Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-11-22 06:23:02 -05:00
Code Issues Packages Projects Releases Wiki Activity

codepoint_to_chr (regex)

Browse Source 
codepoint_to_chr(
chr(
This commit is contained in:
un-pogaz 2025-11-16 18:27:08 +01:00
parent 94a51a1acc
commit 47257e1262
17 changed files with 39 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
setup/translations.py
View File

@ -23,7 +23,7 @@ from collections import defaultdict
from functools import lru_cache, partial
from locale import normalize as normalize_locale
from polyglot.builtins import codepoint_to_chr, iteritems
from polyglot.builtins import iteritems
from setup import Command, __appname__, __version__, build_cache_dir, dump_json, edit_file, is_ci, require_git_master
from setup.iso_codes import iso_data
from setup.parallel_build import batched_parallel_jobs
@ -128,7 +128,7 @@ class POT(Command): # {{{
ans = []
for lineno, msg in msgs:
ans.append(f'#: {path}:{lineno}')
slash = codepoint_to_chr(92)
slash = chr(92)
msg = msg.replace(slash, slash*2).replace('"', r'\"').replace('\n',
r'\n').replace('\r', r'\r').replace('\t', r'\t')
ans.append(f'msgid "{msg}"')

3
src/calibre/ebooks/docx/fonts.py
View File

@ -13,7 +13,6 @@ from calibre.utils.filenames import ascii_filename
from calibre.utils.fonts.scanner import NoFonts, font_scanner
from calibre.utils.fonts.utils import is_truetype_font, panose_to_css_generic_family
from calibre.utils.icu import ord_string
from polyglot.builtins import codepoint_to_chr
Embed = namedtuple('Embed', 'name key subsetted')
@ -124,7 +123,7 @@ 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):

8
src/calibre/ebooks/lit/reader.py
View File

@ -20,7 +20,7 @@ from calibre.ebooks.lit.maps import HTML_MAP, OPF_MAP
from calibre.ebooks.oeb.base import urlnormalize, xpath
from calibre.ebooks.oeb.reader import OEBReader
from calibre_extensions import lzx, msdes
from polyglot.builtins import codepoint_to_chr, itervalues, string_or_bytes
from polyglot.builtins import itervalues, string_or_bytes
from polyglot.urllib import unquote as urlunquote
from polyglot.urllib import urldefrag
@ -109,7 +109,7 @@ def read_utf8_char(bytes, pos):
raise LitError(
f'Invalid UTF8 character: {bytes[pos:pos+i]!r}')
c = (c << 6) | (b & 0x3F)
return codepoint_to_chr(c), pos+elsize
return chr(c), pos+elsize
def consume_sized_utf8_string(bytes, zpad=False):
@ -250,9 +250,9 @@ class UnBinary:
else:
dynamic_tag += 1
errors += 1
tag_name = '?'+codepoint_to_chr(tag)+'?'
tag_name = '?'+chr(tag)+'?'
current_map = self.tag_to_attr_map[tag]
print(f'WARNING: tag {codepoint_to_chr(tag)} unknown')
print(f'WARNING: tag {chr(tag)} unknown')
buf.write(encode(tag_name))
elif flags & FLAG_CLOSING:
if depth == 0:

18
src/calibre/ebooks/lit/writer.py
View File

@ -26,7 +26,7 @@ from calibre.ebooks.lit.reader import DirectoryEntry
from calibre.ebooks.oeb.base import CSS_MIME, OEB_DOCS, OEB_STYLES, OPF_MIME, XHTML_MIME, XML, XML_NS, prefixname, urlnormalize
from calibre.ebooks.oeb.stylizer import Stylizer
from calibre_extensions import msdes
from polyglot.builtins import codepoint_to_chr, native_string_type, string_or_bytes
from polyglot.builtins import native_string_type, string_or_bytes
from polyglot.urllib import unquote, urldefrag
__all__ = ['LitWriter']
@ -162,7 +162,7 @@ class ReBinary:
for value in values:
if isinstance(value, numbers.Integral):
try:
value = codepoint_to_chr(value)
value = chr(value)
except OverflowError:
self.logger.warn('Unicode overflow for integer:', value)
value = '?'
@ -215,9 +215,9 @@ class ReBinary:
path, frag = urldefrag(value)
if self.item:
path = self.item.abshref(path)
prefix = codepoint_to_chr(3)
prefix = chr(3)
if path in self.manifest.hrefs:
prefix = codepoint_to_chr(2)
prefix = chr(2)
value = self.manifest.hrefs[path].id
if frag:
value = '#'.join((value, frag))
@ -280,9 +280,9 @@ class ReBinary:
self.logger.warn(f'More than six anchors in file {self.item.href!r}. '
'Some links may not work properly.')
data = io.BytesIO()
data.write(codepoint_to_chr(len(self.anchors)).encode('utf-8'))
data.write(chr(len(self.anchors)).encode('utf-8'))
for anchor, offset in self.anchors:
data.write(codepoint_to_chr(len(anchor)).encode('utf-8'))
data.write(chr(len(anchor)).encode('utf-8'))
if isinstance(anchor, str):
anchor = anchor.encode('utf-8')
data.write(anchor)
@ -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)), str(id),
codepoint_to_chr(len(href)), str(href),
codepoint_to_chr(len(media_type)), str(media_type)]
entry = [chr(len(id)), str(id),
chr(len(href)), str(href),
chr(len(media_type)), str(media_type)]
for value in entry:
data.write(value.encode('utf-8'))
data.write(b'\0')

3
src/calibre/ebooks/metadata/kdl.py
View File

@ -14,12 +14,11 @@ from calibre import browser
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.ebooks.chardet import xml_to_unicode
from calibre.ebooks.metadata.book.base import Metadata
from polyglot.builtins import codepoint_to_chr
from polyglot.urllib import parse_qs, quote_plus
URL = 'http://ww2.kdl.org/libcat/WhatsNext.asp?AuthorLastName={0}&AuthorFirstName=&SeriesName=&BookTitle={1}&CategoryID=0&cmdSearch=Search&Search=1&grouping='
_ignore_starts = '\'"'+''.join(codepoint_to_chr(x) for x in list(range(0x2018, 0x201e))+[0x2032, 0x2033])
_ignore_starts = '\'"'+''.join(chr(x) for x in list(range(0x2018, 0x201e))+[0x2032, 0x2033])
def get_series(title, authors, timeout=60):

3
src/calibre/ebooks/metadata/mobi.py
View File

@ -14,7 +14,6 @@ from calibre.ebooks.mobi.utils import rescale_image
from calibre.utils.date import now as nowf
from calibre.utils.imghdr import what
from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
from polyglot.builtins import codepoint_to_chr
'''
Retrieve and modify in-place Mobipocket book metadata.
@ -279,7 +278,7 @@ class MetadataUpdater:
def hexdump(self, src, length=16):
# Diagnostic
FILTER=''.join([((len(repr(codepoint_to_chr(x)))==3) and codepoint_to_chr(x)) or '.' for x in range(256)])
FILTER=''.join([((len(repr(chr(x)))==3) and chr(x)) or '.' for x in range(256)])
N=0
result=''
while src:

4
src/calibre/ebooks/metadata/rtf.py
View File

@ -10,7 +10,7 @@ import re
from calibre import force_unicode
from calibre.ebooks.metadata import MetaInformation
from polyglot.builtins import codepoint_to_chr, int_to_byte, string_or_bytes
from polyglot.builtins import int_to_byte, string_or_bytes
title_pat = re.compile(br'\{\\info.*?\{\\title(.*?)(?<!\\)\}', re.DOTALL)
author_pat = re.compile(br'\{\\info.*?\{\\author(.*?)(?<!\\)\}', re.DOTALL)
@ -93,7 +93,7 @@ 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 '?'

