Last active
April 10, 2017 08:05
-
-
Save matsumonkie/90c079d2ee5798ea7f03 to your computer and use it in GitHub Desktop.
gd-to-html.js
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
function ConvertGoogleDocToCleanHtml() { | |
var body = DocumentApp.getActiveDocument()//.getBody(); | |
var numChildren = body.getNumChildren(); | |
var output = []; | |
var images = []; | |
var listCounters = {}; | |
var toc = {} | |
for (var i = 0; i < numChildren; i++) { | |
var p = body.getChild(i); | |
if (p.getType() == DocumentApp.ElementType.TABLE_OF_CONTENTS) { | |
var contents = p.asTableOfContents(); | |
for (var j = 0; j < contents.getNumChildren(); j++) { // looping over each ToC item | |
var itemToc = contents.getChild(j).asParagraph().getChild(0).asText(); | |
var itemText = itemToc.getText(); | |
var itemUrl = itemToc.getLinkUrl(); | |
toc[itemText] = itemUrl; | |
Logger.log("[" + itemText + "] -> " + itemUrl); | |
} | |
} else { | |
output.push(processItem(toc, p, listCounters, images)); | |
} | |
} | |
var html = output.join('\r'); | |
emailHtml(html, images); | |
} | |
function emailHtml(html, images) { | |
var attachments = []; | |
for (var j=0; j<images.length; j++) { | |
attachments.push( { | |
"fileName": images[j].name, | |
"mimeType": images[j].type, | |
"content": images[j].blob.getBytes() } ); | |
} | |
var inlineImages = {}; | |
for (var j=0; j<images.length; j++) { | |
inlineImages[[images[j].name]] = images[j].blob; | |
} | |
var name = DocumentApp.getActiveDocument().getName()+".html"; | |
attachments.push({"fileName":name, "mimeType": "text/html", "content": html}); | |
MailApp.sendEmail({ | |
to: Session.getActiveUser().getEmail(), | |
subject: name, | |
//htmlBody: html, | |
inlineImages: inlineImages, | |
attachments: attachments | |
}); | |
} | |
function processItem(toc, item, listCounters, images) { | |
var output = []; | |
var prefix = "", suffix = ""; | |
if (item.getType() == DocumentApp.ElementType.PARAGRAPH) { | |
switch (item.getHeading()) { | |
case DocumentApp.ParagraphHeading.HEADING6: | |
title = item.getChild(0).getText().trim(); | |
prefix = '<h6 name="' + toc[title] + '">'; | |
suffix = "</h6>"; | |
break; | |
case DocumentApp.ParagraphHeading.HEADING5: | |
title = item.getChild(0).getText().trim(); | |
prefix = '<h5 name="' + toc[title] + '">'; | |
suffix = "</h5>"; | |
break; | |
case DocumentApp.ParagraphHeading.HEADING4: | |
title = item.getChild(0).getText().trim(); | |
prefix = '<h4 name="' + toc[title] + '">'; | |
suffix = "</h4>"; | |
break; | |
case DocumentApp.ParagraphHeading.HEADING3: | |
title = item.getChild(0).getText().trim(); | |
prefix = '<h3 name="' + toc[title] + '">'; | |
suffix = "</h3>"; | |
break; | |
case DocumentApp.ParagraphHeading.HEADING2: | |
title = item.getChild(0).getText().trim(); | |
prefix = '<h2 name="' + toc[title] + '">'; | |
suffix = "</h2>"; | |
break; | |
case DocumentApp.ParagraphHeading.HEADING1: | |
Logger.log(item.getChild(0)) | |
title = item.getChild(0).getText().trim(); | |
prefix = '<h1 name="' + toc[title] + '">'; | |
suffix = "</h1>"; | |
break; | |
default: | |
prefix = "<p>", suffix = "</p>"; | |
} | |
if (item.getNumChildren() == 0) | |
return ""; | |
} | |
else if (item.getType() == DocumentApp.ElementType.INLINE_IMAGE) | |
{ | |
processImage(item, images, output); | |
} | |
else if (item.getType() === DocumentApp.ElementType.LIST_ITEM) { | |
var listItem = item; | |
var gt = listItem.getGlyphType(); | |
var key = listItem.getListId() + '.' + listItem.getNestingLevel(); | |
var counter = listCounters[key] || 0; | |
// First list item | |
if ( counter == 0 ) { | |
// Bullet list (<ul>): | |
