Created
February 4, 2015 04:59
-
-
Save pdlug/ec2c6eef8fc51f6b6e40 to your computer and use it in GitHub Desktop.
Demo of parsing JATS XML using `clojure.data.zip.xml` to extract contributors.
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
(ns jats.contribs | |
(:require [clojure.java.io :as io] | |
[clojure.zip :as zip] | |
[clojure.data.xml :as xml] | |
[clojure.data.zip.xml :as zx] | |
[clojure.pprint :as pprint]) | |
(:gen-class :main true)) | |
(defn contrib-name [name] | |
(let [first-name (zx/xml1-> name :given-names zx/text) | |
surname (zx/xml1-> name :surname zx/text)] | |
{:first-name first-name | |
:surname surname})) | |
(defn contrib [contrib] | |
{:name (zx/xml1-> contrib :name contrib-name) | |
:type (zx/xml1-> contrib (zx/attr :contrib-type)) | |
:role (zx/xml1-> contrib :role zx/text) | |
:orcid (zx/xml1-> contrib :contrib-id (zx/attr= :contrib-id-type "orcid") zx/text)}) | |
(defn contributors [data] | |
(zx/xml-> data :front :article-meta :contrib-group :contrib contrib)) | |
(defn parse [filename] | |
(with-open [input-xml (java.io.FileInputStream. filename)] | |
(let [doc (-> input-xml xml/parse zip/xml-zip)] | |
(pprint/pprint (contributors doc))))) | |
(defn -main | |
[& args] | |
(parse (first args))) |
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
Output of parsing a file from the eLife JATS XML repository: | |
% lein run -m jats.contribs ~/tmp/elife-articles/elife04193.xml | |
({:name {:first-name "Haidun", :surname "Yan"}, | |
:type "author", | |
:role nil, | |
:orcid nil} | |
{:name {:first-name "Juan L", :surname "Pablo"}, | |
:type "author", | |
:role nil, | |
:orcid nil} | |
{:name {:first-name "Chaojian", :surname "Wang"}, | |
:type "author", | |
:role nil, | |
:orcid nil} | |
{:name {:first-name "Geoffrey S", :surname "Pitt"}, | |
:type "author", | |
:role nil, | |
:orcid "http://orcid.org/0000-0003-2246-0289"} | |
{:name {:first-name "Gary L", :surname "Westbrook"}, | |
:type "editor", | |
:role "Reviewing editor", | |
:orcid nil}) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment