2012-07-19 00:11:26 +00:00
|
|
|
/**
|
|
|
|
* VisualEditor data model Converter class.
|
2012-07-19 21:25:16 +00:00
|
|
|
*
|
2012-07-19 00:11:26 +00:00
|
|
|
* @copyright 2011-2012 VisualEditor Team and others; see AUTHORS.txt
|
|
|
|
* @license The MIT License (MIT); see LICENSE.txt
|
|
|
|
*/
|
|
|
|
|
2012-05-31 23:50:16 +00:00
|
|
|
/**
|
|
|
|
* Converter between HTML DOM and VisualEditor linear data.
|
|
|
|
*
|
|
|
|
* @class
|
|
|
|
* @constructor
|
|
|
|
* @param {Object} options Conversion options
|
|
|
|
*/
|
2012-09-06 23:15:55 +00:00
|
|
|
ve.dm.Converter = function VeDmConverter( nodeFactory, annotationFactory ) {
|
2012-05-31 23:50:16 +00:00
|
|
|
// Properties
|
|
|
|
this.nodeFactory = nodeFactory;
|
|
|
|
this.annotationFactory = annotationFactory;
|
2012-09-17 13:30:50 +00:00
|
|
|
this.elements = {
|
|
|
|
'toDomElement': {},
|
|
|
|
'toDataElement': {},
|
|
|
|
'dataElementTypes': {}
|
|
|
|
};
|
|
|
|
this.annotations = {
|
|
|
|
'toDomElement': {},
|
|
|
|
'toDataAnnotation': {}
|
|
|
|
};
|
2012-05-31 23:50:16 +00:00
|
|
|
|
|
|
|
// Events
|
|
|
|
this.nodeFactory.addListenerMethod( this, 'register', 'onNodeRegister' );
|
|
|
|
this.annotationFactory.addListenerMethod( this, 'register', 'onAnnotationRegister' );
|
|
|
|
};
|
|
|
|
|
2012-06-07 00:47:27 +00:00
|
|
|
/* 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
|
|
|
|
*/
|
2012-08-07 01:50:44 +00:00
|
|
|
ve.dm.Converter.getDataContentFromText = function ( text, annotations ) {
|
2012-06-07 00:47:27 +00:00
|
|
|
var characters = text.split( '' ),
|
2012-08-24 02:06:36 +00:00
|
|
|
annotationSet = new ve.AnnotationSet(),
|
2012-06-07 00:47:27 +00:00
|
|
|
i;
|
|
|
|
if ( !annotations || annotations.length === 0 ) {
|
|
|
|
return characters;
|
|
|
|
}
|
2012-08-24 02:06:36 +00:00
|
|
|
// Build annotation set
|
2012-06-07 00:47:27 +00:00
|
|
|
for ( i = 0; i < annotations.length; i++ ) {
|
|
|
|
if ( annotations[i].data && ve.isEmptyObject( annotations[i].data ) ) {
|
|
|
|
// Cleanup empty data property
|
|
|
|
delete annotations[i].data;
|
|
|
|
}
|
2012-08-24 02:06:36 +00:00
|
|
|
annotationSet.push( annotations[i] );
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
|
|
|
// Apply annotations to characters
|
|
|
|
for ( i = 0; i < characters.length; i++ ) {
|
2012-08-24 02:06:36 +00:00
|
|
|
// Make a shallow copy of the annotationSet object, otherwise adding an annotation to one
|
2012-06-07 00:47:27 +00:00
|
|
|
// character automatically adds it to all of others as well, annotations should be treated
|
2012-08-24 02:06:36 +00:00
|
|
|
// 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()];
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
|
|
|
return characters;
|
|
|
|
};
|
|
|
|
|
2012-05-31 23:50:16 +00:00
|
|
|
/* Methods */
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Responds to register events from the node factory.
