import csv
import codecs
import pandas as pd
import re
import os
import io
import tokenize

merged_data = open('mergeOVI.csv', 'w')
csvwriter = csv.writer(merged_data)

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

def get_link_ovi (lemma):
    link_file = open('/Users/leonardocanova/Library/CloudStorage/OneDrive-UniversityofPisa(1)/Documenti/Progetti università/OVI/Programmazione/OVI_lemmi_clean.csv')
    reader = csv.DictReader(link_file)
    for row in reader:
        sLemma = row['sLemma']
        if (sLemma == lemma):
            return (row['FileHTM'])


merge_file = open('/Users/leonardocanova/Library/CloudStorage/OneDrive-UniversityofPisa(1)/Documenti/Progetti università/OVI/Programmazione/data_lemmi.csv')
reader = csv.DictReader(merge_file)
for row in reader:
    line = []
    sigla = row['sigla']
    n_lemma = row['n_lemma']
    lemma = row['lemma']
    n_iperlemma = row['n_iperlemma']
    iperlemma = row['iperlemma']
    pos = row['pos']
    commento = row['commento']
    merce = row['merce']
    link_ovi = get_link_ovi(lemma)
    line.append (sigla)
    line.append (n_lemma)
    line.append (lemma)
    line.append (n_iperlemma)
    line.append (iperlemma)
    line.append (pos)
    line.append (commento)
    line.append (merce)
    if link_ovi is not None:
        line.append(link_ovi)
    else:
        line.append("")

    csvwriter.writerow(line)
    #print (line)
merged_data.close()