gecko/content/base/public/nsIDocumentEncoder.idl

/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* ***** BEGIN LICENSE BLOCK *****
 * Version: MPL 1.1/GPL 2.0/LGPL 2.1
 *
 * The contents of this file are subject to the Mozilla Public License Version
 * 1.1 (the "License"); you may not use this file except in compliance with
 * the License. You may obtain a copy of the License at
 * http://www.mozilla.org/MPL/
* 
 * Software distributed under the License is distributed on an "AS IS" basis,
 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
 * for the specific language governing rights and limitations under the
 * License.
 *
 * The Original Code is mozilla.org code.
 *
 * The Initial Developer of the Original Code is
 * the Mozilla Foundation.
 * Portions created by the Initial Developer are Copyright (C) 2006
 * the Initial Developer. All Rights Reserved.
 *
 * Contributor(s):
 *   Josh Lurz <jlurz24@gmail.com>
 *
 * Alternatively, the contents of this file may be used under the terms of
 * either of the GNU General Public License Version 2 or later (the "GPL"),
 * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
 * in which case the provisions of the GPL or the LGPL are applicable instead
 * of those above. If you wish to allow use of your version of this file only
 * under the terms of either the GPL or the LGPL, and not to allow others to
 * use your version of this file under the terms of the MPL, indicate your
 * decision by deleting the provisions above and replace them with the notice
 * and other provisions required by the GPL or the LGPL. If you do not delete
 * the provisions above, a recipient may use your version of this file under
 * the terms of any one of the MPL, the GPL or the LGPL.
 *
 * ***** END LICENSE BLOCK ***** */

#include "nsISupports.idl"

interface nsIDOMDocument;
interface nsIDOMRange;
interface nsISelection;
interface nsIDOMNode;
interface nsIOutputStream;

%{ C++
class nsINode;
class nsIDocument;
%}
[ptr] native nsINodePtr(nsINode);
[ptr] native nsIDocumentPtr(nsIDocument);

[scriptable, uuid(c0da5b87-0ba7-4d7c-8cb3-fcb02af4253d)]
interface nsIDocumentEncoderNodeFixup : nsISupports
{
  /**
   * Create a fixed up version of a node. This method is called before
   * each node in a document is about to be persisted. The implementor
   * may return a new node with fixed up attributes or null. If null is
   * returned the node should be used as-is.
   * @param aNode Node to fixup.
   * @param [OUT] aSerializeCloneKids True if the document encoder should
   * apply recursive serialization to the children of the fixed up node
   * instead of the children of the original node.
   * @return The resulting fixed up node.
   */
  nsIDOMNode fixupNode(in nsIDOMNode aNode, out boolean aSerializeCloneKids);
};

[scriptable, uuid(7222bdf1-c2b9-41f1-a40a-a3d65283a95b)]
interface nsIDocumentEncoder : nsISupports
{
  // Output methods flag bits. There are a frightening number of these,
  // because everyone wants something a little bit different
   

  /** 
   * Output only the selection (as opposed to the whole document).
   */
  const unsigned long OutputSelectionOnly = (1 << 0);

  /** Plaintext output: Convert html to plaintext that looks like the html.
    * Implies wrap (except inside <pre>), since html wraps.
    * HTML, XHTML and XML output: do prettyprinting, ignoring existing formatting.
    * XML output : it doesn't implicitly wrap
    */
  const unsigned long OutputFormatted     = (1 << 1);

  /** Don't do prettyprinting. Don't do any wrapping that's not in the existing
   * HTML/XML source. This option overrides OutputFormatted if both are set.
   * HTML/XHTML output: If neither are set, there won't be prettyprinting too, but
   * long lines will be wrapped.
   * Supported also in XML and Plaintext output.
   * @note This option does not affect entity conversion.
   */
  const unsigned long OutputRaw           = (1 << 2);

  /** 
   * Do not print html head tags.
   * XHTML/HTML output only.
   */
  const unsigned long OutputBodyOnly      = (1 << 3);

