Data update

Task/Rosetta-Code-Find-unimplemented-tasks/Icon/rosetta-code-find-unimplemented-tasks.icon

@@ -1,75 +1,46 @@
-$define RCINDEX "http://rosettacode.org/mw/api.php?format=xml&action=query&list=categorymembers&cmtitle=Category:Programming_Tasks&cmlimit=500"
-$define RCTASK  "http://rosettacode.org/mw/index.php?action=raw&title="
-$define RCUA    "User-Agent: Unicon Rosetta 0.1"
-$define RCXUA   "X-Unicon: http://unicon.org/"
-$define TASKTOT "* Total Tasks *"
-$define TOTTOT  "* Total Headers*"
-
-link strings
-link hexcvt
+$define RCPREFIX "https://rosettacode.org/w/api.php?action=query&list=categorymembers&format=xml&cmlimit=5000&cmtitle=Category:"
+$define RCSUFFIX1 "Programming%20Tasks"
 
 procedure main(A)   # simple single threaded read all at once implementation
     lang := \A[1] | "Unicon"
     write("Unimplemented tasks for ",lang," as of ",&date)
-    every task := taskNames() do {
-       if lang == languages(task) then next
-       write(task)
-       }
+    all_tasks := set([: taskNames() :])
+    tasks_for_lang := set([: tasksForLang(lang) :])
+    every write(!sort(all_tasks -- tasks_for_lang))
 end
 
 # Generate task names
 procedure taskNames()
     continue := ""
-    while \(txt := ReadURL(RCINDEX||continue)) do {
+    while \(txt := ReadURL(RCPREFIX||RCSUFFIX1||continue)) do {
         txt ? {
-            while tab(find("<cm ") & find(s :="title=\"")+*s) do
+            while tab((find("<cm "),find(s :="title=\""))+*s) do
                 suspend tab(find("\""))\1
-            if tab(find("cmcontinue=")) then {
-                continue := "&"||tab(upto(' \t'))
-                }
-            else break
+            continue := getContinue() | break
             }
         }
 end
 
-# Generate language headers in a task
-procedure languages(task)
-    static WS
-    initial WS := ' \t'
-    page := ReadURL(RCTASK||CleanURI(task))
-    page ? while (tab(find("\n==")),tab(many(WS))|"",tab(find("{{"))) do {
-               header := tab(find("=="))
-               header ? {
-                   while tab(find("{{header|")) do {
-                       suspend 2(="{{header|",tab(find("}}")))\1
-                       }
-                   }
-               }
+# Generate all tasks for a language
+procedure tasksForLang(lang)
+   continue := ""
+   while \(txt := ReadURL(RCPREFIX||lang||continue)) do {
+      txt ? {
+          while tab(find(s :="title=\"")+*s) do
+                suspend tab(find("\""))\1
+          continue := getContinue() | break
+          }
+      }
 end
 
-procedure CleanURI(u)                  #: clean up a URI
-    static tr,dxml                     # xml & http translation
-    initial {
-       tr := table()
-       every c := !string(~(&digits++&letters++'-_.!~*()/\'`')) do
-          tr[c] := "%"||hexstring(ord(c),2)
-       every /tr[c := !string(&cset)] := c
-       tr[" "] := "_"                                      # wiki convention
-       every push(dxml := [],"&#"||right(ord(c := !"&<>'\""),3,"0")||";",c)
-       }
-
-    dxml[1] := u                       # insert URI as 1st arg
-    u := replacem!dxml                 # de-xml it
-    every (c := "") ||:= tr[!u]        # reencode everything
-    c := replace(c,"%3E","'")          # Hack to put single quotes back in
-    c := replace(c,"%26quot%3B","\"")  # Hack to put double quotes back in
-    return c
+procedure getContinue()
+    gcm := "cmcontinue="
+    return (tab(1),"&"||2(tab(find(gcm)),=gcm,="\"")||tab(upto('"')))
 end
 
 procedure ReadURL(url)                 #: read URL into string
-    page := open(url,"m",RCUA,RCXUA) | stop("Unable to open ",url)
-    text := ""
-    if page["Status-Code"] < 300 then while text ||:= reads(page,-1)
+    page := open(url,"m-") | stop("Unable to open ",url," -> ",&errortext)
+    if page["Status-Code"] < 300 then text := reads(page,-1)
     else write(&errout,image(url),": ",
                        page["Status-Code"]," ",page["Reason-Phrase"])
     close(page)