Changeset 316

Timestamp:

06/26/2007 07:02:16 PM

Author:

luedi

Message:

#51: correctly encode text files, if the "svn:eol-style" is set to "native"
#54: generate a new UUID for each Dumpfile.pm
#53: optionally generate MD5 checksums for "Text-content"
#55: detect and remove unnecessary UNPIN/PIN activities
#56: detect and remove temporary .NET checkins

Files:

• trunk/script/Vss2Svn/Dumpfile.pm (modified) (7 diffs)
• trunk/script/devnotes.txt (modified) (1 diff)
• trunk/script/vss2svn.pl (modified) (7 diffs)

trunk/script/Vss2Svn/Dumpfile.pm

@@ -11 +11 @@
-
-use File::Copy;
+use Digest::MD5;
+use Data::UUID;
-
-our %gHandlers =
@@ -32 +34 @@
-our %gDeleted = ();
-our %gVersion = ();
+our $gTmpDir;
+
+###############################################################################
+#  SetTempDir
+###############################################################################
+sub SetTempDir {
+    my($class, $dir) = @_;
+
+    $gTmpDir = $dir;
+}  #  End SetTempDir
-
-###############################################################################
@@ -37 +49 @@
-###############################################################################
-sub new {
-
+, $md5
-
-    my $self =
@@ -48 +60 @@
-         repository => Vss2Svn::Dumpfile::SanityChecker->new(),
-         auto_props => $autoprops,
+         do_md5 => $md5,
-        };
-
@@ -58 +71 @@
-
-    print $fh "SVN-fs-dump-format-version: 2\n\n";
+    
+    my $ug    = new Data::UUID;
+    my $uuid = $ug->to_string( $ug->create() );
+    
+    print $fh "UUID: $uuid\n\n";
-
-    $self = bless($self, $class);
@@ -770 +788 @@
-    }
-
+    my $md5;
+    $md5 = Digest::MD5->new if $self->{do_md5};
+
+    # convert CRLF -> LF before calculating the size and compute the md5
+    if(!defined $text && defined $file) {
+        my ($input, $output);
+        my $style = $props->{'svn:eol-style'};
+        if (defined $style && $style eq 'native') {
+            open ($input, "<:crlf", $file);
+            my $tmpFile = "$gTmpDir/crlf_to_lf.tmp.txt";
+            open ($output, ">", $tmpFile);
+            binmode ($output);
+
+            while(<$input>) {
+                $md5->add($_) if $self->{do_md5};
+                print $output $_;
+            }
+            
+            close $input;
+            close $output;
+            $file = $tmpFile;
+        }
+        else {
+            open ($input, "<", $file);
+            binmode ($input);
+            $md5->addfile($input) if $self->{do_md5};
+            close $input;            
+        }
+    } else {
+        $md5->add($text) if $self->{do_md5};
+    }       
+    
+    my $digest = $md5->hexdigest if $self->{do_md5};
+#    print "digest: $digest\n";
+
-    if(!defined $text && defined $file) {
-        $textlen = -s $file;
@@ -783 +836 @@
-    if ($textlen > 0) {
-        print $fh "Text-content-length: $textlen\n";
+        print $fh "Text-content-md5: $digest\n" if $self->{do_md5};
-    }
-

