mirror of
https://github.com/ether/etherpad-lite.git
synced 2025-04-25 09:56:15 -04:00
Merge branch 'develop' of github.com:ether/etherpad-lite into mochawesome
This commit is contained in:
commit
7696ec0a02
7 changed files with 333 additions and 356 deletions
|
@ -421,7 +421,20 @@ Things in context:
|
|||
4. text - the text for that line
|
||||
|
||||
This hook allows you to validate/manipulate the text before it's sent to the
|
||||
server side. The return value should be the validated/manipulated text.
|
||||
server side. To change the text, either:
|
||||
|
||||
* Set the `text` context property to the desired value and return `undefined`.
|
||||
* (Deprecated) Return a string. If a hook function changes the `text` context
|
||||
property, the return value is ignored. If no hook function changes `text` but
|
||||
multiple hook functions return a string, the first one wins.
|
||||
|
||||
Example:
|
||||
|
||||
```
|
||||
exports.collectContentLineText = (hookName, context) => {
|
||||
context.text = tweakText(context.text);
|
||||
};
|
||||
```
|
||||
|
||||
## collectContentLineBreak
|
||||
|
||||
|
|
|
@ -391,9 +391,9 @@ const defaultResponseRefs = {
|
|||
|
||||
// convert to a dictionary of operation objects
|
||||
const operations = {};
|
||||
for (const resource in resources) {
|
||||
for (const action in resources[resource]) {
|
||||
const {operationId, responseSchema, ...operation} = resources[resource][action];
|
||||
for (const [resource, actions] of Object.entries(resources)) {
|
||||
for (const [action, spec] of Object.entries(actions)) {
|
||||
const {operationId, responseSchema, ...operation} = spec;
|
||||
|
||||
// add response objects
|
||||
const responses = {...defaultResponseRefs};
|
||||
|
@ -623,7 +623,7 @@ exports.expressCreateServer = (hookName, args, cb) => {
|
|||
} else {
|
||||
// an unknown error happened
|
||||
// log it and throw internal error
|
||||
apiLogger.error(err);
|
||||
apiLogger.error(err.stack || err.toString());
|
||||
throw new createHTTPError.InternalError('internal error');
|
||||
}
|
||||
});
|
||||
|
|
|
@ -1139,7 +1139,7 @@ function Ace2Inner() {
|
|||
|
||||
lastDirtyNode = (lastDirtyNode && isNodeDirty(lastDirtyNode) && lastDirtyNode);
|
||||
if (firstDirtyNode && lastDirtyNode) {
|
||||
const cc = makeContentCollector(isStyled, browser, rep.apool, null, className2Author);
|
||||
const cc = makeContentCollector(isStyled, browser, rep.apool, className2Author);
|
||||
cc.notifySelection(selection);
|
||||
const dirtyNodes = [];
|
||||
for (let n = firstDirtyNode; n &&
|
||||
|
|
|
@ -32,30 +32,31 @@ const hooks = require('./pluginfw/hooks');
|
|||
|
||||
const sanitizeUnicode = (s) => UNorm.nfc(s);
|
||||
|
||||
const makeContentCollector = (collectStyles, abrowser, apool, domInterface, className2Author) => {
|
||||
const dom = domInterface || {
|
||||
isNodeText: (n) => n.nodeType === 3,
|
||||
nodeTagName: (n) => n.tagName,
|
||||
nodeValue: (n) => n.nodeValue,
|
||||
nodeNumChildren: (n) => {
|
||||
if (n.childNodes == null) return 0;
|
||||
return n.childNodes.length;
|
||||
},
|
||||
nodeChild: (n, i) => {
|
||||
if (n.childNodes.item == null) {
|
||||
return n.childNodes[i];
|
||||
}
|
||||
return n.childNodes.item(i);
|
||||
},
|
||||
nodeProp: (n, p) => n[p],
|
||||
nodeAttr: (n, a) => {
|
||||
if (n.getAttribute != null) return n.getAttribute(a);
|
||||
if (n.attribs != null) return n.attribs[a];
|
||||
return null;
|
||||
},
|
||||
optNodeInnerHTML: (n) => n.innerHTML,
|
||||
};
|
||||
// This file is used both in browsers and with cheerio in Node.js (for importing HTML). Cheerio's
|
||||
// Node-like objects are not 100% API compatible with the DOM specification; the following functions
|
||||
// abstract away the differences.
|
||||
|
||||
// .nodeType works with DOM and cheerio 0.22.0, but cheerio 0.22.0 does not provide the Node.*_NODE
|
||||
// constants so they cannot be used here.
|
||||
const isElementNode = (n) => n.nodeType === 1; // Node.ELEMENT_NODE
|
||||
const isTextNode = (n) => n.nodeType === 3; // Node.TEXT_NODE
|
||||
// .tagName works with DOM and cheerio 0.22.0, but:
|
||||
// * With DOM, .tagName is an uppercase string.
|
||||
// * With cheerio 0.22.0, .tagName is a lowercase string.
|
||||
// For consistency, this function always returns a lowercase string.
|
||||
const tagName = (n) => n.tagName && n.tagName.toLowerCase();
|
||||
// .childNodes works with DOM and cheerio 0.22.0, except in cheerio the .childNodes property does
|
||||
// not exist on text nodes (and maybe other non-element nodes).
|
||||
const childNodes = (n) => n.childNodes || [];
|
||||
const getAttribute = (n, a) => {
|
||||
// .getAttribute() works with DOM but not with cheerio 0.22.0.
|
||||
if (n.getAttribute != null) return n.getAttribute(a);
|
||||
// .attribs[] works with cheerio 0.22.0 but not with DOM.
|
||||
if (n.attribs != null) return n.attribs[a];
|
||||
return null;
|
||||
};
|
||||
|
||||
const makeContentCollector = (collectStyles, abrowser, apool, className2Author) => {
|
||||
const _blockElems = {
|
||||
div: 1,
|
||||
p: 1,
|
||||
|
@ -67,7 +68,7 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
_blockElems[element] = 1;
|
||||
});
|
||||
|
||||
const isBlockElement = (n) => !!_blockElems[(dom.nodeTagName(n) || '').toLowerCase()];
|
||||
const isBlockElement = (n) => !!_blockElems[tagName(n) || ''];
|
||||
|
||||
const textify = (str) => sanitizeUnicode(
|
||||
str.replace(/(\n | \n)/g, ' ')
|
||||
|
@ -75,7 +76,7 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
.replace(/\xa0/g, ' ')
|
||||
.replace(/\t/g, ' '));
|
||||
|
||||
const getAssoc = (node, name) => dom.nodeProp(node, `_magicdom_${name}`);
|
||||
const getAssoc = (node, name) => node[`_magicdom_${name}`];
|
||||
|
||||
const lines = (() => {
|
||||
const textArray = [];
|
||||
|
@ -123,13 +124,17 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
let selEnd = [-1, -1];
|
||||
const _isEmpty = (node, state) => {
|
||||
// consider clean blank lines pasted in IE to be empty
|
||||
if (dom.nodeNumChildren(node) === 0) return true;
|
||||
if (dom.nodeNumChildren(node) === 1 &&
|
||||
if (childNodes(node).length === 0) return true;
|
||||
if (childNodes(node).length === 1 &&
|
||||
getAssoc(node, 'shouldBeEmpty') &&
|
||||
dom.optNodeInnerHTML(node) === ' ' &&
|
||||
// Note: The .innerHTML property exists on DOM Element objects but not on cheerio's
|
||||
// Element-like objects (cheerio v0.22.0) so this equality check will always be false.
|
||||
// Cheerio's Element-like objects have no equivalent to .innerHTML. (Cheerio objects have an
|
||||
// .html() method, but that isn't accessible here.)
|
||||
node.innerHTML === ' ' &&
|
||||
!getAssoc(node, 'unpasted')) {
|
||||
if (state) {
|
||||
const child = dom.nodeChild(node, 0);
|
||||
const child = childNodes(node)[0];
|
||||
_reachPoint(child, 0, state);
|
||||
_reachPoint(child, 1, state);
|
||||
}
|
||||
|
@ -149,7 +154,7 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
};
|
||||
|
||||
const _reachBlockPoint = (nd, idx, state) => {
|
||||
if (!dom.isNodeText(nd)) _reachPoint(nd, idx, state);
|
||||
if (!isTextNode(nd)) _reachPoint(nd, idx, state);
|
||||
};
|
||||
|
||||
const _reachPoint = (nd, idx, state) => {
|
||||
|
@ -228,25 +233,24 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
|
||||
const _recalcAttribString = (state) => {
|
||||
const lst = [];
|
||||
for (const a in state.attribs) {
|
||||
if (state.attribs[a]) {
|
||||
// The following splitting of the attribute name is a workaround
|
||||
// to enable the content collector to store key-value attributes
|
||||
// see https://github.com/ether/etherpad-lite/issues/2567 for more information
|
||||
// in long term the contentcollector should be refactored to get rid of this workaround
|
||||
const ATTRIBUTE_SPLIT_STRING = '::';
|
||||
for (const [a, count] of Object.entries(state.attribs)) {
|
||||
if (!count) continue;
|
||||
// The following splitting of the attribute name is a workaround
|
||||
// to enable the content collector to store key-value attributes
|
||||
// see https://github.com/ether/etherpad-lite/issues/2567 for more information
|
||||
// in long term the contentcollector should be refactored to get rid of this workaround
|
||||
const ATTRIBUTE_SPLIT_STRING = '::';
|
||||
|
||||
// see if attributeString is splittable
|
||||
const attributeSplits = a.split(ATTRIBUTE_SPLIT_STRING);
|
||||
if (attributeSplits.length > 1) {
|
||||
// the attribute name follows the convention key::value
|
||||
// so save it as a key value attribute
|
||||
lst.push([attributeSplits[0], attributeSplits[1]]);
|
||||
} else {
|
||||
// the "normal" case, the attribute is just a switch
|
||||
// so set it true
|
||||
lst.push([a, 'true']);
|
||||
}
|
||||
// see if attributeString is splittable
|
||||
const attributeSplits = a.split(ATTRIBUTE_SPLIT_STRING);
|
||||
if (attributeSplits.length > 1) {
|
||||
// the attribute name follows the convention key::value
|
||||
// so save it as a key value attribute
|
||||
lst.push([attributeSplits[0], attributeSplits[1]]);
|
||||
} else {
|
||||
// the "normal" case, the attribute is just a switch
|
||||
// so set it true
|
||||
lst.push([a, 'true']);
|
||||
}
|
||||
}
|
||||
if (state.authorLevel > 0) {
|
||||
|
@ -316,25 +320,15 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
const startLine = lines.length() - 1;
|
||||
_reachBlockPoint(node, 0, state);
|
||||
|
||||
if (dom.isNodeText(node)) {
|
||||
let txt = dom.nodeValue(node);
|
||||
const tname = dom.nodeAttr(node.parentNode, 'name');
|
||||
|
||||
const txtFromHook = hooks.callAll('collectContentLineText', {
|
||||
cc: this,
|
||||
state,
|
||||
tname,
|
||||
node,
|
||||
text: txt,
|
||||
styl: null,
|
||||
cls: null,
|
||||
});
|
||||
|
||||
if (typeof (txtFromHook) === 'object') {
|
||||
txt = dom.nodeValue(node);
|
||||
} else if (txtFromHook) {
|
||||
txt = txtFromHook;
|
||||
}
|
||||
if (isTextNode(node)) {
|
||||
const tname = getAttribute(node.parentNode, 'name');
|
||||
const context = {cc: this, state, tname, node, text: node.nodeValue};
|
||||
// Hook functions may either return a string (deprecated) or modify context.text. If any hook
|
||||
// function modifies context.text then all returned strings are ignored. If no hook functions
|
||||
// modify context.text, the first hook function to return a string wins.
|
||||
const [hookTxt] =
|
||||
hooks.callAll('collectContentLineText', context).filter((s) => typeof s === 'string');
|
||||
let txt = context.text === node.nodeValue && hookTxt != null ? hookTxt : context.text;
|
||||
|
||||
let rest = '';
|
||||
let x = 0; // offset into original text
|
||||
|
@ -384,8 +378,8 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
cc.startNewLine(state);
|
||||
}
|
||||
}
|
||||
} else {
|
||||
const tname = (dom.nodeTagName(node) || '').toLowerCase();
|
||||
} else if (isElementNode(node)) {
|
||||
const tname = tagName(node) || '';
|
||||
|
||||
if (tname === 'img') {
|
||||
hooks.callAll('collectContentImage', {
|
||||
|
@ -403,8 +397,8 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
|
||||
if (tname === 'br') {
|
||||
this.breakLine = true;
|
||||
const tvalue = dom.nodeAttr(node, 'value');
|
||||
const induceLineBreak = hooks.callAll('collectContentLineBreak', {
|
||||
const tvalue = getAttribute(node, 'value');
|
||||
const [startNewLine = true] = hooks.callAll('collectContentLineBreak', {
|
||||
cc: this,
|
||||
state,
|
||||
tname,
|
||||
|
@ -412,17 +406,14 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
styl: null,
|
||||
cls: null,
|
||||
});
|
||||
const startNewLine = (
|
||||
typeof (induceLineBreak) === 'object' &&
|
||||
induceLineBreak.length === 0) ? true : induceLineBreak[0];
|
||||
if (startNewLine) {
|
||||
cc.startNewLine(state);
|
||||
}
|
||||
} else if (tname === 'script' || tname === 'style') {
|
||||
// ignore
|
||||
} else if (!isEmpty) {
|
||||
let styl = dom.nodeAttr(node, 'style');
|
||||
let cls = dom.nodeAttr(node, 'class');
|
||||
let styl = getAttribute(node, 'style');
|
||||
let cls = getAttribute(node, 'class');
|
||||
let isPre = (tname === 'pre');
|
||||
if ((!isPre) && abrowser && abrowser.safari) {
|
||||
isPre = (styl && /\bwhite-space:\s*pre\b/i.exec(styl));
|
||||
|
@ -469,26 +460,23 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
cc.doAttrib(state, 'strikethrough');
|
||||
}
|
||||
if (tname === 'ul' || tname === 'ol') {
|
||||
let type = node.attribs ? node.attribs.class : null;
|
||||
let type = getAttribute(node, 'class');
|
||||
const rr = cls && /(?:^| )list-([a-z]+[0-9]+)\b/.exec(cls);
|
||||
// lists do not need to have a type, so before we make a wrong guess
|
||||
// check if we find a better hint within the node's children
|
||||
if (!rr && !type) {
|
||||
for (const i in node.children) {
|
||||
if (node.children[i] && node.children[i].name === 'ul') {
|
||||
type = node.children[i].attribs.class;
|
||||
if (type) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
for (const child of childNodes(node)) {
|
||||
if (tagName(child) !== 'ul') continue;
|
||||
type = getAttribute(child, 'class');
|
||||
if (type) break;
|
||||
}
|
||||
}
|
||||
if (rr && rr[1]) {
|
||||
type = rr[1];
|
||||
} else {
|
||||
if (tname === 'ul') {
|
||||
if ((type && type.match('indent')) ||
|
||||
(node.attribs && node.attribs.class && node.attribs.class.match('indent'))) {
|
||||
const cls = getAttribute(node, 'class');
|
||||
if ((type && type.match('indent')) || (cls && cls.match('indent'))) {
|
||||
type = 'indent';
|
||||
} else {
|
||||
type = 'bullet';
|
||||
|
@ -503,7 +491,7 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
// This has undesirable behavior in Chrome but is right in other browsers.
|
||||
// See https://github.com/ether/etherpad-lite/issues/2412 for reasoning
|
||||
if (!abrowser.chrome) oldListTypeOrNull = (_enterList(state, undefined) || 'none');
|
||||
} else if ((tname === 'li')) {
|
||||
} else if (tname === 'li') {
|
||||
state.lineAttributes.start = state.start || 0;
|
||||
_recalcAttribString(state);
|
||||
if (state.lineAttributes.list.indexOf('number') !== -1) {
|
||||
|
@ -513,7 +501,7 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
Note how the <ol> item has to be inside a <li>
|
||||
Because of this we don't increment the start number
|
||||
*/
|
||||
if (node.parent && node.parent.name !== 'ol') {
|
||||
if (node.parentNode && tagName(node.parentNode) !== 'ol') {
|
||||
/*
|
||||
TODO: start number has to increment based on indentLevel(numberX)
|
||||
This means we have to build an object IE
|
||||
|
@ -530,7 +518,7 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
}
|
||||
}
|
||||
// UL list items never modify the start value.
|
||||
if (node.parent && node.parent.name === 'ul') {
|
||||
if (node.parentNode && tagName(node.parentNode) === 'ul') {
|
||||
state.start++;
|
||||
// TODO, this is hacky.
|
||||
// Because if the first item is an UL it will increment a list no?
|
||||
|
@ -559,9 +547,7 @@ const makeContentCollector = (collectStyles, abrowser, apool, domInterface, clas
|
|||
}
|
||||
}
|
||||
|
||||
const nc = dom.nodeNumChildren(node);
|
||||
for (let i = 0; i < nc; i++) {
|
||||
const c = dom.nodeChild(node, i);
|
||||
for (const c of childNodes(node)) {
|
||||
cc.collectContent(c, state);
|
||||
}
|
||||
|
||||
|
|
|
@ -1,3 +1,5 @@
|
|||
'use strict';
|
||||
|
||||
/*
|
||||
* This file is copied & modified from <basedir>/tests/backend/specs/api/pad.js
|
||||
*
|
||||
|
|
|
@ -6,151 +6,148 @@
|
|||
* TODO: unify those two files, and merge in a single one.
|
||||
*/
|
||||
|
||||
/* eslint-disable max-len */
|
||||
|
||||
const common = require('../../common');
|
||||
const supertest = require(`${__dirname}/../../../../src/node_modules/supertest`);
|
||||
const settings = require(`${__dirname}/../../../../tests/container/loadSettings.js`).loadSettings();
|
||||
const api = supertest(`http://${settings.ip}:${settings.port}`);
|
||||
const settings = require('../../../container/loadSettings.js').loadSettings();
|
||||
const supertest = require('ep_etherpad-lite/node_modules/supertest');
|
||||
|
||||
const api = supertest(`http://${settings.ip}:${settings.port}`);
|
||||
const apiKey = common.apiKey;
|
||||
const apiVersion = 1;
|
||||
|
||||
const testImports = {
|
||||
'malformed': {
|
||||
input: '<html><body><li>wtf</ul></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>wtf<br><br></body></html>',
|
||||
expectedText: 'wtf\n\n',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>wtf<br><br></body></html>',
|
||||
wantText: 'wtf\n\n',
|
||||
disabled: true,
|
||||
},
|
||||
'nonelistiteminlist #3620': {
|
||||
input: '<html><body><ul>test<li>FOO</li></ul></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body><ul class="bullet">test<li>FOO</ul><br></body></html>',
|
||||
expectedText: '\ttest\n\t* FOO\n\n',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body><ul class="bullet">test<li>FOO</ul><br></body></html>',
|
||||
wantText: '\ttest\n\t* FOO\n\n',
|
||||
disabled: true,
|
||||
},
|
||||
'whitespaceinlist #3620': {
|
||||
input: '<html><body><ul> <li>FOO</li></ul></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body><ul class="bullet"><li>FOO</ul><br></body></html>',
|
||||
expectedText: '\t* FOO\n\n',
|
||||
disabled: true,
|
||||
wantHTML: '<!DOCTYPE HTML><html><body><ul class="bullet"><li>FOO</ul><br></body></html>',
|
||||
wantText: '\t* FOO\n\n',
|
||||
},
|
||||
'prefixcorrectlinenumber': {
|
||||
input: '<html><body><ol><li>should be 1</li><li>should be 2</li></ol></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body><ol start="1" class="number"><li>should be 1</li><li>should be 2</ol><br></body></html>',
|
||||
expectedText: '\t1. should be 1\n\t2. should be 2\n\n',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body><ol start="1" class="number"><li>should be 1</li><li>should be 2</ol><br></body></html>',
|
||||
wantText: '\t1. should be 1\n\t2. should be 2\n\n',
|
||||
},
|
||||
'prefixcorrectlinenumbernested': {
|
||||
input: '<html><body><ol><li>should be 1</li><ol><li>foo</li></ol><li>should be 2</li></ol></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body><ol start="1" class="number"><li>should be 1<ol start="2" class="number"><li>foo</ol><li>should be 2</ol><br></body></html>',
|
||||
expectedText: '\t1. should be 1\n\t\t1.1. foo\n\t2. should be 2\n\n',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body><ol start="1" class="number"><li>should be 1<ol start="2" class="number"><li>foo</ol><li>should be 2</ol><br></body></html>',
|
||||
wantText: '\t1. should be 1\n\t\t1.1. foo\n\t2. should be 2\n\n',
|
||||
},
|
||||
|
||||
/*
|
||||
"prefixcorrectlinenumber when introduced none list item - currently not supported see #3450":{
|
||||
"prefixcorrectlinenumber when introduced none list item - currently not supported see #3450": {
|
||||
input: '<html><body><ol><li>should be 1</li>test<li>should be 2</li></ol></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body><ol start="1" class="number"><li>should be 1</li>test<li>should be 2</li></ol><br></body></html>',
|
||||
expectedText: '\t1. should be 1\n\ttest\n\t2. should be 2\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body><ol start="1" class="number"><li>should be 1</li>test<li>should be 2</li></ol><br></body></html>',
|
||||
wantText: '\t1. should be 1\n\ttest\n\t2. should be 2\n\n',
|
||||
}
|
||||
,
|
||||
"newlinesshouldntresetlinenumber #2194":{
|
||||
"newlinesshouldntresetlinenumber #2194": {
|
||||
input: '<html><body><ol><li>should be 1</li>test<li>should be 2</li></ol></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body><ol class="number"><li>should be 1</li>test<li>should be 2</li></ol><br></body></html>',
|
||||
expectedText: '\t1. should be 1\n\ttest\n\t2. should be 2\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body><ol class="number"><li>should be 1</li>test<li>should be 2</li></ol><br></body></html>',
|
||||
wantText: '\t1. should be 1\n\ttest\n\t2. should be 2\n\n',
|
||||
}
|
||||
*/
|
||||
'ignoreAnyTagsOutsideBody': {
|
||||
description: 'Content outside body should be ignored',
|
||||
input: '<html><head><title>title</title><style></style></head><body>empty<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>empty<br><br></body></html>',
|
||||
expectedText: 'empty\n\n',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>empty<br><br></body></html>',
|
||||
wantText: 'empty\n\n',
|
||||
},
|
||||
'indentedListsAreNotBullets': {
|
||||
description: 'Indented lists are represented with tabs and without bullets',
|
||||
input: '<html><body><ul class="indent"><li>indent</li><li>indent</ul></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body><ul class="indent"><li>indent</li><li>indent</ul><br></body></html>',
|
||||
expectedText: '\tindent\n\tindent\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body><ul class="indent"><li>indent</li><li>indent</ul><br></body></html>',
|
||||
wantText: '\tindent\n\tindent\n\n',
|
||||
},
|
||||
lineWithMultipleSpaces: {
|
||||
'lineWithMultipleSpaces': {
|
||||
description: 'Multiple spaces should be collapsed',
|
||||
input: '<html><body>Text with more than one space.<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>Text with more than one space.<br><br></body></html>',
|
||||
expectedText: 'Text with more than one space.\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>Text with more than one space.<br><br></body></html>',
|
||||
wantText: 'Text with more than one space.\n\n',
|
||||
},
|
||||
lineWithMultipleNonBreakingAndNormalSpaces: {
|
||||
'lineWithMultipleNonBreakingAndNormalSpaces': {
|
||||
// XXX the HTML between "than" and "one" looks strange
|
||||
description: 'non-breaking space should be preserved, but can be replaced when it',
|
||||
input: '<html><body>Text with more than one space.<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>Text with more than one space.<br><br></body></html>',
|
||||
expectedText: 'Text with more than one space.\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>Text with more than one space.<br><br></body></html>',
|
||||
wantText: 'Text with more than one space.\n\n',
|
||||
},
|
||||
multiplenbsp: {
|
||||
'multiplenbsp': {
|
||||
description: 'Multiple non-breaking space should be preserved',
|
||||
input: '<html><body> <br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body> <br><br></body></html>',
|
||||
expectedText: ' \n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body> <br><br></body></html>',
|
||||
wantText: ' \n\n',
|
||||
},
|
||||
multipleNonBreakingSpaceBetweenWords: {
|
||||
'multipleNonBreakingSpaceBetweenWords': {
|
||||
description: 'A normal space is always inserted before a word',
|
||||
input: '<html><body> word1 word2 word3<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body> word1 word2 word3<br><br></body></html>',
|
||||
expectedText: ' word1 word2 word3\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body> word1 word2 word3<br><br></body></html>',
|
||||
wantText: ' word1 word2 word3\n\n',
|
||||
},
|
||||
nonBreakingSpacePreceededBySpaceBetweenWords: {
|
||||
'nonBreakingSpacePreceededBySpaceBetweenWords': {
|
||||
description: 'A non-breaking space preceeded by a normal space',
|
||||
input: '<html><body> word1 word2 word3<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body> word1 word2 word3<br><br></body></html>',
|
||||
expectedText: ' word1 word2 word3\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body> word1 word2 word3<br><br></body></html>',
|
||||
wantText: ' word1 word2 word3\n\n',
|
||||
},
|
||||
nonBreakingSpaceFollowededBySpaceBetweenWords: {
|
||||
'nonBreakingSpaceFollowededBySpaceBetweenWords': {
|
||||
description: 'A non-breaking space followed by a normal space',
|
||||
input: '<html><body> word1 word2 word3<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body> word1 word2 word3<br><br></body></html>',
|
||||
expectedText: ' word1 word2 word3\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body> word1 word2 word3<br><br></body></html>',
|
||||
wantText: ' word1 word2 word3\n\n',
|
||||
},
|
||||
spacesAfterNewline: {
|
||||
'spacesAfterNewline': {
|
||||
description: 'Collapse spaces that follow a newline',
|
||||
input:'<!doctype html><html><body>something<br> something<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>something<br>something<br><br></body></html>',
|
||||
expectedText: 'something\nsomething\n\n'
|
||||
input: '<!doctype html><html><body>something<br> something<br></body></html>',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>something<br>something<br><br></body></html>',
|
||||
wantText: 'something\nsomething\n\n',
|
||||
},
|
||||
spacesAfterNewlineP: {
|
||||
'spacesAfterNewlineP': {
|
||||
description: 'Collapse spaces that follow a paragraph',
|
||||
input:'<!doctype html><html><body>something<p></p> something<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>something<br><br>something<br><br></body></html>',
|
||||
expectedText: 'something\n\nsomething\n\n'
|
||||
input: '<!doctype html><html><body>something<p></p> something<br></body></html>',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>something<br><br>something<br><br></body></html>',
|
||||
wantText: 'something\n\nsomething\n\n',
|
||||
},
|
||||
spacesAtEndOfLine: {
|
||||
'spacesAtEndOfLine': {
|
||||
description: 'Collapse spaces that preceed/follow a newline',
|
||||
input:'<html><body>something <br> something<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>something<br>something<br><br></body></html>',
|
||||
expectedText: 'something\nsomething\n\n'
|
||||
input: '<html><body>something <br> something<br></body></html>',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>something<br>something<br><br></body></html>',
|
||||
wantText: 'something\nsomething\n\n',
|
||||
},
|
||||
spacesAtEndOfLineP: {
|
||||
'spacesAtEndOfLineP': {
|
||||
description: 'Collapse spaces that preceed/follow a paragraph',
|
||||
input:'<html><body>something <p></p> something<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>something<br><br>something<br><br></body></html>',
|
||||
expectedText: 'something\n\nsomething\n\n'
|
||||
input: '<html><body>something <p></p> something<br></body></html>',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>something<br><br>something<br><br></body></html>',
|
||||
wantText: 'something\n\nsomething\n\n',
|
||||
},
|
||||
nonBreakingSpacesAfterNewlines: {
|
||||
'nonBreakingSpacesAfterNewlines': {
|
||||
description: 'Don\'t collapse non-breaking spaces that follow a newline',
|
||||
input:'<html><body>something<br> something<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>something<br> something<br><br></body></html>',
|
||||
expectedText: 'something\n something\n\n'
|
||||
input: '<html><body>something<br> something<br></body></html>',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>something<br> something<br><br></body></html>',
|
||||
wantText: 'something\n something\n\n',
|
||||
},
|
||||
nonBreakingSpacesAfterNewlinesP: {
|
||||
'nonBreakingSpacesAfterNewlinesP': {
|
||||
description: 'Don\'t collapse non-breaking spaces that follow a paragraph',
|
||||
input:'<html><body>something<p></p> something<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>something<br><br> something<br><br></body></html>',
|
||||
expectedText: 'something\n\n something\n\n'
|
||||
input: '<html><body>something<p></p> something<br></body></html>',
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>something<br><br> something<br><br></body></html>',
|
||||
wantText: 'something\n\n something\n\n',
|
||||
},
|
||||
collapseSpacesInsideElements: {
|
||||
'collapseSpacesInsideElements': {
|
||||
description: 'Preserve only one space when multiple are present',
|
||||
input: '<html><body>Need <span> more </span> space<i> s </i> !<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>Need more space<em> s </em>!<br><br></body></html>',
|
||||
expectedText: 'Need more space s !\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>Need more space<em> s </em>!<br><br></body></html>',
|
||||
wantText: 'Need more space s !\n\n',
|
||||
},
|
||||
collapseSpacesAcrossNewlines: {
|
||||
'collapseSpacesAcrossNewlines': {
|
||||
description: 'Newlines and multiple spaces across newlines should be collapsed',
|
||||
input: `
|
||||
<html><body>Need
|
||||
|
@ -158,30 +155,30 @@ const testImports = {
|
|||
space
|
||||
<i> s </i>
|
||||
!<br></body></html>`,
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>Need more space <em>s </em>!<br><br></body></html>',
|
||||
expectedText: 'Need more space s !\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>Need more space <em>s </em>!<br><br></body></html>',
|
||||
wantText: 'Need more space s !\n\n',
|
||||
},
|
||||
multipleNewLinesAtBeginning: {
|
||||
'multipleNewLinesAtBeginning': {
|
||||
description: 'Multiple new lines and paragraphs at the beginning should be preserved',
|
||||
input: '<html><body><br><br><p></p><p></p>first line<br><br>second line<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body><br><br><br><br>first line<br><br>second line<br><br></body></html>',
|
||||
expectedText: '\n\n\n\nfirst line\n\nsecond line\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body><br><br><br><br>first line<br><br>second line<br><br></body></html>',
|
||||
wantText: '\n\n\n\nfirst line\n\nsecond line\n\n',
|
||||
},
|
||||
multiLineParagraph:{
|
||||
description: "A paragraph with multiple lines should not loose spaces when lines are combined",
|
||||
input:`<html><body>
|
||||
'multiLineParagraph': {
|
||||
description: 'A paragraph with multiple lines should not loose spaces when lines are combined',
|
||||
input: `<html><body>
|
||||
<p>
|
||||
а б в г ґ д е є ж з и і ї й к л м н о
|
||||
п р с т у ф х ц ч ш щ ю я ь
|
||||
</p>
|
||||
</body></html>`,
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>а б в г ґ д е є ж з и і ї й к л м н о п р с т у ф х ц ч ш щ ю я ь<br><br></body></html>',
|
||||
expectedText: 'а б в г ґ д е є ж з и і ї й к л м н о п р с т у ф х ц ч ш щ ю я ь\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>а б в г ґ д е є ж з и і ї й к л м н о п р с т у ф х ц ч ш щ ю я ь<br><br></body></html>',
|
||||
wantText: 'а б в г ґ д е є ж з и і ї й к л м н о п р с т у ф х ц ч ш щ ю я ь\n\n',
|
||||
},
|
||||
multiLineParagraphWithPre:{
|
||||
//XXX why is there before "in"?
|
||||
description: "lines in preformatted text should be kept intact",
|
||||
input:`<html><body>
|
||||
'multiLineParagraphWithPre': {
|
||||
// XXX why is there before "in"?
|
||||
description: 'lines in preformatted text should be kept intact',
|
||||
input: `<html><body>
|
||||
<p>
|
||||
а б в г ґ д е є ж з и і ї й к л м н о<pre>multiple
|
||||
lines
|
||||
|
@ -190,55 +187,55 @@ const testImports = {
|
|||
</pre></p><p>п р с т у ф х ц ч ш щ ю я
|
||||
ь</p>
|
||||
</body></html>`,
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>а б в г ґ д е є ж з и і ї й к л м н о<br>multiple<br> lines<br> in<br> pre<br><br>п р с т у ф х ц ч ш щ ю я ь<br><br></body></html>',
|
||||
expectedText: 'а б в г ґ д е є ж з и і ї й к л м н о\nmultiple\n lines\n in\n pre\n\nп р с т у ф х ц ч ш щ ю я ь\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>а б в г ґ д е є ж з и і ї й к л м н о<br>multiple<br> lines<br> in<br> pre<br><br>п р с т у ф х ц ч ш щ ю я ь<br><br></body></html>',
|
||||
wantText: 'а б в г ґ д е є ж з и і ї й к л м н о\nmultiple\n lines\n in\n pre\n\nп р с т у ф х ц ч ш щ ю я ь\n\n',
|
||||
},
|
||||
preIntroducesASpace: {
|
||||
description: "pre should be on a new line not preceeded by a space",
|
||||
input:`<html><body><p>
|
||||
'preIntroducesASpace': {
|
||||
description: 'pre should be on a new line not preceeded by a space',
|
||||
input: `<html><body><p>
|
||||
1
|
||||
<pre>preline
|
||||
</pre></p></body></html>`,
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>1<br>preline<br><br><br></body></html>',
|
||||
expectedText: '1\npreline\n\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>1<br>preline<br><br><br></body></html>',
|
||||
wantText: '1\npreline\n\n\n',
|
||||
},
|
||||
dontDeleteSpaceInsideElements: {
|
||||
'dontDeleteSpaceInsideElements': {
|
||||
description: 'Preserve spaces inside elements',
|
||||
input: '<html><body>Need<span> more </span>space<i> s </i>!<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>Need more space<em> s </em>!<br><br></body></html>',
|
||||
expectedText: 'Need more space s !\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>Need more space<em> s </em>!<br><br></body></html>',
|
||||
wantText: 'Need more space s !\n\n',
|
||||
},
|
||||
dontDeleteSpaceOutsideElements: {
|
||||
'dontDeleteSpaceOutsideElements': {
|
||||
description: 'Preserve spaces outside elements',
|
||||
input: '<html><body>Need <span>more</span> space <i>s</i> !<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>Need more space <em>s</em> !<br><br></body></html>',
|
||||
expectedText: 'Need more space s !\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>Need more space <em>s</em> !<br><br></body></html>',
|
||||
wantText: 'Need more space s !\n\n',
|
||||
},
|
||||
dontDeleteSpaceAtEndOfElement: {
|
||||
'dontDeleteSpaceAtEndOfElement': {
|
||||
description: 'Preserve spaces at the end of an element',
|
||||
input: '<html><body>Need <span>more </span>space <i>s </i>!<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>Need more space <em>s </em>!<br><br></body></html>',
|
||||
expectedText: 'Need more space s !\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>Need more space <em>s </em>!<br><br></body></html>',
|
||||
wantText: 'Need more space s !\n\n',
|
||||
},
|
||||
dontDeleteSpaceAtBeginOfElements: {
|
||||
'dontDeleteSpaceAtBeginOfElements': {
|
||||
description: 'Preserve spaces at the start of an element',
|
||||
input: '<html><body>Need<span> more</span> space<i> s</i> !<br></body></html>',
|
||||
expectedHTML: '<!DOCTYPE HTML><html><body>Need more space<em> s</em> !<br><br></body></html>',
|
||||
expectedText: 'Need more space s !\n\n'
|
||||
wantHTML: '<!DOCTYPE HTML><html><body>Need more space<em> s</em> !<br><br></body></html>',
|
||||
wantText: 'Need more space s !\n\n',
|
||||
},
|
||||
};
|
||||
|
||||
describe(__filename, function () {
|
||||
Object.keys(testImports).forEach((testName) => {
|
||||
const testPadId = makeid();
|
||||
const test = testImports[testName];
|
||||
if (test.disabled) {
|
||||
return xit(`DISABLED: ${testName}`, function (done) {
|
||||
done();
|
||||
});
|
||||
}
|
||||
describe(`createPad ${testName}`, function () {
|
||||
it('creates a new Pad', function (done) {
|
||||
describe(testName, function () {
|
||||
const testPadId = makeid();
|
||||
const test = testImports[testName];
|
||||
if (test.disabled) {
|
||||
return xit(`DISABLED: ${testName}`, function (done) {
|
||||
done();
|
||||
});
|
||||
}
|
||||
it('createPad', function (done) {
|
||||
api.get(`${endPoint('createPad')}&padID=${testPadId}`)
|
||||
.expect((res) => {
|
||||
if (res.body.code !== 0) throw new Error('Unable to create new Pad');
|
||||
|
@ -246,10 +243,8 @@ describe(__filename, function () {
|
|||
.expect('Content-Type', /json/)
|
||||
.expect(200, done);
|
||||
});
|
||||
});
|
||||
|
||||
describe(`setHTML ${testName}`, function () {
|
||||
it('Sets the HTML', function (done) {
|
||||
it('setHTML', function (done) {
|
||||
api.get(`${endPoint('setHTML')}&padID=${testPadId}&html=${encodeURIComponent(test.input)}`)
|
||||
.expect((res) => {
|
||||
if (res.body.code !== 0) throw new Error(`Error:${testName}`);
|
||||
|
@ -257,23 +252,21 @@ describe(__filename, function () {
|
|||
.expect('Content-Type', /json/)
|
||||
.expect(200, done);
|
||||
});
|
||||
});
|
||||
|
||||
describe(`getHTML ${testName}`, function () {
|
||||
it('Gets back the HTML of a Pad', function (done) {
|
||||
it('getHTML', function (done) {
|
||||
api.get(`${endPoint('getHTML')}&padID=${testPadId}`)
|
||||
.expect((res) => {
|
||||
const receivedHtml = res.body.data.html;
|
||||
if (receivedHtml !== test.expectedHTML) {
|
||||
const gotHtml = res.body.data.html;
|
||||
if (gotHtml !== test.wantHTML) {
|
||||
throw new Error(`HTML received from export is not the one we were expecting.
|
||||
Test Name:
|
||||
${testName}
|
||||
|
||||
Received:
|
||||
${JSON.stringify(receivedHtml)}
|
||||
Got:
|
||||
${JSON.stringify(gotHtml)}
|
||||
|
||||
Expected:
|
||||
${JSON.stringify(test.expectedHTML)}
|
||||
Want:
|
||||
${JSON.stringify(test.wantHTML)}
|
||||
|
||||
Which is a different version of the originally imported one:
|
||||
${test.input}`);
|
||||
|
@ -282,23 +275,21 @@ describe(__filename, function () {
|
|||
.expect('Content-Type', /json/)
|
||||
.expect(200, done);
|
||||
});
|
||||
});
|
||||
|
||||
describe(`getText ${testName}`, function () {
|
||||
it('Gets back the Text of a Pad', function (done) {
|
||||
it('getText', function (done) {
|
||||
api.get(`${endPoint('getText')}&padID=${testPadId}`)
|
||||
.expect((res) => {
|
||||
const receivedText = res.body.data.text;
|
||||
if (receivedText !== test.expectedText) {
|
||||
const gotText = res.body.data.text;
|
||||
if (gotText !== test.wantText) {
|
||||
throw new Error(`Text received from export is not the one we were expecting.
|
||||
Test Name:
|
||||
${testName}
|
||||
|
||||
Received:
|
||||
${JSON.stringify(receivedText)}
|
||||
Got:
|
||||
${JSON.stringify(gotText)}
|
||||
|
||||
Expected:
|
||||
${JSON.stringify(test.expectedText)}
|
||||
Want:
|
||||
${JSON.stringify(test.wantText)}
|
||||
|
||||
Which is a different version of the originally imported one:
|
||||
${test.input}`);
|
||||
|
@ -315,7 +306,7 @@ describe(__filename, function () {
|
|||
function endPoint(point, version) {
|
||||
version = version || apiVersion;
|
||||
return `/api/${version}/${point}?apikey=${apiKey}`;
|
||||
};
|
||||
}
|
||||
|
||||
function makeid() {
|
||||
let text = '';
|
||||
|
|
|
@ -1,34 +1,34 @@
|
|||
'use strict';
|
||||
|
||||
/* eslint-disable max-len */
|
||||
/*
|
||||
* While importexport tests target the `setHTML` API endpoint, which is nearly identical to what happens
|
||||
* when a user manually imports a document via the UI, the contentcollector tests here don't use rehype to process
|
||||
* the document. Rehype removes spaces and newĺines were applicable, so the expected results here can
|
||||
* differ from importexport.js.
