generate_ids.py

import glob
import os

unknown_location_acronym = 'tbd'

# https://gist.github.com/rogerallen/1583593
us_state_to_abbrev = {
    'Alabama': 'AL',
    'Alaska': 'AK',
    'American Samoa': 'AS',
    'Arizona': 'AZ',
    'Arkansas': 'AR',
    'California': 'CA',
    'Colorado': 'CO',
    'Connecticut': 'CT',
    'Delaware': 'DE',
    'District of Columbia': 'DC',
    'Florida': 'FL',
    'Georgia': 'GA',
    'Guam': 'GU',
    'Hawaii': 'HI',
    'Idaho': 'ID',
    'Illinois': 'IL',
    'Indiana': 'IN',
    'Iowa': 'IA',
    'Kansas': 'KS',
    'Kentucky': 'KY',
    'Louisiana': 'LA',
    'Maine': 'ME',
    'Maryland': 'MD',
    'Massachusetts': 'MA',
    'Michigan': 'MI',
    'Minnesota': 'MN',
    'Mississippi': 'MS',
    'Missouri': 'MO',
    'Montana': 'MT',
    'Nebraska': 'NE',
    'Nevada': 'NV',
    'New Hampshire': 'NH',
    'New Jersey': 'NJ',
    'New Mexico': 'NM',
    'New York': 'NY',
    'North Carolina': 'NC',
    'North Dakota': 'ND',
    'Northern Mariana Islands':'MP',
    'Ohio': 'OH',
    'Oklahoma': 'OK',
    'Oregon': 'OR',
    'Pennsylvania': 'PA',
    'Puerto Rico': 'PR',
    'Rhode Island': 'RI',
    'South Carolina': 'SC',
    'South Dakota': 'SD',
    'Tennessee': 'TN',
    'Texas': 'TX',
    'Utah': 'UT',
    'Vermont': 'VT',
    'Virgin Islands': 'VI',
    'Virginia': 'VA',
    'Washington': 'WA',
    'Washington DC': 'DC',
    'West Virginia': 'WV',
    'Wisconsin': 'WI',
    'Wyoming': 'WY',
    'Unknown Location': unknown_location_acronym,
}

def gen_id_text(text, state_abbrev):
    new_lines = []
    city = ''
    city_abbrev = ''
    if state_abbrev == unknown_location_acronym:
        city_abbrev = unknown_location_acronym
    if state_abbrev == 'dc':
        city_abbrev = 'dc'
    city_prefix = '## '
    city_index = 1
    for line in text.splitlines():
        line = line.strip()
        if line.startswith(city_prefix):
            city = line[len(city_prefix):].strip()
            # transform the city name to a more id-friendly string
            city_abbrev = city.replace(' ', '').replace('.', '').lower()
        if '**Links**' in line:
            # Links are starting, use this section to add an id
            id_line = f'pb-id: {state_abbrev}-{city_abbrev}-{city_index}'
            #print(id_line)
            new_lines.append(id_line)
            new_lines.append('')
            city_index += 1
        elif 'link' in line.lower():
            print(f"Found a links in: {line} but did not process")
        new_lines.append(line)
    
    return '\n'.join(new_lines)


if __name__ == "__main__":
    src_dir = os.path.relpath(os.path.dirname(__file__))
    md_dir = os.path.join(src_dir, '..', 'reports')

    for md_file in glob.glob(md_dir + '/*.md'):
        print(f"Reading '{os.path.basename(md_file)}'")
        with open(md_file, 'rb') as fin:
            fname = os.path.basename(md_file)
            state_name = fname.replace('.md', '')
            state_abbrev = us_state_to_abbrev[state_name].lower()
            text = fin.read().decode('utf-8')
            new_text = gen_id_text(text=text, state_abbrev=state_abbrev)
        
        with open(md_file, 'wb') as fout:
            fout.write(new_text.encode('utf-8'))