/// <summary> Create an empty index.</summary>
/// <param name="page">The page associated with this index.
/// </param>
public PageIndex(Page page)
{
mPage = page;
mIndices = new int[mIncrement];
mCount = 0;
mIncrement = mStartIncrement * 2;
}
//
// provide same constructors as super class
//
private void Init()
{
mPage = null;
mNameStart = - 1;
mNameEnd = - 1;
mValueStart = - 1;
mValueEnd = - 1;
}
/// <summary> Create an abstract node with the page positions given.
/// Remember the page and start & end cursor positions.
/// </summary>
/// <param name="page">The page this tag was read from.
/// </param>
/// <param name="start">The starting offset of this node within the page.
/// </param>
/// <param name="end">The ending offset of this node within the page.
/// </param>
public AbstractNode(Page page, int start, int end)
{
mPage = page;
nodeBegin = start;
nodeEnd = end;
parent = null;
children = null;
}
/// <summary> Create an attribute.</summary>
/// <param name="page">The page containing the attribute.
/// </param>
/// <param name="name_start">The starting offset of the name within the page.
/// If this is negative, the name is considered null.
/// </param>
/// <param name="name_end">The ending offset of the name within the page.
/// </param>
/// <param name="value_start">he starting offset of the value within the page.
/// If this is negative, the value is considered null.
/// </param>
/// <param name="value_end">The ending offset of the value within the page.
/// </param>
/// <param name="quote">The quote, if any, surrounding the value of the attribute,
/// (i.e. ' or "), or zero if none.
/// </param>
public PageAttribute(Page page, int name_start, int name_end, int value_start, int value_end, char quote)
{
mPage = page;
mNameStart = name_start;
mNameEnd = name_end;
mValueStart = value_start;
mValueEnd = value_end;
SetName(null);
SetAssignment(null);
SetValue(null);
SetQuote(quote);
}
/// <summary> Create a tag with the location and attributes provided</summary>
/// <param name="page">The page this tag was read from.
/// </param>
/// <param name="start">The starting offset of this node within the page.
/// </param>
/// <param name="end">The ending offset of this node within the page.
/// </param>
/// <param name="attributes">The list of attributes that were parsed in this tag.
/// </param>
/// <seealso cref="Attribute">
/// </seealso>
public TagNode(Page page, int start, int end, System.Collections.ArrayList attributes):base(page, start, end)
{
mScanner = mDefaultScanner;
mAttributes = attributes;
if ((null == mAttributes) || (0 == mAttributes.Count))
{
System.String[] names;
names = Ids;
if ((null != names) && (0 != names.Length))
TagName = names[0];
else
TagName = ""; // make sure it's not null
}
}
/// <summary> Create a new remark node.</summary>
/// <param name="page">The page the node is on.
/// </param>
/// <param name="start">The beginning position of the remark.
/// </param>
/// <param name="end">The ending position of the remark.
/// </param>
/// <returns> A remark node comprising the indicated characters from the page.
/// </returns>
public virtual IRemark CreateRemarkNode(Page page, int start, int end)
{
IRemark ret;
try
{
ret = (IRemark) (RemarkPrototype.Clone());
ret.Page = page;
ret.StartPosition = start;
ret.EndPosition = end;
}
catch
{
ret = new RemarkNode(page, start, end);
}
return (ret);
}
/// <summary> Create a new string node.</summary>
/// <param name="page">The page the node is on.
/// </param>
/// <param name="start">The beginning position of the string.
/// </param>
/// <param name="end">The ending position of the string.
/// </param>
/// <returns> A text node comprising the indicated characters from the page.
/// </returns>
public virtual IText CreateStringNode(Page page, int start, int end)
{
IText ret;
try
{
ret = (IText) (TextPrototype.Clone());
ret.Page = page;
ret.StartPosition = start;
ret.EndPosition = end;
}
catch
{
ret = new TextNode(page, start, end);
}
return (ret);
}
/// <summary> Creates a new instance of a Lexer.</summary>
/// <param name="page">The page with HTML text.
/// </param>
public Lexer(Page page)
{
Page = page;
Cursor = new Cursor(page, 0);
NodeFactory = this;
}
/// <summary> Create a new tag node.
/// Note that the attributes vector contains at least one element,
/// which is the tag name (standalone attribute) at position zero.
/// This can be used to decide which type of node to create, or
/// gate other processing that may be appropriate.
/// </summary>
/// <param name="page">The page the node is on.
/// </param>
/// <param name="start">The beginning position of the tag.
/// </param>
/// <param name="end">The ending positiong of the tag.
/// </param>
/// <param name="attributes">The attributes contained in this tag.
/// </param>
/// <returns> The created Tag node.
/// </returns>
public virtual ITag CreateTagNode(Page page, int start, int end, System.Collections.ArrayList attributes)
{
return (new TagNode(page, start, end, attributes));
}
/// <summary> Create a new remark node.</summary>
/// <param name="page">The page the node is on.
/// </param>
/// <param name="start">The beginning position of the remark.
/// </param>
/// <param name="end">The ending positiong of the remark.
/// </param>
/// <returns> The created Remark node.
/// </returns>
public virtual IRemark CreateRemarkNode(Page page, int start, int end)
{
return (new RemarkNode(page, start, end));
}
//
// NodeFactory interface
//
/// <summary> Create a new string node.</summary>
/// <param name="page">The page the node is on.
/// </param>
/// <param name="start">The beginning position of the string.
/// </param>
/// <param name="end">The ending positiong of the string.
/// </param>
/// <returns> The created Text node.
/// </returns>
public virtual IText CreateStringNode(Page page, int start, int end)
{
return (new TextNode(page, start, end));
}
/// <summary> Creates an end tag with the same name as the given tag.</summary>
/// <param name="tag">The tag to end.
/// </param>
/// <param name="lexer">The object containg the node factory.
/// </param>
/// <param name="page">The page the tag is on (virtually).
/// </param>
/// <param name="position">The offset into the page at which the tag is to
/// be anchored.
/// </param>
/// <returns> An end tag with the name '"/" + tag.getTagName()' and a start
/// and end position at the given position. The fact these positions are
/// equal may be used to distinguish it as a virtual tag later on.
/// </returns>
protected internal virtual ITag CreateVirtualEndTag(ITag tag, Lexer lexer, Page page, int position)
{
ITag ret;
System.String name;
System.Collections.ArrayList attributes;
name = "/" + tag.RawTagName;
attributes = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
attributes.Add(new TagAttribute(name, (System.String) null));
ret = lexer.NodeFactory.CreateTagNode(page, position, position, attributes);
return (ret);
}
/// <summary> Create an index with the elements given.</summary>
/// <param name="page">The page associated with this index.
/// </param>
/// <param name="cursors">The initial elements of the index.
/// NOTE: The list must be sorted in ascending order.
/// </param>
public PageIndex(Page page, int[] cursors)
{
mPage = page;
mIndices = cursors;
mCount = cursors.Length;
}
/// <summary> Constructor takes in the page and beginning and ending posns.</summary>
/// <param name="page">The page this string is on.
/// </param>
/// <param name="start">The beginning position of the string.
/// </param>
/// <param name="end">The ending positiong of the string.
/// </param>
public TextNode(Page page, int start, int end):base(page, start, end)
{
mText = null;
}
/// <summary> Create a new tag node.
/// Note that the attributes vector contains at least one element,
/// which is the tag name (standalone attribute) at position zero.
/// This can be used to decide which type of node to create, or
/// gate other processing that may be appropriate.
/// </summary>
/// <param name="page">The page the node is on.
/// </param>
/// <param name="start">The beginning position of the tag.
/// </param>
/// <param name="end">The ending positiong of the tag.
/// </param>
/// <param name="attributes">The attributes contained in this tag.
/// </param>
/// <returns> A tag node comprising the indicated characters from the page.
/// </returns>
public virtual ITag CreateTagNode(Page page, int start, int end, System.Collections.ArrayList attributes)
{
TagAttribute attribute;
System.String id;
ITag prototype;
ITag ret;
ret = null;
if (0 != attributes.Count)
{
attribute = (TagAttribute) attributes[0];
id = attribute.GetName();
if (null != id)
{
try
{
id = id.ToUpper(new System.Globalization.CultureInfo("en"));
if (!id.StartsWith("/"))
{
if (id.EndsWith("/"))
id = id.Substring(0, (id.Length - 1) - (0));
prototype = (ITag) mBlastocyst[id];
if (null != prototype)
{
ret = (ITag) prototype.Clone();
ret.Page = page;
ret.StartPosition = start;
ret.EndPosition = end;
ret.AttributesEx = attributes;
}
}
}
catch
{
// default to creating a generic one
}
}
}
if (null == ret)
{
// generate a generic node
try
{
ret = (ITag) TagPrototype.Clone();
ret.Page = page;
ret.StartPosition = start;
ret.EndPosition = end;
ret.AttributesEx = attributes;
}
catch
{
ret = new TagNode(page, start, end, attributes);
}
}
return (ret);
}
/// <summary> Construct a <code>Cursor</code> from the page and position given.</summary>
/// <param name="page">The page this cursor is on.
/// </param>
/// <param name="offset">The character offset within the page.
/// </param>
public Cursor(Page page, int offset)
{
mPage = page;
mPosition = offset;
}
/// <summary> Decode script encoded by the Microsoft obfuscator.</summary>
/// <param name="page">The source for encoded text.
/// </param>
/// <param name="cursor">The position at which to start decoding.
/// This is advanced to the end of the encoded text.
/// </param>
/// <returns> The plaintext.
/// </returns>
/// <exception cref="ParserException">If an error is discovered while decoding.
/// </exception>
public static System.String Decode(Page page, Cursor cursor)
{
int state;
int substate_initial;
int substate_length;
int substate_prefix;
int substate_checksum;
int substate_final;
long checksum;
long length;
char[] buffer;
buffer = new char[6];
int index;
char character;
int input_character;
bool found;
System.Text.StringBuilder ret;
ret = new System.Text.StringBuilder(1024);
state = STATE_INITIAL;
substate_initial = 0;
substate_length = 0;
substate_prefix = 0;
substate_checksum = 0;
substate_final = 0;
length = 0L;
checksum = 0L;
index = 0;
while (STATE_DONE != state)
{
input_character = page.GetCharacter(cursor);
character = (char) input_character;
if (Page.EOF == input_character)
{
if ((STATE_INITIAL != state) || (0 != substate_initial) || (0 != substate_length) || (0 != substate_prefix) || (0 != substate_checksum) || (0 != substate_final))
throw new ParserException("illegal state for exit");
state = STATE_DONE;
}
else
switch (state)
{
case STATE_INITIAL:
if (character == mLeader[substate_initial])
{
substate_initial++;
if (substate_initial == mLeader.Length)
{
substate_initial = 0;
state = STATE_LENGTH;
}
}
else
{
// oops, flush
for (int k = 0; 0 < substate_initial; k++)
{
ret.Append(mLeader[k++]);
substate_initial--;
}
ret.Append(character);
}
break;
case STATE_LENGTH:
buffer[substate_length] = character;
substate_length++;
if (substate_length >= buffer.Length)
{
length = DecodeBase64(buffer);
if (0 > length)
throw new ParserException("illegal length: " + length);
substate_length = 0;
state = STATE_PREFIX;
}
break;
case STATE_PREFIX:
if (character == mPrefix[substate_prefix])
substate_prefix++;
else
throw new ParserException("illegal character encountered: " + (int) character + " ('" + character + "')");
if (substate_prefix >= mPrefix.Length)
{
substate_prefix = 0;
state = STATE_DECODE;
}
break;
case STATE_DECODE:
if ('@' == character)
state = STATE_ESCAPE;
else
{
if (input_character < 0x80)
{
if (input_character == '\t')
input_character = 0;
else if (input_character >= ' ')
input_character -= (' ' - 1);
else
throw new ParserException("illegal encoded character: " + input_character + " ('" + character + "')");
char ch = mLookupTable[mEncodingIndex[index % 64]][input_character];
ret.Append(ch);
checksum += ch;
index++;
}
else
ret.Append(character);
}
length--;
if (0 == length)
{
index = 0;
state = STATE_CHECKSUM;
}
break;
case STATE_ESCAPE:
found = false;
for (int i = 0; i < mEscapes.Length; i++)
if (character == mEscapes[i])
{
found = true;
character = mEscaped[i];
}
if (!found)
throw new ParserException("unexpected escape character: " + (int) character + " ('" + character + "')");
ret.Append(character);
checksum += character;
index++;
state = STATE_DECODE;
length--;
if (0 == length)
{
index = 0;
state = STATE_CHECKSUM;
}
break;
case STATE_CHECKSUM:
buffer[substate_checksum] = character;
substate_checksum++;
if (substate_checksum >= buffer.Length)
{
long check = DecodeBase64(buffer);
if (check != checksum)
throw new ParserException("incorrect checksum, expected " + check + ", calculated " + checksum);
checksum = 0;
substate_checksum = 0;
state = STATE_FINAL;
}
break;
case STATE_FINAL:
if (character == mTrailer[substate_final])
substate_final++;
else
throw new ParserException("illegal character encountered: " + (int) character + " ('" + character + "')");
if (substate_final >= mTrailer.Length)
{
substate_final = 0;
state = LAST_STATE;
}
break;
default:
throw new ParserException("invalid state: " + state);
}
}
return (ret.ToString());
}
