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
171
172
173
174
175
176
177
178
179
180
181
182
183
|
#include "line_accumulator.h"
#include <cassert>
#include <iostream>
#include <algorithm>
namespace {
std::uint8_t getRandomIndex(
std::mt19937& generator,
const std::uint8_t n
) {
return std::uniform_int_distribution<std::uint8_t>{0, n}(generator);
}
std::vector<std::uint8_t> getRandomIndizes(
std::mt19937& generator,
const std::uint8_t n
) {
std::vector<std::uint8_t> indizes(n);
std::iota(indizes.begin(), indizes.end(), 0);
std::shuffle(
indizes.begin(),
indizes.end(),
generator
);
return indizes;
}
std::size_t getCharacterLength(const std::string& token) {
std::size_t codeUnitIndex = 0;
std::size_t codePointIndex = 0;
while ( token.data()[codeUnitIndex] ) {
// advance `codePointIndex` if current unit is not a continuation byte
// see RFC3629 for further information
if ( (token.data()[codeUnitIndex] & 0b11000000 ) != 0b10000000 ) {
++codePointIndex;
}
++codeUnitIndex;
}
return codePointIndex;
}
}
namespace justify {
LineAccumulator::LineAccumulator(
const std::uint8_t max_length,
const std::uint8_t offset,
const std::uint32_t seed
):
max_length_{max_length},
offset_{offset},
generator_{seed},
length_{0},
tokens_{} { }
LineAccumulator::~LineAccumulator() {
this->discharge(false);
}
void LineAccumulator::operator()(const std::string& token) {
const std::size_t tokenLength = getCharacterLength(token);
if ( tokenLength > this->getMissing() ) {
this->discharge(true);
}
this->tokens_.emplace_back(token, 0);
this->length_ += tokenLength;
if ( this->getMissing() > 0 ) {
this->tokens_.back().second += 1;
this->length_ += 1;
}
}
std::uint8_t LineAccumulator::getMissing() const {
if ( this->length_ < this->max_length_ ) {
return this->max_length_ - this->length_;
} else {
return 0;
}
}
void LineAccumulator::justify() {
switch ( this->tokens_.size() ) {
// There is no sensible block justification of null or any single token
case 0:
case 1: {
this->length_ = this->max_length_;
break;
}
// i.e. left align the first token and right align the second token
case 2: {
this->tokens_[0].second += this->getMissing();
this->length_ = this->max_length_;
break;
}
// most common branch for normal texts, add the maximum equal amount of
// spaces to all but the last token
default: {
const std::uint8_t base = this->getMissing()
/ (this->tokens_.size() - 2);
std::for_each(
this->tokens_.begin(),
this->tokens_.end() - 2,
[&, base](auto& token) {
token.second += base;
this->length_ += base;
}
);
break;
}
}
assert(this->getMissing() < this->tokens_.size());
switch ( this->getMissing() ) {
case 0: {
break;
}
// randomly distribute missing spaces
case 1: {
this->tokens_[getRandomIndex(
this->generator_,
this->tokens_.size() - 2
)].second += 1;
break;
}
default: {
const auto indizes = getRandomIndizes(
this->generator_,
this->tokens_.size() - 2
);
std::for_each(
indizes.begin(),
indizes.begin() + this->getMissing(),
[&](const std::uint8_t x) {
this->tokens_[x].second += 1;
this->length_ += 1;
}
);
break;
}
}
}
void LineAccumulator::discharge(const bool full) {
this->length_ -= this->tokens_.back().second;
this->tokens_.back().second = 0;
if ( full ) {
this->justify();
}
if ( this->offset_ > 0 ) {
std::cout << std::string(this->offset_, ' ');
}
for ( const auto& token : this->tokens_ ) {
std::cout << token.first
<< std::string(token.second, ' ');
}
std::cout << '\n';
this->length_ = 0;
this->tokens_.clear();
}
}
|
