diff --git a/include/hbgtcore.h b/include/hbgtcore.h
index e7089d5f1d..aa75b7bdea 100644
--- a/include/hbgtcore.h
+++ b/include/hbgtcore.h
@@ -297,6 +297,7 @@ typedef struct _HB_GT_BASE
HB_BOOL fBlinking;
HB_BOOL fStdOutCon;
HB_BOOL fStdErrCon;
+ HB_BOOL fWideCharWidth; /* Enable Unicode wide character width calculation for UTF-8 */
int iCursorShape;
int iDispCount;
int iExtCount;
diff --git a/include/hbgtinfo.ch b/include/hbgtinfo.ch
index 02a81b82bb..59eb3f3b6e 100644
--- a/include/hbgtinfo.ch
+++ b/include/hbgtinfo.ch
@@ -154,6 +154,7 @@
#define HB_GTI_SYSMENUADD 77 /* Add item to window system menu with keycode to generate when selected (supported by: GTWVT) */
#define HB_GTI_MSGBOX 78 /* Display native MessageBox (supported by: GTQTC) */
#define HB_GTI_SOUND 79 /* play sound file (supported by: GTQTC) */
+#define HB_GTI_WIDECHARWIDTH 80 /* Enable/Disable Unicode wide character width calculation (for UTF-8) */
/* Font weights */
#define HB_GTI_FONTW_THIN 1
diff --git a/include/hbgtwide.h b/include/hbgtwide.h
new file mode 100644
index 0000000000..577d68707c
--- /dev/null
+++ b/include/hbgtwide.h
@@ -0,0 +1,78 @@
+/*
+ * hbgtwide.h - Graphic Terminal Wide Character Width Support
+ *
+ * Copyright (C) 2001 Markus Kuhn
+ *
+ * This software is placed in the public domain.
+ *
+ * Original source: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
+ *
+ * Adapted for Harbour by Dongming Wang
+ *
+ * ANSI C89 compatible version for Harbour
+ *
+ * Unicode TR11 (East Asian Width) implementation
+ */
+
+#ifndef HBGTWIDE_H_
+#define HBGTWIDE_H_
+
+#include "hbdefs.h"
+
+HB_EXTERN_BEGIN
+
+/*
+ * Returns the width in screen columns of a Unicode code point.
+ *
+ * Parameters:
+ * ucs: Unicode code point (HB_WCHAR32)
+ *
+ * Returns:
+ * 0: Control characters, non-printing characters, combining characters
+ * 1: Most characters (Latin, Cyrillic, Greek, Arabic, etc.)
+ * 2: East Asian full-width characters (Chinese, Japanese, Korean)
+ *
+ * Notes:
+ * - This function implements Unicode TR11 (East Asian Width)
+ * - Ambiguous characters are treated as narrow (width 1)
+ * - Private use area characters are treated as narrow (width 1)
+ * - Unassigned characters are treated as narrow (width 1)
+ */
+HB_EXTERN int hb_wcwidth( HB_WCHAR32 ucs );
+
+/*
+ * Returns the width in screen columns of a null-terminated Unicode string.
+ *
+ * Parameters:
+ * pwcs: Pointer to wide character string (HB_WCHAR*)
+ *
+ * Returns:
+ * Total width of the string in screen columns
+ * -1 if the string contains a non-printable character
+ *
+ * Notes:
+ * - This function processes the entire string until null terminator
+ * - Returns -1 if any character has width 0 (non-printable)
+ */
+HB_EXTERN int hb_wcswidth( const HB_WCHAR *pwcs );
+
+/*
+ * Returns the width in screen columns of a substring of a Unicode string.
+ *
+ * Parameters:
+ * pwcs: Pointer to wide character string (HB_WCHAR*)
+ * n: Maximum number of characters to process
+ *
+ * Returns:
+ * Total width of the substring in screen columns
+ * -1 if the string contains a non-printable character
+ *
+ * Notes:
+ * - This function processes at most n characters
+ * - Returns -1 if any character has width 0 (non-printable)
+ */
+HB_EXTERN int hb_wcswidth_cjk( const HB_WCHAR *pwcs, HB_SIZE n );
+
+HB_EXTERN_END
+
+#endif /* HBGTWIDE_H_ */
diff --git a/src/codepage/Makefile b/src/codepage/Makefile
index 373ef55d1a..6d5f2075c7 100644
--- a/src/codepage/Makefile
+++ b/src/codepage/Makefile
@@ -5,6 +5,7 @@ C_SOURCES := \
cp_big5.c \
cp_gbk.c \
cp_utf8.c \
+ hb_wcwidth.c \
cp_u16le.c \
cpbg866.c \
cpbgiso.c \
diff --git a/src/codepage/hb_wcwidth.c b/src/codepage/hb_wcwidth.c
new file mode 100644
index 0000000000..7494e4e753
--- /dev/null
+++ b/src/codepage/hb_wcwidth.c
@@ -0,0 +1,212 @@
+/*
+ * hb_wcwidth.c - Graphic Terminal Wide Character Width Implementation
+ *
+ * Copyright (C) 2001 Markus Kuhn
+ *
+ * This software is placed in the public domain.
