Fixed problems with signed characters.

git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@85 d0cd1f9f-072b-0410-8dd7-cf729c803f20
lzpfmh · Jul 18, 2007 · eeaca1b · eeaca1b
1 parent 4df1016
commit eeaca1b
Show file tree

Hide file tree

Showing 4 changed files with 225 additions and 62 deletions.
diff --git a/ccutil/unichar.cpp b/ccutil/unichar.cpp
@@ -103,16 +103,16 @@ int UNICHAR::first_uni() const {
   default:
     break;
   case 4:
-    uni += *src++;
+    uni += static_cast<unsigned char>(*src++);
     uni <<= 6;
   case 3:
-    uni += *src++;
+    uni += static_cast<unsigned char>(*src++);
     uni <<= 6;
   case 2:
-    uni += *src++;
+    uni += static_cast<unsigned char>(*src++);
     uni <<= 6;
   case 1:
-    uni += *src++;
+    uni += static_cast<unsigned char>(*src++);
   }
   uni -= utf8_offsets[len];
   return uni;
@@ -140,5 +140,5 @@ int UNICHAR::utf8_step(const char* utf8_str) {
     3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3, 4,4,4,4,4,4,4,4,0,0,0,0,0,0,0,0
   };
 
-  return utf8_bytes[*utf8_str];
+  return utf8_bytes[static_cast<unsigned char>(*utf8_str)];
 }
diff --git a/ccutil/unicharmap.cpp b/ccutil/unicharmap.cpp
@@ -41,9 +41,9 @@ UNICHAR_ID UNICHARMAP::unichar_to_id(const char* const unichar_repr) const {
 
   do {
     if (*(current_char + 1) == '\0')
-      return current_nodes[static_cast<unsigned int>(*current_char)].id;
+      return current_nodes[static_cast<unsigned char>(*current_char)].id;
     current_nodes =
-        current_nodes[static_cast<unsigned int>(*current_char)].children;
+        current_nodes[static_cast<unsigned char>(*current_char)].children;
     ++current_char;
   } while (true);
 }
@@ -61,9 +61,9 @@ UNICHAR_ID UNICHARMAP::unichar_to_id(const char* const unichar_repr,
 
   do {
     if (length == 1 || *(current_char + 1) == '\0')
-      return current_nodes[static_cast<unsigned int>(*current_char)].id;
+      return current_nodes[static_cast<unsigned char>(*current_char)].id;
     current_nodes =
-        current_nodes[static_cast<unsigned int>(*current_char)].children;
+        current_nodes[static_cast<unsigned char>(*current_char)].children;
     ++current_char;
     --length;
   } while (true);
@@ -85,12 +85,12 @@ void UNICHARMAP::insert(const char* const unichar_repr, UNICHAR_ID id) {
       *current_nodes_pointer = new UNICHARMAP_NODE[256];
     if (*(current_char + 1) == '\0') {
       (*current_nodes_pointer)
-          [static_cast<unsigned int>(*current_char)].id = id;
+          [static_cast<unsigned char>(*current_char)].id = id;
       return;
     }
     current_nodes_pointer =
         &((*current_nodes_pointer)
-          [static_cast<unsigned int>(*current_char)].children);
+          [static_cast<unsigned char>(*current_char)].children);
     ++current_char;
   } while (true);
 }
@@ -106,11 +106,11 @@ bool UNICHARMAP::contains(const char* const unichar_repr) const {
 
   while (current_nodes != 0 && *(current_char + 1) != '\0') {
     current_nodes =
-        current_nodes[static_cast<unsigned int>(*current_char)].children;
+        current_nodes[static_cast<unsigned char>(*current_char)].children;
     ++current_char;
   }
   return current_nodes != 0 && *(current_char + 1) == '\0' &&
-      current_nodes[static_cast<unsigned int>(*current_char)].id >= 0;
+      current_nodes[static_cast<unsigned char>(*current_char)].id >= 0;
 }
 
 // Search the given unichar representation in the tree, using length characters
@@ -127,12 +127,12 @@ bool UNICHARMAP::contains(const char* const unichar_repr,
 
   while (current_nodes != 0 && (length > 1 && *(current_char + 1) != '\0')) {
     current_nodes =
-        current_nodes[static_cast<unsigned int>(*current_char)].children;
+        current_nodes[static_cast<unsigned char>(*current_char)].children;
     --length;
     ++current_char;
   }
   return current_nodes != 0 && (length == 1 || *(current_char + 1) == '\0') &&
-      current_nodes[static_cast<unsigned int>(*current_char)].id >= 0;
+      current_nodes[static_cast<unsigned char>(*current_char)].id >= 0;
 }
 
 void UNICHARMAP::clear() {