AppPkg/Applications/Python: Add Python 2.7.2 sources since the release of Python...

[mirror_edk2.git] / AppPkg / Applications / Python / Python-2.7.2 / Lib / email / quoprimime.py

# Copyright (C) 2001-2006 Python Software Foundation\r
# Author: Ben Gertzfield\r
# Contact: email-sig@python.org\r
\r
"""Quoted-printable content transfer encoding per RFCs 2045-2047.\r
\r
This module handles the content transfer encoding method defined in RFC 2045\r
to encode US ASCII-like 8-bit data called `quoted-printable'.  It is used to\r
safely encode text that is in a character set similar to the 7-bit US ASCII\r
character set, but that includes some 8-bit characters that are normally not\r
allowed in email bodies or headers.\r
\r
Quoted-printable is very space-inefficient for encoding binary files; use the\r
email.base64mime module for that instead.\r
\r
This module provides an interface to encode and decode both headers and bodies\r
with quoted-printable encoding.\r
\r
RFC 2045 defines a method for including character set information in an\r
`encoded-word' in a header.  This method is commonly used for 8-bit real names\r
in To:/From:/Cc: etc. fields, as well as Subject: lines.\r
\r
This module does not do the line wrapping or end-of-line character\r
conversion necessary for proper internationalized headers; it only\r
does dumb encoding and decoding.  To deal with the various line\r
wrapping issues, use the email.header module.\r
"""\r
\r
__all__ = [\r
    'body_decode',\r
    'body_encode',\r
    'body_quopri_check',\r
    'body_quopri_len',\r
    'decode',\r
    'decodestring',\r
    'encode',\r
    'encodestring',\r
    'header_decode',\r
    'header_encode',\r
    'header_quopri_check',\r
    'header_quopri_len',\r
    'quote',\r
    'unquote',\r
    ]\r
\r
import re\r
\r
from string import hexdigits\r
from email.utils import fix_eols\r
\r
CRLF = '\r\n'\r
NL = '\n'\r
\r
# See also Charset.py\r
MISC_LEN = 7\r
\r
hqre = re.compile(r'[^-a-zA-Z0-9!*+/ ]')\r
bqre = re.compile(r'[^ !-<>-~\t]')\r
\r
\r
\f\r
# Helpers\r
def header_quopri_check(c):\r
    """Return True if the character should be escaped with header quopri."""\r
    return bool(hqre.match(c))\r
\r
\r
def body_quopri_check(c):\r
    """Return True if the character should be escaped with body quopri."""\r
    return bool(bqre.match(c))\r
\r
\r
def header_quopri_len(s):\r
    """Return the length of str when it is encoded with header quopri."""\r
    count = 0\r
    for c in s:\r
        if hqre.match(c):\r
            count += 3\r
        else:\r
            count += 1\r
    return count\r
\r
\r
def body_quopri_len(str):\r
    """Return the length of str when it is encoded with body quopri."""\r
    count = 0\r
    for c in str:\r
        if bqre.match(c):\r
            count += 3\r
        else:\r
            count += 1\r
    return count\r
\r
\r
def _max_append(L, s, maxlen, extra=''):\r
    if not L:\r
        L.append(s.lstrip())\r
    elif len(L[-1]) + len(s) <= maxlen:\r
        L[-1] += extra + s\r
    else:\r
        L.append(s.lstrip())\r
\r
\r
def unquote(s):\r
    """Turn a string in the form =AB to the ASCII character with value 0xab"""\r
    return chr(int(s[1:3], 16))\r
\r
\r
def quote(c):\r
    return "=%02X" % ord(c)\r
\r
\r
\f\r
def header_encode(header, charset="iso-8859-1", keep_eols=False,\r
                  maxlinelen=76, eol=NL):\r
    """Encode a single header line with quoted-printable (like) encoding.\r
\r
    Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but\r
    used specifically for email header fields to allow charsets with mostly 7\r
    bit characters (and some 8 bit) to remain more or less readable in non-RFC\r
    2045 aware mail clients.\r
\r
    charset names the character set to use to encode the header.  It defaults\r
    to iso-8859-1.\r
\r
    The resulting string will be in the form:\r
\r
    "=?charset?q?I_f=E2rt_in_your_g=E8n=E8ral_dire=E7tion?\\n\r
