diff dwtx/dwtxhelper/mangoicu/UBreakIterator.d @ 91:11e8159caf7a

make the mango icu fork work.
author Frank Benoit <benoit@tionex.de>
date Mon, 07 Jul 2008 15:53:07 +0200
parents 040da1cb0d76
children f05207c07a98
line wrap: on
line diff
--- a/dwtx/dwtxhelper/mangoicu/UBreakIterator.d	Sun Jul 06 23:30:07 2008 +0200
+++ b/dwtx/dwtxhelper/mangoicu/UBreakIterator.d	Mon Jul 07 15:53:07 2008 +0200
@@ -1,23 +1,23 @@
 /*******************************************************************************
 
         @file UBreakIterator.d
-        
+
         Copyright (c) 2004 Kris Bell
-        
+
         This software is provided 'as-is', without any express or implied
         warranty. In no event will the authors be held liable for damages
         of any kind arising from the use of this software.
-        
-        Permission is hereby granted to anyone to use this software for any 
-        purpose, including commercial applications, and to alter it and/or 
+
+        Permission is hereby granted to anyone to use this software for any
+        purpose, including commercial applications, and to alter it and/or
         redistribute it freely, subject to the following restrictions:
-        
-        1. The origin of this software must not be misrepresented; you must 
-           not claim that you wrote the original software. If you use this 
-           software in a product, an acknowledgment within documentation of 
+
+        1. The origin of this software must not be misrepresented; you must
+           not claim that you wrote the original software. If you use this
+           software in a product, an acknowledgment within documentation of
            said product would be appreciated but is not required.
 
-        2. Altered source versions must be plainly marked as such, and must 
+        2. Altered source versions must be plainly marked as such, and must
            not be misrepresented as being the original software.
 
         3. This notice may not be removed or altered from any distribution
@@ -30,11 +30,11 @@
                         ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 
-        @version        Initial version, November 2004      
+        @version        Initial version, November 2004
         @author         Kris
 
-        Note that this package and documentation is built around the ICU 
-        project (http://oss.software.ibm.com/icu/). Below is the license 
+        Note that this package and documentation is built around the ICU
+        project (http://oss.software.ibm.com/icu/). Below is the license
         statement as specified by that software:
 
 
@@ -45,7 +45,7 @@
 
         COPYRIGHT AND PERMISSION NOTICE
 
-        Copyright (c) 1995-2003 International Business Machines Corporation and 
+        Copyright (c) 1995-2003 International Business Machines Corporation and
         others.
 
         All rights reserved.
@@ -77,245 +77,251 @@
 
         ----------------------------------------------------------------------
 
-        All trademarks and registered trademarks mentioned herein are the 
+        All trademarks and registered trademarks mentioned herein are the
         property of their respective owners.
 
 *******************************************************************************/
 
-module dwtx.dwthelper.mangoicu.UBreakIterator;
-
-private import  dwtx.dwthelper.mangoicu.ICU;
+module dwtx.dwtxhelper.mangoicu.UBreakIterator;
 
-public  import  dwtx.dwthelper.mangoicu.ULocale,
-                dwtx.dwthelper.mangoicu.UString;
-
-/*******************************************************************************
-
-*******************************************************************************/
+private import  dwtx.dwtxhelper.mangoicu.ICU;
 
-class UCharacterIterator : UBreakIterator
-{
-        /***********************************************************************
-        
-        ***********************************************************************/
+public  import  dwtx.dwtxhelper.mangoicu.ULocale,
+                dwtx.dwtxhelper.mangoicu.UText,
+                dwtx.dwtxhelper.mangoicu.UString;
 
-        this (inout ULocale locale, UText text = null)
-        {
-                super (Type.Character, locale, text);
-        }
-}
 
