Xah's parsing challenge - answered in python

# Wish I'd been up for writing an elisp version!  This is from 2011-11.  My blog is offline at the moment.  -kurt

# https://plus.google.com/u/0/113859563190964307534/posts/aqmFrjcY7WH
#Here is my answers to emacs lisp exercise: latitude-longitude-decimalize. The first is dumb. It hard codes #the characters, which I think source-highlight mangled pretty badly. The code wasn't very pretty to start #with. The second solution is much more robust. It allows and character(s) to be the separator(s).


#!/usr/bin/env python
# -*- coding: utf-8 -*-

test_data = r"37ÃÇ°26âÂIJ36.42âÂijN 06ÃÇ°15âÂIJ14.28âÂijW"

def decimal_deg_simple(coord_str):
    lat_str, lon_str = coord_str.split()
    lat = int(lat_str.split('ÃÇ°')[0])
    lat += int(lat_str.split('ÃÇ°')[1].split('âÂIJ')[0]) / 60.
    lat += float(lat_str.split('âÂIJ')[1][:-4]) / 3600.
    if 'S' in lat_str:
        lat = -lat

    lon = int(lon_str.split('ÃÇ°')[0])
    lon += int(lon_str.split('ÃÇ°')[1].split('âÂIJ')[0]) / 60.
    lon += float(lon_str.split('âÂIJ')[1][:-4]) / 3600.
    if 'W' in lon_str:
        lon = -lon

    return lat,lon

print 'simple:', decimal_deg_simple(test_data)

########################################
# Use a regular expression

import re

rawstr = r"""(?P<lat_deg>\d{1,2})\D+
(?P<lat_min>\d{1,2})\D+
(?P<lat_sec>\d{1,2}(\.\d+))\D+
(?P<lat_hemi>[NS])
\s+
(?P<lon_deg>\d{1,3})\D+
(?P<lon_min>\d{1,2})\D+
(?P<lon_sec>\d{1,2}(\.\d+))\D+
(?P<lon_hemi>[EW])
"""

compile_obj = re.compile(rawstr,  re.VERBOSE)

def decimal_deg_re(coord_str):
    g = compile_obj.search(coord_str).groupdict() # m is match
    lat = int(g['lat_deg']) + int(g['lat_min'])/60. + float(g['lat_sec']) / 3600.
    if g['lat_hemi'] == 'S':
        lat = -lat
    lon = int(g['lon_deg']) + int(g['lon_min'])/60. + float(g['lon_sec']) / 3600.
    if g['lon_hemi'] == 'S':
        lon = -lon
    return {'y':lat, 'x':lon}

print 're:', decimal_deg_re(test_data)