autoimport: stream package list and use generic decompressor

 * streaming means that we do not need to hold the entire package list
   in memory (but the pkgs dict will become large anyway).
 * The decompress utility allows easily switching to e.g. xz which is
   the only compression format for the dbgsym suites.

1 files changed, 4 insertions, 5 deletions

diff --git a/autoimport.py b/autoimport.py
index bbe5029..94358b6 100755
--- a/autoimport.py
+++ b/autoimport.py
@@ -4,9 +4,7 @@ packages contained. It has rather strong assumptions on the working directory.
 """
 
 import argparse
-import gzip
 import errno
-import io
 import multiprocessing
 import os
 import sqlite3
@@ -26,12 +24,13 @@ import concurrent.futures
 from debian import deb822
 from debian.debian_support import version_compare
 
+from dedup.compression import decompress
+
 from readyaml import readyaml
 
 def process_http(pkgs, url):
-    pkglist = urlopen(url + "/dists/sid/main/binary-amd64/Packages.gz").read()
-    pkglist = gzip.GzipFile(fileobj=io.BytesIO(pkglist)).read()
-    pkglist = io.BytesIO(pkglist)
+    pkglist = urlopen(url + "/dists/sid/main/binary-amd64/Packages.gz")
+    pkglist = decompress(pkglist, ".gz")
     pkglist = deb822.Packages.iter_paragraphs(pkglist)
     for pkg in pkglist:
         name = pkg["Package"]