Toby Johnson wrote:
>
> Gotcha. I'll close ticket 26 and open another to add an encoding switch
> to ssphys.
>
I have written a patch for
<http://www.pumacode.org/projects/vss2svn/ticket/44>
Since I have technical problems at work with running vss2svn from the
source, I cannot test it with my VSS repository.
I know this isn't a healthy way to submit patches, but I think it will
at least help speed the ticket along, and since I made changes to ssphys
it can basically be tested with a regular latin-codepage VSS repository.
There is a chance it may not run at all, though :)
I've added an encoding flag to the xml formatter of ssphys with a
default value of windows-1252, and a matching flag for vss2svn.pl (also
with a default).
Regarding DoSsCMD() in vss2svn.pl, the character range removed from the
output is correct for *most* windows codepages, since all of them
re-define just the lower part of windows-1255.
Arabic, for example, has rarely used characters in 0x8D and 0x90
<http://en.wikipedia.org/wiki/Windows-1256>
-Ori
Index: script/vss2svn.pl
===================================================================
--- script/vss2svn.pl (revision 272)
+++ script/vss2svn.pl (working copy)
@@ -106,7 +106,7 @@
# LoadVssNames
###############################################################################
sub LoadVssNames {
- &DoSsCmd("info \"$gCfg{vssdatadir}/names.dat\"");
+ &DoSsCmd("info -e$gCfg{encoding} \"$gCfg{vssdatadir}/names.dat\"");
my $xs = XML::Simple->new(KeyAttr => [],
ForceArray => [qw(NameCacheEntry Entry)],);
@@ -246,7 +246,7 @@
return;
}
- &DoSsCmd("info \"$filesegment[0]/$filesegment[1]/$filesegment[2]\"");
+ &DoSsCmd("info -e$gCfg{encoding} \"$filesegment[0]/$filesegment[1]/$filesegment[2]\"");
my $xml = $xs->XMLin($gSysOut);
my $parentphys;
@@ -920,7 +920,7 @@
}
if (! -e "$exportdir/$physname.$version" ) {
- &DoSsCmd("get -b -v$version --force-overwrite \"$physpath\" $exportdir/$physname");
+ &DoSsCmd("get -b -v$version --force-overwrite -e$gCfg{encoding} \"$physpath\" $exportdir/$physname");
}
return $exportdir;
@@ -944,6 +944,7 @@
VSS Dir : $gCfg{vssdir}
Temp Dir : $gCfg{tempdir}
Dumpfile : $gCfg{dumpfile}
+VSS Encoding : $gCfg{encoding}
SSPHYS exe : $gCfg{ssphys}
SSPHYS ver : $ssversion
@@ -1551,7 +1552,7 @@
###############################################################################
sub Initialize {
GetOptions(\%gCfg,'vssdir=s','tempdir=s','dumpfile=s','resume','verbose',
- 'debug','timing+','task=s','revtimerange=i', 'ssphys=s');
+ 'debug','timing+','task=s','revtimerange=i','ssphys=s','encoding=s');
&GiveHelp("Must specify --vssdir") if !defined($gCfg{vssdir});
$gCfg{tempdir} = './_vss2svn' if !defined($gCfg{tempdir});
@@ -1561,6 +1562,7 @@
# XML output from ssphysout placed here.
$gCfg{ssphysout} = "$gCfg{tempdir}/ssphysout";
+ $gCfg{encoding} = 'windows-1252' if !defined($gCfg{encoding});
# Commit messages for SVN placed here.
$gCfg{svncomment} = "$gCfg{tempdir}/svncomment.tmp.txt";
@@ -1690,6 +1692,8 @@
--verbose : Print more info about the items being processed
--debug : Print lots of debugging info.
--timing : Show timing information during various steps
+ --encoding : Specify the encoding used in VSS;
+ Default is windows-1252
EOTXT
exit(1);
Index: ssphys/SSPhys/Formatter.cpp
===================================================================
--- ssphys/SSPhys/Formatter.cpp (revision 272)
+++ ssphys/SSPhys/Formatter.cpp (working copy)
@@ -50,11 +50,11 @@
class CXMLFormatter : public CFormatter
{
public:
- CXMLFormatter ()
+ CXMLFormatter (std::string encoding)
: m_pCurrentFileNode (NULL)
{
// patch this line to match your VSS DB's locale
- TiXmlDeclaration decl ("1.0", "windows-1252", "");
+ TiXmlDeclaration decl ("1.0", encoding, "");
m_Document.InsertEndChild (decl);
}
~CXMLFormatter ()
@@ -301,12 +301,12 @@
}
//////////////////////////////////////////////////////////////////////
-std::auto_ptr<CFormatter> CFormatterFactory::MakeFormatter (eStyle style, po::variables_map const& vm)
+std::auto_ptr<CFormatter> CFormatterFactory::MakeFormatter (eStyle style, std::string encoding, po::variables_map const& vm)
{
if (style == eBinary)
return std::auto_ptr<CFormatter> (new CBinaryFormatter (/*value*/));
if (style == eXML)
- return std::auto_ptr<CFormatter> (new CXMLFormatter ());
+ return std::auto_ptr<CFormatter> (new CXMLFormatter (encoding));
if (style == eVSS)
return std::auto_ptr<CFormatter> (new CVssFormatter ());
if (style == eDump)
@@ -324,7 +324,7 @@
if (style == "binary")
return std::auto_ptr<CFormatter> (new CBinaryFormatter (/*value*/));
if (style == "xml")
- return std::auto_ptr<CFormatter> (new CXMLFormatter ());
+ return std::auto_ptr<CFormatter> (new CXMLFormatter (options["encoding"].as<std::string>()));
if (style == "vss")
return std::auto_ptr<CFormatter> (new CVssFormatter ());
if (style == "dump")
@@ -339,6 +339,8 @@
po::options_description descr ("Formatter options");
descr.add_options ()
("style,s", po::value<std::string>()->default_value("XML"), "output style {XML|binary|vss|dump}");
+ descr.add_options ()
+ ("encoding,e", po::value<std::string>()->default_value("windows-1252"), "VSS text encoding for the XML output style");
return descr;
}
Index: ssphys/SSPhys/Formatter.h
===================================================================
--- ssphys/SSPhys/Formatter.h (revision 272)
+++ ssphys/SSPhys/Formatter.h (working copy)
@@ -59,7 +59,7 @@
class CFormatterFactory
{
public:
- static std::auto_ptr<CFormatter> MakeFormatter (eStyle style, po::variables_map const& vm);
+ static std::auto_ptr<CFormatter> MakeFormatter (eStyle style, std::string encoding, po::variables_map const& vm);
static std::auto_ptr<CFormatter> MakeFormatter (po::variables_map const& vm);
static po::options_description GetOptionsDescription ();
};
_______________________________________________
vss2svn-users mailing list
Project homepage:
http://www.pumacode.org/projects/vss2svn/
Subscribe/Unsubscribe/Admin:
http://lists.pumacode.org/mailman/listinfo/vss2svn-users-lists.pumacode.org
Mailing list web interface (with searchable archives):
http://dir.gmane.org/gmane.comp.version-control.subversion.vss2svn.user
