From e756e0af5e00def9f032d708a701beb7b01702b4 Mon Sep 17 00:00:00 2001
From: dgtlmoon <dgtlmoon@gmail.com>
Date: Thu, 18 Jul 2024 13:05:27 +0200
Subject: [PATCH] Fixing file:// file pickup  - for change detection of local
 files (#2505)

---
 .../content_fetchers/requests.py              | 21 ++++++++++-----
 changedetectionio/run_basic_tests.sh          |  6 ++++-
 changedetectionio/tests/test_security.py      | 27 ++++++++++++++++---
 requirements.txt                              |  1 +
 4 files changed, 44 insertions(+), 11 deletions(-)

diff --git a/changedetectionio/content_fetchers/requests.py b/changedetectionio/content_fetchers/requests.py
index 2c28cda7..5e984c5e 100644
--- a/changedetectionio/content_fetchers/requests.py
+++ b/changedetectionio/content_fetchers/requests.py
@@ -4,6 +4,7 @@ import os
 import chardet
 import requests
 
+from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
 
@@ -45,13 +46,19 @@ class fetcher(Fetcher):
             if self.system_https_proxy:
                 proxies['https'] = self.system_https_proxy
 
-        r = requests.request(method=request_method,
-                             data=request_body,
-                             url=url,
-                             headers=request_headers,
-                             timeout=timeout,
-                             proxies=proxies,
-                             verify=False)
+        session = requests.Session()
+
+        if strtobool(os.getenv('ALLOW_FILE_URI', 'false')) and url.startswith('file://'):
+            from requests_file import FileAdapter
+            session.mount('file://', FileAdapter())
+
+        r = session.request(method=request_method,
+                            data=request_body,
+                            url=url,
+                            headers=request_headers,
+                            timeout=timeout,
+                            proxies=proxies,
+                            verify=False)
 
         # If the response did not tell us what encoding format to expect, Then use chardet to override what `requests` thinks.
         # For example - some sites don't tell us it's utf-8, but return utf-8 content
diff --git a/changedetectionio/run_basic_tests.sh b/changedetectionio/run_basic_tests.sh
index d9fa9ff0..38bcd603 100755
--- a/changedetectionio/run_basic_tests.sh
+++ b/changedetectionio/run_basic_tests.sh
@@ -35,4 +35,8 @@ pytest tests/test_access_control.py
 pytest tests/test_notification.py
 pytest tests/test_backend.py
 pytest tests/test_rss.py
-pytest tests/test_unique_lines.py
\ No newline at end of file
+pytest tests/test_unique_lines.py
+
+# Check file:// will pickup a file when enabled
+echo "Hello world" > /tmp/test-file.txt
+ALLOW_FILE_URI=yes pytest tests/test_security.py
diff --git a/changedetectionio/tests/test_security.py b/changedetectionio/tests/test_security.py
index 0b2ee7dc..af55efb2 100644
--- a/changedetectionio/tests/test_security.py
+++ b/changedetectionio/tests/test_security.py
@@ -1,7 +1,12 @@
+import os
+
 from flask import url_for
 from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
 import time
 
+from .. import strtobool
+
+
 def test_setup(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
 
@@ -55,17 +60,33 @@ def test_bad_access(client, live_server, measure_memory_usage):
 
     assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
 
-    # file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
 
+def test_file_access(client, live_server, measure_memory_usage):
+    #live_server_setup(live_server)
+
+    test_file_path = "/tmp/test-file.txt"
+
+    # file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
     client.post(
         url_for("form_quick_watch_add"),
-        data={"url": 'file:///tasty/disk/drive', "tags": ''},
+        data={"url": f"file://{test_file_path}", "tags": ''},
         follow_redirects=True
     )
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
 
-    assert b'file:// type access is denied for security reasons.' in res.data
+    # If it is enabled at test time
+    if strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
+        res = client.get(
+            url_for("preview_page", uuid="first"),
+            follow_redirects=True
+        )
+
+        # Should see something (this file added by run_basic_tests.sh)
+        assert b"Hello world" in res.data
+    else:
+        # Default should be here
+        assert b'file:// type access is denied for security reasons.' in res.data
 
 def test_xss(client, live_server, measure_memory_usage):
     #live_server_setup(live_server)
diff --git a/requirements.txt b/requirements.txt
index fcfdf774..770c8601 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -22,6 +22,7 @@ validators~=0.21
 # >= 2.26 also adds Brotli support if brotli is installed
 brotli~=1.0
 requests[socks]
+requests-file
 
 urllib3==1.26.19
 chardet>2.3.0