4
src/calibre/ebooks/metadata/topaz.py
View File

@ -10,7 +10,7 @@ from struct import pack
from calibre import force_unicode
from calibre.ebooks.metadata import MetaInformation
from polyglot.builtins import codepoint_to_chr, int_to_byte
from polyglot.builtins import int_to_byte
def is_dkey(x):
@ -154,7 +154,7 @@ class MetadataUpdater:
def dump_hex(self, src, length=16):
''' Diagnostic '''
FILTER=''.join([((len(repr(codepoint_to_chr(x)))==3) and codepoint_to_chr(x)) or '.' for x in range(256)])
FILTER=''.join([((len(repr(chr(x)))==3) and chr(x)) or '.' for x in range(256)])
N=0
result=''
while src:

4
src/calibre/ebooks/oeb/base.py
View File

@ -30,7 +30,7 @@ from calibre.utils.icu import title_case as icu_title
from calibre.utils.localization import __, is_rtl_lang
from calibre.utils.short_uuid import uuid4
from calibre.utils.xml_parse import safe_xml_fromstring
from polyglot.builtins import codepoint_to_chr, iteritems, itervalues, string_or_bytes
from polyglot.builtins import iteritems, itervalues, string_or_bytes
from polyglot.urllib import unquote as urlunquote
from polyglot.urllib import urldefrag, urljoin, urlparse, urlunparse
@ -452,7 +452,7 @@ def serialize(data, media_type, pretty_print=False):
return b'' if data is None else 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'

3
src/calibre/ebooks/pdb/plucker/reader.py
View File

@ -12,7 +12,6 @@ from calibre.ebooks.compression.palmdoc import decompress_doc
from calibre.ebooks.pdb.formatreader import FormatReader
from calibre.utils.img import Canvas, image_from_data, save_cover_data_to
from calibre.utils.imghdr import identify
from polyglot.builtins import codepoint_to_chr
DATATYPE_PHTML = 0
DATATYPE_PHTML_COMPRESSED = 1
@ -700,7 +699,7 @@ class Reader(FormatReader):
elif c == 0xa0:
html += '&nbsp;'
else:
html += codepoint_to_chr(c)
html += chr(c)
offset += 1
if offset in paragraph_offsets:
need_set_p_id = True

3
src/calibre/ebooks/pdf/render/common.py
View File

@ -14,7 +14,6 @@ from io import BytesIO
from calibre.utils.logging import default_log
from calibre_extensions.speedup import pdf_float
from polyglot.binary import as_hex_bytes
from polyglot.builtins import codepoint_to_chr
EOL = b'\n'
@ -91,7 +90,7 @@ 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
f'#{x:x}'.encode('ascii') for x in raw)
stream.write(b'/'+b''.join(buf))

3
src/calibre/ebooks/pdf/render/fonts.py
View File

@ -14,7 +14,6 @@ from calibre import as_unicode
from calibre.ebooks.pdf.render.common import Array, Dictionary, Name, Stream, String
from calibre.utils.fonts.sfnt.subset import NoGlyphs, UnsupportedFont, pdf_subset
from calibre.utils.short_uuid import uuid4
from polyglot.builtins import codepoint_to_chr
STANDARD_FONTS = {
'Times-Roman', 'Helvetica', 'Courier', 'Symbol', 'Times-Bold',
@ -121,7 +120,7 @@ class Font:
self.metrics, self.compress = metrics, compress
self.is_otf = self.metrics.is_otf
self.subset_tag = str(
re.sub(r'.', lambda m: codepoint_to_chr(int(m.group())+ord('A')), oct(num).replace('o', '')
re.sub(r'.', lambda m: chr(int(m.group())+ord('A')), oct(num).replace('o', '')
)).rjust(6, 'A')
self.font_stream = FontStream(metrics.is_otf, compress=compress)
try:

3
src/calibre/ebooks/rtf2xml/tokenize.py
View File

@ -16,7 +16,6 @@ import re
from calibre.ebooks.rtf2xml import copy
from calibre.ptempfile import better_mktemp
from calibre.utils.mreplace import MReplace
from polyglot.builtins import codepoint_to_chr
from . import open_for_read, open_for_write
@ -98,7 +97,7 @@ 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:

11
src/calibre/gui2/tweak_book/char_select.py
View File

@ -43,7 +43,6 @@ from calibre.gui2.tweak_book.widgets import Dialog
from calibre.gui2.widgets import BusyCursor
from calibre.gui2.widgets2 import HistoryLineEdit2
from calibre.startup import connect_lambda
from calibre.utils.icu import safe_chr as codepoint_to_chr
from calibre.utils.unicode_names import character_name_from_code, points_for_word
from calibre_extensions.progress_indicator import set_no_activate_on_click
@ -590,7 +589,7 @@ class CharDelegate(QStyledItemDelegate):
f = option.font
f.setPixelSize(option.rect.height() - 8)
painter.setFont(f)
painter.drawText(option.rect, Qt.AlignmentFlag.AlignHCenter | Qt.AlignmentFlag.AlignBottom | Qt.TextFlag.TextSingleLine, codepoint_to_chr(charcode))
painter.drawText(option.rect, Qt.AlignmentFlag.AlignHCenter | Qt.AlignmentFlag.AlignBottom | Qt.TextFlag.TextSingleLine, chr(charcode))
def paint_non_printing(self, painter, option, charcode):
text = self.np_pat.sub(r'\n\1', non_printing[charcode])
@ -630,7 +629,7 @@ class CharView(QListView):
except (TypeError, ValueError):
pass
else:
self.char_selected.emit(codepoint_to_chr(char_code))
self.char_selected.emit(chr(char_code))
def set_allow_drag_and_drop(self, enabled):
if not enabled:
@ -681,9 +680,9 @@ class CharView(QListView):
pass
else:
m = QMenu(self)
m.addAction(QIcon.ic('edit-copy.png'), _('Copy %s to clipboard') % codepoint_to_chr(char_code), partial(self.copy_to_clipboard, char_code))
m.addAction(QIcon.ic('edit-copy.png'), _('Copy %s to clipboard') % chr(char_code), partial(self.copy_to_clipboard, char_code))
m.addAction(QIcon.ic('rating.png'),
(_('Remove %s from favorites') if self.showing_favorites else _('Add %s to favorites')) % codepoint_to_chr(char_code),
(_('Remove %s from favorites') if self.showing_favorites else _('Add %s to favorites')) % chr(char_code),
partial(self.remove_from_favorites, char_code))
if self.showing_favorites:
m.addAction(_('Restore favorites to defaults'), self.restore_defaults)
@ -697,7 +696,7 @@ class CharView(QListView):
def copy_to_clipboard(self, char_code):
c = QApplication.clipboard()
c.setText(codepoint_to_chr(char_code))
c.setText(chr(char_code))
def remove_from_favorites(self, char_code):
existing = tprefs['charmap_favorites']

4
src/calibre/gui2/tweak_book/editor/snippets.py
View File

@ -42,7 +42,7 @@ from calibre.gui2.tweak_book.widgets import Dialog, PlainTextEdit
from calibre.utils.config import JSONConfig
from calibre.utils.icu import string_length as strlen
from calibre.utils.localization import localize_user_manual_link
from polyglot.builtins import codepoint_to_chr, iteritems
from polyglot.builtins import iteritems
def string_length(x):
@ -118,7 +118,7 @@ escape = unescape = None
def escape_funcs():
global escape, unescape
if escape is None:
escapem = {('\\' + x):codepoint_to_chr(i+1) for i, x in enumerate('\\${}')}
escapem = {('\\' + x):chr(i+1) for i, x in enumerate('\\${}')}
escape_pat = re.compile('|'.join(map(re.escape, escapem)))
def escape(x):
return escape_pat.sub(lambda m: escapem[m.group()], x.replace('\\\\', '\x01'))

6
src/calibre/utils/cleantext.py
View File

@ -80,15 +80,15 @@ 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(name2codepoint[text[1:-1]])
text = chr(name2codepoint[text[1:-1]])
except KeyError:
pass
if rm:

3
src/calibre/utils/search_query_parser.py
View File

@ -26,7 +26,6 @@ from calibre.utils.icu import lower as icu_lower
from calibre.utils.icu import sort_key
from calibre.utils.localization import _
from polyglot.binary import as_hex_unicode, from_hex_unicode
from polyglot.builtins import codepoint_to_chr
'''
This class manages access to the preference holding the saved search queries.
@ -151,7 +150,7 @@ class Parser:
WORD = 2
QUOTED_WORD = 3
EOF = 4
REPLACEMENTS = tuple(('\\' + x, codepoint_to_chr(i + 1)) for i, x in enumerate('\\"()'))
REPLACEMENTS = tuple(('\\' + x, chr(i + 1)) for i, x in enumerate('\\"()'))
# the sep must be a printable character sequence that won't actually appear naturally
docstring_sep = '□ༀ؆' # Unicode white square, Tibetan Om, Arabic-Indic Cube Root