{
  "cells": [
    {
      "attachments": {},
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# StringSplitter\n",
        "\n",
        "This presentation's goal it to introduce the features of the `StringSplitter` and how to configure it."
      ]
    },
    {
      "attachments": {},
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "### The challenges\n",
        "\n",
        "- I want to split strings of varying length contained in a source field\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "given preprocessed log entry:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {},
      "outputs": [],
      "source": [
        "document = {\n",
        "    \"ip_addresses\": \"192.168.5.1, 10.10.2.1, fe80::, 127.0.0.1\"\n",
        "}\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "### Create rules and processor"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "create the rules:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {},
      "outputs": [
        {
          "ename": "ModuleNotFoundError",
          "evalue": "No module named 'logprep.processor.string_splitter'",
          "output_type": "error",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
            "Cell \u001b[0;32mIn[10], line 4\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39msys\u001b[39;00m\n\u001b[1;32m      2\u001b[0m \u001b[39m# sys.path.append(\"../../../../../\")\u001b[39;00m\n\u001b[0;32m----> 4\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mlogprep\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mprocessor\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mstring_splitter\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mrule\u001b[39;00m \u001b[39mimport\u001b[39;00m StringSplitterRule\n\u001b[1;32m      5\u001b[0m rules_definitions \u001b[39m=\u001b[39m [\n\u001b[1;32m      6\u001b[0m     {\n\u001b[1;32m      7\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39mfilter\u001b[39m\u001b[39m\"\u001b[39m: \u001b[39m\"\u001b[39m\u001b[39mip_addresses\u001b[39m\u001b[39m\"\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     12\u001b[0m     }\n\u001b[1;32m     13\u001b[0m ]\n\u001b[1;32m     14\u001b[0m rules \u001b[39m=\u001b[39m [StringSplitterRule\u001b[39m.\u001b[39m_create_from_dict(rule_dict) \u001b[39mfor\u001b[39;00m rule_dict \u001b[39min\u001b[39;00m rules_definitions]\n",
            "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'logprep.processor.string_splitter'"
          ]
        }
      ],
      "source": [
        "import sys\n",
        "sys.path.append(\"../../../../../\")\n",
        "\n",
        "from logprep.processor.string_splitter.rule import StringSplitterRule\n",
        "rules_definitions = [\n",
        "    {\n",
        "        \"filter\": \"ip_addresses\",\n",
        "        \"string_splitter\": {\n",
        "            \"source_fields\": [\"ip_addresses\"],\n",
        "            \"target_field\": \"ip_address_list\"\n",
        "        },\n",
        "    }\n",
        "]\n",
        "rules = [StringSplitterRule.create_from_dict(rule_dict) for rule_dict in rules_definitions]\n",
        "rules"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "create the processor config:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "processor_config = {\n",
        "    \"allmighty_string_splitter\": {\n",
        "        \"type\": \"string_splitter\",\n",
        "        \"rules\": [\"/dev\"],\n",
        "    }\n",
        "}\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "create the processor with the factory:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [
        {
          "data": {
            "text/plain": [
              "string_splitter"
            ]
          },
          "execution_count": 4,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "from logging import getLogger\n",
        "from logprep.factory import Factory\n",
        "\n",
        "logger = getLogger()\n",
        "\n",
        "processor = Factory.create(processor_config)\n",
        "processor\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "load rules to processor"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [
        {
          "data": {
            "text/plain": [
              "[filter=\"ip_addresses\", StringSplitterRule.Config(description='', regex_fields=[], tests=[], tag_on_failure=['_string_splitter_failure'], source_fields=['ip_addresses'], target_field='ip_addresses', delete_source_fields=False, overwrite_target=True, extend_target_list=False, delimeter=' ')]"
            ]
          },
          "execution_count": 5,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "for rule in rules:\n",
        "    processor._rule_tree.add_rule(rule)\n",
        "    \n",
        "processor.rules"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "### Process event"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from copy import deepcopy\n",
        "\n",
        "mydocument = deepcopy(document)\n",
        "processor.process(mydocument)\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "### Check Results"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [
        {
          "data": {
            "text/plain": [
              "{'ip_addresses': '192.168.5.1, 10.10.2.1, fe80::, 127.0.0.1'}"
            ]
          },
          "execution_count": 7,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "document"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [
        {
          "data": {
            "text/plain": [
              "{'ip_addresses': ['192.168.5.1,', '10.10.2.1,', 'fe80::,', '127.0.0.1']}"
            ]
          },
          "execution_count": 8,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "mydocument"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3.11.0 ('.venv': venv)",
      "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": "3.11.1"
    },
    "orig_nbformat": 4,
    "vscode": {
      "interpreter": {
        "hash": "586280540a85d3e21edc698fe7b86af2848b9b02644e6c22463da25c40a3f1be"
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}