diff --git a/src/node/utils/ExportHtml.js b/src/node/utils/ExportHtml.js
index e6bfef37f..d885c6824 100644
--- a/src/node/utils/ExportHtml.js
+++ b/src/node/utils/ExportHtml.js
@@ -1,3 +1,5 @@
+'use strict';
+
/**
* Copyright 2009 Google Inc.
*
@@ -15,572 +17,514 @@
*/
-var async = require("async");
-var Changeset = require("ep_etherpad-lite/static/js/Changeset");
-var padManager = require("../db/PadManager");
-var ERR = require("async-stacktrace");
+var async = require('async');
+var Changeset = require('ep_etherpad-lite/static/js/Changeset');
+var padManager = require('../db/PadManager');
+var eRR = require('async-stacktrace');
var _ = require('underscore');
var Security = require('ep_etherpad-lite/static/js/security');
var hooks = require('ep_etherpad-lite/static/js/pluginfw/hooks');
var eejs = require('ep_etherpad-lite/node/eejs');
var _analyzeLine = require('./ExportHelper')._analyzeLine;
var _encodeWhitespace = require('./ExportHelper')._encodeWhitespace;
+// copied from ACE
+var _REGEX_WORDCHAR = /[\u0030-\u0039\u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u1FFF\u3040-\u9FFF\uF900-\uFDFF\uFE70-\uFEFE\uFF10-\uFF19\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFDC]/;
+var _REGEX_URLCHAR = new RegExp('(' + (/[-:@a-zA-Z0-9_.,~%+/\\?=&#;()$]/).source + '|' + _REGEX_WORDCHAR.source + ')');
+var _REGEX_URL = new RegExp(/(?:(?:https?|s?ftp|ftps|file|smb|afp|nfs|(x-)?man|gopher|txmt):\/\/|mailto:)/.source + _REGEX_URLCHAR.source + '*(?![:.,;])' + _REGEX_URLCHAR.source, 'g');
-function getPadHTML(pad, revNum, callback)
-{
- var atext = pad.atext;
- var html;
- async.waterfall([
- // fetch revision atext
- function (callback)
- {
- if (revNum != undefined)
- {
- pad.getInternalRevisionAText(revNum, function (err, revisionAtext)
- {
- if(ERR(err, callback)) return;
- atext = revisionAtext;
- callback();
- });
+// returns null if no URLs, or [[startIndex1, url1], [startIndex2, url2], ...]
+// copied from ACE
+function _processSpaces (s) {
+ var doesWrap = true;
+ if (s.indexOf('<') < 0 && !doesWrap) {
+ // short-cut
+ return s.replace(/ /g, ' ');
}
- else
- {
- callback(null);
+ var parts = [];
+ s.replace(/<[^>]*>?| |[^ <]+/g, function (m) {
+ parts.push(m);
+ });
+ if (doesWrap) {
+ var endOfLine = true;
+ var beforeSpace = false;
+ // last space in a run is normal, others are nbsp,
+ // end of line is nbsp
+ for (var i = parts.length - 1; i >= 0; i--) {
+ var p = parts[i];
+ if (p === ' ') {
+ if (endOfLine || beforeSpace) parts[i] = ' ';
+ endOfLine = false;
+ beforeSpace = true;
+ } else if (p.charAt(0) !== '<') {
+ endOfLine = false;
+ beforeSpace = false;
+ }
+ }
+ // beginning of line is nbsp
+ for (i = 0; i < parts.length; i++) {
+ p = parts[i];
+ if (p === ' ') {
+ parts[i] = ' ';
+ break;
+ } else if (p.charAt(0) !== '<') {
+ break;
+ }
+ }
+ } else {
+ for (i = 0; i < parts.length; i++) {
+ p = parts[i];
+ if (p === ' ') {
+ parts[i] = ' ';
+ }
+ }
}
- },
- // convert atext to html
-
-
- function (callback)
- {
- html = getHTMLFromAtext(pad, atext);
- callback(null);
- }],
- // run final callback
-
-
- function (err)
- {
- if(ERR(err, callback)) return;
- callback(null, html);
- });
+ return parts.join('');
}
-exports.getPadHTML = getPadHTML;
-exports.getHTMLFromAtext = getHTMLFromAtext;
+function _findURLs (text) {
+ _REGEX_URL.lastIndex = 0;
+ var urls = null;
+ var execResult;
+ while (execResult = _REGEX_URL.exec(text)) {
+ urls = urls || [];
+ var startIndex = execResult.index;
+ var url = execResult[0];
+ urls.push([startIndex, url]);
+ }
-function getHTMLFromAtext(pad, atext, authorColors)
-{
- var apool = pad.apool();
- var textLines = atext.text.slice(0, -1).split('\n');
- var attribLines = Changeset.splitAttributionLines(atext.attribs, atext.text);
+ return urls;
+}
- var tags = ['h1', 'h2', 'strong', 'em', 'u', 's'];
- var props = ['heading1', 'heading2', 'bold', 'italic', 'underline', 'strikethrough'];
+/**
+ * Return docx from input html
+ *
+ * @param {text} [pad] text
+ * @param {text} [atext] text
+ * @param {text} [authorColors] text
+ *
+ * @returns {html} html
+ *
+ * @public
+ */
+function getHTMLFromAtext (pad, atext, authorColors) {
+ var apool = pad.apool();
+ var textLines = atext.text.slice(0, -1).split('\n');
+ var attribLines = Changeset.splitAttributionLines(atext.attribs, atext.text);
- // prepare tags stored as ['tag', true] to be exported
- hooks.aCallAll("exportHtmlAdditionalTags", pad, function(err, newProps){
- newProps.forEach(function (propName, i){
- tags.push(propName);
- props.push(propName);
+ var tags = ['h1', 'h2', 'strong', 'em', 'u', 's'];
+ var props = ['heading1', 'heading2', 'bold', 'italic', 'underline', 'strikethrough'];
+
+ // prepare tags stored as ['tag', true] to be exported
+ hooks.aCallAll('exportHtmlAdditionalTags', pad, function (err, newProps) {
+ if (err) {
+ return err;
+ }
+ newProps.forEach(function (propName) {
+ tags.push(propName);
+ props.push(propName);
+ });
});
- });
- // prepare tags stored as ['tag', 'value'] to be exported. This will generate HTML
- // with tags like
- hooks.aCallAll("exportHtmlAdditionalTagsWithData", pad, function(err, newProps){
- newProps.forEach(function (propName, i){
- tags.push('span data-' + propName[0] + '="' + propName[1] + '"');
- props.push(propName);
+ // prepare tags stored as ['tag', 'value'] to be exported. This will generate HTML
+ // with tags like
+ hooks.aCallAll('exportHtmlAdditionalTagsWithData', pad, function (err, newProps) {
+ if (err) {
+ return err;
+ }
+ newProps.forEach(function (propName) {
+ tags.push('span data-' + propName[0] + '="' + propName[1] + '"');
+ props.push(propName);
+ });
});
- });
- // holds a map of used styling attributes (*1, *2, etc) in the apool
- // and maps them to an index in props
- // *3:2 -> the attribute *3 means strong
- // *2:5 -> the attribute *2 means s(trikethrough)
- var anumMap = {};
- var css = "";
+ // holds a map of used styling attributes (*1, *2, etc) in the apool
+ // and maps them to an index in props
+ // *3:2 -> the attribute *3 means strong
+ // *2:5 -> the attribute *2 means s(trikethrough)
+ var anumMap = {};
+ var css = '';
- var stripDotFromAuthorID = function(id){
- return id.replace(/\./g,'_');
- };
+ var stripDotFromAuthorID = function (id) {
+ return id.replace(/\./g, '_');
+ };
- if(authorColors){
- css+="';
}
- css+="";
- }
+ // iterates over all props(h1,h2,strong,...), checks if it is used in
+ // this pad, and if yes puts its attrib id->props value into anumMap
+ props.forEach(function (propName, i) {
+ var attrib = [propName, true];
+ if (_.isArray(propName)) {
+ // propName can be in the form of ['color', 'red'],
+ // see hook exportHtmlAdditionalTagsWithData
+ attrib = propName;
+ }
+ var propTrueNum = apool.putAttrib(attrib, true);
+ if (propTrueNum >= 0) {
+ anumMap[propTrueNum] = i;
+ }
+ });
- // iterates over all props(h1,h2,strong,...), checks if it is used in
- // this pad, and if yes puts its attrib id->props value into anumMap
- props.forEach(function (propName, i)
- {
- var attrib = [propName, true];
- if (_.isArray(propName)) {
- // propName can be in the form of ['color', 'red'],
- // see hook exportHtmlAdditionalTagsWithData
- attrib = propName;
- }
- var propTrueNum = apool.putAttrib(attrib, true);
- if (propTrueNum >= 0)
- {
- anumMap[propTrueNum] = i;
- }
- });
-
- function getLineHTML(text, attribs)
- {
+ function getLineHTML (text, attribs) {
// Use order of tags (b/i/u) as order of nesting, for simplicity
// and decent nesting. For example,
// Just bold Bold and italics Just italics
// becomes
// Just bold Bold and italics Just italics
- var taker = Changeset.stringIterator(text);
- var assem = Changeset.stringAssembler();
- var openTags = [];
+ var taker = Changeset.stringIterator(text);
+ var assem = Changeset.stringAssembler();
+ var openTags = [];
- function getSpanClassFor(i){
- //return if author colors are disabled
- if (!authorColors) return false;
+ function getSpanClassFor (i) {
+ //return if author colors are disabled
+ if (!authorColors) return false;
- var property = props[i];
+ var property = props[i];
- // we are not insterested on properties in the form of ['color', 'red'],
- // see hook exportHtmlAdditionalTagsWithData
- if (_.isArray(property)) {
- return false;
- }
+ // we are not insterested on properties in the form of ['color', 'red'],
+ // see hook exportHtmlAdditionalTagsWithData
+ if (_.isArray(property)) {
+ return false;
+ }
- if(property.substr(0,6) === "author"){
- return stripDotFromAuthorID(property);
- }
+ if (property.substr(0, 6) === 'author') {
+ return stripDotFromAuthorID(property);
+ }
- if(property === "removed"){
- return "removed";
- }
+ if (property === 'removed') {
+ return 'removed';
+ }
- return false;
+ return false;
+ }
+
+ // tags added by exportHtmlAdditionalTagsWithData will be exported as with
+ // data attributes
+ function isSpanWithData (i) {
+ var property = props[i];
+
+ return _.isArray(property);
+ }
+
+ function emitOpenTag (i) {
+ openTags.unshift(i);
+ var spanClass = getSpanClassFor(i);
+
+ if (spanClass) {
+ assem.append('');
+ } else {
+ assem.append('<');
+ assem.append(tags[i]);
+ assem.append('>');
+ }
+ }
+
+ // this closes an open tag and removes its reference from openTags
+ function emitCloseTag (i) {
+ openTags.shift();
+ var spanClass = getSpanClassFor(i);
+ var spanWithData = isSpanWithData(i);
+
+ if (spanClass || spanWithData) {
+ assem.append('');
+ } else {
+ assem.append('');
+ }
+ }
+
+ var urls = _findURLs(text);
+
+ var idx = 0;
+
+ function processNextChars (numChars) {
+ if (numChars <= 0) {
+ return;
+ }
+
+ var iter = Changeset.opIterator(Changeset.subattribution(attribs, idx, idx + numChars));
+ idx += numChars;
+
+ // this iterates over every op string and decides which tags to open or to close
+ // based on the attribs used
+ while (iter.hasNext()) {
+ var o = iter.next();
+ var usedAttribs = [];
+
+ // mark all attribs as used
+ Changeset.eachAttribNumber(o.attribs, function (a) {
+ if (a in anumMap) {
+ usedAttribs.push(anumMap[a]); // i = 0 => bold, etc.
+ }
+ });
+ var outermostTag = -1;
+ // find the outer most open tag that is no longer used
+ for (var i = openTags.length - 1; i >= 0; i--) {
+ if (usedAttribs.indexOf(openTags[i]) === -1) {
+ outermostTag = i;
+ break;
+ }
+ }
+
+ // close all tags upto the outer most
+ if (outermostTag !== -1) {
+ while (outermostTag >= 0) {
+ emitCloseTag(openTags[0]);
+ outermostTag--;
+ }
+ }
+
+ // open all tags that are used but not open
+ for (i = 0; i < usedAttribs.length; i++) {
+ if (openTags.indexOf(usedAttribs[i]) === -1) {
+ emitOpenTag(usedAttribs[i]);
+ }
+ }
+
+ var chars = o.chars;
+ if (o.lines) {
+ chars--; // exclude newline at end of line, if present
+ }
+
+ var s = taker.take(chars);
+
+ //removes the characters with the code 12. Don't know where they come
+ //from but they break the abiword parser and are completly useless
+ s = s.replace(String.fromCharCode(12), '');
+
+ assem.append(_encodeWhitespace(Security.escapeHTML(s)));
+ } // end iteration over spans in line
+
+ // close all the tags that are open after the last op
+ while (openTags.length > 0) {
+ emitCloseTag(openTags[0]);
+ }
+ } // end processNextChars
+
+ if (urls) {
+ urls.forEach(function (urlData) {
+ var startIndex = urlData[0];
+ var url = urlData[1];
+ var urlLength = url.length;
+ processNextChars(startIndex - idx);
+ assem.append('');
+ processNextChars(urlLength);
+ assem.append('');
+ });
+ }
+
+ processNextChars(text.length - idx);
+
+ return _processSpaces(assem.toString());
+ } // end getLineHTML
+
+ var pieces = [css];
+
+ // Need to deal with constraints imposed on HTML lists; can
+ // only gain one level of nesting at once, can't change type
+ // mid-list, etc.
+ // People might use weird indenting, e.g. skip a level,
+ // so we want to do something reasonable there. We also
+ // want to deal gracefully with blank lines.
+ // => keeps track of the parents level of indentation
+ var lists = []; // e.g. [[1,'bullet'], [3,'bullet'], ...]
+ var listLevels = [];
+ for (var i = 0; i < textLines.length; i++) {
+ var context;
+ var line = _analyzeLine(textLines[i], attribLines[i], apool);
+ var lineContent = getLineHTML(line.text, line.aline);
+ listLevels.push(line.listLevel);
+
+ if (line.listLevel) { //If we are inside a list
+ // do list stuff
+ var whichList = -1; // index into lists or -1
+ if (line.listLevel) {
+ whichList = lists.length;
+ for (var j = lists.length - 1; j >= 0; j--) {
+ if (line.listLevel <= lists[j][0]) {
+ whichList = j;
+ }
+ }
+ }
+ context = {
+ line: line,
+ lineContent: lineContent,
+ apool: apool,
+ attribLine: attribLines[i],
+ text: textLines[i],
+ padId: pad.id
+ };
+ hooks.callAll('getLineHTMLForExport', context);
+ if (whichList >= lists.length) {
+ if (lists.length > 0) {
+ pieces.push('');
+ }
+ lists.push([line.listLevel, line.listTypeName]);
+
+ // if there is a previous list we need to open x tags, where x is the difference of the levels
+ // if there is no previous list we need to open x tags, where x is the wanted level
+ var toOpen = lists.length > 1 ? line.listLevel - lists[lists.length - 2][0] - 1 : line.listLevel - 1
+
+ if (line.listTypeName === 'number') {
+ if (toOpen > 0) {
+ pieces.push(new Array(toOpen + 1).join('- '));
+ }
+ pieces.push('
- ', context.lineContent || '
');
+ } else {
+ if (toOpen > 0) {
+ pieces.push(new Array(toOpen + 1).join(' - '));
+ }
+ pieces.push('
- ', context.lineContent || '
');
+ }
+ } else { //means we are getting closer to the lowest level of indentation or are at the same level
+ var toClose = lists.length > 0 ? listLevels[listLevels.length - 2] - line.listLevel : 0
+ if (toClose > 0) {
+ pieces.push(' ');
+ if (lists[lists.length - 1][1] === 'number') {
+ pieces.push(new Array(toClose + 1).join('
'));
+ pieces.push('- ', context.lineContent || '
');
+ } else {
+ pieces.push(new Array(toClose + 1).join(' '));
+ pieces.push('- ', context.lineContent || '
');
+ }
+ lists = lists.slice(0, whichList + 1);
+ } else {
+ pieces.push(' - ', context.lineContent || '
');
+ }
+ }
+ } else { //outside any list, need to close line.listLevel of lists
+
+ if (lists.length > 0) {
+ if (lists[lists.length - 1][1] === 'number') {
+ pieces.push('
');
+ pieces.push(new Array(listLevels[listLevels.length - 2]).join(''));
+ } else {
+ pieces.push('');
+ pieces.push(new Array(listLevels[listLevels.length - 2]).join(''));
+ }
+ }
+ lists = [];
+
+ context = {
+ line: line,
+ lineContent: lineContent,
+ apool: apool,
+ attribLine: attribLines[i],
+ text: textLines[i],
+ padId: pad.id
+ };
+
+ hooks.callAll('getLineHTMLForExport', context);
+ pieces.push(context.lineContent, '
');
+ }
}
- // tags added by exportHtmlAdditionalTagsWithData will be exported as with
- // data attributes
- function isSpanWithData(i){
- var property = props[i];
- return _.isArray(property);
- }
-
- function emitOpenTag(i)
- {
- openTags.unshift(i);
- var spanClass = getSpanClassFor(i);
-
- if(spanClass){
- assem.append('');
- } else {
- assem.append('<');
- assem.append(tags[i]);
- assem.append('>');
- }
- }
-
- // this closes an open tag and removes its reference from openTags
- function emitCloseTag(i)
- {
- openTags.shift();
- var spanClass = getSpanClassFor(i);
- var spanWithData = isSpanWithData(i);
-
- if(spanClass || spanWithData){
- assem.append('');
- } else {
- assem.append('');
- }
- }
-
- var urls = _findURLs(text);
-
- var idx = 0;
-
- function processNextChars(numChars)
- {
- if (numChars <= 0)
- {
- return;
- }
-
- var iter = Changeset.opIterator(Changeset.subattribution(attribs, idx, idx + numChars));
- idx += numChars;
-
- // this iterates over every op string and decides which tags to open or to close
- // based on the attribs used
- while (iter.hasNext())
- {
- var o = iter.next();
- var usedAttribs = [];
-
- // mark all attribs as used
- Changeset.eachAttribNumber(o.attribs, function (a)
- {
- if (a in anumMap)
- {
- usedAttribs.push(anumMap[a]); // i = 0 => bold, etc.
- }
- });
- var outermostTag = -1;
- // find the outer most open tag that is no longer used
- for (var i = openTags.length - 1; i >= 0; i--)
- {
- if (usedAttribs.indexOf(openTags[i]) === -1)
- {
- outermostTag = i;
- break;
- }
- }
-
- // close all tags upto the outer most
- if (outermostTag != -1)
- {
- while ( outermostTag >= 0 )
- {
- emitCloseTag(openTags[0]);
- outermostTag--;
- }
- }
-
- // open all tags that are used but not open
- for (i=0; i < usedAttribs.length; i++)
- {
- if (openTags.indexOf(usedAttribs[i]) === -1)
- {
- emitOpenTag(usedAttribs[i])
- }
- }
-
- var chars = o.chars;
- if (o.lines)
- {
- chars--; // exclude newline at end of line, if present
- }
-
- var s = taker.take(chars);
-
- //removes the characters with the code 12. Don't know where they come
- //from but they break the abiword parser and are completly useless
- s = s.replace(String.fromCharCode(12), "");
-
- assem.append(_encodeWhitespace(Security.escapeHTML(s)));
- } // end iteration over spans in line
-
- // close all the tags that are open after the last op
- while (openTags.length > 0)
- {
- emitCloseTag(openTags[0])
- }
- } // end processNextChars
- if (urls)
- {
- urls.forEach(function (urlData)
- {
- var startIndex = urlData[0];
- var url = urlData[1];
- var urlLength = url.length;
- processNextChars(startIndex - idx);
- assem.append('');
- processNextChars(urlLength);
- assem.append('');
- });
- }
- processNextChars(text.length - idx);
-
- return _processSpaces(assem.toString());
- } // end getLineHTML
- var pieces = [css];
-
- // Need to deal with constraints imposed on HTML lists; can
- // only gain one level of nesting at once, can't change type
- // mid-list, etc.
- // People might use weird indenting, e.g. skip a level,
- // so we want to do something reasonable there. We also
- // want to deal gracefully with blank lines.
- // => keeps track of the parents level of indentation
- var lists = []; // e.g. [[1,'bullet'], [3,'bullet'], ...]
- var listLevels = []
- for (var i = 0; i < textLines.length; i++)
- {
- var line = _analyzeLine(textLines[i], attribLines[i], apool);
- var lineContent = getLineHTML(line.text, line.aline);
- listLevels.push(line.listLevel)
-
- if (line.listLevel)//If we are inside a list
- {
- // do list stuff
- var whichList = -1; // index into lists or -1
- if (line.listLevel)
- {
- whichList = lists.length;
- for (var j = lists.length - 1; j >= 0; j--)
- {
- if (line.listLevel <= lists[j][0])
- {
- whichList = j;
- }
- }
- }
- var context = {
- line: line,
- lineContent: lineContent,
- apool: apool,
- attribLine: attribLines[i],
- text: textLines[i],
- padId: pad.id
- }
- hooks.callAll("getLineHTMLForExport", context);
- if (whichList >= lists.length)//means we are on a deeper level of indentation than the previous line
- {
- if(lists.length > 0){
- pieces.push('')
- }
- lists.push([line.listLevel, line.listTypeName]);
-
- // if there is a previous list we need to open x tags, where x is the difference of the levels
- // if there is no previous list we need to open x tags, where x is the wanted level
- var toOpen = lists.length > 1 ? line.listLevel - lists[lists.length - 2][0] - 1 : line.listLevel - 1
-
- if(line.listTypeName == "number")
- {
- if(toOpen > 0){
- pieces.push(new Array(toOpen + 1).join(''))
- }
- pieces.push('- ', context.lineContent || '
');
- }
- else
- {
- if(toOpen > 0){
- pieces.push(new Array(toOpen + 1).join(''))
- }
- pieces.push('- ', context.lineContent || '
');
- }
- }
- //the following code *seems* dead after my patch.
- //I keep it just in case I'm wrong...
- /*else if (whichList == -1)//means we are not inside a list
- {
- if (line.text)
- {
- console.log('trace 1');
- // non-blank line, end all lists
- if(line.listTypeName == "number")
- {
- pieces.push(new Array(lists.length + 1).join('
'));
- }
- else
- {
- pieces.push(new Array(lists.length + 1).join(''));
- }
- lists.length = 0;
- pieces.push(lineContent, '
');
- }
- else
- {
- console.log('trace 2');
- pieces.push('
');
- }
- }*/
- else//means we are getting closer to the lowest level of indentation or are at the same level
- {
- var toClose = lists.length > 0 ? listLevels[listLevels.length - 2] - line.listLevel : 0
- if( toClose > 0){
- pieces.push('')
- if(lists[lists.length - 1][1] == "number")
- {
- pieces.push(new Array(toClose+1).join('
'))
- pieces.push('', context.lineContent || '
');
- }
- else
- {
- pieces.push(new Array(toClose+1).join(''))
- pieces.push('', context.lineContent || '
');
- }
- lists = lists.slice(0,whichList+1)
+ for (var k = lists.length - 1; k >= 0; k--) {
+ if (lists[k][1] === 'number') {
+ pieces.push('');
} else {
- pieces.push('', context.lineContent || '
');
+ pieces.push('');
}
- }
}
- else//outside any list, need to close line.listLevel of lists
- {
- if(lists.length > 0){
- if(lists[lists.length - 1][1] == "number"){
- pieces.push('');
- pieces.push(new Array(listLevels[listLevels.length - 2]).join(''))
- } else {
- pieces.push('');
- pieces.push(new Array(listLevels[listLevels.length - 2]).join(''))
- }
- }
- lists = []
- var context = {
- line: line,
- lineContent: lineContent,
- apool: apool,
- attribLine: attribLines[i],
- text: textLines[i],
- padId: pad.id
- }
-
- hooks.callAll("getLineHTMLForExport", context);
-
- pieces.push(context.lineContent, '
');
- }
- }
-
- for (var k = lists.length - 1; k >= 0; k--)
- {
- if(lists[k][1] == "number")
- {
- pieces.push('');
- }
- else
- {
- pieces.push('');
- }
- }
-
- return pieces.join('');
+ return pieces.join('');
}
-exports.getPadHTMLDocument = function (padId, revNum, callback)
-{
- padManager.getPad(padId, function (err, pad)
- {
- if(ERR(err, callback)) return;
+function getPadHTML (pad, revNum, callback) {
+ var atext = pad.atext;
+ var html;
+ async.waterfall(
