1UNICODE::LINEBREAK(3) Courier Unicode Library UNICODE::LINEBREAK(3)
2
3
4
6 unicode::linebreak_callback_base, unicode::linebreak_callback_save_buf,
7 unicode::linebreakc_callback_base, unicode::linebreak_iter,
8 unicode::linebreakc_iter - unicode line-breaking rules
9
11 #include <courier-unicode.h>
12
13 class linebreak : public unicode::linebreak_callback_base {
14
15 public:
16
17 using unicode::linebreak_callback_base::operator<<;
18 using unicode::linebreak_callback_base::operator();
19 int callback(int linebreak_code)
20 {
21 // ...
22 }
23 };
24
25 char32_t c;
26 std::u32string buf;
27
28 linebreak compute_linebreak;
29
30 compute_linebreak.set_opts(UNICODE_LB_OPT_SYBREAK);
31 compute_linebreak << c;
32
33 compute_linebreak(buf);
34 compute_linebreak(buf.begin(), buf.end());
35
36 compute_linebreak.finish();
37
38 // ...
39
40 unicode::linebreak_callback_save_buf linebreaks;
41
42 std::list<int> lb=linebreaks.lb_buf;
43
44 class linebreakc : public unicode::linebreakc_callback_base {
45
46 public:
47
48 using unicode::linebreak_callback_base::operator<<;
49 using unicode::linebreak_callback_base::operator();
50 int callback(int linebreak_code, char32_t ch)
51 {
52 // ...
53 }
54 };
55
56 // ...
57
58 std::u32string buf;
59
60 typedef unicode::linebreak_iter<std::u32string::const_iterator> iter_t;
61
62 iter_t beg_iter(buf.begin(), buf.end()), end_iter;
63
64 beg_iter.set_opts(UNICODE_LB_OPT_SYBREAK);
65
66 std::vector<int> linebreaks;
67
68 std::copy(beg_iter, end_iter, std::back_insert_iterator<std::vector<int>>(linebreaks));
69
70 // ...
71
72 typedef unicode::linebreakc_iter<std::u32string::const_iterator> iter_t;
73
74 iter_t beg_iter(buf.begin(), buf.end()), end_iter;
75
76 beg_iter.set_opts(UNICODE_LB_OPT_SYBREAK);
77
78 std::vector<std::pair<int, char32_t>> linebreaks;
79
80 std::copy(beg_iter, end_iter, std::back_insert_iterator<std::vector<int>>(linebreaks));
81
83 unicode::linebreak_callback_base is a C++ binding for the unicode
84 line-breaking rule implementation described in unicode_line_break(3).
85
86 Subclass unicode::linebreak_callback_base and implement callback()
87 that's virtually inherited from unicode::linebreak_callback_base. The
88 callback() callback function receives the output values from the
89 line-breaking algorithm, the UNICODE_LB_MANDATORY, UNICODE_LB_NONE, or
90 the UNICODE_LB_ALLOWED value, for each unicode character.
91
92 callback() should return 0. A non-zero return reports an error, that
93 stops the line-breaking algorithm. See unicode_line_break(3) for more
94 information.
95
96 The alternate unicode::linebreakc_callback_base interface uses a
97 virtually inherited callback() that receives two parameters, the
98 line-break code value, and the corresponding unicode character.
99
100 The input unicode characters for the line-breaking algorithm are
101 provided by the << operator, one unicode character at a time; or by the
102 () operator, passing either a container, or a beginning and an ending
103 iterator value for an input sequence of unicode characters. finish()
104 indicates the end of the unicode character sequence.
105
106 set_opts sets line-breaking options (see unicode_lb_set_opts() for more
107 information).
108
109 unicode::linebreak_callback_save_buf is a subclass that implements
110 callback() by saving the linebreaks codes into a std::list.
111
112 The linebreak_iter template implements an input iterator over ints. The
113 template parameter is an input iterator over unicode chars. The
114 constructor's parameters are a beginning and an ending iterator value
115 for a sequence of char32_t. This constructs the beginning iterator
116 value for a sequence of ints consisting of line-break values
117 (UNICODE_LB_MANDATORY, UNICODE_LB_NONE, or UNICODE_LB_ALLOWED)
118 corresponding to each char32_t in the underlying sequence. The default
119 constructor creates the ending iterator value for the sequence.
120
121 The iterator implements a set_opts() methods that sets the options for
122 the line-breaking algorithm.
123
124 The linebreakc_iter template implements a similar input iterator, with
125 the difference that it ends up iterating over a std::pair of
126 line-breaking values and the corresponding char32_t from the underlying
127 input sequence.
128
130 courier-unicode(7), unicode_line_break(3).
131
133 Sam Varshavchik
134 Author
135
136
137
138Courier Unicode Library 03/11/2017 UNICODE::LINEBREAK(3)