feat: add tag blacklisting via --exclude-tags (#2352)

* Initial plan

* feat: add tag blacklisting support (--exclude-tags CLI flag, web UI, docs, tests)

Co-authored-by: soxoj <31013580+soxoj@users.noreply.github.com>
Agent-Logs-Url: https://github.com/soxoj/maigret/sessions/1a656af2-36bf-494f-9f03-1b5340f0357c

* fix: correct tag cloud label to match click-cycle interaction

Co-authored-by: soxoj <31013580+soxoj@users.noreply.github.com>
Agent-Logs-Url: https://github.com/soxoj/maigret/sessions/1a656af2-36bf-494f-9f03-1b5340f0357c

* feat: add all country tags to web interface tag cloud

Co-authored-by: soxoj <31013580+soxoj@users.noreply.github.com>
Agent-Logs-Url: https://github.com/soxoj/maigret/sessions/7e184b24-ff26-48fd-8a93-aea12b0a8d7b

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: soxoj <31013580+soxoj@users.noreply.github.com>

tests/test_cli.py

@@ -36,6 +36,7 @@ DEFAULT_ARGS: Dict[str, Any] = {
     'site_list': [],
     'stats': False,
     'tags': '',
+    'exclude_tags': '',
     'timeout': 30,
     'tor_proxy': 'socks5://127.0.0.1:9050',
     'i2p_proxy': 'http://127.0.0.1:4444',
@@ -105,3 +106,34 @@ def test_args_multiple_sites(argparser):
 
     for arg in vars(args):
         assert getattr(args, arg) == want_args[arg]
+
+
+def test_args_exclude_tags(argparser):
+    args = argparser.parse_args('--exclude-tags porn,dating username'.split())
+
+    want_args = dict(DEFAULT_ARGS)
+    want_args.update(
+        {
+            'exclude_tags': 'porn,dating',
+            'username': ['username'],
+        }
+    )
+
+    for arg in vars(args):
+        assert getattr(args, arg) == want_args[arg]
+
+
+def test_args_tags_with_exclude_tags(argparser):
+    args = argparser.parse_args('--tags coding --exclude-tags porn username'.split())
+
+    want_args = dict(DEFAULT_ARGS)
+    want_args.update(
+        {
+            'tags': 'coding',
+            'exclude_tags': 'porn',
+            'username': ['username'],
+        }
+    )
+
+    for arg in vars(args):
+        assert getattr(args, arg) == want_args[arg]

tests/test_sites.py

@@ -182,6 +182,54 @@ def test_ranked_sites_dict_id_type():
     assert len(db.ranked_sites_dict(id_type='gaia_id')) == 1
 
 
+def test_ranked_sites_dict_excluded_tags():
+    db = MaigretDatabase()
+    db.update_site(MaigretSite('3', {'alexaRank': 1000, 'engine': 'ucoz'}))
+    db.update_site(MaigretSite('1', {'alexaRank': 2, 'tags': ['forum']}))
+    db.update_site(MaigretSite('2', {'alexaRank': 10, 'tags': ['ru', 'forum']}))
+
+    # excluding by tag
+    assert list(db.ranked_sites_dict(excluded_tags=['ru']).keys()) == ['1', '3']
+    assert list(db.ranked_sites_dict(excluded_tags=['forum']).keys()) == ['3']
+
+    # excluding by engine
+    assert list(db.ranked_sites_dict(excluded_tags=['ucoz']).keys()) == ['1', '2']
+
+    # combining include and exclude tags
+    assert list(db.ranked_sites_dict(tags=['forum'], excluded_tags=['ru']).keys()) == ['1']
+
+    # excluding non-existent tag has no effect
+    assert list(db.ranked_sites_dict(excluded_tags=['nonexistent']).keys()) == ['1', '2', '3']
+
+    # exclude all
+    assert list(db.ranked_sites_dict(excluded_tags=['forum', 'ucoz']).keys()) == []
+
+
+def test_ranked_sites_dict_excluded_tags_with_top():
+    """Excluded tags should also prevent mirrors from being included."""
+    db = MaigretDatabase()
+    db.update_site(
+        MaigretSite('Parent', {'alexaRank': 1, 'tags': ['forum'], 'type': 'username'})
+    )
+    db.update_site(
+        MaigretSite('Mirror', {'alexaRank': 999999, 'source': 'Parent', 'tags': ['forum'], 'type': 'username'})
+    )
+    db.update_site(
+        MaigretSite('Other', {'alexaRank': 2, 'tags': ['coding'], 'type': 'username'})
+    )
+
+    # Without exclusion, mirror should be included
+    result = db.ranked_sites_dict(top=1, id_type='username')
+    assert 'Parent' in result
+    assert 'Mirror' in result
+
+    # With exclusion of 'forum', both Parent and Mirror should be excluded
+    result = db.ranked_sites_dict(top=2, excluded_tags=['forum'], id_type='username')
+    assert 'Parent' not in result
+    assert 'Mirror' not in result
+    assert 'Other' in result
+
+
 def test_ranked_sites_dict_mirrors_disabled_parent():
     """Mirror is included when parent ranks in top N but parent is disabled."""
     db = MaigretDatabase()