Browse Source

Code and data push

master
Alarig Le Lay 2 years ago
parent
commit
2b8f378a9d
No known key found for this signature in database
GPG Key ID: C865491BF197B54F
  1. 4749
      2020-1 SubdivisionCodes.csv
  2. 50820
      2020-1 UNLOCODE CodeListPart1.csv
  3. 27246
      2020-1 UNLOCODE CodeListPart2.csv
  4. 33832
      2020-1 UNLOCODE CodeListPart3.csv
  5. BIN
      2020-1 UNLOCODE SecretariatNotes.pdf
  6. 10
      README.md
  7. 94
      get-city-code.py

4749
2020-1 SubdivisionCodes.csv

File diff suppressed because it is too large Load Diff

50820
2020-1 UNLOCODE CodeListPart1.csv

File diff suppressed because it is too large Load Diff

27246
2020-1 UNLOCODE CodeListPart2.csv

File diff suppressed because it is too large Load Diff

33832
2020-1 UNLOCODE CodeListPart3.csv

File diff suppressed because it is too large Load Diff

BIN
2020-1 UNLOCODE SecretariatNotes.pdf

Binary file not shown.

10
README.md

@ -1,3 +1,11 @@
# UNLOCODE-lookup
Python3 script to find a city 3-letters code from UN/LOCODE
Python3 script to find a city 3-letters code from UN/LOCODE
## Usage
Every help should be avaible in the `--help` output.
## Updating data
To update data, go to
http://www.unece.org/cefact/codesfortrade/codes_index.html to download the CSV
archive and uncompress it in this directory.

94
get-city-code.py

@ -0,0 +1,94 @@
#!/usr/bin/env python
import argparse
import csv
import os
import re
import sys
# CSV structure:
# 0 empty
# 1 iso country code
# 2 city code
# 3 full name
# the rest is unused
parser = argparse.ArgumentParser(description='''Find cities code from UNLOCODE.
If the exact name is found when a country code is given, only this match will
be shown, all the MATCHES are displayed otherwise. The font case isnt taken in
%s/EXACT_MATCH/EXACT_MATCH/account but the accents are. ''')
parser.add_argument('--city', dest='city', type=str, required=True,
help='City name, will be looked for inside the CSV files')
parser.add_argument('--country', dest='country', type=str, required=False,
default='', help='''Country name, in ISO-3166 format, to narrow queries if
needed''')
args = parser.parse_args()
files = [file for file in os.listdir('.') if os.path.isfile(file)]
if len(files) == 0:
print('ERROR: No CSV file has been found.')
sys.exit(1)
def csvprocessing(city):
"""Tries to find the wanted city code into the list `city`."""
if (args.city.lower() == city[3].lower() and
args.country.lower() == city[1].lower()):
EXACT_MATCH.append(city)
if args.city.lower() == city[3].lower() and len(args.country) == 0:
MULTIPLE_MATCHES.append(city)
elif args.city.lower() in city[3].lower():
MATCHES.append(city)
def csvloop(file):
"""Loop over the lines of the CSV file. We have one list per line."""
entries = csv.reader(file)
for entry in entries:
if len(args.country) > 0:
if args.country.lower() == entry[1].lower():
csvprocessing(entry)
else:
pass
else:
csvprocessing(entry)
def print_results(exactitude, result_list):
"""Stupid function to print results based on very basic formating
condition."""
for match in result_list:
if re.match(r"^([A-Z]+)$", match[1]) and len(match[2]) > 0:
print('{} {} found for {} from country {}'.format(
exactitude, match[2], match[3], match[1]
))
# Global variables needed on the used functions
global MATCHES
global EXACT_MATCH
global MULTIPLE_MATCHES
MATCHES = []
EXACT_MATCH = []
MULTIPLE_MATCHES = []
# We look for all the CSV files in the current dir
for dir_file in files:
if re.match(r".*\.csv", dir_file, re.I):
# We can’t assume that CSV file is utf-8 encoded
try:
with open(dir_file) as csvfile:
csvloop(csvfile)
except UnicodeDecodeError:
with open(dir_file, encoding='latin-1') as csvfile:
csvloop(csvfile)
# If the country has been provided
if len(EXACT_MATCH) > 0:
print_results('Exact match', EXACT_MATCH)
# If the country hasn’t been provided but the cit(y|es) exist(s)
elif len(MULTIPLE_MATCHES) > 0:
print_results('Multiple MATCHES', MULTIPLE_MATCHES)
# Otherwise, throw some garbage to the user
else:
print_results('Non-exact MATCHES', MATCHES)
Loading…
Cancel
Save