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
csharp
System.Xml.XmlDocument doc = new System.Xml.XmlDocument();
doc.LoadXml(
@"<shopping>
<item name='bread' quantity='3' price='2.50'/>
<item name='milk' quantity='2' price='3.50'/>
</shopping>");

string decimalSeparator= System.Globalization.CultureInfo.CurrentCulture.NumberFormat.CurrencyDecimalSeparator;

double sum=0;

foreach(System.Xml.XmlNode nodo in doc.SelectNodes("/shopping/item")){
sum += int.Parse(nodo.Attributes["quantity"].InnerText) * double.Parse(nodo.Attributes["price"].InnerText.Replace(".",decimalSeparator));
}
Console.WriteLine("{0:#.00}",sum);
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]).
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*))
csharp
string cvs ="bread,3,2.50\nmilk,2,3.50";
IList<string> rows = cvs.Split('\n');

System.Text.StringBuilder sb = new System.Text.StringBuilder("<shopping>");
foreach(string row in rows){
IList<string> data = row.Split(',');
sb.AppendFormat("<item name='{0}' quantity='{1}' price='{2}' />",data[0],data[1],data[2]);
}
sb.Append("</shopping>");
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).