hemna
/
aprsd
mirror of https://github.com/craigerl/aprsd.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge pull request #22 from craigerl/fix_email 

Fix unknown characterset emails
This commit is contained in:
Walter A. Boring IV 2020-12-15 18:05:28 -05:00 committed by GitHub
parent b4526f3a0e 96bae795a5
commit 3002ac2e89
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
aprsd/main.py
View File

@ -220,25 +220,27 @@ def parse_email(msgid, data, server):
text = ""
html = None
# default in case body somehow isn't set below - happened once
body = "* unreadable msg received"
body = b"* unreadable msg received"
# this uses the last text or html part in the email, phone companies often put content in an attachment
for part in msg.get_payload():
if (
part.get_content_charset() is None
): # or BREAK when we hit a text or html?
if part.get_content_charset() is None:
# or BREAK when we hit a text or html?
# We cannot know the character set,
# so return decoded "something"
LOG.debug("Email got unknown content type")
text = part.get_payload(decode=True)
continue
charset = part.get_content_charset()
if part.get_content_type() == "text/plain":
LOG.debug("Email got text/plain")
text = six.text_type(
part.get_payload(decode=True), str(charset), "ignore"
).encode("utf8", "replace")
if part.get_content_type() == "text/html":
LOG.debug("Email got text/html")
html = six.text_type(
part.get_payload(decode=True), str(charset), "ignore"
).encode("utf8", "replace")
@ -250,6 +252,7 @@ def parse_email(msgid, data, server):
body = html.strip()
else: # message is not multipart
# email.uscc.net sends no charset, blows up unicode function below
LOG.debug("Email is not multipart")
if msg.get_content_charset() is None:
text = six.text_type(
msg.get_payload(decode=True), "US-ASCII", "ignore"