 
-/*******************************************************************************
-
-*******************************************************************************/
-
-class UWordIterator : UBreakIterator
-{
-        public enum     Break 
-                        {
-                        None = 0, 
-                        NoneLimit = 100, 
-                        Number = 100, 
-                        NumberLimit = 200,
-                        Letter = 200, 
-                        LetterLimit = 300, 
-                        Kana = 300, 
-                        KanaLimit = 400,
-                        Ideo = 400, 
-                        IdeoLimit = 500
-                        }
-
-        /***********************************************************************
-        
-        ***********************************************************************/
-
-        this (inout ULocale locale, UText text = null)
-        {
-                super (Type.Word, locale, text);
-        }
-
-        /***********************************************************************
-        
-                Return the status from the break rule that determined 
-                the most recently returned break position.
-
-        ***********************************************************************/
-
-        void getStatus (inout Break b)
-        {
-                b = cast(Break) super.getStatus();
-        }
-}
+// /*******************************************************************************
+//
+// *******************************************************************************/
+//
+// class UCharacterIterator : UBreakIterator
+// {
+//         /***********************************************************************
+//
+//         ***********************************************************************/
+//
+//         this (inout ULocale locale, UStringView text = null)
+//         {
+//                 super (Type.Character, locale, text);
+//         }
+// }
+//
+//
+// /*******************************************************************************
+//
+// *******************************************************************************/
+//
+// class UWordIterator : UBreakIterator
+// {
+//         public enum     Break
+//                         {
+//                         None = 0,
+//                         NoneLimit = 100,
+//                         Number = 100,
+//                         NumberLimit = 200,
+//                         Letter = 200,
+//                         LetterLimit = 300,
+//                         Kana = 300,
+//                         KanaLimit = 400,
+//                         Ideo = 400,
+//                         IdeoLimit = 500
+//                         }
+//
+//         /***********************************************************************
+//
+//         ***********************************************************************/
+//
+//         this (inout ULocale locale, UStringView text = null)
+//         {
+//                 super (Type.Word, locale, text);
+//         }
+//
+//         /***********************************************************************
+//
+//                 Return the status from the break rule that determined
+//                 the most recently returned break position.
+//
+//         ***********************************************************************/
+//
+//         void getStatus (inout Break b)
+//         {
+//                 b = cast(Break) super.getStatus();
+//         }
+// }
+//
+//
+// /*******************************************************************************
+//
+// *******************************************************************************/
+//
+// class ULineIterator : UBreakIterator
+// {
+//         public enum     Break
+//                         {
+//                         Soft = 0,
+//                         SoftLimit = 100,
+//                         Hard = 100,
+//                         HardLimit = 200
+//                         }
+//
+//         /***********************************************************************
+//
+//         ***********************************************************************/
+//
+//         this (inout ULocale locale, UStringView text = null)
+//         {
+//                 super (Type.Line, locale, text);
+//         }
+//
+//         /***********************************************************************
+//
+//                 Return the status from the break rule that determined
+//                 the most recently returned break position.
+//
+//         ***********************************************************************/
+//
+//         void getStatus (inout Break b)
+//         {
+//                 b = cast(Break) super.getStatus();
+//         }
+// }
+//
+//
+// /*******************************************************************************
+//
+// *******************************************************************************/
+//
+// class USentenceIterator : UBreakIterator
+// {
+//         public enum     Break
+//                         {
+//                         Term = 0,
+//                         TermLimit = 100,
+//                         Sep = 100,
+//                         Limit = 200
+//                         }
+//
+//         /***********************************************************************
+//
+//         ***********************************************************************/
+//
+//         this (inout ULocale locale, UStringView text = null)
+//         {
+//                 super (Type.Sentence, locale, text);
+//         }
+//
+//         /***********************************************************************
+//
+//                 Return the status from the break rule that determined
+//                 the most recently returned break position.
+//
+//         ***********************************************************************/
+//
+//         void getStatus (inout Break b)
+//         {
+//                 b = cast(Break) super.getStatus();
+//         }
+// }
+//
+//
+// /*******************************************************************************
+//
+// *******************************************************************************/
+//
+// class UTitleIterator : UBreakIterator
+// {
+//         /***********************************************************************
+//
+//         ***********************************************************************/
+//
+//         this (inout ULocale locale, UStringView text = null)
+//         {
+//                 super (Type.Title, locale, text);
+//         }
+// }
+//
+//
+// /*******************************************************************************
+//
+// *******************************************************************************/
+//
+// class URuleIterator : UBreakIterator
+// {
+//         /***********************************************************************
+//
+//                 Open a new UBreakIterator for locating text boundaries
+//                 using specified breaking rules
+//
+//         ***********************************************************************/
+//
+//         this (UStringView rules, UStringView text = null)
+//         {
+//                 UErrorCode e;
+//
+//                 handle = ubrk_openRules (rules.get.ptr, rules.length, text.get.ptr, text.length, null, e);
+//                 testError (e, "failed to open rule iterator");
+//         }
+// }
 
