feat(import): v5.6.0 unified data import (phases 0-5)

- unified importer framework (app/services/importers/): normalized model, registry, common pipeline (hierarchy, attachments, collections, dedup), async jobs, dry-run preview, column->type mapping - Phase 1: Obsidian, Notion, Logseq/Roam, HTML (Apple Notes/Bear/Ulysses/ OneNote), Google Keep, generic Markdown - Phase 2: typed CSV/TSV, Excel (openpyxl), generic JSON - Phase 3: Word .docx (python-docx), PDF (pypdf), HTML folders - Phase 4: Raindrop, Pocket, Readwise, Shaarli, Netscape bookmarks, .ics, OPML, Standard Notes, Gitea/GitHub issues (+labels/milestones) - Phase 5: incremental re-sync (skip/update/duplicate), partial-error resume, forge repo files, URL web clipper (SSRF guard), batch multi-file + UI queue, Notion relation resolution, exportable JSON reports - /import wizard, API /api/import/*, migration 9 (import_items, import_jobs) - fix: property values stored by property id (correct DB view rendering) - deps: openpyxl, beautifulsoup4, PyYAML, python-docx, pypdf - 43 import tests; full suite 491 green; ruff clean - bump version 5.11.5
2026-09-13 10:43:20 -04:00
parent d986959927
commit 3b00cbc371
32 changed files with 5275 additions and 58 deletions
@@ -0,0 +1,96 @@
+"""FlowDeck — Standard Notes importer (v5.6.0, Phase 4).
+
+Imports a Standard Notes backup (``.json``): each non-encrypted note becomes a
+FlowDeck page. Encrypted notes are reported as warnings.
+"""
+from __future__ import annotations
+
+import json
+from typing import Any
+
+from app.services.importers.base import (
+    Importer,
+    ImportPage,
+    ImportResult,
+    decode_text,
+    register_importer,
+)
+
+_NOTE_TYPES = ("note", "org.standardnotes.sn", "org.standardnotes.plain-text")
+
+
+def _note_body(content: Any) -> tuple[str, str, bool]:
+    """Return (title, markdown, encrypted)."""
+    if isinstance(content, dict):
+        if content.get("encrypted"):
+            return "", "", True
+        text = content.get("text") or content.get("preview_plain") or ""
+        title = content.get("title") or ""
+        return title, text, False
+    if isinstance(content, str):
+        stripped = content.strip()
+        if stripped.startswith("{"):
+            try:
+                parsed = json.loads(stripped)
+                if isinstance(parsed, dict) and ("encrypted" in parsed or "000" in parsed):
+                    return "", "", True
+                if isinstance(parsed, dict):
+                    return parsed.get("title", ""), parsed.get("text", "") or parsed.get("preview_plain", ""), False
+            except json.JSONDecodeError:
+                pass
+        return "", content, False
+    return "", "", False
+
+
+@register_importer
+class StandardNotesImporter(Importer):
+    source_id = "standard_notes"
+    label = "Standard Notes"
+    description = "Sauvegarde JSON Standard Notes → pages (notes chiffrées ignorées)."
+    extensions = (".json",)
+    order = 39
+
+    def _items(self, data: bytes) -> list[dict] | None:
+        try:
+            obj = json.loads(decode_text(data))
+        except Exception:  # noqa: BLE001
+            return None
+        if isinstance(obj, dict) and isinstance(obj.get("items"), list):
+            return [x for x in obj["items"] if isinstance(x, dict)]
+        return None
+
+    def detect(self, filename: str, data: bytes) -> bool:
+        if not filename.lower().endswith(".json"):
+            return False
+        items = self._items(data)
+        if not items:
+            return False
+        return any("content_type" in it for it in items)
+
+    def parse(self, filename: str, data: bytes) -> ImportResult:
+        result = ImportResult(source=self.source_id)
+        items = self._items(data) or []
+        count = 0
+        for item in items:
+            if item.get("deleted"):
+                continue
+            ctype = str(item.get("content_type", "")).lower()
+            if ctype and not any(t in ctype for t in _NOTE_TYPES):
+                continue
+            title, body, encrypted = _note_body(item.get("content"))
+            if encrypted:
+                result.warn("Note chiffrée ignorée (déchiffrement non pris en charge)")
+                continue
+            if not body.strip():
+                continue
+            if not title:
+                title = next((ln.strip(" #") for ln in body.splitlines() if ln.strip()), "Note")
+            result.pages.append(ImportPage(
+                title=title[:200] or "Note",
+                markdown=body,
+                source_path=item.get("uuid") or filename,
+                external_id=item.get("uuid") or f"{filename}#{count}",
+            ))
+            count += 1
+        result.stats["rows"] = count
+        return result.finalize()