filter_issue_1.ipynb

fitler_whoosh

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Whoosh Filtering Issue"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import whoosh\n",
    "import timeit\n",
    "import pandas as pd\n",
    "from whoosh.index import create_in\n",
    "from whoosh.fields import *\n",
    "from whoosh.qparser import QueryParser\n",
    "from whoosh import qparser, query\n",
    "from whoosh.query import Term"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create schema\n",
    "schema = Schema(title=TEXT(stored=True), ind_id=ID(stored=True), content=TEXT(stored = True))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Add trial cleaned documents to schema\n",
    "iy = create_in(\"indexdir\", schema)\n",
    "writer = iy.writer()\n",
    "writer.add_document(title=u\"First document\", ind_id=u\"123\",content=u\"This is the first document we are using as an example.\")\n",
    "writer.add_document(title=u\"Second document\", ind_id=u\"123\",content=u\"This is the second document we are using as an example: it is not the first.\")\n",
    "writer.add_document(title=u\"Third document\", ind_id=u\"456\",content=u\"This is the third document we are using as an example.\")\n",
    "writer.commit()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1.1 Working Example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<Top 2 Results for Term('content', 'example') runtime=0.0007069744169712067> 2\n"
     ]
    }
   ],
   "source": [
    "with iy.searcher() as searcher:\n",
    "    q = QueryParser(\"content\", iy.schema).parse(\"example\")\n",
    "    allow_q = query.Term(\"ind_id\", \"123\")\n",
    "    results = searcher.search(q, filter=allow_q, limit=None)\n",
    "    print(results, len(results))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1.2 Not Working"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def filtered():\n",
    "    \n",
    "    #search for term in individual\n",
    "    with iy.searcher() as searcher:\n",
    "        query = QueryParser(\"content\", iy.schema).parse(\"example\")\n",
    "        allow_q = query.Term(\"ind_id\", \"123\")\n",
    "        results = searcher.search(query, filter=allow_q, limit=None)\n",
    "        print(results, len(results))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'Term' object has no attribute 'Term'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-6-1e07ac61d74e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mfiltered\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m<ipython-input-5-02f7f6bb4e02>\u001b[0m in \u001b[0;36mfiltered\u001b[0;34m()\u001b[0m\n\u001b[1;32m     14\u001b[0m     \u001b[0;32mwith\u001b[0m \u001b[0miy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msearcher\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0msearcher\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m         \u001b[0mquery\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mQueryParser\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"content\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0miy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mschema\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"example\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 16\u001b[0;31m         \u001b[0mallow_q\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mquery\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTerm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"ind_id\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"123\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     17\u001b[0m         \u001b[0mresults\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msearcher\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msearch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mquery\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mallow_q\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlimit\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     18\u001b[0m         \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresults\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresults\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mAttributeError\u001b[0m: 'Term' object has no attribute 'Term'"
     ]
    }
   ],
   "source": [
    "filtered()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:pyconnect_py37]",
   "language": "python",
   "name": "conda-env-pyconnect_py37-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}