diff options
author | RanKKI <hliu86.me@gmail.com> | 2024-11-16 23:01:52 (GMT) |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-11-16 23:01:52 (GMT) |
commit | ed81971e6b26c34445f06850192b34458b029337 (patch) | |
tree | 1089c83be8c5ae5bcd12f9f4c087789e76ce2e31 /Lib/email | |
parent | 2313f8421080ceb3343c6f5d291279adea85e073 (diff) | |
download | cpython-ed81971e6b26c34445f06850192b34458b029337.zip cpython-ed81971e6b26c34445f06850192b34458b029337.tar.gz cpython-ed81971e6b26c34445f06850192b34458b029337.tar.bz2 |
gh-124452: Fix header mismatches when folding/unfolding with email message (#125919)
The header-folder of the new email API has a long standing known buglet where
if the first token is longer than max_line_length, it puts that token on the next
line. It turns out there is also a *parsing* bug when parsing such a header:
the space prefixing that first, non-empty line gets preserved and tacked on to
the start of the header value, which is not the expected behavior per the RFCs.
The bug arises from the fact that the parser assumed that there would be at
least one token on the line with the header, which is going to be true for
probably every email producer other than the python email library with its
folding buglet. Clearly, though, this is a case that needs to be handled
correctly. The fix is simple: strip the blanks off the start of the whole
value, not just the first physical line of the value.
Co-authored-by: blurb-it[bot] <43283697+blurb-it[bot]@users.noreply.github.com>
Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com>
Diffstat (limited to 'Lib/email')
-rw-r--r-- | Lib/email/_policybase.py | 4 | ||||
-rw-r--r-- | Lib/email/policy.py | 4 |
2 files changed, 4 insertions, 4 deletions
diff --git a/Lib/email/_policybase.py b/Lib/email/_policybase.py index c7694a4..4b63b97 100644 --- a/Lib/email/_policybase.py +++ b/Lib/email/_policybase.py @@ -302,12 +302,12 @@ class Compat32(Policy): """+ 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, joining all subsequent lines together, and + remainder of the first line joined with all subsequent lines, and stripping any trailing carriage return or linefeed characters. """ name, value = sourcelines[0].split(':', 1) - value = value.lstrip(' \t') + ''.join(sourcelines[1:]) + value = ''.join((value, *sourcelines[1:])).lstrip(' \t\r\n') return (name, value.rstrip('\r\n')) def header_store_parse(self, name, value): diff --git a/Lib/email/policy.py b/Lib/email/policy.py index 46b7de5..6e109b6 100644 --- a/Lib/email/policy.py +++ b/Lib/email/policy.py @@ -119,13 +119,13 @@ class EmailPolicy(Policy): """+ 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, joining all subsequent lines together, and + 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 = value.lstrip(' \t') + ''.join(sourcelines[1:]) + value = ''.join((value, *sourcelines[1:])).lstrip(' \t\r\n') return (name, value.rstrip('\r\n')) def header_store_parse(self, name, value): |