summaryrefslogtreecommitdiff
path: root/lib/uniwbrk/u-wordbreaks.h
blob: 1be288067111a3e7f752446357e76096991f2b05 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
/* Word breaks in UTF-8/UTF-16/UTF-32 strings.  -*- coding: utf-8 -*-
   Copyright (C) 2009-2021 Free Software Foundation, Inc.
   Written by Bruno Haible <bruno@clisp.org>, 2009.

   This file is free software.
   It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".
   You can redistribute it and/or modify it under either
     - the terms of the GNU Lesser General Public License as published
       by the Free Software Foundation; either version 3, or (at your
       option) any later version, or
     - the terms of the GNU General Public License as published by the
       Free Software Foundation; either version 2, or (at your option)
       any later version, or
     - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".

   This file is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License and the GNU General Public License
   for more details.

   You should have received a copy of the GNU Lesser General Public
   License and of the GNU General Public License along with this
   program.  If not, see <https://www.gnu.org/licenses/>.  */

void
FUNC (const UNIT *s, size_t n, char *p)
{
  if (n > 0)
    {
      const UNIT *s_end = s + n;

      /* Word break property of the last character.
         -1 at the very beginning of the string.  */
      int last_char_prop = -1;

      /* Format and Extend characters are ignored; this means, the mostly used
         unit is the complex character (= character with subsequent ignored
         characters).
         Word break property of the last complex character.
         -1 at the very beginning of the string.  */
      int last_compchar_prop = -1;
      char *last_compchar_ptr = NULL;

      /* For recognizing rules involving 3 complex characters:
         Word break property of the second-to-last complex character.
         -1 at the very beginning of the string.  */
      int secondlast_compchar_prop = -1;

      size_t ri_count = 0;

      /* Don't break inside multibyte characters.  */
      memset (p, 0, n);

      while (s < s_end)
        {
          ucs4_t uc;
          int count = U_MBTOUC_UNSAFE (&uc, s, s_end - s);
          int prop = uc_wordbreak_property (uc);

          /* No break at the start of the string.  */
          if (last_char_prop >= 0)
            {
              /* No break between CR and LF (WB3).  */
              if (last_char_prop == WBP_CR && prop == WBP_LF)
                /* *p = 0 */;
              /* Break before and after newlines (WB3a, WB3b).  */
              else if ((last_char_prop == WBP_CR
                        || last_char_prop == WBP_LF
                        || last_char_prop == WBP_NEWLINE)
                       || (prop == WBP_CR
                           || prop == WBP_LF
                           || prop == WBP_NEWLINE))
                *p = 1;
              /* No break within emoji zwj sequence (WB3c).  */
              else if (last_char_prop == WBP_ZWJ &&
                       (prop == WBP_GAZ || prop == WBP_EBG))
                /* *p = 0 */;
              /* Ignore Format and Extend characters.  */
              else if (!(prop == WBP_EXTEND || prop == WBP_FORMAT || prop == WBP_ZWJ))
                {
                  /* No break in these situations (see UAX #29):

                      secondlast          last             current

    (ALetter | HL)   (MidLetter | MidNumLet | SQ) × (ALetter | HL)      (WB7)
    (ALetter | HL) × (MidLetter | MidNumLet | SQ)   (ALetter | HL)      (WB6)
                  Numeric   (MidNum | MidNumLet | SQ)    × Numeric      (WB11)
                  Numeric × (MidNum | MidNumLet | SQ)      Numeric      (WB12)
                                                        HL × DQ HL      (WB7b)
                                                        HL DQ × HL      (WB7c)
                                                ^ (RI RI)* RI × RI      (WB15)
                                            [^RI] (RI RI)* RI × RI      (WB16)
                   */
                  /* No break across certain punctuation.  Also, disable word
                     breaks that were recognized earlier (due to lookahead of
                     only one complex character).  */
                  if (((prop == WBP_ALETTER
                        || prop == WBP_HL)
                       && (last_compchar_prop == WBP_MIDLETTER
                           || last_compchar_prop == WBP_MIDNUMLET
                           || last_compchar_prop == WBP_SQ)
                       && (secondlast_compchar_prop == WBP_ALETTER
                           || secondlast_compchar_prop == WBP_HL))
                      || (prop == WBP_NUMERIC
                          && (last_compchar_prop == WBP_MIDNUM
                              || last_compchar_prop == WBP_MIDNUMLET
                              || last_compchar_prop == WBP_SQ)
                          && secondlast_compchar_prop == WBP_NUMERIC)
                      || (prop == WBP_HL
                          && last_compchar_prop == WBP_DQ
                          && secondlast_compchar_prop == WBP_HL))
                    {
                      *last_compchar_ptr = 0;
                      /* *p = 0; */
                    }
                  /* Break before RI, if odd number of RI's are
                     preceding (WB15, WB16).  */
                  else if (last_compchar_prop == WBP_RI && prop == WBP_RI)
                    {
                      if (ri_count % 2 == 0)
                        *p = 1;
                      /* else *p = 0 */
                    }
                  /* Break after Format and Extend character.  */
                  else if (last_compchar_prop == WBP_EXTEND
                           || last_compchar_prop == WBP_FORMAT)
                    *p = 1;
                  else
                    {
                      int last_compchar_index =
                        uniwbrk_prop_index[last_compchar_prop];
                      int index = uniwbrk_prop_index[prop];

                      /* Break between unknown pair (WB999).  */
                      if (last_compchar_index < 0 || index < 0)
                        *p = 1;
                      /* Perform a single table lookup.  */
                      else if (uniwbrk_table[last_compchar_index][index])
                        *p = 1;
                      /* else *p = 0; */
                    }
                }
            }

          last_char_prop = prop;

          /* Ignore Format and Extend characters, except at the
             start of the line.  */
          if (last_compchar_prop < 0
              || last_compchar_prop == WBP_CR
              || last_compchar_prop == WBP_LF
              || last_compchar_prop == WBP_NEWLINE
              || !(prop == WBP_EXTEND || prop == WBP_FORMAT || prop == WBP_ZWJ))
            {
              secondlast_compchar_prop = last_compchar_prop;
              last_compchar_prop = prop;
              last_compchar_ptr = p;

              if (prop == WBP_RI)
                ri_count++;
              else
                ri_count = 0;
            }

          s += count;
          p += count;
        }
    }
}