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

//! Contains common types and functions used throughout the library.

use std::fmt;

/// Represents a position inside some textual document.
#[derive(Copy, Clone, PartialEq, Eq)]
pub struct TextPosition {
    /// Row, counting from 0
    pub row: u64,
    /// Column, counting from 0
    pub column: u64,
}

impl TextPosition {
    /// Creates a new position initialized to the beginning of the document
    #[inline]
    #[must_use]
    pub fn new() -> TextPosition {
        TextPosition { row: 0, column: 0 }
    }

    /// Advances the position in a line
    #[inline]
    pub fn advance(&mut self, count: u8) {
        self.column += u64::from(count);
    }

    /// Advances the position in a line to the next tab position
    #[inline]
    pub fn advance_to_tab(&mut self, width: u8) {
        let width = u64::from(width);
        self.column += width - self.column % width;
    }

    /// Advances the position to the beginning of the next line
    #[inline]
    pub fn new_line(&mut self) {
        self.column = 0;
        self.row += 1;
    }
}

impl fmt::Debug for TextPosition {
    #[cold]
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        write!(f, "{}:{}", self.row + 1, self.column + 1)
    }
}

impl fmt::Display for TextPosition {
    #[inline]
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        write!(f, "{}:{}", self.row + 1, self.column + 1)
    }
}

/// Get the position in the document corresponding to the object
///
/// This trait is implemented by parsers, lexers and errors.
pub trait Position {
    /// Returns the current position or a position corresponding to the object.
    fn position(&self) -> TextPosition;
}

impl Position for TextPosition {
    #[inline]
    fn position(&self) -> TextPosition {
        *self
    }
}

/// XML version enumeration.
#[derive(Copy, Clone, PartialEq, Eq, PartialOrd, Ord)]
pub enum XmlVersion {
    /// XML version 1.0.
    Version10,

    /// XML version 1.1.
    Version11,
}

impl fmt::Display for XmlVersion {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        match *self {
            XmlVersion::Version10 => "1.0",
            XmlVersion::Version11 => "1.1",
        }.fmt(f)
    }
}

impl fmt::Debug for XmlVersion {
    #[cold]
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        fmt::Display::fmt(self, f)
    }
}

/// Checks whether the given character is a white space character (`S`)
/// as is defined by XML 1.1 specification, [section 2.3][1].
///
/// [1]: http://www.w3.org/TR/2006/REC-xml11-20060816/#sec-common-syn
#[must_use]
#[inline]
pub fn is_whitespace_char(c: char) -> bool {
    matches!(c, '\x20' | '\x0a' | '\x09' | '\x0d')
}

/// Checks whether the given string is compound only by white space
/// characters (`S`) using the previous `is_whitespace_char` to check
/// all characters of this string
pub fn is_whitespace_str(s: &str) -> bool {
    s.chars().all(is_whitespace_char)
}

pub fn is_xml10_char(c: char) -> bool {
    matches!(c, '\u{09}' | '\u{0A}' | '\u{0D}' | '\u{20}'..='\u{D7FF}' | '\u{E000}'..='\u{FFFD}' | '\u{10000}'..)
}

pub fn is_xml11_char(c: char) -> bool {
    matches!(c, '\u{01}'..='\u{D7FF}' | '\u{E000}'..='\u{FFFD}' | '\u{10000}'..)
}

pub fn is_xml11_char_not_restricted(c: char) -> bool {
    is_xml11_char(c) && !matches!(c, '\u{01}'..='\u{08}' | '\u{0B}'..='\u{0C}' | '\u{0E}'..='\u{1F}' | '\u{7F}'..='\u{84}' | '\u{86}'..='\u{9F}')
}

/// Checks whether the given character is a name start character (`NameStartChar`)
/// as is defined by XML 1.1 specification, [section 2.3][1].
///
/// [1]: http://www.w3.org/TR/2006/REC-xml11-20060816/#sec-common-syn
#[must_use]
pub fn is_name_start_char(c: char) -> bool {
    match c {
        ':' | 'A'..='Z' | '_' | 'a'..='z' |
        '\u{C0}'..='\u{D6}' | '\u{D8}'..='\u{F6}' | '\u{F8}'..='\u{2FF}' |
        '\u{370}'..='\u{37D}' | '\u{37F}'..='\u{1FFF}' |
        '\u{200C}'..='\u{200D}' | '\u{2070}'..='\u{218F}' |
        '\u{2C00}'..='\u{2FEF}' | '\u{3001}'..='\u{D7FF}' |
        '\u{F900}'..='\u{FDCF}' | '\u{FDF0}'..='\u{FFFD}' |
        '\u{10000}'..='\u{EFFFF}' => true,
        _ => false
    }
}

/// Checks whether the given character is a name character (`NameChar`)
/// as is defined by XML 1.1 specification, [section 2.3][1].
///
/// [1]: http://www.w3.org/TR/2006/REC-xml11-20060816/#sec-common-syn
#[must_use]
pub fn is_name_char(c: char) -> bool {
    match c {
        _ if is_name_start_char(c) => true,
        '-' | '.' | '0'..='9' | '\u{B7}' |
        '\u{300}'..='\u{36F}' | '\u{203F}'..='\u{2040}' => true,
        _ => false
    }
}