Initial commit: ULPgrammer

- Core Telegram monitoring pipeline (scraper, processor, notifier, downloaders)
- Textual TUI frontend with thread-safe event bus
- SQLite persistence, severity scoring, dedup cache
- Fixed ULP parser: handles https:// truncation, port+path URLs, semicolon separator
- Test suite: 88 tests across scorer, cache, database, processor

tests/test_cache.py

@@ -0,0 +1,55 @@
+"""
+Tests for utils/cache.py — file-ID deduplication cache.
+
+Each test gets an isolated cache file via the `isolated_cache` fixture
+so tests never touch data/cache.json.
+"""
+
+import pytest
+import utils.cache as cache_module
+
+
+@pytest.fixture(autouse=True)
+def isolated_cache(tmp_path, monkeypatch):
+    monkeypatch.setattr(cache_module, "CACHE_FILE", tmp_path / "cache.json")
+
+
+def test_unseen_id_returns_false():
+    assert cache_module.is_seen(12345) is False
+
+
+def test_mark_seen_makes_id_seen():
+    cache_module.mark_seen(12345)
+    assert cache_module.is_seen(12345) is True
+
+
+def test_multiple_ids_stored_independently():
+    cache_module.mark_seen(1)
+    cache_module.mark_seen(2)
+    cache_module.mark_seen(3)
+    assert cache_module.is_seen(1)
+    assert cache_module.is_seen(2)
+    assert cache_module.is_seen(3)
+    assert not cache_module.is_seen(4)
+
+
+def test_persists_to_disk_between_calls():
+    """
+    is_seen() and mark_seen() each load from disk independently.
+    This verifies the persist-on-write / load-on-read contract
+    (simulating what happens across separate function calls in the bot loop).
+    """
+    cache_module.mark_seen(999)
+    assert cache_module.is_seen(999) is True
+
+
+def test_missing_cache_file_handled_gracefully(tmp_path, monkeypatch):
+    monkeypatch.setattr(cache_module, "CACHE_FILE", tmp_path / "nonexistent.json")
+    assert cache_module.is_seen(42) is False
+
+
+def test_mark_seen_is_idempotent():
+    cache_module.mark_seen(7)
+    cache_module.mark_seen(7)
+    cache_module.mark_seen(7)
+    assert cache_module.is_seen(7) is True