Skip to content

Commit

Permalink
merged several changes submitted by @edbacher
Browse files Browse the repository at this point in the history
  • Loading branch information
@mangini
mangini committed Oct 9, 2013
1 parent c2139cf commit 7637168
Showing 1 changed file with 71 additions and 17 deletions.
88 changes: 71 additions & 17 deletions converttomarkdown.gapps
View file
@@ -1,19 +1,40 @@
/*
Usage:
Adding this script to your doc:
- Tools > Script Manager > New
- Select "Blank Project", then paste this code in and save.
Running the script:
- Tools > Script Manager
- Select "ConvertToMarkdown" function.
- Click Run button.
- Converted doc will be mailed to you. Subject will be "[MARKDOWN_MAKER]...".
*/

function ConvertToMarkdown() {
var numChildren = DocumentApp.getActiveDocument().getActiveSection().getNumChildren();
var text = "";
var inSrc = false;
var inClass = false;
var globalImageCounter = 0;
var globalListCounters = {};
// edbacher: added a variable for indent in src <pre> block. Let style sheet do margin.
var srcIndent = "";

var attachments = [];

for (var i=0; i<numChildren; i++) {
// Walk through all the child elements of the doc.
for (var i = 0; i < numChildren; i++) {
var child = DocumentApp.getActiveDocument().getActiveSection().getChild(i);
var result = processParagraph(i, child, inSrc, globalImageCounter, globalListCounters);
globalImageCounter += (result && result.images) ? result.images.length : 0;
if (result!==null) {
if (result.source==="start" && !inSrc) {
if (result.sourcePretty==="start" && !inSrc) {
inSrc=true;
text+="<pre class=\"prettyprint\">\n";
} else if (result.sourcePretty==="end" && inSrc) {
inSrc=false;
text+="</pre>\n\n";
} else if (result.source==="start" && !inSrc) {
inSrc=true;
text+="<pre>\n";
} else if (result.source==="end" && inSrc) {
Expand All @@ -28,7 +49,7 @@ function ConvertToMarkdown() {
} else if (inClass) {
text+=result.text+"\n\n";
} else if (inSrc) {
text+=(" "+escapeHTML(result.text)+"\n");
text+=(srcIndent+escapeHTML(result.text)+"\n");
} else if (result.text && result.text.length>0) {
text+=result.text+"\n\n";
}
Expand All @@ -52,33 +73,55 @@ function ConvertToMarkdown() {
MailApp.sendEmail(Session.getActiveUser().getEmail(),
"[MARKDOWN_MAKER] "+DocumentApp.getActiveDocument().getName(),
"Your converted markdown document is attached (converted from "+DocumentApp.getActiveDocument().getUrl()+")"+
"\n\nDon't know how to use the format options? See http://github.com/mangini/gdocs2md#readme\n",
"\n\nDon't know how to use the format options? See http://github.com/mangini/gdocs2md\n",
{ "attachments": attachments });
}

function escapeHTML(text) {
return text.replace(/</g, '&lt;').replace(/>/g, '&gt;');
}

// Process each child element (not just paragraphs).
function processParagraph(index, element, inSrc, imageCounter, listCounters) {
// First, check for things that require no processing.
if (element.getNumChildren()==0) {
return null;
}

}
// Punt on TOC.
if (element.getType() === DocumentApp.ElementType.TABLE_OF_CONTENTS) {
return {"text": "[[TOC]]"};
}

// Set up for real results.
var result = {};

var pOut = "";
var textElements = [];
var imagePrefix = "image_";

for (var i=0; i<element.getNumChildren(); i++) {
// Handle Table elements. Pretty simple-minded now, but works for simple tables.
// Note that Markdown does not process within block-level HTML, so it probably
// doesn't make sense to add markup within tables.
if (element.getType() === DocumentApp.ElementType.TABLE) {
textElements.push("<table>\n");
var nCols = element.getChild(0).getNumCells();
for (var i = 0; i < element.getNumChildren(); i++) {
textElements.push(" <tr>\n");
// process this row
for (var j = 0; j < nCols; j++) {
textElements.push(" <td>" + element.getChild(i).getChild(j).getText() + "</td>\n");
}
textElements.push(" </tr>\n");
}
textElements.push("</table>\n");
}

// Process various types (ElementType).
for (var i = 0; i < element.getNumChildren(); i++) {
var t=element.getChild(i).getType();
if (t === DocumentApp.ElementType.TEXT || t === DocumentApp.ElementType.TABLE_ROW) {
// TODO: proper handling of table_row

if (t === DocumentApp.ElementType.TABLE_ROW) {
// do nothing: already handled TABLE_ROW
} else if (t === DocumentApp.ElementType.TEXT) {
var txt=element.getChild(i);
pOut += txt.getText();
textElements.push(txt);
Expand Down Expand Up @@ -109,23 +152,28 @@ function processParagraph(index, element, inSrc, imageCounter, listCounters) {
} else if (t === DocumentApp.ElementType.FOOTNOTE) {
textElements.push(' (NOTE: '+element.getChild(i).getFootnoteContents().getText()+')');
} else {
throw "Paragraph "+index+" of type "+element.getType()+" has an unsupported child: "+t+" "+(element.getChild(i)["getText"] ? element.getChild(i).getText():'')+" index="+index;
throw "Paragraph "+index+" of type "+element.getType()+" has an unsupported child: "
+t+" "+(element.getChild(i)["getText"] ? element.getChild(i).getText():'')+" index="+index;
}
}

if (textElements.length==0) {
// Isn't result empty now?
return result;
}


// evb: Add source pretty too. (And abbreviations: src and srcp.)
// process source code block:
if (/^\s*---\s+source code\s*$/.test(pOut)) {
if (/^\s*---\s+srcp\s*$/.test(pOut) || /^\s*---\s+source pretty\s*$/.test(pOut)) {
result.sourcePretty = "start";
} else if (/^\s*---\s+src\s*$/.test(pOut) || /^\s*---\s+source code\s*$/.test(pOut)) {
result.source = "start";
} else if (/^\s*---\s+class\s+([^ ]+)\s*$/.test(pOut)) {
result.inClass = "start";
result.className = RegExp.$1;
} else if (/^\s*---\s*$/.test(pOut)) {
result.source = "end";
result.sourcePretty = "end";
result.inClass = "end";
} else if (/^\s*---\s+jsperf\s*([^ ]+)\s*$/.test(pOut)) {
result.text = '<iframe style="width: 100%; height: 340px; overflow: hidden; border: 0;" '+
Expand All @@ -149,12 +197,14 @@ function processParagraph(index, element, inSrc, imageCounter, listCounters) {
return result;
}

// Add correct prefix to list items.
function findPrefix(inSrc, element, listCounters) {
var prefix="";
if (!inSrc) {
if (element.getType()===DocumentApp.ElementType.PARAGRAPH) {
var paragraphObj = element;
switch (paragraphObj.getHeading()) {
// Add a # for each heading level. No break, so we accumulate the right number.
case DocumentApp.ParagraphHeading.HEADING6: prefix+="#";
case DocumentApp.ParagraphHeading.HEADING5: prefix+="#";
case DocumentApp.ParagraphHeading.HEADING4: prefix+="#";
Expand All @@ -170,10 +220,13 @@ function findPrefix(inSrc, element, listCounters) {
prefix += " ";
}
var gt = listItem.getGlyphType();
if (gt === DocumentApp.GlyphType.BULLET || gt === DocumentApp.GlyphType.HOLLOW_BULLET ||
gt === DocumentApp.GlyphType.SQUARE_BULLET) {
// Bullet list (<ul>):
if (gt === DocumentApp.GlyphType.BULLET
|| gt === DocumentApp.GlyphType.HOLLOW_BULLET
|| gt === DocumentApp.GlyphType.SQUARE_BULLET) {
prefix += "* ";
} else {
// Ordered list (<ol>):
var key = listItem.getListId() + '.' + listItem.getNestingLevel();
var counter = listCounters[key] || 0;
counter++;
Expand All @@ -197,7 +250,7 @@ function processTextElement(inSrc, txt) {

var attrs=txt.getTextAttributeIndices();
var lastOff=pOut.length;

for (var i=attrs.length-1; i>=0; i--) {
var off=attrs[i];
var url=txt.getLinkUrl(off);
Expand All @@ -223,7 +276,8 @@ function processTextElement(inSrc, txt) {
if (txt.isBold(off)) {
var d1 = d2 = "**";
if (txt.isItalic(off)) {
d1 = "** *"; d2 = "* **";
// edbacher: changed this to handle bold italic properly.
d1 = "**_"; d2 = "_**";
}
pOut=pOut.substring(0, off)+d1+pOut.substring(off, lastOff)+d2+pOut.substring(lastOff);
} else if (txt.isItalic(off)) {
Expand Down

0 comments on commit 7637168

Please sign in to comment.