Struct hard_xml::XmlReader

source ·
pub struct XmlReader<'a> { /* private fields */ }
Expand description

Xml Reader

It behaves almost exactly like xmlparser::Tokenizer::from("...").peekable() but with some helper functions.

Implementations§

Examples found in repository?
src/xml_read.rs (line 7)
6
7
8
9
    fn from_str(text: &'a str) -> XmlResult<Self> {
        let mut reader = XmlReader::new(text);
        Self::from_reader(&mut reader)
    }
Examples found in repository?
src/xml_reader.rs (line 42)
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
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
    pub fn read_text(&mut self, end_tag: &str) -> XmlResult<Cow<'a, str>> {
        let mut res = Cow::Borrowed("");

        while let Some(token) = self.next() {
            match token? {
                Token::ElementEnd {
                    end: ElementEnd::Open,
                    ..
                }
                | Token::Attribute { .. } => (),
                Token::Text { text } => {
                    let text = xml_unescape(text.as_str())?;
                    if res.is_empty() {
                        res = text;
                    } else {
                        res.to_mut().push_str(&text);
                    }
                }
                Token::Cdata { text, .. } => {
                    if res.is_empty() {
                        res = Cow::Borrowed(text.as_str());
                    } else {
                        res.to_mut().push_str(&text);
                    }
                }
                Token::ElementEnd {
                    end: ElementEnd::Close(_, _),
                    span,
                } => {
                    let span = span.as_str(); // </tag>
                    let tag = &span[2..span.len() - 1]; // remove `</` and `>`
                    if end_tag == tag {
                        break;
                    } else {
                        return Err(XmlError::TagMismatch {
                            expected: end_tag.to_owned(),
                            found: tag.to_owned(),
                        });
                    }
                }
                Token::ElementEnd {
                    end: ElementEnd::Empty,
                    ..
                } => {
                    break;
                }
                token => {
                    return Err(XmlError::UnexpectedToken {
                        token: format!("{:?}", token),
                    });
                }
            }
        }

        Ok(res)
    }

    #[inline]
    pub fn read_till_element_start(&mut self, end_tag: &str) -> XmlResult<()> {
        while let Some(token) = self.next() {
            match token? {
                Token::ElementStart { span, .. } => {
                    let tag = &span.as_str()[1..];
                    if end_tag == tag {
                        break;
                    } else {
                        self.read_to_end(tag)?;
                    }
                }
                Token::ElementEnd { .. }
                | Token::Attribute { .. }
                | Token::Text { .. }
                | Token::Cdata { .. } => {
                    return Err(XmlError::UnexpectedToken {
                        token: format!("{:?}", token),
                    });
                }
                _ => (),
            }
        }
        Ok(())
    }

    #[inline]
    pub fn find_attribute(&mut self) -> XmlResult<Option<(&'a str, Cow<'a, str>)>> {
        if let Some(token) = self.tokenizer.peek() {
            match token {
                Ok(Token::Attribute { span, value, .. }) => {
                    let value = value.as_str();
                    let span = span.as_str(); // key="value"
                    let key = &span[0..span.len() - value.len() - 3]; // remove `="`, value and `"`
                    let value = xml_unescape(value)?;
                    self.next();
                    return Ok(Some((key, value)));
                }
                Ok(Token::ElementEnd {
                    end: ElementEnd::Open,
                    ..
                })
                | Ok(Token::ElementEnd {
                    end: ElementEnd::Empty,
                    ..
                }) => return Ok(None),
                Ok(token) => {
                    return Err(XmlError::UnexpectedToken {
                        token: format!("{:?}", token),
                    })
                }
                Err(_) => {
                    // we have call .peek() above, and it's safe to use unwrap
                    self.next().unwrap()?;
                }
            }
        }

