lib/unilbrk/lbrktables.h

   1 /* Line breaking auxiliary tables.
   2    Copyright (C) 2001-2003, 2006-2024 Free Software Foundation, Inc.
   3    Written by Bruno Haible <bruno@clisp.org>, 2001.
   4
   5    This file is free software.
   6    It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".
   7    You can redistribute it and/or modify it under either
   8      - the terms of the GNU Lesser General Public License as published
   9        by the Free Software Foundation, either version 3, or (at your
  10        option) any later version, or
  11      - the terms of the GNU General Public License as published by the
  12        Free Software Foundation; either version 2, or (at your option)
  13        any later version, or
  14      - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".
  15
  16    This file is distributed in the hope that it will be useful,
  17    but WITHOUT ANY WARRANTY; without even the implied warranty of
  18    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  19    Lesser General Public License and the GNU General Public License
  20    for more details.
  21
  22    You should have received a copy of the GNU Lesser General Public
  23    License and of the GNU General Public License along with this
  24    program.  If not, see <https://www.gnu.org/licenses/>.  */
  25
  26 #include "unitypes.h"
  27
  28 #ifdef __cplusplus
  29 extern "C" {
  30 #endif
  31
  32
  33 /* Line breaking classification.  */
  34
  35 enum
  36 {
  37   /* Values >= 40 are resolved at run time. */
  38   LBP_BK  = 40, /* mandatory break */
  39   LBP_CR  = 41, /* carriage return */
  40   LBP_LF  = 42, /* line feed */
  41   LBP_CM  = 43, /* attached characters and combining marks */
  42 /*LBP_NL,          next line - not used here because it's equivalent to LBP_BK */
  43 /*LBP_SG,          surrogates - not used here because they are not characters */
  44   LBP_WJ  =  0, /* word joiner */
  45   LBP_ZW  = 44, /* zero width space */
  46   LBP_GL  =  1, /* non-breaking (glue) */
  47   LBP_SP  = 45, /* space */
  48   LBP_B2  =  2, /* break opportunity before and after */
  49   LBP_BA  =  3, /* break opportunity after */
  50   LBP_BB  =  4, /* break opportunity before */
  51   LBP_HY  =  5, /* hyphen */
  52   LBP_CB  = 46, /* contingent break opportunity */
  53   LBP_CL  =  6, /* closing punctuation */
  54   LBP_CP1 =  7, /* closing parenthesis, non-EastAsian character */
  55   LBP_CP2 =  8, /* closing parenthesis, EastAsian character */
  56   LBP_EX  =  9, /* exclamation/interrogation */
  57   LBP_IN  = 10, /* inseparable */
  58   LBP_NS  = 11, /* non starter */
  59   LBP_OP1 = 12, /* opening punctuation, non-EastAsian character */
  60   LBP_OP2 = 13, /* opening punctuation, EastAsian character */
  61   LBP_QU1 = 14, /* ambiguous quotation, neither initial nor final punctuation */
  62   LBP_QU2 = 15, /* ambiguous quotation, initial punctuation */
  63   LBP_QU3 = 16, /* ambiguous quotation, final punctuation */
  64   LBP_IS  = 17, /* infix separator (numeric) */
  65   LBP_NU  = 18, /* numeric */
  66   LBP_PO  = 19, /* postfix (numeric) */
  67   LBP_PR  = 20, /* prefix (numeric) */
  68   LBP_SY  = 21, /* symbols allowing breaks */
  69   LBP_AI  = 47, /* ambiguous (alphabetic or ideograph) */
  70   LBP_AL  = 22, /* ordinary alphabetic and symbol characters */
  71 /*LBP_CJ,          conditional Japanese starter, resolved to NS */
  72   LBP_H2  = 23, /* Hangul LV syllable */
  73   LBP_H3  = 24, /* Hangul LVT syllable */
  74   LBP_HL  = 30, /* Hebrew letter */
  75   LBP_ID1 = 25, /* ideographic */
  76   LBP_ID2 = 26, /* ideographic and potential future emoji */
  77   LBP_JL  = 27, /* Hangul L Jamo */
  78   LBP_JV  = 28, /* Hangul V Jamo */
  79   LBP_JT  = 29, /* Hangul T Jamo */
  80   LBP_AP  = 31, /* Brahmic scripts: pre-base repha */
  81   LBP_AK  = 32, /* Brahmic scripts: consonants */
  82   LBP_AS  = 33, /* Brahmic scripts: independent vowels */
  83   LBP_VI  = 34, /* Brahmic scripts: conjoining viramas */
  84   LBP_VF  = 35, /* Brahmic scripts: viramas for final consonants */
  85   LBP_RI  = 36, /* regional indicator */
  86   LBP_SA  = 48, /* complex context (South East Asian) */
  87   LBP_ZWJ = 37, /* zero width joiner */
  88   LBP_EB  = 38, /* emoji base */
  89   LBP_EM  = 39, /* emoji modifier */
  90   LBP_XX  = 49, /* unknown */
  91   /* Artificial values that exist only at runtime, not in the tables. */
  92   LBP_HL_BA = 100
  93 };
  94
  95 #include "lbrkprop1.h"
  96
  97 static inline unsigned char
  98 unilbrkprop_lookup (ucs4_t uc)
  99 {
 100   unsigned int index1 = uc >> lbrkprop_header_0;
 101   if (index1 < lbrkprop_header_1)
 102     {
 103       int lookup1 = unilbrkprop.level1[index1];
 104       if (lookup1 >= 0)
 105         {
 106           unsigned int index2 = (uc >> lbrkprop_header_2) & lbrkprop_header_3;
 107           int lookup2 = unilbrkprop.level2[lookup1 + index2];
 108           if (lookup2 >= 0)
 109             {
 110               unsigned int index3 = uc & lbrkprop_header_4;
 111               return unilbrkprop.level3[lookup2 + index3];
 112             }
 113         }
 114     }
 115   return LBP_XX;
 116 }
 117
 118 /* Table indexed by two line breaking classifications.  */
 119 #define D 1  /* direct break opportunity, empty in table 7.3 of UTR #14 */
 120 #define I 2  /* indirect break opportunity, '%' in table 7.3 of UTR #14 */
 121 #define P 3  /* prohibited break,           '^' in table 7.3 of UTR #14 */
 122
 123 extern const unsigned char unilbrk_table[40][40];
 124
 125 /* We don't support line breaking of complex-context dependent characters
 126    (Thai, Lao, Myanmar, Khmer) yet, because it requires dictionary lookup. */
 127
 128
 129 #ifdef __cplusplus
 130 }
 131 #endif