o2w/talon
4
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fixes mailgun/talon#18

Browse Source
This commit is contained in:
Sergey Obukhov
2016-02-19 18:30:43 -08:00
parent 2ecd9779fc
commit 31803d41bc
3 changed files with 15 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
setup.py
View File

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
setup(name='talon',
version='1.2.2',
version='1.2.3',
description=("Mailgun library "
"to extract message quotations and signatures."),
long_description=open("README.rst").read(),

8
talon/html_quotations.py
View File

@@ -12,6 +12,7 @@ CHECKPOINT_PATTERN = re.compile(CHECKPOINT_PREFIX + '\d+' + CHECKPOINT_SUFFIX)
# HTML quote indicators (tag ids)
QUOTE_IDS = ['OLK_SRC_BODY_SECTION']
RE_FWD = re.compile("^[-]+[ ]*Forwarded message[ ]*[-]+$", re.I | re.M)
def add_checkpoint(html_note, counter):
@@ -77,7 +78,7 @@ def delete_quotation_tags(html_note, counter, quotation_checkpoints):
def cut_gmail_quote(html_message):
''' Cuts the outermost block element with class gmail_quote. '''
gmail_quote = html_message.cssselect('div.gmail_quote')
if gmail_quote:
if gmail_quote and not RE_FWD.match(gmail_quote[0].text):
gmail_quote[0].getparent().remove(gmail_quote[0])
return True
@@ -172,6 +173,7 @@ def cut_from_block(html_message):
parent_div_is_all_content = (
maybe_body is not None and maybe_body.tag == 'body' and
len(maybe_body.getchildren()) == 1)
if not parent_div_is_all_content:
block.getparent().remove(block)
return True
@@ -185,6 +187,10 @@ def cut_from_block(html_message):
"//*[starts-with(mg:tail(), 'Date:')]"))
if block:
block = block[0]
if RE_FWD.match(block.getparent().text or ''):
return False
while(block.getnext() is not None):
block.getparent().remove(block.getnext())
block.getparent().remove(block)

7
tests/html_quotations_test.py
View File

@@ -340,3 +340,10 @@ def test_CRLF():
assert_false(symbol in extracted)
eq_("<html><body><p>Reply</p></body></html>",
RE_WHITESPACE.sub('', extracted))
def test_gmail_forwarded_msg():
msg_body = """<div dir="ltr"><br><div class="gmail_quote">---------- Forwarded message ----------<br>From: <b class="gmail_sendername">Bob</b> <span dir="ltr">&lt;<a href="mailto:bob@example.com">bob@example.com</a>&gt;</span><br>Date: Fri, Feb 11, 2010 at 5:59 PM<br>Subject: Bob WFH today<br>To: Mary &lt;<a href="mailto:mary@example.com">mary@example.com</a>&gt;<br><br><br><div dir="ltr">eom</div>
</div><br></div>"""
extracted = quotations.extract_from_html(msg_body)
eq_(RE_WHITESPACE.sub('', msg_body), RE_WHITESPACE.sub('', extracted))