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
use crate::{
CHARDATA_CHUNK_LENGTH,
error::XMLError,
sax::{InputSource, ParserSpec, SAXHandler, XMLReader, error::fatal_error},
};
impl<'a, Spec: ParserSpec<Reader = InputSource<'a>>, H: SAXHandler + ?Sized> XMLReader<Spec, H> {
/// ```text
/// [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)
/// ```
pub(crate) fn parse_char_data(&mut self) -> Result<(), XMLError> {
self.source.grow()?;
if self.source.content_bytes().is_empty() {
return Ok(());
}
self.text_buffer.clear();
let mut non_whitespace = 0usize;
'outer: loop {
while let content = self.source.content_bytes()
&& !content.is_empty()
&& !matches!(content[0], b'<' | b'&')
{
if content[0] == b'\r' {
self.source.advance(1);
if self.source.content_bytes().first() != Some(&b'\n') {
self.locator.update_line(|l| l + 1);
self.locator.set_column(1);
self.text_buffer.push('\n');
}
} else if content[0] == b'\n' {
self.source.advance(1);
self.locator.update_line(|l| l + 1);
self.locator.set_column(1);
self.text_buffer.push('\n');
} else if content[0] == b']' {
if content.starts_with(b"]]>") {
fatal_error!(
self,
ParserUnacceptablePatternInCharData,
"']]>' is not allowed in a character data."
);
}
self.source.advance(1);
self.locator.update_column(|c| c + 1);
self.text_buffer.push(']');
non_whitespace += 1;
} else if matches!(content[0], b'\x20' | b'\t') {
self.text_buffer.push(content[0] as char);
self.source.advance(1);
self.locator.update_column(|c| c + 1);
} else if let at = content
.iter()
.position(|&b| !matches!(b, 0x21..0x80) || b == b'<' || b == b'&' || b == b']')
.unwrap_or(content.len())
&& at > 0
{
let at = at.min(CHARDATA_CHUNK_LENGTH.saturating_sub(self.text_buffer.len()));
non_whitespace += at;
self.text_buffer.push_str(unsafe {
// # Safety
// `content[..at]` contains only ASCII graphic characters
// other than '<', '&' and ']', so UTF-8 validation won't fail.
std::str::from_utf8_unchecked(&content[..at])
});
self.source.advance(at);
self.locator.update_column(|c| c + at);
} else {
match self.source.next_char()? {
Some(c) if self.is_char(c) => {
self.locator.update_column(|c| c + 1);
self.text_buffer.push(c);
if !self.is_whitespace(c) {
non_whitespace += c.len_utf8();
}
}
Some(c) => {
fatal_error!(
self,
ParserInvalidCharacter,
"The characeter '0x{:X}' is not allowed in the XML document.",
c as u32
);
self.locator.update_column(|c| c + 1);
self.text_buffer.push(c);
non_whitespace += c.len_utf8();
}
_ => unreachable!(),
}
}
if self.text_buffer.len() >= CHARDATA_CHUNK_LENGTH {
if !self.fatal_error_occurred {
if let Some(Some((_, validator))) = self.validation_stack.last_mut() {
if non_whitespace != self.text_buffer.len() {
validator.push_whitespaces();
}
if non_whitespace == 0 && validator.is_element_content() {
self.handler.ignorable_whitespace(&self.text_buffer);
} else {
validator.push_pcdata();
self.handler.characters(&self.text_buffer);
}
} else {
self.handler.characters(&self.text_buffer);
}
}
self.text_buffer.clear();
non_whitespace = 0;
}
// Since it is necessary to check whether ']]>' is included,
// maintain at least 3 bytes as much as possible.
if self.source.content_bytes().len() < 3 {
self.source.grow()?;
if self.source.content_bytes().is_empty() {
break 'outer;
}
}
}
self.source.grow()?;
if self.source.content_bytes().starts_with(b"&#") {
// Resolve character references here and include them in the character data.
let c = self.parse_char_ref()?;
self.text_buffer.push(c);
non_whitespace += c.len_utf8();
if self.text_buffer.len() >= CHARDATA_CHUNK_LENGTH {
if !self.fatal_error_occurred {
if let Some(Some((_, validator))) = self.validation_stack.last_mut() {
if non_whitespace != self.text_buffer.len() {
validator.push_whitespaces();
}
if non_whitespace == 0 && validator.is_element_content() {
self.handler.ignorable_whitespace(&self.text_buffer);
} else {
validator.push_pcdata();
self.handler.characters(&self.text_buffer);
}
} else {
self.handler.characters(&self.text_buffer);
}
}
self.text_buffer.clear();
non_whitespace = 0;
}
} else {
// Do not process references other than character references or markup here,
// and exit the loop.
break;
}
}
if !self.text_buffer.is_empty() && !self.fatal_error_occurred {
if let Some(Some((_, validator))) = self.validation_stack.last_mut() {
if non_whitespace != self.text_buffer.len() {
validator.push_whitespaces();
}
if non_whitespace == 0 && validator.is_element_content() {
self.handler.ignorable_whitespace(&self.text_buffer);
} else {
validator.push_pcdata();
self.handler.characters(&self.text_buffer);
}
} else {
self.handler.characters(&self.text_buffer);
}
}
Ok(())
}
}