mirror of
https://we.phorge.it/source/phorge.git
synced 2024-12-22 21:40:55 +01:00
Transcode the HTML part of incoming email into UTF-8 as well
Summary: D1093 did this for just the text/plain part of incoming email. Most text/html parts choose to either use entity encoding //or// are already UTF-8, thus obviating the need to transcode the HTML part. However, this is not always the case, and leads to dropped messages, by way of: ``` EXCEPTION: (Exception) Failed to JSON encode value (#5: Malformed UTF-8 characters, possibly incorrectly encoded): Dictionary value at key "html" is not valid UTF8, and cannot be JSON encoded: [snip HTML part of message content]``` Generalize the charset transcoding to not apply to just the text/plain part, but both text/plain and text/html parts. Test Plan: Fed in a Windows-1252-encoded text/html part with 0x92 bytes in it; verified that $content only contained valid UTF-8 after this change. Reviewers: #blessed_reviewers, epriestley Reviewed By: #blessed_reviewers, epriestley Subscribers: Korvin, epriestley Differential Revision: https://secure.phabricator.com/D18776
This commit is contained in:
parent
bea45e90d3
commit
d2cff6a2cf
1 changed files with 14 additions and 14 deletions
|
@ -35,16 +35,19 @@ $args->parse(
|
|||
$parser = new MimeMailParser();
|
||||
$parser->setText(file_get_contents('php://stdin'));
|
||||
|
||||
$text_body = $parser->getMessageBody('text');
|
||||
|
||||
$text_body_headers = $parser->getMessageBodyHeaders('text');
|
||||
$content_type = idx($text_body_headers, 'content-type');
|
||||
if (
|
||||
!phutil_is_utf8($text_body) &&
|
||||
(preg_match('/charset="(.*?)"/', $content_type, $matches) ||
|
||||
preg_match('/charset=(\S+)/', $content_type, $matches))
|
||||
) {
|
||||
$text_body = phutil_utf8_convert($text_body, 'UTF-8', $matches[1]);
|
||||
$content = array();
|
||||
foreach (array('text', 'html') as $part) {
|
||||
$part_body = $parser->getMessageBody($part);
|
||||
$part_headers = $parser->getMessageBodyHeaders($part);
|
||||
$content_type = idx($part_headers, 'content-type');
|
||||
if (
|
||||
!phutil_is_utf8($part_body) &&
|
||||
(preg_match('/charset="(.*?)"/', $content_type, $matches) ||
|
||||
preg_match('/charset=(\S+)/', $content_type, $matches))
|
||||
) {
|
||||
$part_body = phutil_utf8_convert($part_body, 'UTF-8', $matches[1]);
|
||||
}
|
||||
$content[$part] = $part_body;
|
||||
}
|
||||
|
||||
$headers = $parser->getHeaders();
|
||||
|
@ -57,10 +60,7 @@ if ($args->getArg('process-duplicates')) {
|
|||
|
||||
$received = new PhabricatorMetaMTAReceivedMail();
|
||||
$received->setHeaders($headers);
|
||||
$received->setBodies(array(
|
||||
'text' => $text_body,
|
||||
'html' => $parser->getMessageBody('html'),
|
||||
));
|
||||
$received->setBodies($content);
|
||||
|
||||
$attachments = array();
|
||||
foreach ($parser->getAttachments() as $attachment) {
|
||||
|
|
Loading…
Reference in a new issue