  /**
   * Output as though the content is preformatted
   * (e.g. maybe it's wrapped in a PRE or PRE_WRAP style tag)
   * Plaintext output only.
   * XXXbz How does this interact with
   * OutputFormatted/OutputRaw/OutputPreformatted/OutputFormatFlowed?
   */
  const unsigned long OutputPreformatted  = (1 << 4);

  /**
   * Wrap even if we're not doing formatted output (e.g. for text fields).
   * Supported in XML, XHTML, HTML and Plaintext output.
   * Set implicitly in HTML/XHTML output when no OutputRaw.
   * Ignored when OutputRaw.
   * XXXLJ: set implicitly in HTML/XHTML output, to keep compatible behaviors
   *        for old callers of this interface
   * XXXbz How does this interact with OutputFormatFlowed?
   */
  const unsigned long OutputWrap          = (1 << 5);

  /**
   * Output for format flowed (RFC 2646). This is used when converting
   * to text for mail sending. This differs just slightly
   * but in an important way from normal formatted, and that is that
   * lines are space stuffed. This can't (correctly) be done later.
   * PlainText output only.
   * XXXbz How does this interact with
   * OutputFormatted/OutputRaw/OutputPreformatted/OutputWrap?
   */
  const unsigned long OutputFormatFlowed  = (1 << 6);

  /**
   * Convert links, image src, and script src to absolute URLs when possible.
   * XHTML/HTML output only.
   */
  const unsigned long OutputAbsoluteLinks = (1 << 7);

  /**
   * Attempt to encode entities standardized at W3C (HTML, MathML, etc).
   * This is a catch-all flag for documents with mixed contents. Beware of
   * interoperability issues. See below for other flags which might likely
   * do what you want.
   * HTML output only.
   */
  const unsigned long OutputEncodeW3CEntities = (1 << 8);

  /** 
   * LineBreak processing: if this flag is set than CR line breaks will
   * be written. If neither this nor OutputLFLineBreak is set, then we
   * will use platform line breaks. The combination of the two flags will
   * cause CRLF line breaks to be written.
   */
  const unsigned long OutputCRLineBreak = (1 << 9);

  /** 
   * LineBreak processing: if this flag is set than LF line breaks will
   * be written. If neither this nor OutputCRLineBreak is set, then we
   * will use platform line breaks. The combination of the two flags will
   * cause CRLF line breaks to be written.
   */
  const unsigned long OutputLFLineBreak = (1 << 10);

  /**
   * Output the content of noscript elements (only for serializing
   * to plaintext).
   */
  const unsigned long OutputNoScriptContent = (1 << 11);

  /**
   * Output the content of noframes elements (only for serializing
   * to plaintext).
   */
  const unsigned long OutputNoFramesContent = (1 << 12);

  /**
   * Don't allow any formatting nodes (e.g. <br>, <b>) inside a <pre>.
   * This is used primarily by mail. XHTML/HTML output only.
   */
  const unsigned long OutputNoFormattingInPre = (1 << 13);

  /**
   * Encode entities when outputting to a string.
   * E.g. If set, we'll output &nbsp; if clear, we'll output 0xa0.
   * The basic set is just &nbsp; &amp; &lt; &gt; &quot; for interoperability
   * with older products that don't support &alpha; and friends.
   * HTML output only.
   */
  const unsigned long OutputEncodeBasicEntities = (1 << 14);
    
  /**
   * Encode entities when outputting to a string.
   * The Latin1 entity set additionally includes 8bit accented letters
   * between 128 and 255.
   * HTML output only.
   */
  const unsigned long OutputEncodeLatin1Entities = (1 << 15);
  
  /**
   * Encode entities when outputting to a string.
   * The HTML entity set additionally includes accented letters, greek
   * letters, and other special markup symbols as defined in HTML4.
   * HTML output only.
   */
  const unsigned long OutputEncodeHTMLEntities = (1 << 16);

  /**
   * Normally &nbsp; is replaced with a space character when
   * encoding data as plain text, set this flag if that's
   * not desired.
   * Plaintext output only.
   */
  const unsigned long OutputPersistNBSP = (1 << 17);

