This repository has been archived by the owner on Jun 26, 2020. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 18
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #30 from ckeditor/t/29
Internal: Moved parsing and spacing normalization functions to separate files. Closes #29.
- Loading branch information
Showing
5 changed files
with
131 additions
and
55 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,55 @@ | ||
/** | ||
* @license Copyright (c) 2003-2018, CKSource - Frederico Knabben. All rights reserved. | ||
* For licensing, see LICENSE.md. | ||
*/ | ||
|
||
/** | ||
* @module paste-from-office/filters/space | ||
*/ | ||
|
||
/** | ||
* Replaces last space preceding elements closing tag with ` `. Such operation prevents spaces from being removed | ||
* during further DOM/View processing (see especially {@link module:engine/view/domconverter~DomConverter#_processDataFromDomText}). | ||
* This method also takes into account Word specific `<o:p></o:p>` empty tags. | ||
* | ||
* @param {String} htmlString HTML string in which spacing should be normalized. | ||
* @returns {String} Input HTML with spaces normalized. | ||
*/ | ||
export function normalizeSpacing( htmlString ) { | ||
return normalizeSafariSpaceSpans( normalizeSafariSpaceSpans( htmlString ) ) // Run normalization two times to cover nested spans. | ||
.replace( / <\//g, '\u00A0</' ) | ||
.replace( / <o:p><\/o:p>/g, '\u00A0<o:p></o:p>' ); | ||
} | ||
|
||
/** | ||
* Normalizes spacing in special Word `spacerun spans` (`<span style='mso-spacerun:yes'>\s+</span>`) by replacing | ||
* all spaces with ` ` pairs. This prevents spaces from being removed during further DOM/View processing | ||
* (see especially {@link module:engine/view/domconverter~DomConverter#_processDataFromDomText}). | ||
* | ||
* @param {Document} htmlDocument Native `Document` object in which spacing should be normalized. | ||
*/ | ||
export function normalizeSpacerunSpans( htmlDocument ) { | ||
htmlDocument.querySelectorAll( 'span[style*=spacerun]' ).forEach( el => { | ||
// Use `el.childNodes[ 0 ].data.length` instead of `el.innerText.length`. For `el.innerText.length` which | ||
// contains spaces mixed with ` ` Edge browser returns incorrect length. | ||
const innerTextLength = el.childNodes[ 0 ].data.length; | ||
|
||
el.innerHTML = Array( innerTextLength + 1 ).join( '\u00A0 ' ).substr( 0, innerTextLength ); | ||
} ); | ||
} | ||
|
||
// Normalizes specific spacing generated by Safari when content pasted from Word (`<span class="Apple-converted-space"> </span>`) | ||
// by replacing all spaces sequences longer than 1 space with ` ` pairs. This prevents spaces from being removed during | ||
// further DOM/View processing (see especially {@link module:engine/view/domconverter~DomConverter#_processDataFromDomText}). | ||
// | ||
// This function is similar to {@link module:clipboard/utils/normalizeclipboarddata normalizeClipboardData util} but uses | ||
// regular spaces / sequence for replacement. | ||
// | ||
// @param {String} htmlString HTML string in which spacing should be normalized | ||
// @returns {String} Input HTML with spaces normalized. | ||
function normalizeSafariSpaceSpans( htmlString ) { | ||
return htmlString.replace( /<span(?: class="Apple-converted-space"|)>(\s+)<\/span>/g, ( fullMatch, spaces ) => { | ||
return spaces.length === 1 ? ' ' : Array( spaces.length + 1 ).join( '\u00A0 ' ).substr( 0, spaces.length ); | ||
} ); | ||
} | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,61 @@ | ||
/** | ||
* @license Copyright (c) 2003-2018, CKSource - Frederico Knabben. All rights reserved. | ||
* For licensing, see LICENSE.md. | ||
*/ | ||
|
||
/* globals DOMParser */ | ||
|
||
import { normalizeSpacing, normalizeSpacerunSpans } from '../../src/filters/space'; | ||
|
||
describe( 'Filters', () => { | ||
describe( 'space', () => { | ||
describe( 'normalizeSpacing', () => { | ||
it( 'should replace last space before closing tag with NBSP', () => { | ||
const input = '<p>Foo </p><p><span> Bar </span> Baz </p>'; | ||
const expected = '<p>Foo\u00A0</p><p><span> Bar \u00A0</span> Baz\u00A0</p>'; | ||
|
||
expect( normalizeSpacing( input ) ).to.equal( expected ); | ||
} ); | ||
|
||
it( 'should replace last space before special "o:p" tag with NBSP', () => { | ||
const input = '<p>Foo <o:p></o:p><span> <o:p></o:p> Bar</span></p>'; | ||
const expected = '<p>Foo \u00A0<o:p></o:p><span>\u00A0<o:p></o:p> Bar</span></p>'; | ||
|
||
expect( normalizeSpacing( input ) ).to.equal( expected ); | ||
} ); | ||
|
||
it( 'should normalize Safari "space spans"', () => { | ||
const input = '<p>Foo <span class="Apple-converted-space"> </span> Baz <span> </span></p>'; | ||
const expected = '<p>Foo \u00A0 \u00A0 Baz \u00A0\u00A0</p>'; | ||
|
||
expect( normalizeSpacing( input ) ).to.equal( expected ); | ||
} ); | ||
|
||
it( 'should normalize nested Safari "space spans"', () => { | ||
const input = '<p> Foo <span class="Apple-converted-space"> <span class="Apple-converted-space"> </span></span> Baz</p>'; | ||
const expected = '<p> Foo \u00A0 \u00A0 \u00A0 Baz</p>'; | ||
|
||
expect( normalizeSpacing( input ) ).to.equal( expected ); | ||
} ); | ||
} ); | ||
|
||
describe( 'normalizeSpacerunSpans', () => { | ||
it( 'should normalize spaces inside special "span.spacerun" elements', () => { | ||
const input = '<p> <span style=\'mso-spacerun:yes\'> </span>Foo</p>' + | ||
'<p> Baz <span style=\'mso-spacerun:yes\'> </span></p>'; | ||
|
||
const expected = '<p> <span style="mso-spacerun:yes"> </span>Foo</p>' + | ||
'<p> Baz <span style="mso-spacerun:yes"> </span></p>'; | ||
|
||
const domParser = new DOMParser(); | ||
const htmlDocument = domParser.parseFromString( input, 'text/html' ); | ||
|
||
expect( htmlDocument.body.innerHTML.replace( /'/g, '"' ).replace( /: /g, ':' ) ).to.not.equal( expected ); | ||
|
||
normalizeSpacerunSpans( htmlDocument ); | ||
|
||
expect( htmlDocument.body.innerHTML.replace( /'/g, '"' ).replace( /: /g, ':' ) ).to.equal( expected ); | ||
} ); | ||
} ); | ||
} ); | ||
} ); |