[GB.XML]

* BUG: the parser now correctly supports UTF-8
* BUG: the parser now allows all special characters in tag names and attribute names, including the UTF-8 ones, as defined in http://www.w3.org/TR/REC-xml/#NT-NameChar

git-svn-id: svn://localhost/gambas/trunk@4654 867c0c6c-44f3-4631-809d-bfa615b0a4ec

gb.xml/src/element.cpp

@@ -280,7 +280,7 @@ vector<Node*>* Element::fromText(wstring data, wstring::size_type i, uint c, uin
 
             for(INC; i < data.length(); INC) //On cherche le tagName
             {
-                if(!isLetter(s) && s != L":" && s != L"-"&& s != L"_") break;
+                if(!isNameChar(s)) break;
                 tag += s;
             }
 
@@ -357,9 +357,9 @@ vector<Node*>* Element::fromText(wstring data, wstring::size_type i, uint c, uin
 
                 wstring attr, sVal = L"";
 
-                if(isLetter(s))
+                if(isNameStartChar(s))
                 {
-                    while(i < data.length() && (isLetter(s) || s == L"-" || s == L":" || s == L"_"))
+                    while(i < data.length() && isNameChar(s))
                     {
                         attr += s;
                         INC;

gb.xml/src/main.cpp

@@ -9,18 +9,91 @@
 #include "CExplorer.h"
 #endif
 
-std::string WStringToString(const std::wstring& s)
-{
-std::string temp(s.length(), ' ');
-std::copy(s.begin(), s.end(), temp.begin());
-return temp;
+
+void utf8toWStr(wstring& dest, const string& src){
+    dest.clear();
+    wchar_t w = 0;
+    int bytes = 0;
+    wchar_t err = L'<EFBFBD>';
+    for (size_t i = 0; i < src.size(); i++){
+        unsigned char c = (unsigned char)src[i];
+        if (c <= 0x7f){//first byte
+            if (bytes){
+                dest.push_back(err);
+                bytes = 0;
+            }
+            dest.push_back((wchar_t)c);
+        }
+        else if (c <= 0xbf){//second/third/etc byte
+            if (bytes){
+                w = ((w << 6)|(c & 0x3f));
+                bytes--;
+                if (bytes == 0)
+                    dest.push_back(w);
+            }
+            else
+                dest.push_back(err);
+        }
+        else if (c <= 0xdf){//2byte sequence start
+            bytes = 1;
+            w = c & 0x1f;
+        }
+        else if (c <= 0xef){//3byte sequence start
+            bytes = 2;
+            w = c & 0x0f;
+        }
+        else if (c <= 0xf7){//3byte sequence start
+            bytes = 3;
+            w = c & 0x07;
+        }
+        else{
+            dest.push_back(err);
+            bytes = 0;
+        }
+    }
+    if (bytes)
+        dest.push_back(err);
 }
 
-std::wstring StringToWString(const std::string& s)
+void wstrToUtf8(string& dest, const wstring& src){
+    dest.clear();
+    for (size_t i = 0; i < src.size(); i++){
+        wchar_t w = src[i];
+        if (w <= 0x7f)
+            dest.push_back((char)w);
+        else if (w <= 0x7ff){
+            dest.push_back(0xc0 | ((w >> 6)& 0x1f));
+            dest.push_back(0x80| (w & 0x3f));
+        }
+        else if (w <= 0xffff){
+            dest.push_back(0xe0 | ((w >> 12)& 0x0f));
+            dest.push_back(0x80| ((w >> 6) & 0x3f));
+            dest.push_back(0x80| (w & 0x3f));
+        }
+        else if (w <= 0x10ffff){
+            dest.push_back(0xf0 | ((w >> 18)& 0x07));
+            dest.push_back(0x80| ((w >> 12) & 0x3f));
+            dest.push_back(0x80| ((w >> 6) & 0x3f));
+            dest.push_back(0x80| (w & 0x3f));
+        }
+        else
+            dest.push_back('?');
+    }
+}
+
+
+std::string WStringToString(const std::wstring& str)
 {
-std::wstring temp(s.length(),L' ');
-std::copy(s.begin(), s.end(), temp.begin());
-return temp;
+    string result;
+    wstrToUtf8(result, str);
+    return result;
+}
+
+std::wstring StringToWString(const std::string& str)
+{
+    wstring result;
+    utf8toWStr(result, str);
+    return result;
 }
 
 wstring Html$(wstring text)
@@ -69,6 +142,44 @@ ostream &operator<<( ostream &out, std::wstring *str )
     return out;
 }
 
+/* http://www.w3.org/TR/REC-xml/#NT-NameStartChar
+
+  NameStartChar	::=  ":" | [A-Z] | "_" | [a-z] | [#xC0-#xD6] | [#xD8-#xF6] | [#xF8-#x2FF] |
+  [#x370-#x37D] | [#x37F-#x1FFF] | [#x200C-#x200D] | [#x2070-#x218F] |
+  [#x2C00-#x2FEF] | [#x3001-#xD7FF] | [#xF900-#xFDCF] | [#xFDF0-#xFFFD] | [#x10000-#xEFFFF]
+  */
+
+#define INTER(min, max) (car >= min && car <= max)
+#define INTERCAR(min, max) (car >= *(min) && car <= *(max))
+#define CAR(c) (car == *(c))
+
+bool isNameStartChar(wstring &s)
+{
+    const wchar_t car = (s.at(0));
+
+    return CAR(":") || INTERCAR("A", "Z") || CAR("_") || INTERCAR("a", "z") || CAR("Ø") ||
+            INTER(0xC0, 0xD6) || INTER(0xD8, 0xF6) || INTER(0xF8, 0x2FF) ||
+            INTER(0x370, 0x37D) || INTER(0x37F, 0x1FFF) || INTER(0x200C, 0x200D) ||
+            INTER(0x2070, 0x218F) || INTER(0xC200, 0x2FEF) || INTER(0x3001, 0xD7FF) ||
+            INTER(0xF900, 0xFDCF) || INTER(0xFDF0, 0xFFFD) || INTER(0x10000, 0xEFFFF);
+
+
+}
+
+/* http://www.w3.org/TR/REC-xml/#NT-NameChar
+
+  NameChar ::= 	NameStartChar | "-" | "." | [0-9] | #xB7 | [#x0300-#x036F] | [#x203F-#x2040]
+
+  */
+
+bool isNameChar(wstring &s)
+{
+    const wchar_t car = (s.at(0));
+
+    return isNameStartChar(s) || CAR("-") || CAR(".") || INTERCAR("0", "9") ||
+            (car == 0xB7) || INTER(0x0300, 0x036F) || INTER(0x203F, 0x2040);
+}
+
 #ifndef __HMAIN_CPP
 
 GB_INTERFACE GB EXPORT;

gb.xml/src/main.h

@@ -64,6 +64,9 @@ extern "C" GB_INTERFACE GB;
 
 #define VARGOBJ(type, arg) reinterpret_cast<type*>(VARG(arg))
 
+bool isNameStartChar(wstring &s);
+bool isNameChar(wstring &s);
+
 
 
 #endif // MAIN_H