Class: LibXML::XML::HTMLParser::Context

Inherits:
Parser::Context show all
Defined in:
ext/libxml/ruby_xml_html_parser_context.c,
ext/libxml/ruby_xml_html_parser_context.c

Overview

The XML::HTMLParser::Context class provides in-depth control over how a document is parsed.

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from Parser::Context

#base_uri, #base_uri=, #data_directory, #depth, #disable_sax?, #docbook?, document, #encoding, #encoding=, #errno, #html?, #io_max_num_streams, #io_num_streams, #keep_blanks?, #name_depth, #name_depth_max, #name_node, #name_tab, #node, #node_depth, #node_depth_max, #num_chars, #options, #recovery=, #recovery?, #replace_entities=, #replace_entities?, #space_depth, #space_depth_max, #standalone?, #stats?, #subset_external?, #subset_external_system_id, #subset_external_uri, #subset_internal?, #subset_internal_name, #valid, #validate?, #version, #well_formed?

Class Method Details

.XML::HTMLParser::Context.file(file) ⇒ XML::HTMLParser::Context

Creates a new parser context based on the specified file or uri.

Parameters:

file - A filename or uri.

Returns:



36
37
38
39
40
 
# File 'ext/libxml/ruby_xml_html_parser_context.c', line 36

static VALUE rxml_html_parser_context_file(VALUE klass, VALUE file)
{
  xmlParserCtxtPtr ctxt = htmlCreateFileParserCtxt(StringValuePtr(file), NULL);
  return rxml_html_parser_context_wrap(ctxt);
}

.XML::HTMLParser::Context.io(io) ⇒ XML::HTMLParser::Context

Creates a new parser context based on the specified io object.

Parameters:

io - A ruby IO object.

Returns:



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
 
# File 'ext/libxml/ruby_xml_html_parser_context.c', line 51

static VALUE rxml_html_parser_context_io(VALUE klass, VALUE io)
{
  htmlParserCtxtPtr ctxt;
  xmlParserInputBufferPtr input;
  xmlParserInputPtr stream;

  input = xmlParserInputBufferCreateIO((xmlInputReadCallback) rxml_read_callback, NULL,
                                     (void*)io, XML_CHAR_ENCODING_NONE);

  ctxt = htmlNewParserCtxt();
  if (!ctxt)
  {
    xmlFreeParserInputBuffer(input);
    rxml_raise(&xmlLastError);
  }

  stream = xmlNewIOInputStream(ctxt, input, XML_CHAR_ENCODING_NONE);

  if (!stream)
  {
    xmlFreeParserInputBuffer(input);
    xmlFreeParserCtxt(ctxt);
    rxml_raise(&xmlLastError);
  }
  inputPush(ctxt, stream);

  return rxml_html_parser_context_wrap(ctxt);
}

.XML::HTMLParser::Context.string(string) ⇒ XML::HTMLParser::Context

Creates a new parser context based on the specified string.

Parameters:

string - A string that contains the data to parse.

Returns:



89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
 
# File 'ext/libxml/ruby_xml_html_parser_context.c', line 89

static VALUE rxml_html_parser_context_string(VALUE klass, VALUE string)
{
  xmlParserCtxtPtr ctxt;
  Check_Type(string, T_STRING);

  if (RSTRING_LEN(string) == 0)
    rb_raise(rb_eArgError, "Must specify a string with one or more characters");

  ctxt = xmlCreateMemoryParserCtxt(StringValuePtr(string),
                                   RSTRING_LEN(string));
  if (!ctxt)
    rxml_raise(&xmlLastError);

  htmlDefaultSAXHandlerInit();
  if (ctxt->sax != NULL)
    memcpy(ctxt->sax, &htmlDefaultSAXHandler, sizeof(xmlSAXHandlerV1));
  
  return rxml_html_parser_context_wrap(ctxt);
}

Instance Method Details

#options=(XML) ⇒ Object #XML::Parser::Options::NOCDATA ⇒ Object

Provides control over the execution of a parser. Valid values are the constants defined on XML::Parser::Options. Multiple options can be combined by using Bitwise OR (|).



118
119
120
121
122
123
124
125
126
127
128
 
# File 'ext/libxml/ruby_xml_html_parser_context.c', line 118

static VALUE rxml_html_parser_context_options_set(VALUE self, VALUE options)
{
  int result;
  xmlParserCtxtPtr ctxt;
  Check_Type(options, T_FIXNUM);

  Data_Get_Struct(self, xmlParserCtxt, ctxt);
  result = htmlCtxtUseOptions(ctxt, NUM2INT(options));

  return self;
}