mediawiki-extensions-Visual.../modules/ve/dm/ve.dm.Converter.js

835 lines
28 KiB
JavaScript
Raw Normal View History

/**
* VisualEditor data model Converter class.
*
* @copyright 2011-2012 VisualEditor Team and others; see AUTHORS.txt
* @license The MIT License (MIT); see LICENSE.txt
*/
/**
* Converter between HTML DOM and VisualEditor linear data.
*
* @class
* @constructor
* @param {Object} options Conversion options
*/
Object management: Object create/inherit/clone utilities * For the most common case: - replace ve.extendClass with ve.inheritClass (chose slightly different names to detect usage of the old/new one, and I like 'inherit' better). - move it up to below the constructor, see doc block for why. * Cases where more than 2 arguments were passed to ve.extendClass are handled differently depending on the case. In case of a longer inheritance tree, the other arguments could be omitted (like in "ve.ce.FooBar, ve.FooBar, ve.Bar". ve.ce.FooBar only needs to inherit from ve.FooBar, because ve.ce.FooBar inherits from ve.Bar). In the case of where it previously had two mixins with ve.extendClass(), either one becomes inheritClass and one a mixin, both to mixinClass(). No visible changes should come from this commit as the instances still all have the same visible properties in the end. No more or less than before. * Misc.: - Be consistent in calling parent constructors in the same order as the inheritance. - Add missing @extends and @param documentation. - Replace invalid {Integer} type hint with {Number}. - Consistent doc comments order: @class, @abstract, @constructor, @extends, @params. - Fix indentation errors A fairly common mistake was a superfluous space before the identifier on the assignment line directly below the documentation comment. $ ack "^ [^*]" --js modules/ve - Typo "Inhertiance" -> "Inheritance". - Replacing the other confusing comment "Inheritance" (inside the constructor) with "Parent constructor". - Add missing @abstract for ve.ui.Tool. - Corrected ve.FormatDropdownTool to ve.ui.FormatDropdownTool.js - Add function names to all @constructor functions. Now that we have inheritance it is important and useful to have these functions not be anonymous. Example of debug shot: http://cl.ly/image/1j3c160w3D45 Makes the difference between < documentNode; > ve_dm_DocumentNode ... : ve_dm_BranchNode ... : ve_dm_Node ... : ve_dm_Node ... : Object ... without names (current situation): < documentNode; > Object ... : Object ... : Object ... : Object ... : Object ... though before this commit, it really looks like this (flattened since ve.extendClass really did a mixin): < documentNode; > Object ... ... ... Pattern in Sublime (case-sensitive) to find nameless constructor functions: "^ve\..*\.([A-Z])([^\.]+) = function \(" Change-Id: Iab763954fb8cf375900d7a9a92dec1c755d5407e
2012-09-05 06:07:47 +00:00
ve.dm.Converter = function ve_dm_Converter( nodeFactory, annotationFactory ) {
// Properties
this.nodeFactory = nodeFactory;
this.annotationFactory = annotationFactory;
this.elements = { 'toDomElement': {}, 'toDataElement': {}, 'dataElementTypes': {} };
this.annotations = { 'toDomElement': {}, 'toDataAnnotation': {} };
// Events
this.nodeFactory.addListenerMethod( this, 'register', 'onNodeRegister' );
this.annotationFactory.addListenerMethod( this, 'register', 'onAnnotationRegister' );
};
/* Static Methods */
/**
* Get linear model data from a string optionally applying annotations
*
* @param {String} text Plain text to convert
* @param {Array} [annotations] Array of annotation objects to apply
* @returns {Array} Linear model data, one element per character
*/
ve.dm.Converter.getDataContentFromText = function ( text, annotations ) {
var characters = text.split( '' ),
annotationSet = new ve.AnnotationSet(),
i;
if ( !annotations || annotations.length === 0 ) {
return characters;
}
// Build annotation set
for ( i = 0; i < annotations.length; i++ ) {
if ( annotations[i].data && ve.isEmptyObject( annotations[i].data ) ) {
// Cleanup empty data property
delete annotations[i].data;
}
annotationSet.push( annotations[i] );
}
// Apply annotations to characters
for ( i = 0; i < characters.length; i++ ) {
// Make a shallow copy of the annotationSet object, otherwise adding an annotation to one
// character automatically adds it to all of others as well, annotations should be treated
// as immutable, so it's OK to share references, but annotation sets are not immutable, so
// it's not safe to share references - each annotated character needs its own set
characters[i] = [characters[i], annotationSet.clone()];
}
return characters;
};
/* Methods */
/**
* Responds to register events from the node factory.
*
* If a node is special; such as document, alienInline, alienBlock and text; its {converters}
* property should be set to null, as to distinguish it from a new node type that someone has simply
* forgotten to implement converters for.
*
* @method
* @param {String} type Node type
* @param {Function} constructor Node constructor
* @throws 'Missing conversion data in node implementation of {type}'
*/
ve.dm.Converter.prototype.onNodeRegister = function ( dataElementType, constructor ) {
if ( constructor.converters === undefined ) {
throw new Error( 'Missing conversion data in node implementation of ' + dataElementType );
} else if ( constructor.converters !== null ) {
var i,
domElementTypes = constructor.converters.domElementTypes,
toDomElement = constructor.converters.toDomElement,
toDataElement = constructor.converters.toDataElement;
// Registration
this.elements.toDomElement[dataElementType] = toDomElement;
for ( i = 0; i < domElementTypes.length; i++ ) {
this.elements.toDataElement[domElementTypes[i]] = toDataElement;
this.elements.dataElementTypes[domElementTypes[i]] = dataElementType;
}
}
};
/**
* Responds to register events from the annotation factory.
*
* @method
* @param {String} type Base annotation type
* @param {Function} constructor Annotation constructor
* @throws 'Missing conversion data in annotation implementation of {type}'
*/
ve.dm.Converter.prototype.onAnnotationRegister = function ( dataElementType, constructor ) {
if ( constructor.converters === undefined ) {
throw new Error( 'Missing conversion data in annotation implementation of ' + dataElementType );
} else if ( constructor.converters !== null ) {
var i,
domElementTypes = constructor.converters.domElementTypes,
toDomElement = constructor.converters.toDomElement,
toDataAnnotation = constructor.converters.toDataAnnotation;
// Registration
this.annotations.toDomElement[dataElementType] = toDomElement;
for ( i = 0; i < domElementTypes.length; i++ ) {
this.annotations.toDataAnnotation[domElementTypes[i]] = toDataAnnotation;
}
}
};
/**
* Get the DOM element for a given linear model element.
*
* This invokes the toDomElement function registered for the element type.
* NOTE: alienBlock and alienInline elements are not supported, if you pass them this function
* will return false. (Opposite of District 9: no aliens allowed.)
*
* @method
* @param {Object} dataElement Linear model element
* @returns {HTMLElement|false} DOM element, or false if this element cannot be converted
*/
ve.dm.Converter.prototype.getDomElementFromDataElement = function ( dataElement ) {
var key, domElement, dataElementAttributes,
dataElementType = dataElement.type;
if (
// Aliens
dataElementType === 'alienInline' || dataElementType === 'alienBlock' ||
// Unsupported elements
!( dataElementType in this.elements.toDomElement)
) {
return false;
}
domElement = this.elements.toDomElement[dataElementType]( dataElementType, dataElement );
dataElementAttributes = dataElement.attributes;
if ( dataElementAttributes ) {
for ( key in dataElementAttributes ) {
// Only include 'html/*' attributes and strip the 'html/' from the beginning of the name
if ( key.indexOf( 'html/' ) === 0 ) {
domElement.setAttribute( key.substr( 5 ), dataElementAttributes[key] );
}
}
}
return domElement;
};
/**
* Get the linear model data element for a given DOM element.
*
* This invokes the toDataElement function registered for the element type
*
* @method
* @param {HTMLElement} domElement DOM element
* @returns {Object|false} Linear model element, or false if this node cannot be converted
*/
ve.dm.Converter.prototype.getDataElementFromDomElement = function ( domElement ) {
var dataElement, domElementAttributes, dataElementAttributes, domElementAttribute, i,
domElementType = domElement.nodeName.toLowerCase();
if (
// Unsupported elements
!( domElementType in this.elements.toDataElement )
// TODO check for generated elements
) {
return false;
}
dataElement = this.elements.toDataElement[domElementType]( domElementType, domElement );
domElementAttributes = domElement.attributes;
if ( domElementAttributes.length ) {
dataElementAttributes = dataElement.attributes = dataElement.attributes || {};
// Inlcude all attributes and prepend 'html/' to each attribute name
for ( i = 0; i < domElementAttributes.length; i++ ) {
domElementAttribute = domElementAttributes[i];
dataElementAttributes['html/' + domElementAttribute.name] = domElementAttribute.value;
}
}
return dataElement;
};
/**
* Check if an HTML DOM node represents an annotation, and if so, build an annotation object for it.
