Revision: 7195
http://svn.sourceforge.net/mahogany/?rev=7195&view=rev
Author: vadz
Date: 2006-12-25 12:48:14 -0800 (Mon, 25 Dec 2006)
Log Message:
-----------
test if the encoding really works in GuessUnicodeCharset(); also made it public instead of manually declaring it as extern in BareBonesEditor.cpp
Modified Paths:
--------------
trunk/M/include/strutil.h
trunk/M/src/modules/BareBonesEditor.cpp
trunk/M/src/util/strutil.cpp
Modified: trunk/M/include/strutil.h
===================================================================
--- trunk/M/include/strutil.h 2006-12-25 20:05:39 UTC (rev 7194)
+++ trunk/M/include/strutil.h 2006-12-25 20:48:14 UTC (rev 7195)
@@ -341,6 +341,11 @@
extern wxArrayString strutil_uniq_array(const wxSortedArrayString& arrSorted);
/**
+ Return our guess for the encoding of the given Unicode text.
+ */
+extern wxFontEncoding GuessUnicodeCharset(const wchar_t *pwz);
+
+/**
Try to convert text in UTF-8 or 7 to a multibyte encoding.
The conversion is done in place, i.e. the str parameter is read and written
@@ -357,7 +362,6 @@
@return the encoding of the returned string
*/
extern wxFontEncoding ConvertUTFToMB(wxString *str, wxFontEncoding utfEnc);
-extern wxFontEncoding ConvertUTF8ToMB(wxString *str);
// return the length of the line terminator if we're at the end of line or 0
// otherwise
Modified: trunk/M/src/modules/BareBonesEditor.cpp
===================================================================
--- trunk/M/src/modules/BareBonesEditor.cpp 2006-12-25 20:05:39 UTC (rev 7194)
+++ trunk/M/src/modules/BareBonesEditor.cpp 2006-12-25 20:48:14 UTC (rev 7195)
@@ -1169,9 +1169,6 @@
// BareBonesEditor contents: enumerating the different parts
// ----------------------------------------------------------------------------
-// from strutil.cpp
-extern wxFontEncoding GuessUnicodeCharset(const wchar_t *pwz);
-
EditorContentPart *BareBonesEditor::GetFirstPart()
{
m_getNextAttachement = 0;
Modified: trunk/M/src/util/strutil.cpp
===================================================================
--- trunk/M/src/util/strutil.cpp 2006-12-25 20:05:39 UTC (rev 7194)
+++ trunk/M/src/util/strutil.cpp 2006-12-25 20:48:14 UTC (rev 7195)
@@ -1379,7 +1379,7 @@
}
// guess the charset of the given Unicode text
-extern wxFontEncoding GuessUnicodeCharset(const wchar_t *pwz)
+wxFontEncoding GuessUnicodeCharset(const wchar_t *pwz)
{
typedef const unsigned short *codepage;
struct CodePageInfo
@@ -1459,83 +1459,24 @@
if ( wxFontMapper::Get()->IsEncodingAvailable(encodings[nEnc]) )
{
enc = encodings[nEnc];
- break;
- }
- }
-#ifdef DEBUG_nerijus
- // temporary HACK - Lithuanian input in both Windows and X is
- // ISO-8859-13 (or Windows-1257), not ISO-8859-4
- if ( enc == wxFONTENCODING_ISO8859_4 || enc == wxFONTENCODING_ISO8859_1 || enc == wxFONTENCODING_ISO8859_2 ) enc = wxFONTENCODING_ISO8859_13;
-#endif
- return enc;
-}
-// convert a string in UTF-8 or 7 into the string in some multibyte encoding:
-// of course, this doesn't work in general as Unicode is not representable as
-// an 8 bit charset but it works in some common cases and is better than no
-// UTF-8 support at all
-//
-// FIXME this won't be needed when full Unicode support is available
-wxFontEncoding ConvertUTFToMB(wxString *strUtf, wxFontEncoding enc)
-{
-#if !defined __WXGTK20__
- CHECK( strUtf, wxFONTENCODING_SYSTEM, _T("NULL string in ConvertUTFToMB") );
-
- if ( !strUtf->empty() )
- {
- if ( enc == wxFONTENCODING_UTF7 )
- {
- // try to determine which multibyte encoding is best suited for this
- // Unicode string
