commit: bb21b8615e64cb31fa9aa9d533ef328dc1374e45 Author: Matt Turner <mattst88 <AT> gentoo <DOT> org> AuthorDate: Fri Apr 17 18:03:02 2020 +0000 Commit: Matt Turner <mattst88 <AT> gentoo <DOT> org> CommitDate: Fri Apr 17 19:51:32 2020 +0000 URL: https://gitweb.gentoo.org/proj/catalyst.git/commit/?id=bb21b861
catalyst: gzip the .CONTENTS file Other algorithms give better compression ratios, but the difference is not meaningful for a 2MiB text file. In my testing bzip2 gave a better compression ratio of 15:1 vs gzip's 11:1, but that ends up being only a size difference of 50KiB (136 vs 187) which is only an additional 2.5% savings from the uncompressed input. Choose gzip because transparent decompression is widely supported by web servers and clients. Closes: https://bugs.gentoo.org/630284 Signed-off-by: Matt Turner <mattst88 <AT> gentoo.org> catalyst/base/genbase.py | 5 +++-- catalyst/support.py | 2 +- doc/HOWTO.txt | 6 +++--- 3 files changed, 7 insertions(+), 6 deletions(-) diff --git a/catalyst/base/genbase.py b/catalyst/base/genbase.py index eb09a4e0..3db20f84 100644 --- a/catalyst/base/genbase.py +++ b/catalyst/base/genbase.py @@ -2,6 +2,7 @@ import hashlib import io import os +import gzip class GenBase(): """ @@ -28,7 +29,7 @@ class GenBase(): def gen_contents_file(self, path): c = self.settings['contents_map'] - with io.open(path + '.CONTENTS', 'w', encoding='utf-8') as file: + with gzip.open(path + '.CONTENTS.gz', 'w', encoding='utf-8') as file: file.write(c.contents(path, '', verbose=self.settings['VERBOSE'])) def gen_digest_file(self, path): @@ -36,6 +37,6 @@ class GenBase(): return with io.open(path + '.DIGESTS', 'w', encoding='utf-8') as file: - for f in [path, path + '.CONTENTS']: + for f in [path, path + '.CONTENTS.gz']: for i in self.settings['digests']: file.write(self.generate_hash(f, name=i)) diff --git a/catalyst/support.py b/catalyst/support.py index 654b23aa..988a81f5 100644 --- a/catalyst/support.py +++ b/catalyst/support.py @@ -65,7 +65,7 @@ def file_check(filepath, extensions=None, strict=True): files = glob.glob("%s.*" % filepath) # remove any false positive files files = [x for x in files if not x.endswith( - ".CONTENTS") and not x.endswith(".DIGESTS")] + ".CONTENTS") and not x.endswith(".CONTENTS.gz") and not x.endswith(".DIGESTS")] if len(files) == 1: return files[0] if len(files) > 1 and strict: diff --git a/doc/HOWTO.txt b/doc/HOWTO.txt index 960b5761..7b759121 100644 --- a/doc/HOWTO.txt +++ b/doc/HOWTO.txt @@ -22,7 +22,7 @@ Create a snapshot of your current Portage tree (you may want to # catalyst --snapshot 20130131 # ls /var/tmp/catalyst/snapshots/ portage-20130131.tar.bz2 - portage-20130131.tar.bz2.CONTENTS + portage-20130131.tar.bz2.CONTENTS.gz portage-20130131.tar.bz2.DIGESTS where the storage location is relative to the default @@ -44,7 +44,7 @@ For example, Grab the tarball and put it where catalyst will find it: # wget http://…/stage3-amd64-20121213.tar.bz2 - # wget http://…/stage3-amd64-20121213.tar.bz2.CONTENTS + # wget http://…/stage3-amd64-20121213.tar.bz2.CONTENTS.gz # wget http://…/stage3-amd64-20121213.tar.bz2.DIGESTS.asc # sha512sum -c stage3-amd64-20121213.tar.bz2.DIGESTS.asc # gpg --verify stage3-amd64-20121213.tar.bz2.DIGESTS.asc @@ -89,7 +89,7 @@ which will build the target and install something like: # ls /var/tmp/catalyst/builds/default/stage1-amd64-2013.1.* /var/tmp/catalyst/builds/default/stage1-amd64-2013.1.tar.bz2 - /var/tmp/catalyst/builds/default/stage1-amd64-2013.1.tar.bz2.CONTENTS + /var/tmp/catalyst/builds/default/stage1-amd64-2013.1.tar.bz2.CONTENTS.gz /var/tmp/catalyst/builds/default/stage1-amd64-2013.1.tar.bz2.DIGESTS The name is an expansion of