--nextPart2920567.QRFuHvjJuH
Content-Type: multipart/mixed;
  boundary="Boundary-01=_j5dPIyJiUV/Jqj7"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

--Boundary-01=_j5dPIyJiUV/Jqj7
Content-Type: text/plain;
  charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline

[xposted to core-devel]

Hei,

You might remember me as the guy that, four years ago, used internal entiti=
es=20
in kleopatra/index.docbook to have a handy shortcut for the menu entries:
  <!ENTITY view-redisplay "<menuchoice><shortcut><keycombo action=3D'simul'>
  <keycap>F5</keycap></keycombo></shortcut>
  <guimenu>View</guimenu><guimenuitem>Redisplay</guimenuitem></menuchoice>">
=2E..
  Use &view-redisplay; to foo bar.

Up to now, these entities were squarely removed by the poxml parser, which=
=20
made their contents inaccessible to translators. Which, in turn, made it=20
impossible for me to use these handy shortcuts.

Since that is clearly an unacceptable state, and since I think that also=20
translators could save a bunch of work if these shortcuts were made availab=
le=20
to them, I've sat down and after a few hours of staring at incomprehensible=
=20
code, came up with attached patch, which fixes this.

In order to be minimally intrusive, I've only enabled entity extraction for=
=20
entities starting with "i18n-". That way, the standard entities such as=20
kappname and language don't clobber the .po(t). It's trivial to extract all=
=20
internal entities, though.

The patch is forwards- and backwards compatible. Old po2xml will ignore the=
=20
new data, and new po2xml will leave the entity definition in peace if there=
's=20
no translation for them,

On thing I haven't tested is the effect on the other two programs of the po=
xml=20
suite. split2po and swappo. I just don't know what they do...

I'd like to ask for permission to apply this patch now, in the feature free=
ze,=20
because I think it's a bugfix, and because poxml is a development tool that=
's=20
hardly user-visible, so the freeze shouldn't apply to it.

Another reason is that I intend to make much, much use of this new facility=
=20
when updating kleopatra/index.docbook for Kleopatra 2.0.

I'll commit in ~24h unless someone objects.

Please keep my @kdab address CC'ed.

Thanks,
Marc


--Boundary-01=_j5dPIyJiUV/Jqj7
Content-Type: text/x-diff;
  charset="iso-8859-1";
  name="poxml-internal-entities.diff"
Content-Transfer-Encoding: quoted-printable
Content-Disposition: attachment;
	filename="poxml-internal-entities.diff"

