class LibXML::XML::Document

The XML::Document class provides a tree based API for working with xml documents. You may directly create a document and manipulate it, or create a document from a data source by using an XML::Parser object.

To read a document from a file:

doc = XML::Document.file('my_file')

To use a parser to read a document:

parser = XML::Parser.file('my_file')
doc = parser.parse

To create a document from scratch:

doc = XML::Document.new()
doc.root = XML::Node.new('root_node')
doc.root << XML::Node.new('elem1')
doc.save(filename, :indent => true, :encoding => XML::Encoding::UTF_8)

To write a document to a file:

doc = XML::Document.new()
doc.root = XML::Node.new('root_node')
root = doc.root

root << elem1 = XML::Node.new('elem1')
elem1['attr1'] = 'val1'
elem1['attr2'] = 'val2'

root << elem2 = XML::Node.new('elem2')
elem2['attr1'] = 'val1'
elem2['attr2'] = 'val2'

root << elem3 = XML::Node.new('elem3')
elem3 << elem4 = XML::Node.new('elem4')
elem3 << elem5 = XML::Node.new('elem5')

elem5 << elem6 = XML::Node.new('elem6')
elem6 << 'Content for element 6'

elem3['attr'] = 'baz'

doc.save(filename, :indent => true, :encoding => XML::Encoding::UTF_8)

Constants

XML_C14N_1_0: Original C14N 1.0 spec
XML_C14N_1_1: C14N 1.1 spec
XML_C14N_EXCLUSIVE_1_0: Exclusive C14N 1.0 spec

Public Class Methods

XML::Document.document(document) → XML::Document

Source

   # File lib/libxml/document.rb
14 def self.document(value)
15   Parser.document(value).parse
16 end

Creates a new document based on the specified document.

Parameters:

document - A preparsed document.

XML::Document.file(path) → XML::Document

XML::Document.file(path, encoding: XML::Encoding::UTF_8,

options: XML::Parser::Options::NOENT) → XML::Document

Source

   # File lib/libxml/document.rb
33 def self.file(path, encoding: nil, options: nil)
34   Parser.file(path, encoding: encoding, options: options).parse
35 end

Creates a new document from the specified file or uri.

Parameters:

path - Path to file
encoding - The document encoding, defaults to nil. Valid values
           are the encoding constants defined on XML::Encoding.
options - Parser options.  Valid values are the constants defined on
          XML::Parser::Options.  Mutliple options can be combined
          by using Bitwise OR (|).

XML::Document.io(io) → XML::Document

XML::Document.io(io, :encoding → XML::Encoding::UTF_8,

:options → XML::Parser::Options::NOENT

:base_uri="http://libxml.org") → XML::Document

Source

   # File lib/libxml/document.rb
54 def self.io(io, base_uri: nil, encoding: nil, options: nil)
55   Parser.io(io, base_uri: base_uri, encoding: encoding, options: options).parse
56 end

Creates a new document from the specified io object.

Parameters:

io - io object that contains the xml to parser
base_uri - The base url for the parsed document.
encoding - The document encoding, defaults to nil. Valid values
           are the encoding constants defined on XML::Encoding.
options - Parser options.  Valid values are the constants defined on
          XML::Parser::Options.  Mutliple options can be combined
          by using Bitwise OR (|).

XML::Document.initialize(xml_version = 1.0) → document

Source

static VALUE rxml_document_initialize(int argc, VALUE *argv, VALUE self)
{
  xmlDocPtr xdoc;
  VALUE xmlver;

  switch (argc)
  {
  case 0:
    xmlver = rb_str_new2("1.0");
    break;
  case 1:
    rb_scan_args(argc, argv, "01", &xmlver);
    break;
  default:
    rb_raise(rb_eArgError, "wrong number of arguments (need 0 or 1)");
  }

  Check_Type(xmlver, T_STRING);
  xdoc = xmlNewDoc((xmlChar*) StringValuePtr(xmlver));

  // Link the ruby object to the document and the document to the ruby object
  RTYPEDDATA_DATA(self) = xdoc;
  rxml_registry_register(xdoc, self);

  return self;
}

Initializes a new XML::Document, optionally specifying the XML version.

XML::Document.string(string) → XML::Document

XML::Document.string(string, encoding: XML::Encoding::UTF_8,

options: XML::Parser::Options::NOENT

base_uri: "http://libxml.org") → XML::Document

Source

   # File lib/libxml/document.rb
75 def self.string(value, base_uri: nil, encoding: nil, options: nil)
76   Parser.string(value, base_uri: base_uri, encoding: encoding, options: options).parse
77 end

Creates a new document from the specified string.

Parameters:

string - String to parse
base_uri - The base url for the parsed document.
encoding - The document encoding, defaults to nil. Valid values
           are the encoding constants defined on XML::Encoding.
options  - Parser options.  Valid values are the constants defined on
           XML::Parser::Options.  Mutliple options can be combined
           by using Bitwise OR (|).

Public Instance Methods

canonicalize (p1 = v1)

Source

static VALUE
rxml_document_canonicalize(int argc, VALUE *argv, VALUE self)
{
  VALUE result = Qnil;
  xmlDocPtr xdoc;
  xmlChar *buffer = NULL;
  VALUE option_hash = Qnil;
  VALUE o_nodes = Qnil;

  // :comments option
  int comments = 0;
  // :mode option
  int c14n_mode = XML_C14N_1_0;
  // :inclusive_ns_prefixes option (ARRAY)

  xmlChar * inc_ns_prefixes_ptr[C14N_NS_LIMIT];

  // :nodes option (ARRAY)
  xmlNodePtr  node_ptr_array[C14N_NODESET_LIMIT];
  xmlNodeSet nodeset = {
    0, C14N_NODESET_LIMIT, NULL
  };

  /* At least one NULL value must be defined in the array or the extension will
   * segfault when using XML_C14N_EXCLUSIVE_1_0 mode.
   * API docs: "list of inclusive namespace prefixes ended with a NULL"
   */
  inc_ns_prefixes_ptr[0] = NULL;

  rb_scan_args(argc, argv, "01", &option_hash);
  // Do stuff if ruby hash passed as argument
  if (!NIL_P(option_hash)) 
  {
    VALUE o_comments = Qnil;
    VALUE o_mode = Qnil;
    VALUE o_i_ns_prefixes = Qnil;
    
    Check_Type(option_hash, T_HASH);

    o_comments = rb_hash_aref(option_hash, ID2SYM(rb_intern("comments")));
    comments = (RTEST(o_comments) ? 1 : 0);

    o_mode = rb_hash_aref(option_hash, ID2SYM(rb_intern("mode")));
    if (!NIL_P(o_mode)) 
    {
      Check_Type(o_mode, T_FIXNUM);
      c14n_mode = NUM2INT(o_mode);
      //TODO: clean this up
      //if (c14n_mode > 2) { c14n_mode = 0; }
      //mode_int = (NUM2INT(o_mode) > 2 ? 0 : NUM2INT(o_mode));
    }

    o_i_ns_prefixes = rb_hash_aref(option_hash, ID2SYM(rb_intern("inclusive_ns_prefixes")));
    if (!NIL_P(o_i_ns_prefixes)) 
    {
      int i;
      int p = 0; //pointer array index
      VALUE *list_in = NULL;
      long list_size = 0;

      Check_Type(o_i_ns_prefixes, T_ARRAY);
      list_in = RARRAY_PTR(o_i_ns_prefixes);
      list_size = RARRAY_LEN(o_i_ns_prefixes);

      if (list_size > 0) 
      {
        for(i=0; i < list_size; ++i) {
          if (p >= C14N_NS_LIMIT) { break; }

          if (RTEST(list_in[i])) 
          {
            if (TYPE(list_in[i]) == T_STRING) 
            {
              inc_ns_prefixes_ptr[p] = (xmlChar *)StringValueCStr(list_in[i]);
              p++;
            }
          }
        }
      }

      // ensure p is not out of bound
      p = (p >= C14N_NS_LIMIT ? (C14N_NS_LIMIT-1) : p);

      // API docs: "list of inclusive namespace prefixes ended with a NULL"
      // Set last element to NULL
      inc_ns_prefixes_ptr[p] = NULL;
    }
    //o_ns_prefixes will free at end of block

    o_nodes = rb_hash_aref(option_hash, ID2SYM(rb_intern("nodes")));
    if (!NIL_P(o_nodes)) 
    {
      int i;
      int p = 0; // index of pointer array
      VALUE * list_in = NULL;
      long node_list_size = 0;

      if (CLASS_OF(o_nodes) == cXMLXPathObject)
      {
        o_nodes = rb_funcall(o_nodes, rb_intern("to_a"), 0);
      }
      else
      {
        Check_Type(o_nodes, T_ARRAY);
      }
      list_in = RARRAY_PTR(o_nodes);
      node_list_size = RARRAY_LEN(o_nodes);

      for (i=0; i < node_list_size; ++i)
      {
        if (p >= C14N_NODESET_LIMIT) { break; }

        if (RTEST(list_in[i])) 
        {
          xmlNodePtr node_ptr;
          TypedData_Get_Struct(list_in[i], xmlNode, &rxml_node_data_type, node_ptr);
          node_ptr_array[p] = node_ptr;
          p++;
        }
      }

      // Need to set values in nodeset struct
      nodeset.nodeNr = (node_list_size > C14N_NODESET_LIMIT ?
                        C14N_NODESET_LIMIT :
                        (int)node_list_size);
      nodeset.nodeTab = node_ptr_array;
    }
  }//option_hash

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  xmlC14NDocDumpMemory(xdoc,
                       (nodeset.nodeNr == 0 ? NULL : &nodeset),
                       c14n_mode,
                       inc_ns_prefixes_ptr,
                       comments,
                       &buffer);

  if (buffer)
  {
    result = rxml_new_cstr( buffer, NULL);
    xmlFree(buffer);
  }

  return result;
}

child → node

Source

static VALUE rxml_document_child_get(VALUE self)
{
  xmlDocPtr xdoc;
  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->children == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->children);
}

Get this document’s child node.

child? → (true|false)

Source

static VALUE rxml_document_child_q(VALUE self)
{
  xmlDocPtr xdoc;
  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->children == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

Determine whether this document has a child node.

compression → num

Source

static VALUE rxml_document_compression_get(VALUE self)
{
#ifdef HAVE_ZLIB_H
  xmlDocPtr xdoc;

  int compmode;
  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  compmode = xmlGetDocCompressMode(xdoc);
  if (compmode == -1)
  return(Qnil);
  else
  return(INT2NUM(compmode));
#else
  rb_warn("libxml not compiled with zlib support");
  return (Qfalse);
#endif
}

Obtain this document’s compression mode identifier.

compression = num

Source

static VALUE rxml_document_compression_set(VALUE self, VALUE num)
{
#ifdef HAVE_ZLIB_H
  xmlDocPtr xdoc;

  int compmode;
  Check_Type(num, T_FIXNUM);
  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc == NULL)
  {
    return(Qnil);
  }
  else
  {
    xmlSetDocCompressMode(xdoc, NUM2INT(num));

    compmode = xmlGetDocCompressMode(xdoc);
    if (compmode == -1)
    return(Qnil);
    else
    return(INT2NUM(compmode));
  }
#else
  rb_warn("libxml compiled without zlib support");
  return (Qfalse);
#endif
}

Set this document’s compression mode.

compression? → (true|false)

