X-Git-Url: https://git.stderr.nl/gitweb?a=blobdiff_plain;f=interpreters%2Ffrotz%2Ftext.c;fp=interpreters%2Ffrotz%2Ftext.c;h=9cccc2c1cb0be5813b07872fa80095f8eabbb50a;hb=75009f8f40bbb580194e1722db76f4644bf18641;hp=8145cfea29d6307c3969d0eb246c741e540eeaff;hpb=89081782541e85e079f64839ffb26b4e74273eb7;p=projects%2Fchimara%2Fchimara.git diff --git a/interpreters/frotz/text.c b/interpreters/frotz/text.c index 8145cfe..9cccc2c 100644 --- a/interpreters/frotz/text.c +++ b/interpreters/frotz/text.c @@ -25,9 +25,11 @@ enum string_type { }; extern zword object_name (zword); +extern zword get_window_font (zword); -static zchar decoded[10]; -static zword encoded[3]; +zchar* decoded; +zchar* encoded; +static int resolution; /* * According to Matteo De Luigi , @@ -35,21 +37,36 @@ static zword encoded[3]; * Sat Apr 21, 2001 */ static zchar zscii_to_latin1[] = { - 0xe4, 0xf6, 0xfc, 0xc4, 0xd6, 0xdc, 0xdf, 0xbb, - 0xab, 0xeb, 0xef, 0xff, 0xcb, 0xcf, 0xe1, 0xe9, - 0xed, 0xf3, 0xfa, 0xfd, 0xc1, 0xc9, 0xcd, 0xd3, - 0xda, 0xdd, 0xe0, 0xe8, 0xec, 0xf2, 0xf9, 0xc0, - 0xc8, 0xcc, 0xd2, 0xd9, 0xe2, 0xea, 0xee, 0xf4, - 0xfb, 0xc2, 0xca, 0xce, 0xd4, 0xdb, 0xe5, 0xc5, - 0xf8, 0xd8, 0xe3, 0xf1, 0xf5, 0xc3, 0xd1, 0xd5, - 0xe6, 0xc6, 0xe7, 0xc7, 0xfe, 0xf0, 0xde, 0xd0, - 0xa3, 0x00, 0x00, 0xa1, 0xbf + 0x0e4, 0x0f6, 0x0fc, 0x0c4, 0x0d6, 0x0dc, 0x0df, 0x0bb, + 0x0ab, 0x0eb, 0x0ef, 0x0ff, 0x0cb, 0x0cf, 0x0e1, 0x0e9, + 0x0ed, 0x0f3, 0x0fa, 0x0fd, 0x0c1, 0x0c9, 0x0cd, 0x0d3, + 0x0da, 0x0dd, 0x0e0, 0x0e8, 0x0ec, 0x0f2, 0x0f9, 0x0c0, + 0x0c8, 0x0cc, 0x0d2, 0x0d9, 0x0e2, 0x0ea, 0x0ee, 0x0f4, + 0x0fb, 0x0c2, 0x0ca, 0x0ce, 0x0d4, 0x0db, 0x0e5, 0x0c5, + 0x0f8, 0x0d8, 0x0e3, 0x0f1, 0x0f5, 0x0c3, 0x0d1, 0x0d5, + 0x0e6, 0x0c6, 0x0e7, 0x0c7, 0x0fe, 0x0f0, 0x0de, 0x0d0, + 0x0a3, 0x153, 0x152, 0x0a1, 0x0bf }; +/* + * init_text + * + * Initialize text variables. + * + */ + +void init_text (void) +{ + decoded = NULL; + encoded = NULL; + + resolution = 0; +} + /* * translate_from_zscii * - * Map a ZSCII character onto the ISO Latin-1 alphabet. + * Map a ZSCII character into Unicode. * */ @@ -78,7 +95,10 @@ zchar translate_from_zscii (zbyte c) LOW_WORD (addr, unicode) - return (unicode < 0x100) ? (zchar) unicode : '?'; + if (unicode < 0x20) + return '?'; + + return unicode; } else return '?'; @@ -86,36 +106,26 @@ zchar translate_from_zscii (zbyte c) if (c <= 0xdf) { - if (c == 0xdc || c == 0xdd) /* Oe and oe ligatures */ - return '?'; /* are not ISO-Latin 1 */ - return zscii_to_latin1[c - 0x9b]; } else return '?'; } - return c; + return (zchar) c; }/* translate_from_zscii */ /* - * translate_to_zscii + * unicode_to_zscii * - * Map an ISO Latin-1 character onto the ZSCII alphabet. + * Convert a Unicode character to ZSCII, returning 0 on failure. * */ -zbyte translate_to_zscii (zchar c) +zbyte unicode_to_zscii (zchar c) { int i; - if (c == ZC_SINGLE_CLICK) - return 0xfe; - if (c == ZC_DOUBLE_CLICK) - return 0xfd; - if (c == ZC_MENU_CLICK) - return 0xfc; - if (c >= ZC_LATIN1_MIN) { if (hx_unicode_table != 0) { /* game has its own Unicode table */ @@ -137,7 +147,7 @@ zbyte translate_to_zscii (zchar c) } - return '?'; + return 0; } else { /* game uses standard set */ @@ -145,16 +155,39 @@ zbyte translate_to_zscii (zchar c) if (c == zscii_to_latin1[i - 0x9b]) return (zbyte) i; - return '?'; + return 0; } } - if (c == 0) /* Safety thing from David Kinder */ - c = '?'; /* regarding his Unicode patches */ - /* Sept 15, 2002 */ + return (zbyte) c; - return c; +}/* unicode_to_zscii */ + +/* + * translate_to_zscii + * + * Map a Unicode character onto the ZSCII alphabet. + * + */ + +zbyte translate_to_zscii (zchar c) +{ + + if (c == ZC_SINGLE_CLICK) + return 0xfe; + if (c == ZC_DOUBLE_CLICK) + return 0xfd; + if (c == ZC_MENU_CLICK) + return 0xfc; + if (c == 0) + return 0; + + c = unicode_to_zscii (c); + if (c == 0) + c = '?'; + + return (zbyte) c; }/* translate_to_zscii */ @@ -167,6 +200,8 @@ zbyte translate_to_zscii (zchar c) static zchar alphabet (int set, int index) { + if (h_version > V1 && set == 2 && index == 1) + return 0x0D; /* always newline */ if (h_alphabet != 0) { /* game uses its own alphabet */ @@ -190,6 +225,66 @@ static zchar alphabet (int set, int index) }/* alphabet */ +/* + * find_resolution + * + * Find the number of bytes used for dictionary resolution. + * + */ + +static void find_resolution (void) +{ + zword dct = h_dictionary; + zword entry_count; + zbyte sep_count; + zbyte entry_len; + + LOW_BYTE (dct, sep_count) + dct += 1 + sep_count; /* skip word separators */ + LOW_BYTE (dct, entry_len) + dct += 1; /* skip entry length */ + LOW_WORD (dct, entry_count) + dct += 2; /* get number of entries */ + + if (h_version < V9) { + + resolution = (h_version <= V3) ? 2 : 3; + + } else { + + zword addr = dct; + zword code; + + if (entry_count == 0) { + + runtime_error (ERR_DICT_LEN); + + } + + /* check the first word in the dictionary */ + + do { + + LOW_WORD (addr, code) + addr += 2; + + } while (!(code & 0x8000) && (addr - dct < entry_len + 1)); + + resolution = (addr - dct) / 2; + + } + + if (2 * resolution > entry_len) { + + runtime_error (ERR_DICT_LEN); + + } + + decoded = (zchar *)malloc (sizeof (zchar) * (3 * resolution) + 1); + encoded = (zchar *)malloc (sizeof (zchar) * resolution); + +}/* find_resolution */ + /* * load_string * @@ -199,9 +294,10 @@ static zchar alphabet (int set, int index) static void load_string (zword addr, zword length) { - int resolution = (h_version <= V3) ? 2 : 3; int i = 0; + if (resolution == 0) find_resolution(); + while (i < 3 * resolution) if (i < length) { @@ -223,29 +319,34 @@ static void load_string (zword addr, zword length) * Encode the Unicode text in the global "decoded" string then write * the result to the global "encoded" array. (This is used to look up * words in the dictionary.) Up to V3 the vocabulary resolution is - * two, since V4 it is three words. Because each word contains three - * Z-characters, that makes six or nine Z-characters respectively. - * Longer words are chopped to the proper size, shorter