Discource-C
/
discourse
mirror of https://github.com/discourse/discourse.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

FIX: don't extract divs with a 'gmail_default' class

This commit is contained in:
Régis Hanol 2018-05-03 12:29:21 +02:00
parent 50a2508604
commit 2d561a0422
1 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lib/email/receiver.rb
View File

@ -296,7 +296,7 @@ module Email
end end
HTML_EXTRACTERS ||= [ HTML_EXTRACTERS ||= [
[:gmail, / class="gmail_/], [:gmail, /class="gmail_(?!default)/],
[:outlook, /id="(divRplyFwdMsg|Signature)"/], [:outlook, /id="(divRplyFwdMsg|Signature)"/],
[:word, /class="WordSection1"/], [:word, /class="WordSection1"/],
[:exchange, /name="message(Body|Reply)Section"/], [:exchange, /name="message(Body|Reply)Section"/],
@ -309,8 +309,8 @@ module Email
def extract_from_gmail(doc) def extract_from_gmail(doc)
# GMail adds a bunch of 'gmail_' prefixed classes like: gmail_signature, gmail_extra, gmail_quote # GMail adds a bunch of 'gmail_' prefixed classes like: gmail_signature, gmail_extra, gmail_quote
# Just elide them all # Just elide them all except for 'gmail_default'
elided = doc.css("*[class^='gmail_']").remove elided = doc.css("*[class^='gmail_']:not([class*='gmail_default'])").remove
to_markdown(doc.to_html, elided.to_html) to_markdown(doc.to_html, elided.to_html)
end end