Rosetta Code/Count examples
From Rosetta Code
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:
100 doors: 20 examples.
99 Bottles of Beer: 29 examples.
Abstract type: 10 examples.
Total: X examples.
Contents |
[edit] AutoHotkey
UrlDownloadToFile
, http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml
, tasks.xml
FileRead, tasks, tasks.xml
pos = 0
quote = " ; "
regtitle := "<cm.*?title=" . quote . "(.*?)" . quote
While, pos := RegExMatch(tasks, regtitle, title, pos + 1)
{
UrlDownloadToFile
, % "http://www.rosettacode.org/w/index.php?title=" . title1 . "&action=raw"
, task.xml
FileRead, task, task.xml
RegExReplace(task, "\{\{header\|", "", count)
current := title1 . ": " . count . " examples.`n"
output .= current
TrayTip, current, % current
}
MsgBox % output
Return
[edit] C#
Object-oriented solution.
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text.RegularExpressions;
using System.Net;
class Task {
private string _task;
private int _examples;
public Task(string task, int examples) {
_task = task;
_examples = examples;
}
public string Name {
get { return _task; }
}
public int Examples {
get { return _examples; }
}
public override string ToString() {
return String.Format("{0}: {1} examples.", this._task, this._examples);
}
}
class Program {
static List<string> GetTitlesFromCategory(string category, WebClient wc) {
string content = wc.DownloadString(
String.Format("http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:{0}&cmlimit=500&format=json", category)
);
return new Regex("\"title\":\"(.+?)\"").Matches(content).Cast<Match>().Select(x => x.Groups[1].Value.Replace("\\/", "/")).ToList();
}
static string GetSourceCodeFromPage(string page, WebClient wc) {
return wc.DownloadString(
String.Format("http://www.rosettacode.org/w/index.php?title={0}&action=raw", page)
);
}
static void Main(string[] args) {
WebClient wc = new WebClient();
List<Task> tasks = new List<Task>();
List<string> tasknames = GetTitlesFromCategory("Programming_Tasks", wc);
foreach (string task in tasknames) {
string content = GetSourceCodeFromPage(task, wc);
int count = new Regex("=={{header", RegexOptions.IgnoreCase).Matches(content).Count;
Task t = new Task(task, count);
Console.WriteLine(t);
tasks.Add(t);
}
Console.WriteLine("\nTotal: {0} examples.", tasks.Select(x => x.Examples).Sum());
}
}
[edit] Clojure
(ns count-examples
(:import [java.net URLEncoder])
(:use [clojure.contrib.http.agent :only (http-agent string)]
[clojure.contrib.json :only (read-json)]
[clojure.contrib.string :only (join)]))
(defn url-encode [v] (URLEncoder/encode (str v) "utf-8"))
(defn rosettacode-get [path params]
(let [param-string (join "&" (for [[n v] params] (str (name n) "=" (url-encode v))))]
(string (http-agent (format "http://www.rosettacode.org/w/%s?%s" path param-string)))))
(defn rosettacode-query [params]
(read-json (rosettacode-get "api.php" (merge {:action "query" :format "json"} params))))
(defn list-cm
([params] (list-cm params nil))
([params continue]
(let [cm-params (merge {:list "categorymembers"} params (or continue {}))
result (rosettacode-query cm-params)]
(concat (-> result (:query) (:categorymembers))
(if-let [cmcontinue (-> result (:query-continue) (:categorymembers))]
(list-cm params cmcontinue))))))
(defn programming-tasks []
(let [result (list-cm {:cmtitle "Category:Programming_Tasks" :cmlimit 50})]
(map #(:title %) result)))
(defn task-count [task]
[task (count
(re-seq #"==\{\{header"
(rosettacode-get "index.php" {:action "raw" :title task})))])
(defn print-result []
(let [task-counts (map task-count (programming-tasks))]
(doseq [[task count] task-counts]
(println (str task ":") count)
(flush))
(println "Total: " (reduce #(+ %1 (second %2)) 0 task-counts))))
count-examples> (print-result)
100 doors: 73
24 game: 18
24 game/Solve: 14
99 Bottles of Beer: 89
Abstract type: 27
Accumulator factory: 23
Ackermann function: 73
Active Directory/Connect: 4
Active Directory/Search for a user: 3
Active object: 14
Add a variable to a class instance at runtime: 21
Address of a variable: 20
...
