gh-102507 Remove invisible pagebreak characters (#102531)

Co-authored-by: AlexWaygood <alex.waygood@gmail.com>
This commit is contained in:
JosephSBoyle 2023-03-08 13:58:14 +00:00 committed by GitHub
parent 401d7a7f00
commit b097925858
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
16 changed files with 6 additions and 45 deletions

View File

@ -25,7 +25,6 @@ __all__ = [
]
# Some convenience routines. Don't import Parser and Message as side-effects
# of importing email since those cascadingly import most of the rest of the
# email package.

View File

@ -45,7 +45,6 @@ EMPTYSTRING = ''
MISC_LEN = 7
# Helpers
def header_length(bytearray):
"""Return the length of s when it is encoded with base64."""
@ -57,7 +56,6 @@ def header_length(bytearray):
return n
def header_encode(header_bytes, charset='iso-8859-1'):
"""Encode a single header line with Base64 encoding in a given charset.
@ -72,7 +70,6 @@ def header_encode(header_bytes, charset='iso-8859-1'):
return '=?%s?b?%s?=' % (charset, encoded)
def body_encode(s, maxlinelen=76, eol=NL):
r"""Encode a string with base64.
@ -98,7 +95,6 @@ def body_encode(s, maxlinelen=76, eol=NL):
return EMPTYSTRING.join(encvec)
def decode(string):
"""Decode a raw base64 string, returning a bytes object.

View File

@ -18,7 +18,6 @@ from email import errors
from email.encoders import encode_7or8bit
# Flags for types of header encodings
QP = 1 # Quoted-Printable
BASE64 = 2 # Base64
@ -32,7 +31,6 @@ UNKNOWN8BIT = 'unknown-8bit'
EMPTYSTRING = ''
# Defaults
CHARSETS = {
# input header enc body enc output conv
@ -104,7 +102,6 @@ CODEC_MAP = {
}
# Convenience functions for extending the above mappings
def add_charset(charset, header_enc=None, body_enc=None, output_charset=None):
"""Add character set properties to the global registry.
@ -153,7 +150,6 @@ def add_codec(charset, codecname):
CODEC_MAP[charset] = codecname
# Convenience function for encoding strings, taking into account
# that they might be unknown-8bit (ie: have surrogate-escaped bytes)
def _encode(string, codec):
@ -163,7 +159,6 @@ def _encode(string, codec):
return string.encode(codec)
class Charset:
"""Map character sets to their email properties.

View File

@ -16,7 +16,6 @@ from base64 import encodebytes as _bencode
from quopri import encodestring as _encodestring
def _qencode(s):
enc = _encodestring(s, quotetabs=True)
# Must encode spaces, which quopri.encodestring() doesn't do
@ -34,7 +33,6 @@ def encode_base64(msg):
msg['Content-Transfer-Encoding'] = 'base64'
def encode_quopri(msg):
"""Encode the message's payload in quoted-printable.
@ -46,7 +44,6 @@ def encode_quopri(msg):
msg['Content-Transfer-Encoding'] = 'quoted-printable'
def encode_7or8bit(msg):
"""Set the Content-Transfer-Encoding header to 7bit or 8bit."""
orig = msg.get_payload(decode=True)
@ -64,6 +61,5 @@ def encode_7or8bit(msg):
msg['Content-Transfer-Encoding'] = '7bit'
def encode_noop(msg):
"""Do nothing."""

View File

@ -41,7 +41,6 @@ NL = '\n'
NeedMoreData = object()
class BufferedSubFile(object):
"""A file-ish object that can have new data loaded into it.
@ -132,7 +131,6 @@ class BufferedSubFile(object):
return line
class FeedParser:
"""A feed-style parser of email."""

View File

@ -22,7 +22,6 @@ NLCRE = re.compile(r'\r\n|\r|\n')
fcre = re.compile(r'^From ', re.MULTILINE)
class Generator:
"""Generates output from a Message object tree.
@ -392,7 +391,7 @@ class Generator:
def _compile_re(cls, s, flags):
return re.compile(s, flags)
class BytesGenerator(Generator):
"""Generates a bytes version of a Message object tree.
@ -443,7 +442,6 @@ class BytesGenerator(Generator):
return re.compile(s.encode('ascii'), flags)
_FMT = '[Non-text (%(type)s) part of message omitted, filename %(filename)s]'
class DecodedGenerator(Generator):
@ -503,7 +501,6 @@ class DecodedGenerator(Generator):
}, file=self)
# Helper used by Generator._make_boundary
_width = len(repr(sys.maxsize-1))
_fmt = '%%0%dd' % _width

View File

@ -52,12 +52,10 @@ fcre = re.compile(r'[\041-\176]+:$')
_embedded_header = re.compile(r'\n[^ \t]+:')
# Helpers
_max_append = email.quoprimime._max_append
def decode_header(header):
"""Decode a message header value without converting charset.
@ -152,7 +150,6 @@ def decode_header(header):
return collapsed
def make_header(decoded_seq, maxlinelen=None, header_name=None,
continuation_ws=' '):
"""Create a Header from a sequence of pairs as returned by decode_header()
@ -175,7 +172,6 @@ def make_header(decoded_seq, maxlinelen=None, header_name=None,
return h
class Header:
def __init__(self, s=None, charset=None,
maxlinelen=None, header_name=None,
@ -409,7 +405,6 @@ class Header:
self._chunks = chunks
class _ValueFormatter:
def __init__(self, headerlen, maxlen, continuation_ws, splitchars):
self._maxlen = maxlen

View File

@ -15,7 +15,6 @@ import sys
from io import StringIO
# This function will become a method of the Message class
def walk(self):
"""Walk over the message tree, yielding each subpart.
@ -29,7 +28,6 @@ def walk(self):
yield from subpart.walk()
# These two functions are imported into the Iterators.py interface module.
def body_line_iterator(msg, decode=False):
"""Iterate over the parts, returning string payloads line-by-line.
@ -55,7 +53,6 @@ def typed_subpart_iterator(msg, maintype='text', subtype=None):
yield subpart
def _structure(msg, fp=None, level=0, include_default=False):
"""A handy debugging aid"""
if fp is None:

View File

@ -11,7 +11,6 @@ import email.policy
from email import message
class MIMEBase(message.Message):
"""Base class for MIME specializations."""

View File

@ -10,7 +10,6 @@ from email import message
from email.mime.nonmultipart import MIMENonMultipart
class MIMEMessage(MIMENonMultipart):
"""Class representing message/* MIME documents."""

View File

@ -9,7 +9,6 @@ __all__ = ['MIMEMultipart']
from email.mime.base import MIMEBase
class MIMEMultipart(MIMEBase):
"""Base class for MIME multipart/* type messages."""

View File

@ -10,7 +10,6 @@ from email import errors
from email.mime.base import MIMEBase
class MIMENonMultipart(MIMEBase):
"""Base class for MIME non-multipart type messages."""

View File

@ -10,7 +10,6 @@ from email.charset import Charset
from email.mime.nonmultipart import MIMENonMultipart
class MIMEText(MIMENonMultipart):
"""Class for generating text/* type MIME documents."""

View File

@ -64,7 +64,6 @@ class Parser:
return self.parse(StringIO(text), headersonly=headersonly)
class HeaderParser(Parser):
def parse(self, fp, headersonly=True):
return Parser.parse(self, fp, True)
@ -72,7 +71,7 @@ class HeaderParser(Parser):
def parsestr(self, text, headersonly=True):
return Parser.parsestr(self, text, True)
class BytesParser:
def __init__(self, *args, **kw):

View File

@ -1742,7 +1742,6 @@ _bufferedreader_peek_unlocked(buffered *self)
self->pos = 0;
return PyBytes_FromStringAndSize(self->buffer, r);
}
/*
@ -2052,7 +2051,6 @@ error:
LEAVE_BUFFERED(self)
return res;
}
/*
@ -2266,7 +2264,6 @@ bufferedrwpair_closed_get(rwpair *self, void *context)
}
return PyObject_GetAttr((PyObject *) self->writer, &_Py_ID(closed));
}
/*

View File

@ -174,7 +174,6 @@ DEFAULTKEYWORDS = ', '.join(default_keywords)
EMPTYSTRING = ''
# The normal pot-file header. msgmerge and Emacs's po-mode work better if it's
# there.
pot_header = _('''\
@ -196,7 +195,7 @@ msgstr ""
''')
def usage(code, msg=''):
print(__doc__ % globals(), file=sys.stderr)
if msg:
@ -204,7 +203,6 @@ def usage(code, msg=''):
sys.exit(code)
def make_escapes(pass_nonascii):
global escapes, escape
if pass_nonascii:
@ -258,7 +256,7 @@ def normalize(s, encoding):
s = '""\n"' + lineterm.join(lines) + '"'
return s
def containsAny(str, set):
"""Check whether 'str' contains ANY of the chars in 'set'"""
return 1 in [c in str for c in set]
@ -307,7 +305,7 @@ def getFilesForName(name):
return []
class TokenEater:
def __init__(self, options):
self.__options = options
@ -515,7 +513,6 @@ class TokenEater:
print('msgstr ""\n', file=fp)
def main():
global default_keywords
try:
@ -675,7 +672,7 @@ def main():
if closep:
fp.close()
if __name__ == '__main__':
main()
# some more test strings