trunk/script/devnotes.txt

@@ -13 +13 @@
-Config::Ini
-Text::Glob
+Digest::MD5
+Data::UUID
-
-SQLITE SCHEMA

trunk/script/vss2svn.pl

@@ -71 +71 @@
-            # Merge data from move actions 
-            MERGEMOVEDATA => {handler => \&MergeMoveData,
-
+
+
+
+
+
+
+
+
+
-
-            # Take the history of physical actions and convert them to VSS
@@ -774 +782 @@
-
-###############################################################################
+# RemoveTemporaryCheckIns
+# remove temporary checkins that where create to detect MS VSS capabilities
+###############################################################################
+sub RemoveTemporaryCheckIns {
+    my($sth, $rows, $row);
+    $sth = $gCfg{dbh}->prepare('SELECT * FROM PhysicalAction '
+                               . 'WHERE comment = "Temporary file created by Visual Studio .NET to detect Microsoft Visual SourceSafe capabilities."'
+                               . '      AND actiontype = "ADD"'
+                               . '      AND itemtype = 2');             # only delete files, not projects
+    $sth->execute();
+
+    # need to pull in all recs at once, since we'll be updating/deleting data
+    $rows = $sth->fetchall_arrayref( {} );
+
+    foreach $row (@$rows) {
+        my $physname = $row->{physname};
+        
+        my $sql = 'SELECT * FROM PhysicalAction WHERE physname = ?';
+        my $update = $gCfg{dbh}->prepare($sql);
+        
+        $update->execute( $physname );
+
+                    # need to pull in all recs at once, since we'll be updating/deleting data
+                    my $recs = $update->fetchall_arrayref( {} );
+                
+                    foreach my $rec (@$recs) {
+          print "Remove action_id $rec->{action_id}, $rec->{physname}, $rec->{actiontype}, $rec->{itemname}\n";
+          print "       $rec->{comment}\n" if defined ($rec->{comment});
+          &DeleteChildRec($rec->{action_id});
+        }
+                }
+
+    1;
+}
+
+###############################################################################
+#  MergeUnpinPinData
+###############################################################################
+sub MergeUnpinPinData {
+    my($sth, $rows, $row, $r, $next_row);
+    my $sql = 'SELECT * FROM PhysicalAction ORDER BY timestamp ASC, '
+                . 'itemtype ASC, priority ASC, parentdata ASC, sortkey ASC, action_id ASC';
+    $sth = $gCfg{dbh}->prepare($sql);
+    $sth->execute();
+ 
+    # need to pull in all recs at once, since we'll be updating/deleting data
+    $rows = $sth->fetchall_arrayref( {} );
+ 
+    return if ($rows == -1);
+    return if (@$rows < 2);
+ 
+    my @delchild = ();
+ 
+    for $r (0 .. @$rows-2) {
+        $row = $rows->[$r];
+        $next_row = $rows->[$r+1];
+        
+        if ($row->{actiontype} eq 'PIN' 
+            && !defined $row->{version}    # UNPIN
+            && $next_row->{actiontype} eq 'PIN' 
+            && defined $next_row->{version}   # PIN
+            && $row->{physname} eq $next_row->{physname}
+            && $row->{parentphys} eq $next_row->{parentphys}
+            && $next_row->{timestamp} - $row->{timestamp} < 60
+            && $next_row->{action_id} - $row->{action_id} == 1) {
+                print "found UNPIN/PIN combination for $row->{parentphys}/$row->{physname}"
+                    . "($row->{itemname}) @ ID $row->{action_id}\n"  if $gCfg{verbose};
+                push (@delchild, $row->{action_id});
+            }
+         
+    }
+ 
+    my $id;
+    foreach $id (@delchild) {
+        &DeleteChildRec($id);
+    }
+ 
+    1;
+ 
+}  #  End MergeUnpinPinData
+
+###############################################################################
-#  DeleteChildRec
-###############################################################################
@@ -951 +1041 @@
-
-    my $autoprops = Vss2Svn::Dumpfile::AutoProps->new($gCfg{auto_props}) if $gCfg{auto_props};
-
+
+
-
-REVISION:
@@ -1074 +1165 @@
-Dumpfile     : $gCfg{dumpfile}
-VSS Encoding : $gCfg{encoding}
+Auto Props   : $gCfg{auto_props}
+
-
-VSS2SVN ver  : $VERSION
@@ -1707 +1800 @@
-    GetOptions(\%gCfg,'vssdir=s','tempdir=s','dumpfile=s','resume','verbose',
-               'debug','timing+','task=s','revtimerange=i','ssphys=s',
-
+, 'md5'
-
-    &GiveHelp("Must specify --vssdir") if !defined($gCfg{vssdir});
@@ -1868 +1961 @@
-    --task <task>     : specify the task to resume; task is one of the following
-                        INIT, LOADVSSNAMES, FINDDBFILES, GETPHYSHIST,
-
+
+
-
-    --verbose         : Print more info about the items being processed
@@ -1878 +1972 @@
-                        converted repository (default = "/")
-    --auto_props      : Specify an autoprops ini file to use, e.g.
-
+
+
-EOTXT
-