      =?charset?q?Silly_=C8nglish_Kn=EEghts?="\r
\r
    with each line wrapped safely at, at most, maxlinelen characters (defaults\r
    to 76 characters).  If maxlinelen is None, the entire string is encoded in\r
    one chunk with no splitting.\r
\r
    End-of-line characters (\\r, \\n, \\r\\n) will be automatically converted\r
    to the canonical email line separator \\r\\n unless the keep_eols\r
    parameter is True (the default is False).\r
\r
    Each line of the header will be terminated in the value of eol, which\r
    defaults to "\\n".  Set this to "\\r\\n" if you are using the result of\r
    this function directly in email.\r
    """\r
    # Return empty headers unchanged\r
    if not header:\r
        return header\r
\r
    if not keep_eols:\r
        header = fix_eols(header)\r
\r
    # Quopri encode each line, in encoded chunks no greater than maxlinelen in\r
    # length, after the RFC chrome is added in.\r
    quoted = []\r
    if maxlinelen is None:\r
        # An obnoxiously large number that's good enough\r
        max_encoded = 100000\r
    else:\r
        max_encoded = maxlinelen - len(charset) - MISC_LEN - 1\r
\r
    for c in header:\r
        # Space may be represented as _ instead of =20 for readability\r
        if c == ' ':\r
            _max_append(quoted, '_', max_encoded)\r
        # These characters can be included verbatim\r
        elif not hqre.match(c):\r
            _max_append(quoted, c, max_encoded)\r
        # Otherwise, replace with hex value like =E2\r
        else:\r
            _max_append(quoted, "=%02X" % ord(c), max_encoded)\r
\r
    # Now add the RFC chrome to each encoded chunk and glue the chunks\r
    # together.  BAW: should we be able to specify the leading whitespace in\r
    # the joiner?\r
    joiner = eol + ' '\r
    return joiner.join(['=?%s?q?%s?=' % (charset, line) for line in quoted])\r
\r
\r
\f\r
def encode(body, binary=False, maxlinelen=76, eol=NL):\r
    """Encode with quoted-printable, wrapping at maxlinelen characters.\r
\r
    If binary is False (the default), end-of-line characters will be converted\r
    to the canonical email end-of-line sequence \\r\\n.  Otherwise they will\r
    be left verbatim.\r
\r
    Each line of encoded text will end with eol, which defaults to "\\n".  Set\r
    this to "\\r\\n" if you will be using the result of this function directly\r
    in an email.\r
\r
    Each line will be wrapped at, at most, maxlinelen characters (defaults to\r
    76 characters).  Long lines will have the `soft linefeed' quoted-printable\r
    character "=" appended to them, so the decoded text will be identical to\r
    the original text.\r
    """\r
    if not body:\r
        return body\r
\r
    if not binary:\r
        body = fix_eols(body)\r
\r
    # BAW: We're accumulating the body text by string concatenation.  That\r
    # can't be very efficient, but I don't have time now to rewrite it.  It\r
    # just feels like this algorithm could be more efficient.\r
    encoded_body = ''\r
    lineno = -1\r
    # Preserve line endings here so we can check later to see an eol needs to\r
    # be added to the output later.\r
    lines = body.splitlines(1)\r
    for line in lines:\r
        # But strip off line-endings for processing this line.\r
        if line.endswith(CRLF):\r
            line = line[:-2]\r
        elif line[-1] in CRLF:\r
            line = line[:-1]\r
\r
        lineno += 1\r
        encoded_line = ''\r
        prev = None\r
        linelen = len(line)\r
        # Now we need to examine every character to see if it needs to be\r
        # quopri encoded.  BAW: again, string concatenation is inefficient.\r
        for j in range(linelen):\r
            c = line[j]\r
            prev = c\r
            if bqre.match(c):\r
                c = quote(c)\r
            elif j+1 == linelen:\r