- wxWCharBuffer wbuf(strUtf->wc_str(wxConvUTF7));
- if ( !wbuf )
- {
- // invalid UTF-7 data, leave it as is
- enc = wxFONTENCODING_SYSTEM;
- }
- else // try to find a multibyte encoding we can show this in
- {
- enc = GuessUnicodeCharset(wbuf);
-
- // finally convert to multibyte
- wxString str;
- if ( enc == wxFONTENCODING_SYSTEM )
- {
- str = wxString(wbuf);
- }
- else
- {
- wxCSConv conv(enc);
- str = wxString(wbuf, conv);
- }
- if ( str.empty() )
- {
- // conversion failed - use original text (and display incorrectly,
- // unfortunately)
- wxLogDebug(_T("conversion from UTF-7 to default encoding failed"));
- }
- else
- {
- *strUtf = str;
- }
- }
+ // test if we can convert the entire text using it
+ //
+ // NB: normally we shouldn't do the real conversion here as it is
+ // awfully wasteful but currently it's possible for wxCSConv::
+ // WC2MB() to return successfully when it's used for just testing
+ // and not real conversion under Win32
+ if ( !wxString(pwz, wxCSConv(enc)).empty() )
+ break;
}
- else
- {
- ASSERT_MSG( enc == wxFONTENCODING_UTF8, _T("unknown Unicode encoding") );
- return ConvertUTF8ToMB(strUtf);
- }
}
- else // doesn't really matter what we return from here
- {
- enc = wxFONTENCODING_SYSTEM;
- }
-#endif // !__WXGTK20__
return enc;
}
-wxFontEncoding ConvertUTF8ToMB(wxString *strUtf)
+#ifndef __WXGTK20__
+
+static wxFontEncoding ConvertToMB(wxString *strUtf, const wxMBConv& conv)
{
wxFontEncoding enc;
CHECK( strUtf, wxFONTENCODING_SYSTEM, _T("NULL string in ConvertUTF8ToMB") );
@@ -1544,7 +1485,7 @@
{
// try to determine which multibyte encoding is best suited for this
// Unicode string
- wxWCharBuffer wbuf(strUtf->wc_str(wxConvUTF8));
+ wxWCharBuffer wbuf(strUtf->wc_str(conv));
if ( !wbuf )
{
// invalid UTF-8 data, leave it as is
@@ -1565,11 +1506,14 @@
wxCSConv conv(enc);
str = wxString(wbuf, conv);
}
+
if ( str.empty() )
{
// conversion failed - use original text (and display incorrectly,
// unfortunately)
wxLogDebug(_T("conversion from UTF-8 to default encoding failed"));
+
+ enc = wxFONTENCODING_SYSTEM;
}
else
{
@@ -1585,6 +1529,45 @@
return enc;
}
+#endif // __WXGTK20__
+
+// convert a string in UTF-8 or 7 into the string in some multibyte encoding:
+// of course, this doesn't work in general as Unicode is not representable as
+// an 8 bit charset but it works in some common cases and is better than no
+// UTF-8 support at all
+//
+// FIXME this won't be needed when full Unicode support is available
+wxFontEncoding ConvertUTFToMB(wxString *strUtf, wxFontEncoding enc)
+{
+ CHECK( strUtf, wxFONTENCODING_SYSTEM, _T("NULL string in ConvertUTFToMB") );
+
+ wxFontEncoding encConv;
+ if ( !strUtf->empty() )
+ {
+ if ( enc == wxFONTENCODING_UTF7 )
+ {
+ encConv = ConvertToMB(strUtf, wxConvUTF7);
+ }
+ else
+ {
+ ASSERT_MSG( enc == wxFONTENCODING_UTF8, _T("unknown Unicode encoding") );
+
+ // in GTK+ 2.0 we can use UTF-8 directly
+#ifdef __WXGTK20__
+ encConv = wxFONTENCODING_SYSTEM;
+#else
+ return ConvertToMB(strUtf, wxConvUTF8);
+#endif // !__WXGTK20__
+ }
+ }
+ else // doesn't really matter what we return from here
+ {
+ encConv = wxFONTENCODING_SYSTEM;
+ }
+
+ return encConv;
+}
+
// return the length of the line terminator if we're at the end of line or 0
// otherwise
size_t IsEndOfLine(const wxChar *p)
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
lmpx.com only provides a reader for public news (NNTP) servers. It is not
affiliated with the servers or forums shown here and is not responsible for
the content of articles, which is written by their respective authors.