[mirror_edk2.git] / MdeModulePkg / Universal / Console / TerminalDxe / Vtutf8.c

/** @file\r
  Implementation of translation upon VT-UTF8.\r
\r
Copyright (c) 2006 - 2010, Intel Corporation. All rights reserved.<BR>\r
This program and the accompanying materials\r
are licensed and made available under the terms and conditions of the BSD License\r
which accompanies this distribution.  The full text of the license may be found at\r
http://opensource.org/licenses/bsd-license.php\r
\r
THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,\r
WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.\r
\r
**/\r
\r
#include "Terminal.h"\r
\r
/**\r
  Translate all VT-UTF8 characters in the Raw FIFI into unicode characters,\r
  and insert them into Unicode FIFO.\r
\r
  @param TerminalDevice          The terminal device.\r
\r
**/\r
VOID\r
VTUTF8RawDataToUnicode (\r
  IN  TERMINAL_DEV    *TerminalDevice\r
  )\r
{\r
  UTF8_CHAR Utf8Char;\r
  UINT8     ValidBytes;\r
  UINT16    UnicodeChar;\r
\r
  ValidBytes = 0;\r
  //\r
  // pop the raw data out from the raw fifo,\r
  // and translate it into unicode, then push\r
  // the unicode into unicode fifo, until the raw fifo is empty.\r
  //\r
  while (!IsRawFiFoEmpty (TerminalDevice) && !IsUnicodeFiFoFull (TerminalDevice)) {\r
\r
    GetOneValidUtf8Char (TerminalDevice, &Utf8Char, &ValidBytes);\r
\r
    if (ValidBytes < 1 || ValidBytes > 3) {\r
      continue;\r
    }\r
\r
    Utf8ToUnicode (Utf8Char, ValidBytes, (CHAR16 *) &UnicodeChar);\r
\r
    UnicodeFiFoInsertOneKey (TerminalDevice, UnicodeChar);\r
  }\r
}\r
\r
/**\r
  Get one valid VT-UTF8 characters set from Raw Data FIFO.\r
\r
  @param  Utf8Device          The terminal device.\r
  @param  Utf8Char            Returned valid VT-UTF8 characters set.\r
  @param  ValidBytes          The count of returned VT-VTF8 characters.\r
                              If ValidBytes is zero, no valid VT-UTF8 returned.\r
\r
**/\r
VOID\r
GetOneValidUtf8Char (\r
  IN  TERMINAL_DEV      *Utf8Device,\r
  OUT UTF8_CHAR         *Utf8Char,\r
  OUT UINT8             *ValidBytes\r
  )\r
{\r
  UINT8   Temp;\r
  UINT8   Index;\r
  BOOLEAN FetchFlag;\r
\r
  Temp      = 0;\r
  Index     = 0;\r
  FetchFlag = TRUE;\r
\r
  //\r
  // if no valid Utf8 char is found in the RawFiFo,\r
  // then *ValidBytes will be zero.\r
  //\r
  *ValidBytes = 0;\r
\r
  while (!IsRawFiFoEmpty (Utf8Device)) {\r
\r
    RawFiFoRemoveOneKey (Utf8Device, &Temp);\r
\r
    switch (*ValidBytes) {\r
\r
    case 0:\r
      if ((Temp & 0x80) == 0) {\r
        //\r
        // one-byte utf8 char\r
        //\r
        *ValidBytes       = 1;\r
\r
        Utf8Char->Utf8_1  = Temp;\r
\r
        FetchFlag         = FALSE;\r
\r
      } else if ((Temp & 0xe0) == 0xc0) {\r
        //\r
        // two-byte utf8 char\r
        //\r
        *ValidBytes         = 2;\r
\r
        Utf8Char->Utf8_2[1] = Temp;\r
\r
      } else if ((Temp & 0xf0) == 0xe0) {\r
        //\r
        // three-byte utf8 char\r
        //\r
        *ValidBytes         = 3;\r
\r
        Utf8Char->Utf8_3[2] = Temp;\r
\r
        Index++;\r
\r
      } else {\r
        //\r
        // reset *ValidBytes to zero, let valid utf8 char search restart\r
        //\r
        *ValidBytes = 0;\r
      }\r
\r
      break;\r
\r
    case 2:\r
      //\r
      // two-byte utf8 char go on\r
      //\r
      if ((Temp & 0xc0) == 0x80) {\r
\r
        Utf8Char->Utf8_2[0] = Temp;\r
\r
        FetchFlag           = FALSE;\r
\r
      } else {\r
\r
        *ValidBytes = 0;\r
      }\r
      break;\r
\r
    case 3:\r
      //\r
      // three-byte utf8 char go on\r
      //\r
      if ((Temp & 0xc0) == 0x80) {\r
        if (Index == 1) {\r
          Utf8Char->Utf8_3[1] = Temp;\r
          Index++;\r
        } else {\r
          Utf8Char->Utf8_3[0] = Temp;\r
          FetchFlag = FALSE;\r
        }\r
      } else {\r
        //\r
        // reset *ValidBytes and Index to zero, let valid utf8 char search restart\r
        //\r
        *ValidBytes = 0;\r
        Index       = 0;\r
      }\r
      break;\r
\r
    default:\r
      break;\r
    }\r
\r
    if (!FetchFlag) {\r
      break;\r
    }\r
  }\r
\r
  return ;\r
}\r
\r
/**\r
  Translate VT-UTF8 characters into one Unicode character.\r
\r
  UTF8 Encoding Table\r
  Bits per Character | Unicode Character Range | Unicode Binary  Encoding |	UTF8 Binary Encoding\r
        0-7	         |     0x0000 - 0x007F	   |     00000000 0xxxxxxx	  |   0xxxxxxx\r
        8-11 	       |     0x0080 - 0x07FF	   |     00000xxx xxxxxxxx 	  |   110xxxxx 10xxxxxx\r
       12-16	       |     0x0800 - 0xFFFF	   |     xxxxxxxx xxxxxxxx	  |   1110xxxx 10xxxxxx 10xxxxxx\r
\r
\r
  @param  Utf8Char         VT-UTF8 character set needs translating.\r
  @param  ValidBytes       The count of valid VT-UTF8 characters.\r
  @param  UnicodeChar      Returned unicode character.\r
\r
**/\r
VOID\r
Utf8ToUnicode (\r
  IN  UTF8_CHAR       Utf8Char,\r
  IN  UINT8           ValidBytes,\r
  OUT CHAR16          *UnicodeChar\r
  )\r
{\r
  UINT8 UnicodeByte0;\r
  UINT8 UnicodeByte1;\r
  UINT8 Byte0;\r
  UINT8 Byte1;\r
  UINT8 Byte2;\r
\r
  *UnicodeChar = 0;\r
\r
  //\r
  // translate utf8 code to unicode, in terminal standard,\r
  // up to 3 bytes utf8 code is supported.\r
  //\r
  switch (ValidBytes) {\r
  case 1:\r
    //\r
    // one-byte utf8 code\r
    //\r
    *UnicodeChar = (UINT16) Utf8Char.Utf8_1;\r
    break;\r
\r
  case 2:\r
    //\r
    // two-byte utf8 code\r
    //\r
    Byte0         = Utf8Char.Utf8_2[0];\r
    Byte1         = Utf8Char.Utf8_2[1];\r
\r
    UnicodeByte0  = (UINT8) ((Byte1 << 6) | (Byte0 & 0x3f));\r
    UnicodeByte1  = (UINT8) ((Byte1 >> 2) & 0x07);\r