|
|
|
|
*
|
2012-06-20 23:01:02 +00:00
|
|
|
* 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
|
2012-05-31 23:50:16 +00:00
|
|
|
* 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}'
|
|
|
|
*/
|
2012-08-07 01:50:44 +00:00
|
|
|
ve.dm.Converter.prototype.onNodeRegister = function ( dataElementType, constructor ) {
|
2012-05-31 23:50:16 +00:00
|
|
|
if ( constructor.converters === undefined ) {
|
2012-08-08 17:48:53 +00:00
|
|
|
throw new Error( 'Missing conversion data in node implementation of ' + dataElementType );
|
2012-05-31 23:50:16 +00:00
|
|
|
} else if ( constructor.converters !== null ) {
|
2012-08-02 18:46:13 +00:00
|
|
|
var i,
|
|
|
|
domElementTypes = constructor.converters.domElementTypes,
|
2012-06-07 00:47:27 +00:00
|
|
|
toDomElement = constructor.converters.toDomElement,
|
|
|
|
toDataElement = constructor.converters.toDataElement;
|
2012-05-31 23:50:16 +00:00
|
|
|
// Registration
|
2012-06-07 00:47:27 +00:00
|
|
|
this.elements.toDomElement[dataElementType] = toDomElement;
|
2012-08-02 18:46:13 +00:00
|
|
|
for ( i = 0; i < domElementTypes.length; i++ ) {
|
2012-06-07 00:47:27 +00:00
|
|
|
this.elements.toDataElement[domElementTypes[i]] = toDataElement;
|
|
|
|
this.elements.dataElementTypes[domElementTypes[i]] = dataElementType;
|
2012-05-31 23:50:16 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* 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}'
|
|
|
|
*/
|
2012-08-07 01:50:44 +00:00
|
|
|
ve.dm.Converter.prototype.onAnnotationRegister = function ( dataElementType, constructor ) {
|
2012-05-31 23:50:16 +00:00
|
|
|
if ( constructor.converters === undefined ) {
|
2012-08-08 17:48:53 +00:00
|
|
|
throw new Error( 'Missing conversion data in annotation implementation of ' + dataElementType );
|
2012-05-31 23:50:16 +00:00
|
|
|
} else if ( constructor.converters !== null ) {
|
2012-08-02 18:46:13 +00:00
|
|
|
var i,
|
|
|
|
domElementTypes = constructor.converters.domElementTypes,
|
2012-06-07 00:47:27 +00:00
|
|
|
toDomElement = constructor.converters.toDomElement,
|
|
|
|
toDataAnnotation = constructor.converters.toDataAnnotation;
|
2012-05-31 23:50:16 +00:00
|
|
|
// Registration
|
2012-06-07 00:47:27 +00:00
|
|
|
this.annotations.toDomElement[dataElementType] = toDomElement;
|
2012-08-02 18:46:13 +00:00
|
|
|
for ( i = 0; i < domElementTypes.length; i++ ) {
|
2012-06-07 00:47:27 +00:00
|
|
|
this.annotations.toDataAnnotation[domElementTypes[i]] = toDataAnnotation;
|
2012-05-31 23:50:16 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
2012-06-06 17:17:30 +00:00
|
|
|
/**
|
2012-06-08 04:58:56 +00:00
|
|
|
* 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.)
|
2012-06-06 17:17:30 +00:00
|
|
|
*
|
|
|
|
* @method
|
2012-06-08 04:58:56 +00:00
|
|
|
* @param {Object} dataElement Linear model element
|
|
|
|
* @returns {HTMLElement|false} DOM element, or false if this element cannot be converted
|
2012-06-06 17:17:30 +00:00
|
|
|
*/
|
2012-08-07 01:50:44 +00:00
|
|
|
ve.dm.Converter.prototype.getDomElementFromDataElement = function ( dataElement ) {
|
2012-08-02 18:46:13 +00:00
|
|
|
var key, domElement, dataElementAttributes,
|
|
|
|
dataElementType = dataElement.type;
|
2012-06-08 04:58:56 +00:00
|
|
|
if (
|
|
|
|
// Aliens
|
|
|
|
dataElementType === 'alienInline' || dataElementType === 'alienBlock' ||
|
|
|
|
// Unsupported elements
|
|
|
|
!( dataElementType in this.elements.toDomElement)
|
|
|
|
) {
|
|
|
|
return false;
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
2012-08-02 18:46:13 +00:00
|
|
|
domElement = this.elements.toDomElement[dataElementType]( dataElementType, dataElement );
|
|
|
|
dataElementAttributes = dataElement.attributes;
|
2012-06-07 00:47:27 +00:00
|
|
|
if ( dataElementAttributes ) {
|
2012-08-02 18:46:13 +00:00
|
|
|
for ( key in dataElementAttributes ) {
|
2012-06-07 00:47:27 +00:00
|
|
|
// Only include 'html/*' attributes and strip the 'html/' from the beginning of the name
|
2012-06-06 17:17:30 +00:00
|
|
|
if ( key.indexOf( 'html/' ) === 0 ) {
|
2012-06-07 00:47:27 +00:00
|
|
|
domElement.setAttribute( key.substr( 5 ), dataElementAttributes[key] );
|
2012-06-06 17:17:30 +00:00
|
|
|
}
|
|
|
|
}
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
|
|
|
return domElement;
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
2012-06-08 04:58:56 +00:00
|
|
|
* Get the linear model data element for a given DOM element.
|
|
|
|
*
|
2012-08-21 00:44:55 +00:00
|
|
|
* This invokes the toDataElement function registered for the element type
|
2012-06-07 00:47:27 +00:00
|
|
|
*
|
|
|
|
* @method
|
2012-06-08 04:58:56 +00:00
|
|
|
* @param {HTMLElement} domElement DOM element
|
|
|
|
* @returns {Object|false} Linear model element, or false if this node cannot be converted
|
2012-06-07 00:47:27 +00:00
|
|
|
*/
|
2012-08-07 01:50:44 +00:00
|
|
|
ve.dm.Converter.prototype.getDataElementFromDomElement = function ( domElement ) {
|
2012-08-02 18:46:13 +00:00
|
|
|
var dataElement, domElementAttributes, dataElementAttributes, domElementAttribute, i,
|
|
|
|
domElementType = domElement.nodeName.toLowerCase();
|
2012-06-07 00:47:27 +00:00
|
|
|
if (
|
|
|
|
// Unsupported elements
|
|
|
|
!( domElementType in this.elements.toDataElement )
|
2012-08-21 00:44:55 +00:00
|
|
|
// TODO check for generated elements
|
2012-06-07 00:47:27 +00:00
|
|
|
) {
|
2012-06-07 21:16:10 +00:00
|
|
|
return false;
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
2012-08-02 18:46:13 +00:00
|
|
|
dataElement = this.elements.toDataElement[domElementType]( domElementType, domElement );
|
|
|
|
domElementAttributes = domElement.attributes;
|
2012-06-07 00:47:27 +00:00
|
|
|
if ( domElementAttributes.length ) {
|
2012-08-02 18:46:13 +00:00
|
|
|
dataElementAttributes = dataElement.attributes = dataElement.attributes || {};
|
2012-09-06 21:07:39 +00:00
|
|
|
// Include all attributes and prepend 'html/' to each attribute name
|
2012-08-02 18:46:13 +00:00
|
|
|
for ( i = 0; i < domElementAttributes.length; i++ ) {
|
|
|
|
domElementAttribute = domElementAttributes[i];
|
2012-06-07 00:47:27 +00:00
|
|
|
dataElementAttributes['html/' + domElementAttribute.name] = domElementAttribute.value;
|
2012-06-06 17:17:30 +00:00
|
|
|
}
|
|
|
|
}
|
2012-06-07 00:47:27 +00:00
|
|
|
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
|
|
|
|
*/
|
2012-08-07 01:50:44 +00:00
|
|
|
ve.dm.Converter.prototype.getDataAnnotationFromDomElement = function ( domElement ) {
|
2012-07-20 00:24:54 +00:00
|
|
|
var domElementType = domElement.nodeName.toLowerCase(),
|
2012-06-07 00:47:27 +00:00
|
|
|
toDataAnnotation = this.annotations.toDataAnnotation[domElementType];
|
|
|
|
if ( typeof toDataAnnotation === 'function' ) {
|
|
|
|
return toDataAnnotation( domElementType, domElement );
|
|
|
|
}
|
|
|
|
return false;
|
2012-06-06 17:17:30 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
2012-06-08 04:58:56 +00:00
|
|
|
* Build an HTML DOM node for a linear model annotation.
|
2012-06-06 17:17:30 +00:00
|
|
|
*
|
|
|
|
* @method
|
2012-06-08 04:58:56 +00:00
|
|
|
* @param {Object} dataAnnotation Annotation object
|
|
|
|
* @returns {HTMLElement|false} HTML DOM node, or false if this annotation is not known
|
2012-06-06 17:17:30 +00:00
|
|
|
*/
|
2012-08-07 01:50:44 +00:00
|
|
|
ve.dm.Converter.prototype.getDomElementFromDataAnnotation = function ( dataAnnotation ) {
|
2012-08-14 00:50:43 +00:00
|
|
|
var split = dataAnnotation.type.split( '/' ),
|
2012-06-08 04:58:56 +00:00
|
|
|
baseType = split[0],
|
|
|
|
subType = split.slice( 1 ).join( '/' ),
|
|
|
|
toDomElement = this.annotations.toDomElement[baseType];
|
|
|
|
if ( typeof toDomElement === 'function' ) {
|
|
|
|
return toDomElement( subType, dataAnnotation );
|
|
|
|
}
|
|
|
|
return false;
|
2012-06-06 17:17:30 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
2012-06-08 04:58:56 +00:00
|
|
|
* 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.