        Err(XmlError::UnexpectedEof)
    }

    #[inline]
    pub fn find_element_start(&mut self, end_tag: Option<&str>) -> XmlResult<Option<&'a str>> {
        while let Some(token) = self.tokenizer.peek() {
            match token {
                Ok(Token::ElementStart { span, .. }) => {
                    return Ok(Some(&span.as_str()[1..]));
                }
                Ok(Token::ElementEnd {
                    end: ElementEnd::Close(_, _),
                    span,
                }) if end_tag.is_some() => {
                    let end_tag = end_tag.unwrap();
                    let span = span.as_str(); // </tag>
                    let tag = &span[2..span.len() - 1]; // remove `</` and `>`
                    if tag == end_tag {
                        self.next();
                        return Ok(None);
                    } else {
                        return Err(XmlError::TagMismatch {
                            expected: end_tag.to_owned(),
                            found: tag.to_owned(),
                        });
                    }
                }
                Ok(Token::ElementEnd { .. }) | Ok(Token::Attribute { .. }) => {
                    return Err(XmlError::UnexpectedToken {
                        token: format!("{:?}", token),
                    })
                }
                _ => {
                    // we have call .peek() above, and it's safe to use unwrap
                    self.next().unwrap()?;
                }
            }
        }

        Err(XmlError::UnexpectedEof)
    }

    #[inline]
    pub fn read_to_end(&mut self, end_tag: &str) -> XmlResult<()> {
        while let Some(token) = self.next() {
            match token? {
                // if this element is emtpy, just return
                Token::ElementEnd {
                    end: ElementEnd::Empty,
                    ..
                } => return Ok(()),
                Token::ElementEnd {
                    end: ElementEnd::Open,
                    ..
                } => break,
                Token::Attribute { .. } => (),
                // there shouldn't have any token but Attribute between ElementStart and ElementEnd
                token => {
                    return Err(XmlError::UnexpectedToken {
                        token: format!("{:?}", token),
                    })
                }
            }
        }

        let mut depth = 1;

        while let Some(token) = self.next() {
            match token? {
                Token::ElementStart { span, .. } if end_tag == &span.as_str()[1..] => {
                    while let Some(token) = self.next() {
                        match token? {
                            Token::ElementEnd {
                                end: ElementEnd::Empty,
                                ..
                            } => {
                                if depth == 0 {
                                    return Ok(());
                                } else {
                                    // don't advance depth in this case
                                    break;
                                }
                            }
                            Token::ElementEnd {
                                end: ElementEnd::Open,
                                ..
                            } => {
                                depth += 1;
                                break;
                            }
                            Token::Attribute { .. } => (),
                            // there shouldn't have any token but Attribute between ElementStart and ElementEnd
                            token => {
                                return Err(XmlError::UnexpectedToken {
                                    token: format!("{:?}", token),
                                });
                            }
                        }
                    }
                }
                Token::ElementEnd {
                    end: ElementEnd::Close(_, _),
                    span,
                } if end_tag == &span.as_str()[2..span.as_str().len() - 1] => {
                    depth -= 1;
                    if depth == 0 {
                        return Ok(());
                    }
                }
                _ => (),
            }
        }

        Err(XmlError::UnexpectedEof)
    }
Examples found in repository?
src/xml_reader.rs (line 105)
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
    pub fn read_till_element_start(&mut self, end_tag: &str) -> XmlResult<()> {
        while let Some(token) = self.next() {
            match token? {
                Token::ElementStart { span, .. } => {
                    let tag = &span.as_str()[1..];
                    if end_tag == tag {
                        break;
                    } else {
                        self.read_to_end(tag)?;
                    }
                }
                Token::ElementEnd { .. }
                | Token::Attribute { .. }
                | Token::Text { .. }
                | Token::Cdata { .. } => {
                    return Err(XmlError::UnexpectedToken {
                        token: format!("{:?}", token),
                    });
                }
                _ => (),
            }
        }
        Ok(())
    }

Auto Trait Implementations§

Blanket Implementations§

Gets the TypeId of self. Read more
Immutably borrows from an owned value. Read more
Mutably borrows from an owned value. Read more

Returns the argument unchanged.

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

The type returned in the event of a conversion error.
Performs the conversion.
The type returned in the event of a conversion error.
Performs the conversion.