This commit is contained in:
Sergey Obukhov
2016-02-19 17:53:52 -08:00
parent f6940fe878
commit 999e9c3725
2 changed files with 19 additions and 2 deletions

View File

@@ -137,11 +137,16 @@ RE_FROM_COLON_OR_DATE_COLON = re.compile(u'(_+\r?\n)?[\s]*(:?[*]?{})[\s]?:[*]? .
SPLITTER_PATTERNS = [
RE_ORIGINAL_MESSAGE,
# <date> <person>
re.compile("(\d+/\d+/\d+|\d+\.\d+\.\d+).*@", re.S),
RE_ON_DATE_SMB_WROTE,
RE_ON_DATE_WROTE_SMB,
RE_FROM_COLON_OR_DATE_COLON,
# 02.04.2012 14:20 пользователь "bob@example.com" <
# bob@xxx.mailgun.org> написал:
re.compile("(\d+/\d+/\d+|\d+\.\d+\.\d+).*@", re.S),
# 2014-10-17 11:28 GMT+03:00 Bob <
# bob@example.com>:
re.compile("\d{4}-\d{2}-\d{2}\s+\d{2}:\d{2}\s+GMT.*@", re.S),
# Thu, 26 Jun 2014 14:00:51 +0400 Bob <bob@example.com>:
re.compile('\S{3,10}, \d\d? \S{3,10} 20\d\d,? \d\d?:\d\d(:\d\d)?'
'( \S+){3,6}@\S+:')
]

View File

@@ -54,6 +54,18 @@ On 04/19/2011 07:10 AM, Roman Tkachenko wrote:
eq_("Test reply", quotations.extract_from_plain(msg_body))
def test_date_time_email_splitter():
msg_body = """Test reply
2014-10-17 11:28 GMT+03:00 Postmaster <
postmaster@sandboxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx.mailgun.org>:
> First from site
>
"""
eq_("Test reply", quotations.extract_from_plain(msg_body))
def test_pattern_on_date_somebody_wrote_allows_space_in_front():
msg_body = """Thanks Thanmai
On Mar 8, 2012 9:59 AM, "Example.com" <