From 9b3f1717ed84c11d5df27c9594b76acd444a0e13 Mon Sep 17 00:00:00 2001
From: "B. Watson" <yalhcru@gmail.com>
Date: Sun, 24 Jun 2018 23:18:32 -0400
Subject: sbosrcarch: add by-md5 stats to check/status

---
 sbosrcarch | 59 ++++++++++++++++++++++++++++++++++++++---------------------
 1 file changed, 38 insertions(+), 21 deletions(-)

(limited to 'sbosrcarch')

diff --git a/sbosrcarch b/sbosrcarch
index 2b49c22..72c3cdb 100755
--- a/sbosrcarch
+++ b/sbosrcarch
@@ -402,9 +402,11 @@ our $extraneous_byname = 0;
 
 our %infofilecount;
 our %parsedinfo;
+our %allmd5sums;
 our $symlinkcount = 0;
 our $hardlinkcount = 0;
 our $filecount = 0;
+our $md5_filecount = 0;
 our $filebytes = 0;
 our $actualfilecount = 0;
 our $totalfiles = 0;
@@ -1630,8 +1632,6 @@ sub check_bymd5_wanted {
 		return;
 	}
 
-	my $realmd5 = md5sum_file($_) || return;
-
 	my (undef, $a, $b, $md5dir, $filename, $extra) = split /\//;
 
 	if(!defined($filename) || defined($extra)) {
@@ -1650,14 +1650,25 @@ sub check_bymd5_wanted {
 		}
 	}
 
-	my $reala = substr($realmd5, 0, 1);
-	my $realb = substr($realmd5, 1, 1);
-	if($reala ne $a || $realb ne $b) {
-		print "$_: wrong subdir (should be $reala/$realb/$realmd5)\n";
+	if(!$quickcheck) {
+		my $realmd5 = md5sum_file($_) || return;
+		my $reala = substr($realmd5, 0, 1);
+		my $realb = substr($realmd5, 1, 1);
+		if($reala ne $a || $realb ne $b) {
+			print "$_: wrong subdir (should be $reala/$realb/$realmd5)\n";
+			return;
+		}
+
+		if($realmd5 ne $md5dir) {
+			print "$_: md5sum mismatch\n";
+			return;
+		}
 	}
 
-	if($realmd5 ne $md5dir) {
-		print "$_: md5sum mismatch\n";
+	if($allmd5sums{$md5dir}) {
+		print "$_ extraneous: not mentioned in any .info file\n" if $verbosecheck;
+	} else {
+		$md5_filecount++;
 	}
 }
 
@@ -1682,6 +1693,7 @@ sub check_info_wanted {
 	$totalfiles += keys %$dls;
 	$infofilecount{"$category/$prgnam"} += keys %$dls;
 	$parsedinfo{"$category/$prgnam"} = $dls;
+	$allmd5sums{$_}++ for values %$dls;
 }
 
 sub check_mode {
@@ -1700,10 +1712,8 @@ sub check_mode {
 	print "* Checking by-name tree...\n";
 	find({wanted => \&check_byname_wanted, no_chdir => 1}, "by-name");
 
-	if(!$quickcheck) {
-		print "* Checking by-md5 tree...\n";
-		find({wanted => \&check_bymd5_wanted, no_chdir => 1}, "by-md5");
-	}
+	print "* Checking by-md5 tree...\n";
+	find({wanted => \&check_bymd5_wanted, no_chdir => 1}, "by-md5");
 
 	my @missingfilebuilds;
 	for(keys %infofilecount) {
@@ -1711,16 +1721,16 @@ sub check_mode {
 		push @missingfilebuilds, $_ if $count;
 	}
 
-	print "---\n";
+	if($symlinkcount && $hardlinkcount) {
+		print "by-md5 contains both symlinks and hardlinks (harmless but messy)\n";
+	}
+
+	print "--- by-name summary\n";
 	if(@missingfilebuilds) {
-		print "Following SlackBuilds are missing files:\n";
+		print "Following SlackBuilds are missing by-name files:\n";
 		print "  $_\n" for sort { $a cmp $b } @missingfilebuilds;
 	} else {
-		print "All SlackBuild download files present\n";
-	}
-
-	if($symlinkcount && $hardlinkcount) {
-		print "by-md5 contains both symlinks and hardlinks (harmless but messy)\n";
+		print "All SlackBuild download files present in by-name.\n";
 	}
 
 	my $totalbuildcount = keys %infofilecount;
@@ -1731,15 +1741,22 @@ sub check_mode {
 	my $missingfiles = $totalfiles - $filecount;
 	my $filecoverage = sprintf("%.2f", $filecount * 100 / $totalfiles);
 
+	my $md5_totalfiles = keys %allmd5sums;
+	my $md5_missingfiles = $md5_totalfiles - $md5_filecount;
+	my $md5_filecoverage = sprintf("%.2f", $md5_filecount * 100 / $md5_totalfiles);
+
 	print <<EOF;
----
 Total source files: $totalfiles
 Archived files: $filecount
 Archive size: $filemegs
 Missing files: $missingfiles
 Extraneous files: $extraneous_byname
 File coverage: $filecoverage%
-
+--- by-md5 summary:
+Total source files: $md5_totalfiles
+Missing files: $md5_missingfiles
+File coverage: $md5_filecoverage%
+---
 Total SlackBuilds: $totalbuildcount
 SlackBuilds with all files present: $completebuildcount
 SlackBuilds missing at least one file: $missingbuildcount
-- 
cgit v1.2.3