More unicode work. Fixup some usages.

git-svn-id: svn://svn.lyx.org/lyx/lyx-devel/trunk@14968 a592a061-630c-0410-9148-cb99ea01b6c8

src/frontends/qt3/QLyXKeySym.C

@@ -202,18 +202,18 @@ string QLyXKeySym::getSymbolName() const
 
 size_t QLyXKeySym::getUCSEncoded() const
 {
-    unsigned short const * ptr = text_.ucs2();
+    if (text_.isEmpty())
-    std::vector<unsigned short> tmp(ptr, ptr + text_.length());
+	return 0;
+
+    //unsigned short const * ptr = text_.ucs2();
+    //std::vector<unsigned short> tmp(ptr, ptr + text_.length());
 
     //lyxerr << "Data is " << tmp << endl;
     //lyxerr << "Length is " << text_.length() << endl;
 
-    if (text_.isEmpty())
-	return 0;
-
     //size_t res = utf8_to_ucs4(tmp, tmp.length());
     //lyxerr << "Res is " << res << endl;
-    return ucs2_to_ucs4(tmp)[0];
+    return ucs2_to_ucs4(text_.ucs2(), text_.length())[0];
 }
 
 

src/frontends/qt3/qt_helpers.C

@@ -120,7 +120,7 @@ QString const toqstr(string const & str)
 QString const toqstr(docstring const & str)
 {
 	std::vector<unsigned short> ucs2 =
-		ucs4_to_ucs2(str.c_str(), str.length());
+		ucs4_to_ucs2(str.data(), str.length());
 	ucs2.push_back('\0');
 	return QString::fromUcs2(&ucs2[0]);
 }
@@ -149,8 +149,7 @@ string const fromqstr(QString const & str)
 docstring const qstring_to_ucs4(QString const & str)
 {
 	unsigned short const * const ucs2 = str.ucs2();
-	std::vector<char_type> const ucs4 = ucs2_to_ucs4(
+	std::vector<char_type> const ucs4 = ucs2_to_ucs4(ucs2, str.length());
-		std::vector<unsigned short>(ucs2, ucs2 + str.length()));
 	return docstring(ucs4.begin(), ucs4.end());
 }
 

src/lyxlex_pimpl.C

@@ -73,9 +73,9 @@ string const LyXLex::Pimpl::getString() const
 
 lyx::docstring const LyXLex::Pimpl::getDocString() const
 {
-        std::vector<boost::uint32_t> res = utf8_to_ucs4(buff);
+	std::vector<boost::uint32_t> res = utf8_to_ucs4(buff);
-        lyx::docstring dstr(res.begin(), res.end());
+	lyx::docstring dstr(res.begin(), res.end());
-        return dstr;
+	return dstr;
 }
 
 

src/support/docstring.C

@@ -41,7 +41,7 @@ docstring const from_ascii(std::string const & ascii)
 docstring const from_utf8(std::string const & utf8)
 {
 	std::vector<boost::uint32_t> const ucs4 =
-		utf8_to_ucs4(std::vector<char>(utf8.begin(), utf8.end()));
+		utf8_to_ucs4(utf8.data(), utf8.size());
 	return docstring(ucs4.begin(), ucs4.end());
 }
 
@@ -49,7 +49,7 @@ docstring const from_utf8(std::string const & utf8)
 std::string const to_utf8(docstring const & ucs4)
 {
 	std::vector<char> const utf8 =
-		ucs4_to_utf8(std::vector<boost::uint32_t>(ucs4.begin(), ucs4.end()));
+		ucs4_to_utf8(ucs4.data(), ucs4.size());
 	return std::string(utf8.begin(), utf8.end());
 }
 

src/support/unicode.C

@@ -125,19 +125,47 @@ iconv_convert(iconv_t * cd,
 
 
 std::vector<boost::uint32_t> utf8_to_ucs4(std::vector<char> const & utf8str)
+{
+	return utf8_to_ucs4(&utf8str[0], utf8str.size());
+}
+
+
+std::vector<boost::uint32_t>
+utf8_to_ucs4(char const * utf8str, size_t ls)
 {
 	static iconv_t cd = (iconv_t)(-1);
 	return iconv_convert<boost::uint32_t>(&cd, ucs4_codeset, "UTF-8",
-					      &utf8str[0], utf8str.size());
+					      utf8str, ls);
+}
+
+
+boost::uint32_t
+ucs2_to_ucs4(unsigned short c)
+{
+	return ucs2_to_ucs4(&c, 1)[0];
 }
 
