Data update

This commit is contained in:
Ingy döt Net 2023-09-16 17:28:03 -07:00
parent 5af6d93694
commit 796d366b97
455 changed files with 7413 additions and 1900 deletions

View file

@ -9,32 +9,52 @@ class Program
{
static void Main(string[] args)
{
string get1 = new WebClient().DownloadString("http://www.rosettacode.org/w/api.php?action=query&list=categorymembers&cmtitle=Category:Programming_Languages&cmlimit=500&format=json");
string get2 = new WebClient().DownloadString("http://www.rosettacode.org/w/index.php?title=Special:Categories&limit=5000");
string get2 = new WebClient().DownloadString("http://www.rosettacode.org/w/index.php?"
+"title=Special:Categories&limit=5000"
);
ArrayList langs = new ArrayList();
Dictionary<string, int> qtdmbr = new Dictionary<string, int>();
MatchCollection match1 = new Regex("\"title\":\"Category:(.+?)\"").Matches(get1);
MatchCollection match2 = new Regex("title=\"Category:(.+?)\">.+?</a>[^(]*\\((\\d+) members\\)").Matches(get2);
string cmcontinue = "";
foreach (Match lang in match1) langs.Add(lang.Groups[1].Value);
do
{
string get1 = new WebClient().DownloadString("http://www.rosettacode.org/w/api.php?"
+"action=query&list=categorymembers"
+"&cmtitle=Category:Programming_Languages"
+"&cmlimit=500&format=json"
+cmcontinue
);
cmcontinue = "";
MatchCollection languageMatch = new Regex("\"title\":\"Category:(.+?)\"").Matches(get1);
MatchCollection cmcontinueMatch = new Regex("cmcontinue\":\"([a-z0-9A-Z|]*)\"").Matches(get1);
foreach (Match lang in languageMatch) langs.Add(lang.Groups[1].Value);
foreach (Match more in cmcontinueMatch) cmcontinue = "&cmcontinue=" + more.Groups[1].Value;
}
while( cmcontinue != "" );
MatchCollection match2 =
new Regex("title=\"Category:(.+?)\">.+?</a>[^(]*\\(([\\d,.]+) members\\)").Matches(get2);
foreach (Match match in match2)
{
if (langs.Contains(match.Groups[1].Value))
{
qtdmbr.Add(match.Groups[1].Value, Int32.Parse(match.Groups[2].Value));
qtdmbr.Add(match.Groups[1].Value, Int32.Parse(match.Groups[2].Value
.Replace(",",string.Empty)
.Replace(".",string.Empty)));
}
}
string[] test = qtdmbr.OrderByDescending(x => x.Value).Select(x => String.Format("{0,3} - {1}", x.Value, x.Key)).ToArray();
string[] test =
qtdmbr.OrderByDescending(x => x.Value).Select(x => String.Format("{0,4} {1}", x.Value, x.Key)).ToArray();
int count = 1;
foreach (string i in test)
{
Console.WriteLine("{0,3}. {1}", count, i);
Console.WriteLine("{0,4}: {1}", count, i);
count++;
}
}

View file

@ -0,0 +1,82 @@
Imports System.Collections
Imports System.Collections.Generic
Imports System.Net
Imports System.Text.RegularExpressions
Module RankLanguagesByPopularity
Private Class LanguageStat
Public name As String
Public count As Integer
Public Sub New(name As String, count As Integer)
Me.name = name
Me.count = count
End Sub
End Class
Private Function CompareLanguages(x As LanguageStat, y As languageStat) As Integer
Dim result As Integer = 0
If x IsNot Nothing Or y IsNot Nothing Then
If x Is Nothing Then
result = -1
ElseIf y Is Nothing
result = 1
Else
result = - x.count.CompareTo(y.count) ' Sort descending count
If result = 0 Then
result = x.name.CompareTo(y.name) ' Sort ascending name
End If
End If
End If
Return result
End Function
Public Sub Main(ByVal args As String())
Dim languages As New List(Of LanguageStat)
Dim basePage As String = "https://rosettacode.org/wiki/Category:Programming_Languages"
Dim nextPage As String = basePage
Dim nextPageEx = New RegEx("<a href=""/wiki/Category:Programming_Languages([?]subcatfrom=[^""]*)""")
Dim languageStatEx = _
New Regex(">([^<]+?)</a>[^<]*<span title=""Contains *[0-9,.]* *[a-z]*, *([0-9,.]*) *page")
Do While nextPage <> ""
Dim wc As New WebClient()
Dim page As String = wc.DownloadString(nextPage)
nextPage = ""
For Each link In nextPageEx.Matches(page)
nextPage = basePage & link.Groups(1).Value
Next link
For Each language In languageStatEx.Matches(page)
Dim lCount As Integer = 0
Dim lName As String = language.Groups(1).Value
Dim countText As String = language.Groups(2).Value.Replace(",", "").Replace(".", "")
If Not Integer.TryParse(countText, lCount)
Console.Out.WriteLine(lName & "Invalid page count: <<" & countText & ">>")
Else
languages.Add(New LanguageStat(lName, lCount))
End If
Next language
Loop
languages.Sort(AddressOf CompareLanguages)
Dim prevCount As Integer = -1
Dim prevPosition As Integer = -1
Dim position As Integer = 0
For Each stat As LanguageStat In languages
position += 1
If stat.count <> prevCount Then
prevPosition = position
prevCount = stat.Count
End If
Console.Out.WriteLine(prevPosition.ToString.PadLeft(4) & ": " &
stat.count.ToString.PadLeft(4) & " " & stat.name)
Next stat
End Sub
End Module