extending abs_path in db and test coverage

2025-08-30 13:06:16 +02:00
parent f899439f6a
commit 8ad52563fa
3 changed files with 103 additions and 7 deletions
--- a/tests/test_cached_route.py
+++ b/tests/test_cached_route.py
@@ -0,0 +1,53 @@
+import os
+import tempfile
+from web.app import app
+
+
+def test_cached_route_serves_file(monkeypatch):
+    # Create a temporary file in the configured cache dir
+    cache_dir = os.path.abspath(os.path.join(
+        os.path.dirname(__file__), '..', 'cache'))
+    os.makedirs(cache_dir, exist_ok=True)
+    fd, tmp_path = tempfile.mkstemp(
+        prefix='test_cached_', suffix='.html', dir=cache_dir)
+    os.close(fd)
+    with open(tmp_path, 'w', encoding='utf-8') as f:
+        f.write('<html><body>cached</body></html>')
+
+    # Fake job record returned by get_job_by_id
+    fake_job = {
+        'id': 'fake123',
+        'job_id': 'fake123',
+        'file_path': os.path.relpath(tmp_path, cache_dir),
+        'file_path_abs': tmp_path,
+    }
+
+    def fake_get_job_by_id(jid):
+        if str(jid) in ('fake123',):
+            return fake_job
+        return {}
+
+    # Patch the symbol imported into web.app
+    monkeypatch.setattr('web.app.get_job_by_id', fake_get_job_by_id)
+
+    # Request route
+    client = app.test_client()
+    res = client.get('/cached/fake123')
+    assert res.status_code == 200
+    assert b'cached' in res.data
+
+    # Cleanup
+    try:
+        os.remove(tmp_path)
+    except Exception:
+        pass
+
+
+def test_cached_route_missing(monkeypatch):
+    def fake_get_job_by_id(jid):
+        return {}
+
+    monkeypatch.setattr('web.app.get_job_by_id', fake_get_job_by_id)
+    client = app.test_client()
+    res = client.get('/cached/nope')
+    assert res.status_code == 404
--- a/tests/test_cachedpage_abs_path.py
+++ b/tests/test_cachedpage_abs_path.py
@@ -0,0 +1,27 @@
+import os
+from web.db import CachedPage
+from web.utils import get_cache_dir
+
+
+def test_cachedpage_abs_path(tmp_path, monkeypatch):
+    # Create a fake cache dir and monkeypatch get_cache_dir
+    fake_cache = tmp_path / 'cache'
+    fake_cache.mkdir()
+    monkeypatch.setenv('PYTHONIOENCODING', 'utf-8')
+
+    # Patch the symbol used by CachedPage.abs_path (imported into web.db)
+    monkeypatch.setattr('web.db.get_cache_dir', lambda: str(fake_cache))
+
+    # Create a CachedPage instance and set file_path attribute
+    cp = CachedPage()
+    setattr(cp, 'file_path', 'subdir/test.html')
+
+    # Ensure the computed absolute path joins the fake cache dir
+    expected = os.path.join(os.path.abspath(
+        str(fake_cache)), 'subdir/test.html')
+    assert cp.abs_path == expected
+
+    # When file_path is falsy, abs_path should be None
+    cp2 = CachedPage()
+    setattr(cp2, 'file_path', None)
+    assert cp2.abs_path is None
--- a/web/db.py
+++ b/web/db.py
@@ -117,6 +117,18 @@ class CachedPage(Base):

    listing = relationship("JobListing", back_populates="cached_pages")

+    @property
+    def abs_path(self) -> Optional[str]:
+        """Return the absolute filesystem path for this cached page.
+
+        The DB stores `file_path` relative to the configured cache dir. This
+        helper centralizes resolution so callers can use `cached_page.abs_path`.
+        """
+        fp = getattr(self, 'file_path', None)
+        if not fp:
+            return None
+        return os.path.join(os.path.abspath(get_cache_dir()), fp)
+

 class UserInteraction(Base):
    __tablename__ = "user_interactions"
@@ -323,16 +335,18 @@ def db_get_all_cached_pages() -> List[Dict[str, Any]]:
    with _ensure_session() as session:
        rows = session.execute(text(
            "SELECT file_path, url_guess, last_modified, size_bytes, job_id FROM cached_pages")).fetchall()
-        return [
-            {
-                "file_path": row[0],
+        out = []
+        for row in rows:
+            fp = row[0]
+            out.append({
+                "file_path": fp,
+                "file_path_abs": db_get_cached_abs_path(fp) if fp else None,
                "url_guess": row[1],
                "last_modified": row[2],
                "size_bytes": row[3],
                "job_id": row[4],
-            }
-            for row in rows
-        ]
+            })
+        return out


 def db_get_cache_url(url: str):
@@ -346,8 +360,10 @@ def db_get_cache_url(url: str):
            "SELECT file_path, url_guess, last_modified, size_bytes, job_id FROM cached_pages WHERE url_guess = :u"), {"u": url}).fetchone()
        if not row:
            return None
+        fp = row[0]
        return {
-            "file_path": row[0],
+            "file_path": fp,
+            "file_path_abs": db_get_cached_abs_path(fp) if fp else None,
            "url_guess": row[1],
            "last_modified": row[2],
            "size_bytes": row[3],