View Category
XML
Parsing

Process an XML document

Given the XML Document:

<shopping>
  <item name="bread" quantity="3" price="2.50"/>
  <item name="milk" quantity="2" price="3.50"/>
</shopping>

Print out the total cost of the items, e.g. $14.50
python
from xml.dom.minidom import parseString
document = parseString(
"""<shopping>
<item name="bread" quantity="3" price="2.50"/>
<item name="milk" quantity="2" price="3.50"/>
</shopping>""").documentElement
total = sum([float(item.getAttribute('price')) *
int(item.getAttribute('quantity'))
for item in document.getElementsByTagName('item')])
print '$%.2f' % total
clojure
(println (format "Total cost of items are $%#.2f"
(->> (xml-seq (parse *xml-input-stream*))
(filter #(= :item (:tag %))) ; Remove all but the item tags
(map :attrs) ; Keep the attributes
(map (fn [e] (str "(* " (:quantity e) " " (:price e) ")"))) ; Get the total price as a sexp
(map read-string) ; "(* quantity price)" -> (* quantity price)
(map eval) ; (* quantity price) -> quantity*price
(apply +)))) ; Sum all elements
erlang
-include_lib("xmerl/include/xmerl.hrl").
-export([get_total/1]).

get_total(ShoppingList) ->
{XmlElt, _} = xmerl_scan:string(ShoppingList),
Items = xmerl_xpath:string("/shopping/item", XmlElt),
Total = lists:foldl(fun(Item, Tot) ->
[#xmlAttribute{value = PriceString}] = xmerl_xpath:string("/item/@price", Item),
{Price, _} = string:to_float(PriceString),
[#xmlAttribute{value = QuantityString}] = xmerl_xpath:string("/item/@quantity", Item),
{Quantity, _} = string:to_integer(QuantityString),
Tot + Price*Quantity
end,
0, Items),
io:format("$~.2f~n", [Total]).
java
// solution uses JAXP and SAX included in Java API since version >= 1.5
class ShoppingContentHandler extends DefaultHandler {
Double priceSum = 0d;
@Override
public void startElement(String uri, String localName, String name,
Attributes attributes) throws SAXException {
if(name.equals("item")) {
String quantityString = attributes.getValue(attributes.getIndex("quantity"));
String priceString = attributes.getValue(attributes.getIndex("price"));
Integer quantity = Integer.parseInt(quantityString);
Double price = Double.parseDouble(priceString);
priceSum += (quantity * price);
}
}
public Double getPriceSum() {
return priceSum;
}
}

SAXParserFactory parserFactory = SAXParserFactory.newInstance();
try {
SAXParser parser = parserFactory.newSAXParser();
XMLReader reader = parser.getXMLReader();
ShoppingContentHandler contentHandler = new ShoppingContentHandler();
reader.setContentHandler(contentHandler);
reader.parse(new InputSource(new FileReader("shopping.xml")));
System.out.printf("$%.2f", contentHandler.getPriceSum());

} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
Creation

create some XML programmatically

Given the following CSV:

bread,3,2.50
milk,2,3.50

Produce the equivalent information in XML, e.g.:

<shopping>
  <item name="bread" quantity="3" price="2.50" />
  <item name="milk" quantity="2" price="3.50" />
</shopping>
python
from xml.dom import minidom

csv = """bread,3,2.50
milk,2,3.50"""

doc = minidom.Document()
shopping = doc.createElement("shopping")

for line in csv.split("\n"):
name, quantity, price = line.split(",")
el = doc.createElement("item")
el.setAttribute("name", name)
el.setAttribute("quantity", quantity)
el.setAttribute("price", price)
shopping.appendChild(el)

print shopping.toprettyxml()
from xml.etree.ElementTree import Element, SubElement, tostring

csv = """bread,3,2.50
milk,2,3.50"""

root = Element('shopping')

for line in csv.split("\n"):
name, quantity, price = line.split(",")
SubElement(root,'item', {'name' : name,
'quantity' : quantity,
'price' : price })

print tostring(root)
clojure
(defn list->xml-item [lst]
(let [[name quantity price] (map str lst)]
{:tag :item
:attrs {:name name
:quantity quantity
:price price}}))

(defn cvs->xml [r]
(->> (map #(read-string (str "(" % ")")) (line-seq r))
(map list->xml-item)
(assoc {:tag :shopping} :content)
(emit)
(with-out-str)))

(println (cvs->xml *cvs-reader*))
erlang
to_xml(ShoppingList) ->
Items = lists:map(fun(L) ->
[Name, Quantity, Price] = string:tokens(L, ","),
{item, [{name, Name}, {quantity, Quantity}, {price, Price}], []}
end, string:tokens(ShoppingList, "\n")),
xmerl:export_simple([{shopping, [], Items}], xmerl_xml).
java
// In this solution JAXB is used to created the xml output.
// JAXB is included in Java 1.6. Runs with 1.5 if you include JAXB Jars
// in the classpath.
class Item {
// Of course you use getters and setters and declare attributes private.
// In this sample a "dirty" way is chosen to keep LOC low.
@XmlAttribute
String name;
@XmlAttribute
Integer quantity;
@XmlAttribute
Double price;
}

@XmlRootElement
class Shopping {
@XmlElement
Set<Item> items = new HashSet<Item>();
}

String line = null;
Shopping shopping = new Shopping();
try {
BufferedReader reader = new BufferedReader(new FileReader("shopping.csv"));
while ((line = reader.readLine()) != null) {
String[] parts = line.split(",");
Item item = new Item();
item.name = parts[0];
item.quantity = Integer.parseInt(parts[1]);
item.price = Double.parseDouble(parts[2]);
shopping.items.add(item);

}
JAXB.marshal(shopping, "D:" + File.separatorChar + "shopping.auto.xml");
} catch (IOException e) {
e.printStackTrace();
}