fix range problem

(bzr r6103)

2 files changed, 27 insertions, 13 deletions

diff --git a/src/dom/ucd.cpp b/src/dom/ucd.cpp
index 602c71630..3747334d2 100644
--- a/src/dom/ucd.cpp
+++ b/src/dom/ucd.cpp
@@ -1,5 +1,5 @@
 /*
- * Generated by UcdReader at:Tue Jun 24 11:58:24 GMT-06:00 2008
+ * Generated by UcdReader at:Mon Jun 30 13:52:41 GMT-06:00 2008
  * block table size:2 (4 bytes)
  * plane table size:6 (64 bytes)
  *
@@ -2266,10 +2266,16 @@ static unsigned int prop[] =
 #define UNI_CODE(ch) (prop[block[plane[(ch>>8)&8191]+((ch>>2)&63)]+(ch&3)])
 
 /**
+ * Get type part of code
+
+ */
+#define UNI_CODE_TO_TYPE(ch) (ch & 0x1f)
+
+/**
  * Fetch the category type
 
  */
-#define UNI_TYPE(ch) (UNI_CODE(ch) & 0x1f)
+#define UNI_TYPE(ch) (UNI_CODE_TO_TYPE(UNI_CODE(ch)))
 
 /**
  * Fetch the digit offset
@@ -2461,28 +2467,28 @@ int uni_is_defined(int ch)
 
 int uni_is_letter(int ch)
 {
-    int c = UNI_CODE(ch);
+    int c = UNI_TYPE(ch);
     return (c>=UNI_UPPERCASE_LETTER && c<=UNI_OTHER_LETTER);
 }
 
 int uni_is_letter_or_digit(int ch)
 {
-    int c = UNI_CODE(ch);
+    int c = UNI_TYPE(ch);
     return ((c>=UNI_UPPERCASE_LETTER && c<=UNI_OTHER_LETTER)
               || c==UNI_DECIMAL_DIGIT_NUMBER);
 }
 
 int uni_is_space(int ch)
 {
-    int c = UNI_CODE(ch);
+    int c = UNI_TYPE(ch);
     return (c==UNI_SPACE_SEPARATOR || c==UNI_LINE_SEPARATOR
-              || c==UNI_PARAGRAPH_SEPARATOR);
+              || c==UNI_PARAGRAPH_SEPARATOR || (ch>= 0x09 && ch <= 0x0d));
 }
 
 int uni_to_lower(int ch)
 {
     int c = UNI_CODE(ch);
-    if (c == UNI_LOWERCASE_LETTER)
+    if (UNI_CODE_TO_TYPE(c) == UNI_LOWERCASE_LETTER)
         return ch;
     ch -= (c>>18) & 0x1ff;
     return ch;
@@ -2491,7 +2497,7 @@ int uni_to_lower(int ch)
 int uni_to_upper(int ch)
 {
     int c = UNI_CODE(ch);
-    if (c == UNI_UPPERCASE_LETTER)
+    if (UNI_CODE_TO_TYPE(c) == UNI_UPPERCASE_LETTER)
         return ch;
     ch += (c>>18) & 0x1ff;
     return ch;
@@ -2500,7 +2506,7 @@ int uni_to_upper(int ch)
 int uni_to_title(int ch)
 {
     int c = UNI_CODE(ch);
-    if (c == UNI_TITLECASE_LETTER)
+    if (UNI_CODE_TO_TYPE(c) == UNI_TITLECASE_LETTER)
         return ch;
     ch += (c>>18) & 0x1ff;
     return ch;
diff --git a/src/dom/ucd.h b/src/dom/ucd.h
index d8b301d47..c4d0ab4e0 100644
--- a/src/dom/ucd.h
+++ b/src/dom/ucd.h
@@ -1,17 +1,25 @@
 /**
+ * Phoebe DOM Implementation.
  *
- * Inkscape Unicode Character Database (UCD) 5.1.0. Utility 
+ * This is a C++ approximation of the W3C DOM model, which follows
+ * fairly closely the specifications in the various .idl files, copies of
+ * which are provided for reference.  Most important is this one:
  *
+ * http://www.w3.org/TR/2004/REC-DOM-Level-3-Core-20040407/idl-definitions.html
+ * 
+ * More thorough explanations of the various classes and their algorithms
+ * can be found there.
+ *     
  *
  * Authors:
  *   Bob Jamison
  *
- * Copyright (C) 2008 Bob Jamison
+ * Copyright (C) 2006-2008 Bob Jamison
  *
  *  This library is free software; you can redistribute it and/or
  *  modify it under the terms of the GNU Lesser General Public
  *  License as published by the Free Software Foundation; either
- *  version 3 of the License, or (at your option) any later version.
+ *  version 2.1 of the License, or (at your option) any later version.
  *
  *  This library is distributed in the hope that it will be useful,
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -21,7 +29,7 @@
  *  You should have received a copy of the GNU Lesser General Public
  *  License along with this library; if not, write to the Free Software
  *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
+ *  
  */
 #ifndef __UCD_H__
 #define __UCD_H__