*
* @example Annotation Object
* { 'type': 'type', data: { 'key': 'value', ... } }
*
* @param {HTMLElement} domElement HTML DOM node
* @returns {Object|false} Annotation object, or false if this node is not an annotation
*/
ve.dm.Converter.prototype.getDataAnnotationFromDomElement = function ( domElement ) {
var domElementType = domElement.nodeName.toLowerCase(),
toDataAnnotation = this.annotations.toDataAnnotation[domElementType];
if ( typeof toDataAnnotation === 'function' ) {
return toDataAnnotation( domElementType, domElement );
}
return false;
};
/**
* Build an HTML DOM node for a linear model annotation.
*
* @method
* @param {Object} dataAnnotation Annotation object
* @returns {HTMLElement|false} HTML DOM node, or false if this annotation is not known
*/
ve.dm.Converter.prototype.getDomElementFromDataAnnotation = function ( dataAnnotation ) {
var split = dataAnnotation.type.split( '/' ),
baseType = split[0],
subType = split.slice( 1 ).join( '/' ),
toDomElement = this.annotations.toDomElement[baseType];
if ( typeof toDomElement === 'function' ) {
return toDomElement( subType, dataAnnotation );
}
return false;
};
/**
* Convert an HTML DOM tree to a linear model.
*
* Do not use the annotations, dataElement and path parameters, they're used for internal
* recursion only.
*
* @method
* @param {HTMLElement} domElement Wrapper div containing the HTML to convert
* @param {Array} [annotations] Array of annotations (objects) to apply to the generated data
* @param {Object} [dataElement] Data element to wrap the returned data in
* @param {Array} [path] Array of linear model element types
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
* @param {Boolean} [alreadyWrapped] Whether the caller has already started wrapping bare content in a paragraph
* @returns {Array} Linear model data
*/
ve.dm.Converter.prototype.getDataFromDom = function ( domElement, annotations, dataElement, path, alreadyWrapped ) {
function createAlien( domElement, isInline ) {
var type = isInline ? 'alienInline' : 'alienBlock';
return [
{
'type': type,
'attributes': {
'html': $( '<div>' ).append( $( domElement ).clone() ).html()
}
},
{ 'type': '/' + type }
];
}
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
function addWhitespace( element, index, whitespace ) {
if ( !element.internal ) {
element.internal = {};
}
// whitespace = [ outerPre, innerPre, innerPost, outerPost ]
// <tag> text </tag> <nextTag>
// ^^^^^^^^^^ ^^^^^^^^^ ^^^^^^^^^^^ ^^^^^^^^^^
// outerPre innerPre innerPost outerPost
if ( !element.internal.whitespace ) {
element.internal.whitespace = [];
}
if ( !element.internal.whitespace[index] ) {
element.internal.whitespace[index] = '';
}
element.internal.whitespace[index] = whitespace;
}
function processNextWhitespace( element ) {
// This function uses and changes nextWhitespace in the outer function's scope,
// which means it's not really a function but more of a shortcut.
if ( nextWhitespace !== '' ) {
addWhitespace( element, 0, nextWhitespace );
nextWhitespace = '';
}
}
// Fallback to defaults
annotations = annotations || [];
path = path || ['document'];
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
var i, childDomElement, annotation, childDataElement, text, childTypes, matches,
wrappingParagraph, prevElement, alien, rdfaType,
data = [],
branchType = path[path.length - 1],
branchIsContent = ve.dm.nodeFactory.canNodeContainContent( branchType ),
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
nextWhitespace = '',
wrappedWhitespace = '',
wrapping = alreadyWrapped,
wrappingIsOurs = false;
// Open element
if ( dataElement ) {
data.push( dataElement );
}
// Add contents
for ( i = 0; i < domElement.childNodes.length; i++ ) {
childDomElement = domElement.childNodes[i];
switch ( childDomElement.nodeType ) {
case Node.ELEMENT_NODE:
// Alienate anything with a mw: type that isn't registered
// HACK because we don't actually have an RDFa type registry yet,
// this hardcodes the set of recognized types
rdfaType = childDomElement.getAttribute( 'rel' ) ||
childDomElement.getAttribute( 'typeof' ) ||
childDomElement.getAttribute( 'property' );
if (
rdfaType &&
rdfaType.match( /^mw:/ ) &&
!rdfaType.match( /^mw:WikiLink/ ) &&
!rdfaType.match( /^mw:ExtLink/ )
) {
alien = createAlien( childDomElement, branchIsContent );
data = data.concat( alien );
processNextWhitespace( alien );
prevElement = alien;
break;
}
