Created
June 15, 2011 16:14
-
-
Save tebeka/1027445 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python | |
| data = '''GEOMETRYCOLLECTION ( | |
| POINT (-8.9648437500000000 -4.1308593750000000), | |
| POINT (2.0214843750000000 -2.6367187500000000), | |
| POINT (-1.4062500000000000 -11.1621093750000000), | |
| POINT (-11.9531250000000000 -10.8984375000000000), | |
| POLYGON | |
| ((-21.6210937500000000 1.8457031250000000,2.4609375000000000 | |
| 2.1972656250000000, -18.9843750000000000 -3.6914062500000000, | |
| -22.6757812500000000 -3.3398437500000000, -22.1484375000000000 | |
| -2.6367187500000000, -21.6210937500000000 | |
| 1.8457031250000000)), | |
| LINESTRING (-11.9531250000000000 | |
| 11.3378906250000000, 7.7343750000000000 11.5136718750000000, | |
| 12.3046875000000000 2.5488281250000000, 12.2167968750000000 | |
| 1.6699218750000000, 14.5019531250000000 3.9550781250000000))''' | |
| import re | |
| from collections import defaultdict | |
| from pprint import pprint | |
| prefix = len("GEOMETRYCOLLECTION") | |
| shapes = defaultdict(list) | |
| for match in re.finditer("([A-Z]+)\s*(\(+[^)]+\))+", data[prefix:]): | |
| type = match.group(1) | |
| matches = re.finditer("(-?\d+\.\d+)\s*(-?\d+\.\d+)", match.group(2)) | |
| coords = [(float(m.group(1)), float(m.group(2))) for m in matches] | |
| shapes[type].append(coords) | |
| pprint(dict(shapes)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment