Files
odoo_source/addons/website/tools.py
T
roen-odoo d8568944b4 [FIX] website, website_blog: remove stars from blog description
Current behavior:
When adding a "Heading" in the first 200 characters of a blog with
/Heading, the short description of the blog preview would have
unwanted stars (*) around the heading

Steps to reproduce:
- Create a blog article
- In the first 200 characters of the blog use a heading (e.g. /Heading1)
- Go back to the blog list, the description of the new article contains
  unwanted stars (*)

opw-2798595

closes odoo/odoo#88352

X-original-commit: 6cb57d2f1ffb0adceaa3199cc0bf5140589d9328
Signed-off-by: Romain Derie (rde) <rde@odoo.com>
2022-04-14 14:07:05 +02:00

162 lines
5.0 KiB
Python

# Part of Odoo. See LICENSE file for full copyright and licensing details.
import contextlib
import re
from lxml import etree
from unittest.mock import Mock, MagicMock, patch
from werkzeug.exceptions import NotFound
from werkzeug.test import EnvironBuilder
import odoo
from odoo.tests.common import HttpCase, HOST
from odoo.tools.misc import DotDict, frozendict
@contextlib.contextmanager
def MockRequest(
env, *, path='/mockrequest/', routing=True, multilang=True,
context=frozendict(), cookies=frozendict(), country_code=None,
website=None, sale_order_id=None, website_sale_current_pl=None,
):
lang_code = context.get('lang', env.context.get('lang', 'en_US'))
env = env(context=dict(context, lang=lang_code))
request = Mock(
# request
httprequest=Mock(
host='localhost',
path=path,
app=odoo.http.root,
environ=dict(
EnvironBuilder(
path=path,
base_url=HttpCase.base_url()
).get_environ(),
REMOTE_ADDR=HOST,
),
cookies=cookies,
referrer='',
),
type='http',
future_response=odoo.http.FutureResponse(),
params={},
redirect=env['ir.http']._redirect,
session=DotDict(
odoo.http.DEFAULT_SESSION,
geoip={'country_code': country_code},
sale_order_id=sale_order_id,
website_sale_current_pl=website_sale_current_pl,
),
geoip={},
db=None,
env=env,
registry=env.registry,
cr=env.cr,
uid=env.uid,
context=env.context,
lang=env['res.lang']._lang_get(lang_code),
website=website,
)
if website:
request.website_routing = website.id
# The following code mocks match() to return a fake rule with a fake
# 'routing' attribute (routing=True) or to raise a NotFound
# exception (routing=False).
#
# router = odoo.http.root.get_db_router()
# rule, args = router.bind(...).match(path)
# # arg routing is True => rule.endpoint.routing == {...}
# # arg routing is False => NotFound exception
router = MagicMock()
match = router.return_value.bind.return_value.match
if routing:
match.return_value[0].routing = {
'type': 'http',
'website': True,
'multilang': multilang
}
else:
match.side_effect = NotFound
with contextlib.ExitStack() as s:
odoo.http._request_stack.push(request)
s.callback(odoo.http._request_stack.pop)
s.enter_context(patch('odoo.http.root.get_db_router', router))
yield request
# Fuzzy matching tools
def distance(s1="", s2="", limit=4):
"""
Limited Levenshtein-ish distance (inspired from Apache text common)
Note: this does not return quick results for simple cases (empty string, equal strings)
those checks should be done outside loops that use this function.
:param s1: first string
:param s2: second string
:param limit: maximum distance to take into account, return -1 if exceeded
:return: number of character changes needed to transform s1 into s2 or -1 if this exceeds the limit
"""
BIG = 100000 # never reached integer
if len(s1) > len(s2):
s1, s2 = s2, s1
l1 = len(s1)
l2 = len(s2)
if l2 - l1 > limit:
return -1
boundary = min(l1, limit) + 1
p = [i if i < boundary else BIG for i in range(0, l1 + 1)]
d = [BIG for _ in range(0, l1 + 1)]
for j in range(1, l2 + 1):
j2 = s2[j -1]
d[0] = j
range_min = max(1, j - limit)
range_max = min(l1, j + limit)
if range_min > 1:
d[range_min -1] = BIG
for i in range(range_min, range_max + 1):
if s1[i - 1] == j2:
d[i] = p[i - 1]
else:
d[i] = 1 + min(d[i - 1], p[i], p[i - 1])
p, d = d, p
return p[l1] if p[l1] <= limit else -1
def similarity_score(s1, s2):
"""
Computes a score that describes how much two strings are matching.
:param s1: first string
:param s2: second string
:return: float score, the higher the more similar
pairs returning non-positive scores should be considered non similar
"""
dist = distance(s1, s2)
if dist == -1:
return -1
set1 = set(s1)
score = len(set1.intersection(s2)) / len(set1)
score -= dist / len(s1)
score -= len(set1.symmetric_difference(s2)) / (len(s1) + len(s2))
return score
def text_from_html(html_fragment, collapse_whitespace=False):
"""
Returns the plain non-tag text from an html
:param html_fragment: document from which text must be extracted
:return: text extracted from the html
"""
# lxml requires one single root element
tree = etree.fromstring('<p>%s</p>' % html_fragment, etree.XMLParser(recover=True))
content = ' '.join(tree.itertext())
if collapse_whitespace:
content = re.sub('\\s+', ' ', content).strip()
return content