class Nokogiri::XML::Reader

The Reader parser allows you to effectively pull parse an XML document. Once instantiated, call Nokogiri::XML::Reader#each to iterate over each node. Note that you may only iterate over the document once!

Nokogiri::XML::Reader parses an XML document similar to the way a cursor would move. The Reader is given an XML document, and yields nodes to an each block.

The Reader parser might be good for when you need the speed and low memory usage of the SAX parser, but do not want to write a Document handler.

Here is an example of usage:

reader = Nokogiri::XML::Reader(<<-eoxml)
  <x xmlns:tenderlove='http://tenderlovemaking.com/'>
    <tenderlove:foo awesome='true'>snuggles!</tenderlove:foo>
  </x>
eoxml

reader.each do |node|

  # node is an instance of Nokogiri::XML::Reader
  puts node.name

end

⚠ Nokogiri::XML::Reader#each can only be called once! Once the cursor moves through the entire document, you must parse the document again. It may be better to capture all information you need during a single iteration.

⚠ libxml2 does not support error recovery in the Reader parser. The ‘RECOVER` ParseOption is ignored. If a syntax error is encountered during parsing, an exception will be raised.

Constants

TYPE_ATTRIBUTE: Attribute node type
TYPE_CDATA: CDATA node type
TYPE_COMMENT: Comment node type
TYPE_DOCUMENT: Document node type
TYPE_DOCUMENT_FRAGMENT: Document Fragment node type
TYPE_DOCUMENT_TYPE: Document Type node type
TYPE_ELEMENT: Element node type
TYPE_END_ELEMENT: Element end node type
TYPE_END_ENTITY: Entity end node type
TYPE_ENTITY: Entity node type
TYPE_ENTITY_REFERENCE: Entity Reference node type
TYPE_NONE
TYPE_NOTATION: Notation node type
TYPE_PROCESSING_INSTRUCTION: PI node type
TYPE_SIGNIFICANT_WHITESPACE: Significant Whitespace node type
TYPE_TEXT: Text node type
TYPE_WHITESPACE: Whitespace node type
TYPE_XML_DECLARATION: XML Declaration node type

Attributes

errors [RW]

A list of errors encountered while parsing

source [R]

The XML source

Public Class Methods

from_io(io, url = nil, encoding = nil, options = 0)

Source

static VALUE
from_io(int argc, VALUE *argv, VALUE klass)
{
  VALUE rb_io, rb_url, encoding, rb_options;
  xmlTextReaderPtr reader;
  const char *c_url      = NULL;
  const char *c_encoding = NULL;
  int c_options           = 0;
  VALUE rb_reader, args[3];

  rb_scan_args(argc, argv, "13", &rb_io, &rb_url, &encoding, &rb_options);

  if (!RTEST(rb_io)) { rb_raise(rb_eArgError, "io cannot be nil"); }
  if (RTEST(rb_url)) { c_url = StringValueCStr(rb_url); }
  if (RTEST(encoding)) { c_encoding = StringValueCStr(encoding); }
  if (RTEST(rb_options)) { c_options = (int)NUM2INT(rb_options); }

  reader = xmlReaderForIO(
             (xmlInputReadCallback)noko_io_read,
             (xmlInputCloseCallback)noko_io_close,
             (void *)rb_io,
             c_url,
             c_encoding,
             c_options
           );

  if (reader == NULL) {
    xmlFreeTextReader(reader);
    rb_raise(rb_eRuntimeError, "couldn't create a parser");
  }

  rb_reader = TypedData_Wrap_Struct(klass, &xml_text_reader_type, reader);
  args[0] = rb_io;
  args[1] = rb_url;
  args[2] = encoding;
  rb_obj_call_init(rb_reader, 3, args);

  return rb_reader;
}

Create a new reader that parses io

from_memory(string, url = nil, encoding = nil, options = 0)

Source

static VALUE
from_memory(int argc, VALUE *argv, VALUE klass)
{
  VALUE rb_buffer, rb_url, encoding, rb_options;
  xmlTextReaderPtr reader;
  const char *c_url      = NULL;
  const char *c_encoding = NULL;
  int c_options           = 0;
  VALUE rb_reader, args[3];

  rb_scan_args(argc, argv, "13", &rb_buffer, &rb_url, &encoding, &rb_options);

  if (!RTEST(rb_buffer)) { rb_raise(rb_eArgError, "string cannot be nil"); }
  if (RTEST(rb_url)) { c_url = StringValueCStr(rb_url); }
  if (RTEST(encoding)) { c_encoding = StringValueCStr(encoding); }
  if (RTEST(rb_options)) { c_options = (int)NUM2INT(rb_options); }

  reader = xmlReaderForMemory(
             StringValuePtr(rb_buffer),
             (int)RSTRING_LEN(rb_buffer),
             c_url,
             c_encoding,
             c_options
           );

  if (reader == NULL) {
    xmlFreeTextReader(reader);
    rb_raise(rb_eRuntimeError, "couldn't create a parser");
  }

  rb_reader = TypedData_Wrap_Struct(klass, &xml_text_reader_type, reader);
  args[0] = rb_buffer;
  args[1] = rb_url;
  args[2] = encoding;
  rb_obj_call_init(rb_reader, 3, args);

  return rb_reader;
}

Create a new reader that parses string

Public Instance Methods

attribute(name)

Source

static VALUE
reader_attribute(VALUE self, VALUE name)
{
  xmlTextReaderPtr reader;
  xmlChar *value ;
  VALUE rb_value;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);

  if (NIL_P(name)) { return Qnil; }
  name = StringValue(name) ;

  value = xmlTextReaderGetAttribute(reader, (xmlChar *)StringValueCStr(name));
  if (value == NULL) { return Qnil; }

  rb_value = NOKOGIRI_STR_NEW2(value);
  xmlFree(value);
  return rb_value;
}

Get the value of attribute named name

attribute_at(index)

Source

static VALUE
attribute_at(VALUE self, VALUE index)
{
  xmlTextReaderPtr reader;
  xmlChar *value;
  VALUE rb_value;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);

  if (NIL_P(index)) { return Qnil; }
  index = rb_Integer(index);

  value = xmlTextReaderGetAttributeNo(
            reader,
            (int)NUM2INT(index)
          );
  if (value == NULL) { return Qnil; }

  rb_value = NOKOGIRI_STR_NEW2(value);
  xmlFree(value);
  return rb_value;
}

Get the value of attribute at index

attribute_count

Source

static VALUE
attribute_count(VALUE self)
{
  xmlTextReaderPtr reader;
  int count;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  count = xmlTextReaderAttributeCount(reader);
  if (count == -1) { return Qnil; }

  return INT2NUM(count);
}

Get the number of attributes for the current node

attribute_hash() → Hash<String ⇒ String>

Source

static VALUE
rb_xml_reader_attribute_hash(VALUE rb_reader)
{
  VALUE rb_attributes = rb_hash_new();
  xmlTextReaderPtr c_reader;
  xmlNodePtr c_node;
  xmlAttrPtr c_property;
  VALUE rb_errors;

  TypedData_Get_Struct(rb_reader, xmlTextReader, &xml_text_reader_type, c_reader);

  if (!has_attributes(c_reader)) {
    return rb_attributes;
  }

  rb_errors = rb_funcall(rb_reader, rb_intern("errors"), 0);

  xmlSetStructuredErrorFunc((void *)rb_errors, Nokogiri_error_array_pusher);
  c_node = xmlTextReaderExpand(c_reader);
  xmlSetStructuredErrorFunc(NULL, NULL);

  if (c_node == NULL) {
    if (RARRAY_LEN(rb_errors) > 0) {
      VALUE rb_error = rb_ary_entry(rb_errors, 0);
      VALUE exception_message = rb_funcall(rb_error, rb_intern("to_s"), 0);
      rb_exc_raise(rb_class_new_instance(1, &exception_message, cNokogiriXmlSyntaxError));
    }
    return Qnil;
  }

  c_property = c_node->properties;
  while (c_property != NULL) {
    VALUE rb_name = NOKOGIRI_STR_NEW2(c_property->name);
    VALUE rb_value = Qnil;
    xmlChar *c_value = xmlNodeGetContent((xmlNode *)c_property);

    if (c_value) {
      rb_value = NOKOGIRI_STR_NEW2(c_value);
      xmlFree(c_value);
    }

    rb_hash_aset(rb_attributes, rb_name, rb_value);

    c_property = c_property->next;
  }

  return rb_attributes;
}

Get the attributes of the current node as a Hash of names and values.

See related: #attributes and #namespaces

attributes ()

Source

# File lib/nokogiri/xml/reader.rb, line 93
def attributes
  attribute_hash.merge(namespaces)
end

Get the attributes and namespaces of the current node as a Hash.

This is the union of Reader#attribute_hash and Reader#namespaces

Returns: (Hash<String, String>) Attribute names and values, and namespace prefixes and hrefs.

attributes?

Source

static VALUE
attributes_eh(VALUE self)
{
  xmlTextReaderPtr reader;
  int eh;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  eh = has_attributes(reader);
  if (eh == 0) { return Qfalse; }
  if (eh == 1) { return Qtrue; }

  return Qnil;
}

Does this node have attributes?

base_uri

Source

static VALUE
rb_xml_reader_base_uri(VALUE rb_reader)
{
  VALUE rb_base_uri;
  xmlTextReaderPtr c_reader;
  xmlChar *c_base_uri;

  TypedData_Get_Struct(rb_reader, xmlTextReader, &xml_text_reader_type, c_reader);

  c_base_uri = xmlTextReaderBaseUri(c_reader);
  if (c_base_uri == NULL) {
    return Qnil;
  }

  rb_base_uri = NOKOGIRI_STR_NEW2(c_base_uri);
  xmlFree(c_base_uri);

  return rb_base_uri;
}

Get the xml:base of the node

default?

Source

static VALUE
default_eh(VALUE self)
{
  xmlTextReaderPtr reader;
  int eh;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  eh = xmlTextReaderIsDefault(reader);
  if (eh == 0) { return Qfalse; }
  if (eh == 1) { return Qtrue; }

  return Qnil;
}

Was an attribute generated from the default value in the DTD or schema?

depth

Source

static VALUE
depth(VALUE self)
{
  xmlTextReaderPtr reader;
  int depth;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  depth = xmlTextReaderDepth(reader);
  if (depth == -1) { return Qnil; }

  return INT2NUM(depth);
}

Get the depth of the node

each () { |cursor| ... }

Source

# File lib/nokogiri/xml/reader.rb, line 99
def each
  while (cursor = read)
    yield cursor
  end
end

Move the cursor through the document yielding the cursor to the block

empty_element? # → true or false

Source

static VALUE
empty_element_p(VALUE self)
{
  xmlTextReaderPtr reader;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);

  if (xmlTextReaderIsEmptyElement(reader)) {
    return Qtrue;
  }

  return Qfalse;
}

Returns true if the current node is empty, otherwise false.

Also aliased as: self_closing?

encoding ()

Source

static VALUE
rb_xml_reader_encoding(VALUE rb_reader)
{
  xmlTextReaderPtr c_reader;
  const char *parser_encoding;
  VALUE constructor_encoding;

  TypedData_Get_Struct(rb_reader, xmlTextReader, &xml_text_reader_type, c_reader);
  parser_encoding = (const char *)xmlTextReaderConstEncoding(c_reader);
  if (parser_encoding) {
    return NOKOGIRI_STR_NEW2(parser_encoding);
  }

  constructor_encoding = rb_iv_get(rb_reader, "@encoding");
  if (RTEST(constructor_encoding)) {
    return constructor_encoding;
  }

  return Qnil;
}

inner_xml

Source

static VALUE
inner_xml(VALUE self)
{
  xmlTextReaderPtr reader;
  xmlChar *value;
  VALUE str;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);

  value = xmlTextReaderReadInnerXml(reader);

  str = Qnil;
  if (value) {
    str = NOKOGIRI_STR_NEW2((char *)value);
    xmlFree(value);
  }

  return str;
}

Read the contents of the current node, including child nodes and markup. Returns a utf-8 encoded string.

lang

Source

static VALUE
lang(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *lang;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  lang = (const char *)xmlTextReaderConstXmlLang(reader);
  if (lang == NULL) { return Qnil; }

  return NOKOGIRI_STR_NEW2(lang);
}

Get the xml:lang scope within which the node resides.

local_name

Source

static VALUE
local_name(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *name;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  name = (const char *)xmlTextReaderConstLocalName(reader);
  if (name == NULL) { return Qnil; }

  return NOKOGIRI_STR_NEW2(name);
}

Get the local name of the node

name

Source

static VALUE
name(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *name;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  name = (const char *)xmlTextReaderConstName(reader);
  if (name == NULL) { return Qnil; }

  return NOKOGIRI_STR_NEW2(name);
}

Get the name of the node. Returns a utf-8 encoded string.

namespace_uri

Source

static VALUE
namespace_uri(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *uri;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  uri = (const char *)xmlTextReaderConstNamespaceUri(reader);
  if (uri == NULL) { return Qnil; }

  return NOKOGIRI_STR_NEW2(uri);
}

Get the URI defining the namespace associated with the node

namespaces

Source

static VALUE
rb_xml_reader_namespaces(VALUE rb_reader)
{
  VALUE rb_namespaces = rb_hash_new() ;
  xmlTextReaderPtr c_reader;
  xmlNodePtr c_node;
  VALUE rb_errors;

  TypedData_Get_Struct(rb_reader, xmlTextReader, &xml_text_reader_type, c_reader);

  if (! has_attributes(c_reader)) {
    return rb_namespaces ;
  }

  rb_errors = rb_funcall(rb_reader, rb_intern("errors"), 0);

  xmlSetStructuredErrorFunc((void *)rb_errors, Nokogiri_error_array_pusher);
  c_node = xmlTextReaderExpand(c_reader);
  xmlSetStructuredErrorFunc(NULL, NULL);

  if (c_node == NULL) {
    if (RARRAY_LEN(rb_errors) > 0) {
      VALUE rb_error = rb_ary_entry(rb_errors, 0);
      VALUE exception_message = rb_funcall(rb_error, rb_intern("to_s"), 0);
      rb_exc_raise(rb_class_new_instance(1, &exception_message, cNokogiriXmlSyntaxError));
    }
    return Qnil;
  }

  Nokogiri_xml_node_namespaces(c_node, rb_namespaces);

  return rb_namespaces ;
}

Get a hash of namespaces for this Node

node_type

Source

static VALUE
node_type(VALUE self)
{
  xmlTextReaderPtr reader;
  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  return INT2NUM(xmlTextReaderNodeType(reader));
}

Get the type of readers current node

outer_xml

Source

static VALUE
outer_xml(VALUE self)
{
  xmlTextReaderPtr reader;
  xmlChar *value;
  VALUE str = Qnil;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);

  value = xmlTextReaderReadOuterXml(reader);

  if (value) {
    str = NOKOGIRI_STR_NEW2((char *)value);
    xmlFree(value);
  }
  return str;
}

Read the current node and its contents, including child nodes and markup. Returns a utf-8 encoded string.

prefix

Source

static VALUE
prefix(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *prefix;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  prefix = (const char *)xmlTextReaderConstPrefix(reader);
  if (prefix == NULL) { return Qnil; }

  return NOKOGIRI_STR_NEW2(prefix);
}

Get the shorthand reference to the namespace associated with the node.

read

Source

static VALUE
read_more(VALUE self)
{
  xmlTextReaderPtr reader;
  xmlErrorConstPtr error;
  VALUE error_list;
  int ret;
  xmlDocPtr c_document;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);

  error_list = rb_funcall(self, rb_intern("errors"), 0);

  xmlSetStructuredErrorFunc((void *)error_list, Nokogiri_error_array_pusher);
  ret = xmlTextReaderRead(reader);
  xmlSetStructuredErrorFunc(NULL, NULL);

  c_document = xmlTextReaderCurrentDoc(reader);
  if (c_document && c_document->encoding == NULL) {
    VALUE constructor_encoding = rb_iv_get(self, "@encoding");
    if (RTEST(constructor_encoding)) {
      c_document->encoding = xmlStrdup(BAD_CAST StringValueCStr(constructor_encoding));
    } else {
      rb_iv_set(self, "@encoding", NOKOGIRI_STR_NEW2("UTF-8"));
      c_document->encoding = xmlStrdup(BAD_CAST "UTF-8");
    }
  }

  if (ret == 1) { return self; }
  if (ret == 0) { return Qnil; }

  error = xmlGetLastError();
  if (error) {
    rb_exc_raise(Nokogiri_wrap_xml_syntax_error(error));
  } else {
    rb_raise(rb_eRuntimeError, "Error pulling: %d", ret);
  }

  return Qnil;
}

Move the Reader forward through the XML document.

self_closing?

Alias for: empty_element?

state

Source

static VALUE
state(VALUE self)
{
  xmlTextReaderPtr reader;
  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  return INT2NUM(xmlTextReaderReadState(reader));
}

Get the state of the reader

value

Source

static VALUE
value(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *value;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  value = (const char *)xmlTextReaderConstValue(reader);
  if (value == NULL) { return Qnil; }

  return NOKOGIRI_STR_NEW2(value);
}

Get the text value of the node if present. Returns a utf-8 encoded string.

value?

Source

static VALUE
value_eh(VALUE self)
{
  xmlTextReaderPtr reader;
  int eh;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  eh = xmlTextReaderHasValue(reader);
  if (eh == 0) { return Qfalse; }
  if (eh == 1) { return Qtrue; }

  return Qnil;
}

Does this node have a text value?

xml_version

Source

static VALUE
xml_version(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *version;

  TypedData_Get_Struct(self, xmlTextReader, &xml_text_reader_type, reader);
  version = (const char *)xmlTextReaderConstXmlVersion(reader);
  if (version == NULL) { return Qnil; }

  return NOKOGIRI_STR_NEW2(version);
}

Get the XML version of the document being read