Add tests and documentation

Author: JannisBush

README.md

@@ -21,16 +21,24 @@ Our modified version of the wptserve HTTP server implementation can be found in
 - Manually check if the server and the tests are working: Visit http://sub.headers.websec.saarland:80/_hp/tests/framing.sub.html
 - Automatic testrunners:
   - `cd _hp/hp/tools/crawler`
-  - Android: `poetry run python android_intent.py` (Additional config required)
+  - Android: `poetry run python android_intent.py` (TODO: Additional config required; solve android_intent and more?!)
   - MacOS/Ubuntu: `poetry run python desktop_selenium.py` (For a quick test run: `poetry run python desktop_selenium.py --debug_browsers --resp_type debug --ignore_certs`)
   - iPadOS/iOS: `poetry run python desktop_selenium.py ----gen_page_runner --page_runner_json urls.json --max_urls_until_restart 10000"`, then visit the URLs in that file manually
   - TODO: Exact settings of the runs for our experiment:
     - TODO: some information about how to exactly reproduce our results?
     - TODO: repeat to ensure each test has 5x repetitions (`poetry run python create_repeat ...`)
     - ...
+- Optional configuration to run headfull browsers on linux server:
+```bash
+Xvfb :99 -screen 0 1920x1080x24 &
+x11vnc -display :99 -bg -shared -forever -passwd abc -xkb -rfbport 5900
+export DISPLAY=:99 && fluxbox -log fluxbox.log &
+```
 - Analysis:
   - Run `cd _hp/hp/tools/analysis && poetry run jupyter-lab`
-  - Open `_hp/hp/tools/analysis/main_analysis_desktop_basic+parsing.ipynb` (Also contains the mobile analysis)
+  - Open `_hp/hp/tools/analysis/main_analysis_desktop_basic+parsing.ipynb`
+  - TODO: rename: (Also contains the mobile analysis)
+  - TODO: check analysis code and improve
 
 ## Inventory
 - `_hp/`: All test and analysis code for the paper:

_hp/hp/test_internals.py

@@ -1,10 +1,10 @@
 import pytest
 import json
-import httpx
 
-from hp.tools.crawler.selenium_run_specific import config, run_specific
-from hp.tools.crawler.utils import generate_short_uuid
+from hp.tools.crawler.selenium_run_specific import run_specific
+from hp.tools.crawler.utils import generate_short_uuid, get_tests, get_resp_ids, get_or_create_browser
 from hp.tools.create_responses import create_responses
+from hp.tools.crawler.desktop_selenium import get_child_processes
 
 with open("_hp/wpt-config.json", "r") as f:
     wpt_config = json.load(f)
@@ -14,10 +14,14 @@ def test_generate_short_uuid():
     """Assert length of generate_shot_uuid is correct."""
     assert len(generate_short_uuid(3)) == 3
 
-
 def test_selenium_test_specific():
     """Smoke test for run_specific: function runs without crashing, browser can visit one of our test pages."""
     url = f"http://sub.{wpt_config['browser_host']}/_hp/tests/referrer-access-rp.sub.html?resp_type=basic&browser_id=1&label=RP&first_id=199&last_id=199&scheme=http&t_resp_id=199&t_element_relation=iframe_window.open&t_resp_origin=http://sub.{wpt_config['browser_host']}"
+    config = [
+        # Browsers (managed by Selenium itself)
+        # Released 2024-01-23
+        ("firefox", "122", None, ["-headless"], get_or_create_browser("firefox", "122", "Ubuntu 22.04", "headless", "selenium", "")),
+    ]
     for browser_name, browser_version, binary_location, arguments, _ in config:
         run_specific(url, browser_name, browser_version, binary_location, arguments)
 
@@ -31,3 +35,38 @@ def test_create_responses():
     status_code = 200
     create_responses(header_list=header_list, label=label, status_code=status_code, resp_type=resp_type)
     assert True
+
+def test_get_tests():
+    """Check whether get_tests returns test URLs"""
+    resp_type = "basic"
+    browser_id = "-5"
+    scheme = "http"
+    max_popups = 2
+    max_resps = 10
+    browser_modifier = 2
+    tests = get_tests(resp_type=resp_type, browser_id=browser_id, scheme=scheme, max_popups=max_popups, max_resps=max_resps, browser_modifier=browser_modifier)
+    assert len(tests) == 325
+
+def test_get_resp_ids():
+    """Check whether get_resp_ids returns valid splits
+    """
+    label = "XFO"
+    resp_type = "basic"
+    num_resp_ids = 3
+    splits = get_resp_ids(label=label, resp_type=resp_type, num_resp_ids=num_resp_ids)
+
+    assert len(splits) == 4
+
+def test_get_or_create_browser():
+    """Check whether a browser configuration entry can be created
+    """
+    # The unknown browser always has to be ID 1
+    browser = get_or_create_browser(name="Unknown", version="Unknown", os="Unknown", headless_mode="real", automation_mode="manual", add_info=None)
+    assert browser == 1
+
+def test_get_child_processes():
+    """Check that 0 has a couple of childs
+    """
+    process_list = get_child_processes(0)
+    assert len(process_list) > 5
+

_hp/hp/tools/crawler/android_intent.py

@@ -6,7 +6,7 @@
 
 
 from hp.tools.crawler.desktop_selenium import CustomErrorTimeout, CustomTimeout
-from hp.tools.crawler.utils import get_tests, get_or_create_browser, TIMEOUT
+from hp.tools.crawler.utils import get_tests, get_or_create_browser
 from multiprocessing import Pool
 import psycopg
 import uuid
@@ -206,7 +206,7 @@ def main(browser_list, url_dict, repeat_times, num_devices, resp_type, auto_rest
 
 	device_ids = get_available_device()
 	while len(device_ids) > 0:
-		print('Force stop current emulatos ...')
+		print('Force stop current emulators ...')
 		force_stop_emulators()
 		device_ids = get_available_device()
 		time.sleep(2)

_hp/hp/tools/crawler/create_page_runner_repeats.py

@@ -1,3 +1,6 @@
+"""
+Generate URLs to visit that contain all URLs that have to be repeated in a browser (iOS/MacOS)
+"""
 import json
 from hp.tools.crawler.utils import create_test_page_runner, generate_short_uuid
 import argparse
@@ -6,17 +9,17 @@
     parser = argparse.ArgumentParser(description="Convert repeats for pagerunner.")
     parser.add_argument("--browser_id", type=int, required=True)
     args = parser.parse_args()
+    browser_id = str(args.browser_id)
+    rand_token = generate_short_uuid()
 
     with open("../repeat.json", "r") as f:
         d = json.load(f)
-    
-    browser_id = str(args.browser_id)
-
-    rand_token = generate_short_uuid()
+    # Ensure there are some entries for the browser_id in the repeat dict
     print(len(d[browser_id]))
-    
-    safari_special = False
-    if safari_special:
+
+    # Either create one repeat URL or several ones with maximum 1000 URLs per chunk
+    chunk = False
+    if chunk:
         test_urls = d[browser_id]
         url_chunks = [test_urls[i:i + 1000] for i in range(0, len(test_urls), 1000)]
         url_list = []
@@ -26,8 +29,8 @@
             chunk_id += 1
 
         print(f"URLs to visit: {url_list}")
-        with open(f"parsing-MaxURLs1000-MaxResps10-MaxPopups100-{rand_token}.json", "w") as f:
+        with open(f"repeats-MaxURLs1000-{rand_token}.json", "w") as f:
                 json.dump(url_list, f)
     else:
         r = create_test_page_runner(browser_id, f"{rand_token}-0", d[browser_id])
-        print(r)
+        print(r)