see TODO.md

.gitignore

@@ -668,3 +668,8 @@ fabric.properties
 # Android studio 3.1+ serialized cache file
 .idea/caches/build_file_checksums.ser
 
+
+
+## ENVIRONMENT
+
+.env

TODO.md

@@ -11,17 +11,19 @@
 ## To implement:
 
 things not yet implemented in the program
+NOTE: That things which are in italic text are already implemented!
 
 ### url filtering:
-- [ ] block external URL in strict mode (eg a link with href to some porn site or something)
-- [ ] allow relative paths:
-    - eg "/path/to/my/awesome/post.html"
-- [ ] apply to any of these:
-    - a
-    - img
-    - link href
-- [ ] add custom attribute filter function
 
+- *[x] block external URL in strict mode (eg a link with href to some porn site or something)*
+- *[x] allow relative paths:*
+    *- eg "/path/to/my/awesome/post.html"*
+- *[x] apply to any of these:*
+    - *a*
+    - *img*
+    - *link href*
+- *[x] add custom attribute filter function*
+- [] load dotenv (chore for profiles.py) ; do this someday when implementing JSON configs. Or dotenv stuff : PRIO:HIGH
 ---
 
 ### Expland strict mode:

src/log/Logger.py

@@ -0,0 +1,35 @@
+#
+#   src/log/Logger.py
+#   AGPL-3.0    -   saningi-html
+#   usage:
+#       insantiate using logger = Logger()
+#       import using import .log.Logger
+#
+#
+
+import time
+import sys
+import colorama
+
+colorama.init(autoreset=True)
+
+class Logger:
+    @staticmethod
+    def _now() -> str:
+        return time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+
+    @staticmethod
+    def log_error(message: str) -> None:
+        print(f"{colorama.Fore.RED}[ ERROR@{Logger._now()} ]: {message}", file=sys.stderr)
+
+    @staticmethod
+    def log_info(message: str) -> None:
+        print(f"{colorama.Fore.CYAN}[ INFO@{Logger._now()} ]: {message}", file=sys.stderr)
+
+    @staticmethod
+    def log_debug(message: str) -> None:
+        print(f"[ DEBUG@{Logger._now()} ]: {message}", file=sys.stderr)
+
+    @staticmethod
+    def log_warning(message: str) -> None:
+        print(f"{colorama.Fore.YELLOW}[ WARNING@{Logger._now()} ]: {message}", file=sys.stderr)

src/main.py

@@ -1,30 +1,13 @@
+#
+#   src/profiles.py
+#   AGPL-3  -   saningi-html
+#   
+#   entrypoint
+#
+
 import sys
 import argparse
-import bleach
-from profiles import STRICT, LOOSE
-
-PROFILES = {
-    "strict": STRICT,
-    "loose": LOOSE,
-}
-
-def sanitize(html : str, mode : str) -> str:
-    # this should be used with caution! it is for trusted
-    # individuals only
-    if mode == "passthrough":
-        return html
-
-    config = PROFILES.get(mode)
-    if not config:
-        raise ValueError(f"Unknown mode! : {mode}")
-    
-    return bleach.clean(
-        html,
-        tags=config["tags"],
-        attributes=config["attributes"],
-        protocols=config["protocols"],
-        strip=config["strip"],
-    )
+from sanitizer import sanitize
 
 def entry():
     parser = argparse.ArgumentParser(description="saningi-html sanitizer")

src/profiles.py

@@ -4,6 +4,49 @@
 #
 #   presets for sanitization of HTML
 #
+import re
+from dotenv import dotenv_values
+from urllib.parse import urlparse
+
+def is_safe_url(url : str, allowed_domain=None, allow_relative : bool = True) -> bool:
+    """
+    Determine wether or not a URL is safe or not.
+    Safe URL's are only local so /this/url
+    Unsafe URL's are external ones like https://pornhub.com
+    """
+    if not url:
+        return False
+
+    if allow_relative:
+        if url.startswith(("#", "/", "./", "../")):
+            return True
+    
+    if url.startswith("//"):
+        if not allowed_domain:
+            return False
+        
+        parsed = urlparse("http:" + url)
+        domain = parsed.netloc or parsed.path.split("/")[0]
+        return domain in allowed_domain
+    
+    parsed = urlparse(url)
+    if parsed.scheme in ("http", "https"):
+        if not allowed_domain:
+            return False
+        return parsed.netloc in allowed_domain
+    
+    return False
+
+def create_url_filter(allowed_attrs, allowed_domains=None, allow_relative=True):
+    def filter_func(tag, name, value):
+        if name not in allowed_attrs:
+            return None
+        if name in ('href', 'src'):
+            if is_safe_url(value, allowed_domains, allow_relative):
+                return value
+            return None
+        return value
+    return filter_func
 
 STRICT = {
     "tags" : [
@@ -12,7 +55,12 @@ STRICT = {
         "br", "hr",
         "h1", "h2", "h3", "h4", "h5", "h6"
     ],
-    "attributes": {},
+    "attributes": {
+        # TODO: add loading dotenv variables
+        "a": create_url_filter(["href"], allowed_domains=[], allow_relative=True),
+        "img" : create_url_filter(["src", "alt"], allowed_domains=[], allow_relative=True),
+        "link" : create_url_filter(["href"], allowed_domains=[], allow_relative=True),
+    },
     "protocols": [],
     "strip": True,
 }

src/sanitizer.py

@@ -0,0 +1,35 @@
+import bleach
+from profiles import STRICT, LOOSE
+from log.Logger import *
+logger = Logger()
+
+PROFILES = {
+    "strict": STRICT,
+    "loose": LOOSE,
+}
+
+def sanitize(html : str, mode : str) -> str:
+    # this should be used with caution! it is for trusted
+    # individuals only
+    if mode == "passthrough":
+        return html
+
+    config = PROFILES.get(mode)
+    if not config:
+        raise ValueError(f"Unknown mode! : {mode}")
+    
+    logger.log_debug(
+        "called sanitizer! using this as args: \n" + 
+        str(html) +
+        str(config["tags"]) + "\n" +
+        str(config["protocols"]) + "\n" +
+        str(config["strip"]) 
+    )
+
+    return bleach.clean(
+        html,
+        tags=config["tags"],
+        attributes=config["attributes"],
+        protocols=config["protocols"],
+        strip=config["strip"],
+    )