Parser/OVI/Lemmi/OVI_allLemmaInfo.py

import os
import xml.etree.ElementTree as Xet
import re
from xml.etree import ElementTree
import csv

ovi_data = open('ovi_lemmi.csv', 'w')
csvwriter = csv.writer(ovi_data)

params = ["sigla", "n_lemma", "lemma", "pos", "iperlemma", "n_iperlemma", "commento"]
csvwriter.writerow(params)

'''lemmi = []
basepath_lemmi = '/Users/alessiaspadi/Documents/RESTORE/temp_ovi/lemmi'
for entry in os.listdir(basepath_lemmi):
    if os.path.isfile(os.path.join(basepath_lemmi, entry)):
        ll = entry.split('.')[1].lstrip().split(' ')[0]
        if ll != '':
            lemmi.append([ll, entry])'''

def get_iperlemma(sig, n_lem, lem):
    link_file = open('/Users/federicaspinelli/TEAMOVI/Parser/DATA/OVI/CSV/ovi_lemmi.csv')
    reader = csv.DictReader(link_file)
    for row in reader:
        sigla = row['sigla'].upper()
        n_lemma = row['n_lemma']
        pos = row['pos']
        lemma = row['lemma']
        commento = row['commento']
        if (sig == sigla) and (n_lem == n_lemma) and (lem == lemma):
            return([pos, commento])

merge_file = open('/Users/federicaspinelli/TEAMOVI/Parser/DATA/OVI/CSV/lemma-iperlemma_Data.csv')
reader = csv.DictReader(merge_file)
for row in reader:
    line=[]
    sigla = row['sigla'].upper()
    n_lemma = row['n_lemma']
    lemma = row['lemma']
    iperlemma = row['iperlemma']
    n_iperlemma = row['n_iperlemma']
    iper = get_iperlemma(sigla, n_lemma, lemma)
    line.append(sigla)
    line.append(n_lemma)
    line.append(lemma)
    line.append(n_iperlemma)
    line.append(iperlemma)
    if iper is not None:
        for ip in iper:
            line.append(ip)
    csvwriter.writerow(line)

'''for x in range(len(lemmi)):
    sigla = lemmi[x][0]
    sig = sigla.upper()

    file_name = lemmi[x][1]
    f = open('/Users/alessiaspadi/Documents/RESTORE/temp_ovi/lemmi/' + file_name, "r", encoding='ISO-8859-1')
    lines = f.readlines()
    for line in lines:
        row = [sig]
        if "IPERLEMMA" not in line:
            lem = re.split(' \| ', line)
            lung = len(lem)
            n_lemma = lem[0]
            if (lung >= 2):
                lemma = lem[1]
            else:
                lemma = ""
            iper = get_iperlemma(sig, n_lemma, lemma)
            for el in lem:
                rr = el.replace('\n', '')
                row.append(rr)
            if iper is not None:
                for ip in iper:
                    row.append(ip)
            csvwriter.writerow(row)

f.close()'''

ovi_data.close()