diff options
Diffstat (limited to 'lib/uninorm/canonical-decomposition.c')
| -rw-r--r-- | lib/uninorm/canonical-decomposition.c | 104 |
1 files changed, 52 insertions, 52 deletions
diff --git a/lib/uninorm/canonical-decomposition.c b/lib/uninorm/canonical-decomposition.c index 210b74b..e6e39e0 100644 --- a/lib/uninorm/canonical-decomposition.c +++ b/lib/uninorm/canonical-decomposition.c @@ -1,5 +1,5 @@ /* Canonical decomposition of Unicode characters. - Copyright (C) 2009 Free Software Foundation, Inc. + Copyright (C) 2009-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2009. This program is free software: you can redistribute it and/or modify it @@ -31,77 +31,77 @@ uc_canonical_decomposition (ucs4_t uc, ucs4_t *decomposition) { /* Hangul syllable. See Unicode standard, chapter 3, section "Hangul Syllable Decomposition", See also the clarification at - <http://www.unicode.org/versions/Unicode5.1.0/>, section - "Clarification of Hangul Jamo Handling". */ + <http://www.unicode.org/versions/Unicode5.1.0/>, section + "Clarification of Hangul Jamo Handling". */ unsigned int t; uc -= 0xAC00; t = uc % 28; if (t == 0) - { - unsigned int v, l; + { + unsigned int v, l; - uc = uc / 28; - v = uc % 21; - l = uc / 21; + uc = uc / 28; + v = uc % 21; + l = uc / 21; - decomposition[0] = 0x1100 + l; - decomposition[1] = 0x1161 + v; - return 2; - } + decomposition[0] = 0x1100 + l; + decomposition[1] = 0x1161 + v; + return 2; + } else - { + { #if 1 /* Return the pairwise decomposition, not the full decomposition. */ - decomposition[0] = 0xAC00 + uc - t; /* = 0xAC00 + (l * 21 + v) * 28; */ - decomposition[1] = 0x11A7 + t; - return 2; + decomposition[0] = 0xAC00 + uc - t; /* = 0xAC00 + (l * 21 + v) * 28; */ + decomposition[1] = 0x11A7 + t; + return 2; #else - unsigned int v, l; + unsigned int v, l; - uc = uc / 28; - v = uc % 21; - l = uc / 21; + uc = uc / 28; + v = uc % 21; + l = uc / 21; - decomposition[0] = 0x1100 + l; - decomposition[1] = 0x1161 + v; - decomposition[2] = 0x11A7 + t; - return 3; + decomposition[0] = 0x1100 + l; + decomposition[1] = 0x1161 + v; + decomposition[2] = 0x11A7 + t; + return 3; #endif - } + } } else if (uc < 0x110000) { unsigned short entry = decomp_index (uc); /* An entry of (unsigned short)(-1) denotes an absent entry. - Otherwise, bit 15 of the entry tells whether the decomposition - is a canonical one. */ + Otherwise, bit 15 of the entry tells whether the decomposition + is a canonical one. */ if (entry < 0x8000) - { - const unsigned char *p; - unsigned int element; - unsigned int length; - - p = &gl_uninorm_decomp_chars_table[3 * entry]; - element = (p[0] << 16) | (p[1] << 8) | p[2]; - /* The first element has 5 bits for the decomposition type. */ - if (((element >> 18) & 0x1f) != UC_DECOMP_CANONICAL) - abort (); - length = 1; - for (;;) - { - /* Every element has an 18 bits wide Unicode code point. */ - *decomposition = element & 0x3ffff; - /* Bit 23 tells whether there are more elements, */ - if ((element & (1 << 23)) == 0) - break; - p += 3; - element = (p[0] << 16) | (p[1] << 8) | p[2]; - decomposition++; - length++; - } - return length; - } + { + const unsigned char *p; + unsigned int element; + unsigned int length; + + p = &gl_uninorm_decomp_chars_table[3 * entry]; + element = (p[0] << 16) | (p[1] << 8) | p[2]; + /* The first element has 5 bits for the decomposition type. */ + if (((element >> 18) & 0x1f) != UC_DECOMP_CANONICAL) + abort (); + length = 1; + for (;;) + { + /* Every element has an 18 bits wide Unicode code point. */ + *decomposition = element & 0x3ffff; + /* Bit 23 tells whether there are more elements, */ + if ((element & (1 << 23)) == 0) + break; + p += 3; + element = (p[0] << 16) | (p[1] << 8) | p[2]; + decomposition++; + length++; + } + return length; + } } return -1; } |