    *UnicodeChar  = (UINT16) (UnicodeByte0 | (UnicodeByte1 << 8));\r
    break;\r
\r
  case 3:\r
    //\r
    // three-byte utf8 code\r
    //\r
    Byte0         = Utf8Char.Utf8_3[0];\r
    Byte1         = Utf8Char.Utf8_3[1];\r
    Byte2         = Utf8Char.Utf8_3[2];\r
\r
    UnicodeByte0  = (UINT8) ((Byte1 << 6) | (Byte0 & 0x3f));\r
    UnicodeByte1  = (UINT8) ((Byte2 << 4) | ((Byte1 >> 2) & 0x0f));\r
    *UnicodeChar  = (UINT16) (UnicodeByte0 | (UnicodeByte1 << 8));\r
\r
  default:\r
    break;\r
  }\r
\r
  return ;\r
}\r
\r
/**\r
  Translate one Unicode character into VT-UTF8 characters.\r
\r
  UTF8 Encoding Table\r
  Bits per Character | Unicode Character Range | Unicode Binary  Encoding |	UTF8 Binary Encoding\r
        0-7	         |     0x0000 - 0x007F	   |     00000000 0xxxxxxx	  |   0xxxxxxx\r
        8-11 	       |     0x0080 - 0x07FF	   |     00000xxx xxxxxxxx 	  |   110xxxxx 10xxxxxx\r
       12-16	       |     0x0800 - 0xFFFF	   |     xxxxxxxx xxxxxxxx	  |   1110xxxx 10xxxxxx 10xxxxxx\r
\r
\r
  @param  Unicode          Unicode character need translating.\r
  @param  Utf8Char         Return VT-UTF8 character set.\r
  @param  ValidBytes       The count of valid VT-UTF8 characters. If\r
                           ValidBytes is zero, no valid VT-UTF8 returned.\r
\r
**/\r
VOID\r
UnicodeToUtf8 (\r
  IN  CHAR16      Unicode,\r
  OUT UTF8_CHAR   *Utf8Char,\r
  OUT UINT8       *ValidBytes\r
  )\r
{\r
  UINT8 UnicodeByte0;\r
  UINT8 UnicodeByte1;\r
  //\r
  // translate unicode to utf8 code\r
  //\r
  UnicodeByte0  = (UINT8) Unicode;\r
  UnicodeByte1  = (UINT8) (Unicode >> 8);\r
\r
  if (Unicode < 0x0080) {\r
\r
    Utf8Char->Utf8_1  = (UINT8) (UnicodeByte0 & 0x7f);\r
    *ValidBytes       = 1;\r
\r
  } else if (Unicode < 0x0800) {\r
    //\r
    // byte sequence: high -> low\r
    //                Utf8_2[0], Utf8_2[1]\r
    //\r
    Utf8Char->Utf8_2[1] = (UINT8) ((UnicodeByte0 & 0x3f) + 0x80);\r
    Utf8Char->Utf8_2[0] = (UINT8) ((((UnicodeByte1 << 2) + (UnicodeByte0 >> 6)) & 0x1f) + 0xc0);\r
\r
    *ValidBytes         = 2;\r
\r
  } else {\r
    //\r
    // byte sequence: high -> low\r
    //                Utf8_3[0], Utf8_3[1], Utf8_3[2]\r
    //\r
    Utf8Char->Utf8_3[2] = (UINT8) ((UnicodeByte0 & 0x3f) + 0x80);\r
    Utf8Char->Utf8_3[1] = (UINT8) ((((UnicodeByte1 << 2) + (UnicodeByte0 >> 6)) & 0x3f) + 0x80);\r
    Utf8Char->Utf8_3[0] = (UINT8) (((UnicodeByte1 >> 4) & 0x0f) + 0xe0);\r
\r
    *ValidBytes         = 3;\r
  }\r
}\r
\r
\r
/**\r
  Check if input string is valid VT-UTF8 string.\r
\r
  @param  TerminalDevice          The terminal device.\r
  @param  WString                 The input string.\r
\r
  @retval EFI_SUCCESS             If all input characters are valid.\r
\r
**/\r
EFI_STATUS\r
VTUTF8TestString (\r
  IN  TERMINAL_DEV    *TerminalDevice,\r
  IN  CHAR16          *WString\r
