^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1) // SPDX-License-Identifier: GPL-2.0-or-later
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 3) * upcase.c - Generate the full NTFS Unicode upcase table in little endian.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 4) * Part of the Linux-NTFS project.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 5) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 6) * Copyright (c) 2001 Richard Russon <ntfs@flatcap.org>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 7) * Copyright (c) 2001-2006 Anton Altaparmakov
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 8) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 9)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 10) #include "malloc.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 11) #include "ntfs.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 12)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 13) ntfschar *generate_default_upcase(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 14) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 15) static const int uc_run_table[][3] = { /* Start, End, Add */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 16) {0x0061, 0x007B, -32}, {0x0451, 0x045D, -80}, {0x1F70, 0x1F72, 74},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 17) {0x00E0, 0x00F7, -32}, {0x045E, 0x0460, -80}, {0x1F72, 0x1F76, 86},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 18) {0x00F8, 0x00FF, -32}, {0x0561, 0x0587, -48}, {0x1F76, 0x1F78, 100},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 19) {0x0256, 0x0258, -205}, {0x1F00, 0x1F08, 8}, {0x1F78, 0x1F7A, 128},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 20) {0x028A, 0x028C, -217}, {0x1F10, 0x1F16, 8}, {0x1F7A, 0x1F7C, 112},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 21) {0x03AC, 0x03AD, -38}, {0x1F20, 0x1F28, 8}, {0x1F7C, 0x1F7E, 126},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 22) {0x03AD, 0x03B0, -37}, {0x1F30, 0x1F38, 8}, {0x1FB0, 0x1FB2, 8},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 23) {0x03B1, 0x03C2, -32}, {0x1F40, 0x1F46, 8}, {0x1FD0, 0x1FD2, 8},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 24) {0x03C2, 0x03C3, -31}, {0x1F51, 0x1F52, 8}, {0x1FE0, 0x1FE2, 8},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 25) {0x03C3, 0x03CC, -32}, {0x1F53, 0x1F54, 8}, {0x1FE5, 0x1FE6, 7},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 26) {0x03CC, 0x03CD, -64}, {0x1F55, 0x1F56, 8}, {0x2170, 0x2180, -16},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 27) {0x03CD, 0x03CF, -63}, {0x1F57, 0x1F58, 8}, {0x24D0, 0x24EA, -26},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 28) {0x0430, 0x0450, -32}, {0x1F60, 0x1F68, 8}, {0xFF41, 0xFF5B, -32},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 29) {0}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 30) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 31)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 32) static const int uc_dup_table[][2] = { /* Start, End */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 33) {0x0100, 0x012F}, {0x01A0, 0x01A6}, {0x03E2, 0x03EF}, {0x04CB, 0x04CC},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 34) {0x0132, 0x0137}, {0x01B3, 0x01B7}, {0x0460, 0x0481}, {0x04D0, 0x04EB},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 35) {0x0139, 0x0149}, {0x01CD, 0x01DD}, {0x0490, 0x04BF}, {0x04EE, 0x04F5},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 36) {0x014A, 0x0178}, {0x01DE, 0x01EF}, {0x04BF, 0x04BF}, {0x04F8, 0x04F9},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 37) {0x0179, 0x017E}, {0x01F4, 0x01F5}, {0x04C1, 0x04C4}, {0x1E00, 0x1E95},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 38) {0x018B, 0x018B}, {0x01FA, 0x0218}, {0x04C7, 0x04C8}, {0x1EA0, 0x1EF9},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 39) {0}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 40) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 41)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 42) static const int uc_word_table[][2] = { /* Offset, Value */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 43) {0x00FF, 0x0178}, {0x01AD, 0x01AC}, {0x01F3, 0x01F1}, {0x0269, 0x0196},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 44) {0x0183, 0x0182}, {0x01B0, 0x01AF}, {0x0253, 0x0181}, {0x026F, 0x019C},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 45) {0x0185, 0x0184}, {0x01B9, 0x01B8}, {0x0254, 0x0186}, {0x0272, 0x019D},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 46) {0x0188, 0x0187}, {0x01BD, 0x01BC}, {0x0259, 0x018F}, {0x0275, 0x019F},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 47) {0x018C, 0x018B}, {0x01C6, 0x01C4}, {0x025B, 0x0190}, {0x0283, 0x01A9},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 48) {0x0192, 0x0191}, {0x01C9, 0x01C7}, {0x0260, 0x0193}, {0x0288, 0x01AE},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 49) {0x0199, 0x0198}, {0x01CC, 0x01CA}, {0x0263, 0x0194}, {0x0292, 0x01B7},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 50) {0x01A8, 0x01A7}, {0x01DD, 0x018E}, {0x0268, 0x0197},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 51) {0}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 52) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 53)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 54) int i, r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 55) ntfschar *uc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 56)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 57) uc = ntfs_malloc_nofs(default_upcase_len * sizeof(ntfschar));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 58) if (!uc)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 59) return uc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 60) memset(uc, 0, default_upcase_len * sizeof(ntfschar));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 61) /* Generate the little endian Unicode upcase table used by ntfs. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 62) for (i = 0; i < default_upcase_len; i++)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 63) uc[i] = cpu_to_le16(i);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 64) for (r = 0; uc_run_table[r][0]; r++)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 65) for (i = uc_run_table[r][0]; i < uc_run_table[r][1]; i++)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 66) le16_add_cpu(&uc[i], uc_run_table[r][2]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 67) for (r = 0; uc_dup_table[r][0]; r++)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 68) for (i = uc_dup_table[r][0]; i < uc_dup_table[r][1]; i += 2)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 69) le16_add_cpu(&uc[i + 1], -1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 70) for (r = 0; uc_word_table[r][0]; r++)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 71) uc[uc_word_table[r][0]] = cpu_to_le16(uc_word_table[r][1]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 72) return uc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 73) }