Source

static VALUE rxml_document_compression_q(VALUE self)
{
#ifdef HAVE_ZLIB_H
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->compression != -1)
  return(Qtrue);
  else
  return(Qfalse);
#else
  rb_warn("libxml compiled without zlib support");
  return (Qfalse);
#endif
}

Determine whether this document is compressed.

context(namespaces=nil) → XPath::Context

Source

   # File lib/libxml/document.rb
85 def context(nslist = nil)
86   context = XPath::Context.new(self)
87   context.node = self.root
88   context.register_namespaces_from_node(self.root)
89   context.register_namespaces(nslist) if nslist
90   context
91 end

Returns a new XML::XPathContext for the document.

Namespaces is an optional array of XML::NS objects

debug → true|false

Source

static VALUE rxml_document_debug(VALUE self)
{
#ifdef LIBXML_DEBUG_ENABLED
  xmlDocPtr xdoc;
  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  xmlDebugDumpDocument(NULL, xdoc);
  return Qtrue;
#else
  rb_warn("libxml was compiled without debugging support.");
  return Qfalse;
#endif
}

Print libxml debugging information to stdout. Requires that libxml was compiled with debugging enabled.

encoding → XML::Encoding::UTF_8

Source

static VALUE rxml_document_encoding_get(VALUE self)
{
  xmlDocPtr xdoc;
  const char *xencoding;
  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  xencoding = (const char*)xdoc->encoding;
  return INT2NUM(xmlParseCharEncoding(xencoding));
}

Returns the LibXML encoding constant specified by this document.

encoding = XML::Encoding::UTF_8

Source

static VALUE rxml_document_encoding_set(VALUE self, VALUE encoding)
{
  xmlDocPtr xdoc;
  const char* xencoding = xmlGetCharEncodingName((xmlCharEncoding)NUM2INT(encoding));

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->encoding != NULL)
    xmlFree((xmlChar *) xdoc->encoding);

  xdoc->encoding = xmlStrdup((xmlChar *)xencoding);
  return self;
}

Set the encoding for this document.

find(xpath, nslist=nil) → XML::XPath::Object

Source

    # File lib/libxml/document.rb
122 def find(xpath, nslist = nil)
123   self.context(nslist).find(xpath)
124 end

Return the nodes matching the specified xpath expression, optionally using the specified namespace. For more information about working with namespaces, please refer to the XML::XPath documentation.

Parameters:

xpath - The xpath expression as a string
namespaces - An optional list of namespaces (see XML::XPath for information).

document.find('/foo', 'xlink:http://www.w3.org/1999/xlink')

IMPORTANT - The returned XML::Node::Set must be freed before its associated document. In a running Ruby program this will happen automatically via Ruby’s mark and sweep garbage collector. However, if the program exits, Ruby does not guarantee the order in which objects are freed (see blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-core/17700). As a result, the associated document may be freed before the node list, which will cause a segmentation fault. To avoid this, use the following (non-ruby like) coding style:

nodes = doc.find('/header')
nodes.each do |node|
  ... do stuff ...
end

# nodes = nil # GC.start

find_first (xpath, nslist = nil)

Source

    # File lib/libxml/document.rb
129 def find_first(xpath, nslist = nil)
130   find(xpath, nslist).first
131 end

Return the first node matching the specified xpath expression. For more information, please refer to the documentation for XML::Document#find.

import(node) → XML::Node

Source

static VALUE rxml_document_import(VALUE self, VALUE node)
{
  xmlDocPtr xdoc;
  xmlNodePtr xnode, xresult;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  TypedData_Get_Struct(node, xmlNode, &rxml_node_data_type, xnode);

  xresult = xmlDocCopyNode(xnode, xdoc, 1);

  if (xresult == NULL)
    rxml_raise(xmlGetLastError());

  return rxml_node_wrap(xresult);
}

Creates a copy of the node that can be inserted into the current document.