// Detect and handle annotated content
annotation = this.getDataAnnotationFromDomElement( childDomElement );
if ( annotation ) {
// Start auto-wrapping of bare content
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
if ( !wrapping && !branchIsContent ) {
// Mark this paragraph as having been generated by
// us, so we can strip it on the way out
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
wrappingParagraph = {
'type': 'paragraph',
'internal': { 'generated': 'wrapper' }
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
};
data.push( wrappingParagraph );
wrapping = true;
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
wrappingIsOurs = true;
processNextWhitespace( wrappingParagraph );
prevElement = wrappingParagraph;
}
// Append child element data
data = data.concat(
this.getDataFromDom(
childDomElement, annotations.concat( [ annotation ] ), undefined, path, wrapping
)
);
break;
}
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// End auto-wrapping of bare content from a previously processed node
if ( wrapping ) {
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
if ( wrappedWhitespace !== '' ) {
// Remove wrappedWhitespace from data
data.splice( -wrappedWhitespace.length, wrappedWhitespace.length );
addWhitespace( wrappingParagraph, 3, wrappedWhitespace );
nextWhitespace = wrappedWhitespace;
}
data.push( { 'type': '/paragraph' } );
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
wrappingParagraph = undefined;
wrapping = false;
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
wrappingIsOurs = false;
}
// Append child element data
childDataElement = this.getDataElementFromDomElement( childDomElement );
if ( childDataElement ) {
data = data.concat(
this.getDataFromDom(
childDomElement,
[],
childDataElement,
path.concat( childDataElement.type ),
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
wrapping
)
);
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
processNextWhitespace( childDataElement );
prevElement = childDataElement;
break;
}
// We don't know what this is, fall back to alien
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
alien = createAlien( childDomElement, branchIsContent );
data = data.concat( alien );
processNextWhitespace( alien );
prevElement = alien;
break;
case Node.TEXT_NODE:
text = childDomElement.data;
if ( text === '' ) {
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// Empty text node?!?
break;
}
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
if ( !branchIsContent ) {
// Strip and store outer whitespace
if ( text.match( /^\s+$/ ) ) {
// This text node is whitespace only
if ( wrapping ) {
// We're already wrapping, so output this whitespace
// and store it in wrappedWhitespace (see
// comment about wrappedWhitespace below)
wrappedWhitespace = text;
data = data.concat(
ve.dm.Converter.getDataContentFromText( wrappedWhitespace, annotations )
);
} else {
// We're not in wrapping mode, store this whitespace
if ( !prevElement ) {
if ( dataElement ) {
// First child, store as inner
// whitespace in the parent
addWhitespace( dataElement, 1, text );
}
// Else, WTF?!? This is not supposed to
// happen, but it's not worth
// throwing an exception over.
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
} else {
addWhitespace( prevElement, 3, text );
}
nextWhitespace = text;
wrappedWhitespace = '';
}
// We're done, no actual text left to process
break;
} else {
// This text node contains actual text
// Separate the real text from the whitespace
// HACK: . doesn't match newlines in JS, so use
// [\s\S] to match any character
matches = text.match( /^(\s*)([\s\S]*?)(\s*)$/ );
if ( !wrapping ) {
// Wrap the text in a paragraph and output it
// Mark this paragraph as having been generated by
// us, so we can strip it on the way out
wrappingParagraph = {
'type': 'paragraph',
'internal': { 'generated': 'wrapper' }
};
processNextWhitespace( wrappingParagraph );
data.push( wrappingParagraph );
wrapping = true;
wrappingIsOurs = true;
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// Only store leading whitespace if we just
// started wrapping
if ( matches[1] !== '' ) {
if ( !prevElement ) {
if ( dataElement ) {
// First child, store as inner
// whitespace in the parent
addWhitespace( dataElement, 1, matches[1] );
}
// Else, WTF?!? This is not supposed to
// happen, but it's not worth
// throwing an exception over.
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
} else {
addWhitespace( prevElement, 3, matches[1] );
}
addWhitespace( wrappingParagraph, 0, matches[1] );
}
} else {
// We were already wrapping in a paragraph,
// so the leading whitespace must be output
data = data.concat(
ve.dm.Converter.getDataContentFromText( matches[1], annotations )
);
}
// Output the text sans whitespace
data = data.concat(
ve.dm.Converter.getDataContentFromText( matches[2], annotations )
);
// Don't store this in wrappingParagraph.internal.whitespace[3]
// and nextWhitespace just yet. Instead, store it
// in wrappedWhitespace. There might be more text
// nodes after this one, so we output wrappedWhitespace
// for now and undo that if it turns out this was
// the last text node. We can't output it later
// because we have to apply the correct annotations.
wrappedWhitespace = matches[3];
data = data.concat(
ve.dm.Converter.getDataContentFromText( wrappedWhitespace, annotations )
);
prevElement = wrappingParagraph;
break;
}
2012-08-10 21:09:04 +00:00
}
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// Strip leading and trailing inner whitespace
// (but only in non-annotation nodes)
// and store it so it can be restored later.
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
if ( annotations.length === 0 && i === 0 && dataElement ) {
2012-08-10 21:09:04 +00:00
// Strip leading whitespace from the first child
matches = text.match( /^\s+/ );
if ( matches && matches[0] !== '' ) {
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
addWhitespace( dataElement, 1, matches[0] );
2012-08-10 21:09:04 +00:00
text = text.substring( matches[0].length );
}
}
if (
annotations.length === 0 &&
i === domElement.childNodes.length - 1 &&
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
dataElement
2012-08-10 21:09:04 +00:00
) {
// Strip trailing whitespace from the last child
matches = text.match( /\s+$/ );
if ( matches && matches[0] !== '' ) {
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
addWhitespace( dataElement, 2, matches[0] );
2012-08-10 21:09:04 +00:00
text = text.substring( 0,
text.length - matches[0].length );
}
}
// Annotate the text and output it
data = data.concat(
ve.dm.Converter.getDataContentFromText( text, annotations )
);
break;
case Node.COMMENT_NODE:
// TODO: Preserve comments by inserting them into the linear model too
// Could use placeholders for this too, although they'd need to be
// inline in certain cases
break;
}
}
// End auto-wrapping of bare content
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
if ( wrapping && wrappingIsOurs ) {
if ( wrappedWhitespace !== '' ) {
// Remove wrappedWhitespace from data
data.splice( -wrappedWhitespace.length, wrappedWhitespace.length );
addWhitespace( wrappingParagraph, 3, wrappedWhitespace );
nextWhitespace = wrappedWhitespace;
}
data.push( { 'type': '/paragraph' } );
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// Don't set wrapping = false here because it's checked below
wrappingParagraph = undefined;
}
// If we're closing a node that doesn't have any children, but could contain a paragraph,
// add a paragraph. This prevents things like empty list items
childTypes = ve.dm.nodeFactory.getChildNodeTypes( branchType );
if ( branchType !== 'paragraph' && dataElement && data[data.length - 1] === dataElement &&
!wrapping && !ve.dm.nodeFactory.canNodeContainContent( branchType ) &&
!ve.dm.nodeFactory.isNodeContent( branchType ) &&
Refactor ve.js utilities and improve documentation Refactor: * ve.indexOf Renamed from ve.inArray. This was named after the jQuery method which in turn has a longer story about why it is so unfortunately named. It doesn't return a boolean, but an index. Hence the native method being called indexOf as well. * ve.bind Renamed from ve.proxy. I considered making it use Function.prototype.bind if available. As it performs better than $.proxy (which doesn't use to the native bind if available). However since bind needs to be bound itself in order to use it detached, it turns out with the "call()" and "bind()" it is slower than the $.proxy shim: http://jsperf.com/function-bind-shim-perf It would've been like this: ve.bind = Function.prototype.bind ? Function.prototype.call.bind( Function.prototype.bind ) : $.proxy; But instead sticking to ve.bind = $.proxy; * ve.extendObject Documented the parts of jQuery.extend that we use. This makes it easier to replace in the future. Documentation: * Added function documentation blocks. * Added annotations to functions that we will be able to remove in the future in favour of the native methods. With "@until + when/how". In this case "ES5". Meaning, whenever we drop support for browsers that don't support ES5. Although in the developer community ES5 is still fairly fresh, browsers have been aware for it long enough that thee moment we're able to drop it may be sooner than we think. The only blocker so far is IE8. The rest of the browsers have had it long enough that the traffic we need to support of non-IE supports it. Misc.: * Removed 'node: true' from .jshintrc since Parsoid is no longer in this repo and thus no more nodejs files. - This unraveled two lint errors: Usage of 'module' and 'console'. (both were considered 'safe globals' due to nodejs, but not in browser code). * Replaced usage (before renaming): - $.inArray -> ve.inArray - Function.prototype.bind -> ve.proxy - Array.isArray -> ve.isArray - [].indexOf -> ve.inArray - $.fn.bind/live/delegate/unbind/die/delegate -> $.fn.on/off Change-Id: Idcf1fa6a685b6ed3d7c99ffe17bd57a7bc586a2c
2012-08-11 08:14:56 +00:00
( childTypes === null || ve.indexOf( 'paragraph', childTypes ) !== -1 )
) {
data.push( { 'type': 'paragraph', 'internal': { 'generated': 'wrapper' } } );
data.push( { 'type': '/paragraph' } );
}
// Close element
if ( dataElement ) {
data.push( { 'type': '/' + dataElement.type } );
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// Add the whitespace after the last child to the parent as innerPost
if ( nextWhitespace !== '' ) {
addWhitespace( dataElement, 2, nextWhitespace );
nextWhitespace = '';
}
}
// Don't return an empty document
if ( branchType === 'document' && data.length === 0 ) {
return [
{ 'type': 'paragraph', 'internal': { 'generated': 'wrapper' } },
{ 'type': '/paragraph' }
];
}
return data;
};
/**
* Convert linear model data to an HTML DOM
*
* @method
* @param {Array} data Linear model data
* @returns {HTMLElement} Wrapper div containing the resulting HTML
*/
ve.dm.Converter.prototype.getDomFromData = function ( data ) {
var text, i, j, annotations, annotation, hash, annotationElement, done, dataElement, arr,
wrapper, childDomElement, pre, post, ours, theirs, parentDomElement, startClosingAt,
container = document.createElement( 'div' ),
domElement = container,
annotationStack = new ve.AnnotationSet();
for ( i = 0; i < data.length; i++ ) {
if ( typeof data[i] === 'string' ) {
// Text
text = '';
// Continue forward as far as the plain text goes
while ( typeof data[i] === 'string' ) {
text += data[i];
i++;
}
// i points to the first non-text thing, go back one so we don't skip this later
i--;
// Add text
domElement.appendChild( document.createTextNode( text ) );
} else if (
ve.isArray( data[i] ) ||
(
data[i].annotations !== undefined &&
ve.dm.nodeFactory.isNodeContent( data[i].type )
)
) {
// Annotated text or annotated nodes
text = '';
while (
ve.isArray( data[i] ) ||
(
data[i].annotations !== undefined &&
ve.dm.nodeFactory.isNodeContent( data[i].type )
)
) {
annotations = data[i].annotations || data[i][1];
// Close annotations as needed
// Go through annotationStack from bottom to top (low to high),
// and find the first annotation that's not in annotations.
startClosingAt = undefined;
arr = annotationStack.get();
for ( j = 0; j < arr.length; j++ ) {
annotation = arr[j];
if ( !annotations.contains( annotation ) ) {
startClosingAt = j;
break;
}
}
if ( startClosingAt !== undefined ) {
// Close all annotations from top to bottom (high to low)
// until we reach startClosingAt
for ( j = annotationStack.getLength() - 1; j >= startClosingAt; j-- ) {
// Add text if needed
if ( text.length > 0 ) {
domElement.appendChild( document.createTextNode( text ) );
text = '';
}
// Traverse up
domElement = domElement.parentNode;
// Remove from annotationStack
annotationStack.removeAt( j );
}
}
// Open annotations as needed
arr = annotations.get();
for ( j = 0; j < arr.length; j++ ) {
annotation = arr[j];
if ( !annotationStack.contains( annotation ) ) {
// Add text if needed
if ( text.length > 0 ) {
domElement.appendChild( document.createTextNode( text ) );
text = '';
}
// Create new node and descend into it
annotationElement = this.getDomElementFromDataAnnotation( annotation );
domElement.appendChild( annotationElement );
domElement = annotationElement;
// Add to annotationStack
annotationStack.push( annotation );
}
}
if ( data[i].annotations === undefined ) {
// Annotated text
text += data[i][0];
} else {
// Annotated node
// Add text if needed
if ( text.length > 0 ) {
domElement.appendChild( document.createTextNode( text ) );
text = '';
}
// Insert the element
domElement.appendChild( this.getDomElementFromDataElement( data[i] ) );
// Increment i once more so we skip over the closing as well
i++;
}
i++;
}
// We're now at the first non-annotated thing, go back one so we don't skip this later
i--;
// Add any gathered text
if ( text.length > 0 ) {
domElement.appendChild( document.createTextNode( text ) );
text = '';
}
// Close any remaining annotation nodes
for ( j = annotationStack.getLength() - 1; j >= 0; j-- ) {
// Traverse up
domElement = domElement.parentNode;
}
// Clear annotationStack
annotationStack = new ve.AnnotationSet();
} else if ( data[i].type !== undefined ) {
dataElement = data[i];
// Element
if ( dataElement.type === 'alienBlock' || dataElement.type === 'alienInline' ) {
// Create nodes from source
wrapper = document.createElement( 'div' );
wrapper.innerHTML = dataElement.attributes.html;
// Add element - adds all child elements, but there really should only be 1
while ( wrapper.firstChild ) {
domElement.appendChild( wrapper.firstChild );
}
// Make sure the alien closing is skipped
i++;
} else if ( dataElement.type.charAt( 0 ) === '/' ) {
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
parentDomElement = domElement.parentNode;
// Process whitespace
// whitespace = [ outerPre, innerPre, innerPost, outerPost ]
if ( domElement.veInternal && domElement.veInternal.whitespace ) {
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// Process inner whitespace. innerPre is for sure legitimate
// whitespace that should be inserted; if it was a duplicate
// of our child's outerPre, we would have cleared it.
pre = domElement.veInternal.whitespace[1];
2012-08-10 21:09:04 +00:00
if ( pre ) {
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
if (
domElement.firstChild &&
domElement.firstChild.nodeType === 3
) {
2012-08-10 21:09:04 +00:00
// First child is a TextNode, prepend to it
domElement.firstChild.insertData( 0, pre );
} else {
// Prepend a TextNode
domElement.insertBefore(
document.createTextNode( pre ),
domElement.firstChild
);
}
}
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
ours = domElement.veInternal.whitespace[2];
if ( domElement.lastOuterPost === undefined ) {
// This node didn't have any structural children
// (i.e. it's a content-containing node), so there's
// nothing to check innerPost against
theirs = ours;
} else {
theirs = domElement.lastOuterPost;
}
if ( ours && ours === theirs ) {
if (
domElement.lastChild &&
domElement.lastChild.nodeType === 3
) {
2012-08-10 21:09:04 +00:00
// Last child is a TextNode, append to it
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
domElement.lastChild.appendData( ours );
2012-08-10 21:09:04 +00:00
} else {
// Append a TextNode
domElement.appendChild(
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
document.createTextNode( ours )
2012-08-10 21:09:04 +00:00
);
}
}
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// Tell the parent about our outerPost
parentDomElement.lastOuterPost = domElement.veInternal.whitespace[3] || '';
} else {
// Use empty string, because undefined means there were no
// structural children
parentDomElement.lastOuterPost = '';
2012-08-10 21:09:04 +00:00
}
// If closing a generated wrapper node, unwrap it
// It would be nicer if we could avoid generating in the first
// place, but then remembering where we have to skip ascending
// to the parent would be tricky.
if ( domElement.veInternal && domElement.veInternal.generated === 'wrapper' ) {
while ( domElement.firstChild ) {
parentDomElement.insertBefore(
domElement.firstChild,
domElement
);
}
parentDomElement.removeChild( domElement );
}
delete domElement.veInternal;
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
delete domElement.lastOuterPost;
// Ascend to parent node
domElement = parentDomElement;
} else {
// Create node from data
childDomElement = this.getDomElementFromDataElement( dataElement );
// Add reference to internal data
if ( dataElement.internal ) {
childDomElement.veInternal = dataElement.internal;
2012-08-10 21:09:04 +00:00
}
// Add element
domElement.appendChild( childDomElement );
// Descend into child node
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
parentDomElement = domElement;
domElement = childDomElement;
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// Process outer whitespace
// Every piece of outer whitespace is duplicated somewhere:
// each node's outerPost is duplicated as the next node's
// outerPre, the first node's outerPre is the parent's
// innerPre, and the last node's outerPost is the parent's
// innerPost. For each piece of whitespace, we verify that
// the duplicate matches. If it doesn't, we take that to
// mean the user has messed with it and don't output any
// whitespace.