+ [
+ // fetch revision atext
+ function (callback) {
+ if (revNum !== undefined) {
+ pad.getInternalRevisionAText(revNum, function (err, revisionAtext) {
+ if (eRR(err, callback)) return;
+ atext = revisionAtext;
- var stylesForExportCSS = "";
- // Include some Styles into the Head for Export
- hooks.aCallAll("stylesForExport", padId, function(err, stylesForExport){
- stylesForExport.forEach(function(css){
- stylesForExportCSS += css;
- });
+ return callback();
+ });
+ } else {
+ return callback(null);
+ }
+ },
- getPadHTML(pad, revNum, function (err, html)
- {
- if(ERR(err, callback)) return;
- var exportedDoc = eejs.require("ep_etherpad-lite/templates/export_html.html", {
- body: html,
- padId: Security.escapeHTML(padId),
- extraCSS: stylesForExportCSS
+ // convert atext to html
+
+
+ function (callback) {
+ html = getHTMLFromAtext(pad, atext);
+ callback(null);
+ }
+ ],
+ // run final callback
+
+
+ function (err) {
+ if (eRR(err, callback)) return;
+ callback(null, html);
+ }
+ );
+}
+
+exports.getPadHTML = getPadHTML;
+exports.getHTMLFromAtext = getHTMLFromAtext;
+exports.getPadHTMLDocument = function (padId, revNum, callback) {
+ padManager.getPad(padId, function (err, pad) {
+ if (eRR(err, callback)) return;
+
+ var stylesForExportCSS = '';
+ // Include some Styles into the Head for Export
+ hooks.aCallAll('stylesForExport', padId, function (err, stylesForExport) {
+ if (eRR(err, callback)) return;
+ stylesForExport.forEach(function (css) {
+ stylesForExportCSS += css;
+ });
+
+ getPadHTML(pad, revNum, function (err, html) {
+ if (eRR(err, callback)) return;
+ var exportedDoc = eejs.require('ep_etherpad-lite/templates/export_html.html', {
+ body: html,
+ padId: Security.escapeHTML(padId),
+ extraCSS: stylesForExportCSS
+ });
+ callback(null, exportedDoc);
+ });
});
- callback(null, exportedDoc);
- });
});
- });
};
-
-// copied from ACE
-var _REGEX_WORDCHAR = /[\u0030-\u0039\u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u1FFF\u3040-\u9FFF\uF900-\uFDFF\uFE70-\uFEFE\uFF10-\uFF19\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFDC]/;
-var _REGEX_SPACE = /\s/;
-var _REGEX_URLCHAR = new RegExp('(' + /[-:@a-zA-Z0-9_.,~%+\/\\?=&#;()$]/.source + '|' + _REGEX_WORDCHAR.source + ')');
-var _REGEX_URL = new RegExp(/(?:(?:https?|s?ftp|ftps|file|smb|afp|nfs|(x-)?man|gopher|txmt):\/\/|mailto:)/.source + _REGEX_URLCHAR.source + '*(?![:.,;])' + _REGEX_URLCHAR.source, 'g');
-
-// returns null if no URLs, or [[startIndex1, url1], [startIndex2, url2], ...]
-
-
-function _findURLs(text)
-{
- _REGEX_URL.lastIndex = 0;
- var urls = null;
- var execResult;
- while ((execResult = _REGEX_URL.exec(text)))
- {
- urls = (urls || []);
- var startIndex = execResult.index;
- var url = execResult[0];
- urls.push([startIndex, url]);
- }
-
- return urls;
-}
-
-
-// copied from ACE
-function _processSpaces(s){
- var doesWrap = true;
- if (s.indexOf("<") < 0 && !doesWrap){
- // short-cut
- return s.replace(/ /g, ' ');
- }
- var parts = [];
- s.replace(/<[^>]*>?| |[^ <]+/g, function (m){
- parts.push(m);
- });
- if (doesWrap){
- var endOfLine = true;
- var beforeSpace = false;
- // last space in a run is normal, others are nbsp,
- // end of line is nbsp
- for (var i = parts.length - 1; i >= 0; i--){
- var p = parts[i];
- if (p == " "){
- if (endOfLine || beforeSpace) parts[i] = ' ';
- endOfLine = false;
- beforeSpace = true;
- }
- else if (p.charAt(0) != "<"){
- endOfLine = false;
- beforeSpace = false;
- }
- }
- // beginning of line is nbsp
- for (i = 0; i < parts.length; i++){
- p = parts[i];
- if (p == " "){
- parts[i] = ' ';
- break;
- }
- else if (p.charAt(0) != "<"){
- break;
- }
- }
- }
- else
- {
- for (i = 0; i < parts.length; i++){
- p = parts[i];
- if (p == " "){
- parts[i] = ' ';
- }
- }
- }
- return parts.join('');
-}