From 6cab95657f8481abd33a482bd8de6e6b587fd15a Mon Sep 17 00:00:00 2001
From: hanishkvc <hanishkvc@gmail.com>
Date: Sun, 2 Nov 2025 13:39:37 +0530
Subject: [PATCH] SimpleChatTC:SimpleProxy:UrlValidator initial go

Check if the specified scheme is allowed or not.

If allowed then call corresponding validator to check remaining
part of the url is fine or not
---
 .../local.tools/urlvalidator.py               | 47 ++++++++++++++-----
 1 file changed, 35 insertions(+), 12 deletions(-)

diff --git a/tools/server/public_simplechat/local.tools/urlvalidator.py b/tools/server/public_simplechat/local.tools/urlvalidator.py
index dec5f11c5a..59f796d430 100644
--- a/tools/server/public_simplechat/local.tools/urlvalidator.py
+++ b/tools/server/public_simplechat/local.tools/urlvalidator.py
@@ -13,26 +13,27 @@ gMe = {
 @dataclass(frozen=True)
 class UrlVResponse:
     """
-    Used to return result wrt urlreq helper below.
+    Used to return detailed results below.
     """
     callOk: bool
     statusCode: int
     statusMsg: str = ""
 
 
-def validator_ok():
-    pass
-
-
-def validate_url(url: str, tag: str):
-    """
-    Implement a re based filter logic on the specified url.
-    """
-    tag=f"VU:{tag}"
+def validator_ok(tag: str):
     if (not gMe.get('--allowed.domains')):
         return UrlVResponse(False, 400, f"DBUG:{tag}:MissingAllowedDomains")
-    urlParts = urllib.parse.urlparse(url)
-    print(f"DBUG:ValidateUrl:{urlParts}, {urlParts.hostname}")
+    if (not gMe.get('--allowed.schemes')):
+        return UrlVResponse(False, 400, f"DBUG:{tag}:MissingAllowedSchemes")
+    return UrlVResponse(True, 100)
+
+
+def validate_fileurl(urlParts: urllib.parse.ParseResult, tag: str):
+    return UrlVResponse(True, 100)
+
+
+def validate_weburl(urlParts: urllib.parse.ParseResult, tag: str):
+    # Cross check hostname
     urlHName = urlParts.hostname
     if not urlHName:
         return UrlVResponse(False, 400, f"WARN:{tag}:Missing hostname in Url")
@@ -43,3 +44,25 @@ def validate_url(url: str, tag: str):
     if not bMatched:
         return UrlVResponse(False, 400, f"WARN:{tag}:requested hostname not allowed")
     return UrlVResponse(True, 200)
+
+
+def validate_url(url: str, tag: str):
+    """
+    Implement a re based filter logic on the specified url.
+    """
+    tag=f"VU:{tag}"
+    vok = validator_ok(tag)
+    if (not vok.callOk):
+        return vok
+    urlParts = urllib.parse.urlparse(url)
+    print(f"DBUG:{tag}:{urlParts}, {urlParts.hostname}")
+    # Cross check scheme
+    urlScheme = urlParts.scheme
+    if not urlScheme:
+        return UrlVResponse(False, 400, f"WARN:{tag}:Missing scheme in Url")
+    if not (urlScheme in gMe['--allowed.schemes']):
+        return UrlVResponse(False, 400, f"WARN:{tag}:requested scheme not allowed")
+    if urlScheme == 'file':
+        return validate_fileurl(urlParts, tag)
+    else:
+        return validate_weburl(urlParts, tag)