  )\r
{\r
  //\r
  // to utf8, all kind of characters are supported.\r
  //\r
  return EFI_SUCCESS;\r
}\r
Commit	Line	Data
4bc6ad39 RN	1	/** @file\r
	2	Implementation of translation upon VT-UTF8.\r
	3	\r
	4	Copyright (c) 2006 - 2010, Intel Corporation. All rights reserved.<BR>\r
	5	This program and the accompanying materials\r
	6	are licensed and made available under the terms and conditions of the BSD License\r
	7	which accompanies this distribution. The full text of the license may be found at\r
	8	http://opensource.org/licenses/bsd-license.php\r
	9	\r
	10	THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,\r
	11	WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.\r
	12	\r
	13	**/\r
	14	\r
	15	#include "Terminal.h"\r
	16	\r
	17	/**\r
	18	Translate all VT-UTF8 characters in the Raw FIFI into unicode characters,\r
	19	and insert them into Unicode FIFO.\r
	20	\r
	21	@param TerminalDevice The terminal device.\r
	22	\r
	23	**/\r
	24	VOID\r
	25	VTUTF8RawDataToUnicode (\r
	26	IN TERMINAL_DEV *TerminalDevice\r
	27	)\r
	28	{\r
	29	UTF8_CHAR Utf8Char;\r
	30	UINT8 ValidBytes;\r
	31	UINT16 UnicodeChar;\r
	32	\r
	33	ValidBytes = 0;\r
	34	//\r
	35	// pop the raw data out from the raw fifo,\r
	36	// and translate it into unicode, then push\r
	37	// the unicode into unicode fifo, until the raw fifo is empty.\r
	38	//\r
	39	while (!IsRawFiFoEmpty (TerminalDevice) && !IsUnicodeFiFoFull (TerminalDevice)) {\r
	40	\r
	41	GetOneValidUtf8Char (TerminalDevice, &Utf8Char, &ValidBytes);\r
	42	\r
	43	if (ValidBytes < 1 \|\| ValidBytes > 3) {\r
	44	continue;\r
	45	}\r
	46	\r
	47	Utf8ToUnicode (Utf8Char, ValidBytes, (CHAR16 *) &UnicodeChar);\r
	48	\r
	49	UnicodeFiFoInsertOneKey (TerminalDevice, UnicodeChar);\r
	50	}\r
	51	}\r
	52	\r
	53	/**\r
	54	Get one valid VT-UTF8 characters set from Raw Data FIFO.\r
	55	\r
	56	@param Utf8Device The terminal device.\r
	57	@param Utf8Char Returned valid VT-UTF8 characters set.\r
	58	@param ValidBytes The count of returned VT-VTF8 characters.\r
	59	If ValidBytes is zero, no valid VT-UTF8 returned.\r
	60	\r
	61	**/\r
	62	VOID\r
	63	GetOneValidUtf8Char (\r
	64	IN TERMINAL_DEV *Utf8Device,\r
65	OUT UTF8_CHAR *Utf8Char,\r
66	OUT UINT8 *ValidBytes\r
67	)\r
68	{\r
69	UINT8 Temp;\r
70	UINT8 Index;\r
71	BOOLEAN FetchFlag;\r
72	\r
73	Temp = 0;\r
74	Index = 0;\r
75	FetchFlag = TRUE;\r
76	\r
77	//\r
78	// if no valid Utf8 char is found in the RawFiFo,\r
79	// then *ValidBytes will be zero.\r
80	//\r
81	*ValidBytes = 0;\r
82	\r
83	while (!IsRawFiFoEmpty (Utf8Device)) {\r
84	\r
85	RawFiFoRemoveOneKey (Utf8Device, &Temp);\r
86	\r
87	switch (*ValidBytes) {\r
88	\r
89	case 0:\r
90	if ((Temp & 0x80) == 0) {\r
91	//\r
92	// one-byte utf8 char\r
93	//\r
94	*ValidBytes = 1;\r
95	\r
96	Utf8Char->Utf8_1 = Temp;\r
97	\r
98	FetchFlag = FALSE;\r
99	\r
