mapparser.py

# -*- coding: utf-8 -*-
"""
Created on Wed Sep 24 09:33:04 2014

@author: vikramk3
"""

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Your task is to use the iterative parsing to process the map file and
find out not only what tags are there, but also how many, to get the
feeling on how much of which data you can expect to have in the map.
The output should be a dictionary with the tag name as the key
and number of times this tag can be encountered in the map as value.

Note that your code will be tested with a different data file than the 'example.osm'
"""
import xml.etree.ElementTree as ET
import pprint

def count_tags(filename):
    # I added elem.clear() after each iteration to avoid any memory issues with the iterative parsing
    total={}
    for event, elem in ET.iterparse(filename, events=("start", "end")):
        if event == "start" and elem.tag not in total:
            total[elem.tag]=1
        elif event== "start" and elem.tag in total:
            total[elem.tag]=total[elem.tag] + 1
        elem.clear()
    return total


def test():

    tags = count_tags('C:\\Users\\vikramk3\\Documents\\Courses\\Data_Wrangling\\austin_texas.osm')
    pprint.pprint(tags)


if __name__ == "__main__":
    test()