Last active
May 29, 2021 09:53
-
-
Save therohk/664fe94755dab40edd2b76046fee5818 to your computer and use it in GitHub Desktop.
Code for conversion of Tree of Life from xml source to csv dataset using jsoup
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
public static void main(String[] args) { | |
DataSet linkSet = new DataSet(); | |
linkSet.getHeaders().setHeaders("source_node_id", "target_node_id"); | |
DataSet nodeSet = new DataSet(); | |
nodeSet.getHeaders().setHeaders("node_id", "node_name", "child_nodes", "leaf_node", "tolorg_link", "extinct", "confidence", "phylesis"); | |
try { | |
Connection connection = HttpConnection.connect("http://tolweb.org/"); | |
connection.process("tolskeletaldump.xml", "application/xml"); | |
connection.parser(new Parser(new XmlTreeBuilder())); | |
Document document = connection.response().parse(); | |
Elements elements = document.select("node[id]"); | |
for(Element element : elements) { | |
DataTuple tuple = new DataTuple(); | |
tuple.setRecord("source_node_id", element.parent().parent().attr("id")); | |
tuple.setRecord("target_node_id", element.attr("id")); | |
linkSet.getStore().addTuple(tuple); | |
DataTuple nodeTuple = new DataTuple(); | |
String nodeName = element.getElementsByTag("name").first().ownText(); | |
if(StringUtils.containsAny(nodeName, ',')) | |
nodeName = TextUtils.encloseQuotes(nodeName); | |
if(StringUtils.isAllLowerCase(nodeName)) | |
nodeName = StringUtils.leftSub(nodeName, 1) + StringUtils.snip(nodeName, 1, 0); | |
if(StringUtils.isBlank(nodeName)) | |
nodeName = "none"; | |
nodeTuple.setRecord("node_id", element.attr("id")); | |
nodeTuple.setRecord("node_name", nodeName); | |
nodeTuple.setRecord("child_nodes", element.attr("childcount")); | |
nodeTuple.setRecord("leaf_node", element.attr("leaf")); | |
nodeTuple.setRecord("tolorg_link", element.attr("haspage")); | |
nodeTuple.setRecord("extinct", element.attr("extinct")); | |
nodeTuple.setRecord("confidence", element.attr("confidence")); | |
nodeTuple.setRecord("phylesis", element.attr("phylesis")); | |
nodeSet.getStore().addTuple(nodeTuple); | |
} | |
} catch (IOException e) { | |
e.printStackTrace(); | |
} | |
nodeSet.getStore().updateTuples("tolorg_link", s -> "2".equals(s), s -> "1"); | |
nodeSet.getStore().updateTuples("extinct", s -> "2".equals(s), s -> "1"); | |
linkSet.getConfig().setDelimiter(","); | |
StorageUtils.flushDataSet("treeoflife_links.csv", linkSet); | |
nodeSet.getConfig().setDelimiter(","); | |
StorageUtils.flushDataSet("treeoflife_nodes.csv", nodeSet); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment