Contraloria

generate_rows.py

#!/usr/bin/python3
import sys
import re

def get_file_data(file_name):
    
    cleaned = file_name \
                .replace('PERDOMO2016_1', 'PERDOMO_2016_1') \
                .replace('SOSARIELLA_216', 'SOSARIELLA_2016') \
                .replace('221.035', '221035') \
                .replace('991712_8', '991712#8') \
                .replace("_.pdf", "") \
                .replace(".pdf", "") \
                .strip() \
                .replace("\n", "") \
                .replace("-", "_") \
                .replace(" ", "_") \
                .replace(".", "_")

    parts = cleaned.split("_")

    # print('\n')
    # print(file_name.replace("\n", ""))
    # print(cleaned)
    # print(parts)
    document = parts[0]

    name = ''
    last = 'name'
    year = '2016'
    version = '1'
    for part in parts[1:]:
        if last == 'name':
            if part.isdigit():
                last = 'year'
                year = part
            else:
                name += ' ' + part
        if last == 'year':
            version = part

    if year == '216':
        year = '2016'

    return {
            'file_name': file_name.replace("\n", ""),
            'document': document,
            'name': name.strip(),
            'year': year,
            'version': version
           }


if len(sys.argv) < 2:
    raise Exception('Usage: python3 generate_rows.py FILE')

FILE_NAME=sys.argv[1]

print("Reading file: " + FILE_NAME)

with open(FILE_NAME, "r") as file:
    for line in file: 
        if '(1)' in line or '(2)' in line:
            continue
        data = get_file_data(line)
        if not data['year'].isdigit() or int(data['year']) < 1990:
            raise Exception('invalid year: ' + data['year'])
        if not data['version'].isdigit():
            raise Exception('invalid year: ' + data['version'])
        print(data)