                # Check for whitespace at end of line; special case\r
                if c not in ' \t':\r
                    encoded_line += c\r
                prev = c\r
                continue\r
            # Check to see to see if the line has reached its maximum length\r
            if len(encoded_line) + len(c) >= maxlinelen:\r
                encoded_body += encoded_line + '=' + eol\r
                encoded_line = ''\r
            encoded_line += c\r
        # Now at end of line..\r
        if prev and prev in ' \t':\r
            # Special case for whitespace at end of file\r
            if lineno + 1 == len(lines):\r
                prev = quote(prev)\r
                if len(encoded_line) + len(prev) > maxlinelen:\r
                    encoded_body += encoded_line + '=' + eol + prev\r
                else:\r
                    encoded_body += encoded_line + prev\r
            # Just normal whitespace at end of line\r
            else:\r
                encoded_body += encoded_line + prev + '=' + eol\r
            encoded_line = ''\r
        # Now look at the line we just finished and it has a line ending, we\r
        # need to add eol to the end of the line.\r
        if lines[lineno].endswith(CRLF) or lines[lineno][-1] in CRLF:\r
            encoded_body += encoded_line + eol\r
        else:\r
            encoded_body += encoded_line\r
        encoded_line = ''\r
    return encoded_body\r
\r
\r
# For convenience and backwards compatibility w/ standard base64 module\r
body_encode = encode\r
encodestring = encode\r
\r
\r
\f\r
# BAW: I'm not sure if the intent was for the signature of this function to be\r
# the same as base64MIME.decode() or not...\r
def decode(encoded, eol=NL):\r
    """Decode a quoted-printable string.\r
\r
    Lines are separated with eol, which defaults to \\n.\r
    """\r
    if not encoded:\r
        return encoded\r
    # BAW: see comment in encode() above.  Again, we're building up the\r
    # decoded string with string concatenation, which could be done much more\r
    # efficiently.\r
    decoded = ''\r
\r
    for line in encoded.splitlines():\r
        line = line.rstrip()\r
        if not line:\r
            decoded += eol\r
            continue\r
\r
        i = 0\r
        n = len(line)\r
        while i < n:\r
            c = line[i]\r
            if c != '=':\r
                decoded += c\r
                i += 1\r
            # Otherwise, c == "=".  Are we at the end of the line?  If so, add\r
            # a soft line break.\r
            elif i+1 == n:\r
                i += 1\r
                continue\r
            # Decode if in form =AB\r
            elif i+2 < n and line[i+1] in hexdigits and line[i+2] in hexdigits:\r
                decoded += unquote(line[i:i+3])\r
                i += 3\r
            # Otherwise, not in form =AB, pass literally\r
            else:\r
                decoded += c\r
                i += 1\r
\r
            if i == n:\r
                decoded += eol\r
    # Special case if original string did not end with eol\r
    if not encoded.endswith(eol) and decoded.endswith(eol):\r
        decoded = decoded[:-1]\r
    return decoded\r
\r
\r
# For convenience and backwards compatibility w/ standard base64 module\r
body_decode = decode\r
decodestring = decode\r
\r
\r
\f\r
def _unquote_match(match):\r
    """Turn a match in the form =AB to the ASCII character with value 0xab"""\r
    s = match.group(0)\r
    return unquote(s)\r
\r
\r
# Header decoding is done a bit differently\r
def header_decode(s):\r
    """Decode a string encoded with RFC 2045 MIME header `Q' encoding.\r
\r
    This function does not parse a full MIME header value encoded with\r
    quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use\r
    the high level email.header class for that functionality.\r
    """\r
    s = s.replace('_', ' ')\r
    return re.sub(r'=[a-fA-F0-9]{2}', _unquote_match, s)\r