aparler/RosettaCodeData
1
0
Fork 0
Code Issues 12 Pull requests 3 Projects Releases Packages Wiki Activity Actions

Data update

Browse source
This commit is contained in:
Ingy döt Net 2024-07-13 15:19:22 -07:00
parent 29a5eea0d4
commit 5c1bb7bfa9
2011 changed files with 35081 additions and 3229 deletions
Download patch file Download diff file Expand all files Collapse all files

180
Task/Rosetta-Code-Rank-languages-by-popularity/Ada/rosetta-code-rank-languages-by-popularity.ada
View file

@ -1,23 +1,28 @@
pragma Ada_2022;
with Ada.Integer_Text_IO; use Ada.Integer_Text_IO;
with Ada.Strings.Fixed; use Ada.Strings.Fixed;
with Ada.Strings.Unbounded; use Ada.Strings.Unbounded;
with Ada.Text_IO; use Ada.Text_IO;
with Ada.Containers.Ordered_Sets;
with Ada.Strings.Less_Case_Insensitive;
with Ada.Strings.Unbounded.Less_Case_Insensitive;
with Ada.Characters.Handling; use Ada.Characters.Handling;
with AWS.Client;
with AWS.Client; use AWS.Client;
with AWS.Messages; use AWS.Messages;
with AWS.Response;
procedure Test is
procedure Rank_Languages_By_Popularity is
use Ada.Strings;
function "+" (S : String) return Unbounded_String renames To_Unbounded_String;
function "+" (S : String) return Unbounded_String
renames To_Unbounded_String;
type A_Language_Count is
record
Count : Integer := 0;
Count : Natural := 0;
Language : Unbounded_String;
end record;
@ -28,11 +33,12 @@ procedure Test is
function "<" (L, R : A_Language_Count) return Boolean is
begin
-- Sort by 'Count' and then by Language name
-- Sort by 'Count' and then by Language name
return L.Count < R.Count
or else (L.Count = R.Count
and then Less_Case_Insensitive (Left => To_String (L.Language),
Right => To_String (R.Language)));
and then Less_Case_Insensitive
(Left => L.Language,
Right => R.Language));
end "<";
package Sets is new Ada.Containers.Ordered_Sets (A_Language_Count);
@ -41,30 +47,140 @@ procedure Test is
Counts : Set;
procedure Find_Counts (S : String) is
Title_Str : constant String := "title=""Category:";
End_A_Str : constant String := "</a> (";
Title_At : constant Natural := Index (S, Title_Str);
function Strip_Character (S : String; C : Character) return String is
S_Copy_Str : String (1 .. S'Length);
S_Copy_Index : Natural := 0;
begin
for I in S'Range loop
if S (I) /= C then
S_Copy_Index := S_Copy_Index + 1;
S_Copy_Str (S_Copy_Index) := S (I);
end if;
end loop;
return S_Copy_Str (S_Copy_Str'First .. S_Copy_Index);
end Strip_Character;
function Ignore_Category (L : String) return Boolean is
type Unbounded_String_Array is array (Positive range <>)
of Unbounded_String;
-- This list is quite comprehensive, but not complete
Categories_To_Ignore : Unbounded_String_Array := [
+"Pages with syntax highlighting errors",
+"Programming",
+"Examples needing attention",
+"Tasks needing attention",
+"Language users",
+"Implementations",
+"Solutions by ",
+"Maintenance/OmitCategoriesCreated",
+"Collection Members",
+"Pages with too many expensive parser function calls",
+"Garbage collection",
+" User",
+"SQL User",
+"Typing",
+"Parameter passing",
+"Execution method",
+"Unimplemented tasks by language",
+"Wolfram Language",
+"/Omit",
+"Wren-",
+"WrenGo",
+"Phix/",
+"PhixClass",
+"Basic language learning",
+"Encyclopedia",
+"RCTemplates",
+"SysUtils",
+"Action! ",
+"Text processing",
+"Image processing",
+"Scala Digital Signal Processing",
+"List processing",
+"Digital signal processing",
+"Processing Python",
+"Classic CS problems and programs",
+"Brainf*** related",
+"Data Structures",
+"Perl modules",
+"Perl/",
+"Perl:LWP",
+"Perl 6 related",
+"Flow control",
+"Excessively difficult task",
+"WikiStubs",
+"Impl needed",
+"Recursion"
];
begin
for Category of Categories_To_Ignore loop
declare
Category_At : constant Natural :=
Index (+To_Lower (L),
To_Lower (To_String (Category)));
begin
if Category_At /= 0 then
return True;
end if;
end;
end loop;
return False;
end Ignore_Category;
Title_Str : constant String := "title=""Category:";
End_A_Tag_Str : constant String := "</a>";
Space_Paren_Str : constant String := " (";
Title_At : constant Natural := Index (S, Title_Str);
begin
if Title_At /= 0 then
declare
Bracket_At : constant Natural := Index (S (Title_At + Title_Str'Length .. S'Last), ">");
End_A_At : constant Natural := Index (S (Bracket_At + 1 .. S'Last), End_A_Str);
Space_At : constant Natural := Index (S (End_A_At + End_A_Str'Length .. S'Last), " ");
Count : constant Natural := Natural'Value (S (End_A_At + End_A_Str'Length .. Space_At - 1));
Language : constant String := S (Title_At + Title_Str'Length .. Bracket_At - 2);
Closing_Bracket_At : constant Natural :=
Index (S (Title_At + Title_Str'Length .. S'Last), ">");
End_A_Tag_At : constant Natural :=
Index (S (Closing_Bracket_At + 1 .. S'Last), End_A_Tag_Str);
Language : constant String :=
S (Closing_Bracket_At + 1 .. End_A_Tag_At - 1);
Space_Paren_At : constant Natural :=
Index (S (End_A_Tag_At + 1 .. S'Last), Space_Paren_Str);
Space_At : constant Natural :=
Index (S (Space_Paren_At + Space_Paren_Str'Length + 1
.. S'Last),
" ");
Count : constant Natural :=
Natural'Value (
Strip_Character (
S (Space_Paren_At +
Space_Paren_Str'Length
.. Space_At - 1),
','));
begin
if Bracket_At /= 0 and then End_A_At /= 0 and then Space_At /= 0 then
if Closing_Bracket_At /= 0
and then End_A_Tag_At /= 0
and then Space_Paren_At /= 0
and then Space_At /= 0
then
begin
Counts.Insert (New_Item => (Count, +Language));
if Ignore_Category (Language) = False then
Counts.Insert (New_Item => (Count, +Language));
end if;
exception
when Constraint_Error =>
Put_Line (Standard_Error, "Warning: repeated language: " & Language);
-- Ignore repeated results.
Put_Line (Standard_Error, "Warning: repeated language: " &
Language);
-- Ignore repeated results.
null;
end;
end if;
-- Recursively parse the string for languages and counts
-- Recursively parse the string for languages and counts
Find_Counts (S (Space_At + 1 .. S'Last));
end;
end if;
@ -82,8 +198,26 @@ procedure Test is
end Display;
Http_Source : constant AWS.Response.Data :=
AWS.Client.Get ("http://rosettacode.org/mw/index.php?title=Special:Categories&limit=5000");
AWS.Client.Get ("http://rosettacode.org/w/index.php?" &
"title=Special:Categories&limit=5000",
Follow_Redirection => True);
Status : Status_Code;
begin
Put_Line ("Getting website data...");
Status := AWS.Response.Status_Code (Http_Source);
if Status not in Success then
Put_Line ("Unable to retrieve data => Status Code :" &
Image (Status) &
" Reason :" & Reason_Phrase (Status));
raise Connection_Error;
end if;
Put_Line ("Finding categories...");
Find_Counts (AWS.Response.Message_Body (Http_Source));
Put_Line ("Displaying categories...");
Counts.Reverse_Iterate (Display'Access);
end Test;
Put_Line ("Process complete.");
end Rank_Languages_By_Popularity;

31
Task/Rosetta-Code-Rank-languages-by-popularity/Java/rosetta-code-rank-languages-by-popularity.java
View file

@ -1,3 +1,4 @@
import java.net.URI;
import java.net.URL;
import java.net.URLConnection;
import java.io.*;
@ -45,10 +46,8 @@ public class GetRCLanguages
try
{
URL url = new URL( path );
URL url = new URI( path ).toURL();
URLConnection rc = url.openConnection();
// Rosetta Code objects to the default Java user agant so use a blank one
rc.setRequestProperty( "User-Agent", "" );
BufferedReader bfr = new BufferedReader( new InputStreamReader( rc.getInputStream() ) );
gcmcontinue[0] = "";
@ -56,27 +55,27 @@ public class GetRCLanguages
String line = bfr.readLine();
while( line != null )
{
line = line.trim();
if ( line.startsWith( "[title]" ) )
line = line.trim().replaceAll( "[\",]", "" );
if ( line.startsWith( "title" ) )
{
// have a programming language - should look like "[title] => Category:languageName"
languageName = after( line, ':' ).trim();
// have a programming language - should look like "title: Category:languageName"
languageName = after( after( line, ':' ), ':' ).trim();
}
else if( line.startsWith( "[pages]" ) )
else if( line.startsWith( "pages" ) )
{
// number of pages the language has (probably)
String pageCount = after( line, '>' ).trim();
if( pageCount.compareTo( "Array" ) != 0 )
String pageCount = after( line, ':' ).trim();
if( pageCount.compareTo( "{" ) != 0 )
{
// haven't got "[pages] => Array" - must be a number of pages
// haven't got "pages: {" - must be a number of pages
languageList.add( ( (char) Integer.parseInt( pageCount ) ) + languageName );
languageName = "?";
} // if [pageCount.compareTo( "Array" ) != 0
} // if [pageCount.compareTo( "{" ) != 0
}
else if( line.startsWith( "[gcmcontinue]" ) )
else if( line.startsWith( "gcmcontinue" ) )
{
// have an indication of wether there is more data or not
gcmcontinue[0] = after( line, '>' ).trim();
gcmcontinue[0] = after( line, ':' ).trim().replaceAll( "[|]", "%7C" );
} // if various line starts
line = bfr.readLine();
} // while line != null
@ -96,13 +95,13 @@ public class GetRCLanguages
gcmcontinue[0] = "";
do
{
String path = ( "http://www.rosettacode.org/mw/api.php?action=query"
String path = ( "https://www.rosettacode.org/w/api.php?action=query"
+ "&generator=categorymembers"
+ "&gcmtitle=Category:Programming%20Languages"
+ "&gcmlimit=500"
+ ( gcmcontinue[0].compareTo( "" ) == 0 ? "" : ( "&gcmcontinue=" + gcmcontinue[0] ) )
+ "&prop=categoryinfo"
+ "&format=txt"
+ "&format=jsonfm"
);
parseContent( path, gcmcontinue, languageList );
}

13
Task/Rosetta-Code-Rank-languages-by-popularity/PascalABC.NET/rosetta-code-rank-languages-by-popularity.pas Normal file
View file

@ -0,0 +1,13 @@
uses System.Net;
begin
ServicePointManager.SecurityProtocol := SecurityProtocolType(3072);
var wc := new WebClient;
wc.Encoding := Encoding.UTF8;
var s := wc.DownloadString('https://rosettacode.org/wiki/Special:Categories?limit=5000');
s.Matches('([^><]+)</a>.+\(([\d,]+) member')
.Select(x -> KV(x.Groups[1].Value,x.Groups[2].Value.Replace(',','').ToInteger))
.Where(x -> not x.Key.StartsWith('Pages'))
.OrderByDescending(pair -> pair.Value).Numerate.Take(10)
.PrintLines(x -> $'Rank: {x[0],3} ({x[1].Value} entries) {x[1].Key}')
end.