141 lines
3.8 KiB
Python
141 lines
3.8 KiB
Python
import re
|
|
from dataclasses import dataclass
|
|
import json
|
|
|
|
|
|
alinea_a = {}
|
|
|
|
|
|
@dataclass
|
|
class Process:
|
|
name: str
|
|
grau: str
|
|
proc_number: int
|
|
|
|
|
|
@dataclass
|
|
class Line:
|
|
folder: int
|
|
year: int
|
|
month: int
|
|
day: int
|
|
name: str
|
|
dad: str
|
|
mom: str
|
|
associated_processes: list[Process]
|
|
|
|
|
|
processes: dict[int, dict[int, dict[int, list[Line]]]] = {}
|
|
|
|
|
|
def main():
|
|
global processes
|
|
processes = load(None)
|
|
freq_proc_ano()
|
|
freq_nomes()
|
|
freq_relacao()
|
|
write_proc_to_json_file(None)
|
|
|
|
|
|
def freq_proc_ano():
|
|
freq = {}
|
|
for year in processes.keys():
|
|
for month in processes[year].keys():
|
|
for day in processes[year][month].keys():
|
|
if year not in freq:
|
|
freq[year] = 0
|
|
freq[year] += 1
|
|
return freq
|
|
|
|
|
|
def freq_nomes():
|
|
prop = {}
|
|
apelidos = {}
|
|
for year in processes.keys():
|
|
for month in processes[year].keys():
|
|
for day in processes[year][month].keys():
|
|
for entry in processes[year][month][day]:
|
|
spl = entry.name.split(" ")
|
|
if spl[0] not in prop:
|
|
prop[spl[0]] = 1
|
|
else:
|
|
prop[spl[0]] += 1
|
|
|
|
if spl[-1] not in apelidos:
|
|
apelidos[spl[-1]] = 1
|
|
else:
|
|
apelidos[spl[-1]] += 1
|
|
ret = {"prop": prop, "apelidos": apelidos}
|
|
return ret
|
|
|
|
|
|
def freq_relacao():
|
|
freq = {}
|
|
for year in processes.keys():
|
|
for month in processes[year].keys():
|
|
for day in processes[year][month].keys():
|
|
for entry in processes[year][month][day]:
|
|
for proc in entry.associated_processes:
|
|
if proc.grau not in freq:
|
|
freq[proc.grau] = 1
|
|
else:
|
|
freq[proc.grau] += 1
|
|
|
|
return freq
|
|
|
|
|
|
def write_proc_to_json_file(num_of_lines: int | None):
|
|
js = load(num_of_lines)
|
|
with open("processos.json", "w") as file:
|
|
file.write(json.dumps(js, default=vars, indent=4))
|
|
|
|
|
|
def load(num_of_lines: int | None):
|
|
output = {}
|
|
regex = (
|
|
r"(\d+)::(\d+)-(\d+)-(\d+)::([A-Za-z ]+)::([A-Za-z ]+)::([A-Za-z ]+)::(.*)::"
|
|
)
|
|
dataset = open("processos.txt", "r")
|
|
lines = dataset.readlines()
|
|
|
|
if num_of_lines is not None:
|
|
lines = lines[:num_of_lines]
|
|
|
|
for line in lines:
|
|
if line.strip() == "":
|
|
continue
|
|
matched_regex = re.match(regex, line)
|
|
if matched_regex is not None:
|
|
folder = int(matched_regex.group(1))
|
|
year = int(matched_regex.group(2))
|
|
month = int(matched_regex.group(3))
|
|
day = int(matched_regex.group(4))
|
|
name = matched_regex.group(5).split(",")[0]
|
|
dad = matched_regex.group(6).split(",")[0]
|
|
mom = matched_regex.group(7).split(",")[0]
|
|
|
|
proc_str = matched_regex.group(8)
|
|
regex2 = r"([A-Za-z ]+),([A-Za-z ]+)\. Proc\.(\d+)\. *"
|
|
proc_match = re.findall(regex2, proc_str)
|
|
|
|
proc_list = []
|
|
if proc_match is not None:
|
|
for match in proc_match:
|
|
proc_list.append(
|
|
Process(match[0].strip(), match[1].strip(), int(match[2]))
|
|
)
|
|
|
|
line_obj = Line(folder, year, month, day, name, dad, mom, proc_list)
|
|
if year not in output.keys():
|
|
output[year] = {}
|
|
if month not in output[year].keys():
|
|
output[year][month] = {}
|
|
if day not in output[year][month].keys():
|
|
output[year][month][day] = []
|
|
output[year][month][day].append(line_obj)
|
|
dataset.close()
|
|
return output
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|