Segment the upload directory by package name prefix

This implements the following scheme:

* /packages/cower/ --> /packages/co/cower/
* /packages/j/     --> /packages/j/j/
* /packages/zqy/   --> /packages/zq/zqy/

We take up to the first two characters of each package name as a
intermediate subdirectory, and then the full package name lives
underneath that. Shorter named packages live in a single letter
directory.

Why, you ask? Well because earlier today the AUR hit 32,000 entries in
the unsupported/ directory, making new package uploads impossible. While
some might argue we shouldn't have so many damn packages in the repos,
we should be able to handle this case.

Why two characters instead of one? Our two biggest two-char groups, 'pe'
and 'py', both start with 'p', and have nearly 2000 packages each. Go
Python and Perl.

Still needed is a "move the existing data" script, as well as a set of
rewrite rules for those wishing to preserve backward compatible URLs for
any helper programs doing the wrong thing and relying on them.

Signed-off-by: Dan McGee <dan@archlinux.org>
Signed-off-by: Lukas Fleischer <archlinux@cryptocrack.de>
This commit is contained in:
Dan McGee 2011-08-09 17:01:13 -05:00 committed by Lukas Fleischer
parent 1f79258e81
commit 9a79d2105e
4 changed files with 21 additions and 13 deletions

View file

@ -22,17 +22,24 @@ include("pkgfuncs.inc.php");
$count = 0; $count = 0;
$files = scandir(INCOMING_DIR); $buckets = scandir(INCOMING_DIR);
foreach ($files as $pkgname) { foreach ($buckets as $bucket) {
$bucketpath = INCOMING_DIR . $bucket;
if ($bucket == '.' || $bucket == '..' || !is_dir($bucketpath)) {
continue;
}
$files = scandir(INCOMING_DIR . $bucket);
foreach ($files as $pkgname) {
if ($pkgname == '.' || $pkgname == '..') { if ($pkgname == '.' || $pkgname == '..') {
continue; continue;
} }
$fullpath = INCOMING_DIR . $pkgname; $fullpath = INCOMING_DIR . $bucket . "/" . $pkgname;
if (!package_exists($pkgname) && is_dir($fullpath)) { if (!package_exists($pkgname) && is_dir($fullpath)) {
echo 'Removing ' . $fullpath . "\n"; echo 'Removing ' . $fullpath . "\n";
rm_tree($fullpath); rm_tree($fullpath);
$count++; $count++;
} }
}
} }
echo "\nRemoved $count directories.\n"; echo "\nRemoved $count directories.\n";

View file

@ -256,7 +256,7 @@ if ($uid):
} }
if (isset($pkg_name)) { if (isset($pkg_name)) {
$incoming_pkgdir = INCOMING_DIR . $pkg_name; $incoming_pkgdir = INCOMING_DIR . substr($pkg_name, 0, 2) . "/" . $pkg_name;
} }
if (!$error) { if (!$error) {
@ -268,7 +268,8 @@ if ($uid):
rm_tree($incoming_pkgdir); rm_tree($incoming_pkgdir);
} }
if (!@mkdir($incoming_pkgdir)) { # The mode is masked by the current umask, so not as scary as it looks
if (!mkdir($incoming_pkgdir, 0777, true)) {
$error = __( "Could not create directory %s.", $incoming_pkgdir); $error = __( "Could not create directory %s.", $incoming_pkgdir);
} }
} else { } else {
@ -286,7 +287,7 @@ if ($uid):
} }
if (!$error) { if (!$error) {
if (!@chdir($incoming_pkgdir)) { if (!chdir($incoming_pkgdir)) {
$error = __("Could not change directory to %s.", $incoming_pkgdir); $error = __("Could not change directory to %s.", $incoming_pkgdir);
} }

View file

@ -125,7 +125,7 @@ class AurJSON {
$search_data = array(); $search_data = array();
while ( $row = mysql_fetch_assoc($result) ) { while ( $row = mysql_fetch_assoc($result) ) {
$name = $row['Name']; $name = $row['Name'];
$row['URLPath'] = URL_DIR . $name . "/" . $name . ".tar.gz"; $row['URLPath'] = URL_DIR . substr($name, 0, 2) . "/" . $name . "/" . $name . ".tar.gz";
if ($type == 'info') { if ($type == 'info') {
$search_data = $row; $search_data = $row;

View file

@ -90,7 +90,7 @@ $out_of_date_time = ($row["OutOfDateTS"] == 0) ? $msg : gmdate("r", intval($row[
<p><span class='f3'> <p><span class='f3'>
<?php <?php
$urlpath = URL_DIR . $row['Name']; $urlpath = URL_DIR . substr($row['Name'], 0, 2) . "/" . $row['Name'];
print "<a href='$urlpath/" . $row['Name'] . ".tar.gz'>".__("Tarball")."</a> :: "; print "<a href='$urlpath/" . $row['Name'] . ".tar.gz'>".__("Tarball")."</a> :: ";
print "<a href='$urlpath/PKGBUILD'>".__("PKGBUILD")."</a></span>"; print "<a href='$urlpath/PKGBUILD'>".__("PKGBUILD")."</a></span>";