if (gt === DocumentApp.GlyphType.BULLET | |
|| gt === DocumentApp.GlyphType.HOLLOW_BULLET | |
|| gt === DocumentApp.GlyphType.SQUARE_BULLET) { | |
prefix = '<ul><li>'; | |
suffix = "</li>"; | |
} else { | |
// Ordered list (<ol>): | |
prefix = "<ol><li>"; | |
suffix = "</li>"; | |
} | |
} | |
else { | |
prefix = "<li>"; | |
suffix = "</li>"; | |
} | |
if (item.isAtDocumentEnd() || item.getNextSibling().getType() != DocumentApp.ElementType.LIST_ITEM) { | |
if (gt === DocumentApp.GlyphType.BULLET | |
|| gt === DocumentApp.GlyphType.HOLLOW_BULLET | |
|| gt === DocumentApp.GlyphType.SQUARE_BULLET) { | |
suffix += "</ul>"; | |
} | |
else { | |
// Ordered list (<ol>): | |
suffix += "</ol>"; | |
} | |
} | |
counter++; | |
listCounters[key] = counter; | |
} | |
output.push(prefix); | |
if (item.getType() == DocumentApp.ElementType.TEXT) { | |
processText(item, output); | |
} | |
else { | |
if (item.getNumChildren) { | |
var numChildren = item.getNumChildren(); | |
// Walk through all the child elements of the doc. | |
for (var i = 0; i < numChildren; i++) { | |
var child = item.getChild(i); | |
output.push(processItem(toc, child, listCounters, images)); | |
} | |
} | |
} | |
output.push(suffix); | |
return output.join(''); | |
} | |
function processText(item, output) { | |
var text = item.getText(); | |
var indices = item.getTextAttributeIndices(); | |
if (indices.length <= 1) { | |
var partAtts = item.getAttributes(indices[0]); | |
// Assuming that a whole para fully italic is a quote | |
if(item.isBold()) { | |
output.push('<b>' + text + '</b>'); | |
} | |
else if(item.isItalic()) { | |
output.push('<blockquote>' + text + '</blockquote>'); | |
} | |
else if (text.trim().indexOf('http://') > -1) { | |
output.push('<a href="' + text + '" rel="nofollow">' + text + '</a>'); | |
} | |
else { | |
output.push(text); | |
} | |
} | |
else { | |
for (var i=0; i < indices.length; i ++) { | |
var partAtts = item.getAttributes(indices[i]); | |
var startPos = indices[i]; | |
var endPos = i+1 < indices.length ? indices[i+1]: text.length; | |
var partText = text.substring(startPos, endPos); | |
if (partAtts.ITALIC) { | |
output.push('<i>'); | |
} | |
if (partAtts.BOLD) { | |
output.push('<b>'); | |
} | |
if (partAtts.UNDERLINE) { | |
output.push('<u>'); | |
} | |
if (partAtts.LINK_URL) { | |
url = "" | |
if (partAtts.LINK_URL.substring(0, 9) == "#heading=") { | |
prefix = "/d/#/guides/content/"; | |
suffix = partAtts.LINK_URL.substring(1); // remove '#' | |
url = prefix + suffix; | |
} else { | |
url = partAtts.LINK_URL; | |
} | |
output.push('<a href="' + url + '">') | |
} | |
output.push(partText); | |
if (partAtts.ITALIC) { | |
output.push('</i>'); | |
} | |
if (partAtts.BOLD) { | |
output.push('</b>'); | |
} | |
if (partAtts.UNDERLINE) { | |
output.push('</u>'); | |
} | |
if (partAtts.LINK_URL) { | |
output.push('</a>') | |
} | |
} | |
} | |
} | |
function processImage(item, images, output) | |
{ | |
images = images || []; | |
var blob = item.getBlob(); | |
var contentType = blob.getContentType(); | |
var extension = ""; | |
if (/\/png$/.test(contentType)) { | |
extension = ".png"; | |
} else if (/\/gif$/.test(contentType)) { | |
extension = ".gif"; | |
} else if (/\/jpe?g$/.test(contentType)) { | |
extension = ".jpg"; | |
} else { | |
throw "Unsupported image type: "+contentType; | |
} | |
var imagePrefix = "Image_"; | |
var imageCounter = images.length; | |
var name = imagePrefix + imageCounter + extension; | |
imageCounter++; | |
output.push('<img src="cid:'+name+'" />'); | |
images.push( { | |
"blob": blob, | |
"type": contentType, | |
"name": name}); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment