31  * Joerg Wunsch <joerg@freebsd.org> wrote the original support for 8-bit
117 		*code = "Unicode text, UTF-8 (with BOM)";  in file_encoding()
118 		*code_mime = "utf-8";  in file_encoding()
121 		*code = "Unicode text, UTF-8";  in file_encoding()
122 		*code_mime = "utf-8";  in file_encoding()
148 		*code_mime = "unknown-8bit";  in file_encoding()
226  * from the ISO-8859 8-bit extension, characters 0xA0 ... 0xFF.
287  * Decide whether some text looks like UTF-8. Returns:
289  *     -1: invalid UTF-8
292  *      2: definitely UTF-8 text (valid high-bit set bytes)
300 #define	XX 0xF1 // invalid: size 1  macro
313 // first is information about the first byte in a UTF-8 sequence.
315     //   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
324     //   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
325     XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, // 0x80-0x8F
326     XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, // 0x90-0x9F
327     XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, // 0xA0-0xAF
328     XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, // 0xB0-0xBF
329     XX, XX, S1, S1, S1, S1, S1, S1, S1, S1, S1, S1, S1, S1, S1, S1, // 0xC0-0xCF
332     S5, S6, S6, S6, S7, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, XX, // 0xF0-0xFF
335 // acceptRange gives the range of valid values for the second byte in a UTF-8
364 			 * Even if the whole file is valid UTF-8 sequences,  in file_looks_utf8()
375 		} else {			   /* 11xxxxxx begins UTF-8 */  in file_looks_utf8()
380 			if (x == XX)  in file_looks_utf8()
392 			} else if ((buf[i] & 0x04) == 0) {	/* 111110xx */  in file_looks_utf8()
426  * Decide whether some text looks like UTF-8 with BOM. If there is no
446 		case '8':  in looks_utf7()
490 			    bf[i + 1] | (CAST(file_unichar_t, bf[i]) << 8));  in looks_ucs16()
493 			    bf[i] | (CAST(file_unichar_t, bf[i + 1]) << 8));  in looks_ucs16()
548 			    | (CAST(file_unichar_t, bf[i + 2]) << 8)  in looks_ucs32()
553 			    | (CAST(file_unichar_t, bf[i + 1]) << 8)   in looks_ucs32()
572  * This table maps each EBCDIC character to an (8-bit extended) ASCII
595  16,  17,  18,  19, 157, 133,   8, 135,  24,  25, 146, 143,  28,  29,  30,  31,
609 '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 250, 251, 252, 253, 254, 255