Add parser lemmario

OVI/Lemmario_v2.ipynb

@@ -0,0 +1,683 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import xml.etree.ElementTree as ET\n",
+    "import os\n",
+    "import csv\n",
+    "from collections import OrderedDict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "baseDir = '/home/kora/Desktop/OVI_Data_local/Dati nuOVI (fine Giugno 21)/datiniXML/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gat = []\n",
+    "basepath_gat = baseDir + 'xmlgat'\n",
+    "for entry in os.listdir(basepath_gat):\n",
+    "    if os.path.isfile(os.path.join(basepath_gat, entry)): # prolly redundant\n",
+    "        gg = entry.split('.')[1]\n",
+    "        if gg != '':\n",
+    "            gat.append([gg, entry])\n",
+    "\n",
+    "\n",
+    "# NON HO AL MOMENTO A DISPOSIZIONE I 'nolemmi'\n",
+    "            \n",
+    "#nolemmi = []\n",
+    "#basepath_nolemmi = baseDir + 'DatiniXML_incompleto'\n",
+    "#for entry in os.listdir(basepath_nolemmi):\n",
+    "#    if os.path.isfile(os.path.join(basepath_nolemmi, entry)):\n",
+    "#        nn = entry.split('.')[1]\n",
+    "#        if nn != '':\n",
+    "#            nolemmi.append([nn, entry])\n",
+    "\n",
+    "lemmi = []\n",
+    "basepath_lemmi = baseDir + 'lemmi'\n",
+    "for entry in os.listdir(basepath_lemmi):\n",
+    "    if os.path.isfile(os.path.join(basepath_lemmi, entry)):\n",
+    "        ll = entry.split('.')[1]\n",
+    "        if ll != '':\n",
+    "            lemmi.append([ll, entry])\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Non mi è chiaro a cosa servano le **tre** celle seguenti -- in ogni caso, non ho a disposizione BiblioDatini.xml nella versione corrente dei dati OVI."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "xmlparse = ET.parse(baseDir + 'BiblioDatini.xml')\n",
+    "root = xmlparse.getroot()\n",
+    "biblio = root.findall(\"Biblio\")\n",
+    "\n",
+    "sigle = []\n",
+    "for bib in biblio:\n",
+    "    sigla = bib.find(\"sigla\")\n",
+    "    sigle.append(sigla.text.lower())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OVI_data = open(baseDir + 'OVI_Data.csv', 'w')\n",
+    "csvwriter = csv.writer(OVI_data)\n",
+    "\n",
+    "params = [\"BiblioDatini\", \"nolemmi\", \"lemmi\", \"xmlgat\"]\n",
+    "\n",
+    "csvwriter.writerow(params)\n",
+    "\n",
+    "for sigla in sigle:\n",
+    "    row = [sigla]\n",
+    "    no_lemma = \" \"\n",
+    "    lemma = \" \"\n",
+    "    gatto = \" \"\n",
+    "    for x in range(len(nolemmi)):\n",
+    "        if sigla in nolemmi[x][0]:\n",
+    "            no_lemma = nolemmi[x][1]\n",
+    "    row.append(no_lemma)\n",
+    "    for x in range(len(lemmi)):\n",
+    "        if sigla == lemmi[x][0]:\n",
+    "            lemma = lemmi[x][1]\n",
+    "    row.append(lemma)\n",
+    "    for x in range(len(gat)):\n",
+    "        if sigla == gat[x][0]:\n",
+    "            gatto = gat[x][1]\n",
+    "    row.append(gatto)\n",
+    "    csvwriter.writerow(row)\n",
+    "\n",
+    "OVI_data.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Cambiare percorsi file\n",
+    "#xml_file_name = 'Ovi/BiblioDatini.xml'\n",
+    "#tree = Xet.parse(xml_file_name)\n",
+    "#root = tree.getroot()           --> già definito\n",
+    "#biblio = root.findall(\"Biblio\") --> già definito\n",
+    "\n",
+    "\n",
+    "Datini_data = open(baseDir + 'Datini_Data.csv', 'w')\n",
+    "csvwriter = csv.writer(Datini_data)\n",
+    "\n",
+    "elemList = []\n",
+    "\n",
+    "for elem in root.iter():\n",
+    "    elemList.append(elem.tag)\n",
+    "\n",
+    "\n",
+    "elemList = list(set(elemList))\n",
+    "\n",
+    "elemList.remove(\"dataroot\")\n",
+    "elemList.remove(\"Biblio\")\n",
+    "\n",
+    "param = elemList\n",
+    "\n",
+    "csvwriter.writerow(param)\n",
+    "\n",
+    "\n",
+    "def cell(p, arr):\n",
+    "    if arr.find(p) is None:\n",
+    "        res = \" \"\n",
+    "    else:\n",
+    "        res = arr.find(p).text\n",
+    "    return res\n",
+    "\n",
+    "\n",
+    "for scheda in biblio:\n",
+    "    aut = []\n",
+    "\n",
+    "    for par in param:\n",
+    "        if par == \"star_note\":\n",
+    "            if scheda.find(\".//star_note\") is None:\n",
+    "                r = \" \"\n",
+    "            else:\n",
+    "                r = \"True\"\n",
+    "        else:\n",
+    "            r = cell(par, scheda)\n",
+    "        aut.append(r)\n",
+    "\n",
+    "    csvwriter.writerow(aut)\n",
+    "\n",
+    "Datini_data.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Si riprende da qui"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "\n",
+    "\n",
+    "iperlem_data = open(baseDir + 'lem_Data.csv', 'w')\n",
+    "csvwriter = csv.writer(iperlem_data)\n",
+    "\n",
+    "params = [\"sigla\", \"file\", \"num\", \"lemma\", \"commento\", \"livello\"]\n",
+    "csvwriter.writerow(params)\n",
+    "\n",
+    "\n",
+    "def write_lines(lines, sig, file):\n",
+    "    for line in lines:\n",
+    "        row = [sig, file]\n",
+    "        lem = re.split('\\|', line)\n",
+    "        for l in lem:\n",
+    "            m = l.strip()\n",
+    "            row.append(m)\n",
+    "#        print(row)\n",
+    "        csvwriter.writerow(row)\n",
+    "\n",
+    "\n",
+    "for x in range(len(lemmi)):\n",
+    "    sigla = lemmi[x][0]\n",
+    "    file_name = lemmi[x][1]\n",
+    "    #Cambia percorso\n",
+    "    f = open(baseDir + 'lemmi/' + file_name, \"r\", encoding='latin-1')\n",
+    "    lines = f.readlines()\n",
+    "    write_lines(lines, sigla, file_name)\n",
+    "\n",
+    "\n",
+    "f.close()\n",
+    "\n",
+    "iperlem_data.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "110829\n"
+     ]
+    }
+   ],
+   "source": [
+    "redundantLemmas = []\n",
+    "\n",
+    "def write_lines_here(lines, sig):\n",
+    "    toRet = []\n",
+    "    for line in lines:\n",
+    "        row = [sig]\n",
+    "        lem = re.split('\\|', line)\n",
+    "        for l in lem:\n",
+    "            m = l.strip()\n",
+    "            row.append(m)\n",
+    "        toRet.append(row)\n",
+    "    return toRet\n",
+    "\n",
+    "\n",
+    "for x in range(len(lemmi)):\n",
+    "    sigla = lemmi[x][0]\n",
+    "    file_name = lemmi[x][1]\n",
+    "    #Cambia percorso\n",
+    "    f = open(baseDir + 'lemmi/' + file_name, \"r\", encoding='latin-1')\n",
+    "    lines = f.readlines()\n",
+    "    redundantLemmas = redundantLemmas + write_lines_here(lines, sigla)\n",
+    "\n",
+    "\n",
+    "f.close()\n",
+    "\n",
+    "print(len(redundantLemmas))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Check di cosa viene fuori dalla lettura"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['b60', '1', 'denaro', 's.m.', '']"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "redundantLemmas[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Esporto il lemmario"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "90150\n",
+      "7591\n"
+     ]
+    }
+   ],
+   "source": [
+    "preprefinal = list(filter(lambda row: 'IPERLEMMA' not in row[1], redundantLemmas))\n",
+    "prefinal = list(map(lambda row: (row[2], row[3], row[4]), preprefinal))\n",
+    "\n",
+    "print(len(prefinal))\n",
+    "\n",
+    "final = list(set(prefinal))\n",
+    "final.sort()\n",
+    "\n",
+    "print(len(final))\n",
+    "\n",
+    "\n",
+    "# IPERLEMMI\n",
+    "\n",
+    "preprefinalIPER = list(filter(lambda row: 'IPERLEMMA' in row[1], redundantLemmas))\n",
+    "prefinalIPER = list(map(lambda row: (row[2], row[3], row[4]), preprefinalIPER))\n",
+    "\n",
+    "finalIPER = list(set(prefinalIPER))\n",
+    "finalIPER.sort()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lem_data_unique = open(baseDir + 'lem_unique.csv', 'w')\n",
+    "csvwriter = csv.writer(lem_data_unique)\n",
+    "\n",
+    "csvwriter.writerow(['lemma', 'categoria grammaticale', 'note'])\n",
+    "\n",
+    "for line in final:\n",
+    "    csvwriter.writerow(line)\n",
+    "\n",
+    "lem_data_unique.close()\n",
+    "\n",
+    "\n",
+    "# IPERLEMMI\n",
+    "\n",
+    "iperlem_data_unique = open(baseDir + 'iperlem_unique.csv', 'w')\n",
+    "csvwriter = csv.writer(iperlem_data_unique)\n",
+    "\n",
