Struct quick_xml::Reader

pub struct Reader<B: BufRead> { /* fields omitted */ }

A low level encoding-agnostic XML event reader.

Consumes a BufRead and streams XML Events.

Examples

use quick_xml::Reader;
use quick_xml::events::Event;

let xml = r#"<tag1 att1 = "test">
                <tag2><!--Test comment-->Test</tag2>
                <tag2>Test 2</tag2>
            </tag1>"#;
let mut reader = Reader::from_str(xml);
reader.trim_text(true);
let mut count = 0;
let mut txt = Vec::new();
let mut buf = Vec::new();
loop {
    match reader.read_event(&mut buf) {
        Ok(Event::Start(ref e)) => {
            match e.name() {
                b"tag1" => println!("attributes values: {:?}",
                                    e.attributes().map(|a| a.unwrap().value)
                                    .collect::<Vec<_>>()),
                b"tag2" => count += 1,
                _ => (),
            }
        },
        Ok(Event::Text(e)) => txt.push(e.unescape_and_decode(&reader).unwrap()),
        Err(e) => panic!("Error at position {}: {:?}", reader.buffer_position(), e),
        Ok(Event::Eof) => break,
        _ => (),
    }
    buf.clear();
}

Implementations

impl<B: BufRead> Reader<B>

pub fn from_reader(reader: B) -> Reader<B>

Creates a Reader that reads from a reader implementing BufRead.

pub fn expand_empty_elements(&mut self, val: bool) -> &mut Reader<B>

Changes whether empty elements should be split into an Open and a Close event.

When set to true, all Empty events produced by a self-closing tag like <tag/> are expanded into a Start event followed by a End event. When set to false (the default), those tags are represented by an Empty event instead.

(false by default)

pub fn trim_text(&mut self, val: bool) -> &mut Reader<B>

Changes whether whitespace before and after character data should be removed.

When set to true, all Text events are trimmed. If they are empty, no event will be pushed.

(false by default)

pub fn trim_markup_names_in_closing_tags(&mut self, val: bool) -> &mut Reader<B>

Changes wether trailing whitespaces after the markup name are trimmed in closing tags </a >.

If true the emitted End event is stripped of trailing whitespace after the markup name.

Note that if set to false and check_end_names is true the comparison of markup names is going to fail erronously if a closing tag contains trailing whitespaces.

(true by default)

pub fn check_end_names(&mut self, val: bool) -> &mut Reader<B>

Changes whether mismatched closing tag names should be detected.

When set to false, it won’t check if a closing tag matches the corresponding opening tag. For example, <mytag></different_tag> will be permitted.

If the XML is known to be sane (already processed, etc.) this saves extra time.

Note that the emitted End event will not be modified if this is disabled, ie. it will contain the data of the mismatched end tag.

(true by default)

pub fn check_comments(&mut self, val: bool) -> &mut Reader<B>

Changes whether comments should be validated.

When set to true, every Comment event will be checked for not containing --, which is not allowed in XML comments. Most of the time we don’t want comments at all so we don’t really care about comment correctness, thus the default value is false to improve performance.

(false by default)

pub fn buffer_position(&self) -> usize

Gets the current byte position in the input data.

Useful when debugging errors.

pub fn read_event<'a, 'b>(
    &'a mut self,
    buf: &'b mut Vec<u8>
) -> Result<Event<'b>>

Reads the next Event.

This is the main entry point for reading XML Events.

Events borrow buf and can be converted to own their data if needed (uses Cow internally).

Having the possibility to control the internal buffers gives you some additional benefits such as:

• Reduce the number of allocations by reusing the same buffer. For constrained systems, you can call buf.clear() once you are done with processing the event (typically at the end of your loop).
• Reserve the buffer length if you know the file size (using Vec::with_capacity).

Examples

use quick_xml::Reader;
use quick_xml::events::Event;

let xml = r#"<tag1 att1 = "test">
                <tag2><!--Test comment-->Test</tag2>
                <tag2>Test 2</tag2>
            </tag1>"#;
let mut reader = Reader::from_str(xml);
reader.trim_text(true);
let mut count = 0;
let mut buf = Vec::new();
let mut txt = Vec::new();
loop {
    match reader.read_event(&mut buf) {
        Ok(Event::Start(ref e)) => count += 1,
        Ok(Event::Text(e)) => txt.push(e.unescape_and_decode(&reader).expect("Error!")),
        Err(e) => panic!("Error at position {}: {:?}", reader.buffer_position(), e),
        Ok(Event::Eof) => break,
        _ => (),
    }
    buf.clear();
}
println!("Found {} start events", count);
println!("Text events: {:?}", txt);

pub fn event_namespace<'a, 'b, 'c>(
    &'a self,
    qname: &'b [u8],
    namespace_buffer: &'c [u8]
) -> (Option<&'c [u8]>, &'b [u8])

Resolves a potentially qualified event name into (namespace name, local name).

Qualified attribute names have the form prefix:local-name where theprefix is defined on any containing XML element via xmlns:prefix="the:namespace:uri". The namespace prefix can be defined on the same element as the attribute in question.

Unqualified event inherits the current default namespace.

pub fn attribute_namespace<'a, 'b, 'c>(
    &'a self,
    qname: &'b [u8],
    namespace_buffer: &'c [u8]
) -> (Option<&'c [u8]>, &'b [u8])

Resolves a potentially qualified attribute name into (namespace name, local name).

Qualified attribute names have the form prefix:local-name where theprefix is defined on any containing XML element via xmlns:prefix="the:namespace:uri". The namespace prefix can be defined on the same element as the attribute in question.

