diff --git a/drivers/tty/vt/gen_ucs_width_table.py b/drivers/tty/vt/gen_ucs_width_table.py index 76e80ebeff13..4d2476842750 100755 --- a/drivers/tty/vt/gen_ucs_width_table.py +++ b/drivers/tty/vt/gen_ucs_width_table.py @@ -190,12 +190,23 @@ def write_tables(zero_width_ranges, double_width_ranges, out_file=DEFAULT_OUT_FI """ Write the generated tables to C header file. + The output uses a single sorted-by-`first` table per region (BMP and + non-BMP), with zero-width and double-width ranges merged together. The + non-BMP table also hosts the BMP double-width bitmap in spare bits of + `last`. See the encoding comment at the top of ucs.c for the layout. + Args: zero_width_ranges: List of (start, end) ranges for zero-width characters double_width_ranges: List of (start, end) ranges for double-width characters out_file: Output file name (default: DEFAULT_OUT_FILE) """ + # Bits per BMP-bitmap chunk hosted in one non-BMP entry's `last` field. + # 8 bits makes `idx / BITS_PER_CHUNK` / `idx % BITS_PER_CHUNK` compile to + # a cheap shift+mask in the lookup. The chunk size is also emitted as + # UCS_NONBMP_BMP_BITS in the generated header so ucs.c stays in sync. + BITS_PER_CHUNK = 8 + # Function to split ranges into BMP (16-bit) and non-BMP (above 16-bit) def split_ranges_by_size(ranges): bmp_ranges = [] @@ -217,6 +228,40 @@ def write_tables(zero_width_ranges, double_width_ranges, out_file=DEFAULT_OUT_FI zero_width_bmp, zero_width_non_bmp = split_ranges_by_size(zero_width_ranges) double_width_bmp, double_width_non_bmp = split_ranges_by_size(double_width_ranges) + # Merge zero- and double-width ranges per region, tagging each with its + # width, then sort by `first` so binary search works on the union. + bmp_entries = sorted( + [(s, e, 0) for s, e in zero_width_bmp] + + [(s, e, 2) for s, e in double_width_bmp], + key=lambda t: t[0]) + nonbmp_entries = sorted( + [(s, e, 0) for s, e in zero_width_non_bmp] + + [(s, e, 2) for s, e in double_width_non_bmp], + key=lambda t: t[0]) + + # Build the BMP double-width bitmap: one bit per BMP entry (in sort + # order), set iff that entry is double-width. Pack into BITS_PER_CHUNK- + # wide chunks, with bit j of the chunk corresponding to entry + # (chunk_index * BITS_PER_CHUNK + j). + bmp_w2_bits = [1 if w == 2 else 0 for _, _, w in bmp_entries] + n_chunks = (len(bmp_w2_bits) + BITS_PER_CHUNK - 1) // BITS_PER_CHUNK + + if n_chunks > len(nonbmp_entries): + raise RuntimeError( + f"BMP bitmap needs {n_chunks} host entries, " + f"but only {len(nonbmp_entries)} non-BMP entries are available") + + chunks = [] # list of (base_index, end_index, packed_value) + for c in range(n_chunks): + base = c * BITS_PER_CHUNK + end_idx = min(base + BITS_PER_CHUNK - 1, len(bmp_w2_bits) - 1) + value = 0 + for j in range(BITS_PER_CHUNK): + k = base + j + if k < len(bmp_w2_bits) and bmp_w2_bits[k]: + value |= 1 << j + chunks.append((base, end_idx, value)) + # Function to generate code point description comments def get_code_point_comment(start, end): try: @@ -242,48 +287,47 @@ def write_tables(zero_width_ranges, double_width_ranges, out_file=DEFAULT_OUT_FI * Auto-generated by {this_file} * * Unicode Version: {unicodedata.unidata_version} + * + * Zero-width and double-width ranges are merged into one sorted-by-`first` + * table per region. The non-BMP table additionally hosts the BMP + * double-width bitmap in the low {BITS_PER_CHUNK} bits of `last` of its + * first {n_chunks} entries (covering {len(bmp_w2_bits)} BMP entries). + * See ucs.c for the encoding details and the lookup code. */ -/* Zero-width character ranges (BMP - Basic Multilingual Plane, U+0000 to U+FFFF) */ -static const struct ucs_interval16 ucs_zero_width_bmp_ranges[] = {{ +/* Bits per BMP-bitmap chunk hosted in one non-BMP entry's `last` field. */ +#define UCS_NONBMP_BMP_BITS {BITS_PER_CHUNK} + +/* Combined zero- and double-width ranges + * (BMP - Basic Multilingual Plane, U+0000 to U+FFFF). */ +static const struct ucs_width16 ucs_bmp_ranges[] = {{ """) - for start, end in zero_width_bmp: - comment = get_code_point_comment(start, end) - f.write(f"\t{{ 0x{start:04X}, 0x{end:04X} }}, {comment}\n") + for s, e, w in bmp_entries: + macro = "BMP_0WIDTH" if w == 0 else "BMP_2WIDTH" + comment = get_code_point_comment(s, e) + f.write(f"\t{{ {macro}(0x{s:04X}, 0x{e:04X}) }}, {comment}\n") - f.write("""\ -}; + f.write(f"""\ +}}; -/* Zero-width character ranges (non-BMP, U+10000 and above) */ -static const struct ucs_interval32 ucs_zero_width_non_bmp_ranges[] = { +/* Combined zero- and double-width ranges (non-BMP, U+10000 and above). + * The first {n_chunks} entries host the BMP double-width bitmap in the low + * {BITS_PER_CHUNK} bits of `last`. */ +static const struct ucs_width32 ucs_nonbmp_ranges[] = {{ """) - for start, end in zero_width_non_bmp: - comment = get_code_point_comment(start, end) - f.write(f"\t{{ 0x{start:05X}, 0x{end:05X} }}, {comment}\n") - - f.write("""\ -}; - -/* Double-width character ranges (BMP - Basic Multilingual Plane, U+0000 to U+FFFF) */ -static const struct ucs_interval16 ucs_double_width_bmp_ranges[] = { -""") - - for start, end in double_width_bmp: - comment = get_code_point_comment(start, end) - f.write(f"\t{{ 0x{start:04X}, 0x{end:04X} }}, {comment}\n") - - f.write("""\ -}; - -/* Double-width character ranges (non-BMP, U+10000 and above) */ -static const struct ucs_interval32 ucs_double_width_non_bmp_ranges[] = { -""") - - for start, end in double_width_non_bmp: - comment = get_code_point_comment(start, end) - f.write(f"\t{{ 0x{start:05X}, 0x{end:05X} }}, {comment}\n") + for i, (s, e, w) in enumerate(nonbmp_entries): + macro = "RANGE_0WIDTH" if w == 0 else "RANGE_2WIDTH" + comment = get_code_point_comment(s, e) + if i < len(chunks): + base, end_idx, value = chunks[i] + f.write( + f"\t{{ {macro}(0x{s:05X}, 0x{e:05X}) {comment}\n" + f"\t | BMP_2W_BITS(0b{value:0{BITS_PER_CHUNK}b}) }}," + f" /* BMP entries [{base:>3}..{end_idx:>3}] */\n") + else: + f.write(f"\t{{ {macro}(0x{s:05X}, 0x{e:05X}) }}, {comment}\n") f.write("};\n") @@ -301,7 +345,10 @@ if __name__ == "__main__": # Print summary zero_width_count = sum(end - start + 1 for start, end in zero_width_ranges) double_width_count = sum(end - start + 1 for start, end in double_width_ranges) + n_zero = len(zero_width_ranges) + n_double = len(double_width_ranges) print(f"Generated {args.output_file} with:") - print(f"- {len(zero_width_ranges)} zero-width ranges covering ~{zero_width_count} code points") - print(f"- {len(double_width_ranges)} double-width ranges covering ~{double_width_count} code points") + print(f"- {n_zero} zero-width ranges covering ~{zero_width_count} code points") + print(f"- {n_double} double-width ranges covering ~{double_width_count} code points") + print(f"- {n_zero + n_double} merged ranges total") print(f"- Unicode Version: {unicodedata.unidata_version}") diff --git a/drivers/tty/vt/ucs.c b/drivers/tty/vt/ucs.c index 03877485dfb7..fc41c0bb5d7b 100644 --- a/drivers/tty/vt/ucs.c +++ b/drivers/tty/vt/ucs.c @@ -4,96 +4,138 @@ */ #include +#include #include #include -#include +#include -struct ucs_interval16 { +struct ucs_width16 { u16 first; u16 last; }; -struct ucs_interval32 { +struct ucs_width32 { u32 first; u32 last; }; +/* + * Width table encoding (consumed by ucs_width_table.h): + * + * Zero- and double-width ranges are merged into one sorted-by-`first` table + * per region (BMP / non-BMP). The BMP table stores plain (first, last) + * pairs; per-entry width lives in a packed bitmap *hosted by the non-BMP + * table*. + * + * That hosting is the whole point of the encoding. Non-BMP code points use + * only 20 bits, so each u32 has 12 spare high bits sitting around doing + * nothing — we'd rather use them than spend a separate parallel array for + * width and BMP-bitmap bits. So we move the cp value up by UCS_CP_SHIFT + * and stash metadata in the now-free low bits of `last`: + * - bit UCS_NONBMP_W2_FLAG_BIT: this entry's own width (0=zero, 1=double), + * - bits 0..UCS_NONBMP_BMP_BITS-1: a chunk of the BMP double-width + * bitmap. Bit `j` of the chunk in non-BMP entry `c` is set iff BMP + * entry (c * UCS_NONBMP_BMP_BITS + j) is double-width. The first + * ceil(N_BMP / UCS_NONBMP_BMP_BITS) non-BMP entries carry the bitmap; + * the rest leave these bits zero. + * + * Because the metadata bits sit strictly below the lowest cp-scale bit, + * the bsearch comparator does plain u32 comparison on the shifted key and + * stored values without masking — ordering between distinct code points is + * undisturbed. + */ +#define UCS_CP_SHIFT 12 +#define UCS_NONBMP_W2_FLAG_BIT 11 +#define UCS_NONBMP_W2_FLAG (1u << UCS_NONBMP_W2_FLAG_BIT) + +#define BMP_0WIDTH(first, last) first, last +#define BMP_2WIDTH(first, last) first, last +#define RANGE_0WIDTH(first, last) \ + (u32)(first) << UCS_CP_SHIFT, (u32)(last) << UCS_CP_SHIFT +#define RANGE_2WIDTH(first, last) \ + (u32)(first) << UCS_CP_SHIFT, ((u32)(last) << UCS_CP_SHIFT) | UCS_NONBMP_W2_FLAG +#define BMP_2W_BITS(b) (b) + #include "ucs_width_table.h" -static int interval16_cmp(const void *key, const void *element) -{ - u16 cp = *(u16 *)key; - const struct ucs_interval16 *entry = element; - - if (cp < entry->first) - return -1; - if (cp > entry->last) - return 1; - return 0; -} - -static int interval32_cmp(const void *key, const void *element) -{ - u32 cp = *(u32 *)key; - const struct ucs_interval32 *entry = element; - - if (cp < entry->first) - return -1; - if (cp > entry->last) - return 1; - return 0; -} - -static bool cp_in_range16(u16 cp, const struct ucs_interval16 *ranges, size_t size) -{ - if (cp < ranges[0].first || cp > ranges[size - 1].last) - return false; - - return __inline_bsearch(&cp, ranges, size, sizeof(*ranges), - interval16_cmp) != NULL; -} - -static bool cp_in_range32(u32 cp, const struct ucs_interval32 *ranges, size_t size) -{ - if (cp < ranges[0].first || cp > ranges[size - 1].last) - return false; - - return __inline_bsearch(&cp, ranges, size, sizeof(*ranges), - interval32_cmp) != NULL; -} +static_assert(UCS_NONBMP_BMP_BITS <= UCS_NONBMP_W2_FLAG_BIT, + "BMP bitmap chunk would overlap the per-entry width flag"); +static_assert(UCS_NONBMP_W2_FLAG_BIT < UCS_CP_SHIFT, + "Metadata bits collide with the shifted cp value"); +static_assert(DIV_ROUND_UP(ARRAY_SIZE(ucs_bmp_ranges), UCS_NONBMP_BMP_BITS) + <= ARRAY_SIZE(ucs_nonbmp_ranges), + "Not enough non-BMP entries to host the BMP width bitmap"); #define UCS_IS_BMP(cp) ((cp) <= 0xffff) -/** - * ucs_is_zero_width() - Determine if a Unicode code point is zero-width. - * @cp: Unicode code point (UCS-4) - * - * Return: true if the character is zero-width, false otherwise - */ -bool ucs_is_zero_width(u32 cp) +static int width16_cmp(const void *key, const void *element) { - if (UCS_IS_BMP(cp)) - return cp_in_range16(cp, ucs_zero_width_bmp_ranges, - ARRAY_SIZE(ucs_zero_width_bmp_ranges)); - else - return cp_in_range32(cp, ucs_zero_width_non_bmp_ranges, - ARRAY_SIZE(ucs_zero_width_non_bmp_ranges)); + u16 cp = *(u16 *)key; + const struct ucs_width16 *entry = element; + + if (cp < entry->first) + return -1; + if (cp > entry->last) + return 1; + return 0; +} + +static int width32_cmp(const void *key, const void *element) +{ + u32 k = *(u32 *)key; + const struct ucs_width32 *entry = element; + + if (k < entry->first) + return -1; + if (k > entry->last) + return 1; + return 0; } /** - * ucs_is_double_width() - Determine if a Unicode code point is double-width. + * ucs_get_width() - Get the display width of a Unicode code point. * @cp: Unicode code point (UCS-4) * - * Return: true if the character is double-width, false otherwise + * Return: 2 for double-width (East Asian Wide/Fullwidth, emoji, ...), + * 0 for zero-width (combining marks, format characters, ...), + * 1 for everything else (the common case). */ -bool ucs_is_double_width(u32 cp) +unsigned int ucs_get_width(u32 cp) { - if (UCS_IS_BMP(cp)) - return cp_in_range16(cp, ucs_double_width_bmp_ranges, - ARRAY_SIZE(ucs_double_width_bmp_ranges)); - else - return cp_in_range32(cp, ucs_double_width_non_bmp_ranges, - ARRAY_SIZE(ucs_double_width_non_bmp_ranges)); + const struct ucs_width16 *e16; + const struct ucs_width32 *e32; + unsigned int idx; + u32 k; + + if (UCS_IS_BMP(cp)) { + u16 bmp = cp; + + if (bmp < ucs_bmp_ranges[0].first || + bmp > ucs_bmp_ranges[ARRAY_SIZE(ucs_bmp_ranges) - 1].last) + return 1; + + e16 = __inline_bsearch(&bmp, ucs_bmp_ranges, + ARRAY_SIZE(ucs_bmp_ranges), + sizeof(*ucs_bmp_ranges), width16_cmp); + if (!e16) + return 1; + + idx = e16 - ucs_bmp_ranges; + return (ucs_nonbmp_ranges[idx / UCS_NONBMP_BMP_BITS].last + >> (idx % UCS_NONBMP_BMP_BITS)) & 1 ? 2 : 0; + } + + k = cp << UCS_CP_SHIFT; + if (k < ucs_nonbmp_ranges[0].first || + k > ucs_nonbmp_ranges[ARRAY_SIZE(ucs_nonbmp_ranges) - 1].last) + return 1; + + e32 = __inline_bsearch(&k, ucs_nonbmp_ranges, + ARRAY_SIZE(ucs_nonbmp_ranges), + sizeof(*ucs_nonbmp_ranges), width32_cmp); + if (!e32) + return 1; + return (e32->last & UCS_NONBMP_W2_FLAG) ? 2 : 0; } /* diff --git a/drivers/tty/vt/ucs_width_table.h_shipped b/drivers/tty/vt/ucs_width_table.h_shipped index 6fcb8f1d577d..5cd6434bf329 100644 --- a/drivers/tty/vt/ucs_width_table.h_shipped +++ b/drivers/tty/vt/ucs_width_table.h_shipped @@ -5,449 +5,486 @@ * Auto-generated by gen_ucs_width_table.py * * Unicode Version: 16.0.0 + * + * Zero-width and double-width ranges are merged into one sorted-by-`first` + * table per region. The non-BMP table additionally hosts the BMP + * double-width bitmap in the low 8 bits of `last` of its + * first 33 entries (covering 262 BMP entries). + * See ucs.c for the encoding details and the lookup code. */ -/* Zero-width character ranges (BMP - Basic Multilingual Plane, U+0000 to U+FFFF) */ -static const struct ucs_interval16 ucs_zero_width_bmp_ranges[] = { - { 0x00AD, 0x00AD }, /* SOFT HYPHEN */ - { 0x0300, 0x036F }, /* COMBINING GRAVE ACCENT - COMBINING LATIN SMALL LETTER X */ - { 0x0483, 0x0489 }, /* COMBINING CYRILLIC TITLO - COMBINING CYRILLIC MILLIONS SIGN */ - { 0x0591, 0x05BD }, /* HEBREW ACCENT ETNAHTA - HEBREW POINT METEG */ - { 0x05BF, 0x05BF }, /* HEBREW POINT RAFE */ - { 0x05C1, 0x05C2 }, /* HEBREW POINT SHIN DOT - HEBREW POINT SIN DOT */ - { 0x05C4, 0x05C5 }, /* HEBREW MARK UPPER DOT - HEBREW MARK LOWER DOT */ - { 0x05C7, 0x05C7 }, /* HEBREW POINT QAMATS QATAN */ - { 0x0600, 0x0605 }, /* ARABIC NUMBER SIGN - ARABIC NUMBER MARK ABOVE */ - { 0x0610, 0x061A }, /* ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM - ARABIC SMALL KASRA */ - { 0x061C, 0x061C }, /* ARABIC LETTER MARK */ - { 0x064B, 0x065F }, /* ARABIC FATHATAN - ARABIC WAVY HAMZA BELOW */ - { 0x0670, 0x0670 }, /* ARABIC LETTER SUPERSCRIPT ALEF */ - { 0x06D6, 0x06DD }, /* ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA - ARABIC END OF AYAH */ - { 0x06DF, 0x06E4 }, /* ARABIC SMALL HIGH ROUNDED ZERO - ARABIC SMALL HIGH MADDA */ - { 0x06E7, 0x06E8 }, /* ARABIC SMALL HIGH YEH - ARABIC SMALL HIGH NOON */ - { 0x06EA, 0x06ED }, /* ARABIC EMPTY CENTRE LOW STOP - ARABIC SMALL LOW MEEM */ - { 0x070F, 0x070F }, /* SYRIAC ABBREVIATION MARK */ - { 0x0711, 0x0711 }, /* SYRIAC LETTER SUPERSCRIPT ALAPH */ - { 0x0730, 0x074A }, /* SYRIAC PTHAHA ABOVE - SYRIAC BARREKH */ - { 0x07A6, 0x07B0 }, /* THAANA ABAFILI - THAANA SUKUN */ - { 0x07EB, 0x07F3 }, /* NKO COMBINING SHORT HIGH TONE - NKO COMBINING DOUBLE DOT ABOVE */ - { 0x07FD, 0x07FD }, /* NKO DANTAYALAN */ - { 0x0816, 0x0819 }, /* SAMARITAN MARK IN - SAMARITAN MARK DAGESH */ - { 0x081B, 0x0823 }, /* SAMARITAN MARK EPENTHETIC YUT - SAMARITAN VOWEL SIGN A */ - { 0x0825, 0x0827 }, /* SAMARITAN VOWEL SIGN SHORT A - SAMARITAN VOWEL SIGN U */ - { 0x0829, 0x082D }, /* SAMARITAN VOWEL SIGN LONG I - SAMARITAN MARK NEQUDAA */ - { 0x0859, 0x085B }, /* MANDAIC AFFRICATION MARK - MANDAIC GEMINATION MARK */ - { 0x0890, 0x0891 }, /* ARABIC POUND MARK ABOVE - ARABIC PIASTRE MARK ABOVE */ - { 0x0897, 0x089F }, /* ARABIC PEPET - ARABIC HALF MADDA OVER MADDA */ - { 0x08CA, 0x0903 }, /* ARABIC SMALL HIGH FARSI YEH - DEVANAGARI SIGN VISARGA */ - { 0x093A, 0x093C }, /* DEVANAGARI VOWEL SIGN OE - DEVANAGARI SIGN NUKTA */ - { 0x093E, 0x094F }, /* DEVANAGARI VOWEL SIGN AA - DEVANAGARI VOWEL SIGN AW */ - { 0x0951, 0x0957 }, /* DEVANAGARI STRESS SIGN UDATTA - DEVANAGARI VOWEL SIGN UUE */ - { 0x0962, 0x0963 }, /* DEVANAGARI VOWEL SIGN VOCALIC L - DEVANAGARI VOWEL SIGN VOCALIC LL */ - { 0x0981, 0x0983 }, /* BENGALI SIGN CANDRABINDU - BENGALI SIGN VISARGA */ - { 0x09BC, 0x09BC }, /* BENGALI SIGN NUKTA */ - { 0x09BE, 0x09C4 }, /* BENGALI VOWEL SIGN AA - BENGALI VOWEL SIGN VOCALIC RR */ - { 0x09C7, 0x09C8 }, /* BENGALI VOWEL SIGN E - BENGALI VOWEL SIGN AI */ - { 0x09CB, 0x09CD }, /* BENGALI VOWEL SIGN O - BENGALI SIGN VIRAMA */ - { 0x09D7, 0x09D7 }, /* BENGALI AU LENGTH MARK */ - { 0x09E2, 0x09E3 }, /* BENGALI VOWEL SIGN VOCALIC L - BENGALI VOWEL SIGN VOCALIC LL */ - { 0x09FE, 0x09FE }, /* BENGALI SANDHI MARK */ - { 0x0A01, 0x0A03 }, /* GURMUKHI SIGN ADAK BINDI - GURMUKHI SIGN VISARGA */ - { 0x0A3C, 0x0A3C }, /* GURMUKHI SIGN NUKTA */ - { 0x0A3E, 0x0A42 }, /* GURMUKHI VOWEL SIGN AA - GURMUKHI VOWEL SIGN UU */ - { 0x0A47, 0x0A48 }, /* GURMUKHI VOWEL SIGN EE - GURMUKHI VOWEL SIGN AI */ - { 0x0A4B, 0x0A4D }, /* GURMUKHI VOWEL SIGN OO - GURMUKHI SIGN VIRAMA */ - { 0x0A51, 0x0A51 }, /* GURMUKHI SIGN UDAAT */ - { 0x0A70, 0x0A71 }, /* GURMUKHI TIPPI - GURMUKHI ADDAK */ - { 0x0A75, 0x0A75 }, /* GURMUKHI SIGN YAKASH */ - { 0x0A81, 0x0A83 }, /* GUJARATI SIGN CANDRABINDU - GUJARATI SIGN VISARGA */ - { 0x0ABC, 0x0ABC }, /* GUJARATI SIGN NUKTA */ - { 0x0ABE, 0x0AC5 }, /* GUJARATI VOWEL SIGN AA - GUJARATI VOWEL SIGN CANDRA E */ - { 0x0AC7, 0x0AC9 }, /* GUJARATI VOWEL SIGN E - GUJARATI VOWEL SIGN CANDRA O */ - { 0x0ACB, 0x0ACD }, /* GUJARATI VOWEL SIGN O - GUJARATI SIGN VIRAMA */ - { 0x0AE2, 0x0AE3 }, /* GUJARATI VOWEL SIGN VOCALIC L - GUJARATI VOWEL SIGN VOCALIC LL */ - { 0x0AFA, 0x0AFF }, /* GUJARATI SIGN SUKUN - GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE */ - { 0x0B01, 0x0B03 }, /* ORIYA SIGN CANDRABINDU - ORIYA SIGN VISARGA */ - { 0x0B3C, 0x0B3C }, /* ORIYA SIGN NUKTA */ - { 0x0B3E, 0x0B44 }, /* ORIYA VOWEL SIGN AA - ORIYA VOWEL SIGN VOCALIC RR */ - { 0x0B47, 0x0B48 }, /* ORIYA VOWEL SIGN E - ORIYA VOWEL SIGN AI */ - { 0x0B4B, 0x0B4D }, /* ORIYA VOWEL SIGN O - ORIYA SIGN VIRAMA */ - { 0x0B55, 0x0B57 }, /* ORIYA SIGN OVERLINE - ORIYA AU LENGTH MARK */ - { 0x0B62, 0x0B63 }, /* ORIYA VOWEL SIGN VOCALIC L - ORIYA VOWEL SIGN VOCALIC LL */ - { 0x0B82, 0x0B82 }, /* TAMIL SIGN ANUSVARA */ - { 0x0BBE, 0x0BC2 }, /* TAMIL VOWEL SIGN AA - TAMIL VOWEL SIGN UU */ - { 0x0BC6, 0x0BC8 }, /* TAMIL VOWEL SIGN E - TAMIL VOWEL SIGN AI */ - { 0x0BCA, 0x0BCD }, /* TAMIL VOWEL SIGN O - TAMIL SIGN VIRAMA */ - { 0x0BD7, 0x0BD7 }, /* TAMIL AU LENGTH MARK */ - { 0x0C00, 0x0C04 }, /* TELUGU SIGN COMBINING CANDRABINDU ABOVE - TELUGU SIGN COMBINING ANUSVARA ABOVE */ - { 0x0C3C, 0x0C3C }, /* TELUGU SIGN NUKTA */ - { 0x0C3E, 0x0C44 }, /* TELUGU VOWEL SIGN AA - TELUGU VOWEL SIGN VOCALIC RR */ - { 0x0C46, 0x0C48 }, /* TELUGU VOWEL SIGN E - TELUGU VOWEL SIGN AI */ - { 0x0C4A, 0x0C4D }, /* TELUGU VOWEL SIGN O - TELUGU SIGN VIRAMA */ - { 0x0C55, 0x0C56 }, /* TELUGU LENGTH MARK - TELUGU AI LENGTH MARK */ - { 0x0C62, 0x0C63 }, /* TELUGU VOWEL SIGN VOCALIC L - TELUGU VOWEL SIGN VOCALIC LL */ - { 0x0C81, 0x0C83 }, /* KANNADA SIGN CANDRABINDU - KANNADA SIGN VISARGA */ - { 0x0CBC, 0x0CBC }, /* KANNADA SIGN NUKTA */ - { 0x0CBE, 0x0CC4 }, /* KANNADA VOWEL SIGN AA - KANNADA VOWEL SIGN VOCALIC RR */ - { 0x0CC6, 0x0CC8 }, /* KANNADA VOWEL SIGN E - KANNADA VOWEL SIGN AI */ - { 0x0CCA, 0x0CCD }, /* KANNADA VOWEL SIGN O - KANNADA SIGN VIRAMA */ - { 0x0CD5, 0x0CD6 }, /* KANNADA LENGTH MARK - KANNADA AI LENGTH MARK */ - { 0x0CE2, 0x0CE3 }, /* KANNADA VOWEL SIGN VOCALIC L - KANNADA VOWEL SIGN VOCALIC LL */ - { 0x0CF3, 0x0CF3 }, /* KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT */ - { 0x0D00, 0x0D03 }, /* MALAYALAM SIGN COMBINING ANUSVARA ABOVE - MALAYALAM SIGN VISARGA */ - { 0x0D3B, 0x0D3C }, /* MALAYALAM SIGN VERTICAL BAR VIRAMA - MALAYALAM SIGN CIRCULAR VIRAMA */ - { 0x0D3E, 0x0D44 }, /* MALAYALAM VOWEL SIGN AA - MALAYALAM VOWEL SIGN VOCALIC RR */ - { 0x0D46, 0x0D48 }, /* MALAYALAM VOWEL SIGN E - MALAYALAM VOWEL SIGN AI */ - { 0x0D4A, 0x0D4D }, /* MALAYALAM VOWEL SIGN O - MALAYALAM SIGN VIRAMA */ - { 0x0D57, 0x0D57 }, /* MALAYALAM AU LENGTH MARK */ - { 0x0D62, 0x0D63 }, /* MALAYALAM VOWEL SIGN VOCALIC L - MALAYALAM VOWEL SIGN VOCALIC LL */ - { 0x0D81, 0x0D83 }, /* SINHALA SIGN CANDRABINDU - SINHALA SIGN VISARGAYA */ - { 0x0DCA, 0x0DCA }, /* SINHALA SIGN AL-LAKUNA */ - { 0x0DCF, 0x0DD4 }, /* SINHALA VOWEL SIGN AELA-PILLA - SINHALA VOWEL SIGN KETTI PAA-PILLA */ - { 0x0DD6, 0x0DD6 }, /* SINHALA VOWEL SIGN DIGA PAA-PILLA */ - { 0x0DD8, 0x0DDF }, /* SINHALA VOWEL SIGN GAETTA-PILLA - SINHALA VOWEL SIGN GAYANUKITTA */ - { 0x0DF2, 0x0DF3 }, /* SINHALA VOWEL SIGN DIGA GAETTA-PILLA - SINHALA VOWEL SIGN DIGA GAYANUKITTA */ - { 0x0E31, 0x0E31 }, /* THAI CHARACTER MAI HAN-AKAT */ - { 0x0E34, 0x0E3A }, /* THAI CHARACTER SARA I - THAI CHARACTER PHINTHU */ - { 0x0E47, 0x0E4E }, /* THAI CHARACTER MAITAIKHU - THAI CHARACTER YAMAKKAN */ - { 0x0EB1, 0x0EB1 }, /* LAO VOWEL SIGN MAI KAN */ - { 0x0EB4, 0x0EBC }, /* LAO VOWEL SIGN I - LAO SEMIVOWEL SIGN LO */ - { 0x0EC8, 0x0ECE }, /* LAO TONE MAI EK - LAO YAMAKKAN */ - { 0x0F18, 0x0F19 }, /* TIBETAN ASTROLOGICAL SIGN -KHYUD PA - TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS */ - { 0x0F35, 0x0F35 }, /* TIBETAN MARK NGAS BZUNG NYI ZLA */ - { 0x0F37, 0x0F37 }, /* TIBETAN MARK NGAS BZUNG SGOR RTAGS */ - { 0x0F39, 0x0F39 }, /* TIBETAN MARK TSA -PHRU */ - { 0x0F3E, 0x0F3F }, /* TIBETAN SIGN YAR TSHES - TIBETAN SIGN MAR TSHES */ - { 0x0F71, 0x0F84 }, /* TIBETAN VOWEL SIGN AA - TIBETAN MARK HALANTA */ - { 0x0F86, 0x0F87 }, /* TIBETAN SIGN LCI RTAGS - TIBETAN SIGN YANG RTAGS */ - { 0x0F8D, 0x0F97 }, /* TIBETAN SUBJOINED SIGN LCE TSA CAN - TIBETAN SUBJOINED LETTER JA */ - { 0x0F99, 0x0FBC }, /* TIBETAN SUBJOINED LETTER NYA - TIBETAN SUBJOINED LETTER FIXED-FORM RA */ - { 0x0FC6, 0x0FC6 }, /* TIBETAN SYMBOL PADMA GDAN */ - { 0x102B, 0x103E }, /* MYANMAR VOWEL SIGN TALL AA - MYANMAR CONSONANT SIGN MEDIAL HA */ - { 0x1056, 0x1059 }, /* MYANMAR VOWEL SIGN VOCALIC R - MYANMAR VOWEL SIGN VOCALIC LL */ - { 0x105E, 0x1060 }, /* MYANMAR CONSONANT SIGN MON MEDIAL NA - MYANMAR CONSONANT SIGN MON MEDIAL LA */ - { 0x1062, 0x1064 }, /* MYANMAR VOWEL SIGN SGAW KAREN EU - MYANMAR TONE MARK SGAW KAREN KE PHO */ - { 0x1067, 0x106D }, /* MYANMAR VOWEL SIGN WESTERN PWO KAREN EU - MYANMAR SIGN WESTERN PWO KAREN TONE-5 */ - { 0x1071, 0x1074 }, /* MYANMAR VOWEL SIGN GEBA KAREN I - MYANMAR VOWEL SIGN KAYAH EE */ - { 0x1082, 0x108D }, /* MYANMAR CONSONANT SIGN SHAN MEDIAL WA - MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE */ - { 0x108F, 0x108F }, /* MYANMAR SIGN RUMAI PALAUNG TONE-5 */ - { 0x109A, 0x109D }, /* MYANMAR SIGN KHAMTI TONE-1 - MYANMAR VOWEL SIGN AITON AI */ - { 0x135D, 0x135F }, /* ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK - ETHIOPIC COMBINING GEMINATION MARK */ - { 0x1712, 0x1715 }, /* TAGALOG VOWEL SIGN I - TAGALOG SIGN PAMUDPOD */ - { 0x1732, 0x1734 }, /* HANUNOO VOWEL SIGN I - HANUNOO SIGN PAMUDPOD */ - { 0x1752, 0x1753 }, /* BUHID VOWEL SIGN I - BUHID VOWEL SIGN U */ - { 0x1772, 0x1773 }, /* TAGBANWA VOWEL SIGN I - TAGBANWA VOWEL SIGN U */ - { 0x17B4, 0x17D3 }, /* KHMER VOWEL INHERENT AQ - KHMER SIGN BATHAMASAT */ - { 0x17DD, 0x17DD }, /* KHMER SIGN ATTHACAN */ - { 0x180B, 0x180F }, /* MONGOLIAN FREE VARIATION SELECTOR ONE - MONGOLIAN FREE VARIATION SELECTOR FOUR */ - { 0x1885, 0x1886 }, /* MONGOLIAN LETTER ALI GALI BALUDA - MONGOLIAN LETTER ALI GALI THREE BALUDA */ - { 0x18A9, 0x18A9 }, /* MONGOLIAN LETTER ALI GALI DAGALGA */ - { 0x1920, 0x192B }, /* LIMBU VOWEL SIGN A - LIMBU SUBJOINED LETTER WA */ - { 0x1930, 0x193B }, /* LIMBU SMALL LETTER KA - LIMBU SIGN SA-I */ - { 0x1A17, 0x1A1B }, /* BUGINESE VOWEL SIGN I - BUGINESE VOWEL SIGN AE */ - { 0x1A55, 0x1A5E }, /* TAI THAM CONSONANT SIGN MEDIAL RA - TAI THAM CONSONANT SIGN SA */ - { 0x1A60, 0x1A7C }, /* TAI THAM SIGN SAKOT - TAI THAM SIGN KHUEN-LUE KARAN */ - { 0x1A7F, 0x1A7F }, /* TAI THAM COMBINING CRYPTOGRAMMIC DOT */ - { 0x1AB0, 0x1ACE }, /* COMBINING DOUBLED CIRCUMFLEX ACCENT - COMBINING LATIN SMALL LETTER INSULAR T */ - { 0x1B00, 0x1B04 }, /* BALINESE SIGN ULU RICEM - BALINESE SIGN BISAH */ - { 0x1B34, 0x1B44 }, /* BALINESE SIGN REREKAN - BALINESE ADEG ADEG */ - { 0x1B6B, 0x1B73 }, /* BALINESE MUSICAL SYMBOL COMBINING TEGEH - BALINESE MUSICAL SYMBOL COMBINING GONG */ - { 0x1B80, 0x1B82 }, /* SUNDANESE SIGN PANYECEK - SUNDANESE SIGN PANGWISAD */ - { 0x1BA1, 0x1BAD }, /* SUNDANESE CONSONANT SIGN PAMINGKAL - SUNDANESE CONSONANT SIGN PASANGAN WA */ - { 0x1BE6, 0x1BF3 }, /* BATAK SIGN TOMPI - BATAK PANONGONAN */ - { 0x1C24, 0x1C37 }, /* LEPCHA SUBJOINED LETTER YA - LEPCHA SIGN NUKTA */ - { 0x1CD0, 0x1CD2 }, /* VEDIC TONE KARSHANA - VEDIC TONE PRENKHA */ - { 0x1CD4, 0x1CE8 }, /* VEDIC SIGN YAJURVEDIC MIDLINE SVARITA - VEDIC SIGN VISARGA ANUDATTA WITH TAIL */ - { 0x1CED, 0x1CED }, /* VEDIC SIGN TIRYAK */ - { 0x1CF4, 0x1CF4 }, /* VEDIC TONE CANDRA ABOVE */ - { 0x1CF7, 0x1CF9 }, /* VEDIC SIGN ATIKRAMA - VEDIC TONE DOUBLE RING ABOVE */ - { 0x1DC0, 0x1DFF }, /* COMBINING DOTTED GRAVE ACCENT - COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW */ - { 0x200B, 0x200F }, /* ZERO WIDTH SPACE - RIGHT-TO-LEFT MARK */ - { 0x202A, 0x202E }, /* LEFT-TO-RIGHT EMBEDDING - RIGHT-TO-LEFT OVERRIDE */ - { 0x2060, 0x2064 }, /* WORD JOINER - INVISIBLE PLUS */ - { 0x2066, 0x206F }, /* LEFT-TO-RIGHT ISOLATE - NOMINAL DIGIT SHAPES */ - { 0x20D0, 0x20F0 }, /* COMBINING LEFT HARPOON ABOVE - COMBINING ASTERISK ABOVE */ - { 0x2640, 0x2640 }, /* FEMALE SIGN */ - { 0x2642, 0x2642 }, /* MALE SIGN */ - { 0x26A7, 0x26A7 }, /* MALE WITH STROKE AND MALE AND FEMALE SIGN */ - { 0x2CEF, 0x2CF1 }, /* COPTIC COMBINING NI ABOVE - COPTIC COMBINING SPIRITUS LENIS */ - { 0x2D7F, 0x2D7F }, /* TIFINAGH CONSONANT JOINER */ - { 0x2DE0, 0x2DFF }, /* COMBINING CYRILLIC LETTER BE - COMBINING CYRILLIC LETTER IOTIFIED BIG YUS */ - { 0x302A, 0x302F }, /* IDEOGRAPHIC LEVEL TONE MARK - HANGUL DOUBLE DOT TONE MARK */ - { 0x3099, 0x309A }, /* COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK - COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK */ - { 0xA66F, 0xA672 }, /* COMBINING CYRILLIC VZMET - COMBINING CYRILLIC THOUSAND MILLIONS SIGN */ - { 0xA674, 0xA67D }, /* COMBINING CYRILLIC LETTER UKRAINIAN IE - COMBINING CYRILLIC PAYEROK */ - { 0xA69E, 0xA69F }, /* COMBINING CYRILLIC LETTER EF - COMBINING CYRILLIC LETTER IOTIFIED E */ - { 0xA6F0, 0xA6F1 }, /* BAMUM COMBINING MARK KOQNDON - BAMUM COMBINING MARK TUKWENTIS */ - { 0xA802, 0xA802 }, /* SYLOTI NAGRI SIGN DVISVARA */ - { 0xA806, 0xA806 }, /* SYLOTI NAGRI SIGN HASANTA */ - { 0xA80B, 0xA80B }, /* SYLOTI NAGRI SIGN ANUSVARA */ - { 0xA823, 0xA827 }, /* SYLOTI NAGRI VOWEL SIGN A - SYLOTI NAGRI VOWEL SIGN OO */ - { 0xA82C, 0xA82C }, /* SYLOTI NAGRI SIGN ALTERNATE HASANTA */ - { 0xA880, 0xA881 }, /* SAURASHTRA SIGN ANUSVARA - SAURASHTRA SIGN VISARGA */ - { 0xA8B4, 0xA8C5 }, /* SAURASHTRA CONSONANT SIGN HAARU - SAURASHTRA SIGN CANDRABINDU */ - { 0xA8E0, 0xA8F1 }, /* COMBINING DEVANAGARI DIGIT ZERO - COMBINING DEVANAGARI SIGN AVAGRAHA */ - { 0xA8FF, 0xA8FF }, /* DEVANAGARI VOWEL SIGN AY */ - { 0xA926, 0xA92D }, /* KAYAH LI VOWEL UE - KAYAH LI TONE CALYA PLOPHU */ - { 0xA947, 0xA953 }, /* REJANG VOWEL SIGN I - REJANG VIRAMA */ - { 0xA980, 0xA983 }, /* JAVANESE SIGN PANYANGGA - JAVANESE SIGN WIGNYAN */ - { 0xA9B3, 0xA9C0 }, /* JAVANESE SIGN CECAK TELU - JAVANESE PANGKON */ - { 0xA9E5, 0xA9E5 }, /* MYANMAR SIGN SHAN SAW */ - { 0xAA29, 0xAA36 }, /* CHAM VOWEL SIGN AA - CHAM CONSONANT SIGN WA */ - { 0xAA43, 0xAA43 }, /* CHAM CONSONANT SIGN FINAL NG */ - { 0xAA4C, 0xAA4D }, /* CHAM CONSONANT SIGN FINAL M - CHAM CONSONANT SIGN FINAL H */ - { 0xAA7B, 0xAA7D }, /* MYANMAR SIGN PAO KAREN TONE - MYANMAR SIGN TAI LAING TONE-5 */ - { 0xAAB0, 0xAAB0 }, /* TAI VIET MAI KANG */ - { 0xAAB2, 0xAAB4 }, /* TAI VIET VOWEL I - TAI VIET VOWEL U */ - { 0xAAB7, 0xAAB8 }, /* TAI VIET MAI KHIT - TAI VIET VOWEL IA */ - { 0xAABE, 0xAABF }, /* TAI VIET VOWEL AM - TAI VIET TONE MAI EK */ - { 0xAAC1, 0xAAC1 }, /* TAI VIET TONE MAI THO */ - { 0xAAEB, 0xAAEF }, /* MEETEI MAYEK VOWEL SIGN II - MEETEI MAYEK VOWEL SIGN AAU */ - { 0xAAF5, 0xAAF6 }, /* MEETEI MAYEK VOWEL SIGN VISARGA - MEETEI MAYEK VIRAMA */ - { 0xABE3, 0xABEA }, /* MEETEI MAYEK VOWEL SIGN ONAP - MEETEI MAYEK VOWEL SIGN NUNG */ - { 0xABEC, 0xABED }, /* MEETEI MAYEK LUM IYEK - MEETEI MAYEK APUN IYEK */ - { 0xFB1E, 0xFB1E }, /* HEBREW POINT JUDEO-SPANISH VARIKA */ - { 0xFE00, 0xFE0F }, /* VARIATION SELECTOR-1 - VARIATION SELECTOR-16 */ - { 0xFE20, 0xFE2F }, /* COMBINING LIGATURE LEFT HALF - COMBINING CYRILLIC TITLO RIGHT HALF */ - { 0xFEFF, 0xFEFF }, /* ZERO WIDTH NO-BREAK SPACE */ - { 0xFFF9, 0xFFFB }, /* INTERLINEAR ANNOTATION ANCHOR - INTERLINEAR ANNOTATION TERMINATOR */ +/* Bits per BMP-bitmap chunk hosted in one non-BMP entry's `last` field. */ +#define UCS_NONBMP_BMP_BITS 8 + +/* Combined zero- and double-width ranges + * (BMP - Basic Multilingual Plane, U+0000 to U+FFFF). */ +static const struct ucs_width16 ucs_bmp_ranges[] = { + { BMP_0WIDTH(0x00AD, 0x00AD) }, /* SOFT HYPHEN */ + { BMP_0WIDTH(0x0300, 0x036F) }, /* COMBINING GRAVE ACCENT - COMBINING LATIN SMALL LETTER X */ + { BMP_0WIDTH(0x0483, 0x0489) }, /* COMBINING CYRILLIC TITLO - COMBINING CYRILLIC MILLIONS SIGN */ + { BMP_0WIDTH(0x0591, 0x05BD) }, /* HEBREW ACCENT ETNAHTA - HEBREW POINT METEG */ + { BMP_0WIDTH(0x05BF, 0x05BF) }, /* HEBREW POINT RAFE */ + { BMP_0WIDTH(0x05C1, 0x05C2) }, /* HEBREW POINT SHIN DOT - HEBREW POINT SIN DOT */ + { BMP_0WIDTH(0x05C4, 0x05C5) }, /* HEBREW MARK UPPER DOT - HEBREW MARK LOWER DOT */ + { BMP_0WIDTH(0x05C7, 0x05C7) }, /* HEBREW POINT QAMATS QATAN */ + { BMP_0WIDTH(0x0600, 0x0605) }, /* ARABIC NUMBER SIGN - ARABIC NUMBER MARK ABOVE */ + { BMP_0WIDTH(0x0610, 0x061A) }, /* ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM - ARABIC SMALL KASRA */ + { BMP_0WIDTH(0x061C, 0x061C) }, /* ARABIC LETTER MARK */ + { BMP_0WIDTH(0x064B, 0x065F) }, /* ARABIC FATHATAN - ARABIC WAVY HAMZA BELOW */ + { BMP_0WIDTH(0x0670, 0x0670) }, /* ARABIC LETTER SUPERSCRIPT ALEF */ + { BMP_0WIDTH(0x06D6, 0x06DD) }, /* ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA - ARABIC END OF AYAH */ + { BMP_0WIDTH(0x06DF, 0x06E4) }, /* ARABIC SMALL HIGH ROUNDED ZERO - ARABIC SMALL HIGH MADDA */ + { BMP_0WIDTH(0x06E7, 0x06E8) }, /* ARABIC SMALL HIGH YEH - ARABIC SMALL HIGH NOON */ + { BMP_0WIDTH(0x06EA, 0x06ED) }, /* ARABIC EMPTY CENTRE LOW STOP - ARABIC SMALL LOW MEEM */ + { BMP_0WIDTH(0x070F, 0x070F) }, /* SYRIAC ABBREVIATION MARK */ + { BMP_0WIDTH(0x0711, 0x0711) }, /* SYRIAC LETTER SUPERSCRIPT ALAPH */ + { BMP_0WIDTH(0x0730, 0x074A) }, /* SYRIAC PTHAHA ABOVE - SYRIAC BARREKH */ + { BMP_0WIDTH(0x07A6, 0x07B0) }, /* THAANA ABAFILI - THAANA SUKUN */ + { BMP_0WIDTH(0x07EB, 0x07F3) }, /* NKO COMBINING SHORT HIGH TONE - NKO COMBINING DOUBLE DOT ABOVE */ + { BMP_0WIDTH(0x07FD, 0x07FD) }, /* NKO DANTAYALAN */ + { BMP_0WIDTH(0x0816, 0x0819) }, /* SAMARITAN MARK IN - SAMARITAN MARK DAGESH */ + { BMP_0WIDTH(0x081B, 0x0823) }, /* SAMARITAN MARK EPENTHETIC YUT - SAMARITAN VOWEL SIGN A */ + { BMP_0WIDTH(0x0825, 0x0827) }, /* SAMARITAN VOWEL SIGN SHORT A - SAMARITAN VOWEL SIGN U */ + { BMP_0WIDTH(0x0829, 0x082D) }, /* SAMARITAN VOWEL SIGN LONG I - SAMARITAN MARK NEQUDAA */ + { BMP_0WIDTH(0x0859, 0x085B) }, /* MANDAIC AFFRICATION MARK - MANDAIC GEMINATION MARK */ + { BMP_0WIDTH(0x0890, 0x0891) }, /* ARABIC POUND MARK ABOVE - ARABIC PIASTRE MARK ABOVE */ + { BMP_0WIDTH(0x0897, 0x089F) }, /* ARABIC PEPET - ARABIC HALF MADDA OVER MADDA */ + { BMP_0WIDTH(0x08CA, 0x0903) }, /* ARABIC SMALL HIGH FARSI YEH - DEVANAGARI SIGN VISARGA */ + { BMP_0WIDTH(0x093A, 0x093C) }, /* DEVANAGARI VOWEL SIGN OE - DEVANAGARI SIGN NUKTA */ + { BMP_0WIDTH(0x093E, 0x094F) }, /* DEVANAGARI VOWEL SIGN AA - DEVANAGARI VOWEL SIGN AW */ + { BMP_0WIDTH(0x0951, 0x0957) }, /* DEVANAGARI STRESS SIGN UDATTA - DEVANAGARI VOWEL SIGN UUE */ + { BMP_0WIDTH(0x0962, 0x0963) }, /* DEVANAGARI VOWEL SIGN VOCALIC L - DEVANAGARI VOWEL SIGN VOCALIC LL */ + { BMP_0WIDTH(0x0981, 0x0983) }, /* BENGALI SIGN CANDRABINDU - BENGALI SIGN VISARGA */ + { BMP_0WIDTH(0x09BC, 0x09BC) }, /* BENGALI SIGN NUKTA */ + { BMP_0WIDTH(0x09BE, 0x09C4) }, /* BENGALI VOWEL SIGN AA - BENGALI VOWEL SIGN VOCALIC RR */ + { BMP_0WIDTH(0x09C7, 0x09C8) }, /* BENGALI VOWEL SIGN E - BENGALI VOWEL SIGN AI */ + { BMP_0WIDTH(0x09CB, 0x09CD) }, /* BENGALI VOWEL SIGN O - BENGALI SIGN VIRAMA */ + { BMP_0WIDTH(0x09D7, 0x09D7) }, /* BENGALI AU LENGTH MARK */ + { BMP_0WIDTH(0x09E2, 0x09E3) }, /* BENGALI VOWEL SIGN VOCALIC L - BENGALI VOWEL SIGN VOCALIC LL */ + { BMP_0WIDTH(0x09FE, 0x09FE) }, /* BENGALI SANDHI MARK */ + { BMP_0WIDTH(0x0A01, 0x0A03) }, /* GURMUKHI SIGN ADAK BINDI - GURMUKHI SIGN VISARGA */ + { BMP_0WIDTH(0x0A3C, 0x0A3C) }, /* GURMUKHI SIGN NUKTA */ + { BMP_0WIDTH(0x0A3E, 0x0A42) }, /* GURMUKHI VOWEL SIGN AA - GURMUKHI VOWEL SIGN UU */ + { BMP_0WIDTH(0x0A47, 0x0A48) }, /* GURMUKHI VOWEL SIGN EE - GURMUKHI VOWEL SIGN AI */ + { BMP_0WIDTH(0x0A4B, 0x0A4D) }, /* GURMUKHI VOWEL SIGN OO - GURMUKHI SIGN VIRAMA */ + { BMP_0WIDTH(0x0A51, 0x0A51) }, /* GURMUKHI SIGN UDAAT */ + { BMP_0WIDTH(0x0A70, 0x0A71) }, /* GURMUKHI TIPPI - GURMUKHI ADDAK */ + { BMP_0WIDTH(0x0A75, 0x0A75) }, /* GURMUKHI SIGN YAKASH */ + { BMP_0WIDTH(0x0A81, 0x0A83) }, /* GUJARATI SIGN CANDRABINDU - GUJARATI SIGN VISARGA */ + { BMP_0WIDTH(0x0ABC, 0x0ABC) }, /* GUJARATI SIGN NUKTA */ + { BMP_0WIDTH(0x0ABE, 0x0AC5) }, /* GUJARATI VOWEL SIGN AA - GUJARATI VOWEL SIGN CANDRA E */ + { BMP_0WIDTH(0x0AC7, 0x0AC9) }, /* GUJARATI VOWEL SIGN E - GUJARATI VOWEL SIGN CANDRA O */ + { BMP_0WIDTH(0x0ACB, 0x0ACD) }, /* GUJARATI VOWEL SIGN O - GUJARATI SIGN VIRAMA */ + { BMP_0WIDTH(0x0AE2, 0x0AE3) }, /* GUJARATI VOWEL SIGN VOCALIC L - GUJARATI VOWEL SIGN VOCALIC LL */ + { BMP_0WIDTH(0x0AFA, 0x0AFF) }, /* GUJARATI SIGN SUKUN - GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE */ + { BMP_0WIDTH(0x0B01, 0x0B03) }, /* ORIYA SIGN CANDRABINDU - ORIYA SIGN VISARGA */ + { BMP_0WIDTH(0x0B3C, 0x0B3C) }, /* ORIYA SIGN NUKTA */ + { BMP_0WIDTH(0x0B3E, 0x0B44) }, /* ORIYA VOWEL SIGN AA - ORIYA VOWEL SIGN VOCALIC RR */ + { BMP_0WIDTH(0x0B47, 0x0B48) }, /* ORIYA VOWEL SIGN E - ORIYA VOWEL SIGN AI */ + { BMP_0WIDTH(0x0B4B, 0x0B4D) }, /* ORIYA VOWEL SIGN O - ORIYA SIGN VIRAMA */ + { BMP_0WIDTH(0x0B55, 0x0B57) }, /* ORIYA SIGN OVERLINE - ORIYA AU LENGTH MARK */ + { BMP_0WIDTH(0x0B62, 0x0B63) }, /* ORIYA VOWEL SIGN VOCALIC L - ORIYA VOWEL SIGN VOCALIC LL */ + { BMP_0WIDTH(0x0B82, 0x0B82) }, /* TAMIL SIGN ANUSVARA */ + { BMP_0WIDTH(0x0BBE, 0x0BC2) }, /* TAMIL VOWEL SIGN AA - TAMIL VOWEL SIGN UU */ + { BMP_0WIDTH(0x0BC6, 0x0BC8) }, /* TAMIL VOWEL SIGN E - TAMIL VOWEL SIGN AI */ + { BMP_0WIDTH(0x0BCA, 0x0BCD) }, /* TAMIL VOWEL SIGN O - TAMIL SIGN VIRAMA */ + { BMP_0WIDTH(0x0BD7, 0x0BD7) }, /* TAMIL AU LENGTH MARK */ + { BMP_0WIDTH(0x0C00, 0x0C04) }, /* TELUGU SIGN COMBINING CANDRABINDU ABOVE - TELUGU SIGN COMBINING ANUSVARA ABOVE */ + { BMP_0WIDTH(0x0C3C, 0x0C3C) }, /* TELUGU SIGN NUKTA */ + { BMP_0WIDTH(0x0C3E, 0x0C44) }, /* TELUGU VOWEL SIGN AA - TELUGU VOWEL SIGN VOCALIC RR */ + { BMP_0WIDTH(0x0C46, 0x0C48) }, /* TELUGU VOWEL SIGN E - TELUGU VOWEL SIGN AI */ + { BMP_0WIDTH(0x0C4A, 0x0C4D) }, /* TELUGU VOWEL SIGN O - TELUGU SIGN VIRAMA */ + { BMP_0WIDTH(0x0C55, 0x0C56) }, /* TELUGU LENGTH MARK - TELUGU AI LENGTH MARK */ + { BMP_0WIDTH(0x0C62, 0x0C63) }, /* TELUGU VOWEL SIGN VOCALIC L - TELUGU VOWEL SIGN VOCALIC LL */ + { BMP_0WIDTH(0x0C81, 0x0C83) }, /* KANNADA SIGN CANDRABINDU - KANNADA SIGN VISARGA */ + { BMP_0WIDTH(0x0CBC, 0x0CBC) }, /* KANNADA SIGN NUKTA */ + { BMP_0WIDTH(0x0CBE, 0x0CC4) }, /* KANNADA VOWEL SIGN AA - KANNADA VOWEL SIGN VOCALIC RR */ + { BMP_0WIDTH(0x0CC6, 0x0CC8) }, /* KANNADA VOWEL SIGN E - KANNADA VOWEL SIGN AI */ + { BMP_0WIDTH(0x0CCA, 0x0CCD) }, /* KANNADA VOWEL SIGN O - KANNADA SIGN VIRAMA */ + { BMP_0WIDTH(0x0CD5, 0x0CD6) }, /* KANNADA LENGTH MARK - KANNADA AI LENGTH MARK */ + { BMP_0WIDTH(0x0CE2, 0x0CE3) }, /* KANNADA VOWEL SIGN VOCALIC L - KANNADA VOWEL SIGN VOCALIC LL */ + { BMP_0WIDTH(0x0CF3, 0x0CF3) }, /* KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT */ + { BMP_0WIDTH(0x0D00, 0x0D03) }, /* MALAYALAM SIGN COMBINING ANUSVARA ABOVE - MALAYALAM SIGN VISARGA */ + { BMP_0WIDTH(0x0D3B, 0x0D3C) }, /* MALAYALAM SIGN VERTICAL BAR VIRAMA - MALAYALAM SIGN CIRCULAR VIRAMA */ + { BMP_0WIDTH(0x0D3E, 0x0D44) }, /* MALAYALAM VOWEL SIGN AA - MALAYALAM VOWEL SIGN VOCALIC RR */ + { BMP_0WIDTH(0x0D46, 0x0D48) }, /* MALAYALAM VOWEL SIGN E - MALAYALAM VOWEL SIGN AI */ + { BMP_0WIDTH(0x0D4A, 0x0D4D) }, /* MALAYALAM VOWEL SIGN O - MALAYALAM SIGN VIRAMA */ + { BMP_0WIDTH(0x0D57, 0x0D57) }, /* MALAYALAM AU LENGTH MARK */ + { BMP_0WIDTH(0x0D62, 0x0D63) }, /* MALAYALAM VOWEL SIGN VOCALIC L - MALAYALAM VOWEL SIGN VOCALIC LL */ + { BMP_0WIDTH(0x0D81, 0x0D83) }, /* SINHALA SIGN CANDRABINDU - SINHALA SIGN VISARGAYA */ + { BMP_0WIDTH(0x0DCA, 0x0DCA) }, /* SINHALA SIGN AL-LAKUNA */ + { BMP_0WIDTH(0x0DCF, 0x0DD4) }, /* SINHALA VOWEL SIGN AELA-PILLA - SINHALA VOWEL SIGN KETTI PAA-PILLA */ + { BMP_0WIDTH(0x0DD6, 0x0DD6) }, /* SINHALA VOWEL SIGN DIGA PAA-PILLA */ + { BMP_0WIDTH(0x0DD8, 0x0DDF) }, /* SINHALA VOWEL SIGN GAETTA-PILLA - SINHALA VOWEL SIGN GAYANUKITTA */ + { BMP_0WIDTH(0x0DF2, 0x0DF3) }, /* SINHALA VOWEL SIGN DIGA GAETTA-PILLA - SINHALA VOWEL SIGN DIGA GAYANUKITTA */ + { BMP_0WIDTH(0x0E31, 0x0E31) }, /* THAI CHARACTER MAI HAN-AKAT */ + { BMP_0WIDTH(0x0E34, 0x0E3A) }, /* THAI CHARACTER SARA I - THAI CHARACTER PHINTHU */ + { BMP_0WIDTH(0x0E47, 0x0E4E) }, /* THAI CHARACTER MAITAIKHU - THAI CHARACTER YAMAKKAN */ + { BMP_0WIDTH(0x0EB1, 0x0EB1) }, /* LAO VOWEL SIGN MAI KAN */ + { BMP_0WIDTH(0x0EB4, 0x0EBC) }, /* LAO VOWEL SIGN I - LAO SEMIVOWEL SIGN LO */ + { BMP_0WIDTH(0x0EC8, 0x0ECE) }, /* LAO TONE MAI EK - LAO YAMAKKAN */ + { BMP_0WIDTH(0x0F18, 0x0F19) }, /* TIBETAN ASTROLOGICAL SIGN -KHYUD PA - TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS */ + { BMP_0WIDTH(0x0F35, 0x0F35) }, /* TIBETAN MARK NGAS BZUNG NYI ZLA */ + { BMP_0WIDTH(0x0F37, 0x0F37) }, /* TIBETAN MARK NGAS BZUNG SGOR RTAGS */ + { BMP_0WIDTH(0x0F39, 0x0F39) }, /* TIBETAN MARK TSA -PHRU */ + { BMP_0WIDTH(0x0F3E, 0x0F3F) }, /* TIBETAN SIGN YAR TSHES - TIBETAN SIGN MAR TSHES */ + { BMP_0WIDTH(0x0F71, 0x0F84) }, /* TIBETAN VOWEL SIGN AA - TIBETAN MARK HALANTA */ + { BMP_0WIDTH(0x0F86, 0x0F87) }, /* TIBETAN SIGN LCI RTAGS - TIBETAN SIGN YANG RTAGS */ + { BMP_0WIDTH(0x0F8D, 0x0F97) }, /* TIBETAN SUBJOINED SIGN LCE TSA CAN - TIBETAN SUBJOINED LETTER JA */ + { BMP_0WIDTH(0x0F99, 0x0FBC) }, /* TIBETAN SUBJOINED LETTER NYA - TIBETAN SUBJOINED LETTER FIXED-FORM RA */ + { BMP_0WIDTH(0x0FC6, 0x0FC6) }, /* TIBETAN SYMBOL PADMA GDAN */ + { BMP_0WIDTH(0x102B, 0x103E) }, /* MYANMAR VOWEL SIGN TALL AA - MYANMAR CONSONANT SIGN MEDIAL HA */ + { BMP_0WIDTH(0x1056, 0x1059) }, /* MYANMAR VOWEL SIGN VOCALIC R - MYANMAR VOWEL SIGN VOCALIC LL */ + { BMP_0WIDTH(0x105E, 0x1060) }, /* MYANMAR CONSONANT SIGN MON MEDIAL NA - MYANMAR CONSONANT SIGN MON MEDIAL LA */ + { BMP_0WIDTH(0x1062, 0x1064) }, /* MYANMAR VOWEL SIGN SGAW KAREN EU - MYANMAR TONE MARK SGAW KAREN KE PHO */ + { BMP_0WIDTH(0x1067, 0x106D) }, /* MYANMAR VOWEL SIGN WESTERN PWO KAREN EU - MYANMAR SIGN WESTERN PWO KAREN TONE-5 */ + { BMP_0WIDTH(0x1071, 0x1074) }, /* MYANMAR VOWEL SIGN GEBA KAREN I - MYANMAR VOWEL SIGN KAYAH EE */ + { BMP_0WIDTH(0x1082, 0x108D) }, /* MYANMAR CONSONANT SIGN SHAN MEDIAL WA - MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE */ + { BMP_0WIDTH(0x108F, 0x108F) }, /* MYANMAR SIGN RUMAI PALAUNG TONE-5 */ + { BMP_0WIDTH(0x109A, 0x109D) }, /* MYANMAR SIGN KHAMTI TONE-1 - MYANMAR VOWEL SIGN AITON AI */ + { BMP_2WIDTH(0x1100, 0x115F) }, /* HANGUL CHOSEONG KIYEOK - HANGUL CHOSEONG FILLER */ + { BMP_0WIDTH(0x135D, 0x135F) }, /* ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK - ETHIOPIC COMBINING GEMINATION MARK */ + { BMP_0WIDTH(0x1712, 0x1715) }, /* TAGALOG VOWEL SIGN I - TAGALOG SIGN PAMUDPOD */ + { BMP_0WIDTH(0x1732, 0x1734) }, /* HANUNOO VOWEL SIGN I - HANUNOO SIGN PAMUDPOD */ + { BMP_0WIDTH(0x1752, 0x1753) }, /* BUHID VOWEL SIGN I - BUHID VOWEL SIGN U */ + { BMP_0WIDTH(0x1772, 0x1773) }, /* TAGBANWA VOWEL SIGN I - TAGBANWA VOWEL SIGN U */ + { BMP_0WIDTH(0x17B4, 0x17D3) }, /* KHMER VOWEL INHERENT AQ - KHMER SIGN BATHAMASAT */ + { BMP_0WIDTH(0x17DD, 0x17DD) }, /* KHMER SIGN ATTHACAN */ + { BMP_0WIDTH(0x180B, 0x180F) }, /* MONGOLIAN FREE VARIATION SELECTOR ONE - MONGOLIAN FREE VARIATION SELECTOR FOUR */ + { BMP_0WIDTH(0x1885, 0x1886) }, /* MONGOLIAN LETTER ALI GALI BALUDA - MONGOLIAN LETTER ALI GALI THREE BALUDA */ + { BMP_0WIDTH(0x18A9, 0x18A9) }, /* MONGOLIAN LETTER ALI GALI DAGALGA */ + { BMP_0WIDTH(0x1920, 0x192B) }, /* LIMBU VOWEL SIGN A - LIMBU SUBJOINED LETTER WA */ + { BMP_0WIDTH(0x1930, 0x193B) }, /* LIMBU SMALL LETTER KA - LIMBU SIGN SA-I */ + { BMP_0WIDTH(0x1A17, 0x1A1B) }, /* BUGINESE VOWEL SIGN I - BUGINESE VOWEL SIGN AE */ + { BMP_0WIDTH(0x1A55, 0x1A5E) }, /* TAI THAM CONSONANT SIGN MEDIAL RA - TAI THAM CONSONANT SIGN SA */ + { BMP_0WIDTH(0x1A60, 0x1A7C) }, /* TAI THAM SIGN SAKOT - TAI THAM SIGN KHUEN-LUE KARAN */ + { BMP_0WIDTH(0x1A7F, 0x1A7F) }, /* TAI THAM COMBINING CRYPTOGRAMMIC DOT */ + { BMP_0WIDTH(0x1AB0, 0x1ACE) }, /* COMBINING DOUBLED CIRCUMFLEX ACCENT - COMBINING LATIN SMALL LETTER INSULAR T */ + { BMP_0WIDTH(0x1B00, 0x1B04) }, /* BALINESE SIGN ULU RICEM - BALINESE SIGN BISAH */ + { BMP_0WIDTH(0x1B34, 0x1B44) }, /* BALINESE SIGN REREKAN - BALINESE ADEG ADEG */ + { BMP_0WIDTH(0x1B6B, 0x1B73) }, /* BALINESE MUSICAL SYMBOL COMBINING TEGEH - BALINESE MUSICAL SYMBOL COMBINING GONG */ + { BMP_0WIDTH(0x1B80, 0x1B82) }, /* SUNDANESE SIGN PANYECEK - SUNDANESE SIGN PANGWISAD */ + { BMP_0WIDTH(0x1BA1, 0x1BAD) }, /* SUNDANESE CONSONANT SIGN PAMINGKAL - SUNDANESE CONSONANT SIGN PASANGAN WA */ + { BMP_0WIDTH(0x1BE6, 0x1BF3) }, /* BATAK SIGN TOMPI - BATAK PANONGONAN */ + { BMP_0WIDTH(0x1C24, 0x1C37) }, /* LEPCHA SUBJOINED LETTER YA - LEPCHA SIGN NUKTA */ + { BMP_0WIDTH(0x1CD0, 0x1CD2) }, /* VEDIC TONE KARSHANA - VEDIC TONE PRENKHA */ + { BMP_0WIDTH(0x1CD4, 0x1CE8) }, /* VEDIC SIGN YAJURVEDIC MIDLINE SVARITA - VEDIC SIGN VISARGA ANUDATTA WITH TAIL */ + { BMP_0WIDTH(0x1CED, 0x1CED) }, /* VEDIC SIGN TIRYAK */ + { BMP_0WIDTH(0x1CF4, 0x1CF4) }, /* VEDIC TONE CANDRA ABOVE */ + { BMP_0WIDTH(0x1CF7, 0x1CF9) }, /* VEDIC SIGN ATIKRAMA - VEDIC TONE DOUBLE RING ABOVE */ + { BMP_0WIDTH(0x1DC0, 0x1DFF) }, /* COMBINING DOTTED GRAVE ACCENT - COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW */ + { BMP_0WIDTH(0x200B, 0x200F) }, /* ZERO WIDTH SPACE - RIGHT-TO-LEFT MARK */ + { BMP_0WIDTH(0x202A, 0x202E) }, /* LEFT-TO-RIGHT EMBEDDING - RIGHT-TO-LEFT OVERRIDE */ + { BMP_0WIDTH(0x2060, 0x2064) }, /* WORD JOINER - INVISIBLE PLUS */ + { BMP_0WIDTH(0x2066, 0x206F) }, /* LEFT-TO-RIGHT ISOLATE - NOMINAL DIGIT SHAPES */ + { BMP_0WIDTH(0x20D0, 0x20F0) }, /* COMBINING LEFT HARPOON ABOVE - COMBINING ASTERISK ABOVE */ + { BMP_2WIDTH(0x231A, 0x231B) }, /* WATCH - HOURGLASS */ + { BMP_2WIDTH(0x2329, 0x232A) }, /* LEFT-POINTING ANGLE BRACKET - RIGHT-POINTING ANGLE BRACKET */ + { BMP_2WIDTH(0x23E9, 0x23EC) }, /* BLACK RIGHT-POINTING DOUBLE TRIANGLE - BLACK DOWN-POINTING DOUBLE TRIANGLE */ + { BMP_2WIDTH(0x23F0, 0x23F0) }, /* ALARM CLOCK */ + { BMP_2WIDTH(0x23F3, 0x23F3) }, /* HOURGLASS WITH FLOWING SAND */ + { BMP_2WIDTH(0x25FD, 0x25FE) }, /* WHITE MEDIUM SMALL SQUARE - BLACK MEDIUM SMALL SQUARE */ + { BMP_2WIDTH(0x2614, 0x2615) }, /* UMBRELLA WITH RAIN DROPS - HOT BEVERAGE */ + { BMP_2WIDTH(0x2630, 0x2637) }, /* TRIGRAM FOR HEAVEN - TRIGRAM FOR EARTH */ + { BMP_0WIDTH(0x2640, 0x2640) }, /* FEMALE SIGN */ + { BMP_0WIDTH(0x2642, 0x2642) }, /* MALE SIGN */ + { BMP_2WIDTH(0x2648, 0x2653) }, /* ARIES - PISCES */ + { BMP_2WIDTH(0x267F, 0x267F) }, /* WHEELCHAIR SYMBOL */ + { BMP_2WIDTH(0x268A, 0x268F) }, /* MONOGRAM FOR YANG - DIGRAM FOR GREATER YIN */ + { BMP_2WIDTH(0x2693, 0x2693) }, /* ANCHOR */ + { BMP_2WIDTH(0x26A1, 0x26A1) }, /* HIGH VOLTAGE SIGN */ + { BMP_0WIDTH(0x26A7, 0x26A7) }, /* MALE WITH STROKE AND MALE AND FEMALE SIGN */ + { BMP_2WIDTH(0x26AA, 0x26AB) }, /* MEDIUM WHITE CIRCLE - MEDIUM BLACK CIRCLE */ + { BMP_2WIDTH(0x26BD, 0x26BE) }, /* SOCCER BALL - BASEBALL */ + { BMP_2WIDTH(0x26C4, 0x26C5) }, /* SNOWMAN WITHOUT SNOW - SUN BEHIND CLOUD */ + { BMP_2WIDTH(0x26CE, 0x26CE) }, /* OPHIUCHUS */ + { BMP_2WIDTH(0x26D4, 0x26D4) }, /* NO ENTRY */ + { BMP_2WIDTH(0x26EA, 0x26EA) }, /* CHURCH */ + { BMP_2WIDTH(0x26F2, 0x26F3) }, /* FOUNTAIN - FLAG IN HOLE */ + { BMP_2WIDTH(0x26F5, 0x26F5) }, /* SAILBOAT */ + { BMP_2WIDTH(0x26FA, 0x26FA) }, /* TENT */ + { BMP_2WIDTH(0x26FD, 0x26FD) }, /* FUEL PUMP */ + { BMP_2WIDTH(0x2705, 0x2705) }, /* WHITE HEAVY CHECK MARK */ + { BMP_2WIDTH(0x270A, 0x270B) }, /* RAISED FIST - RAISED HAND */ + { BMP_2WIDTH(0x2728, 0x2728) }, /* SPARKLES */ + { BMP_2WIDTH(0x274C, 0x274C) }, /* CROSS MARK */ + { BMP_2WIDTH(0x274E, 0x274E) }, /* NEGATIVE SQUARED CROSS MARK */ + { BMP_2WIDTH(0x2753, 0x2755) }, /* BLACK QUESTION MARK ORNAMENT - WHITE EXCLAMATION MARK ORNAMENT */ + { BMP_2WIDTH(0x2757, 0x2757) }, /* HEAVY EXCLAMATION MARK SYMBOL */ + { BMP_2WIDTH(0x2795, 0x2797) }, /* HEAVY PLUS SIGN - HEAVY DIVISION SIGN */ + { BMP_2WIDTH(0x27B0, 0x27B0) }, /* CURLY LOOP */ + { BMP_2WIDTH(0x27BF, 0x27BF) }, /* DOUBLE CURLY LOOP */ + { BMP_2WIDTH(0x2B1B, 0x2B1C) }, /* BLACK LARGE SQUARE - WHITE LARGE SQUARE */ + { BMP_2WIDTH(0x2B50, 0x2B50) }, /* WHITE MEDIUM STAR */ + { BMP_2WIDTH(0x2B55, 0x2B55) }, /* HEAVY LARGE CIRCLE */ + { BMP_0WIDTH(0x2CEF, 0x2CF1) }, /* COPTIC COMBINING NI ABOVE - COPTIC COMBINING SPIRITUS LENIS */ + { BMP_0WIDTH(0x2D7F, 0x2D7F) }, /* TIFINAGH CONSONANT JOINER */ + { BMP_0WIDTH(0x2DE0, 0x2DFF) }, /* COMBINING CYRILLIC LETTER BE - COMBINING CYRILLIC LETTER IOTIFIED BIG YUS */ + { BMP_2WIDTH(0x2E80, 0x2E99) }, /* CJK RADICAL REPEAT - CJK RADICAL RAP */ + { BMP_2WIDTH(0x2E9B, 0x2EF3) }, /* CJK RADICAL CHOKE - CJK RADICAL C-SIMPLIFIED TURTLE */ + { BMP_2WIDTH(0x2F00, 0x2FD5) }, /* KANGXI RADICAL ONE - KANGXI RADICAL FLUTE */ + { BMP_2WIDTH(0x2FF0, 0x3029) }, /* IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT - HANGZHOU NUMERAL NINE */ + { BMP_0WIDTH(0x302A, 0x302F) }, /* IDEOGRAPHIC LEVEL TONE MARK - HANGUL DOUBLE DOT TONE MARK */ + { BMP_2WIDTH(0x3030, 0x303E) }, /* WAVY DASH - IDEOGRAPHIC VARIATION INDICATOR */ + { BMP_2WIDTH(0x3041, 0x3096) }, /* HIRAGANA LETTER SMALL A - HIRAGANA LETTER SMALL KE */ + { BMP_0WIDTH(0x3099, 0x309A) }, /* COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK - COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK */ + { BMP_2WIDTH(0x309B, 0x30FF) }, /* KATAKANA-HIRAGANA VOICED SOUND MARK - KATAKANA DIGRAPH KOTO */ + { BMP_2WIDTH(0x3105, 0x312F) }, /* BOPOMOFO LETTER B - BOPOMOFO LETTER NN */ + { BMP_2WIDTH(0x3131, 0x318E) }, /* HANGUL LETTER KIYEOK - HANGUL LETTER ARAEAE */ + { BMP_2WIDTH(0x3190, 0x31E5) }, /* IDEOGRAPHIC ANNOTATION LINKING MARK - CJK STROKE SZP */ + { BMP_2WIDTH(0x31EF, 0x321E) }, /* IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION - PARENTHESIZED KOREAN CHARACTER O HU */ + { BMP_2WIDTH(0x3220, 0x3247) }, /* PARENTHESIZED IDEOGRAPH ONE - CIRCLED IDEOGRAPH KOTO */ + { BMP_2WIDTH(0x3250, 0xA48C) }, /* PARTNERSHIP SIGN - YI SYLLABLE YYR */ + { BMP_2WIDTH(0xA490, 0xA4C6) }, /* YI RADICAL QOT - YI RADICAL KE */ + { BMP_0WIDTH(0xA66F, 0xA672) }, /* COMBINING CYRILLIC VZMET - COMBINING CYRILLIC THOUSAND MILLIONS SIGN */ + { BMP_0WIDTH(0xA674, 0xA67D) }, /* COMBINING CYRILLIC LETTER UKRAINIAN IE - COMBINING CYRILLIC PAYEROK */ + { BMP_0WIDTH(0xA69E, 0xA69F) }, /* COMBINING CYRILLIC LETTER EF - COMBINING CYRILLIC LETTER IOTIFIED E */ + { BMP_0WIDTH(0xA6F0, 0xA6F1) }, /* BAMUM COMBINING MARK KOQNDON - BAMUM COMBINING MARK TUKWENTIS */ + { BMP_0WIDTH(0xA802, 0xA802) }, /* SYLOTI NAGRI SIGN DVISVARA */ + { BMP_0WIDTH(0xA806, 0xA806) }, /* SYLOTI NAGRI SIGN HASANTA */ + { BMP_0WIDTH(0xA80B, 0xA80B) }, /* SYLOTI NAGRI SIGN ANUSVARA */ + { BMP_0WIDTH(0xA823, 0xA827) }, /* SYLOTI NAGRI VOWEL SIGN A - SYLOTI NAGRI VOWEL SIGN OO */ + { BMP_0WIDTH(0xA82C, 0xA82C) }, /* SYLOTI NAGRI SIGN ALTERNATE HASANTA */ + { BMP_0WIDTH(0xA880, 0xA881) }, /* SAURASHTRA SIGN ANUSVARA - SAURASHTRA SIGN VISARGA */ + { BMP_0WIDTH(0xA8B4, 0xA8C5) }, /* SAURASHTRA CONSONANT SIGN HAARU - SAURASHTRA SIGN CANDRABINDU */ + { BMP_0WIDTH(0xA8E0, 0xA8F1) }, /* COMBINING DEVANAGARI DIGIT ZERO - COMBINING DEVANAGARI SIGN AVAGRAHA */ + { BMP_0WIDTH(0xA8FF, 0xA8FF) }, /* DEVANAGARI VOWEL SIGN AY */ + { BMP_0WIDTH(0xA926, 0xA92D) }, /* KAYAH LI VOWEL UE - KAYAH LI TONE CALYA PLOPHU */ + { BMP_0WIDTH(0xA947, 0xA953) }, /* REJANG VOWEL SIGN I - REJANG VIRAMA */ + { BMP_2WIDTH(0xA960, 0xA97C) }, /* HANGUL CHOSEONG TIKEUT-MIEUM - HANGUL CHOSEONG SSANGYEORINHIEUH */ + { BMP_0WIDTH(0xA980, 0xA983) }, /* JAVANESE SIGN PANYANGGA - JAVANESE SIGN WIGNYAN */ + { BMP_0WIDTH(0xA9B3, 0xA9C0) }, /* JAVANESE SIGN CECAK TELU - JAVANESE PANGKON */ + { BMP_0WIDTH(0xA9E5, 0xA9E5) }, /* MYANMAR SIGN SHAN SAW */ + { BMP_0WIDTH(0xAA29, 0xAA36) }, /* CHAM VOWEL SIGN AA - CHAM CONSONANT SIGN WA */ + { BMP_0WIDTH(0xAA43, 0xAA43) }, /* CHAM CONSONANT SIGN FINAL NG */ + { BMP_0WIDTH(0xAA4C, 0xAA4D) }, /* CHAM CONSONANT SIGN FINAL M - CHAM CONSONANT SIGN FINAL H */ + { BMP_0WIDTH(0xAA7B, 0xAA7D) }, /* MYANMAR SIGN PAO KAREN TONE - MYANMAR SIGN TAI LAING TONE-5 */ + { BMP_0WIDTH(0xAAB0, 0xAAB0) }, /* TAI VIET MAI KANG */ + { BMP_0WIDTH(0xAAB2, 0xAAB4) }, /* TAI VIET VOWEL I - TAI VIET VOWEL U */ + { BMP_0WIDTH(0xAAB7, 0xAAB8) }, /* TAI VIET MAI KHIT - TAI VIET VOWEL IA */ + { BMP_0WIDTH(0xAABE, 0xAABF) }, /* TAI VIET VOWEL AM - TAI VIET TONE MAI EK */ + { BMP_0WIDTH(0xAAC1, 0xAAC1) }, /* TAI VIET TONE MAI THO */ + { BMP_0WIDTH(0xAAEB, 0xAAEF) }, /* MEETEI MAYEK VOWEL SIGN II - MEETEI MAYEK VOWEL SIGN AAU */ + { BMP_0WIDTH(0xAAF5, 0xAAF6) }, /* MEETEI MAYEK VOWEL SIGN VISARGA - MEETEI MAYEK VIRAMA */ + { BMP_0WIDTH(0xABE3, 0xABEA) }, /* MEETEI MAYEK VOWEL SIGN ONAP - MEETEI MAYEK VOWEL SIGN NUNG */ + { BMP_0WIDTH(0xABEC, 0xABED) }, /* MEETEI MAYEK LUM IYEK - MEETEI MAYEK APUN IYEK */ + { BMP_2WIDTH(0xAC00, 0xD7A3) }, /* HANGUL SYLLABLE GA - HANGUL SYLLABLE HIH */ + { BMP_2WIDTH(0xF900, 0xFAFF) }, /* U+F900 - U+FAFF */ + { BMP_0WIDTH(0xFB1E, 0xFB1E) }, /* HEBREW POINT JUDEO-SPANISH VARIKA */ + { BMP_0WIDTH(0xFE00, 0xFE0F) }, /* VARIATION SELECTOR-1 - VARIATION SELECTOR-16 */ + { BMP_2WIDTH(0xFE10, 0xFE19) }, /* PRESENTATION FORM FOR VERTICAL COMMA - PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS */ + { BMP_0WIDTH(0xFE20, 0xFE2F) }, /* COMBINING LIGATURE LEFT HALF - COMBINING CYRILLIC TITLO RIGHT HALF */ + { BMP_2WIDTH(0xFE30, 0xFE52) }, /* PRESENTATION FORM FOR VERTICAL TWO DOT LEADER - SMALL FULL STOP */ + { BMP_2WIDTH(0xFE54, 0xFE66) }, /* SMALL SEMICOLON - SMALL EQUALS SIGN */ + { BMP_2WIDTH(0xFE68, 0xFE6B) }, /* SMALL REVERSE SOLIDUS - SMALL COMMERCIAL AT */ + { BMP_0WIDTH(0xFEFF, 0xFEFF) }, /* ZERO WIDTH NO-BREAK SPACE */ + { BMP_2WIDTH(0xFF01, 0xFF60) }, /* FULLWIDTH EXCLAMATION MARK - FULLWIDTH RIGHT WHITE PARENTHESIS */ + { BMP_2WIDTH(0xFFE0, 0xFFE6) }, /* FULLWIDTH CENT SIGN - FULLWIDTH WON SIGN */ + { BMP_0WIDTH(0xFFF9, 0xFFFB) }, /* INTERLINEAR ANNOTATION ANCHOR - INTERLINEAR ANNOTATION TERMINATOR */ }; -/* Zero-width character ranges (non-BMP, U+10000 and above) */ -static const struct ucs_interval32 ucs_zero_width_non_bmp_ranges[] = { - { 0x101FD, 0x101FD }, /* PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE */ - { 0x102E0, 0x102E0 }, /* COPTIC EPACT THOUSANDS MARK */ - { 0x10376, 0x1037A }, /* COMBINING OLD PERMIC LETTER AN - COMBINING OLD PERMIC LETTER SII */ - { 0x10A01, 0x10A03 }, /* KHAROSHTHI VOWEL SIGN I - KHAROSHTHI VOWEL SIGN VOCALIC R */ - { 0x10A05, 0x10A06 }, /* KHAROSHTHI VOWEL SIGN E - KHAROSHTHI VOWEL SIGN O */ - { 0x10A0C, 0x10A0F }, /* KHAROSHTHI VOWEL LENGTH MARK - KHAROSHTHI SIGN VISARGA */ - { 0x10A38, 0x10A3A }, /* KHAROSHTHI SIGN BAR ABOVE - KHAROSHTHI SIGN DOT BELOW */ - { 0x10A3F, 0x10A3F }, /* KHAROSHTHI VIRAMA */ - { 0x10AE5, 0x10AE6 }, /* MANICHAEAN ABBREVIATION MARK ABOVE - MANICHAEAN ABBREVIATION MARK BELOW */ - { 0x10D24, 0x10D27 }, /* HANIFI ROHINGYA SIGN HARBAHAY - HANIFI ROHINGYA SIGN TASSI */ - { 0x10D69, 0x10D6D }, /* GARAY VOWEL SIGN E - GARAY CONSONANT NASALIZATION MARK */ - { 0x10EAB, 0x10EAC }, /* YEZIDI COMBINING HAMZA MARK - YEZIDI COMBINING MADDA MARK */ - { 0x10EFC, 0x10EFF }, /* ARABIC COMBINING ALEF OVERLAY - ARABIC SMALL LOW WORD MADDA */ - { 0x10F46, 0x10F50 }, /* SOGDIAN COMBINING DOT BELOW - SOGDIAN COMBINING STROKE BELOW */ - { 0x10F82, 0x10F85 }, /* OLD UYGHUR COMBINING DOT ABOVE - OLD UYGHUR COMBINING TWO DOTS BELOW */ - { 0x11000, 0x11002 }, /* BRAHMI SIGN CANDRABINDU - BRAHMI SIGN VISARGA */ - { 0x11038, 0x11046 }, /* BRAHMI VOWEL SIGN AA - BRAHMI VIRAMA */ - { 0x11070, 0x11070 }, /* BRAHMI SIGN OLD TAMIL VIRAMA */ - { 0x11073, 0x11074 }, /* BRAHMI VOWEL SIGN OLD TAMIL SHORT E - BRAHMI VOWEL SIGN OLD TAMIL SHORT O */ - { 0x1107F, 0x11082 }, /* BRAHMI NUMBER JOINER - KAITHI SIGN VISARGA */ - { 0x110B0, 0x110BA }, /* KAITHI VOWEL SIGN AA - KAITHI SIGN NUKTA */ - { 0x110BD, 0x110BD }, /* KAITHI NUMBER SIGN */ - { 0x110C2, 0x110C2 }, /* KAITHI VOWEL SIGN VOCALIC R */ - { 0x110CD, 0x110CD }, /* KAITHI NUMBER SIGN ABOVE */ - { 0x11100, 0x11102 }, /* CHAKMA SIGN CANDRABINDU - CHAKMA SIGN VISARGA */ - { 0x11127, 0x11134 }, /* CHAKMA VOWEL SIGN A - CHAKMA MAAYYAA */ - { 0x11145, 0x11146 }, /* CHAKMA VOWEL SIGN AA - CHAKMA VOWEL SIGN EI */ - { 0x11173, 0x11173 }, /* MAHAJANI SIGN NUKTA */ - { 0x11180, 0x11182 }, /* SHARADA SIGN CANDRABINDU - SHARADA SIGN VISARGA */ - { 0x111B3, 0x111C0 }, /* SHARADA VOWEL SIGN AA - SHARADA SIGN VIRAMA */ - { 0x111C9, 0x111CC }, /* SHARADA SANDHI MARK - SHARADA EXTRA SHORT VOWEL MARK */ - { 0x111CE, 0x111CF }, /* SHARADA VOWEL SIGN PRISHTHAMATRA E - SHARADA SIGN INVERTED CANDRABINDU */ - { 0x1122C, 0x11237 }, /* KHOJKI VOWEL SIGN AA - KHOJKI SIGN SHADDA */ - { 0x1123E, 0x1123E }, /* KHOJKI SIGN SUKUN */ - { 0x11241, 0x11241 }, /* KHOJKI VOWEL SIGN VOCALIC R */ - { 0x112DF, 0x112EA }, /* KHUDAWADI SIGN ANUSVARA - KHUDAWADI SIGN VIRAMA */ - { 0x11300, 0x11303 }, /* GRANTHA SIGN COMBINING ANUSVARA ABOVE - GRANTHA SIGN VISARGA */ - { 0x1133B, 0x1133C }, /* COMBINING BINDU BELOW - GRANTHA SIGN NUKTA */ - { 0x1133E, 0x11344 }, /* GRANTHA VOWEL SIGN AA - GRANTHA VOWEL SIGN VOCALIC RR */ - { 0x11347, 0x11348 }, /* GRANTHA VOWEL SIGN EE - GRANTHA VOWEL SIGN AI */ - { 0x1134B, 0x1134D }, /* GRANTHA VOWEL SIGN OO - GRANTHA SIGN VIRAMA */ - { 0x11357, 0x11357 }, /* GRANTHA AU LENGTH MARK */ - { 0x11362, 0x11363 }, /* GRANTHA VOWEL SIGN VOCALIC L - GRANTHA VOWEL SIGN VOCALIC LL */ - { 0x11366, 0x1136C }, /* COMBINING GRANTHA DIGIT ZERO - COMBINING GRANTHA DIGIT SIX */ - { 0x11370, 0x11374 }, /* COMBINING GRANTHA LETTER A - COMBINING GRANTHA LETTER PA */ - { 0x113B8, 0x113C0 }, /* TULU-TIGALARI VOWEL SIGN AA - TULU-TIGALARI VOWEL SIGN VOCALIC LL */ - { 0x113C2, 0x113C2 }, /* TULU-TIGALARI VOWEL SIGN EE */ - { 0x113C5, 0x113C5 }, /* TULU-TIGALARI VOWEL SIGN AI */ - { 0x113C7, 0x113CA }, /* TULU-TIGALARI VOWEL SIGN OO - TULU-TIGALARI SIGN CANDRA ANUNASIKA */ - { 0x113CC, 0x113D0 }, /* TULU-TIGALARI SIGN ANUSVARA - TULU-TIGALARI CONJOINER */ - { 0x113D2, 0x113D2 }, /* TULU-TIGALARI GEMINATION MARK */ - { 0x113E1, 0x113E2 }, /* TULU-TIGALARI VEDIC TONE SVARITA - TULU-TIGALARI VEDIC TONE ANUDATTA */ - { 0x11435, 0x11446 }, /* NEWA VOWEL SIGN AA - NEWA SIGN NUKTA */ - { 0x1145E, 0x1145E }, /* NEWA SANDHI MARK */ - { 0x114B0, 0x114C3 }, /* TIRHUTA VOWEL SIGN AA - TIRHUTA SIGN NUKTA */ - { 0x115AF, 0x115B5 }, /* SIDDHAM VOWEL SIGN AA - SIDDHAM VOWEL SIGN VOCALIC RR */ - { 0x115B8, 0x115C0 }, /* SIDDHAM VOWEL SIGN E - SIDDHAM SIGN NUKTA */ - { 0x115DC, 0x115DD }, /* SIDDHAM VOWEL SIGN ALTERNATE U - SIDDHAM VOWEL SIGN ALTERNATE UU */ - { 0x11630, 0x11640 }, /* MODI VOWEL SIGN AA - MODI SIGN ARDHACANDRA */ - { 0x116AB, 0x116B7 }, /* TAKRI SIGN ANUSVARA - TAKRI SIGN NUKTA */ - { 0x1171D, 0x1172B }, /* AHOM CONSONANT SIGN MEDIAL LA - AHOM SIGN KILLER */ - { 0x1182C, 0x1183A }, /* DOGRA VOWEL SIGN AA - DOGRA SIGN NUKTA */ - { 0x11930, 0x11935 }, /* DIVES AKURU VOWEL SIGN AA - DIVES AKURU VOWEL SIGN E */ - { 0x11937, 0x11938 }, /* DIVES AKURU VOWEL SIGN AI - DIVES AKURU VOWEL SIGN O */ - { 0x1193B, 0x1193E }, /* DIVES AKURU SIGN ANUSVARA - DIVES AKURU VIRAMA */ - { 0x11940, 0x11940 }, /* DIVES AKURU MEDIAL YA */ - { 0x11942, 0x11943 }, /* DIVES AKURU MEDIAL RA - DIVES AKURU SIGN NUKTA */ - { 0x119D1, 0x119D7 }, /* NANDINAGARI VOWEL SIGN AA - NANDINAGARI VOWEL SIGN VOCALIC RR */ - { 0x119DA, 0x119E0 }, /* NANDINAGARI VOWEL SIGN E - NANDINAGARI SIGN VIRAMA */ - { 0x119E4, 0x119E4 }, /* NANDINAGARI VOWEL SIGN PRISHTHAMATRA E */ - { 0x11A01, 0x11A0A }, /* ZANABAZAR SQUARE VOWEL SIGN I - ZANABAZAR SQUARE VOWEL LENGTH MARK */ - { 0x11A33, 0x11A39 }, /* ZANABAZAR SQUARE FINAL CONSONANT MARK - ZANABAZAR SQUARE SIGN VISARGA */ - { 0x11A3B, 0x11A3E }, /* ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA - ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA */ - { 0x11A47, 0x11A47 }, /* ZANABAZAR SQUARE SUBJOINER */ - { 0x11A51, 0x11A5B }, /* SOYOMBO VOWEL SIGN I - SOYOMBO VOWEL LENGTH MARK */ - { 0x11A8A, 0x11A99 }, /* SOYOMBO FINAL CONSONANT SIGN G - SOYOMBO SUBJOINER */ - { 0x11C2F, 0x11C36 }, /* BHAIKSUKI VOWEL SIGN AA - BHAIKSUKI VOWEL SIGN VOCALIC L */ - { 0x11C38, 0x11C3F }, /* BHAIKSUKI VOWEL SIGN E - BHAIKSUKI SIGN VIRAMA */ - { 0x11C92, 0x11CA7 }, /* MARCHEN SUBJOINED LETTER KA - MARCHEN SUBJOINED LETTER ZA */ - { 0x11CA9, 0x11CB6 }, /* MARCHEN SUBJOINED LETTER YA - MARCHEN SIGN CANDRABINDU */ - { 0x11D31, 0x11D36 }, /* MASARAM GONDI VOWEL SIGN AA - MASARAM GONDI VOWEL SIGN VOCALIC R */ - { 0x11D3A, 0x11D3A }, /* MASARAM GONDI VOWEL SIGN E */ - { 0x11D3C, 0x11D3D }, /* MASARAM GONDI VOWEL SIGN AI - MASARAM GONDI VOWEL SIGN O */ - { 0x11D3F, 0x11D45 }, /* MASARAM GONDI VOWEL SIGN AU - MASARAM GONDI VIRAMA */ - { 0x11D47, 0x11D47 }, /* MASARAM GONDI RA-KARA */ - { 0x11D8A, 0x11D8E }, /* GUNJALA GONDI VOWEL SIGN AA - GUNJALA GONDI VOWEL SIGN UU */ - { 0x11D90, 0x11D91 }, /* GUNJALA GONDI VOWEL SIGN EE - GUNJALA GONDI VOWEL SIGN AI */ - { 0x11D93, 0x11D97 }, /* GUNJALA GONDI VOWEL SIGN OO - GUNJALA GONDI VIRAMA */ - { 0x11EF3, 0x11EF6 }, /* MAKASAR VOWEL SIGN I - MAKASAR VOWEL SIGN O */ - { 0x11F00, 0x11F01 }, /* KAWI SIGN CANDRABINDU - KAWI SIGN ANUSVARA */ - { 0x11F03, 0x11F03 }, /* KAWI SIGN VISARGA */ - { 0x11F34, 0x11F3A }, /* KAWI VOWEL SIGN AA - KAWI VOWEL SIGN VOCALIC R */ - { 0x11F3E, 0x11F42 }, /* KAWI VOWEL SIGN E - KAWI CONJOINER */ - { 0x11F5A, 0x11F5A }, /* KAWI SIGN NUKTA */ - { 0x13430, 0x13440 }, /* EGYPTIAN HIEROGLYPH VERTICAL JOINER - EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY */ - { 0x13447, 0x13455 }, /* EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START - EGYPTIAN HIEROGLYPH MODIFIER DAMAGED */ - { 0x1611E, 0x1612F }, /* GURUNG KHEMA VOWEL SIGN AA - GURUNG KHEMA SIGN THOLHOMA */ - { 0x16AF0, 0x16AF4 }, /* BASSA VAH COMBINING HIGH TONE - BASSA VAH COMBINING HIGH-LOW TONE */ - { 0x16B30, 0x16B36 }, /* PAHAWH HMONG MARK CIM TUB - PAHAWH HMONG MARK CIM TAUM */ - { 0x16F4F, 0x16F4F }, /* MIAO SIGN CONSONANT MODIFIER BAR */ - { 0x16F51, 0x16F87 }, /* MIAO SIGN ASPIRATION - MIAO VOWEL SIGN UI */ - { 0x16F8F, 0x16F92 }, /* MIAO TONE RIGHT - MIAO TONE BELOW */ - { 0x16FE4, 0x16FE4 }, /* KHITAN SMALL SCRIPT FILLER */ - { 0x16FF0, 0x16FF1 }, /* VIETNAMESE ALTERNATE READING MARK CA - VIETNAMESE ALTERNATE READING MARK NHAY */ - { 0x1BC9D, 0x1BC9E }, /* DUPLOYAN THICK LETTER SELECTOR - DUPLOYAN DOUBLE MARK */ - { 0x1BCA0, 0x1BCA3 }, /* SHORTHAND FORMAT LETTER OVERLAP - SHORTHAND FORMAT UP STEP */ - { 0x1CF00, 0x1CF2D }, /* ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT - ZNAMENNY COMBINING MARK KRYZH ON LEFT */ - { 0x1CF30, 0x1CF46 }, /* ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO - ZNAMENNY PRIZNAK MODIFIER ROG */ - { 0x1D165, 0x1D169 }, /* MUSICAL SYMBOL COMBINING STEM - MUSICAL SYMBOL COMBINING TREMOLO-3 */ - { 0x1D16D, 0x1D182 }, /* MUSICAL SYMBOL COMBINING AUGMENTATION DOT - MUSICAL SYMBOL COMBINING LOURE */ - { 0x1D185, 0x1D18B }, /* MUSICAL SYMBOL COMBINING DOIT - MUSICAL SYMBOL COMBINING TRIPLE TONGUE */ - { 0x1D1AA, 0x1D1AD }, /* MUSICAL SYMBOL COMBINING DOWN BOW - MUSICAL SYMBOL COMBINING SNAP PIZZICATO */ - { 0x1D242, 0x1D244 }, /* COMBINING GREEK MUSICAL TRISEME - COMBINING GREEK MUSICAL PENTASEME */ - { 0x1DA00, 0x1DA36 }, /* SIGNWRITING HEAD RIM - SIGNWRITING AIR SUCKING IN */ - { 0x1DA3B, 0x1DA6C }, /* SIGNWRITING MOUTH CLOSED NEUTRAL - SIGNWRITING EXCITEMENT */ - { 0x1DA75, 0x1DA75 }, /* SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS */ - { 0x1DA84, 0x1DA84 }, /* SIGNWRITING LOCATION HEAD NECK */ - { 0x1DA9B, 0x1DA9F }, /* SIGNWRITING FILL MODIFIER-2 - SIGNWRITING FILL MODIFIER-6 */ - { 0x1DAA1, 0x1DAAF }, /* SIGNWRITING ROTATION MODIFIER-2 - SIGNWRITING ROTATION MODIFIER-16 */ - { 0x1E000, 0x1E006 }, /* COMBINING GLAGOLITIC LETTER AZU - COMBINING GLAGOLITIC LETTER ZHIVETE */ - { 0x1E008, 0x1E018 }, /* COMBINING GLAGOLITIC LETTER ZEMLJA - COMBINING GLAGOLITIC LETTER HERU */ - { 0x1E01B, 0x1E021 }, /* COMBINING GLAGOLITIC LETTER SHTA - COMBINING GLAGOLITIC LETTER YATI */ - { 0x1E023, 0x1E024 }, /* COMBINING GLAGOLITIC LETTER YU - COMBINING GLAGOLITIC LETTER SMALL YUS */ - { 0x1E026, 0x1E02A }, /* COMBINING GLAGOLITIC LETTER YO - COMBINING GLAGOLITIC LETTER FITA */ - { 0x1E08F, 0x1E08F }, /* COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I */ - { 0x1E130, 0x1E136 }, /* NYIAKENG PUACHUE HMONG TONE-B - NYIAKENG PUACHUE HMONG TONE-D */ - { 0x1E2AE, 0x1E2AE }, /* TOTO SIGN RISING TONE */ - { 0x1E2EC, 0x1E2EF }, /* WANCHO TONE TUP - WANCHO TONE KOINI */ - { 0x1E4EC, 0x1E4EF }, /* NAG MUNDARI SIGN MUHOR - NAG MUNDARI SIGN SUTUH */ - { 0x1E5EE, 0x1E5EF }, /* OL ONAL SIGN MU - OL ONAL SIGN IKIR */ - { 0x1E8D0, 0x1E8D6 }, /* MENDE KIKAKUI COMBINING NUMBER TEENS - MENDE KIKAKUI COMBINING NUMBER MILLIONS */ - { 0x1E944, 0x1E94A }, /* ADLAM ALIF LENGTHENER - ADLAM NUKTA */ - { 0x1F3FB, 0x1F3FF }, /* EMOJI MODIFIER FITZPATRICK TYPE-1-2 - EMOJI MODIFIER FITZPATRICK TYPE-6 */ - { 0x1F9B0, 0x1F9B3 }, /* EMOJI COMPONENT RED HAIR - EMOJI COMPONENT WHITE HAIR */ - { 0xE0001, 0xE0001 }, /* LANGUAGE TAG */ - { 0xE0020, 0xE007F }, /* TAG SPACE - CANCEL TAG */ - { 0xE0100, 0xE01EF }, /* VARIATION SELECTOR-17 - VARIATION SELECTOR-256 */ -}; - -/* Double-width character ranges (BMP - Basic Multilingual Plane, U+0000 to U+FFFF) */ -static const struct ucs_interval16 ucs_double_width_bmp_ranges[] = { - { 0x1100, 0x115F }, /* HANGUL CHOSEONG KIYEOK - HANGUL CHOSEONG FILLER */ - { 0x231A, 0x231B }, /* WATCH - HOURGLASS */ - { 0x2329, 0x232A }, /* LEFT-POINTING ANGLE BRACKET - RIGHT-POINTING ANGLE BRACKET */ - { 0x23E9, 0x23EC }, /* BLACK RIGHT-POINTING DOUBLE TRIANGLE - BLACK DOWN-POINTING DOUBLE TRIANGLE */ - { 0x23F0, 0x23F0 }, /* ALARM CLOCK */ - { 0x23F3, 0x23F3 }, /* HOURGLASS WITH FLOWING SAND */ - { 0x25FD, 0x25FE }, /* WHITE MEDIUM SMALL SQUARE - BLACK MEDIUM SMALL SQUARE */ - { 0x2614, 0x2615 }, /* UMBRELLA WITH RAIN DROPS - HOT BEVERAGE */ - { 0x2630, 0x2637 }, /* TRIGRAM FOR HEAVEN - TRIGRAM FOR EARTH */ - { 0x2648, 0x2653 }, /* ARIES - PISCES */ - { 0x267F, 0x267F }, /* WHEELCHAIR SYMBOL */ - { 0x268A, 0x268F }, /* MONOGRAM FOR YANG - DIGRAM FOR GREATER YIN */ - { 0x2693, 0x2693 }, /* ANCHOR */ - { 0x26A1, 0x26A1 }, /* HIGH VOLTAGE SIGN */ - { 0x26AA, 0x26AB }, /* MEDIUM WHITE CIRCLE - MEDIUM BLACK CIRCLE */ - { 0x26BD, 0x26BE }, /* SOCCER BALL - BASEBALL */ - { 0x26C4, 0x26C5 }, /* SNOWMAN WITHOUT SNOW - SUN BEHIND CLOUD */ - { 0x26CE, 0x26CE }, /* OPHIUCHUS */ - { 0x26D4, 0x26D4 }, /* NO ENTRY */ - { 0x26EA, 0x26EA }, /* CHURCH */ - { 0x26F2, 0x26F3 }, /* FOUNTAIN - FLAG IN HOLE */ - { 0x26F5, 0x26F5 }, /* SAILBOAT */ - { 0x26FA, 0x26FA }, /* TENT */ - { 0x26FD, 0x26FD }, /* FUEL PUMP */ - { 0x2705, 0x2705 }, /* WHITE HEAVY CHECK MARK */ - { 0x270A, 0x270B }, /* RAISED FIST - RAISED HAND */ - { 0x2728, 0x2728 }, /* SPARKLES */ - { 0x274C, 0x274C }, /* CROSS MARK */ - { 0x274E, 0x274E }, /* NEGATIVE SQUARED CROSS MARK */ - { 0x2753, 0x2755 }, /* BLACK QUESTION MARK ORNAMENT - WHITE EXCLAMATION MARK ORNAMENT */ - { 0x2757, 0x2757 }, /* HEAVY EXCLAMATION MARK SYMBOL */ - { 0x2795, 0x2797 }, /* HEAVY PLUS SIGN - HEAVY DIVISION SIGN */ - { 0x27B0, 0x27B0 }, /* CURLY LOOP */ - { 0x27BF, 0x27BF }, /* DOUBLE CURLY LOOP */ - { 0x2B1B, 0x2B1C }, /* BLACK LARGE SQUARE - WHITE LARGE SQUARE */ - { 0x2B50, 0x2B50 }, /* WHITE MEDIUM STAR */ - { 0x2B55, 0x2B55 }, /* HEAVY LARGE CIRCLE */ - { 0x2E80, 0x2E99 }, /* CJK RADICAL REPEAT - CJK RADICAL RAP */ - { 0x2E9B, 0x2EF3 }, /* CJK RADICAL CHOKE - CJK RADICAL C-SIMPLIFIED TURTLE */ - { 0x2F00, 0x2FD5 }, /* KANGXI RADICAL ONE - KANGXI RADICAL FLUTE */ - { 0x2FF0, 0x3029 }, /* IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT - HANGZHOU NUMERAL NINE */ - { 0x3030, 0x303E }, /* WAVY DASH - IDEOGRAPHIC VARIATION INDICATOR */ - { 0x3041, 0x3096 }, /* HIRAGANA LETTER SMALL A - HIRAGANA LETTER SMALL KE */ - { 0x309B, 0x30FF }, /* KATAKANA-HIRAGANA VOICED SOUND MARK - KATAKANA DIGRAPH KOTO */ - { 0x3105, 0x312F }, /* BOPOMOFO LETTER B - BOPOMOFO LETTER NN */ - { 0x3131, 0x318E }, /* HANGUL LETTER KIYEOK - HANGUL LETTER ARAEAE */ - { 0x3190, 0x31E5 }, /* IDEOGRAPHIC ANNOTATION LINKING MARK - CJK STROKE SZP */ - { 0x31EF, 0x321E }, /* IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION - PARENTHESIZED KOREAN CHARACTER O HU */ - { 0x3220, 0x3247 }, /* PARENTHESIZED IDEOGRAPH ONE - CIRCLED IDEOGRAPH KOTO */ - { 0x3250, 0xA48C }, /* PARTNERSHIP SIGN - YI SYLLABLE YYR */ - { 0xA490, 0xA4C6 }, /* YI RADICAL QOT - YI RADICAL KE */ - { 0xA960, 0xA97C }, /* HANGUL CHOSEONG TIKEUT-MIEUM - HANGUL CHOSEONG SSANGYEORINHIEUH */ - { 0xAC00, 0xD7A3 }, /* HANGUL SYLLABLE GA - HANGUL SYLLABLE HIH */ - { 0xF900, 0xFAFF }, /* U+F900 - U+FAFF */ - { 0xFE10, 0xFE19 }, /* PRESENTATION FORM FOR VERTICAL COMMA - PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS */ - { 0xFE30, 0xFE52 }, /* PRESENTATION FORM FOR VERTICAL TWO DOT LEADER - SMALL FULL STOP */ - { 0xFE54, 0xFE66 }, /* SMALL SEMICOLON - SMALL EQUALS SIGN */ - { 0xFE68, 0xFE6B }, /* SMALL REVERSE SOLIDUS - SMALL COMMERCIAL AT */ - { 0xFF01, 0xFF60 }, /* FULLWIDTH EXCLAMATION MARK - FULLWIDTH RIGHT WHITE PARENTHESIS */ - { 0xFFE0, 0xFFE6 }, /* FULLWIDTH CENT SIGN - FULLWIDTH WON SIGN */ -}; - -/* Double-width character ranges (non-BMP, U+10000 and above) */ -static const struct ucs_interval32 ucs_double_width_non_bmp_ranges[] = { - { 0x16FE0, 0x16FE3 }, /* TANGUT ITERATION MARK - OLD CHINESE ITERATION MARK */ - { 0x17000, 0x187F7 }, /* U+17000 - U+187F7 */ - { 0x18800, 0x18CD5 }, /* TANGUT COMPONENT-001 - KHITAN SMALL SCRIPT CHARACTER-18CD5 */ - { 0x18CFF, 0x18D08 }, /* U+18CFF - U+18D08 */ - { 0x1AFF0, 0x1AFF3 }, /* KATAKANA LETTER MINNAN TONE-2 - KATAKANA LETTER MINNAN TONE-5 */ - { 0x1AFF5, 0x1AFFB }, /* KATAKANA LETTER MINNAN TONE-7 - KATAKANA LETTER MINNAN NASALIZED TONE-5 */ - { 0x1AFFD, 0x1AFFE }, /* KATAKANA LETTER MINNAN NASALIZED TONE-7 - KATAKANA LETTER MINNAN NASALIZED TONE-8 */ - { 0x1B000, 0x1B122 }, /* KATAKANA LETTER ARCHAIC E - KATAKANA LETTER ARCHAIC WU */ - { 0x1B132, 0x1B132 }, /* HIRAGANA LETTER SMALL KO */ - { 0x1B150, 0x1B152 }, /* HIRAGANA LETTER SMALL WI - HIRAGANA LETTER SMALL WO */ - { 0x1B155, 0x1B155 }, /* KATAKANA LETTER SMALL KO */ - { 0x1B164, 0x1B167 }, /* KATAKANA LETTER SMALL WI - KATAKANA LETTER SMALL N */ - { 0x1B170, 0x1B2FB }, /* NUSHU CHARACTER-1B170 - NUSHU CHARACTER-1B2FB */ - { 0x1D300, 0x1D356 }, /* MONOGRAM FOR EARTH - TETRAGRAM FOR FOSTERING */ - { 0x1D360, 0x1D376 }, /* COUNTING ROD UNIT DIGIT ONE - IDEOGRAPHIC TALLY MARK FIVE */ - { 0x1F000, 0x1F02F }, /* U+1F000 - U+1F02F */ - { 0x1F0A0, 0x1F0FF }, /* U+1F0A0 - U+1F0FF */ - { 0x1F18E, 0x1F18E }, /* NEGATIVE SQUARED AB */ - { 0x1F191, 0x1F19A }, /* SQUARED CL - SQUARED VS */ - { 0x1F200, 0x1F202 }, /* SQUARE HIRAGANA HOKA - SQUARED KATAKANA SA */ - { 0x1F210, 0x1F23B }, /* SQUARED CJK UNIFIED IDEOGRAPH-624B - SQUARED CJK UNIFIED IDEOGRAPH-914D */ - { 0x1F240, 0x1F248 }, /* TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C - TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 */ - { 0x1F250, 0x1F251 }, /* CIRCLED IDEOGRAPH ADVANTAGE - CIRCLED IDEOGRAPH ACCEPT */ - { 0x1F260, 0x1F265 }, /* ROUNDED SYMBOL FOR FU - ROUNDED SYMBOL FOR CAI */ - { 0x1F300, 0x1F3FA }, /* CYCLONE - AMPHORA */ - { 0x1F400, 0x1F64F }, /* RAT - PERSON WITH FOLDED HANDS */ - { 0x1F680, 0x1F9AF }, /* ROCKET - PROBING CANE */ - { 0x1F9B4, 0x1FAFF }, /* U+1F9B4 - U+1FAFF */ - { 0x20000, 0x2FFFD }, /* U+20000 - U+2FFFD */ - { 0x30000, 0x3FFFD }, /* U+30000 - U+3FFFD */ +/* Combined zero- and double-width ranges (non-BMP, U+10000 and above). + * The first 33 entries host the BMP double-width bitmap in the low + * 8 bits of `last`. */ +static const struct ucs_width32 ucs_nonbmp_ranges[] = { + { RANGE_0WIDTH(0x101FD, 0x101FD) /* PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 0.. 7] */ + { RANGE_0WIDTH(0x102E0, 0x102E0) /* COPTIC EPACT THOUSANDS MARK */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 8.. 15] */ + { RANGE_0WIDTH(0x10376, 0x1037A) /* COMBINING OLD PERMIC LETTER AN - COMBINING OLD PERMIC LETTER SII */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 16.. 23] */ + { RANGE_0WIDTH(0x10A01, 0x10A03) /* KHAROSHTHI VOWEL SIGN I - KHAROSHTHI VOWEL SIGN VOCALIC R */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 24.. 31] */ + { RANGE_0WIDTH(0x10A05, 0x10A06) /* KHAROSHTHI VOWEL SIGN E - KHAROSHTHI VOWEL SIGN O */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 32.. 39] */ + { RANGE_0WIDTH(0x10A0C, 0x10A0F) /* KHAROSHTHI VOWEL LENGTH MARK - KHAROSHTHI SIGN VISARGA */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 40.. 47] */ + { RANGE_0WIDTH(0x10A38, 0x10A3A) /* KHAROSHTHI SIGN BAR ABOVE - KHAROSHTHI SIGN DOT BELOW */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 48.. 55] */ + { RANGE_0WIDTH(0x10A3F, 0x10A3F) /* KHAROSHTHI VIRAMA */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 56.. 63] */ + { RANGE_0WIDTH(0x10AE5, 0x10AE6) /* MANICHAEAN ABBREVIATION MARK ABOVE - MANICHAEAN ABBREVIATION MARK BELOW */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 64.. 71] */ + { RANGE_0WIDTH(0x10D24, 0x10D27) /* HANIFI ROHINGYA SIGN HARBAHAY - HANIFI ROHINGYA SIGN TASSI */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 72.. 79] */ + { RANGE_0WIDTH(0x10D69, 0x10D6D) /* GARAY VOWEL SIGN E - GARAY CONSONANT NASALIZATION MARK */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 80.. 87] */ + { RANGE_0WIDTH(0x10EAB, 0x10EAC) /* YEZIDI COMBINING HAMZA MARK - YEZIDI COMBINING MADDA MARK */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 88.. 95] */ + { RANGE_0WIDTH(0x10EFC, 0x10EFF) /* ARABIC COMBINING ALEF OVERLAY - ARABIC SMALL LOW WORD MADDA */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [ 96..103] */ + { RANGE_0WIDTH(0x10F46, 0x10F50) /* SOGDIAN COMBINING DOT BELOW - SOGDIAN COMBINING STROKE BELOW */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [104..111] */ + { RANGE_0WIDTH(0x10F82, 0x10F85) /* OLD UYGHUR COMBINING DOT ABOVE - OLD UYGHUR COMBINING TWO DOTS BELOW */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [112..119] */ + { RANGE_0WIDTH(0x11000, 0x11002) /* BRAHMI SIGN CANDRABINDU - BRAHMI SIGN VISARGA */ + | BMP_2W_BITS(0b00001000) }, /* BMP entries [120..127] */ + { RANGE_0WIDTH(0x11038, 0x11046) /* BRAHMI VOWEL SIGN AA - BRAHMI VIRAMA */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [128..135] */ + { RANGE_0WIDTH(0x11070, 0x11070) /* BRAHMI SIGN OLD TAMIL VIRAMA */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [136..143] */ + { RANGE_0WIDTH(0x11073, 0x11074) /* BRAHMI VOWEL SIGN OLD TAMIL SHORT E - BRAHMI VOWEL SIGN OLD TAMIL SHORT O */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [144..151] */ + { RANGE_0WIDTH(0x1107F, 0x11082) /* BRAHMI NUMBER JOINER - KAITHI SIGN VISARGA */ + | BMP_2W_BITS(0b10000000) }, /* BMP entries [152..159] */ + { RANGE_0WIDTH(0x110B0, 0x110BA) /* KAITHI VOWEL SIGN AA - KAITHI SIGN NUKTA */ + | BMP_2W_BITS(0b01111111) }, /* BMP entries [160..167] */ + { RANGE_0WIDTH(0x110BD, 0x110BD) /* KAITHI NUMBER SIGN */ + | BMP_2W_BITS(0b10111110) }, /* BMP entries [168..175] */ + { RANGE_0WIDTH(0x110C2, 0x110C2) /* KAITHI VOWEL SIGN VOCALIC R */ + | BMP_2W_BITS(0b11111111) }, /* BMP entries [176..183] */ + { RANGE_0WIDTH(0x110CD, 0x110CD) /* KAITHI NUMBER SIGN ABOVE */ + | BMP_2W_BITS(0b11111111) }, /* BMP entries [184..191] */ + { RANGE_0WIDTH(0x11100, 0x11102) /* CHAKMA SIGN CANDRABINDU - CHAKMA SIGN VISARGA */ + | BMP_2W_BITS(0b00111111) }, /* BMP entries [192..199] */ + { RANGE_0WIDTH(0x11127, 0x11134) /* CHAKMA VOWEL SIGN A - CHAKMA MAAYYAA */ + | BMP_2W_BITS(0b11011110) }, /* BMP entries [200..207] */ + { RANGE_0WIDTH(0x11145, 0x11146) /* CHAKMA VOWEL SIGN AA - CHAKMA VOWEL SIGN EI */ + | BMP_2W_BITS(0b11111110) }, /* BMP entries [208..215] */ + { RANGE_0WIDTH(0x11173, 0x11173) /* MAHAJANI SIGN NUKTA */ + | BMP_2W_BITS(0b00000001) }, /* BMP entries [216..223] */ + { RANGE_0WIDTH(0x11180, 0x11182) /* SHARADA SIGN CANDRABINDU - SHARADA SIGN VISARGA */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [224..231] */ + { RANGE_0WIDTH(0x111B3, 0x111C0) /* SHARADA VOWEL SIGN AA - SHARADA SIGN VIRAMA */ + | BMP_2W_BITS(0b00000001) }, /* BMP entries [232..239] */ + { RANGE_0WIDTH(0x111C9, 0x111CC) /* SHARADA SANDHI MARK - SHARADA EXTRA SHORT VOWEL MARK */ + | BMP_2W_BITS(0b00000000) }, /* BMP entries [240..247] */ + { RANGE_0WIDTH(0x111CE, 0x111CF) /* SHARADA VOWEL SIGN PRISHTHAMATRA E - SHARADA SIGN INVERTED CANDRABINDU */ + | BMP_2W_BITS(0b10100110) }, /* BMP entries [248..255] */ + { RANGE_0WIDTH(0x1122C, 0x11237) /* KHOJKI VOWEL SIGN AA - KHOJKI SIGN SHADDA */ + | BMP_2W_BITS(0b00011011) }, /* BMP entries [256..261] */ + { RANGE_0WIDTH(0x1123E, 0x1123E) }, /* KHOJKI SIGN SUKUN */ + { RANGE_0WIDTH(0x11241, 0x11241) }, /* KHOJKI VOWEL SIGN VOCALIC R */ + { RANGE_0WIDTH(0x112DF, 0x112EA) }, /* KHUDAWADI SIGN ANUSVARA - KHUDAWADI SIGN VIRAMA */ + { RANGE_0WIDTH(0x11300, 0x11303) }, /* GRANTHA SIGN COMBINING ANUSVARA ABOVE - GRANTHA SIGN VISARGA */ + { RANGE_0WIDTH(0x1133B, 0x1133C) }, /* COMBINING BINDU BELOW - GRANTHA SIGN NUKTA */ + { RANGE_0WIDTH(0x1133E, 0x11344) }, /* GRANTHA VOWEL SIGN AA - GRANTHA VOWEL SIGN VOCALIC RR */ + { RANGE_0WIDTH(0x11347, 0x11348) }, /* GRANTHA VOWEL SIGN EE - GRANTHA VOWEL SIGN AI */ + { RANGE_0WIDTH(0x1134B, 0x1134D) }, /* GRANTHA VOWEL SIGN OO - GRANTHA SIGN VIRAMA */ + { RANGE_0WIDTH(0x11357, 0x11357) }, /* GRANTHA AU LENGTH MARK */ + { RANGE_0WIDTH(0x11362, 0x11363) }, /* GRANTHA VOWEL SIGN VOCALIC L - GRANTHA VOWEL SIGN VOCALIC LL */ + { RANGE_0WIDTH(0x11366, 0x1136C) }, /* COMBINING GRANTHA DIGIT ZERO - COMBINING GRANTHA DIGIT SIX */ + { RANGE_0WIDTH(0x11370, 0x11374) }, /* COMBINING GRANTHA LETTER A - COMBINING GRANTHA LETTER PA */ + { RANGE_0WIDTH(0x113B8, 0x113C0) }, /* TULU-TIGALARI VOWEL SIGN AA - TULU-TIGALARI VOWEL SIGN VOCALIC LL */ + { RANGE_0WIDTH(0x113C2, 0x113C2) }, /* TULU-TIGALARI VOWEL SIGN EE */ + { RANGE_0WIDTH(0x113C5, 0x113C5) }, /* TULU-TIGALARI VOWEL SIGN AI */ + { RANGE_0WIDTH(0x113C7, 0x113CA) }, /* TULU-TIGALARI VOWEL SIGN OO - TULU-TIGALARI SIGN CANDRA ANUNASIKA */ + { RANGE_0WIDTH(0x113CC, 0x113D0) }, /* TULU-TIGALARI SIGN ANUSVARA - TULU-TIGALARI CONJOINER */ + { RANGE_0WIDTH(0x113D2, 0x113D2) }, /* TULU-TIGALARI GEMINATION MARK */ + { RANGE_0WIDTH(0x113E1, 0x113E2) }, /* TULU-TIGALARI VEDIC TONE SVARITA - TULU-TIGALARI VEDIC TONE ANUDATTA */ + { RANGE_0WIDTH(0x11435, 0x11446) }, /* NEWA VOWEL SIGN AA - NEWA SIGN NUKTA */ + { RANGE_0WIDTH(0x1145E, 0x1145E) }, /* NEWA SANDHI MARK */ + { RANGE_0WIDTH(0x114B0, 0x114C3) }, /* TIRHUTA VOWEL SIGN AA - TIRHUTA SIGN NUKTA */ + { RANGE_0WIDTH(0x115AF, 0x115B5) }, /* SIDDHAM VOWEL SIGN AA - SIDDHAM VOWEL SIGN VOCALIC RR */ + { RANGE_0WIDTH(0x115B8, 0x115C0) }, /* SIDDHAM VOWEL SIGN E - SIDDHAM SIGN NUKTA */ + { RANGE_0WIDTH(0x115DC, 0x115DD) }, /* SIDDHAM VOWEL SIGN ALTERNATE U - SIDDHAM VOWEL SIGN ALTERNATE UU */ + { RANGE_0WIDTH(0x11630, 0x11640) }, /* MODI VOWEL SIGN AA - MODI SIGN ARDHACANDRA */ + { RANGE_0WIDTH(0x116AB, 0x116B7) }, /* TAKRI SIGN ANUSVARA - TAKRI SIGN NUKTA */ + { RANGE_0WIDTH(0x1171D, 0x1172B) }, /* AHOM CONSONANT SIGN MEDIAL LA - AHOM SIGN KILLER */ + { RANGE_0WIDTH(0x1182C, 0x1183A) }, /* DOGRA VOWEL SIGN AA - DOGRA SIGN NUKTA */ + { RANGE_0WIDTH(0x11930, 0x11935) }, /* DIVES AKURU VOWEL SIGN AA - DIVES AKURU VOWEL SIGN E */ + { RANGE_0WIDTH(0x11937, 0x11938) }, /* DIVES AKURU VOWEL SIGN AI - DIVES AKURU VOWEL SIGN O */ + { RANGE_0WIDTH(0x1193B, 0x1193E) }, /* DIVES AKURU SIGN ANUSVARA - DIVES AKURU VIRAMA */ + { RANGE_0WIDTH(0x11940, 0x11940) }, /* DIVES AKURU MEDIAL YA */ + { RANGE_0WIDTH(0x11942, 0x11943) }, /* DIVES AKURU MEDIAL RA - DIVES AKURU SIGN NUKTA */ + { RANGE_0WIDTH(0x119D1, 0x119D7) }, /* NANDINAGARI VOWEL SIGN AA - NANDINAGARI VOWEL SIGN VOCALIC RR */ + { RANGE_0WIDTH(0x119DA, 0x119E0) }, /* NANDINAGARI VOWEL SIGN E - NANDINAGARI SIGN VIRAMA */ + { RANGE_0WIDTH(0x119E4, 0x119E4) }, /* NANDINAGARI VOWEL SIGN PRISHTHAMATRA E */ + { RANGE_0WIDTH(0x11A01, 0x11A0A) }, /* ZANABAZAR SQUARE VOWEL SIGN I - ZANABAZAR SQUARE VOWEL LENGTH MARK */ + { RANGE_0WIDTH(0x11A33, 0x11A39) }, /* ZANABAZAR SQUARE FINAL CONSONANT MARK - ZANABAZAR SQUARE SIGN VISARGA */ + { RANGE_0WIDTH(0x11A3B, 0x11A3E) }, /* ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA - ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA */ + { RANGE_0WIDTH(0x11A47, 0x11A47) }, /* ZANABAZAR SQUARE SUBJOINER */ + { RANGE_0WIDTH(0x11A51, 0x11A5B) }, /* SOYOMBO VOWEL SIGN I - SOYOMBO VOWEL LENGTH MARK */ + { RANGE_0WIDTH(0x11A8A, 0x11A99) }, /* SOYOMBO FINAL CONSONANT SIGN G - SOYOMBO SUBJOINER */ + { RANGE_0WIDTH(0x11C2F, 0x11C36) }, /* BHAIKSUKI VOWEL SIGN AA - BHAIKSUKI VOWEL SIGN VOCALIC L */ + { RANGE_0WIDTH(0x11C38, 0x11C3F) }, /* BHAIKSUKI VOWEL SIGN E - BHAIKSUKI SIGN VIRAMA */ + { RANGE_0WIDTH(0x11C92, 0x11CA7) }, /* MARCHEN SUBJOINED LETTER KA - MARCHEN SUBJOINED LETTER ZA */ + { RANGE_0WIDTH(0x11CA9, 0x11CB6) }, /* MARCHEN SUBJOINED LETTER YA - MARCHEN SIGN CANDRABINDU */ + { RANGE_0WIDTH(0x11D31, 0x11D36) }, /* MASARAM GONDI VOWEL SIGN AA - MASARAM GONDI VOWEL SIGN VOCALIC R */ + { RANGE_0WIDTH(0x11D3A, 0x11D3A) }, /* MASARAM GONDI VOWEL SIGN E */ + { RANGE_0WIDTH(0x11D3C, 0x11D3D) }, /* MASARAM GONDI VOWEL SIGN AI - MASARAM GONDI VOWEL SIGN O */ + { RANGE_0WIDTH(0x11D3F, 0x11D45) }, /* MASARAM GONDI VOWEL SIGN AU - MASARAM GONDI VIRAMA */ + { RANGE_0WIDTH(0x11D47, 0x11D47) }, /* MASARAM GONDI RA-KARA */ + { RANGE_0WIDTH(0x11D8A, 0x11D8E) }, /* GUNJALA GONDI VOWEL SIGN AA - GUNJALA GONDI VOWEL SIGN UU */ + { RANGE_0WIDTH(0x11D90, 0x11D91) }, /* GUNJALA GONDI VOWEL SIGN EE - GUNJALA GONDI VOWEL SIGN AI */ + { RANGE_0WIDTH(0x11D93, 0x11D97) }, /* GUNJALA GONDI VOWEL SIGN OO - GUNJALA GONDI VIRAMA */ + { RANGE_0WIDTH(0x11EF3, 0x11EF6) }, /* MAKASAR VOWEL SIGN I - MAKASAR VOWEL SIGN O */ + { RANGE_0WIDTH(0x11F00, 0x11F01) }, /* KAWI SIGN CANDRABINDU - KAWI SIGN ANUSVARA */ + { RANGE_0WIDTH(0x11F03, 0x11F03) }, /* KAWI SIGN VISARGA */ + { RANGE_0WIDTH(0x11F34, 0x11F3A) }, /* KAWI VOWEL SIGN AA - KAWI VOWEL SIGN VOCALIC R */ + { RANGE_0WIDTH(0x11F3E, 0x11F42) }, /* KAWI VOWEL SIGN E - KAWI CONJOINER */ + { RANGE_0WIDTH(0x11F5A, 0x11F5A) }, /* KAWI SIGN NUKTA */ + { RANGE_0WIDTH(0x13430, 0x13440) }, /* EGYPTIAN HIEROGLYPH VERTICAL JOINER - EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY */ + { RANGE_0WIDTH(0x13447, 0x13455) }, /* EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START - EGYPTIAN HIEROGLYPH MODIFIER DAMAGED */ + { RANGE_0WIDTH(0x1611E, 0x1612F) }, /* GURUNG KHEMA VOWEL SIGN AA - GURUNG KHEMA SIGN THOLHOMA */ + { RANGE_0WIDTH(0x16AF0, 0x16AF4) }, /* BASSA VAH COMBINING HIGH TONE - BASSA VAH COMBINING HIGH-LOW TONE */ + { RANGE_0WIDTH(0x16B30, 0x16B36) }, /* PAHAWH HMONG MARK CIM TUB - PAHAWH HMONG MARK CIM TAUM */ + { RANGE_0WIDTH(0x16F4F, 0x16F4F) }, /* MIAO SIGN CONSONANT MODIFIER BAR */ + { RANGE_0WIDTH(0x16F51, 0x16F87) }, /* MIAO SIGN ASPIRATION - MIAO VOWEL SIGN UI */ + { RANGE_0WIDTH(0x16F8F, 0x16F92) }, /* MIAO TONE RIGHT - MIAO TONE BELOW */ + { RANGE_2WIDTH(0x16FE0, 0x16FE3) }, /* TANGUT ITERATION MARK - OLD CHINESE ITERATION MARK */ + { RANGE_0WIDTH(0x16FE4, 0x16FE4) }, /* KHITAN SMALL SCRIPT FILLER */ + { RANGE_0WIDTH(0x16FF0, 0x16FF1) }, /* VIETNAMESE ALTERNATE READING MARK CA - VIETNAMESE ALTERNATE READING MARK NHAY */ + { RANGE_2WIDTH(0x17000, 0x187F7) }, /* U+17000 - U+187F7 */ + { RANGE_2WIDTH(0x18800, 0x18CD5) }, /* TANGUT COMPONENT-001 - KHITAN SMALL SCRIPT CHARACTER-18CD5 */ + { RANGE_2WIDTH(0x18CFF, 0x18D08) }, /* U+18CFF - U+18D08 */ + { RANGE_2WIDTH(0x1AFF0, 0x1AFF3) }, /* KATAKANA LETTER MINNAN TONE-2 - KATAKANA LETTER MINNAN TONE-5 */ + { RANGE_2WIDTH(0x1AFF5, 0x1AFFB) }, /* KATAKANA LETTER MINNAN TONE-7 - KATAKANA LETTER MINNAN NASALIZED TONE-5 */ + { RANGE_2WIDTH(0x1AFFD, 0x1AFFE) }, /* KATAKANA LETTER MINNAN NASALIZED TONE-7 - KATAKANA LETTER MINNAN NASALIZED TONE-8 */ + { RANGE_2WIDTH(0x1B000, 0x1B122) }, /* KATAKANA LETTER ARCHAIC E - KATAKANA LETTER ARCHAIC WU */ + { RANGE_2WIDTH(0x1B132, 0x1B132) }, /* HIRAGANA LETTER SMALL KO */ + { RANGE_2WIDTH(0x1B150, 0x1B152) }, /* HIRAGANA LETTER SMALL WI - HIRAGANA LETTER SMALL WO */ + { RANGE_2WIDTH(0x1B155, 0x1B155) }, /* KATAKANA LETTER SMALL KO */ + { RANGE_2WIDTH(0x1B164, 0x1B167) }, /* KATAKANA LETTER SMALL WI - KATAKANA LETTER SMALL N */ + { RANGE_2WIDTH(0x1B170, 0x1B2FB) }, /* NUSHU CHARACTER-1B170 - NUSHU CHARACTER-1B2FB */ + { RANGE_0WIDTH(0x1BC9D, 0x1BC9E) }, /* DUPLOYAN THICK LETTER SELECTOR - DUPLOYAN DOUBLE MARK */ + { RANGE_0WIDTH(0x1BCA0, 0x1BCA3) }, /* SHORTHAND FORMAT LETTER OVERLAP - SHORTHAND FORMAT UP STEP */ + { RANGE_0WIDTH(0x1CF00, 0x1CF2D) }, /* ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT - ZNAMENNY COMBINING MARK KRYZH ON LEFT */ + { RANGE_0WIDTH(0x1CF30, 0x1CF46) }, /* ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO - ZNAMENNY PRIZNAK MODIFIER ROG */ + { RANGE_0WIDTH(0x1D165, 0x1D169) }, /* MUSICAL SYMBOL COMBINING STEM - MUSICAL SYMBOL COMBINING TREMOLO-3 */ + { RANGE_0WIDTH(0x1D16D, 0x1D182) }, /* MUSICAL SYMBOL COMBINING AUGMENTATION DOT - MUSICAL SYMBOL COMBINING LOURE */ + { RANGE_0WIDTH(0x1D185, 0x1D18B) }, /* MUSICAL SYMBOL COMBINING DOIT - MUSICAL SYMBOL COMBINING TRIPLE TONGUE */ + { RANGE_0WIDTH(0x1D1AA, 0x1D1AD) }, /* MUSICAL SYMBOL COMBINING DOWN BOW - MUSICAL SYMBOL COMBINING SNAP PIZZICATO */ + { RANGE_0WIDTH(0x1D242, 0x1D244) }, /* COMBINING GREEK MUSICAL TRISEME - COMBINING GREEK MUSICAL PENTASEME */ + { RANGE_2WIDTH(0x1D300, 0x1D356) }, /* MONOGRAM FOR EARTH - TETRAGRAM FOR FOSTERING */ + { RANGE_2WIDTH(0x1D360, 0x1D376) }, /* COUNTING ROD UNIT DIGIT ONE - IDEOGRAPHIC TALLY MARK FIVE */ + { RANGE_0WIDTH(0x1DA00, 0x1DA36) }, /* SIGNWRITING HEAD RIM - SIGNWRITING AIR SUCKING IN */ + { RANGE_0WIDTH(0x1DA3B, 0x1DA6C) }, /* SIGNWRITING MOUTH CLOSED NEUTRAL - SIGNWRITING EXCITEMENT */ + { RANGE_0WIDTH(0x1DA75, 0x1DA75) }, /* SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS */ + { RANGE_0WIDTH(0x1DA84, 0x1DA84) }, /* SIGNWRITING LOCATION HEAD NECK */ + { RANGE_0WIDTH(0x1DA9B, 0x1DA9F) }, /* SIGNWRITING FILL MODIFIER-2 - SIGNWRITING FILL MODIFIER-6 */ + { RANGE_0WIDTH(0x1DAA1, 0x1DAAF) }, /* SIGNWRITING ROTATION MODIFIER-2 - SIGNWRITING ROTATION MODIFIER-16 */ + { RANGE_0WIDTH(0x1E000, 0x1E006) }, /* COMBINING GLAGOLITIC LETTER AZU - COMBINING GLAGOLITIC LETTER ZHIVETE */ + { RANGE_0WIDTH(0x1E008, 0x1E018) }, /* COMBINING GLAGOLITIC LETTER ZEMLJA - COMBINING GLAGOLITIC LETTER HERU */ + { RANGE_0WIDTH(0x1E01B, 0x1E021) }, /* COMBINING GLAGOLITIC LETTER SHTA - COMBINING GLAGOLITIC LETTER YATI */ + { RANGE_0WIDTH(0x1E023, 0x1E024) }, /* COMBINING GLAGOLITIC LETTER YU - COMBINING GLAGOLITIC LETTER SMALL YUS */ + { RANGE_0WIDTH(0x1E026, 0x1E02A) }, /* COMBINING GLAGOLITIC LETTER YO - COMBINING GLAGOLITIC LETTER FITA */ + { RANGE_0WIDTH(0x1E08F, 0x1E08F) }, /* COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I */ + { RANGE_0WIDTH(0x1E130, 0x1E136) }, /* NYIAKENG PUACHUE HMONG TONE-B - NYIAKENG PUACHUE HMONG TONE-D */ + { RANGE_0WIDTH(0x1E2AE, 0x1E2AE) }, /* TOTO SIGN RISING TONE */ + { RANGE_0WIDTH(0x1E2EC, 0x1E2EF) }, /* WANCHO TONE TUP - WANCHO TONE KOINI */ + { RANGE_0WIDTH(0x1E4EC, 0x1E4EF) }, /* NAG MUNDARI SIGN MUHOR - NAG MUNDARI SIGN SUTUH */ + { RANGE_0WIDTH(0x1E5EE, 0x1E5EF) }, /* OL ONAL SIGN MU - OL ONAL SIGN IKIR */ + { RANGE_0WIDTH(0x1E8D0, 0x1E8D6) }, /* MENDE KIKAKUI COMBINING NUMBER TEENS - MENDE KIKAKUI COMBINING NUMBER MILLIONS */ + { RANGE_0WIDTH(0x1E944, 0x1E94A) }, /* ADLAM ALIF LENGTHENER - ADLAM NUKTA */ + { RANGE_2WIDTH(0x1F000, 0x1F02F) }, /* U+1F000 - U+1F02F */ + { RANGE_2WIDTH(0x1F0A0, 0x1F0FF) }, /* U+1F0A0 - U+1F0FF */ + { RANGE_2WIDTH(0x1F18E, 0x1F18E) }, /* NEGATIVE SQUARED AB */ + { RANGE_2WIDTH(0x1F191, 0x1F19A) }, /* SQUARED CL - SQUARED VS */ + { RANGE_2WIDTH(0x1F200, 0x1F202) }, /* SQUARE HIRAGANA HOKA - SQUARED KATAKANA SA */ + { RANGE_2WIDTH(0x1F210, 0x1F23B) }, /* SQUARED CJK UNIFIED IDEOGRAPH-624B - SQUARED CJK UNIFIED IDEOGRAPH-914D */ + { RANGE_2WIDTH(0x1F240, 0x1F248) }, /* TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C - TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 */ + { RANGE_2WIDTH(0x1F250, 0x1F251) }, /* CIRCLED IDEOGRAPH ADVANTAGE - CIRCLED IDEOGRAPH ACCEPT */ + { RANGE_2WIDTH(0x1F260, 0x1F265) }, /* ROUNDED SYMBOL FOR FU - ROUNDED SYMBOL FOR CAI */ + { RANGE_2WIDTH(0x1F300, 0x1F3FA) }, /* CYCLONE - AMPHORA */ + { RANGE_0WIDTH(0x1F3FB, 0x1F3FF) }, /* EMOJI MODIFIER FITZPATRICK TYPE-1-2 - EMOJI MODIFIER FITZPATRICK TYPE-6 */ + { RANGE_2WIDTH(0x1F400, 0x1F64F) }, /* RAT - PERSON WITH FOLDED HANDS */ + { RANGE_2WIDTH(0x1F680, 0x1F9AF) }, /* ROCKET - PROBING CANE */ + { RANGE_0WIDTH(0x1F9B0, 0x1F9B3) }, /* EMOJI COMPONENT RED HAIR - EMOJI COMPONENT WHITE HAIR */ + { RANGE_2WIDTH(0x1F9B4, 0x1FAFF) }, /* U+1F9B4 - U+1FAFF */ + { RANGE_2WIDTH(0x20000, 0x2FFFD) }, /* U+20000 - U+2FFFD */ + { RANGE_2WIDTH(0x30000, 0x3FFFD) }, /* U+30000 - U+3FFFD */ + { RANGE_0WIDTH(0xE0001, 0xE0001) }, /* LANGUAGE TAG */ + { RANGE_0WIDTH(0xE0020, 0xE007F) }, /* TAG SPACE - CANCEL TAG */ + { RANGE_0WIDTH(0xE0100, 0xE01EF) }, /* VARIATION SELECTOR-17 - VARIATION SELECTOR-256 */ }; diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index e99636ab9db5..cf26fb8f6545 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -3094,8 +3094,12 @@ static void vc_con_rewind(struct vc_data *vc) static int vc_process_ucs(struct vc_data *vc, int *c, int *tc) { u32 prev_c, curr_c = *c; + unsigned int w = ucs_get_width(curr_c); - if (ucs_is_double_width(curr_c)) { + if (likely(w == 1)) + return 1; + + if (w == 2) { /* * The Unicode screen memory is allocated only when * required. This is one such case as we need to remember @@ -3105,12 +3109,9 @@ static int vc_process_ucs(struct vc_data *vc, int *c, int *tc) return 2; } - if (!ucs_is_zero_width(curr_c)) - return 1; - /* From here curr_c is known to be zero-width. */ - if (ucs_is_double_width(vc_uniscr_getc(vc, -2))) { + if (ucs_get_width(vc_uniscr_getc(vc, -2)) == 2) { /* * Let's merge this zero-width code point with the preceding * double-width code point by replacing the existing diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h index 6180b803795c..539d488fdc03 100644 --- a/include/linux/consolemap.h +++ b/include/linux/consolemap.h @@ -28,8 +28,7 @@ int conv_uni_to_pc(struct vc_data *conp, long ucs); u32 conv_8bit_to_uni(unsigned char c); int conv_uni_to_8bit(u32 uni); void console_map_init(void); -bool ucs_is_double_width(uint32_t cp); -bool ucs_is_zero_width(uint32_t cp); +unsigned int ucs_get_width(uint32_t cp); u32 ucs_recompose(u32 base, u32 mark); u32 ucs_get_fallback(u32 cp); #else @@ -62,14 +61,9 @@ static inline int conv_uni_to_8bit(u32 uni) static inline void console_map_init(void) { } -static inline bool ucs_is_double_width(uint32_t cp) +static inline unsigned int ucs_get_width(uint32_t cp) { - return false; -} - -static inline bool ucs_is_zero_width(uint32_t cp) -{ - return false; + return 1; } static inline u32 ucs_recompose(u32 base, u32 mark)