IMPORTANT - The returned node MUST be inserted into the document. This is because the returned node refereces internal LibXML data structures owned by the document. Therefore, if the document is is freed before the the node is freed a segmentation fault will occur.

last → node

Source

static VALUE rxml_document_last_get(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->last == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->last);
}

Obtain the last node.

last? → (true|false)

Source

static VALUE rxml_document_last_q(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->last == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

Determine whether there is a last node.

next → node

Source

static VALUE rxml_document_next_get(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->next == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->next);
}

Obtain the next node.

next? → (true|false)

Source

static VALUE rxml_document_next_q(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->next == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

Determine whether there is a next node.

type → num

Source

static VALUE rxml_document_node_type(VALUE self)
{
  xmlDocPtr xdoc;
  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  return (INT2NUM(xdoc->type));
}

Obtain this node’s type identifier.

node_type_name ()

Source

    # File lib/libxml/document.rb
134 def node_type_name
135   case node_type
136   when XML::Node::DOCUMENT_NODE
137     'document_xml'
138   when XML::Node::DOCB_DOCUMENT_NODE
139     'document_docbook'
140   when XML::Node::HTML_DOCUMENT_NODE
141     'document_html'
142   else
143     raise(UnknownType, "Unknown node type: %n", node.node_type);
144   end
145 end

Returns this node’s type name

order_elements!

Source

static VALUE rxml_document_order_elements(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  return LONG2FIX(xmlXPathOrderDocElems(xdoc));
}

Call this routine to speed up XPath computation on static documents. This stamps all the element nodes with the document order.

parent → node

Source

static VALUE rxml_document_parent_get(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->parent == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->parent);
}

Obtain the parent node.

parent? → (true|false)

Source

static VALUE rxml_document_parent_q(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->parent == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

Determine whether there is a parent node.

prev → node

Source

static VALUE rxml_document_prev_get(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->prev == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->prev);
}

Obtain the previous node.

prev? → (true|false)

Source

static VALUE rxml_document_prev_q(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  if (xdoc->prev == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

Determine whether there is a previous node.

rb_encoding → Encoding

Source

static VALUE rxml_document_rb_encoding_get(VALUE self)
{
  xmlDocPtr xdoc;
  rb_encoding* rbencoding;
  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);

  rbencoding = rxml_xml_encoding_to_rb_encoding(mXMLEncoding, xmlParseCharEncoding((const char*)xdoc->encoding));
  return rb_enc_from_encoding(rbencoding);
}

Returns the Ruby encoding specified by this document (available on Ruby 1.9.x and higher).

root → node

Source

static VALUE rxml_document_root_get(VALUE self)
{
  xmlDocPtr xdoc;
  xmlNodePtr root;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  root = xmlDocGetRootElement(xdoc);

  if (root == NULL)
    return (Qnil);

  return rxml_node_wrap(root);
}

Obtain the root node.

root = node

Source

static VALUE rxml_document_root_set(VALUE self, VALUE node)
{
  xmlDocPtr xdoc;
  xmlNodePtr xnode;

  if (rb_obj_is_kind_of(node, cXMLNode) == Qfalse)
    rb_raise(rb_eTypeError, "must pass an XML::Node type object");

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  TypedData_Get_Struct(node, xmlNode, &rxml_node_data_type, xnode);

  if (xnode->doc != NULL && xnode->doc != xdoc)
    rb_raise(eXMLError, "Nodes belong to different documents.  You must first import the node by calling LibXML::XML::Document.import");

  xmlDocSetRootElement(xdoc, xnode);

  // Ruby no longer manages this nodes memory
  rxml_node_unmanage(xnode, node);

  return node;
}

Set the root node.

save(filename) → int

save(filename, :indent => true, :encoding => XML::Encoding::UTF_8) → int

Source

static VALUE rxml_document_save(int argc, VALUE *argv, VALUE self)
{
  VALUE options = Qnil;
  VALUE filename = Qnil;
  xmlDocPtr xdoc;
  int indent = 1;
  const char *xfilename;
  const xmlChar *xencoding;
  int length;

  rb_scan_args(argc, argv, "11", &filename, &options);

