IntelFrameworkPkg/Library/FrameworkUefiLib/Console.c

   1 /** @file
   2   This module provide help function for displaying unicode string.
   3
   4   Copyright (c) 2006, Intel Corporation. All rights reserved.<BR>
   5   This program and the accompanying materials
   6   are licensed and made available under the terms and conditions of the BSD License
   7   which accompanies this distribution.  The full text of the license may be found at
   8   http://opensource.org/licenses/bsd-license.php
   9
  10   THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
  11   WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
  12
  13 **/
  14
  15 #include "UefiLibInternal.h"
  16
  17 typedef struct {
  18   CHAR16  WChar;
  19   UINT32  Width;
  20 } UNICODE_WIDTH_ENTRY;
  21
  22 GLOBAL_REMOVE_IF_UNREFERENCED CONST UNICODE_WIDTH_ENTRY mUnicodeWidthTable[] = {
  23   //
  24   // General script area
  25   //
  26   {(CHAR16)0x1FFF,  1},
  27   /*
  28    * Merge the blocks and replace them with the above entry as they fall to
  29    * the same category and they are all narrow glyph. This will reduce search
  30    * time and table size. The merge will omit the reserved code.
  31    *
  32    * Remove the above item if below is un-commented.
  33    *
  34   {(CHAR16)0x007F,  1},       // C0 controls and basic Latin. 0x0000-0x007F
  35   {(CHAR16)0x00FF,  1},       // C1 controls and Latin-1 support. 0x0080-0x00FF
  36   {(CHAR16)0x017F,  1},       // Latin extended-A. 0x0100-0x017F
  37   {(CHAR16)0x024F,  1},       // Latin extended-B. 0x0180-0x024F
  38   {(CHAR16)0x02AF,  1},       // IPA extensions. 0x0250-0x02AF
  39   {(CHAR16)0x02FF,  1},       // Spacing modifier letters. 0x02B0-0x02FF
  40   {(CHAR16)0x036F,  1},       // Combining diacritical marks. 0x0300-0x036F
  41   {(CHAR16)0x03FF,  1},       // Greek. 0x0370-0x03FF
  42   {(CHAR16)0x04FF,  1},       // Cyrillic. 0x0400-0x04FF
  43   {(CHAR16)0x052F,  0},       // Unassigned. As Armenian in ver3.0. 0x0500-0x052F
  44   {(CHAR16)0x058F,  1},       // Armenian. 0x0530-0x058F
  45   {(CHAR16)0x05FF,  1},       // Hebrew. 0x0590-0x05FF
  46   {(CHAR16)0x06FF,  1},       // Arabic. 0x0600-0x06FF
  47   {(CHAR16)0x08FF,  0},       // Unassigned. 0x0700-0x08FF
  48   {(CHAR16)0x097F,  1},       // Devanagari. 0x0900-0x097F
  49   {(CHAR16)0x09FF,  1},       // Bengali. 0x0980-0x09FF
  50   {(CHAR16)0x0A7F,  1},       // Gurmukhi. 0x0A00-0x0A7F
  51   {(CHAR16)0x0AFF,  1},       // Gujarati. 0x0A80-0x0AFF
  52   {(CHAR16)0x0B7F,  1},       // Oriya. 0x0B00-0x0B7F
  53   {(CHAR16)0x0BFF,  1},       // Tamil. (See page 7-92). 0x0B80-0x0BFF
  54   {(CHAR16)0x0C7F,  1},       // Telugu. 0x0C00-0x0C7F
  55   {(CHAR16)0x0CFF,  1},       // Kannada. (See page 7-100). 0x0C80-0x0CFF
  56   {(CHAR16)0x0D7F,  1},       // Malayalam (See page 7-104). 0x0D00-0x0D7F
  57   {(CHAR16)0x0DFF,  0},       // Unassigned. 0x0D80-0x0DFF
  58   {(CHAR16)0x0E7F,  1},       // Thai. 0x0E00-0x0E7F
  59   {(CHAR16)0x0EFF,  1},       // Lao. 0x0E80-0x0EFF
  60   {(CHAR16)0x0FBF,  1},       // Tibetan. 0x0F00-0x0FBF
  61   {(CHAR16)0x109F,  0},       // Unassigned. 0x0FC0-0x109F
  62   {(CHAR16)0x10FF,  1},       // Georgian. 0x10A0-0x10FF
  63   {(CHAR16)0x11FF,  1},       // Hangul Jamo. 0x1100-0x11FF
  64   {(CHAR16)0x1DFF,  0},       // Unassigned. 0x1200-0x1DFF
  65   {(CHAR16)0x1EFF,  1},       // Latin extended additional. 0x1E00-0x1EFF
  66   {(CHAR16)0x1FFF,  1},       // Greek extended. 0x1F00-0x1FFF
  67   *
  68   */
  69
  70   //
  71   // Symbol area
  72   //
  73   {(CHAR16)0x2FFF,  1},
  74   /*
  75    * Merge the blocks and replace them with the above entry as they fall to
  76    * the same category and they are all narrow glyph. This will reduce search
  77    * time and table size. The merge will omit the reserved code.
  78    *
  79    * Remove the above item if below is un-commented.
  80    *
  81   {(CHAR16)0x206F,  1},       // General punctuation. (See page7-154). 0x200-0x206F
  82   {(CHAR16)0x209F,  1},       // Superscripts and subscripts. 0x2070-0x209F
  83   {(CHAR16)0x20CF,  1},       // Currency symbols. 0x20A0-0x20CF
  84   {(CHAR16)0x20FF,  1},       // Combining diacritical marks for symbols. 0x20D0-0x20FF
  85   {(CHAR16)0x214F,  1},       // Letterlike sympbols. 0x2100-0x214F
  86   {(CHAR16)0x218F,  1},       // Number forms. 0x2150-0x218F
  87   {(CHAR16)0x21FF,  1},       // Arrows. 0x2190-0x21FF
  88   {(CHAR16)0x22FF,  1},       // Mathematical operators. 0x2200-0x22FF
  89   {(CHAR16)0x23FF,  1},       // Miscellaneous technical. 0x2300-0x23FF
  90   {(CHAR16)0x243F,  1},       // Control pictures. 0x2400-0x243F
  91   {(CHAR16)0x245F,  1},       // Optical character recognition. 0x2440-0x245F
  92   {(CHAR16)0x24FF,  1},       // Enclosed alphanumerics. 0x2460-0x24FF
  93   {(CHAR16)0x257F,  1},       // Box drawing. 0x2500-0x257F
  94   {(CHAR16)0x259F,  1},       // Block elements. 0x2580-0x259F
  95   {(CHAR16)0x25FF,  1},       // Geometric shapes. 0x25A0-0x25FF
  96   {(CHAR16)0x26FF,  1},       // Miscellaneous symbols. 0x2600-0x26FF
  97   {(CHAR16)0x27BF,  1},       // Dingbats. 0x2700-0x27BF
  98   {(CHAR16)0x2FFF,  0},       // Reserved. 0x27C0-0x2FFF
  99   *
 100   */
 101
 102   //
 103   // CJK phonetics and symbol area
 104   //
 105   {(CHAR16)0x33FF,  2},
 106   /*
 107    * Merge the blocks and replace them with the above entry as they fall to
 108    * the same category and they are all wide glyph. This will reduce search
 109    * time and table size. The merge will omit the reserved code.
 110    *
 111    * Remove the above item if below is un-commented.
 112    *
 113   {(CHAR16)0x303F,  2},       // CJK symbols and punctuation. 0x3000-0x303F
 114   {(CHAR16)0x309F,  2},       // Hiragana. 0x3040-0x309F
 115   {(CHAR16)0x30FF,  2},       // Katakana. 0x30A0-0x30FF
 116   {(CHAR16)0x312F,  2},       // Bopomofo. 0x3100-0x312F
 117   {(CHAR16)0x318F,  2},       // Hangul compatibility jamo. 0x3130-0x318F
 118   {(CHAR16)0x319F,  2},       // Kanbun. 0x3190-0x319F
 119   {(CHAR16)0x31FF,  0},       // Reserved. As Bopomofo extended in ver3.0. 0x31A0-0x31FF
 120   {(CHAR16)0x32FF,  2},       // Enclosed CJK letters and months. 0x3200-0x32FF
 121   {(CHAR16)0x33FF,  2},       // CJK compatibility. 0x3300-0x33FF
 122   *
 123   */
 124
 125   //
 126   // CJK ideograph area
 127   //
 128   {(CHAR16)0x9FFF,  2},
 129   /*
 130    * Merge the blocks and replace them with the above entry as they fall to
 131    * the same category and they are all wide glyph. This will reduce search
 132    * time and table size. The merge will omit the reserved code.
 133    *
 134    * Remove the above item if below is un-commented.
 135    *
 136   {(CHAR16)0x4DFF,  0},       // Reserved. 0x3400-0x4DBF as CJK unified ideographs
 137                       // extension A in ver3.0. 0x3400-0x4DFF
 138   {(CHAR16)0x9FFF,  2},       // CJK unified ideographs. 0x4E00-0x9FFF
 139   *
 140   */
 141
 142   //
 143   // Reserved
 144   //
 145   {(CHAR16)0xABFF,  0},       // Reserved. 0xA000-0xA490 as Yi syllables. 0xA490-0xA4D0
 146   // as Yi radicals in ver3.0. 0xA000-0xABFF
 147   //
 148   // Hangul syllables
 149   //
 150   {(CHAR16)0xD7FF,  2},
 151   /*
 152    * Merge the blocks and replace them with the above entry as they fall to
 153    * the same category and they are all wide glyph. This will reduce search
 154    * time and table size. The merge will omit the reserved code.
 155    *
 156    * Remove the above item if below is un-commented.
 157    *
 158   {(CHAR16)0xD7A3,  2},       // Hangul syllables. 0xAC00-0xD7A3
 159   {(CHAR16)0xD7FF,  0},       // Reserved. 0xD7A3-0xD7FF
 160   *
 161   */
 162
 163   //
 164   // Surrogates area
 165   //
 166   {(CHAR16)0xDFFF,  0},       // Surrogates, not used now. 0xD800-0xDFFF
 167
 168   //
 169   // Private use area
 170   //
 171   {(CHAR16)0xF8FF,  0},       // Private use area. 0xE000-0xF8FF
 172
 173   //
 174   // Compatibility area and specials
 175   //
 176   {(CHAR16)0xFAFF,  2},       // CJK compatibility ideographs. 0xF900-0xFAFF
 177   {(CHAR16)0xFB4F,  1},       // Alphabetic presentation forms. 0xFB00-0xFB4F
 178   {(CHAR16)0xFDFF,  1},       // Arabic presentation forms-A. 0xFB50-0xFDFF
 179   {(CHAR16)0xFE1F,  0},       // Reserved. As variation selectors in ver3.0. 0xFE00-0xFE1F
 180   {(CHAR16)0xFE2F,  1},       // Combining half marks. 0xFE20-0xFE2F
 181   {(CHAR16)0xFE4F,  2},       // CJK compatibility forms. 0xFE30-0xFE4F
 182   {(CHAR16)0xFE6F,  1},       // Small Form Variants. 0xFE50-0xFE6F
 183   {(CHAR16)0xFEFF,  1},       // Arabic presentation forms-B. 0xFE70-0xFEFF
 184   {(CHAR16)0xFFEF,  1},       // Half width and full width forms. 0xFF00-0xFFEF
 185   {(CHAR16)0xFFFF,  0},       // Speicials. 0xFFF0-0xFFFF
 186 };
 187
 188 /**
 189   Retrieves the width of a Unicode character.
 190
 191   This function computes and returns the width of the Unicode character specified
 192   by UnicodeChar.
 193
 194   @param  UnicodeChar   A Unicode character.
 195
 196   @retval 0             The width if UnicodeChar could not be determined.
 197   @retval 1             UnicodeChar is a narrow glyph.
 198   @retval 2             UnicodeChar is a wide glyph.
 199 **/
 200 UINTN
 201 EFIAPI
 202 GetGlyphWidth (
 203   IN CHAR16                         UnicodeChar
 204   )
 205 {
 206   UINTN                             Index;
 207   UINTN                             Low;
 208   UINTN                             High;
 209   CONST UNICODE_WIDTH_ENTRY         *Item;
 210
 211   Item  = NULL;
 212   Low   = 0;
 213   High  = (sizeof (mUnicodeWidthTable)) / (sizeof (UNICODE_WIDTH_ENTRY)) - 1;
 214
 215   while (Low <= High) {
 216     Index = (Low + High) >> 1;
 217     Item  = &(mUnicodeWidthTable[Index]);
 218     if (Index == 0) {
 219       if (UnicodeChar <= Item->WChar) {
 220         break;
 221       }
 222       return 0;
 223     }
 224
 225     if (UnicodeChar > Item->WChar) {
 226       Low = Index + 1;
 227     } else if (UnicodeChar <= mUnicodeWidthTable[Index - 1].WChar) {
 228       High = Index - 1;
 229     } else {
 230       //
 231       // Index - 1 < UnicodeChar <= Index. Found
 232       //
 233       break;
 234     }
 235   }
 236
 237   if (Low <= High) {
 238     return Item->Width;
 239   }
 240
 241   return 0;
 242 }
 243
 244 /**
 245   Computes the display length of a Null-terminated Unicode String.
 246
 247   This function computes and returns the display length of the Null-terminated Unicode
 248   string specified by String.  If String is NULL then 0 is returned. If any of the widths
 249   of the Unicode characters in String can not be determined, then 0 is returned. The display
 250   width of String can be computed by summing the display widths of each Unicode character
 251   in String.  Unicode characters that are narrow glyphs have a width of 1, and Unicode
 252   characters that are width glyphs have a width of 2.
 253   If String is not aligned on a 16-bit boundary, then ASSERT().
 254
 255   @param  String   A pointer to a Null-terminated Unicode string.
 256
 257   @return          The display length of the Null-terminated Unicode string specified by String.
 258 **/
 259 UINTN
 260 EFIAPI
 261 UnicodeStringDisplayLength (
 262   IN CONST CHAR16                   *String
 263   )
 264 {
 265   UINTN                             Length;
 266   UINTN                             Width;
 267
 268   if (String == NULL) {
 269     return 0;
 270   }
 271
 272   Length = 0;
 273   while (*String != 0) {
 274     Width = GetGlyphWidth (*String);
 275     if (Width == 0) {
 276       return 0;
 277     }
 278
 279     Length += Width;
 280     String++;
 281   }
 282
 283   return Length;
 284 }