From: Jürgen Spitzmüller <spitz@lyx.org>
Date: Sat, 14 Jul 2007 13:00:24 +0000 (+0000)
Subject: * src/support/docstream.cpp (iconv_codecvt_facet::do_max_length()):
X-Git-Tag: 1.6.10~9134
X-Git-Url: https://git.lyx.org/gitweb/?a=commitdiff_plain;h=402a13ba60bd49f8db8b4b806635e9d0883b5f58;p=features.git

* src/support/docstream.cpp (iconv_codecvt_facet::do_max_length()):
	- consider that not only utf8, but also most cjk encodings, are multibyte encodings
	  (fixes bug 4012)

git-svn-id: svn://svn.lyx.org/lyx/lyx-devel/trunk@19076 a592a061-630c-0410-9148-cb99ea01b6c8
---

diff --git a/src/support/docstream.cpp b/src/support/docstream.cpp
index 8f476376e6..6c5dd8bed0 100644
--- a/src/support/docstream.cpp
+++ b/src/support/docstream.cpp
@@ -206,13 +206,32 @@ protected:
 	}
 	virtual int do_max_length() const throw()
 	{
+		// FIXME: this information should be transferred to lib/encodings
 		// UTF8 uses at most 4 bytes to represent one UCS4 code point
 		// (see RFC 3629). RFC 2279 specifies 6 bytes, but that
 		// information is outdated, and RFC 2279 has been superseded by
 		// RFC 3629.
+		// The CJK encodings use (different) multibyte representation as well.
 		// All other encodings encode one UCS4 code point in one byte
 		// (and can therefore only encode a subset of UCS4)
-		return encoding_ == "UTF-8" ? 4 : 1;
+		// Note that BIG5 and SJIS do not work with LaTeX (see lib/encodings). 
+		// Furthermore, all encodings that use shifting (like SJIS) do not work with 
+		// iconv_codecvt_facet.
+		if (encoding_ == "UTF-8" ||
+		    encoding_ == "GB" ||
+		    encoding_ == "EUC-TW")
+			return 4;
+		else if (encoding_ == "EUC-JP")
+			return 3;
+		else if (encoding_ == "BIG5" ||
+			 encoding_ == "EUC-KR" ||
+			 encoding_ == "EUC-CN" ||
+			 encoding_ == "SJIS" ||
+			 encoding_ == "GBK" ||
+			 encoding_ == "JIS" )
+			return 2;
+		else
+			return 1;
 	}
 private:
 	/// Do the actual conversion. The interface is equivalent to that of