 
 /*******************************************************************************
 
-*******************************************************************************/
-
-class ULineIterator : UBreakIterator
-{
-        public enum     Break 
-                        {
-                        Soft = 0, 
-                        SoftLimit = 100, 
-                        Hard = 100, 
-                        HardLimit = 200
-                        }
-
-        /***********************************************************************
-        
-        ***********************************************************************/
-
-        this (inout ULocale locale, UText text = null)
-        {
-                super (Type.Line, locale, text);
-        }
-
-        /***********************************************************************
-        
-                Return the status from the break rule that determined 
-                the most recently returned break position.
-
-        ***********************************************************************/
-
-        void getStatus (inout Break b)
-        {
-                b = cast(Break) super.getStatus();
-        }
-}
-
-
-/*******************************************************************************
-
-*******************************************************************************/
-
-class USentenceIterator : UBreakIterator
-{
-        public enum     Break 
-                        {
-                        Term = 0, 
-                        TermLimit = 100, 
-                        Sep = 100, 
-                        Limit = 200
-                        }
-
-        /***********************************************************************
-        
-        ***********************************************************************/
-
-        this (inout ULocale locale, UText text = null)
-        {
-                super (Type.Sentence, locale, text);
-        }
-
-        /***********************************************************************
-        
-                Return the status from the break rule that determined 
-                the most recently returned break position.
-
-        ***********************************************************************/
-
-        void getStatus (inout Break b)
-        {
-                b = cast(Break) super.getStatus();
-        }
-}
-
-
-/*******************************************************************************
-
-*******************************************************************************/
-
-class UTitleIterator : UBreakIterator
-{
-        /***********************************************************************
-        
-        ***********************************************************************/
-
-        this (inout ULocale locale, UText text = null)
-        {
-                super (Type.Title, locale, text);
-        }
-}
-
-
-/*******************************************************************************
-
-*******************************************************************************/
-
-class URuleIterator : UBreakIterator
-{
-        /***********************************************************************
-        
-                Open a new UBreakIterator for locating text boundaries 
-                using specified breaking rules
-
-        ***********************************************************************/
-
-        this (UText rules, UText text = null)
-        {
-                Error e;
-
-                handle = ubrk_openRules (rules.get.ptr, rules.length, text.get.ptr, text.length, null, e);
-                testError (e, "failed to open rule iterator");
-        }
-}
-
-
-/*******************************************************************************
-
-        BreakIterator defines methods for finding the location of boundaries 
-        in text. Pointer to a UBreakIterator maintain a current position and 
+        BreakIterator defines methods for finding the location of boundaries
+        in text. Pointer to a UBreakIterator maintain a current position and
         scan over text returning the index of characters where boundaries occur.
 
-        Line boundary analysis determines where a text string can be broken 
-        when line-wrapping. The mechanism correctly handles punctuation and 
+        Line boundary analysis determines where a text string can be broken
+        when line-wrapping. The mechanism correctly handles punctuation and
         hyphenated words.
 
-        Sentence boundary analysis allows selection with correct interpretation 
-        of periods within numbers and abbreviations, and trailing punctuation 
+        Sentence boundary analysis allows selection with correct interpretation
+        of periods within numbers and abbreviations, and trailing punctuation
         marks such as quotation marks and parentheses.
 
-        Word boundary analysis is used by search and replace functions, as well 
-        as within text editing applications that allow the user to select words 
-        with a double click. Word selection provides correct interpretation of 
-        punctuation marks within and following words. Characters that are not 
-        part of a word, such as symbols or punctuation marks, have word-breaks 
+        Word boundary analysis is used by search and replace functions, as well
+        as within text editing applications that allow the user to select words
+        with a double click. Word selection provides correct interpretation of
+        punctuation marks within and following words. Characters that are not
+        part of a word, such as symbols or punctuation marks, have word-breaks
         on both sides.
 
-        Character boundary analysis allows users to interact with characters 
-        as they expect to, for example, when moving the cursor through a text 
-        string. Character boundary analysis provides correct navigation of 
-        through character strings, regardless of how the character is stored. 
-        For example, an accented character might be stored as a base character 
-        and a diacritical mark. What users consider to be a character can differ 
+        Character boundary analysis allows users to interact with characters
+        as they expect to, for example, when moving the cursor through a text
+        string. Character boundary analysis provides correct navigation of
+        through character strings, regardless of how the character is stored.
+        For example, an accented character might be stored as a base character
+        and a diacritical mark. What users consider to be a character can differ
         between languages.
 
-        Title boundary analysis locates all positions, typically starts of 
-        words, that should be set to Title Case when title casing the text. 
+        Title boundary analysis locates all positions, typically starts of
+        words, that should be set to Title Case when title casing the text.
 
         See <A HREF="http://oss.software.ibm.com/icu/apiref/ubrk_8h.html">
         this page</A> for full details.
 
 *******************************************************************************/
 
-private class UBreakIterator : ICU
-{       
-        package Handle  handle;  
+struct UBreakIterator
+{
+        typedef void _UBreakIterator;
+        alias _UBreakIterator* Handle;
+        Handle handle;
+        UText ut;
 
         // this is returned by next(), previous() etc ...
         const uint Done = uint.max;
 
         /***********************************************************************
-        
+
                 internal types passed to C API
 
         ***********************************************************************/
 
-        private  enum   Type    
-                        {  
-                        Character, 
+        private  enum   Type
+                        {
+                        Character,
                         Word,
                         Line,
                         Sentence,
@@ -323,58 +329,100 @@
                         }
 
 
+        public enum     WordBreak
+                        {
+                        None = 0,
+                        NoneLimit = 100,
+                        Number = 100,
+                        NumberLimit = 200,
+                        Letter = 200,
+                        LetterLimit = 300,
+                        Kana = 300,
+                        KanaLimit = 400,
+                        Ideo = 400,
+                        IdeoLimit = 500
+                        }
+        public enum     LineBreak
+                        {
+                        Soft = 0,
+                        SoftLimit = 100,
+                        Hard = 100,
+                        HardLimit = 200
+                        }
+        public enum     SentenceBreak
+                        {
+                        Term = 0,
+                        TermLimit = 100,
+                        Sep = 100,
+                        Limit = 200
+                        }
+
+
         /***********************************************************************
-        
-                Internal use only!
+
+                Open a new UBreakIterator for locating text boundaries for
+                a specified locale. A UBreakIterator may be used for detecting
+                character, line, word, and sentence breaks in text.
 
         ***********************************************************************/
 
-        private this ()
-        {
+        static UBreakIterator openWordIterator( ULocale locale, char[] str ){
+            UBreakIterator res;
+            res.ut.openUTF8(str);
+            auto e = ICU.UErrorCode.OK;
+            res.handle = ubrk_open( Type.Word, locale.name.ptr, null, 0, e);
+            ICU.testError (e, "failed to open word iterator");
+            ubrk_setUText( res.handle, & res.ut, e);
+            ICU.testError (e, "failed to set text in iterator");
+            return res;
+        }
+
+        static UBreakIterator openLineIterator( ULocale locale, char[] str ){
+            UBreakIterator res;
+            res.ut.openUTF8(str);
+            auto e = ICU.UErrorCode.OK;
+            res.handle = ubrk_open( Type.Line, locale.name.ptr, null, 0, e);
+            ICU.testError (e, "failed to open line iterator");
+            ubrk_setUText( res.handle, & res.ut, e);
+            ICU.testError (e, "failed to set text in iterator");
+            return res;
         }
 
         /***********************************************************************
-        
-                Open a new UBreakIterator for locating text boundaries for 
-                a specified locale. A UBreakIterator may be used for detecting 
-                character, line, word, and sentence breaks in text. 
 
-        ***********************************************************************/
-
-        this (Type type, inout ULocale locale, UText text)
-        {
-                Error e;
-
-                handle = ubrk_open (type, toString(locale.name), text.get.ptr, text.length, e);
-                testError (e, "failed to create break iterator");
-        }
-
-        /***********************************************************************
-        
                 Close a UBreakIterator
 
         ***********************************************************************/
 
-        ~this ()
+        void close ()
         {
+                ut.close();
                 ubrk_close (handle);
         }
 
         /***********************************************************************
-        
+
                 Sets an existing iterator to point to a new piece of text
 
         ***********************************************************************/
 
-        void setText (UText text)
+        void setText (UStringView text)
         {
-                Error e;
+                ICU.UErrorCode e;
                 ubrk_setText (handle, text.get.ptr, text.length, e);
-                testError (e, "failed to set iterator text");
+                ICU.testError (e, "failed to set iterator text");
+        }
+
+        void setText (char[] text)
+        {
+                auto e = ICU.UErrorCode.OK;
+                ut.openUTF8(text);
+                ubrk_setUText( handle, & ut, e);
+                ICU.testError (e, "failed to set text in iterator");
         }
 
         /***********************************************************************
-        
+
                 Determine the most recently-returned text boundary
 
         ***********************************************************************/
@@ -385,13 +433,13 @@
         }
 
         /***********************************************************************
-        
-                Determine the text boundary following the current text 
-                boundary, or UBRK_DONE if all text boundaries have been 
-                returned. 
-                
-                If offset is specified, determines the text boundary 
-                following the current text boundary: The value returned 
+
+                Determine the text boundary following the current text
+                boundary, or UBRK_DONE if all text boundaries have been
+                returned.
+
+                If offset is specified, determines the text boundary
+                following the current text boundary: The value returned
                 is always greater than offset, or Done
 
         ***********************************************************************/
@@ -404,12 +452,12 @@
         }
 
         /***********************************************************************
-        
-                Determine the text boundary preceding the current text 
+
+                Determine the text boundary preceding the current text
                 boundary, or Done if all text boundaries have been returned.
 
-                If offset is specified, determines the text boundary preceding 
-                the specified offset. The value returned is always smaller than 
+                If offset is specified, determines the text boundary preceding
+                the specified offset. The value returned is always smaller than
                 offset, or Done.
 
         ***********************************************************************/
@@ -422,10 +470,10 @@
         }
 
         /***********************************************************************
-        
-                Determine the index of the first character in the text 
-                being scanned. This is not always the same as index 0 
-                of the text. 
+
+                Determine the index of the first character in the text
+                being scanned. This is not always the same as index 0
+                of the text.
 
         ***********************************************************************/
 
@@ -435,9 +483,9 @@
         }
 
         /***********************************************************************
-        
-                Determine the index immediately beyond the last character 
-                in the text being scanned. This is not the same as the last 
+
+                Determine the index immediately beyond the last character
+                in the text being scanned. This is not the same as the last
                 character
 
         ***********************************************************************/
@@ -448,10 +496,10 @@
         }
 
         /***********************************************************************
-        
+
                 Returns true if the specfied position is a boundary position.
-                As a side effect, leaves the iterator pointing to the first 
-                boundary position at or after "offset". 
+                As a side effect, leaves the iterator pointing to the first
+                boundary position at or after "offset".
 