Total: 11216
nil
[edit] D
Works with: Tango
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);
}
}
[edit] F#
Using asynchronous workflows to perform downloads concurrently:
#r "System.Xml.Linq.dll"
let uri1 = "http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml"
let uri2 task = sprintf "http://www.rosettacode.org/w/index.php?title=%s&action=raw" task
[|for xml in (System.Xml.Linq.XDocument.Load uri1).Root.Descendants() do
for attrib in xml.Attributes() do
if attrib.Name.LocalName = "title" then
yield async {
let uri = uri2 (attrib.Value.Replace(" ", "_") |> System.Web.HttpUtility.UrlEncode)
use client = new System.Net.WebClient()
let! html = client.AsyncDownloadString(System.Uri uri)
let sols' = html.Split([|"{{header|"|], System.StringSplitOptions.None).Length - 1
lock stdout (fun () -> printfn "%s: %d examples" attrib.Value sols')
return sols' }|]
|> Async.Parallel
|> Async.RunSynchronously
|> fun xs -> printfn "Total: %d examples" (Seq.sum xs)
This is 21× faster than the python thanks to the concurrency.
[edit] Haskell
Library: HTTP XML from HackageDB
import Network.Browser
import Network.HTTP
import Network.URI
import Data.List
import Data.Maybe
import Text.XML.Light
import Control.Arrow
justifyR w = foldl ((.return).(++).tail) (replicate w ' ')
showFormatted t n = t ++ ": " ++ justifyR 4 (show n)
getRespons url = do
rsp <- Network.Browser.browse $ do
setAllowRedirects True
setOutHandler $ const (return ()) -- quiet
request $ getRequest url
return $ rspBody $ snd rsp
getNumbOfExampels p = do
let pg = intercalate "_" $ words p
rsp <- getRespons $ "http://www.rosettacode.org/w/index.php?title=" ++ pg ++ "&action=raw"
let taskPage = rsp
countEx = length $ filter (=="=={{header|") $ takeWhile(not.null) $ unfoldr (Just. (take 11 &&& drop 1)) taskPage
return countEx
progTaskExamples = do
rsp <- getRespons "http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml"
let xmls = onlyElems $ parseXML $ rsp
tasks = concatMap (map (fromJust.findAttr (unqual "title")). filterElementsName (== unqual "cm")) xmls
taskxx <- mapM getNumbOfExampels tasks
let ns = taskxx
tot = sum ns
mapM_ putStrLn $ zipWith showFormatted tasks ns
putStrLn $ ("Total: " ++) $ show tot
some output:
*Main> progTaskExamples
100 doors: 56
24 game: 11
24 game Player: 9
99 Bottles of Beer: 73
Abstract type: 23
Ackermann Function: 61
Active object: 9
...
Total: 9156
[edit] J
Solution:
Using getCategoryMembers from Find unimplemented tasks.
require 'web/gethttp'
getAllTaskSolnCounts=: monad define
tasks=. getCategoryMembers 'Programming_Tasks'
counts=. getTaskSolnCounts &> tasks
tasks;counts
)
getTaskSolnCounts=: monad define
makeuri=. 'http://www.rosettacode.org/w/index.php?title=' , ,&'&action=raw'
wikidata=. gethttp makeuri urlencode y
([: +/ '{{header|'&E.) wikidata
)
formatSolnCounts=: monad define
'tasks counts'=. y
tasks=. tasks , &.>':'
res=. ;:^:_1 tasks ,. (8!:0 counts) ,. <'examples.'
res , 'Total examples: ' , ": +/counts
)
Example Usage:
formatSolnCounts getAllTaskSolnCounts ''
100 doors: 61 examples.
24 game: 15 examples.
24 game Player: 11 examples.
99 Bottles of Beer: 76 examples.
...
[edit] Java
Works with: Java version 1.5+
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 = "<span class=\"tocnumber\">";
private static final String exmplEnd = "</span>";
private static final String editBegin = "<span class=\"editsection\">";
/**
* @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);
}
}
}
[edit] OCaml
Library: ocamlnet
Library: xml-light
execute with:
ocaml str.cma unix.cma -I +pcre pcre.cma -I +netsys netsys.cma -I +equeue equeue.cma \ -I +netstring netstring.cma -I +netclient netclient.cma -I +xml-light xml-light.cma countex.ml
or with the findlib package one can compile with:
ocamlfind opt -linkpkg -package str,unix,xml-light,netclient countex.ml -o countex.opt
open Http_client.Convenience
let repl_quote s =
let reg = Str.regexp_string "'" in
(Str.global_replace reg "%27" s)
let repl_space s =
let s = String.copy s in
for i = 0 to pred(String.length s) do
if s.[i] = ' ' then s.[i] <- '_'
done;
(s)
let count_ex s =
let pat = Str.regexp_string "=={{header|" in
let rec aux n p =
try
let p = Str.search_forward pat s p in
aux (n+1) (p+1)
with Not_found -> (n)
in
aux 0 0
let () =
let url = "http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&\
cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml" in
let xml = Xml.parse_string (http_get url) in
let total = ref 0 in
at_exit (fun () -> Printf.printf "\n Total: %d\n" !total);
let f = function
| Xml.Element ("cm", attrs, _) ->
(try
let _title = List.assoc "title" attrs in
let title = repl_quote (repl_space _title) in
let url = "http://www.rosettacode.org/w/index.php?title="^ title ^"&action=raw" in
let n = count_ex (http_get url) in
Printf.printf "%s: %d\n%!" _title n;
total := n + !total;
with Http_client.Http_error (404, _) -> ())
| _ -> ()
in
match xml with
| Xml.Element ("api", [],
[Xml.Element ("query", [],
[Xml.Element ("categorymembers", [], cms)])]) -> List.iter f cms
| _ -> ()
outputs:
100 doors: 56 24 game: 11 24 game Player: 9 99 Bottles of Beer: 73 Abstract type: 23 Ackermann Function: 61 ... XML Reading: 22 XML and XPath: 18 Xiaolin Wu's line algorithm: 3 Y combinator: 23 Yuletide Holiday: 32 Zig Zag: 29 Total: 9106
[edit] Oz
Library: OzHttpClient
declare
[HTTPClient] = {Module.link ['x-ozlib://mesaros/net/HTTPClient.ozf']}
[XMLParser] = {Module.link ['x-oz://system/xml/Parser.ozf']}
[StringX] = {Module.link ['x-oz://system/String.ozf']}
[Regex] = {Module.link ['x-oz://contrib/regex']}
AllTasksUrl = "http://rosettacode.org/mw/api.php?action=query&list="#
"categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml"
proc {Main}
AllTasks = {Parse {GetPage AllTasksUrl}}
TaskTitles = {GetTitles AllTasks}
Total = {NewCell 0}
in
for Task in TaskTitles do
TaskPage = {GetPage {TaskUrl Task}}
RE = {Regex.compile "{{header\\|" [extended newline icase]}
NumMatches = {Length {Regex.allMatches RE TaskPage}}
in
{System.showInfo Task#": "#NumMatches#" examples."}
Total := @Total + NumMatches
end
{System.showInfo "Total: "#@Total#" examples."}
end
fun {TaskUrl Task}
"http://rosettacode.org/mw/index.php?"#
"title="#{PercentEncode {StringX.replace Task " " "_"}}#
"&action=raw"
end
%% GetPage
local
Client = {New HTTPClient.urlGET init(inPrms(toFile:false toStrm:true) _)}
in
fun {GetPage RawUrl}
Url = {VirtualString.toString RawUrl}
OutParams
HttpResponseParams
in
{Client getService(Url ?OutParams ?HttpResponseParams)}
OutParams.sOut
end
end
%% Parse
local
Parser = {New XMLParser.parser init}
in
fun {Parse Xs} {Parser parseVS(Xs $)} end
end
fun {GetTitles Doc}
CMs = Doc.2.1.children.1.children.1.children
fun {Attributes element(attributes:As ...)} As end
fun {IsTitle attribute(name:N ...)} N == title end
in
{Map {Filter {Flatten {Map CMs Attributes}} IsTitle}
fun {$ A} {Atom.toString A.value} end}
end
fun {PercentEncode Xs}
case Xs of nil then nil
[] X|Xr then
if {Char.isDigit X} orelse {Member X [&- &_ &. &~]}
orelse X >= &a andthen X =< &z
orelse X >= &z andthen X =< &Z then
X|{PercentEncode Xr}
else
{Append &%|{ToHex2 X} {PercentEncode Xr}}
end
end
end
fun {ToHex2 X}
[{ToHex1 X div 16} {ToHex1 X mod 16}]
end
fun {ToHex1 X}
if X >= 0 andthen X =< 9 then &0 + X
elseif X >= 10 andthen X =< 15 then &A + X - 10
end
end
in
{Main}
Example output:
100 doors: 86 examples. 24 game: 22 examples. 24 game/Solve: 15 examples. 99 Bottles of Beer: 108 examples. A+B: 59 examples. ... Xiaolin Wu's line algorithm: 5 examples. Y combinator: 29 examples. Yahoo! Search: 10 examples. Zig-zag matrix: 43 examples. Total: 14099 examples.
[edit] Perl
#!/usr/bin/perl -w
use strict ;
use LWP::UserAgent ;
use HTML::Parser ;
use constant DOCROOT => "http://www.rosettacode.org/wiki" ;
use constant SOLUTIONROOT => "http://www.rosettacode.org/w/index.php?title=" ;
my %tasklist = ( ) ; #key: last part of solution list URL, value: title of solution
my $ua = new LWP::UserAgent ;
my $url = DOCROOT . "/Category:Programming_Tasks" ;
my $request = HTTP::Request->new( 'GET' => "$url" ) ;
my $response = $ua->request( $request ) ;
my $counted = 0 ;
my $total_examples = 0 ;
my $solresponse ;
my $p = HTML::Parser->new( api_version => 3 ) ; #parser for list of tasks
my $q = HTML::Parser->new( api_version => 3 ) ; #parser for solutions by task
$p->handler( start => \&process , "tagname , attr" ) ;
$q->handler( text => \&langfinder, "text" ) ;
if ( $response->is_success( ) ) {
$p->parse( $response->content( ) ) ;
foreach my $task( keys %tasklist ) {
$request->uri( SOLUTIONROOT . "$task" . "&action=edit" ) ;
$solresponse = $ua->request( $request ) ;
if ( $solresponse->is_success( )) {
$q->parse( $solresponse->content( ) ) ;
if ( $tasklist{$task} ) {
print "$tasklist{$task} : $counted examples!\n" ;
}
$counted = 0 ;
$q->eof( ) ;
}
else {
print "Error: " . $solresponse->code( ) . " " . $solresponse->message( ) . "\n" ;
}
}
$p->eof( ) ;
print "\nTotal: $total_examples examples.\n" ;
}
else {
print "Error " . $response->code( ) . " " . $response->message( ) . "\n" ;
}
sub process( ) {
return if shift ne "a" ;
my $props = shift ;
if ( $props->{href} && $props->{href} =~ m,/wiki/([^:]+), ) {
if ( $1 !~ /Category/ ) {
$tasklist{ $1 } = $props->{title} ;
}
}
}
sub langfinder( ) {
my $text = shift ;
while ( $text =~ /header\|.+\}/g ) {
$counted++ ;
$total_examples++ ;
}
}
[edit] PicoLisp
(load "@lib/http.l")
(client "rosettacode.org" 80
"mw/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml"
(while (from " title=\"")
(let Task (till "\"")
(client "rosettacode.org" 80 (pack "wiki/" (replace Task " " "_"))
(let Cnt 0
(while (from "<span class=\"tocnumber\">")
(unless (sub? "." (till "<" T))
(inc 'Cnt) ) )
(out NIL (prinl (ht:Pack Task) ": " Cnt)) ) ) ) ) )
Output (05may10):
100 doors: 79 24 game: 21 24 game/Solve: 15 99 Bottles of Beer: 95 A+B: 37 Abstract type: 29 ...
[edit] 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.encode('utf-8'))
tasks.append( y.read().lower().count("{{header|") )
print t.replace("_", " ") + ": %d examples." % tasks[-1]
print "\nTotal: %d examples." % sum(tasks)
[edit] R
Library: XML (R)
Library: RCurl
library(XML)
library(RCurl)
doc <- xmlInternalTreeParse("http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml")
nodes <- getNodeSet(doc,"//cm")
titles = as.character( sapply(nodes, xmlGetAttr, "title") )
headers <- list()
counts <- list()
for (i in 1:length(titles)){
headers[[i]] <- getURL( paste("http://rosettacode.org/mw/index.php?title=", gsub(" ", "_", titles[i]), "&action=raw", sep="") )
counts[[i]] <- strsplit(headers[[i]],split=" ")[[1]]
counts[[i]] <- grep("\\{\\{header", counts[[i]])
cat(titles[i], ":", length(counts[[i]]), "examples\n")
}
cat("Total: ", length(unlist(counts)), "examples\n")
[edit] Ruby
Library: REXML First, a RosettaCode module, saved as rosettacode.rb:
require 'open-uri'
require 'rexml/document'
module RosettaCode
URL_ROOT = "http://rosettacode.org/mw"
def self.get_url(page, query)
url = "#{URL_ROOT}/%s?%s" % [
URI.escape(page),
URI.escape(query.map {|k,v| "%s=%s" % [k,v]}.join("&"))
]
url.gsub!(/\+/, '%2B')
p url if $DEBUG
url
end
def self.get_api_url(query)
get_url "api.php", query
end
def self.category_members(category)
query = {
"action" => "query",
"list" => "categorymembers",
"cmtitle" => "Category:#{category}",
"format" => "xml",
"cmlimit" => 500,
}
while true
url = get_api_url query
doc = REXML::Document.new open(url)
REXML::XPath.each(doc, "//cm") do |task|
yield task.attribute("title").value
end
continue = REXML::XPath.first(doc, "//query-continue")
break if continue.nil?
cm = REXML::XPath.first(continue, "categorymembers")
query["cmcontinue"] = cm.attribute("cmcontinue").value
end
end
end
Then, we implement the task with:
require 'rosettacode'
total_examples = 0
RosettaCode.category_members("Programming_Tasks") do |task|
url = RosettaCode.get_url("index.php", {"action" => "raw", "title" => task})
examples = open(url).read.scan("=={{header").length
puts "#{task}: #{examples}"
total_examples += examples
end
puts
puts "Total: #{total_examples}"
[edit] Scala
This was writen for Scala 2.8, but Scala 2.7 can be used with slight modifications to the IO library.
Different than the example for other languages, it parallelizes the reading and counting, and it also encode the URL, because some URLs are now causing problems. These modifications are minor, though.
It was written in script style.
import java.net.{URL, URLEncoder}
import scala.io.Source.fromURL
val allTasksURL = "http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500&format=xml"
val allTasks = xml.parsing.XhtmlParser(fromURL(new URL(allTasksURL)))
val regexExpr = "(?i)==\\{\\{header\\|".r
def oneTaskURL(title: String) = "http://www.rosettacode.org/w/index.php?title=%s&action=raw" format URLEncoder.encode(title.replace(' ', '_'), "UTF-8")
def count(title: String) = regexExpr findAllIn fromURL(new URL(oneTaskURL(title)))(io.Codec.UTF8).mkString length
val counts = for (task <- allTasks \\ "cm" \\ "@title" map (_.text)) yield scala.actors.Futures.future((task, count(task)))
counts map (_.apply) map Function.tupled("%s: %d examples." format (_, _)) foreach println
println("\nTotal: %d examples." format (counts map (_.apply._2) sum))
[edit] Tcl
Using the json package from Library: tcllib
package require Tcl 8.5
package require http
package require json
fconfigure stdout -buffering none
proc get_tasks {category} {
set start [clock milliseconds]
puts -nonewline "getting $category members..."
set base_url http://www.rosettacode.org/w/api.php
set query {action query list categorymembers cmtitle Category:%s format json cmlimit 500}
set this_query [dict create {*}[split [format $query $category]]]
set tasks [list]
while {1} {
set url [join [list $base_url [http::formatQuery {*}$this_query]] ?]
set response [http::geturl $url]
if {[set s [http::status $response]] ne "ok" || [http::ncode $response] != 200} {
error "Oops: url=$url\nstatus=$s\nhttp code=[http::code $response]"
}
set data [json::json2dict [http::data $response]]
http::cleanup $response
# add tasks to list
foreach task [dict get $data query categorymembers] {
lappend tasks [dict get [dict create {*}$task] title]
}
if {[catch {dict get $data query-continue categorymembers cmcontinue} continue_task] != 0} {
# no more continuations, we're done
break
}
dict set this_query cmcontinue $continue_task
}
puts " found [llength $tasks] tasks in [expr {[clock milliseconds] - $start}] milliseconds"
return $tasks
}
# This proc can be replaced by a single regexp command:
# set count [regexp -all "***=$needle" $haystack]
# However this proc is more efficient -- we're dealing with plain strings only.
proc count_substrings {needle haystack} {
set count 0
set idx 0
while {[set idx [string first $needle $haystack $idx]] != -1} {
incr count
incr idx
}
return $count
}
set total 0
foreach task [get_tasks Programming_Tasks] {
set url [format "http://www.rosettacode.org/w/index.php?title=%s&action=raw" [string map {{ } _} $task]]
set response [http::geturl $url]
if {[set s [http::status $response]] ne "ok" || [http::ncode $response] != 200} {
error "Oops: url=$url\nstatus=$s\nhttp code=[http::code $response]"
}
set count [count_substrings "\{\{header|" [http::data $response]]
puts [format "%3d examples in %s" $count $task]
http::cleanup $response
incr total $count
}
puts "\nTotal: $total examples"
Categories: Programming Tasks | Rosetta Code related | AutoHotkey | C sharp | Clojure | D | F Sharp | Haskell | HTTP XML | J | Java | OCaml | Ocamlnet | Xml-light | Oz | OzHttpClient | Perl | PicoLisp | Python | R | XML (R) | RCurl | Ruby | REXML | Scala | Tcl | Tcllib | TI-83 BASIC/Omit | TI-89 BASIC/Omit
