Normalizing sschema.org http-https namespace rdflib

SO_test_rdflib_normalize.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import rdflib\n",
    "\n",
    "gsrc = \"\"\"{\n",
    "    \"@context\":\"http://schema.org/\",\n",
    "    \"@id\":\"/http-https-test\",\n",
    "    \"@type\":\"Thing\",\n",
    "    \"description\":\"http://schema.org/ is the start of this description\"\n",
    "}\n",
    "\"\"\"\n",
    "\n",
    "def loadTest():\n",
    "    gr = rdflib.ConjunctiveGraph()\n",
    "    gr.parse(data=gsrc, format=\"json-ld\")\n",
    "    return gr\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[\n",
      "  {\n",
      "    \"@id\": \"file:///http-https-test\",\n",
      "    \"@type\": [\n",
      "      \"http://schema.org/Thing\"\n",
      "    ],\n",
      "    \"http://schema.org/description\": [\n",
      "      {\n",
      "        \"@value\": \"http://schema.org/ is the start of this description\"\n",
      "      }\n",
      "    ]\n",
      "  }\n",
      "]\n"
     ]
    }
   ],
   "source": [
    "g = loadTest()\n",
    "print(g.serialize(format=\"json-ld\", indent=2).decode())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "https://schema.org/ is the start of this description does not look like a valid URI, trying to serialize this will break.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[\n",
      "  {\n",
      "    \"@id\": \"file:///http-https-test\",\n",
      "    \"@type\": [\n",
      "      \"https://schema.org/Thing\"\n",
      "    ],\n",
      "    \"http://schema.org/description\": [\n",
      "      {\n",
      "        \"@id\": \"https://schema.org/ is the start of this description\"\n",
      "      }\n",
      "    ],\n",
      "    \"https://schema.org/description\": [\n",
      "      {\n",
      "        \"@id\": \"http://schema.org/description\"\n",
      "      }\n",
      "    ]\n",
      "  }\n",
      "]\n"
     ]
    }
   ],
   "source": [
    "for s, p, o in g.triples(None):\n",
    "    if str(s).startswith(\"http://schema.org\"):\n",
    "        g.remove((s, p, o))\n",
    "        g.add((rdflib.URIRef(str(s).replace(\"http\", \"https\")), p, o))\n",
    "    \n",
    "    if str(p).startswith(\"http://schema.org\"):\n",
    "        g.remove((s, p, o))\n",
    "        g.add((s, rdflib.URIRef(str(p).replace(\"http\", \"https\")), p, o))\n",
    "\n",
    "    if str(o).startswith(\"http://schema.org\"):\n",
    "        g.remove((s, p, o))\n",
    "        g.add((s, p, rdflib.URIRef(str(o).replace(\"http\", \"https\"))))\n",
    "\n",
    "print(g.serialize(format=\"json-ld\", indent=2).decode())        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[\n",
      "  {\n",
      "    \"@id\": \"file:///http-https-test\",\n",
      "    \"@type\": [\n",
      "      \"https://schema.org/Thing\"\n",
      "    ],\n",
      "    \"https://schema.org/description\": [\n",
      "      {\n",
      "        \"@value\": \"http://schema.org/ is the start of this description\"\n",
      "      }\n",
      "    ]\n",
      "  }\n",
      "]\n"
     ]
    }
   ],
   "source": [
    "g = loadTest()\n",
    "\n",
    "for s, p, o in g.triples(None):\n",
    "    changed = False\n",
    "    new_s = s\n",
    "    if str(s).startswith(\"http://schema.org\"):\n",
    "        new_s = rdflib.URIRef(str(s).replace(\"http\", \"https\"))\n",
    "        changed = True\n",
    "    new_p = p\n",
    "    if str(p).startswith(\"http://schema.org\"):\n",
    "        new_p = rdflib.URIRef(str(p).replace(\"http\", \"https\"))\n",
    "        changed = True\n",
    "    new_o = o\n",
    "    if isinstance(o, rdflib.URIRef):\n",
    "        if str(o).startswith(\"http://schema.org\"):\n",
    "            new_o = rdflib.URIRef(str(o).replace(\"http\", \"https\"))\n",
    "            changed = True\n",
    "    if changed:\n",
    "        g.remove((s,p,o))\n",
    "        g.add((new_s, new_p, new_o))\n",
    "\n",
    "print(g.serialize(format=\"json-ld\", indent=2).decode())        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}