cphipps/changedetection.io
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fetching - Be sure that content-type detection works when the headers are a mixed case (#1604)

Browse Source
This commit is contained in:
dgtlmoon
2023-05-29 16:11:43 +02:00
committed by GitHub
parent ba8d2e0c2d
commit f9387522ee
4 changed files with 50 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
changedetectionio/tests/test_jsonpath_jq_selector.py
View File

@@ -3,7 +3,7 @@
import time
from flask import url_for, escape
from . util import live_server_setup
from . util import live_server_setup, wait_for_all_checks
import pytest
jq_support = True
@@ -436,6 +436,32 @@ def test_ignore_json_order(client, live_server):
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_correct_header_detect(client, live_server):
# Like in https://github.com/dgtlmoon/changedetection.io/pull/1593
# Specify extra html that JSON is sometimes wrapped in - when using Browserless/Puppeteer etc
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write('<html><body>{"hello" : 123, "world": 123}')
# Add our URL to the import page
# Check weird casing is cleaned up and detected also
test_url = url_for('test_endpoint', content_type="aPPlication/JSon", uppercase_headers=True, _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.get(url_for("index"))
# This will be fixed in #1593
assert b'No parsable JSON found in this document' in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_jsonpath_ext_filter(client, live_server):
check_json_ext_filter('json:$[?(@.status==Sold)]', client, live_server)

14
changedetectionio/tests/util.py
View File

@@ -119,16 +119,26 @@ def live_server_setup(live_server):
status_code = request.args.get('status_code')
content = request.args.get('content') or None
# Used to just try to break the header detection
uppercase_headers = request.args.get('uppercase_headers')
try:
if content is not None:
resp = make_response(content, status_code)
resp.headers['Content-Type'] = ctype if ctype else 'text/html'
if uppercase_headers:
ctype=ctype.upper()
resp.headers['CONTENT-TYPE'] = ctype if ctype else 'text/html'
else:
resp.headers['Content-Type'] = ctype if ctype else 'text/html'
return resp
# Tried using a global var here but didn't seem to work, so reading from a file instead.
with open("test-datastore/endpoint-content.txt", "r") as f:
resp = make_response(f.read(), status_code)
resp.headers['Content-Type'] = ctype if ctype else 'text/html'
if uppercase_headers:
resp.headers['CONTENT-TYPE'] = ctype if ctype else 'text/html'
else:
resp.headers['Content-Type'] = ctype if ctype else 'text/html'
return resp
except FileNotFoundError:
return make_response('', status_code)