Initial test code

01 Sync Docs.bash

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+rsync -r root@10.11.99.1:/home/root/.local/share/remarkable/xochitl .

02 Parse Metadata.py

@@ -0,0 +1,42 @@
+
+
+from pathlib import Path
+import json
+
+
+## Parameter
+
+IN_FOLDER = './Library/'
+
+
+
+## Helper Functions
+def list_files_pathlib(path=Path('.')):
+    files = []
+    for entry in path.iterdir():
+        if entry.is_file():
+            files.append(entry)
+        elif entry.is_dir():
+            files.extend(list_files_pathlib(entry))
+    return files
+
+
+## File and content parsing
+
+
+
+
+
+## Script
+
+# Specify the directory path you want to start from
+
+file_list = list_files_pathlib(Path(IN_FOLDER))
+print(len(file_list))
+
+meta_data_files = [i for i in file_list if i.suffix == '.metadata']
+
+data_files = [i for i in file_list if i.suffix == '.rm']
+
+
+print(meta_data_files)

0a test.ipynb

@@ -0,0 +1,166 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "437f8866",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "import json\n",
+    "import hashlib\n",
+    "\n",
+    "## Parameter\n",
+    "\n",
+    "IN_FOLDER = './Library/'\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1e0f01fd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Helper Functions\n",
+    "def list_files_pathlib(path=Path('.')):\n",
+    "    files = []\n",
+    "    for entry in path.iterdir():\n",
+    "        if entry.is_file():\n",
+    "            files.append(entry)\n",
+    "        elif entry.is_dir():\n",
+    "            files.extend(list_files_pathlib(entry))\n",
+    "    return files\n",
+    "\n",
+    "# Specify the directory path you want to start from\n",
+    "\n",
+    "file_list = list_files_pathlib(Path(IN_FOLDER))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fe452ca8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_files = [i for i in file_list if i.suffix == '.rm']\n",
+    "meta_data_files = [i for i in file_list if i.suffix == '.metadata']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "73c6e17a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "meta_data_files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0a3b5926",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "[i for i in file_list if '03ec4477-8df9-49c1-96e4-dfca75f32623' in str(i)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b04fdfa2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## scripts to build document structure\n",
+    "\n",
+    "\n",
+    "## Todo: check which documents needs updates via hashes\n",
+    "\n",
+    "\n",
+    "def parse_document_data(filename):\n",
+    "    data = json.load(open(filename))\n",
+    "    page_list = data['cPages']['pages']\n",
+    "    pages_data = []\n",
+    "    for element in page_list:\n",
+    "        page_data = {\n",
+    "            'page_id': element['id'],\n",
+    "            'filename': filename.parent / filename.stem / element['id'],  # construct path to subpages,\n",
+    "        }\n",
+    "        pages_data.append(page_data)\n",
+    "    return pages_data\n",
+    "\n",
+    "\n",
+    "\n",
+    "def parse_metadata(filename):\n",
+    "    data = json.load(open(filename))\n",
+    "    content_filename = filename.parent / str(filename.stem + '.content')\n",
+    "    return {\n",
+    "       'last_modified': data['lastModified'],\n",
+    "       'document_name': data['visibleName'],\n",
+    "       'document_type': data['type'],\n",
+    "       'parent_folder': data['parent'],\n",
+    "       'page_ids': parse_document_data(content_filename)\n",
+    "    }\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb699ffa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# parse_metadata('fc2e4b57-6ce4-48ae-8452-b6d7873967aa.metadata')\n",
+    "\n",
+    "test = parse_metadata(meta_data_files[12])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1deb665",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "31e993f7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Py2025",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}