  Check_Type(filename, T_STRING);
  xfilename = StringValuePtr(filename);

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  xencoding = xdoc->encoding;

  if (!NIL_P(options))
  {
    VALUE rencoding, rindent;
    Check_Type(options, T_HASH);
    rencoding = rb_hash_aref(options, ID2SYM(rb_intern("encoding")));
    rindent = rb_hash_aref(options, ID2SYM(rb_intern("indent")));

    if (rindent == Qfalse)
      indent = 0;

    if (rencoding != Qnil)
    {
      xencoding = (const xmlChar*)xmlGetCharEncodingName((xmlCharEncoding)NUM2INT(rencoding));
      if (!xencoding)
        rb_raise(rb_eArgError, "Unknown encoding value: %d", NUM2INT(rencoding));
    }
  }

  length = xmlSaveFormatFileEnc(xfilename, xdoc, (const char*)xencoding, indent);

  if (length == -1)
    rxml_raise(xmlGetLastError());

  return (INT2NUM(length));
}

Saves a document to a file. You may provide an optional hash table to control how the string is generated. Valid options are:

:indent - Specifies if the string should be indented. The default value is true. Note that indentation is only added if both :indent is true and XML.indent_tree_output is true. If :indent is set to false, then both indentation and line feeds are removed from the result.

:encoding - Specifies the output encoding of the string. It defaults to the original encoding of the document (see encoding. To override the orginal encoding, use one of the XML::Encoding encoding constants.

standalone? → (true|false)

Source

static VALUE rxml_document_standalone_q(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  if (xdoc->standalone)
    return (Qtrue);
  else
    return (Qfalse);
}

Determine whether this is a standalone document.

to_s → "string"

to_s(:indent => true, :encoding => XML::Encoding::UTF_8) → "string"

Source

static VALUE rxml_document_to_s(int argc, VALUE *argv, VALUE self)
{
  VALUE result;
  VALUE options = Qnil;
  xmlDocPtr xdoc;
  int indent = 1;
  const xmlChar *xencoding = (const xmlChar*) "UTF-8";
  xmlChar *buffer;
  int length;

  rb_scan_args(argc, argv, "01", &options);

  if (!NIL_P(options))
  {
    VALUE rencoding, rindent;
    Check_Type(options, T_HASH);
    rencoding = rb_hash_aref(options, ID2SYM(rb_intern("encoding")));
    rindent = rb_hash_aref(options, ID2SYM(rb_intern("indent")));

    if (rindent == Qfalse)
      indent = 0;

    if (rencoding != Qnil)
    {
      xencoding = (const xmlChar*)xmlGetCharEncodingName((xmlCharEncoding)NUM2INT(rencoding));
      if (!xencoding)
        rb_raise(rb_eArgError, "Unknown encoding value: %d", NUM2INT(rencoding));
    }
  }

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  xmlDocDumpFormatMemoryEnc(xdoc, &buffer, &length, (const char*)xencoding, indent);

  result = rxml_new_cstr(buffer, xencoding);
  xmlFree(buffer);
  return result;
}

Converts a document, and all of its children, to a string representation. You may provide an optional hash table to control how the string is generated. Valid options are:

:encoding - Specifies the output encoding of the string. It defaults to XML::Encoding::UTF8. To change it, use one of the XML::Encoding encoding constants.

url → "url"

Source

static VALUE rxml_document_url_get(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  if (xdoc->URL == NULL)
    return (Qnil);
  else
    return (rxml_new_cstr( xdoc->URL, NULL));
}

Obtain this document’s source URL, if any.

validate(dtd) → (true|false)

