feat: LibriVox/NASA/Internet Archive fetchers (+ deferred stubs)

Per sub-project-2 plan Task 9 / spec §6.4. Three keyless first-ship fetchers
parse documented JSON APIs via an injected HttpClient; license/attribution go
through tools.licensing; NASA third-party + IA no-license cases are flagged in
notes for review. musopen/fma/freesound are explicit deferred stubs raising
NotImplementedError; freesound documents FREESOUND_API_TOKEN (secret, env-only).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

tests/test_fetchers.py

@@ -0,0 +1,181 @@
+import json
+
+import pytest
+
+from tools.http import HttpClient
+from tools.ingest.internet_archive import InternetArchiveFetcher
+from tools.ingest.librivox import LibriVoxFetcher
+from tools.ingest.nasa import NasaFetcher
+
+
+class _Resp:
+    def __init__(self, data: bytes):
+        self._data = data
+
+    def read(self):
+        return self._data
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, *a):
+        return False
+
+
+def fake_opener(mapping):
+    """Dispatch a urllib Request to a canned payload by URL substring."""
+
+    def opener(req, timeout=None):
+        url = req.full_url
+        for key, payload in mapping.items():
+            if key in url:
+                if isinstance(payload, (bytes, bytearray)):
+                    return _Resp(bytes(payload))
+                return _Resp(json.dumps(payload).encode("utf-8"))
+        raise AssertionError(f"unexpected url: {url}")
+
+    return opener
+
+
+def test_librivox_fetcher():
+    payload = {
+        "books": [
+            {
+                "id": "123",
+                "title": "Meditations",
+                "url_librivox": "https://librivox.org/meditations/",
+                "url_zip_file": "https://archive.org/download/meditations/meditations_mp3.zip",
+                "authors": [{"first_name": "Marcus", "last_name": "Aurelius"}],
+                "description": "Stoic philosophy.",
+            }
+        ]
+    }
+    client = HttpClient(opener=fake_opener({"librivox.org/api": payload}))
+    cands = LibriVoxFetcher(client).search("medit", limit=5)
+    c = cands[0]
+    assert c.source_archive == "librivox"
+    assert c.license == "public_domain" and c.attribution == ""
+    assert c.suggested_id == "librivox-meditations"
+    assert c.media_url.endswith(".zip")
+    assert c.media_ext == "zip"
+    assert "Aurelius" in c.description
+
+
+def test_nasa_fetcher():
+    search_payload = {
+        "collection": {
+            "items": [
+                {
+                    "data": [
+                        {
+                            "nasa_id": "as08-14-2383",
+                            "title": "Earthrise",
+                            "description": "View of Earth from the Moon",
+                            "media_type": "video",
+                        }
+                    ],
+                    "href": "https://images-assets.nasa.gov/video/as08-14-2383/collection.json",
+                }
+            ]
+        }
+    }
+    asset_payload = [
+        "https://images-assets.nasa.gov/video/as08-14-2383/as08-14-2383~orig.mp4",
+        "https://images-assets.nasa.gov/video/as08-14-2383/as08-14-2383~thumb.jpg",
+    ]
+    client = HttpClient(
+        opener=fake_opener(
+            {
+                "images-api.nasa.gov/search": search_payload,
+                "collection.json": asset_payload,
+            }
+        )
+    )
+    c = NasaFetcher(client).search("earth", limit=3)[0]
+    assert c.suggested_id == "nasa-as08-14-2383"
+    assert c.license == "public_domain" and c.attribution == ""
+    assert c.media_url.endswith("orig.mp4")
+    assert c.media_ext == "mp4"
+    assert "Earth" in c.description
+
+
+def test_internet_archive_cc_by():
+    meta_payload = {
+        "metadata": {
+            "identifier": "earthrise",
+            "title": "Earthrise",
+            "licenseurl": "http://creativecommons.org/licenses/by/4.0/",
+            "creator": "NASA",
+            "description": "Apollo 8 footage.",
+        },
+        "files": [
+            {"name": "earthrise.mp4", "format": "h.264", "source": "original"},
+            {"name": "earthrise.png", "format": "PNG", "source": "derivative"},
+        ],
+        "server": "ia800100.us.archive.org",
+        "dir": "/12/items/earthrise",
+    }
+    client = HttpClient(opener=fake_opener({"archive.org/metadata/earthrise": meta_payload}))
+    c = InternetArchiveFetcher(client).resolve("earthrise")
+    assert c.suggested_id == "ia-earthrise"
+    assert c.license == "cc_by" and "NASA" in c.attribution
+    assert c.media_url == "https://ia800100.us.archive.org/12/items/earthrise/earthrise.mp4"
+    assert c.media_ext == "mp4"
+    assert c.source_url == "https://archive.org/details/earthrise"
+
+
+def test_internet_archive_no_license_assumed_public_domain_and_flagged():
+    meta_payload = {
+        "metadata": {"identifier": "oldfilm", "title": "Old Film"},
+        "files": [{"name": "oldfilm.mp4", "source": "original"}],
+        "server": "ia.example.org",
+        "dir": "/x/items/oldfilm",
+    }
+    client = HttpClient(opener=fake_opener({"archive.org/metadata/oldfilm": meta_payload}))
+    c = InternetArchiveFetcher(client).resolve("oldfilm")
+    assert c.license == "public_domain"
+    assert "verify" in c.description.lower()
+
+
+def test_internet_archive_search_resolves_each_hit():
+    search_payload = {"response": {"docs": [{"identifier": "earthrise"}]}}
+    meta_payload = {
+        "metadata": {
+            "identifier": "earthrise",
+            "title": "Earthrise",
+            "licenseurl": "https://creativecommons.org/publicdomain/mark/1.0/",
+        },
+        "files": [{"name": "earthrise.mp4", "source": "original"}],
+        "server": "ia.example.org",
+        "dir": "/x",
+    }
+    client = HttpClient(
+        opener=fake_opener(
+            {
+                "advancedsearch.php": search_payload,
+                "archive.org/metadata/earthrise": meta_payload,
+            }
+        )
+    )
+    cands = InternetArchiveFetcher(client).search("earthrise", limit=5)
+    assert [c.suggested_id for c in cands] == ["ia-earthrise"]
+    assert cands[0].license == "public_domain"
+
+
+def test_deferred_stubs_raise_not_implemented():
+    from tools.ingest.fma import FmaFetcher
+    from tools.ingest.freesound import FreesoundFetcher
+    from tools.ingest.musopen import MusopenFetcher
+
+    with pytest.raises(NotImplementedError):
+        MusopenFetcher(None).search("x", limit=1)
+    with pytest.raises(NotImplementedError):
+        FmaFetcher(None).search("x", limit=1)
+    with pytest.raises(NotImplementedError):
+        FreesoundFetcher(None).search("x", limit=1)
+
+
+def test_fetchers_expose_archive_label():
+    assert LibriVoxFetcher(None).archive == "librivox"
+    assert NasaFetcher(None).archive == "nasa"
+    assert InternetArchiveFetcher(None).archive == "internet_archive"