|
2012-06-06 17:17:30 +00:00
|
|
|
*
|
|
|
|
* @method
|
2012-06-08 04:58:56 +00:00
|
|
|
* @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
|
2012-06-08 04:58:56 +00:00
|
|
|
* @returns {Array} Linear model data
|
2012-06-06 17:17:30 +00:00
|
|
|
*/
|
2012-08-07 01:50:44 +00:00
|
|
|
ve.dm.Converter.prototype.getDataFromDom = function ( domElement, annotations, dataElement, path, alreadyWrapped ) {
|
2012-06-14 19:18:06 +00:00
|
|
|
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 = '';
|
|
|
|
}
|
|
|
|
}
|
2012-06-14 19:18:06 +00:00
|
|
|
|
2012-06-07 00:47:27 +00:00
|
|
|
// Fallback to defaults
|
|
|
|
annotations = annotations || [];
|
|
|
|
path = path || ['document'];
|
2012-09-06 21:07:39 +00:00
|
|
|
var i, j, childDomElement, annotation, childDataElement, text, childTypes, matches,
|
|
|
|
wrappingParagraph, prevElement, alien, rdfaType, isLink,
|
2012-08-02 18:46:13 +00:00
|
|
|
data = [],
|
2012-06-08 22:16:55 +00:00
|
|
|
branchType = path[path.length - 1],
|
2012-06-14 19:18:06 +00:00
|
|
|
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;
|
2012-06-07 00:47:27 +00:00
|
|
|
// Open element
|
|
|
|
if ( dataElement ) {
|
|
|
|
data.push( dataElement );
|
|
|
|
}
|
|
|
|
// Add contents
|
2012-08-02 18:46:13 +00:00
|
|
|
for ( i = 0; i < domElement.childNodes.length; i++ ) {
|
|
|
|
childDomElement = domElement.childNodes[i];
|
2012-06-07 00:47:27 +00:00
|
|
|
switch ( childDomElement.nodeType ) {
|
|
|
|
case Node.ELEMENT_NODE:
|
2012-09-06 21:07:39 +00:00
|
|
|
// HACK handle <meta>/<link> separately because of the
|
|
|
|
// metaInline/metaBlock distinction
|
|
|
|
if (
|
|
|
|
childDomElement.nodeName.toLowerCase() === 'meta' ||
|
|
|
|
childDomElement.nodeName.toLowerCase() === 'link'
|
|
|
|
) {
|
|
|
|
isLink = childDomElement.nodeName.toLowerCase() === 'link';
|
|
|
|
childDataElement = {
|
|
|
|
'type': branchIsContent ? 'metaInline' : 'metaBlock',
|
|
|
|
'attributes': {
|
|
|
|
'style': isLink ? 'link' : 'meta',
|
|
|
|
'key': childDomElement.getAttribute( isLink ? 'rel' : 'property' )
|
|
|
|
}
|
|
|
|
};
|
|
|
|
if ( childDomElement.hasAttribute( isLink ? 'href' : 'content' ) ) {
|
|
|
|
childDataElement.attributes.value = childDomElement.getAttribute( isLink ? 'href' : 'content' );
|
|
|
|
}
|
|
|
|
// Preserve HTML attributes
|
|
|
|
// FIXME the following is duplicated from getDataElementFromDomElement()
|
|
|
|
// Include all attributes and prepend 'html/' to each attribute name
|
|
|
|
for ( j = 0; j < childDomElement.attributes.length; j++ ) {
|
|
|
|
// ..but exclude attributes we've already processed,
|
|
|
|
// because they'll be overwritten otherwise *sigh*
|
|
|
|
// FIXME this sucks, we need a new node type API so bad
|
|
|
|
if (
|
|
|
|
childDomElement.attributes[j].name !== ( isLink ? 'rel' : 'property' ) &&
|
|
|
|
childDomElement.attributes[j].name !== ( isLink ? 'href' : 'content' )
|
|
|
|
) {
|
|
|
|
childDataElement.attributes['html/' + childDomElement.attributes[j].name] = childDomElement.attributes[j].value;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
data.push( childDataElement );
|
|
|
|
data.push( { 'type': branchIsContent ? '/metaInline' : '/metaBlock' } );
|
|
|
|
processNextWhitespace( childDataElement );
|
|
|
|
prevElement = childDataElement;
|
|
|
|
break;
|
|
|
|
}
|
2012-09-05 22:49:56 +00:00
|
|
|
// 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 );
|
2012-09-07 21:58:27 +00:00
|
|
|
processNextWhitespace( alien[0] );
|
|
|
|
prevElement = alien[0];
|
2012-09-05 22:49:56 +00:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2012-06-07 21:16:10 +00:00
|
|
|
// Detect and handle annotated content
|
2012-08-02 18:46:13 +00:00
|
|
|
annotation = this.getDataAnnotationFromDomElement( childDomElement );
|
2012-06-07 00:47:27 +00:00
|
|
|
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 ) {
|
2012-08-16 20:06:18 +00:00
|
|
|
// 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 = {
|
2012-08-16 20:06:18 +00:00
|
|
|
'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 );
|
2012-06-07 00:47:27 +00:00
|
|
|
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;
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
|
|
|
// Append child element data
|
|
|
|
data = data.concat(
