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
|
#include "Paragraphs.h"
#include "vcpkg_Files.h"
namespace vcpkg::Paragraphs
{
struct Parser
{
Parser(const char* c, const char* e) : cur(c), end(e)
{
}
private:
const char* cur;
const char* const end;
void peek(char& ch) const
{
if (cur == end)
ch = 0;
else
ch = *cur;
}
void next(char& ch)
{
if (cur == end)
ch = 0;
else
{
++cur;
peek(ch);
}
}
void skip_spaces(char& ch)
{
while (ch == ' ' || ch == '\t')
next(ch);
}
static bool is_alphanum(char ch)
{
return (ch >= 'A' && ch <= 'Z')
|| (ch >= 'a' && ch <= 'z')
|| (ch >= '0' && ch <= '9');
}
static bool is_lineend(char ch)
{
return ch == '\r' || ch == '\n' || ch == 0;
}
void get_fieldvalue(char& ch, std::string& fieldvalue)
{
fieldvalue.clear();
auto beginning_of_line = cur;
do
{
// scan to end of current line (it is part of the field value)
while (!is_lineend(ch))
next(ch);
fieldvalue.append(beginning_of_line, cur);
if (ch == '\r')
next(ch);
if (ch == '\n')
next(ch);
if (is_alphanum(ch))
{
// Line begins a new field.
return;
}
beginning_of_line = cur;
// Line may continue the current field with data or terminate the paragraph,
// depending on first nonspace character.
skip_spaces(ch);
if (is_lineend(ch))
{
// Line was whitespace or empty.
// This terminates the field and the paragraph.
// We leave the blank line's whitespace consumed, because it doesn't matter.
return;
}
// First nonspace is not a newline. This continues the current field value.
// We forcibly convert all newlines into single '\n' for ease of text handling later on.
fieldvalue.push_back('\n');
}
while (true);
}
void get_fieldname(char& ch, std::string& fieldname)
{
auto begin_fieldname = cur;
while (is_alphanum(ch) || ch == '-')
next(ch);
Checks::check_throw(ch == ':', "Expected ':'");
fieldname = std::string(begin_fieldname, cur);
// skip ': '
next(ch);
skip_spaces(ch);
}
void get_paragraph(char& ch, std::unordered_map<std::string, std::string>& fields)
{
fields.clear();
std::string fieldname;
std::string fieldvalue;
do
{
get_fieldname(ch, fieldname);
auto it = fields.find(fieldname);
Checks::check_throw(it == fields.end(), "Duplicate field");
get_fieldvalue(ch, fieldvalue);
fields.emplace(fieldname, fieldvalue);
}
while (!is_lineend(ch));
}
public:
std::vector<std::unordered_map<std::string, std::string>> get_paragraphs()
{
std::vector<std::unordered_map<std::string, std::string>> paragraphs;
char ch;
peek(ch);
while (ch != 0)
{
if (ch == '\n' || ch == '\r' || ch == ' ' || ch == '\t')
{
next(ch);
continue;
}
paragraphs.emplace_back();
get_paragraph(ch, paragraphs.back());
}
return paragraphs;
}
};
std::vector<std::unordered_map<std::string, std::string>> get_paragraphs(const fs::path& control_path)
{
return parse_paragraphs(Files::read_contents(control_path).get_or_throw());
}
std::vector<std::unordered_map<std::string, std::string>> parse_paragraphs(const std::string& str)
{
return Parser(str.c_str(), str.c_str() + str.size()).get_paragraphs();
}
}
|
