@rowstile/cli-win32-x64 0.1.0-alpha.2

package/python/Lib/email/policy.py

@@ -0,0 +1,232 @@
+"""This will be the home for the policy that hooks in the new
+code that adds all the email6 features.
+"""
+
+import re
+import sys
+from email._policybase import Policy, Compat32, compat32, _extend_docstrings
+from email.utils import _has_surrogates
+from email.headerregistry import HeaderRegistry as HeaderRegistry
+from email.contentmanager import raw_data_manager
+from email.message import EmailMessage
+
+__all__ = [
+    'Compat32',
+    'compat32',
+    'Policy',
+    'EmailPolicy',
+    'default',
+    'strict',
+    'SMTP',
+    'HTTP',
+    ]
+
+linesep_splitter = re.compile(r'\n|\r\n?')
+
+@_extend_docstrings
+class EmailPolicy(Policy):
+
+    """+
+    PROVISIONAL
+
+    The API extensions enabled by this policy are currently provisional.
+    Refer to the documentation for details.
+
+    This policy adds new header parsing and folding algorithms.  Instead of
+    simple strings, headers are custom objects with custom attributes
+    depending on the type of the field.  The folding algorithm fully
+    implements RFCs 2047 and 5322.
+
+    In addition to the settable attributes listed above that apply to
+    all Policies, this policy adds the following additional attributes:
+
+    utf8                -- if False (the default) message headers will be
+                           serialized as ASCII, using encoded words to encode
+                           any non-ASCII characters in the source strings.  If
+                           True, the message headers will be serialized using
+                           utf8 and will not contain encoded words (see RFC
+                           6532 for more on this serialization format).
+
+    refold_source       -- if the value for a header in the Message object
+                           came from the parsing of some source, this attribute
+                           indicates whether or not a generator should refold
+                           that value when transforming the message back into
+                           stream form.  The possible values are:
+
+                           none  -- all source values use original folding
+                           long  -- source values that have any line that is
+                                    longer than max_line_length will be
+                                    refolded
+                           all  -- all values are refolded.
+
+                           The default is 'long'.
+
+    header_factory      -- a callable that takes two arguments, 'name' and
+                           'value', where 'name' is a header field name and
+                           'value' is an unfolded header field value, and
+                           returns a string-like object that represents that
+                           header.  A default header_factory is provided that
+                           understands some of the RFC5322 header field types.
+                           (Currently address fields and date fields have
+                           special treatment, while all other fields are
+                           treated as unstructured.  This list will be
+                           completed before the extension is marked stable.)
+
+    content_manager     -- an object with at least two methods: get_content
+                           and set_content.  When the get_content or
+                           set_content method of a Message object is called,
+                           it calls the corresponding method of this object,
+                           passing it the message object as its first argument,
+                           and any arguments or keywords that were passed to
+                           it as additional arguments.  The default
+                           content_manager is
+                           :data:`~email.contentmanager.raw_data_manager`.
+
+    """
+
+    message_factory = EmailMessage
+    utf8 = False
+    refold_source = 'long'
+    header_factory = HeaderRegistry()
+    content_manager = raw_data_manager
+
+    def __init__(self, **kw):
+        # Ensure that each new instance gets a unique header factory
+        # (as opposed to clones, which share the factory).
+        if 'header_factory' not in kw:
+            object.__setattr__(self, 'header_factory', HeaderRegistry())
+        super().__init__(**kw)
+
+    def header_max_count(self, name):
+        """+
+        The implementation for this class returns the max_count attribute from
+        the specialized header class that would be used to construct a header
+        of type 'name'.
+        """
+        return self.header_factory[name].max_count
+
+    # The logic of the next three methods is chosen such that it is possible to
+    # switch a Message object between a Compat32 policy and a policy derived
+    # from this class and have the results stay consistent.  This allows a
+    # Message object constructed with this policy to be passed to a library
+    # that only handles Compat32 objects, or to receive such an object and
+    # convert it to use the newer style by just changing its policy.  It is
+    # also chosen because it postpones the relatively expensive full rfc5322
+    # parse until as late as possible when parsing from source, since in many
+    # applications only a few headers will actually be inspected.
+
+    def header_source_parse(self, sourcelines):
+        """+
+        The name is parsed as everything up to the ':' and returned unmodified.
+        The value is determined by stripping leading whitespace off the
+        remainder of the first line joined with all subsequent lines, and
+        stripping any trailing carriage return or linefeed characters.  (This
+        is the same as Compat32).
+
+        """
+        name, value = sourcelines[0].split(':', 1)
+        value = ''.join((value, *sourcelines[1:])).lstrip(' \t\r\n')
+        return (name, value.rstrip('\r\n'))
+
+    def header_store_parse(self, name, value):
+        """+
+        The name is returned unchanged.  If the input value has a 'name'
+        attribute and it matches the name ignoring case, the value is returned
+        unchanged.  Otherwise the name and value are passed to header_factory
+        method, and the resulting custom header object is returned as the
+        value.  In this case a ValueError is raised if the input value contains
+        CR or LF characters.
+
+        """
+        if hasattr(value, 'name') and value.name.lower() == name.lower():
+            return (name, value)
+        if isinstance(value, str) and len(value.splitlines())>1:
+            # XXX this error message isn't quite right when we use splitlines
+            # (see issue 22233), but I'm not sure what should happen here.
+            raise ValueError("Header values may not contain linefeed "
+                             "or carriage return characters")
+        return (name, self.header_factory(name, value))
+
+    def header_fetch_parse(self, name, value):
+        """+
+        If the value has a 'name' attribute, it is returned to unmodified.
+        Otherwise the name and the value with any linesep characters removed
+        are passed to the header_factory method, and the resulting custom
+        header object is returned.  Any surrogateescaped bytes get turned
+        into the unicode unknown-character glyph.
+
+        """
+        if hasattr(value, 'name'):
+            return value
+        # We can't use splitlines here because it splits on more than \r and \n.
+        value = ''.join(linesep_splitter.split(value))
+        return self.header_factory(name, value)
+
+    def fold(self, name, value):
+        """+
+        Header folding is controlled by the refold_source policy setting.  A
+        value is considered to be a 'source value' if and only if it does not
+        have a 'name' attribute (having a 'name' attribute means it is a header
+        object of some sort).  If a source value needs to be refolded according
+        to the policy, it is converted into a custom header object by passing
+        the name and the value with any linesep characters removed to the
+        header_factory method.  Folding of a custom header object is done by
+        calling its fold method with the current policy.
+
+        Source values are split into lines using splitlines.  If the value is
+        not to be refolded, the lines are rejoined using the linesep from the
+        policy and returned.  The exception is lines containing non-ascii
+        binary data.  In that case the value is refolded regardless of the
+        refold_source setting, which causes the binary data to be CTE encoded
+        using the unknown-8bit charset.
+
+        """
+        return self._fold(name, value, refold_binary=True)
+
+    def fold_binary(self, name, value):
+        """+
+        The same as fold if cte_type is 7bit, except that the returned value is
+        bytes.
+
+        If cte_type is 8bit, non-ASCII binary data is converted back into
+        bytes.  Headers with binary data are not refolded, regardless of the
+        refold_header setting, since there is no way to know whether the binary
+        data consists of single byte characters or multibyte characters.
+
+        If utf8 is true, headers are encoded to utf8, otherwise to ascii with
+        non-ASCII unicode rendered as encoded words.
+
+        """
+        folded = self._fold(name, value, refold_binary=self.cte_type=='7bit')
+        charset = 'utf8' if self.utf8 else 'ascii'
+        return folded.encode(charset, 'surrogateescape')
+
+    def _fold(self, name, value, refold_binary=False):
+        if hasattr(value, 'name'):
+            return value.fold(policy=self)
+        maxlen = self.max_line_length if self.max_line_length else sys.maxsize
+        # We can't use splitlines here because it splits on more than \r and \n.
+        lines = linesep_splitter.split(value)
+        refold = (self.refold_source == 'all' or
+                  self.refold_source == 'long' and
+                    (lines and len(lines[0])+len(name)+2 > maxlen or
+                     any(len(x) > maxlen for x in lines[1:])))
+
+        if not refold:
+            if not self.utf8:
+                refold = not value.isascii()
+            elif refold_binary:
+                refold = _has_surrogates(value)
+        if refold:
+            return self.header_factory(name, ''.join(lines)).fold(policy=self)
+
+        return name + ': ' + self.linesep.join(lines) + self.linesep
+
+
+default = EmailPolicy()
+# Make the default policy use the class default header_factory
+del default.header_factory
+strict = default.clone(raise_on_defect=True)
+SMTP = default.clone(linesep='\r\n')
+HTTP = default.clone(linesep='\r\n', max_line_length=None)
+SMTPUTF8 = SMTP.clone(utf8=True)

package/python/Lib/email/quoprimime.py

@@ -0,0 +1,300 @@
+# Copyright (C) 2001-2006 Python Software Foundation
+# Author: Ben Gertzfield
+# Contact: email-sig@python.org
+
+"""Quoted-printable content transfer encoding per RFCs 2045-2047.
+
+This module handles the content transfer encoding method defined in RFC 2045
+to encode US ASCII-like 8-bit data called `quoted-printable'.  It is used to
+safely encode text that is in a character set similar to the 7-bit US ASCII
+character set, but that includes some 8-bit characters that are normally not
+allowed in email bodies or headers.
+
+Quoted-printable is very space-inefficient for encoding binary files; use the
+email.base64mime module for that instead.
+
+This module provides an interface to encode and decode both headers and bodies
+with quoted-printable encoding.
+
+RFC 2045 defines a method for including character set information in an
+`encoded-word' in a header.  This method is commonly used for 8-bit real names
+in To:/From:/Cc: etc. fields, as well as Subject: lines.
+
+This module does not do the line wrapping or end-of-line character
+conversion necessary for proper internationalized headers; it only
+does dumb encoding and decoding.  To deal with the various line
+wrapping issues, use the email.header module.
+"""
+
+__all__ = [
+    'body_decode',
+    'body_encode',
+    'body_length',
+    'decode',
+    'decodestring',
+    'header_decode',
+    'header_encode',
+    'header_length',
+    'quote',
+    'unquote',
+    ]
+
+import re
+
+from string import ascii_letters, digits, hexdigits
+
+CRLF = '\r\n'
+NL = '\n'
+EMPTYSTRING = ''
+
+# Build a mapping of octets to the expansion of that octet.  Since we're only
+# going to have 256 of these things, this isn't terribly inefficient
+# space-wise.  Remember that headers and bodies have different sets of safe
+# characters.  Initialize both maps with the full expansion, and then override
+# the safe bytes with the more compact form.
+_QUOPRI_MAP = ['=%02X' % c for c in range(256)]
+_QUOPRI_HEADER_MAP = _QUOPRI_MAP[:]
+_QUOPRI_BODY_MAP = _QUOPRI_MAP[:]
+
+# Safe header bytes which need no encoding.
+for c in b'-!*+/' + ascii_letters.encode('ascii') + digits.encode('ascii'):
+    _QUOPRI_HEADER_MAP[c] = chr(c)
+# Headers have one other special encoding; spaces become underscores.
+_QUOPRI_HEADER_MAP[ord(' ')] = '_'
+
+# Safe body bytes which need no encoding.
+for c in (b' !"#$%&\'()*+,-./0123456789:;<>'
+          b'?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`'
+          b'abcdefghijklmnopqrstuvwxyz{|}~\t'):
+    _QUOPRI_BODY_MAP[c] = chr(c)
+
+
+
+# Helpers
+def header_check(octet):
+    """Return True if the octet should be escaped with header quopri."""
+    return chr(octet) != _QUOPRI_HEADER_MAP[octet]
+
+
+def body_check(octet):
+    """Return True if the octet should be escaped with body quopri."""
+    return chr(octet) != _QUOPRI_BODY_MAP[octet]
+
+
+def header_length(bytearray):
+    """Return a header quoted-printable encoding length.
+
+    Note that this does not include any RFC 2047 chrome added by
+    `header_encode()`.
+
+    :param bytearray: An array of bytes (a.k.a. octets).
+    :return: The length in bytes of the byte array when it is encoded with
+        quoted-printable for headers.
+    """
+    return sum(len(_QUOPRI_HEADER_MAP[octet]) for octet in bytearray)
+
+
+def body_length(bytearray):
+    """Return a body quoted-printable encoding length.
+
+    :param bytearray: An array of bytes (a.k.a. octets).
+    :return: The length in bytes of the byte array when it is encoded with
+        quoted-printable for bodies.
+    """
+    return sum(len(_QUOPRI_BODY_MAP[octet]) for octet in bytearray)
+
+
+def _max_append(L, s, maxlen, extra=''):
+    if not isinstance(s, str):
+        s = chr(s)
+    if not L:
+        L.append(s.lstrip())
+    elif len(L[-1]) + len(s) <= maxlen:
+        L[-1] += extra + s
+    else:
+        L.append(s.lstrip())
+
+
+def unquote(s):
+    """Turn a string in the form =AB to the ASCII character with value 0xab"""
+    return chr(int(s[1:3], 16))
+
+
+def quote(c):
+    return _QUOPRI_MAP[ord(c)]
+
+
+def header_encode(header_bytes, charset='iso-8859-1'):
+    """Encode a single header line with quoted-printable (like) encoding.
+
+    Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but
+    used specifically for email header fields to allow charsets with mostly 7
+    bit characters (and some 8 bit) to remain more or less readable in non-RFC
+    2045 aware mail clients.
+
+    charset names the character set to use in the RFC 2046 header.  It
+    defaults to iso-8859-1.
+    """
+    # Return empty headers as an empty string.
+    if not header_bytes:
+        return ''
+    # Iterate over every byte, encoding if necessary.
+    encoded = header_bytes.decode('latin1').translate(_QUOPRI_HEADER_MAP)
+    # Now add the RFC chrome to each encoded chunk and glue the chunks
+    # together.
+    return '=?%s?q?%s?=' % (charset, encoded)
+
+
+_QUOPRI_BODY_ENCODE_MAP = _QUOPRI_BODY_MAP[:]
+for c in b'\r\n':
+    _QUOPRI_BODY_ENCODE_MAP[c] = chr(c)
+del c
+
+def body_encode(body, maxlinelen=76, eol=NL):
+    """Encode with quoted-printable, wrapping at maxlinelen characters.
+
+    Each line of encoded text will end with eol, which defaults to "\\n".  Set
+    this to "\\r\\n" if you will be using the result of this function directly
+    in an email.
+
+    Each line will be wrapped at, at most, maxlinelen characters before the
+    eol string (maxlinelen defaults to 76 characters, the maximum value
+    permitted by RFC 2045).  Long lines will have the 'soft line break'
+    quoted-printable character "=" appended to them, so the decoded text will
+    be identical to the original text.
+
+    The minimum maxlinelen is 4 to have room for a quoted character ("=XX")
+    followed by a soft line break.  Smaller values will generate a
+    ValueError.