|
|
|
|
this.getDataFromDom(
|
2012-08-24 02:06:36 +00:00
|
|
|
childDomElement, annotations.concat( [ annotation ] ), undefined, path, wrapping
|
2012-06-07 00:47:27 +00:00
|
|
|
)
|
|
|
|
);
|
2012-06-07 21:16:10 +00:00
|
|
|
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
|
2012-06-07 21:16:10 +00:00
|
|
|
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;
|
|
|
|
}
|
2012-06-07 21:16:10 +00:00
|
|
|
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;
|
2012-06-07 21:16:10 +00:00
|
|
|
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;
|
2012-06-07 21:16:10 +00:00
|
|
|
}
|
|
|
|
// Append child element data
|
2012-08-02 18:46:13 +00:00
|
|
|
childDataElement = this.getDataElementFromDomElement( childDomElement );
|
2012-06-07 21:16:10 +00:00
|
|
|
if ( childDataElement ) {
|
2012-06-07 00:47:27 +00:00
|
|
|
data = data.concat(
|
|
|
|
this.getDataFromDom(
|
|
|
|
childDomElement,
|
|
|
|
[],
|
|
|
|
childDataElement,
|
2012-06-08 22:16:55 +00:00
|
|
|
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
|
2012-06-07 00:47:27 +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
|
|
|
processNextWhitespace( childDataElement );
|
|
|
|
prevElement = childDataElement;
|
2012-06-07 21:16:10 +00:00
|
|
|
break;
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
2012-06-14 19:18:06 +00:00
|
|
|
// 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 );
|
2012-09-07 21:58:27 +00:00
|
|
|
processNextWhitespace( alien[0] );
|
|
|
|
prevElement = alien[0];
|
2012-06-07 00:47:27 +00:00
|
|
|
break;
|
|
|
|
case Node.TEXT_NODE:
|
2012-08-02 18:46:13 +00:00
|
|
|
text = childDomElement.data;
|
2012-08-03 19:12:09 +00:00
|
|
|
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?!?
|
2012-08-03 19:12:09 +00:00
|
|
|
break;
|
2012-06-15 05:46:04 +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
|
|
|
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 );
|
|
|
|
}
|
Remainder JSHint fixes on modules/ve/*
[jshint]
ce/ve.ce.Surface.js: line 670, col 9, Too many var statements.
ce/ve.ce.Surface.js: line 695, col 6, Missing semicolon.
ce/ve.ce.Surface.js: line 726, col 22, Expected '===' and instead saw '=='.
ce/ve.ce.Surface.js: line 726, col 41, Expected '===' and instead saw '=='.
ce/ve.ce.Surface.js: line 733, col 13, Too many var statements.
ce/ve.ce.Surface.js: line 734, col 24, Expected '===' and instead saw '=='.
ce/ve.ce.Surface.js: line 1013, col 13, Too many var statements.
ce/ve.ce.Surface.js: line 1019, col 17, Too many var statements.
ce/ve.ce.Surface.js: line 1023, col 18, Too many ar statements.
ce/ve.ce.Surface.js: line 1027, col 13, Too many var statements.
dm/annotations/ve.dm.LinkAnnotation.js: line 70, col 52, Insecure '.'.
dm/ve.dm.Converter.js: line 383, col 29, Empty block.
dm/ve.dm.Converter.js: line 423, col 33, Empty block.
Commands:
* jshint .
* ack '(if|else|function|switch|for|while)\('
* Sublime Text 2:
Find(*): (if|else|function|switch|for|while)\(
Replace: $1 (
* ack ' ' -Q # double spaces, except in certain comments
Change-Id: I8e34bf2924bc8688fdf8acef08bbc4f6707e93be
2012-09-02 21:45:01 +00:00
|
|
|
// 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;
|
2012-06-15 05:46:04 +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
|
|
|
// 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] );
|
|
|
|
}
|
Remainder JSHint fixes on modules/ve/*
[jshint]
ce/ve.ce.Surface.js: line 670, col 9, Too many var statements.
ce/ve.ce.Surface.js: line 695, col 6, Missing semicolon.
ce/ve.ce.Surface.js: line 726, col 22, Expected '===' and instead saw '=='.
ce/ve.ce.Surface.js: line 726, col 41, Expected '===' and instead saw '=='.
ce/ve.ce.Surface.js: line 733, col 13, Too many var statements.
ce/ve.ce.Surface.js: line 734, col 24, Expected '===' and instead saw '=='.
ce/ve.ce.Surface.js: line 1013, col 13, Too many var statements.
ce/ve.ce.Surface.js: line 1019, col 17, Too many var statements.
ce/ve.ce.Surface.js: line 1023, col 18, Too many ar statements.
ce/ve.ce.Surface.js: line 1027, col 13, Too many var statements.
dm/annotations/ve.dm.LinkAnnotation.js: line 70, col 52, Insecure '.'.
dm/ve.dm.Converter.js: line 383, col 29, Empty block.
dm/ve.dm.Converter.js: line 423, col 33, Empty block.
Commands:
* jshint .