         ***********************************************************************/
 
@@ -461,8 +509,8 @@
         }
 
         /***********************************************************************
-        
-                Return the status from the break rule that determined 
+
+                Return the status from the break rule that determined
                 the most recently returned break position.
 
         ***********************************************************************/
@@ -473,15 +521,15 @@
         }
 
         /***********************************************************************
-        
-                Return the status from the break rule that determined 
+
+                Return the status from the break rule that determined
                 the most recently returned break position.
 
-                The values appear in the rule source within brackets, 
-                {123}, for example. For rules that do not specify a status, 
+                The values appear in the rule source within brackets,
+                {123}, for example. For rules that do not specify a status,
                 a default value of 0 is returned.
 
-                For word break iterators, the possible values are defined 
+                For word break iterators, the possible values are defined
                 in enum UWordBreak
 
         ***********************************************************************/
@@ -493,7 +541,7 @@
 
 
         /***********************************************************************
-        
+
                 Bind the ICU functions from a shared library. This is
                 complicated by the issues regarding D and DLLs on the
                 Windows platform
@@ -501,17 +549,17 @@
         ***********************************************************************/
 
         private static void* library;
-        
+
         /***********************************************************************
-                
+
         ***********************************************************************/
 
-        private static extern (C) 
+        private static extern (C)
         {
-                Handle function (uint, char*, wchar*, uint, inout Error) ubrk_open;
-                Handle function (wchar*, uint, wchar*, uint, void*, inout Error) ubrk_openRules;
+                Handle function (uint, char*, wchar*, uint, inout ICU.UErrorCode) ubrk_open;
+                Handle function (wchar*, uint, wchar*, uint, void*, inout ICU.UErrorCode) ubrk_openRules;
                 void   function (Handle) ubrk_close;
-                void   function (Handle, wchar*, uint, inout Error) ubrk_setText;
+                void   function (Handle, wchar*, uint, inout ICU.UErrorCode) ubrk_setText;
                 uint   function (Handle) ubrk_current;
                 uint   function (Handle) ubrk_next;
                 uint   function (Handle) ubrk_previous;
@@ -521,15 +569,17 @@
                 uint   function (Handle, uint) ubrk_following;
                 byte   function (Handle, uint) ubrk_isBoundary;
                 uint   function (Handle) ubrk_getRuleStatus;
+                Handle function (Handle, void *, int *, inout ICU.UErrorCode) ubrk_safeClone;
+                void   function (Handle, UText*, inout ICU.UErrorCode) ubrk_setUText;
         }
 
         /***********************************************************************
 
         ***********************************************************************/
 
-        static  FunctionLoader.Bind[] targets = 
+        static FunctionLoader.Bind[] targets =
                 [
-                {cast(void**) &ubrk_open,               "ubrk_open"}, 
+                {cast(void**) &ubrk_open,               "ubrk_open"},
                 {cast(void**) &ubrk_close,              "ubrk_close"},
                 {cast(void**) &ubrk_openRules,          "ubrk_openRules"},
                 {cast(void**) &ubrk_setText,            "ubrk_setText"},
@@ -542,6 +592,8 @@
                 {cast(void**) &ubrk_following,          "ubrk_following"},
                 {cast(void**) &ubrk_isBoundary,         "ubrk_isBoundary"},
                 {cast(void**) &ubrk_getRuleStatus,      "ubrk_getRuleStatus"},
+                {cast(void**) &ubrk_setUText,           "ubrk_setUText"},
+                {cast(void**) &ubrk_safeClone,          "ubrk_safeClone"},
                 ];
 
          /**********************************************************************
@@ -550,13 +602,13 @@
 
          static this ()
          {
-                library = FunctionLoader.bind (icuuc, targets);
+                library = FunctionLoader.bind (ICU.icuuc, targets);
          }
 
          /**********************************************************************
 
          **********************************************************************/
-               
+
          static ~this ()
          {
                FunctionLoader.unbind (library);