summaryrefslogtreecommitdiffstats
path: root/Lib/email
diff options
context:
space:
mode:
authorAbhilash Raj <maxking@users.noreply.github.com>2020-05-29 00:04:59 (GMT)
committerGitHub <noreply@github.com>2020-05-29 00:04:59 (GMT)
commit21017ed904f734be9f195ae1274eb81426a9e776 (patch)
tree407b8d0170e82598d769d6b8dcb439323cb9b930 /Lib/email
parentc610d970f5373b143bf5f5900d4645e6a90fb460 (diff)
downloadcpython-21017ed904f734be9f195ae1274eb81426a9e776.zip
cpython-21017ed904f734be9f195ae1274eb81426a9e776.tar.gz
cpython-21017ed904f734be9f195ae1274eb81426a9e776.tar.bz2
bpo-39040: Fix parsing of email mime headers with whitespace between encoded-words. (gh-17620)
* bpo-39040: Fix parsing of email headers with encoded-words inside a quoted string. It is fairly common to find malformed mime headers (especially content-disposition headers) where the parameter values, instead of being encoded to RFC standards, are "encoded" by doing RFC 2047 "encoded word" encoding, and then enclosing the whole thing in quotes. The processing of these malformed headers was incorrectly leaving the spaces between encoded words in the decoded text (whitespace between adjacent encoded words is supposed to be stripped on decoding). This changeset fixes the encoded word processing inside quoted strings (bare-quoted-string) to do correct RFC 2047 decoding by stripping that whitespace.
Diffstat (limited to 'Lib/email')
-rw-r--r--Lib/email/_header_value_parser.py9
1 files changed, 9 insertions, 0 deletions
diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
index 9c55ef7..51d355f 100644
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -1218,12 +1218,21 @@ def get_bare_quoted_string(value):
if value[0] in WSP:
token, value = get_fws(value)
elif value[:2] == '=?':
+ valid_ew = False
try:
token, value = get_encoded_word(value)
bare_quoted_string.defects.append(errors.InvalidHeaderDefect(
"encoded word inside quoted string"))
+ valid_ew = True
except errors.HeaderParseError:
token, value = get_qcontent(value)
+ # Collapse the whitespace between two encoded words that occur in a
+ # bare-quoted-string.
+ if valid_ew and len(bare_quoted_string) > 1:
+ if (bare_quoted_string[-1].token_type == 'fws' and
+ bare_quoted_string[-2].token_type == 'encoded-word'):
+ bare_quoted_string[-1] = EWWhiteSpaceTerminal(
+ bare_quoted_string[-1], 'fws')
else:
token, value = get_qcontent(value)
bare_quoted_string.append(token)