  /**
   * Normally when serializing the whole document using the HTML or 
   * XHTML serializer, the encoding declaration is rewritten to match.
   * This flag suppresses that behavior.
   */
  const unsigned long OutputDontRewriteEncodingDeclaration = (1 << 18);
 
  /**
   * When using the HTML or XHTML serializer, skip elements that are not
   * visible when this flag is set.  Elements are not visible when they
   * have CSS style display:none or visibility:collapse, for example.
   */
  const unsigned long SkipInvisibleContent = (1 << 19);
  
  /**
   * Output for delsp=yes (RFC 3676). This is used with OutputFormatFlowed
   * when converting to text for mail sending.
   * PlainText output only.
   */
  const unsigned long OutputFormatDelSp  = (1 << 20);
 
  /**
   * Initialize with a pointer to the document and the mime type.
   * @param aDocument Document to encode.
   * @param aMimeType MimeType to use. May also be set by SetMimeType.
   * @param aFlags Flags to use while encoding. May also be set by SetFlags.
   */
  void init(in nsIDOMDocument aDocument,
            in AString aMimeType,
            in unsigned long aFlags);
  [noscript] void nativeInit(in nsIDocumentPtr aDocument,
                             in AString aMimeType,
                             in unsigned long aFlags);

  /**
   *  If the selection is set to a non-null value, then the
   *  selection is used for encoding, otherwise the entire
   *  document is encoded.
   * @param aSelection The selection to encode.
   */
  void setSelection(in nsISelection aSelection);

  /**
   *  If the range is set to a non-null value, then the
   *  range is used for encoding, otherwise the entire
   *  document or selection is encoded.
   * @param aRange The range to encode.
   */
  void setRange(in nsIDOMRange aRange);

  /**
   *  If the node is set to a non-null value, then the
   *  node is used for encoding, otherwise the entire
   *  document or range or selection is encoded.
   * @param aNode The node to encode.
   */
  void setNode(in nsIDOMNode aNode);

  /**
   *  If the container is set to a non-null value, then its
   *  child nodes are used for encoding, otherwise the entire
   *  document or range or selection or node is encoded.
   *  @param aContainer The node which child nodes will be encoded.
   */
  void setContainerNode(in nsIDOMNode aContainer);
  [noscript] void setNativeContainerNode(in nsINodePtr aContainer);

  /**
   *  Documents typically have an intrinsic character set,
   *  but if no intrinsic value is found, the platform character set
   *  is used. This function overrides both the intrinisc and platform
   *  charset.
   *  @param aCharset Overrides the both the intrinsic or platform
   *  character set when encoding the document.
   *
   *  Possible result codes: NS_ERROR_NO_CHARSET_CONVERTER
   */
  void setCharset(in ACString aCharset);

  /**
   *  Set a wrap column.  This may have no effect in some types of encoders.
   * @param aWrapColumn Column to which to wrap.
   */
  void setWrapColumn(in unsigned long aWrapColumn);

  /**
   *  The mime type preferred by the encoder.  This piece of api was
   *  added because the copy encoder may need to switch mime types on you
   *  if you ask it to copy html that really represents plaintext content.
   *  Call this AFTER Init() and SetSelection() have both been called.
   */
  readonly attribute AString mimeType;
  
  /**
   *  Encode the document and send the result to the nsIOutputStream.
   *
   *  Possible result codes are the stream errors which might have
   *  been encountered.
   * @param aStream Stream into which to encode.
   */
  void encodeToStream(in nsIOutputStream aStream);

  /**
   * Encode the document into a string.
   *
   * @return The document encoded into a string.
   */
  AString encodeToString();

  /**
   * Encode the document into a string. Stores the extra context information
   * into the two arguments.
   * @param [OUT] aContextString The string where the parent hierarchy
   *              information will be stored.
   * @param [OUT] aInfoString The string where extra context info will
   *              be stored.
   * @return The document encoded as a string.
   * 
   */
  AString encodeToStringWithContext( out AString aContextString,
                                     out AString aInfoString);

  /**
   * Set the fixup object associated with node persistence.
   * @param aFixup The fixup object.
   */
  void setNodeFixup(in nsIDocumentEncoderNodeFixup aFixup);
};