if ( domElement.veInternal && domElement.veInternal.whitespace ) {
// Process this node's outerPre
ours = domElement.veInternal.whitespace[0];
theirs = undefined;
if ( domElement.previousSibling ) {
// Get previous sibling's outerPost
theirs = parentDomElement.lastOuterPost;
} else if ( parentDomElement === container ) {
// outerPre of the very first node in the document, this one
// has no duplicate
theirs = ours;
} else {
// First child, get parent's innerPre
if (
parentDomElement.veInternal &&
parentDomElement.veInternal.whitespace
) {
theirs = parentDomElement.veInternal.whitespace[1];
// Clear after use so it's not used twice
parentDomElement.veInternal.whitespace[1] = undefined;
}
// else theirs=undefined
}
if ( ours && ours === theirs ) {
// Matches the duplicate, insert a TextNode
parentDomElement.insertBefore(
document.createTextNode( ours ),
domElement
);
}
}
}
}
}
Preserve whitespace between elements This commit fully utilizes all four positions in the internal.whitespace array. Outer whitespace is now preserved as well, and is duplicated either in the adjacent sibling (one node's outerPost is the next sibling's outerPre) or in the parent (a branch node's innerPre is its first child's outerPre, and its innerPost is its last child's outerPost). Before restoring saved whitespace, we check that these two agree with each other, and if they disagree we assume the user has been moving stuff around and don't restore any whitespace in that spot. The whitespace at the very beginning and the very end of the document (i.e. the first node's outerPre and the last node's outerPost) isn't duplicated anywhere, nor is inner whitespace in content nodes. The basic outline of the implementation is: * When we encounter whitespace, strip it and store it in the previous node's outerPost. Also store it in nextWhitespace so we can put it in the next node's outerPre once we encounter that node. * When we encounter whitespace in wrapped bare text, we don't know in advance if it's gonna be succeeded by more non-whitespace (in which case it needs to be output verbatim), or not (in which case it's leading whitespace and needs to be stripped and stored). The fact that annotations are nodes in HTML makes this trickier. So we write the whitespace to the temporary linmod and store it in wrappedWhitespace, then if it turns out to be trailing whitespace we take it back out of the data array and record it the usual way. * Because text nodes can contain any combination of leading whitespace actual text and trailing whitespace, and because we may or may not already have opened a wrapping paragraph, there are a lot of different combinations to handle. We handle all of them but the resulting code is pretty dense and verbose. More low-level list of changes: In getDataFromDom(): * Added helper function addWhitespace() for storing whitespace for an element * Added helper function processNextWhitespace() for processing any whitespace passed on from the previous node via the nextWhitespace var * Rename paragraph to wrappingParagraph. Make wrapping default to alreadyWrapped so we can simplify wrapping||alreadyWrapped and !wrapping&&!alreadyWrapped. Add wrappingIsOurs to track whether the wrapping originated in this recursion level (needed for deciding when to close the wrapper). * Add prevElement to track the previous element so we can propagate whitespace to it, and nextWhitespace so we can propagate whitespace to the next element. * Remove previous newline stripping hacks * Integrate the logic for wrapping bare content with the outer whitespace preservation code * Remove wrapperElement, no longer needed because we have a dedicated variable for the wrapping paragraph now and what was previously inner whitespace preservation for wrapper paragraphs is now covered by the outer whitespace preservation code. In getDomFromData(): * Reinsert whitespace where appropriate ** outerPre is inserted when opening the element ** This covers outerPost as well except for the last child's outerPost, which is handled as the parent's innerPost when closing the parent. ** innerPre and innerPost are inserted when closing the element. Care is taken not to insert these if they're duplicates of something else. * Propagate each node's outerPost to the next node (either the next sibling or the parent) using parentDomElement.lastOuterPost. We can't get this using .lastChild because we will have destroyed that child's .veInternal by then, and we can't tell whether a node will be its parent's last child when we process it (all other processing, including first child handling is done when processing the node itself, but this cannot be). * Special handling is needed for the last node's outerPost, which ends up in the container's .lastOuterPost property. Tests: * Allow .html to be null in data<->DOM converter tests. This indicates that the test is a one-way data->DOM test, not a DOM->data->DOM round-trip test. The data will be converted to HTML and checked against .normalizedHtml * Update existing tests as needed * Add tests for outer whitespace preservation and storage * Add test for squashing of whitespace in case of disagreement (this requires .html=null) Change-Id: I4db4fe372a421182e80a2535657af7784ff15f95
2012-08-21 00:37:42 +00:00
// Process the outerPost whitespace of the very last node
if ( container.lastOuterPost !== undefined ) {
if ( container.lastChild && container.lastChild.nodeType === 3 ) {
// Last child is a TextNode, append to it
container.lastChild.appendData( container.lastOuterPost );
} else {
// Append a TextNode
container.appendChild( document.createTextNode( container.lastOuterPost ) );
}
delete container.lastOuterPost;
}
return container;
};
/* Initialization */
ve.dm.converter = new ve.dm.Converter( ve.dm.nodeFactory, ve.dm.annotationFactory );