The following commit has been merged in the master branch:
commit b997ba1a1938510ecb432dee7bf2c5cd66a3c8b4
Author: Cyril Brulebois <[email protected]>
Date: Tue Feb 21 03:06:08 2012 +0100
Bug#657557: [PATCH 4/4] Extract English translations before processing
packages.
Since long descriptions are determined using English translations (for
some suites only, right now), it's needed to process them before
Packages files are processed.
diff --git a/bin/parse-packages b/bin/parse-packages
index b926982..e75a500 100755
--- a/bin/parse-packages
+++ b/bin/parse-packages
@@ -60,8 +60,8 @@ $/ = "";
mkpath( "$DBDIR/xapian.new" );
# Needed to compensate removal of long descriptions from Packages files:
-my %descriptions_translated_db;
-tie %descriptions_translated_db, "DB_File",
"files/db/descriptions_translated.db", O_RDONLY, 0666, $DB_BTREE;
+my %descriptions_english_db;
+tie %descriptions_english_db, "DB_File",
"files/db/descriptions_translated_english_only.db", O_RDONLY, 0666, $DB_BTREE;
for my $suite (@SUITES) {
my %package_names_suite = ();
@@ -139,11 +139,13 @@ for my $suite (@SUITES) {
if ($data{'description-md5'}) {
# The short description is a nice fallback:
my $description = $data{'description'};
- my $lookup =
$descriptions_translated_db{$data{'description-md5'}};
+ my $lookup =
$descriptions_english_db{$data{'description-md5'}};
if ($lookup) {
+ # There should only be an English translation
+ # in there, but let's make sure:
while ($lookup =~ /([^\001]*)\001([^\000]*)\000/g) {
- my ($language, $translated_description) = ($1, $2);
- $description = $translated_description
+ my ($language, $english_description) = ($1, $2);
+ $description = $english_description
if $language eq 'en';
}
$data{'description'} = $description;
@@ -215,7 +217,7 @@ for my $suite (@SUITES) {
untie %packages_all_db;
}
-untie %descriptions_translated_db;
+untie %descriptions_english_db;
print "Writing databases...\n";
my %packages_small_db;
diff --git a/cron.d/200process_archive b/cron.d/200process_archive
index b8f6a6d..29a7385 100755
--- a/cron.d/200process_archive
+++ b/cron.d/200process_archive
@@ -5,6 +5,8 @@
cd "$topdir"
date
+./bin/parse-translations --english-only
+date
./bin/parse-packages
date
./bin/parse-sources
--
APT Archive Web-Frontend (Alioth repository)
--
To UNSUBSCRIBE, email to [email protected]
with a subject of "unsubscribe". Trouble? Contact [email protected]
