gecko/content/base/src/nsXMLContentSerializer.h

409 lines
15 KiB
C++

/* -*- 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
* Netscape Communications Corporation.
* Portions created by the Initial Developer are Copyright (C) 1998
* the Initial Developer. All Rights Reserved.
*
* Contributor(s):
* Laurent Jouanneau <laurent.jouanneau@disruptive-innovations.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 ***** */
/*
* nsIContentSerializer implementation that can be used with an
* nsIDocumentEncoder to convert an XML DOM to an XML string that
* could be parsed into more or less the original DOM.
*/
#ifndef nsXMLContentSerializer_h__
#define nsXMLContentSerializer_h__
#include "nsIContent.h"
#include "nsIContentSerializer.h"
#include "nsISupportsUtils.h"
#include "nsCOMPtr.h"
#include "nsTArray.h"
#include "nsString.h"
#include "nsIParser.h"
#define kIndentStr NS_LITERAL_STRING(" ")
#define kEndTag NS_LITERAL_STRING("</")
class nsIDOMNode;
class nsIAtom;
class nsXMLContentSerializer : public nsIContentSerializer {
public:
nsXMLContentSerializer();
virtual ~nsXMLContentSerializer();
NS_DECL_ISUPPORTS
NS_IMETHOD Init(PRUint32 flags, PRUint32 aWrapColumn,
const char* aCharSet, PRBool aIsCopying,
PRBool aRewriteEncodingDeclaration);
NS_IMETHOD AppendText(nsIDOMText* aText, PRInt32 aStartOffset,
PRInt32 aEndOffset, nsAString& aStr);
NS_IMETHOD AppendCDATASection(nsIDOMCDATASection* aCDATASection,
PRInt32 aStartOffset, PRInt32 aEndOffset,
nsAString& aStr);
NS_IMETHOD AppendProcessingInstruction(nsIDOMProcessingInstruction* aPI,
PRInt32 aStartOffset,
PRInt32 aEndOffset,
nsAString& aStr);
NS_IMETHOD AppendComment(nsIDOMComment* aComment, PRInt32 aStartOffset,
PRInt32 aEndOffset, nsAString& aStr);
NS_IMETHOD AppendDoctype(nsIDOMDocumentType *aDoctype,
nsAString& aStr);
NS_IMETHOD AppendElementStart(nsIDOMElement *aElement,
nsIDOMElement *aOriginalElement,
nsAString& aStr);
NS_IMETHOD AppendElementEnd(nsIDOMElement *aElement,
nsAString& aStr);
NS_IMETHOD Flush(nsAString& aStr) { return NS_OK; }
NS_IMETHOD AppendDocumentStart(nsIDOMDocument *aDocument,
nsAString& aStr);
protected:
/**
* Appends a PRUnichar string and increments the column position
*/
virtual void AppendToString(const PRUnichar* aStr,
PRInt32 aLength,
nsAString& aOutputStr);
/**
* Appends a PRUnichar character and increments the column position
*/
virtual void AppendToString(const PRUnichar aChar,
nsAString& aOutputStr);
/**
* Appends a nsAString string and increments the column position
*/
virtual void AppendToString(const nsAString& aStr,
nsAString& aOutputStr);
/**
* Appends a string by replacing all line-endings
* by mLineBreak, except in the case of raw output.
* It increments the column position.
*/
virtual void AppendToStringConvertLF(const nsAString& aStr,
nsAString& aOutputStr);
/**
* Appends a string by wrapping it when necessary.
* It updates the column position.
*/
virtual void AppendToStringWrapped(const nsASingleFragmentString& aStr,
nsAString& aOutputStr);
/**
* Appends a string by formating and wrapping it when necessary
* It updates the column position.
*/
virtual void AppendToStringFormatedWrapped(const nsASingleFragmentString& aStr,
nsAString& aOutputStr);
// used by AppendToStringWrapped
void AppendWrapped_WhitespaceSequence(
nsASingleFragmentString::const_char_iterator &aPos,
const nsASingleFragmentString::const_char_iterator aEnd,
const nsASingleFragmentString::const_char_iterator aSequenceStart,
nsAString &aOutputStr);
// used by AppendToStringFormatedWrapped
void AppendFormatedWrapped_WhitespaceSequence(
nsASingleFragmentString::const_char_iterator &aPos,
const nsASingleFragmentString::const_char_iterator aEnd,
const nsASingleFragmentString::const_char_iterator aSequenceStart,
PRBool &aMayIgnoreStartOfLineWhitespaceSequence,
nsAString &aOutputStr);
// used by AppendToStringWrapped and AppendToStringFormatedWrapped
void AppendWrapped_NonWhitespaceSequence(
nsASingleFragmentString::const_char_iterator &aPos,
const nsASingleFragmentString::const_char_iterator aEnd,
const nsASingleFragmentString::const_char_iterator aSequenceStart,
PRBool &aMayIgnoreStartOfLineWhitespaceSequence,
PRBool &aSequenceStartAfterAWhiteSpace,
nsAString &aOutputStr);
/**
* add mLineBreak to the string
* It updates the column position and other flags.
*/
virtual void AppendNewLineToString(nsAString& aOutputStr);
/**
* Appends a string by translating entities
* It doesn't increment the column position
*/
virtual void AppendAndTranslateEntities(const nsAString& aStr,
nsAString& aOutputStr);
/**
* retrieve the text content of the node and append it to the given string
* It doesn't increment the column position
*/
nsresult AppendTextData(nsIDOMNode* aNode,
PRInt32 aStartOffset,
PRInt32 aEndOffset,
nsAString& aStr,
PRBool aTranslateEntities);
virtual nsresult PushNameSpaceDecl(const nsAString& aPrefix,
const nsAString& aURI,
nsIDOMElement* aOwner);
void PopNameSpaceDeclsFor(nsIDOMElement* aOwner);
/**
* The problem that ConfirmPrefix fixes is that anyone can insert nodes
* through the DOM that have a namespace URI and a random or empty or
* previously existing prefix that's totally unrelated to the prefixes
* declared at that point through xmlns attributes. So what ConfirmPrefix
* does is ensure that we can map aPrefix to the namespace URI aURI (for
* example, that the prefix is not already mapped to some other namespace).
* aPrefix will be adjusted, if necessary, so the value of the prefix
* _after_ this call is what should be serialized.
* @param aPrefix the prefix that may need adjusting
* @param aURI the namespace URI we want aPrefix to point to
* @param aElement the element we're working with (needed for proper default
* namespace handling)
* @param aIsAttribute PR_TRUE if we're confirming a prefix for an attribute.
* @return PR_TRUE if we need to push the (prefix, uri) pair on the namespace
* stack (note that this can happen even if the prefix is
* empty).
*/
PRBool ConfirmPrefix(nsAString& aPrefix,
const nsAString& aURI,
nsIDOMElement* aElement,
PRBool aIsAttribute);
/**
* GenerateNewPrefix generates a new prefix and writes it to aPrefix
*/
void GenerateNewPrefix(nsAString& aPrefix);
PRUint32 ScanNamespaceDeclarations(nsIContent* aContent,
nsIDOMElement *aOriginalElement,
const nsAString& aTagNamespaceURI);
virtual void SerializeAttributes(nsIContent* aContent,
nsIDOMElement *aOriginalElement,
nsAString& aTagPrefix,
const nsAString& aTagNamespaceURI,
nsIAtom* aTagName,
nsAString& aStr,
PRUint32 aSkipAttr,
PRBool aAddNSAttr);
void SerializeAttr(const nsAString& aPrefix,
const nsAString& aName,
const nsAString& aValue,
nsAString& aStr,
PRBool aDoEscapeEntities);
virtual PRBool IsJavaScript(nsIContent * aContent,
nsIAtom* aAttrNameAtom,
PRInt32 aAttrNamespaceID,
const nsAString& aValueString);
/**
* This method can be redefined to check if the element can be serialized.
* It is called when the serialization of the start tag is asked
* (AppendElementStart)
* In this method you can also force the formating
* by setting aForceFormat to PR_TRUE.
* @return boolean PR_TRUE if the element can be output
*/
virtual PRBool CheckElementStart(nsIContent * aContent,
PRBool & aForceFormat,
nsAString& aStr);
/**
* this method is responsible to finish the start tag,
* in particulary to append the "greater than" sign
*/
virtual void AppendEndOfElementStart(nsIDOMElement *aOriginalElement,
nsIAtom * aName,
PRInt32 aNamespaceID,
nsAString& aStr);
/**
* This method can be redefine to serialize additional things just after
* after the serialization ot the start tag.
* (called at the end of AppendElementStart)
*/
virtual void AfterElementStart(nsIContent * aContent,
nsIDOMElement *aOriginalElement,
nsAString& aStr) { };
/**
* This method can be redefined to check if the element can be serialized.
* It is called when the serialization of the end tag is asked
* (AppendElementEnd)
* In this method you can also force the formating
* by setting aForceFormat to PR_TRUE.
* @return boolean PR_TRUE if the element can be output
*/
virtual PRBool CheckElementEnd(nsIContent * aContent,
PRBool & aForceFormat,
nsAString& aStr);
/**
* This method can be redefine to serialize additional things just after
* after the serialization ot the end tag.
* (called at the end of AppendElementStart)
*/
virtual void AfterElementEnd(nsIContent * aContent,
nsAString& aStr) { };
/**
* Returns PR_TRUE if a line break should be inserted before an element open tag
*/
virtual PRBool LineBreakBeforeOpen(PRInt32 aNamespaceID, nsIAtom* aName);
/**
* Returns PR_TRUE if a line break should be inserted after an element open tag
*/
virtual PRBool LineBreakAfterOpen(PRInt32 aNamespaceID, nsIAtom* aName);
/**
* Returns PR_TRUE if a line break should be inserted after an element close tag
*/
virtual PRBool LineBreakBeforeClose(PRInt32 aNamespaceID, nsIAtom* aName);
/**
* Returns PR_TRUE if a line break should be inserted after an element close tag
*/
virtual PRBool LineBreakAfterClose(PRInt32 aNamespaceID, nsIAtom* aName);
/**
* add intendation. Call only in the case of formating and if the current
* position is at 0. It updates the column position.
*/
void AppendIndentation(nsAString& aStr);
virtual void IncrIndentation(nsIAtom* aName);
virtual void DecrIndentation(nsIAtom* aName);
// Functions to check for newlines that needs to be added between nodes in
// the root of a document. See mAddNewlineForRootNode
void MaybeAddNewlineForRootNode(nsAString& aStr);
void MaybeFlagNewlineForRootNode(nsIDOMNode* aNode);
// Functions to check if we enter in or leave from a preformated content
virtual void MaybeEnterInPreContent(nsIContent* aNode);
virtual void MaybeLeaveFromPreContent(nsIContent* aNode);
PRInt32 mPrefixIndex;
struct NameSpaceDecl {
nsString mPrefix;
nsString mURI;
nsIDOMElement* mOwner;
};
nsTArray<NameSpaceDecl> mNameSpaceStack;
// nsIDocumentEncoder flags
PRUint32 mFlags;
// characters to use for line break
nsString mLineBreak;
// The charset that was passed to Init()
nsCString mCharset;
// current column position on the current line
PRInt32 mColPos;
// true = pretty formating should be done (OutputFormated flag)
PRPackedBool mDoFormat;
// true = no formatting,(OutputRaw flag)
// no newline convertion and no rewrap long lines even if OutputWrap is set.
PRPackedBool mDoRaw;
// true = wrapping should be done (OutputWrap flag)
PRPackedBool mDoWrap;
// number of maximum column in a line, in the wrap mode
PRInt32 mMaxColumn;
// current indent value
nsString mIndent;
// this is the indentation level after the indentation reached
// the maximum length of indentation
PRInt32 mIndentOverflow;
// says if the indentation has been already added on the current line
PRPackedBool mIsIndentationAddedOnCurrentLine;
// the string which is currently added is in an attribute
PRPackedBool mInAttribute;
// true = a newline character should be added. It's only
// useful when serializing root nodes. see MaybeAddNewlineForRootNode and
// MaybeFlagNewlineForRootNode
PRPackedBool mAddNewlineForRootNode;
// Indicates that a space will be added if and only if content is
// continued on the same line while serializing source. Otherwise,
// the newline character acts as the whitespace and no space is needed.
// used when mDoFormat = true
PRPackedBool mAddSpace;
// says that if the next string to add contains a newline character at the
// begining, then this newline character should be ignored, because a
// such character has already been added into the output string
PRPackedBool mMayIgnoreLineBreakSequence;
// number of nested elements which have preformated content
PRInt32 mPreLevel;
};
nsresult
NS_NewXMLContentSerializer(nsIContentSerializer** aSerializer);
#endif