Flat to hierarchical XML

Flat to Hierarchy.ipynb

{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from lxml import etree\n",
      "\n",
      "origtree = etree.XML('''\n",
      "<sp xml:id=\"sp-0001\" who=\"#Egeon_Err\">\n",
      "<speaker xml:id=\"spk-0001\">\n",
      "<w xml:id=\"w0000410\">EGEON</w>\n",
      "</speaker>\n",
      "<ab xml:id=\"ab-0001\">\n",
      "<lb xml:id=\"lb-00009\"/>\n",
      "<milestone unit=\"ftln\" xml:id=\"ftln-0001\" n=\"1.1.1\" ana=\"#verse\"\n",
      "corresp=\"#w0000420 #p0000430 #c0000440 #w0000450 #p0000460 #c0000470\n",
      "#w0000480 #c0000490 #w0000500 #c0000510 #w0000520 #c0000530 #w0000540\n",
      "#p0000550\"/>\n",
      "<w xml:id=\"w0000420\" n=\"1.1.1\">Proceed</w>\n",
      "<pc xml:id=\"p0000430\" n=\"1.1.1\">,</pc>\n",
      "<c xml:id=\"c0000440\" n=\"1.1.1\"> </c>\n",
      "<w xml:id=\"w0000450\" n=\"1.1.1\">Solinus</w>\n",
      "<pc xml:id=\"p0000460\" n=\"1.1.1\">,</pc>\n",
      "<c xml:id=\"c0000470\" n=\"1.1.1\"> </c>\n",
      "<w xml:id=\"w0000480\" n=\"1.1.1\">to</w>\n",
      "<c xml:id=\"c0000490\" n=\"1.1.1\"> </c>\n",
      "<w xml:id=\"w0000500\" n=\"1.1.1\">procure</w>\n",
      "<c xml:id=\"c0000510\" n=\"1.1.1\"> </c>\n",
      "<w xml:id=\"w0000520\" n=\"1.1.1\">my</w>\n",
      "<c xml:id=\"c0000530\" n=\"1.1.1\"> </c>\n",
      "<w xml:id=\"w0000540\" n=\"1.1.1\">fall</w>\n",
      "<pc xml:id=\"p0000550\" n=\"1.1.1\">,</pc>\n",
      "<lb xml:id=\"lb-00010\"/>\n",
      "<milestone unit=\"ftln\" xml:id=\"ftln-0002\" n=\"1.1.2\" ana=\"#verse\"\n",
      "corresp=\"#w0000560 #c0000570 #w0000580 #c0000590 #w0000600 #c0000610\n",
      "#w0000620 #c0000630 #w0000640 #c0000650 #w0000660 #c0000670 #w0000680\n",
      "#c0000690 #w0000700 #c0000710 #w0000720 #c0000730 #w0000740 #p0000750\"/>\n",
      "<w xml:id=\"w0000560\" n=\"1.1.2\">And</w>\n",
      "<c xml:id=\"c0000570\" n=\"1.1.2\"> </c>\n",
      "<w xml:id=\"w0000580\" n=\"1.1.2\">by</w>\n",
      "<c xml:id=\"c0000590\" n=\"1.1.2\"> </c>\n",
      "<w xml:id=\"w0000600\" n=\"1.1.2\">the</w>\n",
      "<c xml:id=\"c0000610\" n=\"1.1.2\"> </c>\n",
      "<w xml:id=\"w0000620\" n=\"1.1.2\">doom</w>\n",
      "<c xml:id=\"c0000630\" n=\"1.1.2\"> </c>\n",
      "<w xml:id=\"w0000640\" n=\"1.1.2\">of</w>\n",
      "<c xml:id=\"c0000650\" n=\"1.1.2\"> </c>\n",
      "<w xml:id=\"w0000660\" n=\"1.1.2\">death</w>\n",
      "<c xml:id=\"c0000670\" n=\"1.1.2\"> </c>\n",
      "<w xml:id=\"w0000680\" n=\"1.1.2\">end</w>\n",
      "<c xml:id=\"c0000690\" n=\"1.1.2\"> </c>\n",
      "<w xml:id=\"w0000700\" n=\"1.1.2\">woes</w>\n",
      "<c xml:id=\"c0000710\" n=\"1.1.2\"> </c>\n",
      "<w xml:id=\"w0000720\" n=\"1.1.2\">and</w>\n",
      "<c xml:id=\"c0000730\" n=\"1.1.2\"> </c>\n",
      "<w xml:id=\"w0000740\" n=\"1.1.2\">all</w>\n",
      "<pc xml:id=\"p0000750\" n=\"1.1.2\">.</pc>\n",
      "</ab>\n",
      "</sp>\n",
      "''', parser=etree.XMLParser(remove_blank_text=True))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from copy import deepcopy\n",
      "tree = deepcopy(origtree)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "for sp in tree.xpath('//sp'):\n",
      "    ab = sp.xpath('ab')[0]  # Assumes only one ab per sp.\n",
      "    for milestone in ab.xpath('milestone'):\n",
      "        line = etree.SubElement(sp, 'l')\n",
      "        corr_ids = [id_.lstrip('#') for id_ in milestone.get('corresp').split()]\n",
      "        for id_ in corr_ids:\n",
      "            elem = sp.xpath('id($cid)', cid=id_)[0]\n",
      "            line.append(elem)\n",
      "    sp.remove(ab)\n",
      "print(etree.tostring(tree, pretty_print=True, encoding='unicode'))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "<sp xml:id=\"sp-0001\" who=\"#Egeon_Err\">\n",
        "  <speaker xml:id=\"spk-0001\">\n",
        "    <w xml:id=\"w0000410\">EGEON</w>\n",
        "  </speaker>\n",
        "  <l>\n",
        "    <w xml:id=\"w0000420\" n=\"1.1.1\">Proceed</w>\n",
        "    <pc xml:id=\"p0000430\" n=\"1.1.1\">,</pc>\n",
        "    <c xml:id=\"c0000440\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000450\" n=\"1.1.1\">Solinus</w>\n",
        "    <pc xml:id=\"p0000460\" n=\"1.1.1\">,</pc>\n",
        "    <c xml:id=\"c0000470\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000480\" n=\"1.1.1\">to</w>\n",
        "    <c xml:id=\"c0000490\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000500\" n=\"1.1.1\">procure</w>\n",
        "    <c xml:id=\"c0000510\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000520\" n=\"1.1.1\">my</w>\n",
        "    <c xml:id=\"c0000530\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000540\" n=\"1.1.1\">fall</w>\n",
        "    <pc xml:id=\"p0000550\" n=\"1.1.1\">,</pc>\n",
        "  </l>\n",
        "  <l>\n",
        "    <w xml:id=\"w0000560\" n=\"1.1.2\">And</w>\n",
        "    <c xml:id=\"c0000570\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000580\" n=\"1.1.2\">by</w>\n",
        "    <c xml:id=\"c0000590\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000600\" n=\"1.1.2\">the</w>\n",
        "    <c xml:id=\"c0000610\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000620\" n=\"1.1.2\">doom</w>\n",
        "    <c xml:id=\"c0000630\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000640\" n=\"1.1.2\">of</w>\n",
        "    <c xml:id=\"c0000650\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000660\" n=\"1.1.2\">death</w>\n",
        "    <c xml:id=\"c0000670\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000680\" n=\"1.1.2\">end</w>\n",
        "    <c xml:id=\"c0000690\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000700\" n=\"1.1.2\">woes</w>\n",
        "    <c xml:id=\"c0000710\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000720\" n=\"1.1.2\">and</w>\n",
        "    <c xml:id=\"c0000730\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000740\" n=\"1.1.2\">all</w>\n",
        "    <pc xml:id=\"p0000750\" n=\"1.1.2\">.</pc>\n",
        "  </l>\n",
        "</sp>\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from copy import deepcopy\n",
      "tree = deepcopy(origtree)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "for sp in tree.xpath('//sp'):\n",
      "    ab = sp.xpath('ab')[0]  # Assumes only one ab per sp.\n",
      "    for milestone in ab.xpath('milestone'):\n",
      "        line = etree.SubElement(sp, 'l')\n",
      "        elem = milestone.getnext()\n",
      "        while True:\n",
      "            if elem is None or elem.tag == 'milestone':\n",
      "                break\n",
      "            line.append(deepcopy(elem))  # Can't append directly, would break getnext().\n",
      "            elem = elem.getnext()\n",
      "    sp.remove(ab)\n",
      "print(etree.tostring(tree, pretty_print=True, encoding='unicode'))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "<sp xml:id=\"sp-0001\" who=\"#Egeon_Err\">\n",
        "  <speaker xml:id=\"spk-0001\">\n",
        "    <w xml:id=\"w0000410\">EGEON</w>\n",
        "  </speaker>\n",
        "  <l>\n",
        "    <w xml:id=\"w0000420\" n=\"1.1.1\">Proceed</w>\n",
        "    <pc xml:id=\"p0000430\" n=\"1.1.1\">,</pc>\n",
        "    <c xml:id=\"c0000440\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000450\" n=\"1.1.1\">Solinus</w>\n",
        "    <pc xml:id=\"p0000460\" n=\"1.1.1\">,</pc>\n",
        "    <c xml:id=\"c0000470\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000480\" n=\"1.1.1\">to</w>\n",
        "    <c xml:id=\"c0000490\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000500\" n=\"1.1.1\">procure</w>\n",
        "    <c xml:id=\"c0000510\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000520\" n=\"1.1.1\">my</w>\n",
        "    <c xml:id=\"c0000530\" n=\"1.1.1\"> </c>\n",
        "    <w xml:id=\"w0000540\" n=\"1.1.1\">fall</w>\n",
        "    <pc xml:id=\"p0000550\" n=\"1.1.1\">,</pc>\n",
        "    <lb xml:id=\"lb-00010\"/>\n",
        "  </l>\n",
        "  <l>\n",
        "    <w xml:id=\"w0000560\" n=\"1.1.2\">And</w>\n",
        "    <c xml:id=\"c0000570\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000580\" n=\"1.1.2\">by</w>\n",
        "    <c xml:id=\"c0000590\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000600\" n=\"1.1.2\">the</w>\n",
        "    <c xml:id=\"c0000610\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000620\" n=\"1.1.2\">doom</w>\n",
        "    <c xml:id=\"c0000630\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000640\" n=\"1.1.2\">of</w>\n",
        "    <c xml:id=\"c0000650\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000660\" n=\"1.1.2\">death</w>\n",
        "    <c xml:id=\"c0000670\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000680\" n=\"1.1.2\">end</w>\n",
        "    <c xml:id=\"c0000690\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000700\" n=\"1.1.2\">woes</w>\n",
        "    <c xml:id=\"c0000710\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000720\" n=\"1.1.2\">and</w>\n",
        "    <c xml:id=\"c0000730\" n=\"1.1.2\"> </c>\n",
        "    <w xml:id=\"w0000740\" n=\"1.1.2\">all</w>\n",
        "    <pc xml:id=\"p0000750\" n=\"1.1.2\">.</pc>\n",
        "  </l>\n",
        "</sp>\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 5
    }
   ],
   "metadata": {}
  }
 ]
}