feat: adds crawl resource cache

tests/test_crawler.py

@@ -1,7 +1,9 @@
+import gzip
 from datetime import datetime, timezone
 
-from app.models import CrawlRun, CrawlRunEmployeeChange, Employee
-from app.services.crawler import _mark_dismissed, _upsert_employee
+from app.models import CrawlRun, CrawlRunEmployeeChange, Employee, EmployeeSnapshot, ParseResourceCache
+from app.services.crawler import _checksum, _mark_dismissed, _upsert_employee
+from app.services.resource_cache import ResourceCache
 
 
 class FakeResponse:
@@ -17,6 +19,34 @@ class FakeSession:
         return FakeResponse(self.statuses[url])
 
 
+class ConditionalResponse:
+    def __init__(self, status_code, text="", headers=None):
+        self.status_code = status_code
+        self._text = text
+        self.headers = headers or {}
+        self.text_read = False
+
+    @property
+    def text(self):
+        self.text_read = True
+        return self._text
+
+    def raise_for_status(self):
+        return None
+
+
+class ConditionalSession:
+    def __init__(self):
+        self.requests = []
+        self.not_modified_response = ConditionalResponse(304)
+
+    def get(self, url, **kwargs):
+        self.requests.append((url, kwargs))
+        if kwargs["headers"].get("If-None-Match") == '"cached"':
+            return self.not_modified_response
+        return ConditionalResponse(200, "fresh", {"ETag": '"fresh"'})
+
+
 def test_mark_dismissed_records_missing_source_when_profile_is_available(db_session):
     run = CrawlRun(source_url="https://miem.hse.ru/persons", status="running")
     db_session.add(run)
@@ -111,3 +141,86 @@ def test_upsert_employee_increments_new_count_and_records_change_for_new_employe
     change = db_session.query(CrawlRunEmployeeChange).one()
     assert change.change_type == "new"
     assert change.full_name == "New Person"
+
+
+def test_resource_cache_uses_etag_and_reuses_cached_body_on_304(db_session):
+    db_session.add(
+        ParseResourceCache(
+            profile_key="staff:cached",
+            resource_key="main-html",
+            method="GET",
+            url="https://www.hse.ru/staff/cached",
+            request_fingerprint="020d59db7b358d9023d0f185bcbf5a9c085d3cf2bf91d92d48eee9147e8d0f01",
+            etag='"cached"',
+            body_hash="cached-hash",
+            body_snapshot=gzip.compress("cached body".encode("utf-8")),
+            parser_version="0.6.0",
+        )
+    )
+    db_session.commit()
+    session = ConditionalSession()
+
+    result = ResourceCache(db_session).fetch_text(
+        session,
+        profile_key="staff:cached",
+        resource_key="main-html",
+        method="GET",
+        url="https://www.hse.ru/staff/cached",
+        headers={"User-Agent": "test"},
+        timeout=10,
+    )
+
+    assert session.requests[0][1]["headers"]["If-None-Match"] == '"cached"'
+    assert result.text == "cached body"
+    assert result.from_cache is True
+    assert session.not_modified_response.text_read is False
+
+
+def test_upsert_employee_skips_snapshot_when_checksum_is_unchanged(db_session):
+    first_run = CrawlRun(source_url="https://miem.hse.ru/persons", status="running")
+    second_run = CrawlRun(source_url="https://miem.hse.ru/persons", status="running")
+    db_session.add_all([first_run, second_run])
+    db_session.commit()
+
+    _, first_changed = _upsert_employee(db_session, first_run, _parsed_employee("same"))
+    _, second_changed = _upsert_employee(db_session, second_run, _parsed_employee("same"))
+    db_session.commit()
+
+    assert first_changed is True
+    assert second_changed is False
+    assert db_session.query(EmployeeSnapshot).count() == 1
+
+
+def test_checksum_changes_when_widget_data_changes():
+    base = _parsed_employee("widgets")
+    changed = _parsed_employee("widgets")
+    changed["sections"] = [
+        {
+            "type": "publications",
+            "publications": [{"id": "1", "title": "New publication"}],
+        }
+    ]
+
+    assert _checksum(base) != _checksum(changed)
+
+
+def test_checksum_ignores_date_dependent_experience_text():
+    first = _parsed_employee("experience")
+    second = _parsed_employee("experience")
+    first["sections"] = [{"raw_text": "Стаж работы в НИУ ВШЭ: 5 лет"}]
+    second["sections"] = [{"raw_text": "Стаж работы в НИУ ВШЭ: 6 лет"}]
+
+    assert _checksum(first) == _checksum(second)
+
+
+def _parsed_employee(profile_id: str) -> dict:
+    return {
+        "source_url": f"https://www.hse.ru/staff/{profile_id}",
+        "profile_type": "staff",
+        "profile_id": profile_id,
+        "full_name": "Same Person",
+        "tabs": [],
+        "sections": [],
+        "parser_version": "0.6.0",
+        "_html": "<html></html>",
+    }