100	} else if ((Temp & 0xe0) == 0xc0) {\r
101	//\r
102	// two-byte utf8 char\r
103	//\r
104	*ValidBytes = 2;\r
105	\r
106	Utf8Char->Utf8_2[1] = Temp;\r
107	\r
108	} else if ((Temp & 0xf0) == 0xe0) {\r
109	//\r
110	// three-byte utf8 char\r
111	//\r
112	*ValidBytes = 3;\r
113	\r
114	Utf8Char->Utf8_3[2] = Temp;\r
115	\r
116	Index++;\r
117	\r
118	} else {\r
119	//\r
120	// reset *ValidBytes to zero, let valid utf8 char search restart\r
121	//\r
122	*ValidBytes = 0;\r
123	}\r
124	\r
125	break;\r
126	\r
127	case 2:\r
128	//\r
129	// two-byte utf8 char go on\r
130	//\r
131	if ((Temp & 0xc0) == 0x80) {\r
132	\r
133	Utf8Char->Utf8_2[0] = Temp;\r
134	\r
135	FetchFlag = FALSE;\r
136	\r
137	} else {\r
138	\r
139	*ValidBytes = 0;\r
140	}\r
141	break;\r
142	\r
143	case 3:\r
144	//\r
145	// three-byte utf8 char go on\r
146	//\r
147	if ((Temp & 0xc0) == 0x80) {\r
148	if (Index == 1) {\r
149	Utf8Char->Utf8_3[1] = Temp;\r
150	Index++;\r
151	} else {\r
152	Utf8Char->Utf8_3[0] = Temp;\r
153	FetchFlag = FALSE;\r
154	}\r
155	} else {\r
156	//\r
157	// reset *ValidBytes and Index to zero, let valid utf8 char search restart\r
158	//\r
159	*ValidBytes = 0;\r
160	Index = 0;\r
161	}\r
162	break;\r
163	\r
164	default:\r
165	break;\r
166	}\r
167	\r
168	if (!FetchFlag) {\r
169	break;\r
170	}\r
171	}\r
172	\r
173	return ;\r
174	}\r
175	\r
176	/**\r
177	Translate VT-UTF8 characters into one Unicode character.\r
178	\r
179	UTF8 Encoding Table\r
180	Bits per Character \| Unicode Character Range \| Unicode Binary Encoding \| UTF8 Binary Encoding\r
181	0-7 \| 0x0000 - 0x007F \| 00000000 0xxxxxxx \| 0xxxxxxx\r
182	8-11 \| 0x0080 - 0x07FF \| 00000xxx xxxxxxxx \| 110xxxxx 10xxxxxx\r
183	12-16 \| 0x0800 - 0xFFFF \| xxxxxxxx xxxxxxxx \| 1110xxxx 10xxxxxx 10xxxxxx\r
184	\r
185	\r
186	@param Utf8Char VT-UTF8 character set needs translating.\r
187	@param ValidBytes The count of valid VT-UTF8 characters.\r
188	@param UnicodeChar Returned unicode character.\r
189	\r
190	**/\r
191	VOID\r
192	Utf8ToUnicode (\r
193	IN UTF8_CHAR Utf8Char,\r
194	IN UINT8 ValidBytes,\r
195	OUT CHAR16 *UnicodeChar\r
196	)\r
197	{\r
198	UINT8 UnicodeByte0;\r
199	UINT8 UnicodeByte1;\r
200	UINT8 Byte0;\r
201	UINT8 Byte1;\r
202	UINT8 Byte2;\r
203	\r
204	*UnicodeChar = 0;\r
205	\r
206	//\r
207	// translate utf8 code to unicode, in terminal standard,\r
208	// up to 3 bytes utf8 code is supported.\r
209	//\r
210	switch (ValidBytes) {\r
211	case 1:\r
212	//\r
213	// one-byte utf8 code\r
214	//\r
215	*UnicodeChar = (UINT16) Utf8Char.Utf8_1;\r
216	break;\r
217	\r
218	case 2:\r
219	//\r
220	// two-byte utf8 code\r
221	//\r
222	Byte0 = Utf8Char.Utf8_2[0];\r
223	Byte1 = Utf8Char.Utf8_2[1];\r
224	\r
225	UnicodeByte0 = (UINT8) ((Byte1 << 6) \| (Byte0 & 0x3f));\r
226	UnicodeByte1 = (UINT8) ((Byte1 >> 2) & 0x07);\r
227	*UnicodeChar = (UINT16) (UnicodeByte0 \| (UnicodeByte1 << 8));\r
