode
+from polyglot.builtins import codepoint_to_chr, iteritems, as_unicode
 from polyglot.urllib import quote, unquote, urlparse
 
 
@@ -207,7 +207,7 @@ coding = list(zip(
 
 def roman(num):
     if num <= 0 or num >= 4000 or int(num) != num:
-        return unicode_type(num)
+        return str(num)
     result = []
     for d, r in coding:
         while num >= d:
@@ -222,7 +222,7 @@ def fmt_sidx(i, fmt='%.2f', use_roman=False):
     try:
         i = float(i)
     except Exception:
-        return unicode_type(i)
+        return str(i)
     if int(i) == float(i):
         return roman(int(i)) if use_roman else '%d'%int(i)
     return fmt%i
@@ -266,7 +266,7 @@ class Resource:
                 self._href = href_or_path
             else:
                 pc = url[2]
-                if isinstance(pc, unicode_type):
+                if isinstance(pc, str):
                     pc = pc.encode('utf-8')
                 pc = unquote(pc).decode('utf-8')
                 self.path = os.path.abspath(os.path.join(basedir, pc.replace('/', os.sep)))
@@ -287,7 +287,7 @@ class Resource:
                 basedir = os.getcwd()
         if self.path is None:
             return self._href
-        f = self.fragment.encode('utf-8') if isinstance(self.fragment, unicode_type) else self.fragment
+        f = self.fragment.encode('utf-8') if isinstance(self.fragment, str) else self.fragment
         frag = '#'+as_unicode(quote(f)) if self.fragment else ''
         if self.path == basedir:
             return ''+frag
@@ -295,7 +295,7 @@ class Resource:
             rpath = relpath(self.path, basedir)
         except OSError:  # On windows path and basedir could be on different drives
             rpath = self.path
-        if isinstance(rpath, unicode_type):
+        if isinstance(rpath, str):
             rpath = rpath.encode('utf-8')
         return as_unicode(quote(rpath.replace(os.sep, '/')))+frag
 
@@ -332,7 +332,7 @@ class ResourceCollection:
         return '[%s]'%', '.join(resources)
 
     def __repr__(self):
-        return unicode_type(self)
+        return str(self)
 
     def append(self, resource):
         if not isinstance(resource, Resource):

src/calibre/ebooks/metadata/archive.py

@@ -11,7 +11,6 @@ from contextlib import closing
 
 from calibre.customize import FileTypePlugin
 from calibre.utils.localization import canonicalize_lang
-from polyglot.builtins import unicode_type
 
 
 def is_comic(list_of_names):
@@ -170,7 +169,7 @@ def get_comic_book_info(d, mi, series_index='volume'):
         from datetime import date
         try:
             dt = date(puby, 6 if pubm is None else pubm, 15)
-            dt = parse_only_date(unicode_type(dt))
+            dt = parse_only_date(str(dt))
             mi.pubdate = dt
         except Exception:
             pass