small script for filtering Wiki Monkey's logs
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
#! /usr/bin/env python | |
import sys | |
import json | |
class PackageTemplatesFilter: | |
def __init__(self): | |
self.pages = {} | |
def add_log(self, logfile): | |
lines = open(logfile, "r").readlines() | |
title = "" | |
for line in lines: | |
s = line.split(maxsplit=2) | |
if len(s) < 3: | |
print("Unexpected log format on line %d in file %s" % (lines.index(line), logfile), file=sys.stderr) | |
break | |
timestamp, level, msg = s | |
# detect warnings for packages not found in any repo | |
if level == "JSN": | |
data = json.loads(msg)["data"] | |
title = data["page"] | |
lang = data["pagelanguage"] | |
pkg = data["package"] | |
assert data["error"] == "notfound" | |
if lang not in self.pages: | |
self.pages[lang] = {} | |
if title in self.pages[lang]: | |
self.pages[lang][title].append(pkg) | |
else: | |
self.pages[lang][title] = [pkg] | |
def report(self): | |
report = "" | |
for lang in sorted(self.pages.keys()): | |
report += "== %s ==\n" % lang | |
pages = self.pages[lang] | |
for title in sorted(pages.keys()): | |
report += "* [[%s]]\n" % title | |
for pkg in pages[title]: | |
report += "** %s\n" % pkg | |
return report | |
if __name__ == "__main__": | |
f = PackageTemplatesFilter() | |
for log in sys.argv[1:]: | |
f.add_log(log) | |
print(f.report()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment