More changes to build in standard bitmaps,

update the charset data from the latest usincode,
add 0x85 to the whitespace and newline set
add the capitalizedLetterCharacterSet


git-svn-id: svn+ssh://svn.gna.org/svn/gnustep/libs/base/trunk@20856 72102866-910b-0410-8b05-ffd578937521

ChangeLog

@@ -1,3 +1,17 @@
+2005-03-06  Richard Frith-Macdonald <rfm@gnu.org>
+
+	* Headers/Foundation/NSCharacterSet.h: Add documentation and method
+	([-capitalizedLetterCharacterSet])
+	* Source/NSCharacterSet.m: Add new method and move documentation to
+	header.  Include local NSCharacterSetData.h for bitmap data.
+	* Source/NSCharacterSetData.h: New file containing the bitmap data
+	for the standard charactersets.  Generated by dev-apps/charsets
+	tools using the latest unicode characterset data today.
+	* Source/NSCharacterSets/README.CharSet: mark as obsolete.
+	* Source/GNUmakefile: No longer build/install NSCharacterSets
+	The standard bitmap data for charactersets is now built in to
+	NSCharacterSet.
+
 2005-03-04  Richard Frith-Macdonald <rfm@gnu.org>
 
 	* Source/Additions/GSXML.m: GSXMLRPC integrated.

GNUmakefile

@@ -50,7 +50,7 @@ PACKAGE_NAME = gnustep-base
 #
 # The list of subproject directories
 #
-SUBPROJECTS = NSCharacterSets Source SSL Tools NSTimeZones Resources
+SUBPROJECTS = Source SSL Tools NSTimeZones Resources
 
 -include Makefile.preamble
 

Headers/Foundation/NSCharacterSet.h

@@ -28,45 +28,185 @@
 
 @class NSData;
 
+/**
+ *  Represents a set of unicode characters.  Used by [NSScanner] and [NSString]
+ *  for parsing-related methods.
+ */
 @interface NSCharacterSet : NSObject <NSCoding, NSCopying, NSMutableCopying>
 
-// Creating standard character sets
+/**
+ *  Returns a character set containing letters, numbers, and diacritical
+ *  marks.  Note that "letters" includes all alphabetic as well as Chinese
+ *  characters, etc..
+ */
 + (NSCharacterSet*) alphanumericCharacterSet;
+
+#ifndef	STRICT_OPENSTEP
+/**
+ *  Returns a character set containing letters in the unicode
+ *  Titlecase category.
+ */
++ (NSCharacterSet*) capitalizedLetterCharacterSet;
+#endif
+
+/**
+ *  Returns a character set containing control and format characters.
+ */
 + (NSCharacterSet*) controlCharacterSet;
+
+/**
+ * Returns a character set containing characters that represent
+ * the decimal digits 0 through 9.
+ */
 + (NSCharacterSet*) decimalDigitCharacterSet;
+
+/**
+ * Returns a character set containing individual charactars that
+ * can be represented also by a composed character sequence.
+ */
 + (NSCharacterSet*) decomposableCharacterSet;
+
+/**
+ * Returns a character set containing unassigned (illegal)
+ * character values.
+ */
 + (NSCharacterSet*) illegalCharacterSet;
+
+/**
+ *  Returns a character set containing letters, including all alphabetic as
+ *  well as Chinese characters, etc..
+ */
 + (NSCharacterSet*) letterCharacterSet;
+
+/**
+ * Returns a character set that contains the lowercase characters.
+ * This set does not include caseless characters, only those that
+ * have corresponding characters in uppercase and/or titlecase.
+ */
 + (NSCharacterSet*) lowercaseLetterCharacterSet;
+
+/**
+ *  Returns a character set containing characters for diacritical marks, which
+ *  are usually only rendered in conjunction with another character.
+ */
 + (NSCharacterSet*) nonBaseCharacterSet;
+
+/**
+ *  Returns a character set containing punctuation marks.
+ */
 + (NSCharacterSet*) punctuationCharacterSet;
+
+/**
+ *  Returns a character set containing mathematical symbols, etc..
+ */
 + (NSCharacterSet*) symbolAndOperatorCharacterSet;
+
+/**
+ * Returns a character set that contains the uppercase characters.
+ * This set does not include caseless characters, only those that
+ * have corresponding characters in lowercase and/or titlecase.
+ */
 + (NSCharacterSet*) uppercaseLetterCharacterSet;
+
+/**
+ * Returns a character set that contains the whitespace characters,
+ * plus the newline characters, values 0x000A and 0x000D and nextline
+ * 0x0085 character.
+ */
 + (NSCharacterSet*) whitespaceAndNewlineCharacterSet;
+
+/**
+ * Returns a character set that contains the whitespace characters.
+ */
 + (NSCharacterSet*) whitespaceCharacterSet;
 
-// Creating custom character sets
+/**
+ * Returns a character set containing characters as encoded in the
+ * data object (8192 bytes)
+ */
 + (NSCharacterSet*) characterSetWithBitmapRepresentation: (NSData*)data;
+
+/**
+ *  Returns set with characters in aString, or empty set for empty string.
+ *  Raises an exception if given a nil string.
+ */
 + (NSCharacterSet*) characterSetWithCharactersInString: (NSString*)aString;
+
+/**
+ *  Returns set containing unicode index range given by aRange.
+ */
 + (NSCharacterSet*) characterSetWithRange: (NSRange)aRange;
 
-- (NSData*) bitmapRepresentation;
-- (BOOL) characterIsMember: (unichar)aCharacter;
-- (NSCharacterSet*) invertedSet;
-
 #ifndef	STRICT_MACOS_X
+/**
+ *  Initializes from a bitmap.  (See [NSBitmapCharSet].)  File must have
+ *  extension "<code>.bitmap</code>".  (To get around this load the file
+ *  into data yourself and use
+ *  [NSCharacterSet -characterSetWithBitmapRepresentation].
+ */
 + (NSCharacterSet*) characterSetWithContentsOfFile: (NSString*)aFile;
 #endif
+
+/**
+ * Returns a bitmap representation of the receiver's character set
+ * suitable for archiving or writing to a file, in an NSData object.
+ */
+- (NSData*) bitmapRepresentation;
+
+/**
+ * Returns YES if the receiver contains <em>aCharacter</em>, NO if
+ * it does not.
+ */
+- (BOOL) characterIsMember: (unichar)aCharacter;
+
+/**
+ * Returns a character set containing only characters that the
+ * receiver does not contain.
+ */
+- (NSCharacterSet*) invertedSet;
+
 @end
 
+/**
+ *  An [NSCharacterSet] that can be modified.
+ */
 @interface NSMutableCharacterSet : NSCharacterSet
 
+/**
+ *  Adds characters specified by unicode indices in aRange to set.
+ */
 - (void) addCharactersInRange: (NSRange)aRange;
+
+/**
+ *  Adds characters in aString to set.
+ */
 - (void) addCharactersInString: (NSString*)aString;
+
+/**
+ *  Set union of character sets.
+ */
 - (void) formUnionWithCharacterSet: (NSCharacterSet*)otherSet;
+
+/**
+ *  Set intersection of character sets.
+ */
 - (void) formIntersectionWithCharacterSet: (NSCharacterSet*)otherSet;
+
+/**
+ *  Drop given range of characters.  No error for characters not currently in
+ *  set.
+ */
 - (void) removeCharactersInRange: (NSRange)aRange;
+
+/**
+ *  Drop characters in aString.  No error for characters not currently in
+ *  set.
+ */
 - (void) removeCharactersInString: (NSString*)aString;
+
+/**
+ *  Remove all characters currently in set and add all other characters.
+ */
 - (void) invert;
 
 @end

NSCharacterSets/README.CharSet

@@ -1,3 +1,11 @@
+#############################################################################
+   THIS DIRECTORY IS OBSOLETE AND IS NO LONGER USED
+
+   The NSCharacterSetData.h file (in CVS in core/base/Source) is generated
+   using the tools in dev-apps/charsets and the library in dev-libs/ucsdata
+
+#############################################################################
+
 
    This files in this directory are CharacterSet bitmaps which contain
    a bitmap representation of the Unicode characters in the respective
@@ -7,10 +15,6 @@
    of the Unicode character set as of Feb. 27, 2001.  The Unicode character
    set can be obtained from http://www.unicode.org
 
-   The NSCharacterSetData.h file is generated from the binary bitmap
-   data in the individual .dat files, and is compiled in to the
-   NSCharacterSet class.
-
    The binary data files are no longer used at runtime.
 
    The current character sets are based on UnicodeData.txt version 3.0.1.

Source/NSCharacterSet.m

@@ -36,7 +36,7 @@
 #include "Foundation/NSThread.h"
 #include "Foundation/NSNotification.h"
 
-#include "../NSCharacterSets/NSCharacterSetData.h"
+#include "NSCharacterSetData.h"
 
 /* A simple array for caching standard bitmap sets */
 #define MAX_STANDARD_SETS 15
@@ -88,10 +88,6 @@ static Class abstractClass = nil;
 
 @end
 
-/**
- *  Represents a set of unicode characters.  Used by [NSScanner] and [NSString]
- *  for parsing-related methods.
- */
 @implementation NSCharacterSet
 
 + (void) initialize
@@ -123,137 +119,81 @@ static Class abstractClass = nil;
   return cache_set[number];
 }
 
-/**
- *  Returns a character set containing letters, numbers, and diacritical
- *  marks.  Note that "letters" includes all alphabetic as well as Chinese
- *  characters, etc..
- */
 + (NSCharacterSet*) alphanumericCharacterSet
 {
   return [self _staticSet: alphanumericCharSet number: 0];
 }
 
-/**
++ (NSCharacterSet*) capitalizedLetterCharacterSet
- *  Returns a character set containing control and format characters.
+{
- */
+  return [self _staticSet: titlecaseLetterCharSet number: 13];
+}
+
 + (NSCharacterSet*) controlCharacterSet
 {
   return [self _staticSet: controlCharSet number: 1];
 }
 
-/**
- * Returns a character set containing characters that represent
- * the decimal digits 0 through 9.
- */
 + (NSCharacterSet*) decimalDigitCharacterSet
 {
   return [self _staticSet: decimalDigitCharSet number: 2];
 }
 
-/**
- * Returns a character set containing individual charactars that
- * can be represented also by a composed character sequence.
- */
 + (NSCharacterSet*) decomposableCharacterSet
 {
   return [self _staticSet: decomposableCharSet number: 3];
 }
 
-/**
- * Returns a character set containing unassigned (illegal)
- * character values.
- */
 + (NSCharacterSet*) illegalCharacterSet
 {
   return [self _staticSet: illegalCharSet number: 4];
 }
 
-/**
- *  Returns a character set containing letters, including all alphabetic as
- *  well as Chinese characters, etc..
- */
 + (NSCharacterSet*) letterCharacterSet
 {
   return [self _staticSet: letterCharSet number: 5];
 }
 
-/**
- * Returns a character set that contains the lowercase characters.
- * This set does not include caseless characters, only those that
- * have corresponding characters in uppercase and/or titlecase.
- */
 + (NSCharacterSet*) lowercaseLetterCharacterSet
 {
   return [self _staticSet: lowercaseLetterCharSet number: 6];
 }
 
-/**
- *  Returns a character set containing characters for diacritical marks, which
- *  are usually only rendered in conjunction with another character.
- */
 + (NSCharacterSet*) nonBaseCharacterSet
 {
   return [self _staticSet: nonBaseCharSet number: 7];
 }
 
-/**
- *  Returns a character set containing punctuation marks.
- */
 + (NSCharacterSet*) punctuationCharacterSet
 {
   return [self _staticSet: punctuationCharSet number: 8];
 }
 
-/**
- *  Returns a character set containing mathematical symbols, etc..
- */
 + (NSCharacterSet*) symbolAndOperatorCharacterSet
 {
   return [self _staticSet: symbolAndOperatorCharSet number: 9];
 }
 
-/**
- * Returns a character set that contains the uppercase characters.
- * This set does not include caseless characters, only those that
- * have corresponding characters in lowercase and/or titlecase.
- */
 + (NSCharacterSet*) uppercaseLetterCharacterSet
 {
   return [self _staticSet: uppercaseLetterCharSet number: 10];
 }
 
-/**
- * Returns a character set that contains the whitespace characters,
- * plus the newline characters, values 0x000A and 0x000D.
- */
 + (NSCharacterSet*) whitespaceAndNewlineCharacterSet
 {
   return [self _staticSet: whitespaceAndNlCharSet number: 11];
 }
 
-/**
- * Returns a character set that contains the whitespace characters.
- */
 + (NSCharacterSet*) whitespaceCharacterSet
 {
   return [self _staticSet: whitespaceCharSet number: 12];
 }
 
-// Creating custom character sets
-
-/**
- * Returns a character set containing characters as encoded in the
- * data object.
- */
 + (NSCharacterSet*) characterSetWithBitmapRepresentation: (NSData*)data
 {
   return AUTORELEASE([[NSBitmapCharSet alloc] initWithBitmap: data]);
 }
 
-/**
- *  Returns set with characters in aString, or empty set for empty string.
- *  Raises an exception if given a nil string.
- */
 + (NSCharacterSet*) characterSetWithCharactersInString: (NSString*)aString
 {
   unsigned	i;
@@ -280,9 +220,6 @@ static Class abstractClass = nil;
   return [self characterSetWithBitmapRepresentation: bitmap];
 }
 
-/**
- *  Returns set containing unicode index range given by aRange.
- */
 + (NSCharacterSet*)characterSetWithRange: (NSRange)aRange
 {
   unsigned	i;
@@ -304,12 +241,6 @@ static Class abstractClass = nil;
   return [self characterSetWithBitmapRepresentation: bitmap];
 }
 
-/**
- *  Initializes from a bitmap.  (See [NSBitmapCharSet].)  File must have
- *  extension "<code>.bitmap</code>".  (To get around this load the file
- *  into data yourself and use
- *  [NSCharacterSet -characterSetWithBitmapRepresentation].
- */
 + (NSCharacterSet*) characterSetWithContentsOfFile: (NSString*)aFile
 {
   if ([@"bitmap" isEqual: [aFile pathExtension]])
@@ -321,20 +252,12 @@ static Class abstractClass = nil;
     return nil;
 }
 
-/**
- * Returns a bitmap representation of the receiver's character set
- * suitable for archiving or writing to a file, in an NSData object.
- */
 - (NSData*) bitmapRepresentation
 {
   [self subclassResponsibility: _cmd];
   return 0;
 }
 
-/**
- * Returns YES if the receiver contains <em>aCharacter</em>, NO if
- * it does not.
- */
 - (BOOL) characterIsMember: (unichar)aCharacter
 {
   [self subclassResponsibility: _cmd];
@@ -385,10 +308,6 @@ static Class abstractClass = nil;
   return NO;
 }
 
-/**
- * Returns a character set containing only characters that the
- * receiver does not contain.
- */
 - (NSCharacterSet*) invertedSet
 {
   unsigned	i;
@@ -425,9 +344,6 @@ static Class abstractClass = nil;
 
 @end
 
-/**
- *  An [NSCharacterSet] that can be modified.
- */
 @implementation NSMutableCharacterSet
 
 /* Provide a default object for allocation */
@@ -447,6 +363,11 @@ static Class abstractClass = nil;
   return AUTORELEASE([[abstractClass performSelector: _cmd] mutableCopy]);
 }
 
++ (NSCharacterSet*) capitalizedLetterCharacterSet
+{
+  return AUTORELEASE([[abstractClass performSelector: _cmd] mutableCopy]);
+}
+
 + (NSCharacterSet*) controlCharacterSet
 {
   return AUTORELEASE([[abstractClass performSelector: _cmd] mutableCopy]);
@@ -507,61 +428,36 @@ static Class abstractClass = nil;
   return AUTORELEASE([[abstractClass performSelector: _cmd] mutableCopy]);
 }
 
-/* Mutable subclasses must implement ALL of these methods. */
-
-/**
- *  Adds characters specified by unicode indices in aRange to set.
- */
 - (void) addCharactersInRange: (NSRange)aRange
 {
   [self subclassResponsibility: _cmd];
 }
 
-/**
- *  Adds characters in aString to set.
- */
 - (void) addCharactersInString: (NSString*)aString
 {
   [self subclassResponsibility: _cmd];
 }
 
-/**
- *  Set union of character sets.
- */
 - (void) formUnionWithCharacterSet: (NSCharacterSet*)otherSet
 {
   [self subclassResponsibility: _cmd];
 }
 
-/**
- *  Set intersection of character sets.
- */
 - (void) formIntersectionWithCharacterSet: (NSCharacterSet*)otherSet
 {
   [self subclassResponsibility: _cmd];
 }
 
-/**
- *  Drop given range of characters.  No error for characters not currently in
- *  set.
- */
 - (void) removeCharactersInRange: (NSRange)aRange
 {
   [self subclassResponsibility: _cmd];
 }
 
-/**
- *  Drop characters in aString.  No error for characters not currently in
- *  set.
- */
 - (void) removeCharactersInString: (NSString*)aString
 {
   [self subclassResponsibility: _cmd];
 }
 
-/**
- *  Remove all characters currently in set and add all other characters.
- */
 - (void) invert
 {
   [self subclassResponsibility: _cmd];