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

add more tests, make standard reply tests more relaxed

Browse Source
This commit is contained in:
Sergey Obukhov
2015-12-18 18:56:41 -08:00
parent 41457d8fbd
commit 3d9ae356ea
5 changed files with 134 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
tests/html_quotations_test.py
View File

@@ -5,9 +5,7 @@ from . fixtures import *
import regex as re
from talon import quotations
import html2text
from talon import quotations, utils as u
RE_WHITESPACE = re.compile("\s")
@@ -270,26 +268,15 @@ def test_reply_separated_by_hr():
'', quotations.extract_from_html(REPLY_SEPARATED_BY_HR)))
RE_REPLY = re.compile(r"^Hi\. I am fine\.\s*\n\s*Thanks,\s*\n\s*Alex\s*$")
def extract_reply_and_check(filename):
f = open(filename)
msg_body = f.read()
reply = quotations.extract_from_html(msg_body)
plain_reply = u.html_to_text(reply)
h = html2text.HTML2Text()
h.body_width = 0
plain_reply = h.handle(reply)
#remove   spaces
plain_reply = plain_reply.replace(u'\xa0', u' ')
if RE_REPLY.match(plain_reply):
eq_(1, 1)
else:
eq_("Hi. I am fine.\n\nThanks,\nAlex", plain_reply)
eq_(RE_WHITESPACE.sub('', "Hi. I am fine.\n\nThanks,\nAlex"),
RE_WHITESPACE.sub('', plain_reply))
def test_gmail_reply():

47
tests/utils_test.py
View File

@@ -58,3 +58,50 @@ def test_quick_detect_encoding_edge_cases(detect_encoding, cchardet_detect):
detect_encoding.return_value = 'utf-8'
eq_('utf-8', u.quick_detect_encoding("qwe"))
ok_(detect_encoding.called)
def test_html_to_text():
html = """<body>
<p>Hello world!</p>
<br>
<ul>
<li>One!</li>
<li>Two</li>
</ul>
<p>
Haha
</p>
</body>"""
text = u.html_to_text(html)
eq_("Hello world! \n\n * One! \n * Two \nHaha", text)
eq_("привет!", u.html_to_text("<b>привет!</b>"))
html = '<body><br/><br/>Hi</body>'
eq_ ('Hi', u.html_to_text(html))
html = """Hi
<style type="text/css">
div, p, li {
font: 13px 'Lucida Grande', Arial, sans-serif;
}
</style>
<style type="text/css">
h1 {
font: 13px 'Lucida Grande', Arial, sans-serif;
}
</style>"""
eq_ ('Hi', u.html_to_text(html))
html = """<div>
<!-- COMMENT 1 -->
<span>TEXT 1</span>
<p>TEXT 2 <!-- COMMENT 2 --></p>
</div>"""
eq_('TEXT 1 \nTEXT 2', u.html_to_text(html))