Parser/OVI/Lemmi/lemmario_v3.py

# %%
import xml.etree.ElementTree as ET
import os
import csv
from collections import OrderedDict, defaultdict
import re
import json
# %%
baseDir = '/home/kora/Desktop/OVI_Data_Local/OVIaspo/DallOVI/datiniXML/'
# %%
gat = []
basepath_gat = baseDir + 'xmlgat'
for entry in os.listdir(basepath_gat):
    if os.path.isfile(os.path.join(basepath_gat, entry)): # prolly redundant
        gg = entry.split('.')[1]
        if gg != '':
            gat.append([gg, entry])

lemmi = []
basepath_lemmi = baseDir + 'lemmi'
for entry in os.listdir(basepath_lemmi):
    if os.path.isfile(os.path.join(basepath_lemmi, entry)):
        ll = entry.split('.')[1]
        if ll != '':
            lemmi.append([ll, entry])
# %%
xmlparse = ET.parse(baseDir + 'BiblioDatini.xml')
root = xmlparse.getroot()
biblio = root.findall("Biblio")

sigle = []
for bib in biblio:
    sigla = bib.find("sigla")
    sigle.append(sigla.text.lower())
# %%
OVI_data = open(baseDir + 'OVI_Data.csv', 'w')
csvwriter = csv.writer(OVI_data)

params = ["BiblioDatini", "lemmi", "xmlgat"]

csvwriter.writerow(params)

for sigla in sigle:
    row = [sigla]
    no_lemma = " "
    lemma = " "
    gatto = " "
    row.append(no_lemma)
    for x in range(len(lemmi)):
        if sigla == lemmi[x][0]:
            lemma = lemmi[x][1]
    row.append(lemma)
    for x in range(len(gat)):
        if sigla == gat[x][0]:
            gatto = gat[x][1]
    row.append(gatto)
    csvwriter.writerow(row)

OVI_data.close()
# %%
iperlem_data = open(baseDir + 'lem_Data.csv', 'w')
csvwriter = csv.writer(iperlem_data)

params = ["sigla", "file", "num", "lemma", "commento", "livello"]
csvwriter.writerow(params)


def write_lines(lines, sig, file):
    for line in lines:
        row = [sig, file]
        lem = re.split('\|', line)
        for l in lem:
            m = l.strip()
            row.append(m)
        csvwriter.writerow(row)


for x in range(len(lemmi)):
    sigla = lemmi[x][0]
    file_name = lemmi[x][1]
    #Cambia percorso
    f = open(baseDir + 'lemmi/' + file_name, "r", encoding='latin-1')
    lines = f.readlines()
    write_lines(lines, sigla, file_name)

f.close()

iperlem_data.close()
# %%
redundantLemmas = []

def write_lines_here(lines, sig):
    toRet = []
    for line in lines:
        row = [sig]
        lem = re.split('\|', line)
        for l in lem:
            m = l.strip()
            row.append(m)
        toRet.append(row)
    return toRet


for x in range(len(lemmi)):
    sigla = lemmi[x][0]
    file_name = lemmi[x][1]
    #Cambia percorso
    f = open(baseDir + 'lemmi/' + file_name, "r", encoding='latin-1')
    lines = f.readlines()
    redundantLemmas = redundantLemmas + write_lines_here(lines, sigla)


f.close()

print(len(redundantLemmas))
# %%
preprefinal = list(filter(lambda row: 'IPERLEMMA' not in row[1], redundantLemmas))
prefinal = list(map(lambda row: ((row[2], row[3], row[4]), (row[0], row[1])), preprefinal))

print(len(prefinal))

tmp = defaultdict(list)
for k, v in prefinal: tmp[k].append(v)

final = [{'lemma': {'forma_standard': k[0], 'categoria': k[1], 'note': k[2]}, 'coordinate': list(map(lambda el: {'file': el[0], 'n': el[1]}, v))} for k,v in tmp.items()]
finalB = [{'lemma': {'forma_standard': k[0], 'categoria': k[1], 'note': k[2]}, 'coordinate': list(map(lambda el: el[0] + '_' + el[1], v))} for k,v in tmp.items()]
final.sort(key=lambda el: el['lemma']['forma_standard'])
finalB.sort(key=lambda el: el['lemma']['forma_standard'])
print(len(final))
print(len(finalB))
# %%
for ii, item in enumerate(finalB):
    item['id'] = ii
# %%
# IPERLEMMI

preprefinalIPER = list(filter(lambda row: 'IPERLEMMA' in row[1], redundantLemmas))
prefinalIPER = list(map(lambda row: (row[2], row[3], row[4]), preprefinalIPER))

finalIPER = list(set(prefinalIPER))
finalIPER.sort()
# %%
lem_data_unique = open(baseDir + 'lem_unique.csv', 'w')
csvwriter = csv.writer(lem_data_unique)

csvwriter.writerow(['lemma', 'categoria grammaticale', 'note'])

for line in final:
    csvwriter.writerow(line)

lem_data_unique.close()


# IPERLEMMI

iperlem_data_unique = open(baseDir + 'iperlem_unique.csv', 'w')
csvwriter = csv.writer(iperlem_data_unique)

csvwriter.writerow(['iperlemma', 'categoria grammaticale', 'note'])

for line in finalIPER:
    #print(line)
    csvwriter.writerow(line)

iperlem_data_unique.close()
# %%
cat_gramm = set(map(lambda entry: entry[1], final))
cat_gramm2 = list(cat_gramm)
cat_gramm2.sort()

print(cat_gramm2)
# %%
final[2]
# %%
with open(baseDir + "power_lemmario.json", "w") as outfile:
    json.dump(final, outfile, indent=2)
# %%
with open(baseDir + "power_lemmarioB.json", "w") as outfile:
    json.dump(finalB, outfile, indent=2)
# %%