words are are - * padded out with 5's. For word completion we pad with 0s and 31s, - * the minimum and maximum Z-characters. + * two, from V4 it is three, and from V9 it is any number of words. + * Because each word contains three Z-characters, that makes six or + * nine Z-characters respectively. Longer words are chopped to the + * proper size, shorter words are are padded out with 5's. For word + * completion we pad with 0s and 31s, the minimum and maximum + * Z-characters. * */ static void encode_text (int padding) { - static zchar again[] = { 'a', 'g', 'a', 'i', 'n', 0 }; - static zchar examine[] = { 'e', 'x', 'a', 'm', 'i', 'n', 'e', 0 }; - static zchar wait[] = { 'w', 'a', 'i', 't', 0 }; + static zchar again[] = { 'a', 'g', 'a', 'i', 'n', 0, 0, 0, 0 }; + static zchar examine[] = { 'e', 'x', 'a', 'm', 'i', 'n', 'e', 0, 0 }; + static zchar wait[] = { 'w', 'a', 'i', 't', 0, 0, 0, 0, 0 }; - zbyte zchars[12]; - const zchar *ptr = decoded; + zbyte *zchars; + const zchar *ptr; zchar c; - int resolution = (h_version <= V3) ? 2 : 3; int i = 0; + if (resolution == 0) find_resolution(); + + zchars = (zbyte *)malloc (sizeof (zbyte) * 3 * (resolution + 1)); + ptr = decoded; + /* Expand abbreviations that some old Infocom games lack */ - if (f_setup.expand_abbreviations) + if (option_expand_abbreviations && (h_version <= V8)) if (padding == 0x05 && decoded[1] == 0) @@ -264,6 +365,14 @@ static void encode_text (int padding) int index, set; zbyte c2; + if (c == 32) { + + zchars[i++] = 0; + + continue; + + } + /* Search character in the alphabet */ for (set = 0; set < 3; set++) @@ -304,10 +413,12 @@ static void encode_text (int padding) encoded[resolution - 1] |= 0x8000; + free (zchars); + }/* encode_text */ /* - * z_check_unicode, test if a unicode character can be read and printed. + * z_check_unicode, test if a unicode character can be printed (bit 0) and read (bit 1). * * zargs[0] = Unicode * @@ -316,15 +427,19 @@ static void encode_text (int padding) void z_check_unicode (void) { zword c = zargs[0]; + zword result = 0; - if (c >= 0x20 && c <= 0x7e) - store (3); - else if (c == 0xa0) - store (1); - else if (c >= 0xa1 && c <= 0xff) - store (3); + if (c <= 0x1f) + { + if ((c == 0x08) || (c == 0x0d) || (c == 0x1b)) + result = 2; + } + else if (c <= 0x7e) + result = 3; else - store (0); + result = 1; // we support unicode + + store (result); }/* z_check_unicode */ @@ -349,7 +464,7 @@ void z_encode_text (void) encode_text (0x05); - for (i = 0; i < 3; i++) + for (i = 0; i < resolution; i++) storew ((zword) (zargs[3] + 2 * i), encoded[i]); }/* z_encode_text */ @@ -391,6 +506,8 @@ static void decode_text (enum string_type st, zword addr) ptr = NULL; /* makes compilers shut up */ byte_addr = 0; + if (resolution == 0) find_resolution(); + /* Calculate the byte address if necessary */ if (st == ABBREVIATION) @@ -405,8 +522,12 @@ static void decode_text (enum string_type st, zword addr) byte_addr = (long) addr << 2; else if (h_version <= V7) byte_addr = ((long) addr << 2) + ((long) h_strings_offset << 3); - else /* h_version == V8 */ + else if (h_version <= V8) byte_addr = (long) addr << 3; + else /* h_version == V9 */ { + long indirect = (long) addr << 2; + HIGH_LONG(indirect, byte_addr); + } if (byte_addr >= story_size) runtime_error (ERR_ILL_PRINT_ADDR); @@ -439,6 +560,7 @@ static void decode_text (enum string_type st, zword addr) zword abbr_addr; zword ptr_addr; + zchar zc; c = (code >> i) & 0x1f; @@ -499,8 +621,30 @@ static void decode_text (enum string_type st, zword addr) case 3: /* ZSCII character - second part */ - c2 = translate_from_zscii ((prev_c << 5) | c); - outchar (c2); + zc = (prev_c << 5) | c; + + if (zc > 767) { /* Unicode escape */ + + while (zc-- > 767) { + + if (st == LOW_STRING || st == VOCABULARY) { + LOW_WORD (addr, c2) + addr += 2; + } else if (st == HIGH_STRING || st == ABBREVIATION) { + HIGH_WORD (byte_addr, c2) + byte_addr += 2; + } else + CODE_WORD (c2) + + outchar (c2 ^ 0xFFFF); + } + + } else { + + c2 = translate_from_zscii (zc); + outchar (c2); + + } status = 0; break; @@ -760,7 +904,10 @@ void print_string (const char *s) void z_print_unicode (void) { - print_char ((zargs[0] <= 0xff) ? zargs[0] : '?'); + if (zargs[0] < 0x20) + print_char ('?'); + else + print_char (zargs[0]); }/* z_print_unicode */ @@ -786,12 +933,13 @@ static zword lookup_text (int padding, zword dct) zword addr; zbyte entry_len; zbyte sep_count; - int resolution = (h_version <= V3) ? 2 : 3; int entry_number; int lower, upper; int i; bool sorted; + if (resolution == 0) find_resolution(); + encode_text (padding); LOW_BYTE (dct, sep_count) /* skip word separators */ @@ -1061,6 +1209,8 @@ int completion (const zchar *buffer, zchar *result) *result = 0; + if (resolution == 0) find_resolution(); + /* Copy last word to "decoded" string */ len = 0; @@ -1069,7 +1219,7 @@ int completion (const zchar *buffer, zchar *result) if (c != ' ') { - if (len < 9) + if (len < 3 * resolution) decoded[len++] = c; } else len = 0; @@ -1107,3 +1257,74 @@ int completion (const zchar *buffer, zchar *result) return (minaddr == maxaddr) ? 0 : 1; }/* completion */ + +/* + * unicode_tolower + * + * Convert a Unicode character to lowercase. + * Taken from Zip2000 by Kevin Bracey. + * + */ + +zchar unicode_tolower (zchar c) +{ + const static unsigned char tolower_basic_latin[0x100] = { + 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F, + 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17,0x18,0x19,0x1A,0x1B,0x1C,0x1D,0x1E,0x1F, + 0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27,0x28,0x29,0x2A,0x2B,0x2C,0x2D,0x2E,0x2F, + 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,0x38,0x39,0x3A,0x3B,0x3C,0x3D,0x3E,0x3F, + 0x40,0x61,0x62,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0x6A,0x6B,0x6C,0x6D,0x6E,0x6F, + 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7A,0x5B,0x5C,0x5D,0x5E,0x5F, + 0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0x6A,0x6B,0x6C,0x6D,0x6E,0x6F, + 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7A,0x7B,0x7C,0x7D,0x7E,0x7F, + 0x80,0x81,0x82,0x83,0x84,0x85,0x86,0x87,0x88,0x89,0x8A,0x8B,0x8C,0x8D,0x8E,0x8F, + 0x90,0x91,0x92,0x93,0x94,0x95,0x96,0x97,0x98,0x99,0x9A,0x9B,0x9C,0x9D,0x9E,0x9F, + 0xA0,0xA1,0xA2,0xA3,0xA4,0xA5,0xA6,0xA7,0xA8,0xA9,0xAA,0xAB,0xAC,0xAD,0xAE,0xAF, + 0xB0,0xB1,0xB2,0xB3,0xB4,0xB5,0xB6,0xB7,0xB8,0xB9,0xBA,0xBB,0xBC,0xBD,0xBE,0xBF, + 0xE0,0xE1,0xE2,0xE3,0xE4,0xE5,0xE6,0xE7,0xE8,0xE9,0xEA,0xEB,0xEC,0xED,0xEE,0xEF, + 0xF0,0xF1,0xF2,0xF3,0xF4,0xF5,0xF6,0xD7,0xF8,0xF9,0xFA,0xFB,0xFC,0xFD,0xFE,0xDF, + 0xE0,0xE1,0xE2,0xE3,0xE4,0xE5,0xE6,0xE7,0xE8,0xE9,0xEA,0xEB,0xEC,0xED,0xEE,0xEF, + 0xF0,0xF1,0xF2,0xF3,0xF4,0xF5,0xF6,0xF7,0xF8,0xF9,0xFA,0xFB,0xFC,0xFD,0xFE,0xFF + }; + const static unsigned char tolower_latin_extended_a[0x80] = { + 0x01,0x01,0x03,0x03,0x05,0x05,0x07,0x07,0x09,0x09,0x0B,0x0B,0x0D,0x0D,0x0F,0x0F, + 0x11,0x11,0x13,0x13,0x15,0x15,0x17,0x17,0x19,0x19,0x1B,0x1B,0x1D,0x1D,0x1F,0x1F, + 0x21,0x21,0x23,0x23,0x25,0x25,0x27,0x27,0x29,0x29,0x2B,0x2B,0x2D,0x2D,0x2F,0x2F, + 0x00,0x31,0x33,0x33,0x35,0x35,0x37,0x37,0x38,0x3A,0x3A,0x3C,0x3C,0x3E,0x3E,0x40, + 0x40,0x42,0x42,0x44,0x44,0x46,0x46,0x48,0x48,0x49,0x4B,0x4B,0x4D,0x4D,0x4F,0x4F, + 0x51,0x51,0x53,0x53,0x55,0x55,0x57,0x57,0x59,0x59,0x5B,0x5B,0x5D,0x5D,0x5F,0x5F, + 0x61,0x61,0x63,0x63,0x65,0x65,0x67,0x67,0x69,0x69,0x6B,0x6B,0x6D,0x6D,0x6F,0x6F, + 0x71,0x71,0x73,0x73,0x75,0x75,0x77,0x77,0x00,0x7A,0x7A,0x7C,0x7C,0x7E,0x7E,0x7F + }; + const static unsigned char tolower_greek[0x50] = { + 0x80,0x81,0x82,0x83,0x84,0x85,0xAC,0x87,0xAD,0xAE,0xAF,0x8B,0xCC,0x8D,0xCD,0xCE, + 0x90,0xB1,0xB2,0xB3,0xB4,0xB5,0xB6,0xB7,0xB8,0xB9,0xBA,0xBB,0xBC,0xBD,0xBE,0xBF, + 0xC0,0xC1,0xA2,0xC3,0xC4,0xC5,0xC6,0xC7,0xC8,0xC9,0xCA,0xCB,0xAC,0xAD,0xAE,0xAF, + 0xB0,0xB1,0xB2,0xB3,0xB4,0xB5,0xB6,0xB7,0xB8,0xB9,0xBA,0xBB,0xBC,0xBD,0xBE,0xBF, + 0xC0,0xC1,0xC2,0xC3,0xC4,0xC5,0xC6,0xC7,0xC8,0xC9,0xCA,0xCB,0xCC,0xCD,0xCE,0xCF + }; + const static unsigned char tolower_cyrillic[0x60] = { + 0x00,0x51,0x52,0x53,0x54,0x55,0x56,0x57,0x58,0x59,0x5A,0x5B,0x5C,0x5D,0x5E,0x5F, + 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,0x38,0x39,0x3A,0x3B,0x3C,0x3D,0x3E,0x3F, + 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47,0x48,0x49,0x4A,0x4B,0x4C,0x4D,0x4E,0x4F, + 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,0x38,0x39,0x3A,0x3B,0x3C,0x3D,0x3E,0x3F, + 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47,0x48,0x49,0x4A,0x4B,0x4C,0x4D,0x4E,0x4F, + 0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57,0x58,0x59,0x5A,0x5B,0x5C,0x5D,0x5E,0x5F + }; + + if (c < 0x0100) + c = tolower_basic_latin[c]; + else if (c == 0x0130) + c = 0x0069; /* Capital I with dot -> lower case i */ + else if (c == 0x0178) + c = 0x00FF; /* Capital Y diaeresis -> lower case y diaeresis */ + else if (c < 0x0180) + c = tolower_latin_extended_a[c-0x100] + 0x100; + else if (c >= 0x380 && c < 0x3D0) + c = tolower_greek[c-0x380] + 0x300; + else if (c >= 0x400 && c < 0x460) + c = tolower_cyrillic[c-0x400] + 0x400; + + return c; +} +