sbosrcarch: hack around filename collision issue

1 files changed, 19 insertions, 10 deletions

diff --git a/sbosrcarch b/sbosrcarch
index 3bcdc7a..8e1956c 100755
--- a/sbosrcarch
+++ b/sbosrcarch
@@ -4,16 +4,18 @@
 our $DEBUG_HTTP = 0;
 #our $DEBUG_HTTP = 1;
 
-# TODO create_mode stats are wrong
+# hack to work around the fact that the download filenames for
+# a few builds are the same filename, but different files.
+# this list could be populated automatically, but it wouldn't have
+# changed in the past 3 years, so might as well hard-code it.
+our %url_filename_collisions = (
+	'http://hgwdev.cse.ucsc.edu/~kent/exe/opteron/blatSuite.34.zip' => 'blatSuite.34.zip.x86_64',
+	'https://www.perforce.com/downloads/perforce/r18.1/bin.linux26x86_64/p4' => 'p4.x86_64',
+	'https://www.perforce.com/downloads/perforce/r18.1/bin.linux26x86_64/p4d' => 'p4d.x86_64',
+	'https://ftp.mirrorservice.org/sites/download.salixos.org/x86_64/extra-14.2/source/libraries/p4api/p4api.tgz' => 'p4api.tgz.x86_64'
+);
 
-# FIXME 20151016 bkw: behold:
-#  $ grep ^D libraries/p4api/*.info
-#  DOWNLOAD="ftp://ftp.perforce.com/perforce/r10.1/bin.linux26x86/p4api.tgz"
-#  DOWNLOAD_x86_64="ftp://ftp.perforce.com/perforce/r10.1/bin.linux26x86_64/p4api.tgz"
-# notice that both URLs have the same filename (p4api.tgz)?  this is
-# exactly why we have a by-md5 tree. But right now, "add libraries/p4api"
-# only adds one of them. other builds with the same issue: development/p4
-# and academic/ucsc-blat
+# TODO create_mode stats are wrong
 
 # TODO based on feedback from ttkp and pink_mist on IRC:
 # - IPC::Open3 instead of open my $fh, "wget ...|"? At least use
@@ -22,7 +24,9 @@ our $DEBUG_HTTP = 0;
 #   stderr & stdout to the same place. Hm.
 
 # Also, stuff added with "add" sometimes ends up as separate files
-# instead of hardlinks. Not sure how to replicate this.
+# instead of hardlinks. Not sure how to replicate this. It hasn't
+# actually happened in ages, so probably I fixed it while working
+# on something else...
 
 # Ideas for future features:
 # - autopurge option for update. It only needs to purge the dirs that
@@ -545,6 +549,10 @@ sub blacklisted {
 # called e.g. "c++-utils.tar.gz" that would get broken by it.
 sub url_to_filename {
 	my $u = shift;
+
+	my $v = $url_filename_collisions{$u};
+	return $v if $v;
+
 	$u =~ s,.*/,,;
 	$u =~ s,%([0-9A-F]{2}),chr(hex($1)),ge;
 	return $u;
@@ -572,6 +580,7 @@ sub parse_info {
 	my @md5s = split " ", join " ", @md5lines;
 
 	my %ret;
+
 	for(@urls) {
 		my $m = shift @md5s;
 		#next if /^un(test|support)ed$/i; # no longer need