fix(export): v4.7.2 contenu des documents absent des exports MD/HTML/PDF

Le service d'export ne lisait que les pages content_format='blocks'. Les docs stockees autrement sortaient avec le seul titre: - content_format='file' (.md/code uploades): content=JSON meta, le vrai texte est sur disque (/data/uploads/workspace_*) -> n'etait jamais lu. - content_format='markdown': HTML/PDF enveloppait chaque ligne en <p> (headings et listes aplatis). Resolution de la vraie source pour les 3 formats (app/services/export.py): - lit le fichier upload sur disque pour les pages file (repertoire via FLOWDECK_DATA_DIR, defaut /data), - rend les pages markdown / fichiers .md en blocs (headings, listes, code, quote, todo) pour un HTML/PDF riche, - fichiers texte non-markdown -> bloc de code, - binaires (PDF/images) ignores. 195/195 tests (5 nouveaux v4.7.2). Verifie en reel via HTTP sur README.md et l'arborescence Base de Connaissances (contenu complet dans les 3 formats).
2026-09-03 01:29:35 -04:00
parent 5390a6ceab
commit fa97f07ec8
6 changed files with 417 additions and 21 deletions
@@ -3024,4 +3024,146 @@ def test_v470_export_site_zip(client):
 def test_v470_export_404(client):
    """Export endpoints return 404 for missing pages."""
    resp = client.get("/api/export/markdown/999999")
-    assert resp.status_code == 404
+    assert resp.status_code == 404
+
+
+# ── v4.7.2: Export resolves file & markdown page content (not just title) ──
+# Tested at the service level: the export HTTP endpoints run behind an in-memory
+# rate limiter whose store persists across the whole test process, so dozens of
+# additional HTTP hits at the end of the suite trip 429. These assert on the
+# service functions directly, which is where the content-resolution lives.
+
+def _make_src_page(raw_md=None, file_info=None, title="Src Page", parent_id=None):
+    """Insert a user + page storing raw markdown OR file metadata.
+
+    file_info = (rel_path_under_data_dir, mime). The real file is written to a
+    temp data dir whose path is exposed through ``FLOWDECK_DATA_DIR``.
+    """
+    import uuid
+    import json as _json
+    from app.db import get_conn
+    login = "v472_" + uuid.uuid4().hex[:10]
+    with get_conn() as conn:
+        conn.execute("INSERT INTO users (login, full_name, email) VALUES (?, 'V472', ?)",
+                     (login, login + "@t.com"))
+        uid = conn.execute("SELECT id FROM users WHERE login=?", (login,)).fetchone()["id"]
+        if file_info:
+            rel, mime = file_info
+            payload = _json.dumps({"file_path": rel, "mime_type": mime, "size": 100})
+            fmt = "file"
+        else:
+            payload = raw_md
+            fmt = "markdown"
+        cur = conn.execute(
+            "INSERT INTO pages (workspace, title, content, content_format, parent_id) "
+            "VALUES (?, ?, ?, ?, ?)",
+            (login, title, payload, fmt, parent_id),
+        )
+        pid = cur.lastrowid
+        conn.commit()
+    return pid, uid
+
+
+def _cleanup_src(pid, uid):
+    from app.db import get_conn
+    with get_conn() as conn:
+        conn.execute("DELETE FROM pages WHERE parent_id=? OR id=?", (pid, pid))
+        conn.execute("DELETE FROM users WHERE id=?", (uid,))
+        conn.commit()
+
+
+def _load(pid):
+    from app.db import get_conn
+    with get_conn() as conn:
+        return dict(conn.execute("SELECT * FROM pages WHERE id=?", (pid,)).fetchone())
+
+
+def test_v472_markdown_sourced_page_exports_body(client):
+    """content_format='markdown' page exports its body, not just the title."""
