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
|
/*
* Copyright (c) 2022, Andreas Kling <kling@serenityos.org>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
#include <AK/BinarySearch.h>
#include <AK/Utf8View.h>
#include <LibJS/SourceCode.h>
#include <LibJS/SourceRange.h>
#include <LibJS/Token.h>
namespace JS {
NonnullRefPtr<SourceCode> SourceCode::create(DeprecatedString filename, DeprecatedString code)
{
return adopt_ref(*new SourceCode(move(filename), move(code)));
}
SourceCode::SourceCode(DeprecatedString filename, DeprecatedString code)
: m_filename(move(filename))
, m_code(move(code))
{
}
DeprecatedString const& SourceCode::filename() const
{
return m_filename;
}
DeprecatedString const& SourceCode::code() const
{
return m_code;
}
void SourceCode::compute_line_break_offsets() const
{
m_line_break_offsets = Vector<size_t> {};
if (m_code.is_empty())
return;
bool previous_code_point_was_carriage_return = false;
Utf8View view(m_code.view());
for (auto it = view.begin(); it != view.end(); ++it) {
u32 code_point = *it;
bool is_line_terminator = code_point == '\r' || (code_point == '\n' && !previous_code_point_was_carriage_return) || code_point == LINE_SEPARATOR || code_point == PARAGRAPH_SEPARATOR;
previous_code_point_was_carriage_return = code_point == '\r';
if (is_line_terminator)
m_line_break_offsets->append(view.byte_offset_of(it));
}
}
SourceRange SourceCode::range_from_offsets(u32 start_offset, u32 end_offset) const
{
// If the underlying code is an empty string, the range is 1,1 - 1,1 no matter what.
if (m_code.is_empty())
return { *this, { .line = 1, .column = 1, .offset = 0 }, { .line = 1, .column = 1, .offset = 0 } };
if (!m_line_break_offsets.has_value())
compute_line_break_offsets();
size_t line = 1;
size_t nearest_line_break_index = 0;
size_t nearest_preceding_line_break_offset = 0;
if (!m_line_break_offsets->is_empty()) {
binary_search(*m_line_break_offsets, start_offset, &nearest_line_break_index);
line = 1 + nearest_line_break_index;
nearest_preceding_line_break_offset = (*m_line_break_offsets)[nearest_line_break_index];
}
Optional<Position> start;
Optional<Position> end;
size_t column = 1;
bool previous_code_point_was_carriage_return = false;
Utf8View view(m_code.view());
for (auto it = view.iterator_at_byte_offset_without_validation(nearest_preceding_line_break_offset); it != view.end(); ++it) {
// If we're on or after the start offset, this is the start position.
if (!start.has_value() && view.byte_offset_of(it) >= start_offset) {
start = Position {
.line = line,
.column = column,
.offset = start_offset,
};
}
// If we're on or after the end offset, this is the end position.
if (!end.has_value() && view.byte_offset_of(it) >= end_offset) {
end = Position {
.line = line,
.column = column,
.offset = end_offset,
};
break;
}
u32 code_point = *it;
bool is_line_terminator = code_point == '\r' || (code_point == '\n' && !previous_code_point_was_carriage_return) || code_point == LINE_SEPARATOR || code_point == PARAGRAPH_SEPARATOR;
previous_code_point_was_carriage_return = code_point == '\r';
if (is_line_terminator) {
++line;
column = 1;
continue;
}
++column;
}
// If we didn't find both a start and end position, just return 1,1-1,1.
// FIXME: This is a hack. Find a way to return the nicest possible values here.
if (!start.has_value() || !end.has_value())
return SourceRange { *this, { .line = 1, .column = 1 }, { .line = 1, .column = 1 } };
return SourceRange { *this, *start, *end };
}
}
|
