Created
April 12, 2016 17:11
-
-
Save avantgardnerio/62bc1678377e527545edd0f04972c1f3 to your computer and use it in GitHub Desktop.
HTML packer in a few lines of scala
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
// TODO: Replace with an off-the-shelf Java HTML packer | |
val doc = Jsoup.parse(html) | |
doc.select("link") // Replace CSS | |
.filter(link => "stylesheet".equalsIgnoreCase(link.attr("rel"))) | |
.filter(link => new URI(link.attr("href")).getHost == null) | |
.foreach(link => { | |
val el = new Element(Tag.valueOf("style"), "") | |
val css = getResourceAsString(new URI(link.attr("href")).getPath) | |
val m = cssUrlPattern.matcher(css) | |
val s = new StringBuffer() | |
while (m.find()) { | |
val ext = FilenameUtils.getExtension(m.group(1)) | |
val writer = new StringWriter() | |
val stream = getClass.getResourceAsStream(m.group(1)) | |
IOUtils.copy(new Base64InputStream(stream, true, 0, Array[Byte]()), writer) | |
stream.close() | |
m.appendReplacement(s, s"url(data:image/$ext;base64,${writer.toString})") | |
} | |
m.appendTail(s) | |
el.appendChild(new DataNode(s.toString, "")) | |
link.replaceWith(el) | |
}) | |
doc.select("script") // Replace JavaScript | |
.filter(script => "".equals(script.attr("type")) || "text/javascript".equalsIgnoreCase(script.attr("type"))) | |
.filter(script => script.attr("src").length > 0) | |
.filter(script => new URI(script.attr("src")).getHost == null) | |
.foreach(script => { | |
val js = getResourceAsString(script.attr("src")) | |
script.removeAttr("src") | |
script.attr("type", "text/javascript") | |
script.appendChild(new DataNode(js, "")) | |
}) | |
doc.select("script") // Replace JSON | |
.filter(script => "application/json".equalsIgnoreCase(script.attr("type"))) | |
.filter(script => script.attr("src").length > 0) | |
.filter(script => new URI(script.attr("src")).getHost == null) | |
.foreach(script => { | |
script.removeAttr("src") | |
script.appendChild(new DataNode(data, "")) | |
}) | |
html = doc.toString |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment