1
0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-04-24 07:01:30 +02:00

Move force_uniceode to utils package

This commit is contained in:
2020-11-11 19:30:50 +01:00
parent 35c34c3b45
commit 3152c52839
16 changed files with 72 additions and 60 deletions
+4 -4
View File
@@ -8,9 +8,9 @@ import re
import sys
import urllib.parse
from ebook_converter import force_unicode
from ebook_converter.utils.config_base import tweaks
from ebook_converter.polyglot.urllib import unquote
from ebook_converter.utils import encoding as uenc
try:
@@ -43,7 +43,7 @@ def remove_bracketed_text(src, brackets=None):
from collections import Counter
counts = Counter()
buf = []
src = force_unicode(src)
src = uenc.force_unicode(src)
rmap = {v: k for k, v in brackets.items()}
for char in src:
if char in brackets:
@@ -75,7 +75,7 @@ def author_to_author_sort(author, method=None):
if method == 'copy':
return author
prefixes = {force_unicode(y).lower()
prefixes = {uenc.force_unicode(y).lower()
for y in tweaks['author_name_prefixes']}
prefixes |= {y+'.' for y in prefixes}
while True:
@@ -87,7 +87,7 @@ def author_to_author_sort(author, method=None):
else:
break
suffixes = {force_unicode(y).lower()
suffixes = {uenc.force_unicode(y).lower()
for y in tweaks['author_name_suffixes']}
suffixes |= {y+'.' for y in suffixes}
+2 -2
View File
@@ -12,10 +12,10 @@ from lxml import etree
from ebook_converter.utils.date import parse_only_date
from ebook_converter.utils.img import save_cover_data_to
from ebook_converter.utils.imghdr import identify
from ebook_converter import force_unicode
from ebook_converter.ebooks.metadata import MetaInformation, check_isbn
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.polyglot.binary import as_base64_unicode
from ebook_converter.utils import encoding as uenc
NAMESPACES = {'fb2': 'http://www.gribuser.ru/xml/fictionbook/2.0',
@@ -110,7 +110,7 @@ def get_metadata(stream):
if book_title:
book_title = str(book_title)
else:
book_title = force_unicode(os.path.splitext(
book_title = uenc.force_unicode(os.path.splitext(
os.path.basename(getattr(stream, 'name', 'Unknown')))[0])
mi = MetaInformation(book_title, authors)
+2 -2
View File
@@ -4,8 +4,8 @@ Edit metadata in RTF files.
import codecs
import re
from ebook_converter import force_unicode
from ebook_converter.ebooks.metadata import MetaInformation
from ebook_converter.utils import encoding as uenc
title_pat = re.compile(br'\{\\info.*?\{\\title(.*?)(?<!\\)\}', re.DOTALL)
author_pat = re.compile(br'\{\\info.*?\{\\author(.*?)(?<!\\)\}', re.DOTALL)
@@ -74,7 +74,7 @@ def detect_codepage(stream):
def encode(unistr):
if not isinstance(unistr, str):
unistr = force_unicode(unistr)
unistr = uenc.force_unicode(unistr)
return ''.join(c if ord(c) < 128 else
'\\u{}?'.format(ord(c)) for c in unistr)