Parser/OVI/Antroponimi/names.py

# %%
import json
import csv
# %%
with open("power_lemmarioB.json") as file1:
    lems = json.load(file1)
# %%
antroponyms = list(filter( lambda lem: lem['lemma']['categoria']=='antr.' , lems))
# %%
print(len(antroponyms))
print(len(lems))
# %%
antr2 = list(map( lambda el: el['lemma'], antroponyms ))
print(len(antr2))
antr3 = list(filter( lambda el: el['note']=='', antr2 ))
print(len(antr3))
# %%
with open("antroponimi_ovi.csv", 'w') as outfile:
    writer = csv.DictWriter(outfile, fieldnames=antr2[0].keys())
    writer.writeheader()
    writer.writerows(antr2)
with open("antroponimi_short_ovi.csv", 'w') as outfile:
    writer = csv.DictWriter(outfile, fieldnames=antr3[0].keys())
    writer.writeheader()
    writer.writerows(antr3)
# %%
letters = []
letterIDs = {}
with open("../BiblioDatini_IDAspo.csv") as file2:
    reader = csv.DictReader(file2)
    for row in reader:
        letters.append(row)
        letterIDs[row['sigla']] = row['id']
# %%
print(len(letters))
print(len(letterIDs))
# %%
letterIDsList = list(letterIDs.values())
# %%
antroponymsBySigla = {sigla: [] for sigla in letterIDs.keys()}

for antr in antroponyms:
    sigle = list(map( lambda str1: str1.split("_")[0].upper(), antr['coordinate'] ))
    antr['lemma'].update({'id': antr['id']})
    for sigla in sigle:
        try:
            antroponymsBySigla[sigla].append(antr['lemma'])
        except:
            pass
# %%
antroponymsBySigla
# %%
datiniRelevantItems = []
with open("../../data_item.csv") as file3:
    reader = csv.DictReader(file3)
    for row in reader:
        if row['id'] in letterIDsList:
            datiniRelevantItems.append(row)
# %%
print(len(letterIDsList))
print(len(datiniRelevantItems))
# %%
def takeRelevantProperties(obj):
    toRet = {}
    toRet['id'] = obj['id']
    for tag in ['persona_destinatario', 'persona_mittente', 'persona_indirizzata', 'persona_mano']:
        if obj[tag]=='':
            toRet[tag] = ''
        else:
            toRet[tag] = json.loads(obj[tag])['authID']
    return toRet

datiniRelevantStuff = {obj['id']: obj for obj in map( takeRelevantProperties, datiniRelevantItems ) }
# %%
datiniRelevantStuff
# %%
datiniEAC = {}
with open("../../DallASPO/data_eac_datini.csv") as file4:
    reader = csv.DictReader(file4)
    for row in reader:
        datiniEAC[row['recordId']] = row
# %%
len(datiniEAC)
# %%
datiniEAC
# %%
prr = datiniRelevantStuff[list(datiniRelevantStuff.keys())[0]]['persona_mittente']
datiniEAC[prr]
# %%
def processDatini(obj):
    toRet = []
    for tag in ['persona_destinatario', 'persona_mittente', 'persona_indirizzata', 'persona_mano']:
        if obj[tag] != '':
            toRet.append(datiniEAC[obj[tag]])
    return toRet

out = {}
for sigla in antroponymsBySigla:
    out[sigla] = {}
    out[sigla]['sigla'] = sigla
    out[sigla]['ovi'] = antroponymsBySigla[sigla]
    out[sigla]['aspo'] = processDatini(datiniRelevantStuff[letterIDs[sigla]])
# %%
with open("temp.json", 'w') as outfile1:
    json.dump(out, outfile1, indent = 2)
# %%
aspos = []
tmp = [out[sigla]['aspo'] for sigla in out]
for list in tmp:
    aspos = aspos + list
# %%
asposIDs = set(map( lambda el: el['recordId'], aspos ))
# %%
len(asposIDs)
# %%
len(datiniEAC)
# %%
len(antroponyms)
# %%