Source

static VALUE rxml_document_validate_dtd(VALUE self, VALUE dtd)
{
  xmlValidCtxt ctxt;
  xmlDocPtr xdoc;
  xmlDtdPtr xdtd;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  TypedData_Get_Struct(dtd, xmlDtd, &rxml_dtd_data_type, xdtd);

  /* Setup context */
  memset(&ctxt, 0, sizeof(xmlValidCtxt));

  if (xmlValidateDtd(&ctxt, xdoc, xdtd))
  {
    return Qtrue;
  }
  else
  {
    rxml_raise(xmlGetLastError());
    return Qfalse;
  }
}

Validate this document against the specified XML::DTD. If the document is valid the method returns true. Otherwise an exception is raised with validation information.

validate_relaxng(relaxng)

Source

static VALUE rxml_document_validate_relaxng(VALUE self, VALUE relaxng)
{
  xmlRelaxNGValidCtxtPtr vptr;
  xmlDocPtr xdoc;
  xmlRelaxNGPtr xrelaxng;
  int is_invalid;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  TypedData_Get_Struct(relaxng, xmlRelaxNG, &rxml_relaxng_data_type, xrelaxng);

  vptr = xmlRelaxNGNewValidCtxt(xrelaxng);

  is_invalid = xmlRelaxNGValidateDoc(vptr, xdoc);
  xmlRelaxNGFreeValidCtxt(vptr);
  if (is_invalid)
  {
    rxml_raise(xmlGetLastError());
    return Qfalse;
  }
  else
  {
    return Qtrue;
  }
}

Validate this document against the specified XML::RelaxNG. If the document is valid the method returns true. Otherwise an exception is raised with validation information.

validate_schema(schema)

Source

static VALUE rxml_document_validate_schema(VALUE self, VALUE schema)
{
  xmlSchemaValidCtxtPtr vptr;
  xmlDocPtr xdoc;
  xmlSchemaPtr xschema;
  int is_invalid;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  TypedData_Get_Struct(schema, xmlSchema, &rxml_schema_type, xschema);

  vptr = xmlSchemaNewValidCtxt(xschema);

  is_invalid = xmlSchemaValidateDoc(vptr, xdoc);
  xmlSchemaFreeValidCtxt(vptr);
  if (is_invalid)
  {
    rxml_raise(xmlGetLastError());
    return Qfalse;
  }
  else
  {
    return Qtrue;
  }
}

Validate this document against the specified XML::Schema. If the document is valid the method returns true. Otherwise an exception is raised with validation information.

version → "version"

Source

static VALUE rxml_document_version_get(VALUE self)
{
  xmlDocPtr xdoc;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  if (xdoc->version == NULL)
    return (Qnil);
  else
    return (rxml_new_cstr( xdoc->version, NULL));
}

Obtain the XML version specified by this document.

xhtml? → (true|false)

Source

static VALUE rxml_document_xhtml_q(VALUE self)
{
  xmlDocPtr xdoc;
  xmlDtdPtr xdtd;
  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  xdtd = xmlGetIntSubset(xdoc);
  if (xdtd != NULL && xmlIsXHTML(xdtd->SystemID, xdtd->ExternalID) > 0)
    return (Qtrue);
  else
    return (Qfalse);
}

Determine whether this is an XHTML document.

xinclude → num

Source

static VALUE rxml_document_xinclude(VALUE self)
{
#ifdef LIBXML_XINCLUDE_ENABLED
  xmlDocPtr xdoc;

  int ret;

  TypedData_Get_Struct(self, xmlDoc, &rxml_document_data_type, xdoc);
  ret = xmlXIncludeProcess(xdoc);
  if (ret >= 0)
  {
    return(INT2NUM(ret));
  }
  else
  {
    rxml_raise(xmlGetLastError());
    return Qnil;
  }
#else
  rb_warn(
      "libxml was compiled without XInclude support.  Please recompile libxml and ruby-libxml");
  return (Qfalse);
#endif
}

Process xinclude directives in this document.