From 5e9b556183aeb2bf809a7f5300f560fd87e143be Mon Sep 17 00:00:00 2001
From: Zbigniew Jędrzejewski-Szmek <zbyszek@in.waw.pl>
Date: Dec 17 2017 21:02:14 +0000
Subject: Paralellize


This brings down the wall-clock time down approximately proportionally
to the number of CPUs (or possibly even more, e.g. here 16 min 44 went
down to less then 1 min with 12 CPUs).

I added a loop on failure. Unfortunately sometimes the server returns
an invalid answer. That also happens when running serially, but it
seems to happen more often in parallelized mode.

---

diff --git a/find-package-maintainers b/find-package-maintainers
index 00820b4..d16393e 100755
--- a/find-package-maintainers
+++ b/find-package-maintainers
@@ -3,6 +3,7 @@
 import argparse
 import requests
 import sys
+import multiprocessing
 
 VERBOSE = False
 
@@ -37,7 +38,6 @@ def get_maintainers(pkg):
     vprint('Fetched maintainers of {}: {}'.format(pkg, ', '.join(maintainers)))
     return maintainers
 
-
 def options_parse():
     p = argparse.ArgumentParser(
         description='Find maintainers given package names')
@@ -62,13 +62,14 @@ def main():
     by_package = {}
     opts = options_parse()
 
-    for package in opts.infile:
-        package = package.strip()
-        try:
-            by_package[package] = get_maintainers(package)
-        except PkgdbError as e:
-            print('ERR: {}'.format(e), file=sys.stderr)
-            continue
+    packages = [line.strip() for line in opts.infile]
+    with multiprocessing.Pool() as pool:
+        mapped = pool.map(get_maintainers, packages)
+    for package, mapping in zip(packages, mapped):
+        if isinstance(mapping, Exception):
+            print('ERR: {}: {}'.format(package, mapping), file=sys.stderr)
+        else:
+            by_package[package] = mapping
 
     if not by_package:
         print('No valid packages given.')