+    "csvwriter.writerow(['iperlemma', 'categoria grammaticale', 'note'])\n",
+    "\n",
+    "for line in finalIPER:\n",
+    "    #print(line)\n",
+    "    csvwriter.writerow(line)\n",
+    "\n",
+    "iperlem_data_unique.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Categorie grammaticali ed export ordinato"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cat_gramm = set(map(lambda entry: entry[1], final))\n",
+    "cat_gramm2 = list(cat_gramm)\n",
+    "cat_gramm2.sort()\n",
+    "\n",
+    "print(cat_gramm2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "byType = OrderedDict()\n",
+    "\n",
+    "for type1 in cat_gramm2:\n",
+    "    byType[type1] = list(filter(lambda a: a[1]==type1, final))\n",
+    "\n",
+    "\n",
+    "lem_data_byCat = open(baseDir + 'lem_unique_byCat.csv', 'w')\n",
+    "csvwriter = csv.writer(lem_data_byCat)\n",
+    "\n",
+    "csvwriter.writerow(['lemma', 'categoria grammaticale', 'note'])\n",
+    "\n",
+    "for type1 in cat_gramm2:\n",
+    "    print(type1)\n",
+    "    for line in byType[type1]:\n",
+    "        csvwriter.writerow(line)\n",
+    "\n",
+    "lem_data_byCat.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Microprova di modifica + export di xml (modifico un attribute di un tag).\n",
+    "\n",
+    "Come prima cosa, provo a recuperare la lista dei lemmi di un singolo file, e a rintracciare quel lemma e il suo ID (numero d'ordine) nel lemmario."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'n': '6', 'type': '1'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '6', 'maggio', 's.m.', '']\n",
+      "New ID:  4247\n",
+      "\n",
+      "{'n': '13', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '13', 'simona (donna di piero di paolo rinaldeschi)', 'antr.', '']\n",
+      "New ID:  6666\n",
+      "\n",
+      "{'n': '7', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '7', 'famiglio', 's.m.', '']\n",
+      "New ID:  2514\n",
+      "\n",
+      "{'n': '18', 'type': '2'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '18', 'oncia', 's.f.', '']\n",
+      "New ID:  5069\n",
+      "\n",
+      "{'n': '20', 'type': '4'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '20', 'bottoncino', 's.m.', '']\n",
+      "New ID:  1255\n",
+      "\n",
+      "{'n': '22', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '22', 'infilare', 'v.', '']\n",
+      "New ID:  3786\n",
+      "\n",
+      "{'n': '9', 'type': '2'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '9', 'braccio', 's.m.', '']\n",
+      "New ID:  1269\n",
+      "\n",
+      "{'n': '19', 'type': '4'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '19', 'frangia', 's.f.', '']\n",
+      "New ID:  2907\n",
+      "\n",
+      "{'n': '8', 'type': '3'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '8', 'nero', 'agg./s.m.', '']\n",
+      "New ID:  4860\n",
+      "\n",
+      "{'n': '15', 'type': '3'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '15', 'azzurro', 'agg./s.m.', '']\n",
+      "New ID:  709\n",
+      "\n",
+      "{'n': '16', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '16', 'nannino (manovale)', 'antr.', '']\n",
+      "New ID:  4807\n",
+      "\n",
+      "{'n': '12', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '12', 'san bartolomeo (chiesa e convento di)', 'n.g.', 'a prato (convento di carmelitani)']\n",
+      "New ID:  6303\n",
+      "\n",
+      "{'n': '14', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '14', 'nanni di luca da santa chiara', 'antr.', '']\n",
+      "New ID:  4789\n",
+      "\n",
+      "{'n': '11', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '11', 'garzone', 's.m.', '']\n",
+      "New ID:  3021\n",
+      "\n",
+      "{'n': '21', 'type': '1'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '21', 'nona', 's.f.', '']\n",
+      "New ID:  5025\n",
+      "\n",
+      "{'n': '10', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '10', 'domenica', 's.f.', '']\n",
+      "New ID:  2369\n",
+      "\n",
+      "{'n': '3', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '3', 'sere', 's.m.', '']\n",
+      "New ID:  6611\n",
+      "\n",
+      "{'n': '17', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '17', 'clemente di niccolò di piero', 'antr.', '']\n",
+      "New ID:  1900\n",
+      "\n",
+      "{'n': '14', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '14', 'nanni di luca da santa chiara', 'antr.', '']\n",
+      "New ID:  4789\n",
+      "\n",
+      "{'n': '1', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '1', 'margherita di domenico bandini', 'antr.', '']\n",
+      "New ID:  4378\n",
+      "\n",
+      "{'n': '5', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '5', 'prato', 'n.g.', '']\n",
+      "New ID:  5821\n",
+      "\n",
+      "{'n': '4', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '4', 'francesco di marco datini', 'antr.', '']\n",
+      "New ID:  2864\n",
+      "\n",
+      "{'n': '5', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '5', 'prato', 'n.g.', '']\n",
+      "New ID:  5821\n",
+      "\n",
+      "{'n': '2', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '2', 'firenze', 'n.g.', '']\n",
+      "New ID:  2708\n",
+      "\n",
+      "{'n': '5', 'type': '0'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '5', 'prato', 'n.g.', '']\n",
+      "New ID:  5821\n",
+      "\n",
+      "{'n': '6', 'type': '1'}\n",
+      "lem\n",
+      "Lemma:  ['d16', '6', 'maggio', 's.m.', '']\n",
+      "New ID:  4247\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "ii = 2\n",
+    "\n",
+    "smalltree = ET.parse(baseDir + 'xmlgat/' + gat[ii][1])\n",
+    "smallroot = smalltree.getroot()\n",
+    "\n",
+    "localLemNodes = smallroot.iter('lem')\n",
+    "\n",
+    "for node in localLemNodes:\n",
+    "    print(node.attrib)\n",
+    "    print(node.tag)\n",
+    "    #\n",
+    "    thisLemma = list(filter(lambda lem: lem[0]==gat[ii][0] and lem[1]==node.attrib['n'], redundantLemmas))[0]\n",
+    "    newID = final.index((thisLemma[2], thisLemma[3], thisLemma[4]))\n",
+    "    #\n",
+    "    print('Lemma: ', thisLemma)\n",
+    "    print('New ID: ', newID)\n",
+    "    print()\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Qui faccio una prova di modifica del singolo file e di export in nuovo xml"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ii = 2\n",
+    "\n",
+    "smalltree = ET.parse(baseDir + 'xmlgat/' + gat[ii][1])\n",
+    "smallroot = smalltree.getroot()\n",
+    "\n",
+    "for node in smallroot.iter('lem'):\n",
+    "    node.set('n', '100h')\n",
+    "        \n",
+    "smalltree.write(baseDir + 'prova.xml')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Infine provo un loop su tutti i file, li elaboro e li esporto in una nuova cartella (che va creata a mano) 'newxmlgat'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Parsing original xml file:  xmlgat.k01.txt  failed\n",
+      "Parsing original xml file:  xmlgat.j99.txt  failed\n",
+      "Parsing original xml file:  xmlgat.c13.txt  failed\n"
+     ]
+    }
+   ],
+   "source": [
+    "for ii in range(len(gat)):\n",
+    "    try:\n",
+    "        smalltree = ET.parse(baseDir + 'xmlgat/' + gat[ii][1])\n",
+    "        smallroot = smalltree.getroot()\n",
+    "        #\n",
+    "        localLemNodes = smallroot.iter('lem')\n",
+    "        #\n",
+    "        for node in localLemNodes:\n",
+    "            try:\n",
+    "                thisLemma = list(filter(lambda lem: lem[0]==gat[ii][0] and lem[1]==node.attrib['n'], redundantLemmas))[0]\n",
+    "                newID = final.index((thisLemma[2], thisLemma[3], thisLemma[4]))\n",
+    "                #\n",
+    "                node.set('n', str(newID))\n",
+    "            except Exception as e:\n",
+    "                print('In looking for lemma:')\n",
+    "                print(e)\n",
+    "        try:\n",
+    "            smalltree.write(baseDir + 'newxmlgat/'+'newxmlgat.'+gat[ii][0]+'.xml')\n",
+    "        except Exception as e:\n",
+    "            print('In Export:')\n",
+    "            print(e)\n",
+    "    except:\n",
+    "        print('Parsing original xml file: ', gat[ii][1], ' failed' )"
+   ]
+  },
+  {
+   "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}