some initial commits, starting what is going to be probably rewritten in C or rust later. idk. its getting late.

TODO.md

@@ -0,0 +1,54 @@
+# saningi-html todo
+
+## Current:
+- [x] basic cli argparsing working (stdin -> sanizization -> stdout)
+- [x] Modes implemented:
+    - strict
+    - loose 
+    - passthrough
+- [x] profiles in a seperate .py file
+
+## To implement:
+
+things not yet implemented in the program
+
+### 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
+
+---
+
+### Expland strict mode:
+- [ ] Allow these:
+    - html, head, body
+    - title
+    - meta (with restrictions)
+    - link (for css only)
+    - table, tr, td, th
+    - any of crucuial html tags
+- [ ] restrict metas (allow):
+    - allow only charset, name, content
+- [ ] restrict metas (dont allow):
+    - base
+    - meta http-equiv
+
+---
+
+### passthrough safety
+- [ ] add stderr warning for user
+
+---
+
+### Add some logging:
+- [ ] debugging with --debug
+- [ ] print what was removed, to stderr
+
+### Config files:
+- [ ] allow custom JSON/YAML/yadayadayada configurations
+    - pass in through CLI with flag --config "file.idk"

src/main.py

@@ -0,0 +1,47 @@
+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"],
+    )
+
+def entry():
+    parser = argparse.ArgumentParser(description="saningi-html sanitizer")
+
+    parser.add_argument(
+        "--mode",
+        choices=["strict","loose","passthrough"],
+        default="strict",
+        help="Strictness of Tags or HTML"
+    )
+
+    args = parser.parse_args()
+
+    raw_html = sys.stdin.read()
+    clean_html = sanitize(raw_html, args.mode)
+
+    print(clean_html)
+
+if __name__ == "__main__":
+    entry()

src/profiles.py

@@ -0,0 +1,35 @@
+#
+#   src/profiles.py
+#   AGPL-3    -   saningi-html
+#
+#   presets for sanitization of HTML
+#
+
+STRICT = {
+    "tags" : [
+        "p", "b", "i", "u", "em", "strong",
+        "ul", "ol", "li",
+        "br", "hr",
+        "h1", "h2", "h3", "h4", "h5", "h6"
+    ],
+    "attributes": {},
+    "protocols": [],
+    "strip": True,
+}
+
+# like my ass :3
+LOOSE = {
+    "tags": [
+        "p", "b", "i", "u", "em", "strong",
+        "ul", "ol", "li",
+        "br", "hr", "span", "div",
+        "a", "img",
+        "h1", "h2", "h3", "h4", "h5", "h6"
+    ],
+    "attributes": {
+        "a": ["href", "title"],
+        "img": {"src", "alt", "style", "loading"}
+    },
+    "protocols": ["http", "https"],
+    "strip": True,
+}