Unqualified attribute names do not inherit the current default namespace.

pub fn read_namespaced_event<'a, 'b, 'c>(
    &'a mut self,
    buf: &'b mut Vec<u8>,
    namespace_buffer: &'c mut Vec<u8>
) -> Result<(Option<&'c [u8]>, Event<'b>)>

Reads the next event and resolves its namespace (if applicable).

Examples

use std::str::from_utf8;
use quick_xml::Reader;
use quick_xml::events::Event;

let xml = r#"<x:tag1 xmlns:x="www.xxxx" xmlns:y="www.yyyy" att1 = "test">
                <y:tag2><!--Test comment-->Test</y:tag2>
                <y:tag2>Test 2</y:tag2>
            </x:tag1>"#;
let mut reader = Reader::from_str(xml);
reader.trim_text(true);
let mut count = 0;
let mut buf = Vec::new();
let mut ns_buf = Vec::new();
let mut txt = Vec::new();
loop {
    match reader.read_namespaced_event(&mut buf, &mut ns_buf) {
        Ok((ref ns, Event::Start(ref e))) => {
            count += 1;
            match (*ns, e.local_name()) {
                (Some(b"www.xxxx"), b"tag1") => (),
                (Some(b"www.yyyy"), b"tag2") => (),
                (ns, n) => panic!("Namespace and local name mismatch"),
            }
            println!("Resolved namespace: {:?}", ns.and_then(|ns| from_utf8(ns).ok()));
        }
        Ok((_, Event::Text(e))) => {
            txt.push(e.unescape_and_decode(&reader).expect("Error!"))
        },
        Err(e) => panic!("Error at position {}: {:?}", reader.buffer_position(), e),
        Ok((_, Event::Eof)) => break,
        _ => (),
    }
    buf.clear();
}
println!("Found {} start events", count);
println!("Text events: {:?}", txt);

pub fn decode_without_bom<'c>(&self, bytes: &'c [u8]) -> Result<&'c str>

Decodes a UTF8 slice without BOM (Byte order mark) regardless of XML declaration.

Decode bytes without BOM and with malformed sequences replaced with the U+FFFD REPLACEMENT CHARACTER.

Note

If you instead want to use XML declared encoding, use the encoding feature

pub fn decode<'c>(&self, bytes: &'c [u8]) -> Result<&'c str>

Decodes a UTF8 slice regardless of XML declaration.

Decode bytes with BOM sniffing and with malformed sequences replaced with the U+FFFD REPLACEMENT CHARACTER.

Note

If you instead want to use XML declared encoding, use the encoding feature

pub fn decoder(&self) -> Decoder

Get utf8 decoder

pub fn read_to_end<K: AsRef<[u8]>>(
    &mut self,
    end: K,
    buf: &mut Vec<u8>
) -> Result<()>

Reads until end element is found

Manages nested cases where parent and child elements have the same name

pub fn read_text<K: AsRef<[u8]>>(
    &mut self,
    end: K,
    buf: &mut Vec<u8>
) -> Result<String>

Reads optional text between start and end tags.

If the next event is a Text event, returns the decoded and unescaped content as a String. If the next event is an End event, returns the empty string. In all other cases, returns an error.

Any text will be decoded using the XML encoding specified in the XML declaration (or UTF-8 if none is specified).

Examples

use quick_xml::Reader;
use quick_xml::events::Event;

let mut xml = Reader::from_reader(b"
    <a>&lt;b&gt;</a>
    <a></a>
" as &[u8]);
xml.trim_text(true);

let expected = ["<b>", ""];
for &content in expected.iter() {
    match xml.read_event(&mut Vec::new()) {
        Ok(Event::Start(ref e)) => {
            assert_eq!(&xml.read_text(e.name(), &mut Vec::new()).unwrap(), content);
        },
        e => panic!("Expecting Start event, found {:?}", e),
    }
}

pub fn into_underlying_reader(self) -> B

Consumes Reader returning the underlying reader

Can be used to compute line and column of a parsing error position

Examples

use std::{str, io::Cursor};
use quick_xml::Reader;
use quick_xml::events::Event;

let xml = r#"<tag1 att1 = "test">
                <tag2><!--Test comment-->Test</tag2>
                <tag3>Test 2</tag3>
            </tag1>"#;
let mut reader = Reader::from_reader(Cursor::new(xml.as_bytes()));
let mut buf = Vec::new();

fn into_line_and_column(reader: Reader<Cursor<&[u8]>>) -> (usize, usize) {
    let end_pos = reader.buffer_position();
    let mut cursor = reader.into_underlying_reader();
    let s = String::from_utf8(cursor.into_inner()[0..end_pos].to_owned())
        .expect("can't make a string");
    let mut line = 1;
    let mut column = 0;
    for c in s.chars() {
        if c == '\n' {
            line += 1;
            column = 0;
        } else {
            column += 1;
        }
    }
    (line, column)
}

loop {
    match reader.read_event(&mut buf) {
        Ok(Event::Start(ref e)) => match e.name() {
            b"tag1" | b"tag2" => (),
            tag => {
                assert_eq!(b"tag3", tag);
                assert_eq!((3, 22), into_line_and_column(reader));
                break;
            }
        },
        Ok(Event::Eof) => unreachable!(),
        _ => (),
    }
    buf.clear();
}

impl Reader<BufReader<File>>

pub fn from_file<P: AsRef<Path>>(path: P) -> Result<Reader<BufReader<File>>>

Creates an XML reader from a file path.

impl<'a> Reader<&'a [u8]>

pub fn from_str(s: &'a str) -> Reader<&'a [u8]>

Creates an XML reader from a string slice.