+    from app.services.export import page_to_markdown
+    raw = "# Intro\n\nCeci est le contenu réel de la page.\n\n- point un\n- point deux\n"
+    pid, uid = _make_src_page(raw_md=raw, title="Page MD")
+    try:
+        md = page_to_markdown(_load(pid))
+        assert "# Page MD" in md
+        assert "Ceci est le contenu réel de la page." in md
+        assert "point un" in md
+    finally:
+        _cleanup_src(pid, uid)
+
+
+def test_v472_markdown_sourced_page_renders_headings_to_html(client):
+    """Raw-markdown page renders headings/lists in HTML (not line-wrapped)."""
+    from app.services.export import page_to_standalone_html
+    raw = "# Titre Principal\n\nParagraphe de contenu.\n\n## Sous section\n\n- a\n- b\n"
+    pid, uid = _make_src_page(raw_md=raw, title="Page HTML")
+    try:
+        body = page_to_standalone_html(_load(pid), include_children=False)
+        assert "<h1" in body and "Titre Principal" in body
+        assert "<h2" in body and "Sous section" in body
+        assert "<li>" in body and "Paragraphe de contenu" in body
+    finally:
+        _cleanup_src(pid, uid)
+
+
+def test_v472_file_page_exports_uploaded_content(client, monkeypatch, tmp_path):
+    """Uploaded markdown file page exports its real disk content (v4.7.2 fix)."""
+    from app.services.export import page_to_markdown, page_to_standalone_html, page_to_pdf_bytes
+    monkeypatch.setenv("FLOWDECK_DATA_DIR", str(tmp_path))
+    rel = "uploads/workspace_1/note.md"
+    disk = tmp_path / rel
+    disk.parent.mkdir(parents=True, exist_ok=True)
+    disk.write_text("# Note technique\n\ncontenu du fichier sur disque\n", encoding="utf-8")
+
+    pid, uid = _make_src_page(file_info=(rel, "text/markdown"), title="note.md")
+    try:
+        md = page_to_markdown(_load(pid), include_children=False)
+        assert "# note.md" in md
+        assert "Note technique" in md
+        assert "contenu du fichier sur disque" in md
+
+        html = page_to_standalone_html(_load(pid), include_children=False)
+        assert "Note technique" in html
+        assert "contenu du fichier sur disque" in html
+
+        pdf = page_to_pdf_bytes(_load(pid))
+        assert pdf[:5] == b"%PDF-"
+    finally:
+        _cleanup_src(pid, uid)
+
+
+def test_v472_code_file_page_exported_as_code(client, monkeypatch, tmp_path):
+    """A non-markdown text file page exports its content, not blank."""
+    from app.services.export import page_to_markdown, page_to_standalone_html
+    monkeypatch.setenv("FLOWDECK_DATA_DIR", str(tmp_path))
+    rel = "uploads/workspace_1/app.py"
+    disk = tmp_path / rel
+    disk.parent.mkdir(parents=True, exist_ok=True)
+    disk.write_text("def hello():\n    return 'world'\n", encoding="utf-8")
+
+    pid, uid = _make_src_page(file_info=(rel, "text/x-python"), title="app.py")
+    try:
+        md = page_to_markdown(_load(pid), include_children=False)
+        assert "def hello():" in md and "world" in md
+        html = page_to_standalone_html(_load(pid), include_children=False)
+        assert "def hello():" in html
+    finally:
+        _cleanup_src(pid, uid)
+
+
+def test_v472_binary_file_page_not_exported(client, monkeypatch, tmp_path):
+    """Non-textual files (e.g. PDF uploads) export only the title, no garbage."""
+    from app.services.export import page_to_markdown
+    monkeypatch.setenv("FLOWDECK_DATA_DIR", str(tmp_path))
+    rel = "uploads/workspace_1/manual.pdf"
+    disk = tmp_path / rel
+    disk.parent.mkdir(parents=True, exist_ok=True)
+    disk.write_bytes(b"%PDF-1.4\nfake binary content")
+
+    pid, uid = _make_src_page(file_info=(rel, "application/pdf"), title="manual.pdf")
+    try:
+        md = page_to_markdown(_load(pid), include_children=False)
+        assert "# manual.pdf" in md
+        assert "fake binary" not in md  # never dump binary into markdown
+    finally:
+        _cleanup_src(pid, uid)