 
 std::vector<boost::uint32_t>
 ucs2_to_ucs4(std::vector<unsigned short> const & ucs2str)
+{
+	return ucs2_to_ucs4(&ucs2str[0], ucs2str.size());
+}
+
+
+std::vector<boost::uint32_t>
+ucs2_to_ucs4(unsigned short const * ucs2str, size_t ls)
 {
 	static iconv_t cd = (iconv_t)(-1);
 	return iconv_convert<boost::uint32_t>(&cd, ucs4_codeset, ucs2_codeset,
-					      &ucs2str[0], ucs2str.size());
+					      ucs2str, ls);
+}
+
+
+unsigned short
+ucs4_to_ucs2(boost::uint32_t c)
+{
+	return ucs4_to_ucs2(&c, 1)[0];
 }
 
 
@@ -157,24 +185,25 @@ ucs4_to_ucs2(boost::uint32_t const * s, size_t ls)
 }
 
 
-unsigned short
+std::vector<char>
-ucs4_to_ucs2(boost::uint32_t c)
+ucs4_to_utf8(boost::uint32_t c)
-{
-	boost::uint32_t tmp[] = { c, 0 };
-	return ucs4_to_ucs2(tmp, 1)[0];
-}
-
-
-std::vector<char> ucs4_to_utf8(std::vector<boost::uint32_t> const & ucs4str)
-{
-	static iconv_t cd = (iconv_t)(-1);
-	return iconv_convert<char>(&cd, "UTF-8", ucs4_codeset,
-				   &ucs4str[0], ucs4str.size());
-}
-
-
-std::vector<char> ucs4_to_utf8(boost::uint32_t c)
 {
 	static iconv_t cd = (iconv_t)(-1);
 	return iconv_convert<char>(&cd, "UTF-8", ucs4_codeset, &c, 1);
 }
+
+
+std::vector<char>
+ucs4_to_utf8(std::vector<boost::uint32_t> const & ucs4str)
+{
+	return ucs4_to_utf8(&ucs4str[0], ucs4str.size());
+}
+
+
+std::vector<char>
+ucs4_to_utf8(boost::uint32_t const * ucs4str, size_t ls)
+{
+	static iconv_t cd = (iconv_t)(-1);
+	return iconv_convert<char>(&cd, "UTF-8", ucs4_codeset,
+				   ucs4str, ls);
+}

src/support/unicode.h

@@ -16,25 +16,48 @@
 #include <boost/cstdint.hpp>
 #include <vector>
 
+// utf8_to_ucs4
+
+// A single codepoint conversion for utf8_to_ucs4 does not make
+// sense, so that function is left out.
+
 std::vector<boost::uint32_t>
 utf8_to_ucs4(std::vector<char> const & utf8str);
 
+std::vector<boost::uint32_t>
+utf8_to_ucs4(char const * utf8str, size_t ls);
+
+// ucs2_to_ucs4
+
+boost::uint32_t
+ucs2_to_ucs4(unsigned short c);
+
 std::vector<boost::uint32_t>
 ucs2_to_ucs4(std::vector<unsigned short> const & ucs2str);
 
+std::vector<boost::uint32_t>
+ucs2_to_ucs4(unsigned short const * ucs2str, size_t ls);
+
+// ucs4_to_ucs2
+
+unsigned short
+ucs4_to_ucs2(boost::uint32_t c);
+
 std::vector<unsigned short>
 ucs4_to_ucs2(std::vector<boost::uint32_t> const & ucs4str);
 
 std::vector<unsigned short>
 ucs4_to_ucs2(boost::uint32_t const * s, size_t ls);
 
-unsigned short
+// ucs4_to_utf8
-ucs4_to_ucs2(boost::uint32_t c);
+
+std::vector<char>
+ucs4_to_utf8(boost::uint32_t c);
 
 std::vector<char>
 ucs4_to_utf8(std::vector<boost::uint32_t> const & ucs4str);
 
 std::vector<char>
-ucs4_to_utf8(boost::uint32_t c);
+ucs4_to_utf8(boost::uint32_t const * ucs4str, size_t ls);
 
 #endif