fixed XML-entity decoding error

kuhumcst · Oct 19, 2016 · bead852 · bead852
1 parent f78dc1a
commit bead852
Show file tree

Hide file tree

Showing 3 changed files with 20 additions and 6 deletions.
diff --git a/Changelog b/Changelog
@@ -1,3 +1,9 @@
+-------------------------------
+Version 7.15 (19 October 2016)
+-------------------------------
+Fixed error in the decoding of XML-entities if the decoded string comprised
+more than one byte.
+
 -------------------------------
 Version 7.14 (13 October 2016)
 -------------------------------

diff --git a/src/cstlemma.cpp b/src/cstlemma.cpp
@@ -19,8 +19,8 @@ You should have received a copy of the GNU General Public License
 along with CSTLEMMA; if not, write to the Free Software
 Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
-#define CSTLEMMAVERSION "7.14"
-#define CSTLEMMADATE "2016.10.13"
+#define CSTLEMMAVERSION "7.15"
+#define CSTLEMMADATE "2016.10.19"
 #define CSTLEMMACOPYRIGHT "2002-2016 Center for Sprogteknologi"
 
 #include "lemmatiser.h"

diff --git a/src/wordReader.cpp b/src/wordReader.cpp
@@ -562,11 +562,19 @@ int wordReader::rawput(bool (wordReader::*fnc)(int kar),int kar)
 int wordReader::nrawput(bool (wordReader::*fnc)(int kar),char * c)
     {
     while(*c)
-        if(!rawput(fnc,*c++))
-            return false;
+        //if(!rawput(fnc,*c++))
+        rawput(fnc,*c++);
     return true;
     }
 
+int myUnicodeToUtf8(int w,char * s,size_t len)
+    {
+    int writtenlength = UnicodeToUtf8(w,s,len);
+    if(writtenlength >= 0)
+        s[writtenlength] = '\0';
+    return writtenlength;
+    }
+
 int wordReader::charref(bool (wordReader::*fnc)(int kar),int kar)
     {
     if(kar == ';')
@@ -594,7 +602,7 @@ int wordReader::charref(bool (wordReader::*fnc)(int kar),int kar)
             N = (buf[1] == 'x') ? strtoul(buf+2,NULL,16) : strtoul(buf+1,NULL,10);
             p = buf;
             xput = &wordReader::Put;
-            if(UnicodeToUtf8(N,tmp,sizeof(tmp)))
+            if(myUnicodeToUtf8(N,tmp,sizeof(tmp)))
                 {
                 return nrawput(fnc,tmp);
                 }
@@ -619,7 +627,7 @@ int wordReader::charref(bool (wordReader::*fnc)(int kar),int kar)
                     char tmp[22];
                     p = buf;
                     xput = &wordReader::Put;
-                    if(UnicodeToUtf8(pItem->code,tmp,sizeof(tmp)))
+                    if(myUnicodeToUtf8(pItem->code,tmp,sizeof(tmp)))
                         {
                         return nrawput(fnc,tmp);
                         }