{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "03863eaf-3771-47c3-bf76-dec842375ae0",
   "metadata": {},
   "source": [
    "# Example Layouts\n",
    "\n",
    "**Note, work in progress!**\n",
    "\n",
    "This section provides useful layout specifications."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "41a72bcd-9e6d-4330-9f41-fd0d60ab545e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from h5rdmtoolbox import layout\n",
    "from h5rdmtoolbox.database import hdfdb\n",
    "import h5rdmtoolbox as h5tbx"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d34a1dc2-dff1-4b04-a728-4457e73b9c71",
   "metadata": {},
   "source": [
    "## All string dataset must be one-dimensional"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "2a17a625-ca82-4db6-8c9e-2ad9f46f00e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "lay = layout.Layout()\n",
    "string_dataset_1D = lay.add(\n",
    "    hdfdb.FileDB.find,\n",
    "    flt={'$ndim': {'$eq': 1},\n",
    "         '$dtype': {'$regex': '^(?!S)*'}},\n",
    "    recursive=True,\n",
    "    objfilter='dataset',\n",
    "    description='String dataset must be 1D',\n",
    "    n={'$gt': 0}\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "83a7959a-d879-4f7e-9981-063ccf5ca354",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "int32\n",
      "|S5\n"
     ]
    }
   ],
   "source": [
    "with h5tbx.File() as h5:\n",
    "    dss = h5.create_string_dataset('a string ds', data=['one', 'two', 'three'])\n",
    "    dss = h5.create_string_dataset('grp/a string ds', data=['one', 'two', 'three'])\n",
    "    dsn = h5.create_dataset('a', data=4)\n",
    "    print(dsn.dtype)\n",
    "    print(dss.dtype)\n",
    "    hdf_filename = h5.hdf_filename"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "fc671941-728f-44c5-8f7d-5399413086ac",
   "metadata": {},
   "outputs": [],
   "source": [
    "res = lay.validate(hdf_filename)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "591ba3e5-015c-46d1-8c46-ecf66f3f1232",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Summary of layout validation\n",
      "+--------------------------------------+--------+--------------------+---------------------------+---------------+---------------+-----------------------------------------+\n",
      "| id                                   |   flag | flag description   | description               | target_type   | target_name   | func                                    |\n",
      "|--------------------------------------+--------+--------------------+---------------------------+---------------+---------------+-----------------------------------------|\n",
      "| 39344777-7032-4f34-9f1f-ad14989430f5 |      1 | SUCCESSFUL         | String dataset must be 1D | Group         | tmp0.hdf      | h5rdmtoolbox.database.hdfdb.filedb.find |\n",
      "+--------------------------------------+--------+--------------------+---------------------------+---------------+---------------+-----------------------------------------+\n",
      "--> Layout is valid\n"
     ]
    }
   ],
   "source": [
    "res.print_summary(exclude_keys=('called', 'kwargs'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "3c2e2739-d5b8-449a-8553-dd0ed6bfe7e4",
   "metadata": {},
   "outputs": [],
   "source": [
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "4c43c5dc-7445-45be-bed1-59eee4fc7c6d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<re.Match object; span=(0, 4), match='M123'>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "re.search('^(?!S).*', 'M123')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6d8709ac-3676-4a56-891a-832deca11db4",
   "metadata": {},
   "source": [
    "## Defining RDF specifications\n",
    "\n",
    "All dataset must have the attribute units, which shall be semantically described by `http://w3id.org/nfdi4ing/metadata4ing#hasUnit`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b6bda83f-582e-48d0-a9dc-7b8fc0576520",
   "metadata": {},
   "outputs": [],
   "source": [
    "rdf_lay = layout.Layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "a98ad451-b361-4f62-a24e-bc6840f9ae2f",
   "metadata": {},
   "outputs": [],
   "source": [
    "is_dataset = rdf_lay.add(\n",
    "    hdfdb.FileDB.find,\n",
    "    flt={'units': {'$exists': True}},\n",
    "    recursive=True,\n",
    "    objfilter='dataset',\n",
    "    description='String dataset must be 1D',\n",
    "    n={'$gt': 0}\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "edbd9a8f-03a0-41e8-b954-a97b1b5d180c",
   "metadata": {},
   "outputs": [],
   "source": [
    "from h5rdmtoolbox.database import rdf_find"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "515b96d8-9025-4696-a5d7-6a2d0bc996f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "is_dataset = is_dataset.add(\n",
    "    rdf_find,\n",
    "    rdf_predicate=\"http://w3id.org/nfdi4ing/metadata4ing#hasUnit\",\n",
    "    n=1\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "89fb9a00-eb31-42cf-9de1-e6e9785499b8",
   "metadata": {},
   "source": [
    "Test the layout specification"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "4605bae5-fca9-4e0f-9249-cb77c05aab2a",
   "metadata": {},
   "outputs": [],
   "source": [
    "with h5tbx.File() as h5:\n",
    "    ds =h5.create_dataset('velocity', data=4.5, attrs={'units': 'm/s'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "83cd6254-f597-4dad-b281-7a594a0aec83",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2024-06-23_15:25:31,621 ERROR    [core.py:330] Applying spec. \"LayoutSpecification(kwargs={'rdf_predicate': 'http://w3id.org/nfdi4ing/metadata4ing#hasUnit'})\" failed due to not matching the number of results: 1 != 0\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rdf_lay.validate(h5.hdf_filename).is_valid()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "bb359f6d-929e-46fa-a9c6-6c33e38658a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "with h5tbx.File() as h5:\n",
    "    ds =h5.create_dataset('velocity', data=4.5, attrs={'units': 'm/s'})\n",
    "    ds.rdf['units'].predicate = \"http://w3id.org/nfdi4ing/metadata4ing#hasUnit\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "264024ed-44a5-40ad-b2da-1075c7a58c69",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rdf_lay.validate(h5.hdf_filename).is_valid()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6d93fd9a-8df5-413a-ad92-23021ae8fc19",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}