X-Git-Url: https://git.dogcows.com/gitweb?a=blobdiff_plain;f=otk%2Fustring.cc;h=8ffe07fe000ba7c5febf3639b1fd7cf3f7151633;hb=1e58c863bbaddd2f2dbebfde740ca842e8837a1c;hp=8f3cdfc452fae6bfdc2c4af2f716da9c769ff9d0;hpb=5a90d2b671f01f29043ab82f909440de0abfa362;p=chaz%2Fopenbox

diff --git a/otk/ustring.cc b/otk/ustring.cc
index 8f3cdfc4..8ffe07fe 100644
--- a/otk/ustring.cc
+++ b/otk/ustring.cc
@@ -1,31 +1,69 @@
 // -*- mode: C++; indent-tabs-mode: nil; c-basic-offset: 2; -*-
 
-#ifdef    HAVE_CONFIG_H
-#  include "../config.h"
-#endif // HAVE_CONFIG_H
+#include "config.h"
 
 #include "ustring.hh"
 
-extern "C" {
-#include <assert.h>
-}
+#include <cassert>
 
 namespace otk {
 
 // helper functions
 
-static ustring::size_type utf8_find_offset(const char *str, const char *pos)
+// The number of bytes to skip to find the next character in the string
+static const char utf8_skip[256] = {
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
+  3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
+};
+
+// takes a pointer into a utf8 string and returns a unicode character for the
+// first character at the pointer
+unichar utf8_get_char (const char *p)
+{
+  unichar result = static_cast<unsigned char>(*p);
+
+  // if its not a 7-bit ascii character
+  if((result & 0x80) != 0) {
+    // len is the number of bytes this character takes up in the string
+    unsigned char len = utf8_skip[result];
+    result &= 0x7F >> len;
+
+    while(--len != 0) {
+      result <<= 6;
+      result |= static_cast<unsigned char>(*++p) & 0x3F;
+    }
+  }
+    
+  return result;
+}
+  
+// takes a pointer into a string and finds its offset
+static ustring::size_type utf8_ptr_to_offset(const char *str, const char *pos)
 {
   ustring::size_type offset = 0;
 
   while (str < pos) {
-    str += g_utf8_skip[*str];
-    offset += g_utf8_skip[*str];
+    str += utf8_skip[static_cast<unsigned char>(*str)];
+    offset++;
   }
 
   return offset;
 }
 
+// takes an offset into a string and returns a pointer to it
+const char *utf8_offset_to_ptr(const char *str, ustring::size_type offset)
+{
+  while (offset--)
+    str += utf8_skip[static_cast<unsigned char>(*str)];
+  return str;
+}
+
 // First overload: stop on '\0' character.
 ustring::size_type utf8_byte_offset(const char* str, ustring::size_type offset)
 {
@@ -39,7 +77,7 @@ ustring::size_type utf8_byte_offset(const char* str, ustring::size_type offset)
     if(*p == '\0')
       return ustring::npos;
 
-    p += g_utf8_skip[*p];
+    p += utf8_skip[static_cast<unsigned char>(*p)];
   }
 
   return (p - str);
@@ -60,7 +98,7 @@ ustring::size_type utf8_byte_offset(const char* str, ustring::size_type offset,
     if(p >= pend)
       return ustring::npos;
 
-    p += g_utf8_skip[*p];
+    p += utf8_skip[static_cast<unsigned char>(*p)];
   }
 
   return (p - str);
@@ -69,7 +107,8 @@ ustring::size_type utf8_byte_offset(const char* str, ustring::size_type offset,
 
 // ustring methods
 
-ustring::ustring()
+ustring::ustring(bool utf8)
+  : _utf8(utf8)
 {
 }
 
@@ -89,13 +128,13 @@ ustring& ustring::operator=(const ustring& other)
   return *this;
 }
 
-ustring::ustring(const std::string& src)
-  : _string(src), _utf8(true)
+ustring::ustring(const std::string& src, bool utf8)
+  : _string(src), _utf8(utf8)
 {
 }
 
-ustring::ustring(const char* src)
-  : _string(src), _utf8(true)
+ustring::ustring(const char* src, bool utf8)
+  : _string(src), _utf8(utf8)
 {
 }
 
@@ -122,7 +161,7 @@ ustring::size_type ustring::size() const
 {
   if (_utf8) {
     const char *const pdata = _string.data();
-    return utf8_find_offset(pdata, pdata + _string.size());
+    return utf8_ptr_to_offset(pdata, pdata + _string.size());
   } else
     return _string.size();
 }
@@ -142,6 +181,11 @@ ustring::size_type ustring::max_size() const
   return _string.max_size();
 }
 
+bool ustring::empty() const
+{
+  return _string.empty();
+}
+
 void ustring::clear()
 {
   _string.erase();
@@ -176,6 +220,26 @@ void ustring::resize(ustring::size_type n, char c)
     _string.resize(n, c);
 }
 
+ustring::value_type ustring::operator[](ustring::size_type i) const
+{
+  return utf8_get_char(utf8_offset_to_ptr(_string.data(), i));
+}
+
+bool ustring::operator==(const ustring &other) const
+{
+  return _string == other._string && _utf8 == other._utf8;
+}
+
+bool ustring::operator==(const std::string &other) const
+{
+  return _string == other;
+}
+
+bool ustring::operator==(const char *other) const
+{
+  return _string == other;
+}
+
 const char* ustring::data() const
 {
   return _string.data();