Removed polyglot codepoint_to_chr

ebook_converter/__init__.py

@@ -14,7 +14,7 @@ import urllib.parse
 import urllib.request
 import warnings
 
-from ebook_converter.polyglot.builtins import codepoint_to_chr, hasenv, native_string_type
+from ebook_converter.polyglot.builtins import hasenv, native_string_type
 from functools import partial
 
 if not hasenv('CALIBRE_SHOW_DEPRECATION_WARNINGS'):
@@ -115,7 +115,7 @@ def confirm_config_name(name):
 
 
 _filename_sanitize_unicode = frozenset(('\\', '|', '?', '*', '<',        # no2to3
-    '"', ':', '>', '+', '/') + tuple(map(codepoint_to_chr, range(32))))  # no2to3
+    '"', ':', '>', '+', '/') + tuple(map(chr, range(32))))  # no2to3
 
 
 def sanitize_file_name(name, substitute='_'):

ebook_converter/css_selectors/parser.py

@@ -15,7 +15,6 @@ import operator
 import string
 
 from ebook_converter.css_selectors.errors import SelectorSyntaxError, ExpressionError
-from ebook_converter.polyglot.builtins import codepoint_to_chr
 
 
 utab = {c:c+32 for c in range(ord(u'A'), ord(u'Z')+1)}
@@ -665,7 +664,7 @@ def _replace_unicode(match):
     codepoint = int(match.group(1), 16)
     if codepoint > sys.maxunicode:
         codepoint = 0xFFFD
-    return codepoint_to_chr(codepoint)
+    return chr(codepoint)
 
 
 def unescape_ident(value):

ebook_converter/ebooks/docx/fonts.py

@@ -6,7 +6,7 @@ from ebook_converter.utils.filenames import ascii_filename
 from ebook_converter.utils.fonts.scanner import font_scanner, NoFonts
 from ebook_converter.utils.fonts.utils import panose_to_css_generic_family, is_truetype_font
 from ebook_converter.utils.icu import ord_string
-from ebook_converter.polyglot.builtins import codepoint_to_chr, iteritems
+from ebook_converter.polyglot.builtins import iteritems
 
 
 __license__ = 'GPL v3'
@@ -121,7 +121,7 @@ def do_map(m, points):
         if base < p < limit:
             yield m[p - base]
         else:
-            yield codepoint_to_chr(p)
+            yield chr(p)
 
 
 def map_symbol_text(text, font):

ebook_converter/ebooks/metadata/__init__.py

@@ -9,7 +9,7 @@ import urllib.parse
 
 from ebook_converter import relpath, guess_type, prints, force_unicode
 from ebook_converter.utils.config_base import tweaks
-from ebook_converter.polyglot.builtins import codepoint_to_chr, getcwd, iteritems, itervalues, as_unicode
+from ebook_converter.polyglot.builtins import getcwd, iteritems, itervalues, as_unicode
 from ebook_converter.polyglot.urllib import unquote
 
 
@@ -157,7 +157,7 @@ def get_title_sort_pat(lang=None):
     return ans
 
 
-_ignore_starts = '\'"'+''.join(codepoint_to_chr(x) for x in
+_ignore_starts = '\'"'+''.join(chr(x) for x in
         list(range(0x2018, 0x201e))+[0x2032, 0x2033])
 
 

ebook_converter/ebooks/metadata/rtf.py

@@ -6,7 +6,7 @@ import re
 
 from ebook_converter import force_unicode
 from ebook_converter.ebooks.metadata import MetaInformation
-from ebook_converter.polyglot.builtins import codepoint_to_chr, string_or_bytes, int_to_byte
+from ebook_converter.polyglot.builtins import string_or_bytes, int_to_byte
 
 title_pat    = re.compile(br'\{\\info.*?\{\\title(.*?)(?<!\\)\}', re.DOTALL)
 author_pat   = re.compile(br'\{\\info.*?\{\\author(.*?)(?<!\\)\}', re.DOTALL)
@@ -90,7 +90,7 @@ def decode(raw, codec):
 
     def uni(match):
         try:
-            return codepoint_to_chr(int(match.group(1)))
+            return chr(int(match.group(1)))
         except Exception:
             return '?'
 

ebook_converter/ebooks/oeb/base.py

@@ -17,7 +17,7 @@ from ebook_converter import (isbytestring, as_unicode, get_types_map)
 from ebook_converter.ebooks.oeb.parse_utils import barename, XHTML_NS, namespace, XHTML, parse_html, NotHTML
 from ebook_converter.utils.cleantext import clean_xml_chars
 from ebook_converter.utils.short_uuid import uuid4
-from ebook_converter.polyglot.builtins import iteritems, string_or_bytes, itervalues, codepoint_to_chr
+from ebook_converter.polyglot.builtins import iteritems, string_or_bytes, itervalues
 from ebook_converter.polyglot.urllib import unquote as urlunquote
 
 
@@ -431,7 +431,7 @@ def serialize(data, media_type, pretty_print=False):
     return bytes(data)
 
 
-ASCII_CHARS   = frozenset(codepoint_to_chr(x) for x in range(128))
+ASCII_CHARS   = frozenset(chr(x) for x in range(128))
 UNIBYTE_CHARS = frozenset(x.encode('ascii') for x in ASCII_CHARS)
 USAFE         = ('ABCDEFGHIJKLMNOPQRSTUVWXYZ'
                  'abcdefghijklmnopqrstuvwxyz'

ebook_converter/ebooks/pdb/plucker/reader.py

@@ -9,7 +9,6 @@ from ebook_converter.ebooks.pdb.formatreader import FormatReader
 from ebook_converter.ebooks.compression.palmdoc import decompress_doc
 from ebook_converter.utils.imghdr import identify
 from ebook_converter.utils.img import save_cover_data_to, Canvas, image_from_data
-from ebook_converter.polyglot.builtins import codepoint_to_chr
 
 
 __license__ = 'GPL v3'
@@ -714,7 +713,7 @@ class Reader(FormatReader):
             elif c == 0xa0:
                 html += ' '
             else:
-                html += codepoint_to_chr(c)
+                html += chr(c)
             offset += 1
             if offset in paragraph_offsets:
                 need_set_p_id = True

ebook_converter/ebooks/pdf/render/common.py

@@ -4,7 +4,7 @@ from datetime import datetime
 
 from ebook_converter.constants import ispy3
 from ebook_converter.utils.logging import default_log
-from ebook_converter.polyglot.builtins import iteritems, codepoint_to_chr
+from ebook_converter.polyglot.builtins import iteritems
 from ebook_converter.polyglot.binary import as_hex_bytes
 
 
@@ -89,7 +89,7 @@ class Name(str):
         raw = bytearray(raw)
         sharp = ord(b'#')
         buf = (
-            codepoint_to_chr(x).encode('ascii') if 33 < x < 126 and x != sharp else
+            chr(x).encode('ascii') if 33 < x < 126 and x != sharp else
             '#{:x}'.format(x).encode('ascii') for x in raw)
         stream.write(b'/'+b''.join(buf))
 

ebook_converter/ebooks/rtf2xml/tokenize.py

@@ -15,7 +15,6 @@ import os, re
 from ebook_converter.ebooks.rtf2xml import copy
 from ebook_converter.utils.mreplace import MReplace
 from ebook_converter.ptempfile import better_mktemp
-from ebook_converter.polyglot.builtins import codepoint_to_chr
 from . import open_for_read, open_for_write
 
 
@@ -95,7 +94,7 @@ class Tokenize:
             uni_len = len(match_obj.group(0))
             if uni_char < 0:
                 uni_char += 65536
-            uni_char = codepoint_to_chr(uni_char).encode('ascii', 'xmlcharrefreplace').decode('ascii')
+            uni_char = chr(uni_char).encode('ascii', 'xmlcharrefreplace').decode('ascii')
             self.__uc_char = self.__uc_value[-1]
             # there is only an unicode char
             if len(token)<= uni_len:

ebook_converter/polyglot/builtins.py

@@ -45,7 +45,6 @@ def reraise(tp, value, tb=None):
         tb = None
 
 
-codepoint_to_chr = chr
 string_or_bytes = str, bytes
 string_or_unicode = str
 long_type = int

ebook_converter/utils/cleantext.py

@@ -1,7 +1,6 @@
 import re
 import html.entities
 
-from ebook_converter.polyglot.builtins import codepoint_to_chr
 from ebook_converter.constants import plugins, preferred_encoding
 
 
@@ -11,7 +10,7 @@ def ascii_pat(for_binary=False):
     if ans is None:
         chars = set(range(32)) - {9, 10, 13}
         chars.add(127)
-        pat = '|'.join(map(codepoint_to_chr, chars))
+        pat = '|'.join(map(chr, chars))
         if for_binary:
             pat = pat.encode('ascii')
         ans = re.compile(pat)
@@ -32,7 +31,7 @@ def clean_ascii_chars(txt, charlist=None):
     if charlist is None:
         pat = ascii_pat(is_binary)
     else:
-        pat = '|'.join(map(codepoint_to_chr, charlist))
+        pat = '|'.join(map(chr, charlist))
         if is_binary:
             pat = pat.encode('utf-8')
     return pat.sub(empty, txt)
@@ -69,15 +68,15 @@ def unescape(text, rm=False, rchar=''):
             # character reference
             try:
                 if text[:3] == "&#x":
-                    return codepoint_to_chr(int(text[3:-1], 16))
+                    return chr(int(text[3:-1], 16))
                 else:
-                    return codepoint_to_chr(int(text[2:-1]))
+                    return chr(int(text[2:-1]))
             except ValueError:
                 pass
         else:
             # named entity
             try:
-                text = codepoint_to_chr(html.entities
+                text = chr(html.entities
                                         .name2codepoint[text[1:-1]])
             except KeyError:
                 pass