Rosetta Code/Count examples
Find the total number of programming examples for each task and the total for all tasks.
You are encouraged to solve this task according to the task description, using any language you may know.
Essentially, count the number of occurrences of =={{header| on each task page.
Output:
<lang>100 doors: 20 examples. 99 Bottles of Beer: 29 examples. Abstract type: 10 examples.
Total: X examples.</lang>
D
<lang D> import tango.io.Stdout; import tango.net.http.HttpClient; import tango.net.http.HttpHeaders; import tango.text.xml.Document; import tango.text.Util;
alias HttpHeader.ContentLength CL;
auto url = "http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml"; void main() {
auto client = new HttpClient (HttpClient.Get, url); client.open(); char[] mainData, tmp; int total, i;
void cat(void[] content) { tmp ~= cast(char[]) content; }
if (client.isResponseOK) {
client.read(&cat, client.getResponseHeaders.getInt(CL));
mainData = tmp;
tmp = null;
auto doc = new Document!(char);
doc.parse(mainData);
foreach (n; doc.query.descendant("cm").attribute("title")) {
auto subClient = new HttpClient(HttpClient.Get,
"http://www.rosettacode.org/w/index.php?title=" ~
replace(n.value.dup, ' ', '_') ~ "&action=raw");
subClient.open();
if (! subClient.isResponseOK) {
Stderr (client.getResponse);
break;
}
subClient.read(&cat, subClient.getResponseHeaders.getInt(CL));
foreach (segment; patterns(cast(char[])tmp, "=={{header|")) i++;
--i;
if (i) --i;
Stdout.formatln ("{0,-40} - {}", n.value, i);
total += i;
tmp = null;
i = 0;
}
Stdout("total examples: ", total).newline;
} else {
Stderr (client.getResponse);
}
} </lang>
Python
<lang python>import urllib, xml.dom.minidom
x = urllib.urlopen("http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml")
tasks = [] for i in xml.dom.minidom.parseString(x.read()).getElementsByTagName("cm"):
t = i.getAttribute('title').replace(" ", "_")
y = urllib.urlopen("http://www.rosettacode.org/w/index.php?title=%s&action=raw" % t)
tasks.append( y.read().lower().count("{{header|") )
print t.replace("_", " ") + ": %d examples." % tasks[-1]
print "\nTotal: %d examples." % sum(tasks)</lang>
Java
<lang java> import java.util.ArrayList; import java.util.Iterator; import ScreenScrape;
public class CountProgramExamples { private static final String baseURL = "http://rosettacode.org/wiki/"; private static final String rootURL = "http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml"; private static final String taskBegin = "title=\""; private static final String taskEnd = "\""; private static final String exmplBegin = ""; private static final String exmplEnd = ""; private static final String editBegin = "";
/** * @param args */ public static void main(String[] args) { // Setup variables int exTotal = 0; int exSubTot = 0; String title = ""; String taskPage = ""; int startPos = 0; String countStr = ""; try { // Get root query results ArrayList<String> tasks = new ArrayList<String>(); ScreenScrape ss = new ScreenScrape(); String rootPage = ss.read(rootURL); while(rootPage.contains(taskBegin)){ rootPage = rootPage.substring(rootPage.indexOf(taskBegin)+taskBegin.length()); title = rootPage.substring(0, rootPage.indexOf(taskEnd)); if (!title.contains("Category:")) { tasks.add(title); } rootPage = rootPage.substring(rootPage.indexOf(taskEnd)); } // Loop through each task and print count Iterator<String> itr = tasks.iterator(); while(itr.hasNext()) { title = itr.next().replaceAll("'","'"); taskPage = ss.read(baseURL+title.replaceAll(" ", "_")); if (taskPage.contains(exmplBegin)) { startPos = taskPage.lastIndexOf(exmplBegin)+exmplBegin.length(); countStr = taskPage.substring(startPos, taskPage.indexOf(exmplEnd, startPos)); exSubTot = Integer.parseInt(countStr.contains(".") ? countStr.substring(0,countStr.indexOf(".")) : countStr); }else{ exSubTot = 0; while(taskPage.contains(editBegin)) { taskPage = taskPage.substring(taskPage.indexOf(editBegin)+editBegin.length()); exSubTot++; } } exTotal += exSubTot; System.out.println(title+": "+exSubTot+" examples."); } // Print total System.out.println("\nTotal: "+exTotal+" examples."); }catch(Exception e){ System.out.println(title); System.out.println(startPos+":"+taskPage.indexOf(exmplEnd, startPos)); System.out.println(taskPage); e.printStackTrace(System.out); } } } </lang>
This is the ScreenScrape class imported in the above class.
<lang java> import java.io.*; import java.net.URL; import javax.net.ssl.HttpsURLConnection;
public class ScreenScrape {
public String read(String sUrl) throws Exception { String lastHtml = ""; BufferedReader reader;
if (sUrl.startsWith("https://")) { // The URL class doesn't like HTTPS so we have to check for it.
reader = new BufferedReader(
new InputStreamReader(
getSSLOutputCon(sUrl).getInputStream()));
} else if (sUrl.startsWith("http://")) { // for nonsecure http
reader = new BufferedReader(
new InputStreamReader(
new URL(sUrl).openStream()));
} else {
return "Protocol not supported. Please verify that your URL starts with "
+ "\"http://\" or \"https://\" and try again.";
}
String line = reader.readLine();
while (line != null) {
lastHtml += line;
line = reader.readLine();
}
return lastHtml;
}
private HttpsURLConnection httpsUrlCon;
private HttpsURLConnection getSSLOutputCon(String sUrl) throws Exception {
try {
URL url = new URL(sUrl);
httpsUrlCon = (HttpsURLConnection) url.openConnection();
httpsUrlCon.setHostnameVerifier(new javax.net.ssl.HostnameVerifier() {
public boolean verify(String hostname, javax.net.ssl.SSLSession certHostName) {
return true;
}
});
} catch(Exception e) {
throw e;
}
return httpsUrlCon;
}
} </lang>