228	break;\r
229	\r
230	case 3:\r
231	//\r
232	// three-byte utf8 code\r
233	//\r
234	Byte0 = Utf8Char.Utf8_3[0];\r
235	Byte1 = Utf8Char.Utf8_3[1];\r
236	Byte2 = Utf8Char.Utf8_3[2];\r
237	\r
238	UnicodeByte0 = (UINT8) ((Byte1 << 6) \| (Byte0 & 0x3f));\r
239	UnicodeByte1 = (UINT8) ((Byte2 << 4) \| ((Byte1 >> 2) & 0x0f));\r
240	*UnicodeChar = (UINT16) (UnicodeByte0 \| (UnicodeByte1 << 8));\r
241	\r
242	default:\r
243	break;\r
244	}\r
245	\r
246	return ;\r
247	}\r
248	\r
249	/**\r
250	Translate one Unicode character into VT-UTF8 characters.\r
251	\r
252	UTF8 Encoding Table\r
253	Bits per Character \| Unicode Character Range \| Unicode Binary Encoding \| UTF8 Binary Encoding\r
254	0-7 \| 0x0000 - 0x007F \| 00000000 0xxxxxxx \| 0xxxxxxx\r
255	8-11 \| 0x0080 - 0x07FF \| 00000xxx xxxxxxxx \| 110xxxxx 10xxxxxx\r
256	12-16 \| 0x0800 - 0xFFFF \| xxxxxxxx xxxxxxxx \| 1110xxxx 10xxxxxx 10xxxxxx\r
257	\r
258	\r
259	@param Unicode Unicode character need translating.\r
260	@param Utf8Char Return VT-UTF8 character set.\r
261	@param ValidBytes The count of valid VT-UTF8 characters. If\r
262	ValidBytes is zero, no valid VT-UTF8 returned.\r
263	\r
264	**/\r
265	VOID\r
266	UnicodeToUtf8 (\r
267	IN CHAR16 Unicode,\r
268	OUT UTF8_CHAR *Utf8Char,\r
269	OUT UINT8 *ValidBytes\r
270	)\r
271	{\r
272	UINT8 UnicodeByte0;\r
273	UINT8 UnicodeByte1;\r
274	//\r
275	// translate unicode to utf8 code\r
276	//\r
277	UnicodeByte0 = (UINT8) Unicode;\r
278	UnicodeByte1 = (UINT8) (Unicode >> 8);\r
279	\r
280	if (Unicode < 0x0080) {\r
281	\r
282	Utf8Char->Utf8_1 = (UINT8) (UnicodeByte0 & 0x7f);\r
283	*ValidBytes = 1;\r
284	\r
285	} else if (Unicode < 0x0800) {\r
286	//\r
287	// byte sequence: high -> low\r
288	// Utf8_2[0], Utf8_2[1]\r
289	//\r
290	Utf8Char->Utf8_2[1] = (UINT8) ((UnicodeByte0 & 0x3f) + 0x80);\r
291	Utf8Char->Utf8_2[0] = (UINT8) ((((UnicodeByte1 << 2) + (UnicodeByte0 >> 6)) & 0x1f) + 0xc0);\r
292	\r
293	*ValidBytes = 2;\r
294	\r
295	} else {\r
296	//\r
297	// byte sequence: high -> low\r
298	// Utf8_3[0], Utf8_3[1], Utf8_3[2]\r
299	//\r
300	Utf8Char->Utf8_3[2] = (UINT8) ((UnicodeByte0 & 0x3f) + 0x80);\r
301	Utf8Char->Utf8_3[1] = (UINT8) ((((UnicodeByte1 << 2) + (UnicodeByte0 >> 6)) & 0x3f) + 0x80);\r
302	Utf8Char->Utf8_3[0] = (UINT8) (((UnicodeByte1 >> 4) & 0x0f) + 0xe0);\r
303	\r
304	*ValidBytes = 3;\r
305	}\r
306	}\r
307	\r
308	\r
309	/**\r
310	Check if input string is valid VT-UTF8 string.\r
311	\r
312	@param TerminalDevice The terminal device.\r
313	@param WString The input string.\r
314	\r
315	@retval EFI_SUCCESS If all input characters are valid.\r
316	\r
317	**/\r
318	EFI_STATUS\r
319	VTUTF8TestString (\r
320	IN TERMINAL_DEV *TerminalDevice,\r
321	IN CHAR16 *WString\r
322	)\r
323	{\r
324	//\r
325	// to utf8, all kind of characters are supported.\r
326	//\r
327	return EFI_SUCCESS;\r
328	}\r