+
+    """
+
+    if maxlinelen < 4:
+        raise ValueError("maxlinelen must be at least 4")
+    if not body:
+        return body
+
+    # quote special characters
+    body = body.translate(_QUOPRI_BODY_ENCODE_MAP)
+
+    soft_break = '=' + eol
+    # leave space for the '=' at the end of a line
+    maxlinelen1 = maxlinelen - 1
+
+    encoded_body = []
+    append = encoded_body.append
+
+    for line in body.splitlines():
+        # break up the line into pieces no longer than maxlinelen - 1
+        start = 0
+        laststart = len(line) - 1 - maxlinelen
+        while start <= laststart:
+            stop = start + maxlinelen1
+            # make sure we don't break up an escape sequence
+            if line[stop - 2] == '=':
+                append(line[start:stop - 1])
+                start = stop - 2
+            elif line[stop - 1] == '=':
+                append(line[start:stop])
+                start = stop - 1
+            else:
+                append(line[start:stop] + '=')
+                start = stop
+
+        # handle rest of line, special case if line ends in whitespace
+        if line and line[-1] in ' \t':
+            room = start - laststart
+            if room >= 3:
+                # It's a whitespace character at end-of-line, and we have room
+                # for the three-character quoted encoding.
+                q = quote(line[-1])
+            elif room == 2:
+                # There's room for the whitespace character and a soft break.
+                q = line[-1] + soft_break
+            else:
+                # There's room only for a soft break.  The quoted whitespace
+                # will be the only content on the subsequent line.
+                q = soft_break + quote(line[-1])
+            append(line[start:-1] + q)
+        else:
+            append(line[start:])
+
+    # add back final newline if present
+    if body[-1] in CRLF:
+        append('')
+
+    return eol.join(encoded_body)
+
+
+
+# BAW: I'm not sure if the intent was for the signature of this function to be
+# the same as base64MIME.decode() or not...
+def decode(encoded, eol=NL):
+    """Decode a quoted-printable string.
+
+    Lines are separated with eol, which defaults to \\n.
+    """
+    if not encoded:
+        return encoded
+    # BAW: see comment in encode() above.  Again, we're building up the
+    # decoded string with string concatenation, which could be done much more
+    # efficiently.
+    decoded = ''
+
+    for line in encoded.splitlines():
+        line = line.rstrip()
+        if not line:
+            decoded += eol
+            continue
+
+        i = 0
+        n = len(line)
+        while i < n:
+            c = line[i]
+            if c != '=':
+                decoded += c
+                i += 1
+            # Otherwise, c == "=".  Are we at the end of the line?  If so, add
+            # a soft line break.
+            elif i+1 == n:
+                i += 1
+                continue
+            # Decode if in form =AB
+            elif i+2 < n and line[i+1] in hexdigits and line[i+2] in hexdigits:
+                decoded += unquote(line[i:i+3])
+                i += 3
+            # Otherwise, not in form =AB, pass literally
+            else:
+                decoded += c
+                i += 1
+
+            if i == n:
+                decoded += eol
+    # Special case if original string did not end with eol
+    if encoded[-1] not in '\r\n' and decoded.endswith(eol):
+        decoded = decoded[:-len(eol)]
+    return decoded
+
+
+# For convenience and backwards compatibility w/ standard base64 module
+body_decode = decode
+decodestring = decode
+
+
+
+def _unquote_match(match):
+    """Turn a match in the form =AB to the ASCII character with value 0xab"""
+    s = match.group(0)
+    return unquote(s)
+
+
+# Header decoding is done a bit differently
+def header_decode(s):
+    """Decode a string encoded with RFC 2045 MIME header `Q' encoding.
+
+    This function does not parse a full MIME header value encoded with
+    quoted-printable (like =?iso-8859-1?q?Hello_World?=) -- please use
+    the high level email.header class for that functionality.
+    """
+    s = s.replace('_', ' ')
+    return re.sub(r'=[a-fA-F0-9]{2}', _unquote_match, s, flags=re.ASCII)