fixed a issue using bs4. see TODO

2026-04-20 08:30:39 +02:00
parent dd5f638149
commit d1d4e497be
3 changed files with 55 additions and 4 deletions
@@ -43,7 +43,7 @@ NOTE: That things which are in italic text are already implemented!
 ---

 ### passthrough safety
- [ ] add stderr warning for user
+- *[x] add stderr warning for user*

 ---

@@ -53,4 +53,30 @@ NOTE: That things which are in italic text are already implemented!

 ### Config files:
 - [ ] allow custom JSON/YAML/yadayadayada configurations
-    - pass in through CLI with flag --config "file.idk"
+    - pass in through CLI with flag --config "file.idk"
+
+## Fixes:
+
+## Content of tag staying after removal of tag
+
+When running strict/loose:
+```
+(venv) rattatwinko@kubuntu:~/Documents/sanigi-html$ echo "<html><body><h1>Heading</h1><script>var=j;</script></body></html>" | python3 src/main.py --mode strict
+[ DEBUG@2026-04-20 07:54:57 ]: called sanitizer! using this as args: 
+<html><body><h1>Heading</h1><script>var=j;</script></body></html>
+['p', 'b', 'i', 'u', 'em', 'strong', 'ul', 'ol', 'li', 'br', 'hr', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']
+[]
+True
+<h1>Heading</h1>**var=j;**
+```
+
+You can see that the ```<script>``` tag gets removed but doesnt bother with removing the contents of that tag. The remaining thing is : **var=j;** ; If this gets rendered its bad, cause it looks bad!
+We need to fix this.
+
+### Plan for fixing this:
+
+Lets maybe use bs4 for this, its fitting cause it can decompose HTML. Fixed! 
+
+### Around 30 minutes later:
+
+This issue is no longer relevant, it is fixed! using bs4.
@@ -5,6 +5,7 @@


 import bleach
+from bs4 import BeautifulSoup, Tag
 from profiles import STRICT, LOOSE
 from log.Logger import *
 logger = Logger()
@@ -14,6 +15,7 @@ PROFILES = {
    "loose": LOOSE,
 }

+
 def sanitize(html : str, mode : str) -> str:
    """
    Arguments:
@@ -27,22 +29,45 @@ def sanitize(html : str, mode : str) -> str:
    # this should be used with caution! it is for trusted
    # individuals only
    if mode == "passthrough":
+        logger.log_warning("You are about to not care about sanitizing ANY HTML. You are in passthrough mode.")
        return html

    config = PROFILES.get(mode)
    if not config:
        raise ValueError(f"Unknown mode! : {mode}")
    
+    allowed = set(config.get("tags", []))
+    good_soup = BeautifulSoup(html, "html.parser")
+
+    def has_allowed_child(node: Tag) -> bool:
+        # check if shit is allowed
+        for child in node.descendants:
+            if isinstance(child, Tag) and child.name.lower() in allowed:
+                return True
+        return False
+
+        
+    for child in list(good_soup.find_all()):
+        name = child.name.lower()
+        if name in allowed:
+            continue
+        if has_allowed_child(child):
+            child.unwrap()
+        else:
+            child.decompose()
+    
+    bs_parsed = str(good_soup)
+   
    logger.log_debug(
        "called sanitizer! using this as args: \n" + 
-        str(html) +
+        str(bs_parsed) +
        str(config["tags"]) + "\n" +
        str(config["protocols"]) + "\n" +
        str(config["strip"]) 
    )

    return bleach.clean(
-        html,
+        bs_parsed,
        tags=config["tags"],
        attributes=config["attributes"],
        protocols=config["protocols"],