|
||||
* While importexport tests target the `setHTML` API endpoint, which is nearly identical to what
|
||||
* happens when a user manually imports a document via the UI, the contentcollector tests here don't
|
||||
* use rehype to process the document. Rehype removes spaces and newĺines were applicable, so the
|
||||
* expected results here can differ from importexport.js.
|
||||
*
|
||||
* If you add tests here, please also add them to importexport.js
|
||||
*/
|
||||
|
||||
const contentcollector = require('../../../src/static/js/contentcollector');
|
||||
const AttributePool = require('../../../src/static/js/AttributePool');
|
||||
const cheerio = require('../../../src/node_modules/cheerio');
|
||||
const AttributePool = require('ep_etherpad-lite/static/js/AttributePool');
|
||||
const assert = require('assert').strict;
|
||||
const cheerio = require('ep_etherpad-lite/node_modules/cheerio');
|
||||
const contentcollector = require('ep_etherpad-lite/static/js/contentcollector');
|
||||
|
||||
const tests = {
|
||||
nestedLi: {
|
||||
description: 'Complex nested Li',
|
||||
html: '<!doctype html><html><body><ol><li>one</li><li><ol><li>1.1</li></ol></li><li>two</li></ol></body></html>',
|
||||
expectedLineAttribs: [
|
||||
wantLineAttribs: [
|
||||
'*0*1*2*3+1+3', '*0*4*2*5+1+3', '*0*1*2*5+1+3',
|
||||
],
|
||||
expectedText: [
|
||||
wantText: [
|
||||
'*one', '*1.1', '*two',
|
||||
],
|
||||
},
|
||||
complexNest: {
|
||||
description: 'Complex list of different types',
|
||||
html: '<!doctype html><html><body><ul class="bullet"><li>one</li><li>two</li><li>0</li><li>1</li><li>2<ul class="bullet"><li>3</li><li>4</li></ul></li></ul><ol class="number"><li>item<ol class="number"><li>item1</li><li>item2</li></ol></li></ol></body></html>',
|
||||
expectedLineAttribs: [
|
||||
wantLineAttribs: [
|
||||
'*0*1*2+1+3',
|
||||
'*0*1*2+1+3',
|
||||
'*0*1*2+1+1',
|
||||
|
@ -40,7 +40,7 @@ const tests = {
|
|||
'*0*6*2*7+1+5',
|
||||
'*0*6*2*7+1+5',
|
||||
],
|
||||
expectedText: [
|
||||
wantText: [
|
||||
'*one',
|
||||
'*two',
|
||||
'*0',
|
||||
|
@ -56,148 +56,142 @@ const tests = {
|
|||
ul: {
|
||||
description: 'Tests if uls properly get attributes',
|
||||
html: '<html><body><ul><li>a</li><li>b</li></ul><div>div</div><p>foo</p></body></html>',
|
||||
expectedLineAttribs: ['*0*1*2+1+1', '*0*1*2+1+1', '+3', '+3'],
|
||||
expectedText: ['*a', '*b', 'div', 'foo'],
|
||||
wantLineAttribs: ['*0*1*2+1+1', '*0*1*2+1+1', '+3', '+3'],
|
||||
wantText: ['*a', '*b', 'div', 'foo'],
|
||||
},
|
||||
ulIndented: {
|
||||
description: 'Tests if indented uls properly get attributes',
|
||||
html: '<html><body><ul><li>a</li><ul><li>b</li></ul><li>a</li></ul><p>foo</p></body></html>',
|
||||
expectedLineAttribs: ['*0*1*2+1+1', '*0*3*2+1+1', '*0*1*2+1+1', '+3'],
|
||||
expectedText: ['*a', '*b', '*a', 'foo'],
|
||||
wantLineAttribs: ['*0*1*2+1+1', '*0*3*2+1+1', '*0*1*2+1+1', '+3'],
|
||||
wantText: ['*a', '*b', '*a', 'foo'],
|
||||
},
|
||||
ol: {
|
||||
description: 'Tests if ols properly get line numbers when in a normal OL',
|
||||
html: '<html><body><ol><li>a</li><li>b</li><li>c</li></ol><p>test</p></body></html>',
|
||||
expectedLineAttribs: ['*0*1*2*3+1+1', '*0*1*2*3+1+1', '*0*1*2*3+1+1', '+4'],
|
||||
expectedText: ['*a', '*b', '*c', 'test'],
|
||||
wantLineAttribs: ['*0*1*2*3+1+1', '*0*1*2*3+1+1', '*0*1*2*3+1+1', '+4'],
|
||||
wantText: ['*a', '*b', '*c', 'test'],
|
||||
noteToSelf: 'Ensure empty P does not induce line attribute marker, wont this break the editor?',
|
||||
},
|
||||
lineDoBreakInOl: {
|
||||
description: 'A single completely empty line break within an ol should reset count if OL is closed off..',
|
||||
html: '<html><body><ol><li>should be 1</li></ol><p>hello</p><ol><li>should be 1</li><li>should be 2</li></ol><p></p></body></html>',
|
||||
expectedLineAttribs: ['*0*1*2*3+1+b', '+5', '*0*1*2*4+1+b', '*0*1*2*4+1+b', ''],
|
||||
expectedText: ['*should be 1', 'hello', '*should be 1', '*should be 2', ''],
|
||||
wantLineAttribs: ['*0*1*2*3+1+b', '+5', '*0*1*2*4+1+b', '*0*1*2*4+1+b', ''],
|
||||
wantText: ['*should be 1', 'hello', '*should be 1', '*should be 2', ''],
|
||||
noteToSelf: "Shouldn't include attribute marker in the <p> line",
|
||||
},
|
||||
bulletListInOL: {
|
||||
description: 'A bullet within an OL should not change numbering..',
|
||||
html: '<html><body><ol><li>should be 1</li><ul><li>should be a bullet</li></ul><li>should be 2</li></ol><p></p></body></html>',
|
||||
expectedLineAttribs: ['*0*1*2*3+1+b', '*0*4*2*3+1+i', '*0*1*2*5+1+b', ''],
|
||||
expectedText: ['*should be 1', '*should be a bullet', '*should be 2', ''],
|
||||
},
|
||||
testP: {
|
||||
description: 'A single <p></p> should create a new line',
|
||||
html: '<html><body><p></p><p></p></body></html>',
|
||||
expectedLineAttribs: ['', ''],
|
||||
expectedText: ['', ''],
|
||||
wantLineAttribs: ['', ''],
|
||||
wantText: ['', ''],
|
||||
noteToSelf: '<p></p>should create a line break but not break numbering',
|
||||
},
|
||||
nestedOl: {
|
||||
description: 'Tests if ols properly get line numbers when in a normal OL',
|
||||
html: '<html><body>a<ol><li>b<ol><li>c</li></ol></ol>notlist<p>foo</p></body></html>',
|
||||
expectedLineAttribs: ['+1', '*0*1*2*3+1+1', '*0*4*2*5+1+1', '+7', '+3'],
|
||||
expectedText: ['a', '*b', '*c', 'notlist', 'foo'],
|
||||
wantLineAttribs: ['+1', '*0*1*2*3+1+1', '*0*4*2*5+1+1', '+7', '+3'],
|
||||
wantText: ['a', '*b', '*c', 'notlist', 'foo'],
|
||||
noteToSelf: 'Ensure empty P does not induce line attribute marker, wont this break the editor?',
|
||||
},
|
||||
nestedOl2: {
|
||||
description: 'First item being an UL then subsequent being OL will fail',
|
||||
html: '<html><body><ul><li>a<ol><li>b</li><li>c</li></ol></li></ul></body></html>',
|
||||
expectedLineAttribs: ['+1', '*0*1*2*3+1+1', '*0*4*2*5+1+1'],
|
||||
expectedText: ['a', '*b', '*c'],
|
||||
wantLineAttribs: ['+1', '*0*1*2*3+1+1', '*0*4*2*5+1+1'],
|
||||
wantText: ['a', '*b', '*c'],
|
||||
noteToSelf: 'Ensure empty P does not induce line attribute marker, wont this break the editor?',
|
||||
disabled: true,
|
||||
},
|
||||
lineDontBreakOL: {
|
||||
description: 'A single completely empty line break within an ol should NOT reset count',
|
||||
html: '<html><body><ol><li>should be 1</li><p></p><li>should be 2</li><li>should be 3</li></ol><p></p></body></html>',
|
||||
expectedLineAttribs: [],
|
||||
expectedText: ['*should be 1', '*should be 2', '*should be 3'],
|
||||
wantLineAttribs: [],
|
||||
wantText: ['*should be 1', '*should be 2', '*should be 3'],
|
||||
noteToSelf: "<p></p>should create a line break but not break numbering -- This is what I can't get working!",
|
||||
disabled: true,
|
||||
},
|
||||
ignoreAnyTagsOutsideBody: {
|
||||
description: 'Content outside body should be ignored',
|
||||
html: '<html><head><title>title</title><style></style></head><body>empty<br></body></html>',
|
||||
expectedLineAttribs: ['+5'],
|
||||
expectedText: ['empty'],
|
||||
wantLineAttribs: ['+5'],
|
||||
wantText: ['empty'],
|
||||
},
|
||||
lineWithMultipleSpaces: {
|
||||
description: 'Multiple spaces should be preserved',
|
||||
html: '<html><body>Text with more than one space.<br></body></html>',
|
||||
expectedLineAttribs: [ '+10' ],
|
||||
expectedText: ['Text with more than one space.']
|
||||
wantLineAttribs: ['+10'],
|
||||
wantText: ['Text with more than one space.'],
|
||||
},
|
||||
lineWithMultipleNonBreakingAndNormalSpaces: {
|
||||
description: 'non-breaking and normal space should be preserved',
|
||||
html: '<html><body>Text with more than one space.<br></body></html>',
|
||||
expectedLineAttribs: [ '+10' ],
|
||||
expectedText: ['Text with more than one space.']
|
||||
wantLineAttribs: ['+10'],
|
||||
wantText: ['Text with more than one space.'],
|
||||
},
|
||||
multiplenbsp: {
|
||||
description: 'Multiple nbsp should be preserved',
|
||||
html: '<html><body> <br></body></html>',
|
||||
expectedLineAttribs: [ '+2' ],
|
||||
expectedText: [' ']
|
||||
wantLineAttribs: ['+2'],
|
||||
wantText: [' '],
|
||||
},
|
||||
multipleNonBreakingSpaceBetweenWords: {
|
||||
description: 'Multiple nbsp between words ',
|
||||
html: '<html><body> word1 word2 word3<br></body></html>',
|
||||
expectedLineAttribs: [ '+m' ],
|
||||
expectedText: [' word1 word2 word3']
|
||||
wantLineAttribs: ['+m'],
|
||||
wantText: [' word1 word2 word3'],
|
||||
},
|
||||
nonBreakingSpacePreceededBySpaceBetweenWords: {
|
||||
description: 'A non-breaking space preceeded by a normal space',
|
||||
html: '<html><body> word1 word2 word3<br></body></html>',
|
||||
expectedLineAttribs: [ '+l' ],
|
||||
expectedText: [' word1 word2 word3']
|
||||
wantLineAttribs: ['+l'],
|
||||
wantText: [' word1 word2 word3'],
|
||||
},
|
||||
nonBreakingSpaceFollowededBySpaceBetweenWords: {
|
||||
description: 'A non-breaking space followed by a normal space',
|
||||
html: '<html><body> word1 word2 word3<br></body></html>',
|
||||
expectedLineAttribs: [ '+l' ],
|
||||
expectedText: [' word1 word2 word3']
|
||||
wantLineAttribs: ['+l'],
|
||||
wantText: [' word1 word2 word3'],
|
||||
},
|
||||
spacesAfterNewline: {
|
||||
description: 'Don\'t collapse spaces that follow a newline',
|
||||
html:'<!doctype html><html><body>something<br> something<br></body></html>',
|
||||
expectedLineAttribs: ['+9', '+m'],
|
||||
expectedText: ['something', ' something']
|
||||
html: '<!doctype html><html><body>something<br> something<br></body></html>',
|
||||
wantLineAttribs: ['+9', '+m'],
|
||||
wantText: ['something', ' something'],
|
||||
},
|
||||
spacesAfterNewlineP: {
|
||||
description: 'Don\'t collapse spaces that follow a empty paragraph',
|
||||
html:'<!doctype html><html><body>something<p></p> something<br></body></html>',
|
||||
expectedLineAttribs: ['+9', '', '+m'],
|
||||
expectedText: ['something', '', ' something']
|
||||
html: '<!doctype html><html><body>something<p></p> something<br></body></html>',
|
||||
wantLineAttribs: ['+9', '', '+m'],
|
||||
wantText: ['something', '', ' something'],
|
||||
},
|
||||
spacesAtEndOfLine: {
|
||||
description: 'Don\'t collapse spaces that preceed/follow a newline',
|
||||
html:'<html><body>something <br> something<br></body></html>',
|
||||
expectedLineAttribs: ['+l', '+m'],
|
||||
expectedText: ['something ', ' something']
|
||||
html: '<html><body>something <br> something<br></body></html>',
|
||||
wantLineAttribs: ['+l', '+m'],
|
||||
wantText: ['something ', ' something'],
|
||||
},
|
||||
spacesAtEndOfLineP: {
|
||||
description: 'Don\'t collapse spaces that preceed/follow a empty paragraph',
|
||||
html:'<html><body>something <p></p> something<br></body></html>',
|
||||
expectedLineAttribs: ['+l', '', '+m'],
|
||||
expectedText: ['something ', '', ' something']
|
||||
html: '<html><body>something <p></p> something<br></body></html>',
|
||||
wantLineAttribs: ['+l', '', '+m'],
|
||||
wantText: ['something ', '', ' something'],
|
||||
},
|
||||
nonBreakingSpacesAfterNewlines: {
|
||||
description: 'Don\'t collapse non-breaking spaces that follow a newline',
|
||||
html:'<html><body>something<br> something<br></body></html>',
|
||||
expectedLineAttribs: ['+9', '+c'],
|
||||
expectedText: ['something', ' something']
|
||||
html: '<html><body>something<br> something<br></body></html>',
|
||||
wantLineAttribs: ['+9', '+c'],
|
||||
wantText: ['something', ' something'],
|
||||
},
|
||||
nonBreakingSpacesAfterNewlinesP: {
|
||||
description: 'Don\'t collapse non-breaking spaces that follow a paragraph',
|
||||
html:'<html><body>something<p></p> something<br></body></html>',
|
||||
expectedLineAttribs: ['+9', '', '+c'],
|
||||
expectedText: ['something', '', ' something']
|
||||
html: '<html><body>something<p></p> something<br></body></html>',
|
||||
wantLineAttribs: ['+9', '', '+c'],
|
||||
wantText: ['something', '', ' something'],
|
||||
},
|
||||
preserveSpacesInsideElements: {
|
||||
description: 'Preserve all spaces when multiple are present',
|
||||
html: '<html><body>Need <span> more </span> space<i> s </i> !<br></body></html>',
|
||||
expectedLineAttribs: ['+h*0+4+2'],
|
||||
expectedText: ['Need more space s !'],
|
||||
wantLineAttribs: ['+h*0+4+2'],
|
||||
wantText: ['Need more space s !'],
|
||||
},
|
||||
preserveSpacesAcrossNewlines: {
|
||||
description: 'Newlines and multiple spaces across newlines should be preserved',
|
||||
|
@ -207,69 +201,76 @@ const tests = {
|
|||
space
|
||||
<i> s </i>
|
||||
!<br></body></html>`,
|
||||
expectedLineAttribs: [ '+19*0+4+b' ],
|
||||
expectedText: [ 'Need more space s !' ]
|
||||
wantLineAttribs: ['+19*0+4+b'],
|
||||
wantText: ['Need more space s !'],
|
||||
},
|
||||
multipleNewLinesAtBeginning: {
|
||||
description: 'Multiple new lines at the beginning should be preserved',
|
||||
html: '<html><body><br><br><p></p><p></p>first line<br><br>second line<br></body></html>',
|
||||
expectedLineAttribs: ['', '', '', '', '+a', '', '+b'],
|
||||
expectedText: [ '', '', '', '', 'first line', '', 'second line']
|
||||
wantLineAttribs: ['', '', '', '', '+a', '', '+b'],
|
||||
wantText: ['', '', '', '', 'first line', '', 'second line'],
|
||||
},
|
||||
multiLineParagraph:{
|
||||
description: "A paragraph with multiple lines should not loose spaces when lines are combined",
|
||||
html:`<html><body><p>
|
||||
multiLineParagraph: {
|
||||