* ack '(if|else|function|switch|for|while)\('
* Sublime Text 2:
Find(*): (if|else|function|switch|for|while)\(
Replace: $1 (
* ack ' ' -Q # double spaces, except in certain comments
Change-Id: I8e34bf2924bc8688fdf8acef08bbc4f6707e93be
2012-09-02 21:45:01 +00:00
|
|
|
// 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;
|
|
|
|
}
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
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
|
2012-08-16 17:53:33 +00:00
|
|
|
// (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 ) {
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
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] );
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
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
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
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] );
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
2012-08-10 21:09:04 +00:00
|
|
|
text = text.substring( 0,
|
|
|
|
text.length - matches[0].length );
|
|
|
|
}
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
2012-06-12 00:32:28 +00:00
|
|
|
|
2012-06-07 00:47:27 +00:00
|
|
|
// Annotate the text and output it
|
|
|
|
data = data.concat(
|
2012-06-12 00:32:28 +00:00
|
|
|
ve.dm.Converter.getDataContentFromText( text, annotations )
|
2012-06-07 00:47:27 +00:00
|
|
|
);
|
|
|
|
break;
|
|
|
|
case Node.COMMENT_NODE:
|
|
|
|
// TODO: Preserve comments by inserting them into the linear model too
|
2012-08-03 19:12:09 +00:00
|
|
|
// Could use placeholders for this too, although they'd need to be
|
|
|
|
// inline in certain cases
|
2012-06-07 00:47:27 +00:00
|
|
|
break;
|
2012-06-06 17:17:30 +00:00
|
|
|
}
|
|
|
|
}
|
2012-06-07 00:47:27 +00:00
|
|
|
// 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;
|
|
|
|
}
|
2012-06-07 00:47:27 +00:00
|
|
|
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;
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
2012-06-19 21:36:35 +00:00
|
|
|
|
|
|
|
// 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
|
2012-08-02 18:46:13 +00:00
|
|
|
childTypes = ve.dm.nodeFactory.getChildNodeTypes( branchType );
|
2012-07-19 03:40:49 +00:00
|
|
|
if ( branchType !== 'paragraph' && dataElement && data[data.length - 1] === dataElement &&
|
2012-06-19 21:36:35 +00:00
|
|
|
!wrapping && !ve.dm.nodeFactory.canNodeContainContent( branchType ) &&
|
|
|
|
!ve.dm.nodeFactory.isNodeContent( branchType ) &&
|
2012-08-11 08:14:56 +00:00
|
|
|
( childTypes === null || ve.indexOf( 'paragraph', childTypes ) !== -1 )
|
2012-06-19 21:36:35 +00:00
|
|
|
) {
|
2012-08-16 20:06:18 +00:00
|
|
|
data.push( { 'type': 'paragraph', 'internal': { 'generated': 'wrapper' } } );
|
2012-06-19 21:36:35 +00:00
|
|
|
data.push( { 'type': '/paragraph' } );
|
|
|
|
}
|
|
|
|
|
2012-06-07 00:47:27 +00:00
|
|
|
// 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 = '';
|
|
|
|
}
|
2012-06-07 00:47:27 +00:00
|
|
|
}
|
2012-06-19 00:38:42 +00:00
|
|
|
// Don't return an empty document
|
|
|
|
if ( branchType === 'document' && data.length === 0 ) {
|
2012-08-16 20:06:18 +00:00
|
|
|
return [
|
|
|
|
{ 'type': 'paragraph', 'internal': { 'generated': 'wrapper' } },
|
|
|
|
{ 'type': '/paragraph' }
|
|
|
|
];
|
2012-06-19 00:38:42 +00:00
|
|
|
}
|
2012-06-07 00:47:27 +00:00
|
|
|
return data;
|
2012-06-06 17:17:30 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
2012-06-08 04:58:56 +00:00
|
|
|
* Convert linear model data to an HTML DOM
|
2012-06-06 17:17:30 +00:00
|
|
|
*
|
|
|
|
* @method
|
2012-06-08 04:58:56 +00:00
|
|
|
* @param {Array} data Linear model data
|
|
|
|
* @returns {HTMLElement} Wrapper div containing the resulting HTML
|
2012-06-06 17:17:30 +00:00
|
|
|
*/
|
2012-08-07 01:50:44 +00:00
|
|
|
ve.dm.Converter.prototype.getDomFromData = function ( data ) {
|
2012-09-17 13:30:50 +00:00
|
|
|
var text, i, j, annotations, annotation, annotationElement, dataElement, arr,
|
|
|
|
wrapper, childDomElement, pre, ours, theirs, parentDomElement, startClosingAt,
|
2012-09-07 21:58:27 +00:00
|
|
|
isContentNode,
|
2012-08-02 18:46:13 +00:00
|
|
|
container = document.createElement( 'div' ),
|
|
|
|
domElement = container,
|
2012-08-24 02:06:36 +00:00
|
|
|
annotationStack = new ve.AnnotationSet();
|
2012-08-02 18:46:13 +00:00
|
|
|
for ( i = 0; i < data.length; i++ ) {
|
2012-06-08 04:58:56 +00:00
|
|
|
if ( typeof data[i] === 'string' ) {
|
2012-06-07 22:02:25 +00:00
|
|
|
// Text
|
2012-06-08 04:58:56 +00:00
|
|
|
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 )
|
|
|
|
)
|
|
|
|
) {
|
2012-08-24 02:06:36 +00:00
|
|
|
// Annotated text or annotated nodes
|
2012-06-08 04:58:56 +00:00
|
|
|
text = '';
|
|
|
|
while (
|
|
|
|
ve.isArray( data[i] ) ||
|
|
|
|
(
|
|
|
|
data[i].annotations !== undefined &&
|
|
|
|
ve.dm.nodeFactory.isNodeContent( data[i].type )
|
|
|
|
)
|
|
|
|
) {
|
|
|
|
annotations = data[i].annotations || data[i][1];
|
2012-08-24 02:06:36 +00:00
|
|
|
// 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 = '';
|
2012-06-08 04:58:56 +00:00
|
|
|
}
|
2012-08-24 02:06:36 +00:00
|
|
|
// Traverse up
|
|
|
|
domElement = domElement.parentNode;
|
|
|
|
// Remove from annotationStack
|
|
|
|
annotationStack.removeAt( j );
|
2012-06-08 04:58:56 +00:00
|
|
|
}
|
|
|
|
}
|
2012-08-24 02:06:36 +00:00
|
|
|
|
|
|
|
// Open annotations as needed
|
|
|
|
arr = annotations.get();
|
|
|
|
for ( j = 0; j < arr.length; j++ ) {
|
|
|
|
annotation = arr[j];
|
|
|
|
if ( !annotationStack.contains( annotation ) ) {
|
2012-06-08 04:58:56 +00:00
|
|
|
// Add text if needed
|
|
|
|
if ( text.length > 0 ) {
|
|
|
|
domElement.appendChild( document.createTextNode( text ) );
|
|
|
|
text = '';
|
|
|
|
}
|
2012-08-24 02:06:36 +00:00
|
|
|
// Create new node and descend into it
|
|
|
|
annotationElement = this.getDomElementFromDataAnnotation( annotation );
|
2012-06-08 04:58:56 +00:00
|
|
|
domElement.appendChild( annotationElement );
|
|
|
|
domElement = annotationElement;
|
2012-08-24 02:06:36 +00:00
|
|
|
// Add to annotationStack
|
|
|
|
annotationStack.push( annotation );
|
2012-06-08 04:58:56 +00:00
|
|
|
}
|
|
|
|
}
|
2012-08-24 02:06:36 +00:00
|
|
|
|
2012-06-08 04:58:56 +00:00
|
|
|
if ( data[i].annotations === undefined ) {
|
2012-08-24 02:06:36 +00:00
|
|
|
// Annotated text
|
2012-06-08 04:58:56 +00:00
|
|
|
text += data[i][0];
|
|
|
|
} else {
|
2012-08-24 02:06:36 +00:00
|
|
|
// Annotated node
|
2012-06-08 04:58:56 +00:00
|
|
|
// 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
|
2012-08-24 02:06:36 +00:00
|
|
|
for ( j = annotationStack.getLength() - 1; j >= 0; j-- ) {
|
|
|
|
// Traverse up
|
2012-06-08 04:58:56 +00:00
|
|
|
domElement = domElement.parentNode;
|
|
|
|
}
|
2012-08-24 02:06:36 +00:00
|
|
|
// Clear annotationStack
|
|
|
|
annotationStack = new ve.AnnotationSet();
|
2012-06-08 04:58:56 +00:00
|
|
|
} else if ( data[i].type !== undefined ) {
|
2012-08-02 18:46:13 +00:00
|
|
|
dataElement = data[i];
|
2012-06-07 22:02:25 +00:00
|
|
|
// Element
|
2012-09-07 21:58:27 +00:00
|
|
|
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;
|
2012-09-07 21:58:27 +00:00
|
|
|
isContentNode = ve.dm.nodeFactory.isNodeContent( data[i].type.substr( 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
|
|
|
// Process whitespace
|
2012-08-16 17:53:33 +00:00
|
|
|
// whitespace = [ outerPre, innerPre, innerPost, outerPost ]
|
2012-09-07 21:58:27 +00:00
|
|
|
if (
|
|
|
|
!isContentNode &&
|
|
|
|
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.
|
2012-08-16 17:53:33 +00:00
|
|
|
pre = domElement.veInternal.whitespace[1];
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
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
|
|
|
|
) {
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
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
|
|
|
|
) {
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
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 );
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
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 )
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
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] || '';
|
2012-09-07 21:58:27 +00:00
|
|
|
} else if ( !isContentNode ) {
|
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
|
|
|
// Use empty string, because undefined means there were no
|
|
|
|
// structural children
|
|
|
|
parentDomElement.lastOuterPost = '';
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
2012-08-10 21:09:04 +00:00
|
|
|
}
|
2012-09-07 21:58:27 +00:00
|
|
|
// else don't touch lastOuterPost
|
2012-08-16 20:06:18 +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' ) {
|
2012-08-20 20:13:07 +00:00
|
|
|
while ( domElement.firstChild ) {
|
2012-08-16 20:06:18 +00:00
|
|
|
parentDomElement.insertBefore(
|
2012-08-20 20:13:07 +00:00
|
|
|
domElement.firstChild,
|
2012-08-16 20:06:18 +00:00
|
|
|
domElement
|
|
|
|
);
|
|
|
|
}
|
|
|
|
parentDomElement.removeChild( domElement );
|
|
|
|
}
|
|
|
|
|
2012-08-16 17:53:33 +00:00
|
|
|
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;
|
2012-06-08 04:58:56 +00:00
|
|
|
// Ascend to parent node
|
2012-08-16 20:06:18 +00:00
|
|
|
domElement = parentDomElement;
|
2012-06-08 04:58:56 +00:00
|
|
|
} else {
|
2012-09-07 21:58:27 +00:00
|
|
|
if ( dataElement.type === 'alienBlock' || dataElement.type === 'alienInline' ) {
|
|
|
|
// Create nodes from source
|
|
|
|
wrapper = document.createElement( 'div' );
|
|
|
|
wrapper.innerHTML = dataElement.attributes.html;
|
|
|
|
// Add element - adds first child element, any other
|
|
|
|
// children are ignored but shouldn't exist
|
|
|
|
//parentDomElement = domElement;
|
|
|
|
childDomElement = wrapper.firstChild;
|
|
|
|
//parentDomElement.appendChild( domElement );
|
|
|
|
// Make sure the alien closing is skipped
|
|
|
|
//parentDomElement = domElement; domElement = wrapper; //i++;
|
|
|
|
} else {
|
|
|
|
// Create node from data
|
|
|
|
childDomElement = this.getDomElementFromDataElement( dataElement );
|
|
|
|
}
|
2012-08-16 20:06:18 +00:00
|
|
|
// Add reference to internal data
|
2012-08-16 17:53:33 +00:00
|
|
|
if ( dataElement.internal ) {
|
|
|
|
childDomElement.veInternal = dataElement.internal;
|
Strip and preserve inner leading&trailing whitespace in the linear model
This makes things like
== Foo ==
* Bar
render without the leading and trailing spaces, while still
round-tripping those spaces.
* Added a .fringeWhitespace property to the linear model and ve.dm.Node
** Object containing innerPre, innerPost, outerPre, outerPost
** Only inner* are used right now, outer* are planned for future use
** Like .attributes , it's suppressed if it's an empty object
* In getDataFromDom():
** Store the stripped whitespace in .fringeWhitespace
** Move emptiness check up: empty elements with .fringeWhitespace have
to be preserved
** Move paragraph wrapping up: .fringeWhitespace has to be applied to
the generated paragraph, not its parent
** Add wrapperElement to keep track of the element .fringeWhitespace has
to be added to; this is either dataElement or the generated paragraph
or nothing, but we can't modify dataElement because it's used later
* In getDomFromData():
** When processing an opening, store the fringeWhitespace data in the
generated DOM node
** When processing a closing, add the stored whitespace back in
* In the ve.dm.Document constructor, pass through .fringeWhitespace from
the linear model data to the generated nodes
Tests:
* Change one existing test case to account for this change
* Add three new test cases for this behavior
* Add normalizedHtml field so I can test behavior with bare content
Change-Id: I0411544652dd72b923c831c495d69ee4322a2c14
2012-08-10 21:09:04 +00:00
|
|
|
}
|
2012-06-08 04:58:56 +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;
|
2012-06-08 04:58:56 +00:00
|
|
|
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
|
|
|
|
);
|
|
|
|
}
|
|
|
|
}
|
2012-06-08 04:58:56 +00:00
|
|
|
}
|
2012-06-07 22:02:25 +00:00
|
|
|
}
|
2012-06-07 00:47:27 +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
|
|
|
// 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;
|
|
|
|
}
|
2012-06-08 04:58:56 +00:00
|
|
|
return container;
|
2012-06-06 17:17:30 +00:00
|
|
|
};
|
|
|
|
|
2012-05-31 23:50:16 +00:00
|
|
|
/* Initialization */
|
|
|
|
|
|
|
|
ve.dm.converter = new ve.dm.Converter( ve.dm.nodeFactory, ve.dm.annotationFactory );
|