Created
April 28, 2016 12:41
-
-
Save reinout/90773bc811bade5f5e020a92516b3f59 to your computer and use it in GitHub Desktop.
This file contains 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
"""Script to report on geoserver layer usage. | |
I've run it on p-web-map-d9 like this:: | |
cd /var/log/nginx | |
mkdir /tmp/logs | |
cp access.log* /tmp/logs/ | |
cd /tmp/logs | |
gunzip *.gz | |
cat access.log* |grep -v ^127.0.0.1 > alles.txt | |
rm access.log* | |
grep -v HEAD alles.txt > alles_zonder_HEAD.txt | |
cat alles_zonder_HEAD.txt |grep -i wms|grep geoserver > geoserver_wms.txt | |
cat geoserver_wms.txt |grep -i layers > geoserver_wms_layers.txt | |
python extract.py | |
""" | |
from collections import defaultdict | |
from pprint import pprint | |
import re | |
import sys | |
REGEX = re.compile(""" | |
.* | |
/geoserver/ | |
(?P<category>[^/]+) | |
/wms | |
.* | |
LAYERS= | |
(?P<layers>[^\&]+) | |
.* | |
""", re.VERBOSE) | |
def main(): | |
categories = {} | |
for index, line in enumerate(open('geoserver_wms_layers.txt')): | |
match = REGEX.search(line) | |
if match: | |
category_name = match.group('category') | |
if category_name not in categories: | |
categories[category_name] = {} | |
category = categories[category_name] | |
layer_names = match.group('layers').split(',') | |
for layer_name in layer_names: | |
if layer_name not in category: | |
category[layer_name] = 0 | |
category[layer_name] += 1 | |
# if index > 20000: | |
# break | |
counts_plus_categories = sorted( | |
[(sum(category.values()), category_name) for (category_name, category) in categories.items()]) | |
counts_plus_categories.reverse() | |
sorted_category_names = [name for count, name in counts_plus_categories] | |
for category_name in sorted_category_names: | |
layers = categories[category_name] | |
title = "Category '%s' (%s hits)" % (category_name, sum(layers.values())) | |
print(title) | |
print("=" * len(title)) | |
print('') | |
counts_plus_layers = sorted([(count, name) for (name, count) in layers.items()]) | |
counts_plus_layers.reverse() | |
for (count, name) in counts_plus_layers: | |
print(" %s\t%s" % (count, name)) | |
print('') | |
print('') | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment