From bbefb1749dd70d3174d1fea8ea4c4b541155ee0e Mon Sep 17 00:00:00 2001
From: rattatwinko <seppmutterman@gmail.com>
Date: Fri, 17 Apr 2026 23:10:59 +0200
Subject: [PATCH] some initial commits, starting what is going to be probably
 rewritten in C or rust later. idk. its getting late.

---
 TODO.md          |  54 +++++++++++++++++++++++++++++++++++++++++++++++
 requirements.txt | Bin 0 -> 74 bytes
 src/main.py      |  47 +++++++++++++++++++++++++++++++++++++++++
 src/profiles.py  |  35 ++++++++++++++++++++++++++++++
 4 files changed, 136 insertions(+)
 create mode 100644 TODO.md
 create mode 100644 requirements.txt
 create mode 100644 src/main.py
 create mode 100644 src/profiles.py

diff --git a/TODO.md b/TODO.md
new file mode 100644
index 0000000..8deb44f
--- /dev/null
+++ b/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"
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..2fe7495d7a83dfa37393aaec32672c0d70f35159
GIT binary patch
literal 74
zcmezWFNq<CA(bJKA(<hA!4?S381xv7f!Kh7mw}6+94MCr#CbsZe1;T;Odu<rp%|>v
M0I13ohz-Fi0WS~?UH||9

literal 0
HcmV?d00001

diff --git a/src/main.py b/src/main.py
new file mode 100644
index 0000000..25cd988
--- /dev/null
+++ b/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()
\ No newline at end of file
diff --git a/src/profiles.py b/src/profiles.py
new file mode 100644
index 0000000..1c15be7
--- /dev/null
+++ b/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,
+}