+ *
+ * Original source: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
+ *
+ * Adapted for Harbour by Dongming Wang
+ *
+ * ANSI C89 compatible version for Harbour
+ *
+ * This is a simplified implementation of Unicode TR11 (East Asian Width).
+ * It covers the most common Unicode character ranges.
+ */
+
+#include "hbgtwide.h"
+
+/* Interval structure for binary search in range tables */
+struct interval
+{
+ unsigned int first;
+ unsigned int last;
+};
+
+/* Binary search in range table */
+static int bisearch( HB_WCHAR32 ucs, const struct interval *table, int max )
+{
+ int min = 0;
+ int mid;
+
+ if( ucs < table[ 0 ].first || ucs > table[ max ].last )
+ return 0;
+
+ while( max >= min )
+ {
+ mid = ( min + max ) / 2;
+
+ if( ucs > table[ mid ].last )
+ min = mid + 1;
+ else if( ucs < table[ mid ].first )
+ max = mid - 1;
+ else
+ return 1;
+ }
+
+ return 0;
+}
+
+/* Combining characters (width 0) */
+static const struct interval combining[] =
+{
+ { 0x0300, 0x034E }, { 0x0360, 0x0362 }, { 0x0483, 0x0486 },
+ { 0x0488, 0x0489 }, { 0x0591, 0x05B9 }, { 0x05BB, 0x05BD },
+ { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 },
+ { 0x05C7, 0x05C7 }, { 0x0610, 0x0615 }, { 0x064B, 0x065E },
+ { 0x0670, 0x0670 }, { 0x06D6, 0x06DC }, { 0x06DE, 0x06E4 },
+ { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x070F, 0x070F },
+ { 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 },
+ { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 }, { 0x093C, 0x093C },
+ { 0x0941, 0x0948 }, { 0x094D, 0x094D }, { 0x0951, 0x0954 },
+ { 0x0962, 0x0963 }, { 0x0981, 0x0981 }, { 0x09BC, 0x09BC },
+ { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 },
+ { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 },
+ { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 },
+ { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 },
+ { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD }, { 0x0AE2, 0x0AE3 },
+ { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C }, { 0x0B3F, 0x0B3F },
+ { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D }, { 0x0B56, 0x0B56 },
+ { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD },
+ { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D },
+ { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC }, { 0x0CBF, 0x0CBF },
+ { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD }, { 0x0CE2, 0x0CE3 },
+ { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D }, { 0x0DCA, 0x0DCA },
+ { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 }, { 0x0E31, 0x0E31 },
+ { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E }, { 0x0EB1, 0x0EB1 },
+ { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC }, { 0x0EC8, 0x0ECD },
+ { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 }, { 0x0F37, 0x0F37 },
+ { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E }, { 0x0F80, 0x0F84 },
+ { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 }, { 0x0F99, 0x0FBC },
+ { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 }, { 0x1032, 0x1032 },
+ { 0x1036, 0x1037 }, { 0x1039, 0x103A }, { 0x1058, 0x1059 },
+ { 0x1160, 0x11FF }, { 0x135F, 0x135F }, { 0x1712, 0x1714 },
+ { 0x1732, 0x1734 }, { 0x1752, 0x1753 }, { 0x1772, 0x1773 },
+ { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, { 0x17C6, 0x17C6 },
+ { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, { 0x180B, 0x180D },
+ { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, { 0x1927, 0x1928 },
+ { 0x1932, 0x1932 }, { 0x1939, 0x193B }, { 0x1A17, 0x1A18 },
+ { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 }, { 0x1B36, 0x1B3A },
+ { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 }, { 0x1B6B, 0x1B73 },
+ { 0x1DC0, 0x1DC3 }, { 0x200B, 0x200F }, { 0x202A, 0x202E },
+ { 0x2060, 0x2063 }, { 0x20D0, 0x20EA }, { 0x302A, 0x302F },
+ { 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
+ { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
+ { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
+ { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
+ { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
+ { 0x1D173, 0x1D17A }, { 0x1D17B, 0x1D182 }, { 0x1D185, 0x1D18B },
+ { 0x1D1AA, 0x1D1AD }, { 0xE0100, 0xE01EF }
+};
+
+/* Wide characters (width 2) - CJK full-width characters */
+static const struct interval wide[] =
+{
+ { 0x1100, 0x1159 }, { 0x2E80, 0xA4CF }, { 0xAC00, 0xD7A3 },
+ { 0xF900, 0xFAFF }, { 0xFE10, 0xFE19 }, { 0xFE30, 0xFE6F },
+ { 0xFF00, 0xFF60 }, { 0xFFE0, 0xFFE6 }, { 0x20000, 0x2FFFD },
+ { 0x30000, 0x3FFFD }
+};
+
+/*
+ * Returns the width in screen columns of a Unicode code point.
+ *
+ * Parameters:
+ * ucs: Unicode code point (HB_WCHAR32)
+ *
+ * Returns:
+ * 0: Control characters, non-printing characters, combining characters
+ * 1: Most characters (Latin, Cyrillic, Greek, Arabic, etc.)
+ * 2: East Asian full-width characters (Chinese, Japanese, Korean)
+ *
+ * Notes:
+ * - This function implements Unicode TR11 (East Asian Width)
+ * - Ambiguous characters are treated as narrow (width 1)
+ * - Private use area characters are treated as narrow (width 1)
+ * - Unassigned characters are treated as narrow (width 1)
+ */
+int hb_wcwidth( HB_WCHAR32 ucs )
+{
+ /* Test for 8-bit control characters */
+ if( ucs == 0 )
+ return 0;
+
+ if( ucs < 32 || ( ucs >= 0x7F && ucs < 0xA0 ) )
+ return 0;
+
+ /* Binary search in table of non-spacing characters */
+ if( bisearch( ucs, combining, sizeof( combining ) / sizeof( struct interval ) - 1 ) )
+ return 0;
+
+ /* Binary search in table of wide characters */
+ if( bisearch( ucs, wide, sizeof( wide ) / sizeof( struct interval ) - 1 ) )
+ return 2;
+
+ return 1;
+}
+
+/*
+ * Returns the width in screen columns of a null-terminated Unicode string.
+ *
+ * Parameters:
+ * pwcs: Pointer to wide character string (HB_WCHAR*)
+ *
+ * Returns:
+ * Total width of the string in screen columns
+ * -1 if the string contains a non-printable character
+ *
+ * Notes:
+ * - This function processes the entire string until null terminator
+ * - Returns -1 if any character has width 0 (non-printable)
+ */
+int hb_wcswidth( const HB_WCHAR *pwcs )
+{
+ int width = 0;
+
+ while( *pwcs != L'\0' )
+ {
+ int w = hb_wcwidth( (HB_WCHAR32)*pwcs );
+
+ if( w < 0 )
+ return -1;
+
+ width += w;
+ pwcs++;
+ }
+
+ return width;
+}
+
+/*
+ * Returns the width in screen columns of a substring of a Unicode string.
+ *
+ * Parameters:
+ * pwcs: Pointer to wide character string (HB_WCHAR*)
+ * n: Maximum number of characters to process
+ *
+ * Returns:
+ * Total width of the substring in screen columns
+ * -1 if the string contains a non-printable character
+ *
+ * Notes:
+ * - This function processes at most n characters
+ * - Returns -1 if any character has width 0 (non-printable)
+ */
+int hb_wcswidth_cjk( const HB_WCHAR *pwcs, HB_SIZE n )
+{
+ int width = 0;
+
+ while( n-- > 0 && *pwcs != L'\0' )
+ {
+ int w = hb_wcwidth( (HB_WCHAR32)*pwcs );
+
+ if( w < 0 )
+ return -1;
+
+ width += w;
+ pwcs++;
+ }
+
+ return width;
+}
diff --git a/src/rtl/hbgtcore.c b/src/rtl/hbgtcore.c
index 6e8f7b0b58..e774fc124e 100644
--- a/src/rtl/hbgtcore.c
+++ b/src/rtl/hbgtcore.c
@@ -58,6 +58,7 @@
#include "hbapifs.h"
#include "hbapierr.h"
#include "hbapicdp.h"
+#include "hbgtwide.h"
#include "hbdate.h"
#include "hbset.h"
#include "hbvm.h"
@@ -87,6 +88,25 @@ void hb_gt_BaseUnlock( PHB_GT pGT )
HB_GTSELF_UNLOCK( pGT );
}
+/* Calculate Unicode character display width based on GT driver setting
+ * This helper function checks the fWideCharWidth flag and returns
+ * the appropriate display width for the character.
+ *
+ * When fWideCharWidth is enabled, uses hb_wcwidth() for accurate
+ * Unicode TR11 East Asian Width calculation. Otherwise returns 1
+ * for backward compatibility.
+ */
+static int hb_gt_charDispWidth( PHB_GT pGT, HB_WCHAR wc )
+{
+ if( pGT->fWideCharWidth )
+ {
+ /* Use accurate Unicode TR11 width calculation */
+ return hb_wcwidth( (HB_WCHAR32)wc );
+ }
+ /* Default: narrow character (width 1) for backward compatibility */
+ return 1;
+}
+
void hb_gt_BaseLock( PHB_GT pGT )
{
HB_GTSELF_LOCK( pGT );
@@ -107,6 +127,7 @@ static void hb_gt_def_BaseInit( PHB_GT_BASE pGT )
pGT->fBlinking = HB_TRUE;
pGT->fStdOutCon = HB_FALSE;
pGT->fStdErrCon = HB_FALSE;
+ pGT->fWideCharWidth = HB_FALSE; /* Default: disable Unicode wide char width calc */
pGT->iCursorShape = SC_NORMAL;
pGT->iDispCount = 0;
pGT->iExtCount = 0;
@@ -856,33 +877,44 @@ static int hb_gt_def_PutText( PHB_GT pGT, int iRow, int iCol, int iColor, const
PHB_CODEPAGE cdp = HB_GTSELF_HOSTCP( pGT );
HB_SIZE nIndex = 0;
HB_WCHAR wc;
+ int iDispCol = iCol; /* Actual display column position */
while( HB_CDPCHAR_GET( cdp, szText, nLen, &nIndex, &wc ) )
{
- if( ! HB_GTSELF_PUTCHAR( pGT, iRow, iCol++, iColor, 0, wc ) )
+ if( ! HB_GTSELF_PUTCHAR( pGT, iRow, iCol, iColor, 0, wc ) )
{
while( HB_CDPCHAR_GET( cdp, szText, nLen, &nIndex, &wc ) )
- ++iCol;
+ iDispCol += hb_gt_charDispWidth( pGT, wc );
break;
}
+ /* Add character display width to actual display position */
+ iDispCol += hb_gt_charDispWidth( pGT, wc );
+ iCol++; /* Cell index only increments by 1 */
}
- return iCol;
+ return iDispCol;
}
static int hb_gt_def_PutTextW( PHB_GT pGT, int iRow, int iCol, int iColor, const HB_WCHAR * szText, HB_SIZE nLen )
{
+ int iDispCol = iCol; /* Actual display column position */
+
if( nLen )
{
do
{
- if( ! HB_GTSELF_PUTCHAR( pGT, iRow, iCol, iColor, 0, *szText++ ) )
+ if( ! HB_GTSELF_PUTCHAR( pGT, iRow, iCol, iColor, 0, *szText ) )
break;
- ++iCol;
+
+ /* Add character display width to actual display position */
+ iDispCol += hb_gt_charDispWidth( pGT, *szText );
+
+ szText++;
+ ++iCol; /* Cell index only increments by 1 */
}
while( --nLen );
}
- return iCol + ( int ) nLen;
+ return iDispCol;
}
static void hb_gt_def_Replicate( PHB_GT pGT, int iRow, int iCol, int iColor,
@@ -1027,7 +1059,7 @@ static void hb_gt_def_WriteCon( PHB_GT pGT, const char * szText, HB_SIZE nLength
break;
default:
- ++iCol;
+ iCol += hb_gt_charDispWidth( pGT, wc );
if( iCol > iMaxCol || iCol <= 0 )
{
/* If the cursor position started off the left edge,
@@ -2006,6 +2038,13 @@ static HB_BOOL hb_gt_def_Info( PHB_GT pGT, int iType, PHB_GT_INFO pInfo )
HB_GTSELF_VERSION( pGT, hb_itemGetNI( pInfo->pNewVal ) ) );
break;
+ case HB_GTI_WIDECHARWIDTH:
+ /* Enable/Disable Unicode wide character width calculation */
+ pInfo->pResult = hb_itemPutL( pInfo->pResult, pGT->fWideCharWidth );
+ if( hb_itemType( pInfo->pNewVal ) & HB_IT_LOGICAL )
+ pGT->fWideCharWidth = hb_itemGetL( pInfo->pNewVal );
+ break;
+
default:
return HB_FALSE;
}