Index: parser.h
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
=2D-- parser.h	(revision 813020)
+++ parser.h	(working copy)
@@ -64,6 +64,12 @@
     void addAnchor(QString anchor) { anchors.insert(anchor, current); }
     void increasePara() { current++; }
=20
+    ParaCounter & operator+=3D( const ParaCounter & other ) {
+        current +=3D other.current;
+        anchors.unite( other.anchors );
+        return *this;
+    }
+
     QMap<QString, int> anchors;
     int current;
 };
@@ -73,6 +79,12 @@
 public:
     MsgList() {}
     ParaCounter pc;
+
+    MsgList & operator+=3D( const MsgList & other ) {
+        Q3ValueList<MsgBlock>::operator+=3D( other );
+        pc +=3D other.pc;
+        return *this;
+    }
 };
=20
 class StructureParser : public QXmlDefaultHandler
Index: lauri.po
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
=2D-- lauri.po	(revision 813020)
+++ lauri.po	(working copy)
@@ -14,6 +14,12 @@
 "Content-Transfer-Encoding: 8bit\n"
 "X-Generator: KBabel 0.9.2\n"
=20
+#. Tag: !ENTITY
+#: lauri.xml:3
+#, no-c-format
+msgid "<!ENTITY i18n-file-quit \"<menuchoice><shortcut><keycombo action=3D=
'simul'>&Ctrl;<keycap>Q</keycap></keycombo></shortcut><guimenu>File</guimen=
u><guimenuitem>Quit</guimenuitem></menuchoice>\">"
+msgstr "<!ENTITY i18n-file-quit \"<menuchoice><shortcut><keycombo action=
=3D'simul'>&Ctrl;<keycap>Q</keycap></keycombo></shortcut><guimenu>Datei</gu=
imenu><guimenuitem>Beenden</guimenuitem></menuchoice>\">"
+
 #. Tag: title
 #: lauri.xml:16
 #, no-c-format
Index: lauri.xml
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
=2D-- lauri.xml	(revision 813020)
+++ lauri.xml	(working copy)
@@ -1,7 +1,7 @@
 <?xml version=3D"1.0" ?>
 <!DOCTYPE book PUBLIC "-//KDE//DTD DocBook XML V4.2-Based Variant V1.1//EN=
" "dtd/kdex.dtd" [
   <!ENTITY % English "INCLUDE" > <!-- change language only here -->
=2D  <!ENTITY lauri "<emphasis>Lauri</emphasis>" >
+  <!ENTITY lauri "<emphasis>Lauri</emphasis>" > <!ENTITY i18n-file-quit "<=
menuchoice><shortcut><keycombo action=3D'simul'>&Ctrl;<keycap>Q</keycap></k=
eycombo></shortcut><guimenu>File</guimenu><guimenuitem>Quit</guimenuitem></=
menuchoice>">
 ]>
=20
 <book>
Index: parser.cpp
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
=2D-- parser.cpp	(revision 813020)
+++ parser.cpp	(working copy)
@@ -11,6 +11,17 @@
=20
 using namespace std;
=20
+static int countRev( const QString & str, QChar ch, int idx ) {
+    if ( idx < 0 )
+        idx +=3D str.length();
+    if ( idx >=3D str.length() )
+        idx =3D str.length();
+    int count =3D 0;
+    for ( int i =3D 0 ; i <=3D idx ; ++i )
+        count +=3D ( str[i] =3D=3D ch );
+    return count;
+}
+
 static const char *singletags[] =3D {"beginpage","imagedata", "colspec", "=
spanspec",
                                    "anchor", "xref", "area",
                                    "footnoteref", "void", "inlinegraphic",
@@ -931,6 +942,38 @@
     QString contents =3D QString::fromUtf8( ccontents );
     StructureParser::cleanupTags(contents);
=20
+    MsgList english;
+    {
+        // find internal entities that start with "i18n-", and extract
+        // their replacement texts:
+        QRegExp rx( "<!ENTITY\\s+([^\\s]+)\\s+([\"'])" );
+        for ( int index =3D rx.indexIn( contents, 0 ) ; index >=3D 0 ; ind=
ex =3D rx.indexIn( contents, index ) ) {
+            const QString name =3D rx.cap( 1 );
+            const QChar delim =3D rx.cap( 2 ).at( 0 );
+            const int start =3D index;
+            index =3D contents.indexOf( delim, index + rx.matchedLength() =
);
+            index =3D contents.indexOf( '>', index );
+            if ( !name.startsWith( "i18n-" ) )
+                continue;
+            const QString entity =3D contents.mid( start, index - start + =
1 );
+            MsgBlock block;
+            block.tag =3D "!ENTITY";
+            BlockInfo bi;
+            bi.start_line =3D countRev( contents, '\n', index ) + 1;
+            bi.start_col  =3D start - contents.lastIndexOf( '\n', start ) =
=2D 1;
+            bi.end_line   =3D bi.start_line + entity.count( '\n' );
+            bi.end_col    =3D index - contents.lastIndexOf( '\n', index ) =
+ 1;
+#ifdef POXML_DEBUG
+            qDebug( "ENTITY %s @ i:%d l:%d c:%d->l:%d c:%d", qPrintable( n=
ame ),
+                    index, bi.start_line, bi.start_col, bi.end_line, bi.en=
d_col );
+#endif
+            block.lines.push_back( bi );
+            block.msgid =3D entity;
+            english.push_back( block );
+        }
+    }
+
+    // Remove all entity definitions now:
     while (true) {
         int index =3D contents.find("<!ENTITY");
         if (index < 0)
@@ -966,7 +1009,7 @@
     reader.setDTDHandler( &handler );
     // reader.setErrorHandler( &handler );
     reader.parse( source );
=2D    MsgList english =3D handler.getList();
+    english +=3D handler.getList();
=20
     bool changed =3D false;
=20

--Boundary-01=_j5dPIyJiUV/Jqj7--

--nextPart2920567.QRFuHvjJuH
Content-Type: application/pgp-signature

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.6 (GNU/Linux)

iD8DBQBIPd5j3oWD+L2/6DgRAkpWAJ4wI9UamrPQmSNHUmGBrtjzZ7XeWgCgnt4G
QkSoBjPhpWbFNCDDksf4KtA=
=J7yW
-----END PGP SIGNATURE-----

--nextPart2920567.QRFuHvjJuH--