feat: add link moderator

poetry.lock

@@ -84,6 +84,38 @@ files = [
     {file = "docopt-0.6.2.tar.gz", hash = "sha256:49b3a825280bd66b3aa83585ef59c4a8c82f2c8a522dbe754a8bc8d08c85c491"},
 ]
 
+[[package]]
+name = "filelock"
+version = "3.18.0"
+description = "A platform independent file lock."
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "filelock-3.18.0-py3-none-any.whl", hash = "sha256:c401f4f8377c4464e6db25fff06205fd89bdd83b65eb0488ed1b160f780e21de"},
+    {file = "filelock-3.18.0.tar.gz", hash = "sha256:adbc88eabb99d2fec8c9c1b229b171f18afa655400173ddc653d5d01501fb9f2"},
+]
+
+[package.extras]
+docs = ["furo (>=2024.8.6)", "sphinx (>=8.1.3)", "sphinx-autodoc-typehints (>=3)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.6.10)", "diff-cover (>=9.2.1)", "pytest (>=8.3.4)", "pytest-asyncio (>=0.25.2)", "pytest-cov (>=6)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.28.1)"]
+typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""]
+
+[[package]]
+name = "idna"
+version = "3.10"
+description = "Internationalized Domain Names in Applications (IDNA)"
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3"},
+    {file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"},
+]
+
+[package.extras]
+all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"]
+
 [[package]]
 name = "irc3"
 version = "1.1.10"
@@ -146,7 +178,7 @@ version = "4.3.8"
 description = "A small Python package for determining appropriate platform-specific dirs, e.g. a `user data dir`."
 optional = false
 python-versions = ">=3.9"
-groups = ["dev"]
+groups = ["main", "dev"]
 files = [
     {file = "platformdirs-4.3.8-py3-none-any.whl", hash = "sha256:ff7059bb7eb1179e2685604f4aaf157cfd9535242bd23742eadc3c13542139b4"},
     {file = "platformdirs-4.3.8.tar.gz", hash = "sha256:3d512d96e16bcb959a814c9f348431070822a6496326a4be0911c40b5a74c2bc"},
@@ -157,6 +189,36 @@ docs = ["furo (>=2024.8.6)", "proselint (>=0.14)", "sphinx (>=8.1.3)", "sphinx-a
 test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=8.3.4)", "pytest-cov (>=6)", "pytest-mock (>=3.14)"]
 type = ["mypy (>=1.14.1)"]
 
+[[package]]
+name = "uritools"
+version = "5.0.0"
+description = "URI parsing, classification and composition"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "uritools-5.0.0-py3-none-any.whl", hash = "sha256:cead3a49ba8fbca3f91857343849d506d8639718f4a2e51b62e87393b493bd6f"},
+    {file = "uritools-5.0.0.tar.gz", hash = "sha256:68180cad154062bd5b5d9ffcdd464f8de6934414b25462ae807b00b8df9345de"},
+]
+
+[[package]]
+name = "urlextract"
+version = "1.9.0"
+description = "Collects and extracts URLs from given text."
+optional = false
+python-versions = "*"
+groups = ["main"]
+files = [
+    {file = "urlextract-1.9.0-py3-none-any.whl", hash = "sha256:f88963532488b1c7c405e21bd162ae97871754ea04b60e18d33ee075b19b82fd"},
+    {file = "urlextract-1.9.0.tar.gz", hash = "sha256:70508e02ba9df372e25cf0642db367cece273e8712cd0ce78178fc5dd7ea00db"},
+]
+
+[package.dependencies]
+filelock = "*"
+idna = "*"
+platformdirs = "*"
+uritools = "*"
+
 [[package]]
 name = "venusian"
 version = "3.1.1"
@@ -176,4 +238,4 @@ testing = ["coverage", "pytest", "pytest-cov"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.12"
-content-hash = "5d7d7513799a39e01fdb8f7159317204c36855b5948f12b89a71ef7b47bd6a1d"
+content-hash = "2f1ca53ab2001cae84774e065f5289b84fe9a77ae87307012ffc6fff0db436d4"

pyproject.toml

@@ -11,6 +11,7 @@ twason = 'twason.__main__:main'
 [tool.poetry.dependencies]
 python = "^3.12"
 irc3 = "^1.1"
+urlextract = "^1.9"
 
 [tool.poetry.group.dev.dependencies]
 black = "^25.1"

twason/config.py

@@ -166,6 +166,16 @@ class Config:
                         moderator_config.get("min-time-between-occurrence", None),
                     )
                 )
+            if mod == 'links':
+                moderators.append(moderator.LinksModerator(
+                    moderator_config.get(
+                        "message",
+                        "{author}, your message contained forbidden links, it had to be removed for safety."
+                    ),
+                    cls.parse_decision(moderator_config.get("decision", "delete")),
+                    moderator_config.get("duration", None),
+                    moderator_config.get("authorized", [])
+                ))
 
         # Generate help command
         if params.get("help", True):

twason/moderator.py

@@ -19,6 +19,9 @@ from abc import ABC, abstractmethod
 from enum import Enum
 from typing import Union
 from datetime import datetime, timedelta
+from urlextract import URLExtract
+from fnmatch import fnmatch
+import re
 
 EPOCH = datetime(1970, 1, 1)
 
@@ -162,3 +165,52 @@ class FloodModerator(Moderator):
 
     def declare_raid(self):
         self.last_raid = datetime.now()
+
+
+class LinksModerator(Moderator):
+    def __init__(
+            self,
+            message: str,
+            decision: ModerationDecision,
+            timeout_duration: Union[None, int],
+            authorized_urls: [str]
+    ):
+        super().__init__(message, decision, timeout_duration)
+        self.authorized_urls = authorized_urls
+
+    def get_name(self) -> str:
+        return 'Link'
+
+    def vote(self, msg: str, author: str) -> ModerationDecision:
+        url_extractor = URLExtract()
+        links = url_extractor.find_urls(msg)
+
+        if len(links) == 0:
+            return ModerationDecision.ABSTAIN
+
+        if not self.are_urls_authorized(links):
+            return self.decision
+
+        return ModerationDecision.ABSTAIN
+
+    def are_urls_authorized(self, links: [str]) -> bool:
+
+        for link in links:
+            is_link_authorized = False
+            print(link)
+
+            for pattern in self.authorized_urls:
+                print(pattern)
+                if dump(fnmatch(link, pattern)) or dump(fnmatch(f"http://{link}", pattern)) or dump(fnmatch(f"https://{link}", pattern)):
+                    is_link_authorized = True
+                    break
+
+            if not is_link_authorized:
+                return False
+
+        return True
+
+
+def dump(what):
+    print(what)
+    return what