description: 'A paragraph with multiple lines should not loose spaces when lines are combined',
|
||||
html: `<html><body><p>
|
||||
а б в г ґ д е є ж з и і ї й к л м н о
|
||||
п р с т у ф х ц ч ш щ ю я ь</p>
|
||||
</body></html>`,
|
||||
expectedLineAttribs: [ '+1t' ],
|
||||
expectedText: ["а б в г ґ д е є ж з и і ї й к л м н о п р с т у ф х ц ч ш щ ю я ь"]
|
||||
wantLineAttribs: ['+1t'],
|
||||
wantText: ['а б в г ґ д е є ж з и і ї й к л м н о п р с т у ф х ц ч ш щ ю я ь'],
|
||||
},
|
||||
multiLineParagraphWithPre:{
|
||||
description: "lines in preformatted text should be kept intact",
|
||||
html:`<html><body><p>
|
||||
а б в г ґ д е є ж з и і ї й к л м н о<pre>multiple
|
||||
multiLineParagraphWithPre: {
|
||||
description: 'lines in preformatted text should be kept intact',
|
||||
html: `<html><body><p>
|
||||
а б в г ґ д е є ж з и і ї й к л м н о</p><pre>multiple
|
||||
lines
|
||||
in
|
||||
pre
|
||||
</pre></p><p>п р с т у ф х ц ч ш щ ю я
|
||||
</pre><p>п р с т у ф х ц ч ш щ ю я
|
||||
ь</p>
|
||||
</body></html>`,
|
||||
expectedLineAttribs: [ '+11', '+8', '+5', '+2', '+3', '+r' ],
|
||||
expectedText: ['а б в г ґ д е є ж з и і ї й к л м н о', 'multiple', 'lines', 'in', 'pre', 'п р с т у ф х ц ч ш щ ю я ь']
|
||||
wantLineAttribs: ['+11', '+8', '+5', '+2', '+3', '+r'],
|
||||
wantText: [
|
||||
'а б в г ґ д е є ж з и і ї й к л м н о',
|
||||
'multiple',
|
||||
'lines',
|
||||
'in',
|
||||
'pre',
|
||||
'п р с т у ф х ц ч ш щ ю я ь',
|
||||
],
|
||||
},
|
||||
preIntroducesASpace: {
|
||||
description: "pre should be on a new line not preceeded by a space",
|
||||
html:`<html><body><p>
|
||||
description: 'pre should be on a new line not preceeded by a space',
|
||||
html: `<html><body><p>
|
||||
1
|
||||
<pre>preline
|
||||
</pre></p></body></html>`,
|
||||
expectedLineAttribs: [ '+6', '+7' ],
|
||||
expectedText: [' 1 ', 'preline']
|
||||
</p><pre>preline
|
||||
</pre></body></html>`,
|
||||
wantLineAttribs: ['+6', '+7'],
|
||||
wantText: [' 1 ', 'preline'],
|
||||
},
|
||||
dontDeleteSpaceInsideElements: {
|
||||
description: 'Preserve spaces on the beginning and end of a element',
|
||||
html: '<html><body>Need<span> more </span>space<i> s </i>!<br></body></html>',
|
||||
expectedLineAttribs: ['+f*0+3+1'],
|
||||
expectedText: ['Need more space s !']
|
||||
wantLineAttribs: ['+f*0+3+1'],
|
||||
wantText: ['Need more space s !'],
|
||||
},
|
||||
dontDeleteSpaceOutsideElements: {
|
||||
description: 'Preserve spaces outside elements',
|
||||
html: '<html><body>Need <span>more</span> space <i>s</i> !<br></body></html>',
|
||||
expectedLineAttribs: ['+g*0+1+2'],
|
||||
expectedText: ['Need more space s !']
|
||||
wantLineAttribs: ['+g*0+1+2'],
|
||||
wantText: ['Need more space s !'],
|
||||
},
|
||||
dontDeleteSpaceAtEndOfElement: {
|
||||
description: 'Preserve spaces at the end of an element',
|
||||
html: '<html><body>Need <span>more </span>space <i>s </i>!<br></body></html>',
|
||||
expectedLineAttribs: ['+g*0+2+1'],
|
||||
expectedText: ['Need more space s !']
|
||||
wantLineAttribs: ['+g*0+2+1'],
|
||||
wantText: ['Need more space s !'],
|
||||
},
|
||||
dontDeleteSpaceAtBeginOfElements: {
|
||||
description: 'Preserve spaces at the start of an element',
|
||||
html: '<html><body>Need<span> more</span> space<i> s</i> !<br></body></html>',
|
||||
expectedLineAttribs: ['+f*0+2+2'],
|
||||
expectedText: ['Need more space s !']
|
||||
wantLineAttribs: ['+f*0+2+2'],
|
||||
wantText: ['Need more space s !'],
|
||||
},
|
||||
};
|
||||
|
||||
|
@ -283,7 +284,7 @@ describe(__filename, function () {
|
|||
});
|
||||
}
|
||||
|
||||
it(testObj.description, function (done) {
|
||||
it(testObj.description, async function () {
|
||||
const $ = cheerio.load(testObj.html); // Load HTML into Cheerio
|
||||
const doc = $('body')[0]; // Creates a dom-like representation of HTML
|
||||
// Create an empty attribute pool
|
||||
|
@ -293,29 +294,13 @@ describe(__filename, function () {
|
|||
const cc = contentcollector.makeContentCollector(true, null, apool);
|
||||
cc.collectContent(doc);
|
||||
const result = cc.finish();
|
||||
const recievedAttributes = result.lineAttribs;
|
||||
const expectedAttributes = testObj.expectedLineAttribs;
|
||||
const recievedText = new Array(result.lines);
|
||||
const expectedText = testObj.expectedText;
|
||||
const gotAttributes = result.lineAttribs;
|
||||
const wantAttributes = testObj.wantLineAttribs;
|
||||
const gotText = new Array(result.lines);
|
||||
const wantText = testObj.wantText;
|
||||
|
||||
// Check recieved text matches the expected text
|
||||
if (arraysEqual(recievedText[0], expectedText)) {
|
||||
// console.log("PASS: Recieved Text did match Expected Text\nRecieved:", recievedText[0], "\nExpected:", testObj.expectedText)
|
||||
} else {
|
||||
console.error('FAIL: Recieved Text did not match Expected Text\nRecieved:', recievedText[0], '\nExpected:', testObj.expectedText);
|
||||
throw new Error();
|
||||
}
|
||||
|
||||
// Check recieved attributes matches the expected attributes
|
||||
if (arraysEqual(recievedAttributes, expectedAttributes)) {
|
||||
// console.log("PASS: Recieved Attributes matched Expected Attributes");
|
||||
done();
|
||||
} else {
|
||||
console.error('FAIL', test, testObj.description);
|
||||
console.error('FAIL: Recieved Attributes did not match Expected Attributes\nRecieved: ', recievedAttributes, '\nExpected: ', expectedAttributes);
|
||||
console.error('FAILING HTML', testObj.html);
|
||||
throw new Error();
|
||||
}
|
||||
assert.deepEqual(gotText[0], wantText);
|
||||
assert.deepEqual(gotAttributes, wantAttributes);
|
||||
});
|
||||
});
|
||||
}
|
||||
|
@ -325,7 +310,7 @@ describe(__filename, function () {
|
|||
function arraysEqual(a, b) {
|
||||
if (a === b) return true;
|
||||
if (a == null || b == null) return false;
|
||||
if (a.length != b.length) return false;
|
||||
if (a.length !== b.length) return false;
|
||||
|
||||
// If you don't care about the order of the elements inside
|
||||
// the array, you should sort both arrays here.
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue