Data update

This commit is contained in:
Ingy döt Net 2025-02-27 18:35:13 -05:00
parent 8e4e15fa56
commit 72eb4943cb
1853 changed files with 35514 additions and 9441 deletions

View file

@ -39,12 +39,22 @@ Module RankLanguagesByPopularity
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")
New Regex(">([^<]+?)</a></bdi> *<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)
' Ensure the WebClient has a User-Agent.
Dim hasAgent As Boolean = False
for hPos As Integer = 0 To wc.Headers.Count - 1
Dim headerKey As String = wc.Headers.GetKey(hPos)
hasAgent = hasAgent Or headerKey = "User-Agent"
Next hPos
If not hasAgent Then
wc.Headers.Add("User-Agent", "RC_Tasks_Agent")
End If
Dim page As String = wc.DownloadString(nextPage)
nextPage = ""
For Each link In nextPageEx.Matches(page)
nextPage = basePage & link.Groups(1).Value
@ -60,6 +70,12 @@ Module RankLanguagesByPopularity
languages.Add(New LanguageStat(lName, lCount))
End If
Next language
If nextPage <> "" Then
' Sleep for a while to avoid looking like a DOS attack...
System.Threading.Thread.Sleep(500)
End If
Loop
languages.Sort(AddressOf CompareLanguages)

View file

@ -1,78 +0,0 @@
/* Rosetta_Code_Rank_languages_by_popularity.wren */
import "./pattern" for Pattern
import "./fmt" for Fmt
var CURLOPT_URL = 10002
var CURLOPT_FOLLOWLOCATION = 52
var CURLOPT_WRITEFUNCTION = 20011
var CURLOPT_WRITEDATA = 10001
foreign class Buffer {
construct new() {} // C will allocate buffer of a suitable size
foreign value // returns buffer contents as a string
}
foreign class Curl {
construct easyInit() {}
foreign easySetOpt(opt, param)
foreign easyPerform()
foreign easyCleanup()
}
var curl = Curl.easyInit()
var getContent = Fn.new { |url|
var buffer = Buffer.new()
curl.easySetOpt(CURLOPT_URL, url)
curl.easySetOpt(CURLOPT_FOLLOWLOCATION, 1)
curl.easySetOpt(CURLOPT_WRITEFUNCTION, 0) // write function to be supplied by C
curl.easySetOpt(CURLOPT_WRITEDATA, buffer)
curl.easyPerform()
return buffer.value
}
var p1 = Pattern.new("> <a href/=\"//wiki//Category:+1^\"\" title/=\"Category:[+1^\"]\">+1^,, [+1^ ] page")
var p2 = Pattern.new("subcatfrom/=[+1^#/#mw-subcategories]\"")
var findLangs = Fn.new {
var url = "https://rosettacode.org/w/index.php?title=Category:Programming_Languages"
var subcatfrom = ""
var langs = []
while (true) {
var content = getContent.call(url + subcatfrom)
var matches1 = p1.findAll(content)
for (m in matches1) {
var name = m.capsText[0]
var tasks = Num.fromString(m.capsText[1].replace(",", ""))
langs.add([name, tasks])
}
var m2 = p2.find(content)
if (m2) subcatfrom = "&subcatfrom=%(m2.capsText[0])" else break
}
return langs
}
var langs = findLangs.call()
langs.sort { |a, b| a[1] > b[1] }
System.print("Languages with most examples as at 3 February, 2024:")
var rank = 0
var lastScore = 0
var lastRank = 0
for (i in 0...langs.count) {
var pair = langs[i]
var eq = " "
rank = i + 1
if (lastScore == pair[1]) {
eq = "="
rank = lastRank
} else {
lastScore = pair[1]
lastRank = rank
}
Fmt.print("$-3d$s $-20s $,5d", rank, eq, pair[0], pair[1])
}

View file

@ -1,191 +0,0 @@
/* gcc Rosetta_Code_Rank_languages_by_popularity.c -o Rosetta_Code_Rank_languages_by_popularity -lcurl -lwren -lm */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <curl/curl.h>
#include "wren.h"
struct MemoryStruct {
char *memory;
size_t size;
};
/* C <=> Wren interface functions */
static size_t WriteMemoryCallback(void *contents, size_t size, size_t nmemb, void *userp) {
size_t realsize = size * nmemb;
struct MemoryStruct *mem = (struct MemoryStruct *)userp;
char *ptr = realloc(mem->memory, mem->size + realsize + 1);
if(!ptr) {
/* out of memory! */
printf("not enough memory (realloc returned NULL)\n");
return 0;
}
mem->memory = ptr;
memcpy(&(mem->memory[mem->size]), contents, realsize);
mem->size += realsize;
mem->memory[mem->size] = 0;
return realsize;
}
void C_bufferAllocate(WrenVM* vm) {
struct MemoryStruct *ms = (struct MemoryStruct *)wrenSetSlotNewForeign(vm, 0, 0, sizeof(struct MemoryStruct));
ms->memory = malloc(1);
ms->size = 0;
}
void C_bufferFinalize(void* data) {
struct MemoryStruct *ms = (struct MemoryStruct *)data;
free(ms->memory);
}
void C_curlAllocate(WrenVM* vm) {
CURL** pcurl = (CURL**)wrenSetSlotNewForeign(vm, 0, 0, sizeof(CURL*));
*pcurl = curl_easy_init();
}
void C_value(WrenVM* vm) {
struct MemoryStruct *ms = (struct MemoryStruct *)wrenGetSlotForeign(vm, 0);
wrenSetSlotString(vm, 0, ms->memory);
}
void C_easyPerform(WrenVM* vm) {
CURL* curl = *(CURL**)wrenGetSlotForeign(vm, 0);
curl_easy_perform(curl);
}
void C_easyCleanup(WrenVM* vm) {
CURL* curl = *(CURL**)wrenGetSlotForeign(vm, 0);
curl_easy_cleanup(curl);
}
void C_easySetOpt(WrenVM* vm) {
CURL* curl = *(CURL**)wrenGetSlotForeign(vm, 0);
CURLoption opt = (CURLoption)wrenGetSlotDouble(vm, 1);
if (opt < 10000) {
long lparam = (long)wrenGetSlotDouble(vm, 2);
curl_easy_setopt(curl, opt, lparam);
} else if (opt < 20000) {
if (opt == CURLOPT_WRITEDATA) {
struct MemoryStruct *ms = (struct MemoryStruct *)wrenGetSlotForeign(vm, 2);
curl_easy_setopt(curl, opt, (void *)ms);
} else if (opt == CURLOPT_URL) {
const char *url = wrenGetSlotString(vm, 2);
curl_easy_setopt(curl, opt, url);
}
} else if (opt < 30000) {
if (opt == CURLOPT_WRITEFUNCTION) {
curl_easy_setopt(curl, opt, &WriteMemoryCallback);
}
}
}
WrenForeignClassMethods bindForeignClass(WrenVM* vm, const char* module, const char* className) {
WrenForeignClassMethods methods;
methods.allocate = NULL;
methods.finalize = NULL;
if (strcmp(module, "main") == 0) {
if (strcmp(className, "Buffer") == 0) {
methods.allocate = C_bufferAllocate;
methods.finalize = C_bufferFinalize;
} else if (strcmp(className, "Curl") == 0) {
methods.allocate = C_curlAllocate;
}
}
return methods;
}
WrenForeignMethodFn bindForeignMethod(
WrenVM* vm,
const char* module,
const char* className,
bool isStatic,
const char* signature) {
if (strcmp(module, "main") == 0) {
if (strcmp(className, "Buffer") == 0) {
if (!isStatic && strcmp(signature, "value") == 0) return C_value;
} else if (strcmp(className, "Curl") == 0) {
if (!isStatic && strcmp(signature, "easySetOpt(_,_)") == 0) return C_easySetOpt;
if (!isStatic && strcmp(signature, "easyPerform()") == 0) return C_easyPerform;
if (!isStatic && strcmp(signature, "easyCleanup()") == 0) return C_easyCleanup;
}
}
return NULL;
}
static void writeFn(WrenVM* vm, const char* text) {
printf("%s", text);
}
void errorFn(WrenVM* vm, WrenErrorType errorType, const char* module, const int line, const char* msg) {
switch (errorType) {
case WREN_ERROR_COMPILE:
printf("[%s line %d] [Error] %s\n", module, line, msg);
break;
case WREN_ERROR_STACK_TRACE:
printf("[%s line %d] in %s\n", module, line, msg);
break;
case WREN_ERROR_RUNTIME:
printf("[Runtime Error] %s\n", msg);
break;
}
}
char *readFile(const char *fileName) {
FILE *f = fopen(fileName, "r");
fseek(f, 0, SEEK_END);
long fsize = ftell(f);
rewind(f);
char *script = malloc(fsize + 1);
fread(script, 1, fsize, f);
fclose(f);
script[fsize] = 0;
return script;
}
static void loadModuleComplete(WrenVM* vm, const char* module, WrenLoadModuleResult result) {
if( result.source) free((void*)result.source);
}
WrenLoadModuleResult loadModule(WrenVM* vm, const char* name) {
WrenLoadModuleResult result = {0};
if (strcmp(name, "random") != 0 && strcmp(name, "meta") != 0) {
result.onComplete = loadModuleComplete;
char fullName[strlen(name) + 6];
strcpy(fullName, name);
strcat(fullName, ".wren");
result.source = readFile(fullName);
}
return result;
}
int main(int argc, char **argv) {
WrenConfiguration config;
wrenInitConfiguration(&config);
config.writeFn = &writeFn;
config.errorFn = &errorFn;
config.bindForeignClassFn = &bindForeignClass;
config.bindForeignMethodFn = &bindForeignMethod;
config.loadModuleFn = &loadModule;
WrenVM* vm = wrenNewVM(&config);
const char* module = "main";
const char* fileName = "Rosetta_Code_Rank_languages_by_popularity.wren";
char *script = readFile(fileName);
WrenInterpretResult result = wrenInterpret(vm, module, script);
switch (result) {
case WREN_RESULT_COMPILE_ERROR:
printf("Compile Error!\n");
break;
case WREN_RESULT_RUNTIME_ERROR:
printf("Runtime Error!\n");
break;
case WREN_RESULT_SUCCESS:
break;
}
wrenFreeVM(vm);
free(script);
return 0;
}

View file

@ -0,0 +1,45 @@
import "os" for Process
import "timer" for Now
import "./xsequence" for XDocument
import "./fmt" for Fmt
var urlBase = "https://rosettacode.org/w/api.php?action=query&format=xml&generator=categorymembers&gcmtitle=Category:Programming\%20Languages&gcmlimit=500&prop=categoryinfo"
var results = []
var url = urlBase
while (true) {
var content = Process.read("curl -s -L \"%(url)\"")
var doc = XDocument.parse(content)
for (p in doc.root.element("query").element("pages").elements("page")) {
if (p.attributeValue("ns") == "14") {
var ci = p.element("categoryinfo")
var numTasks = ci.attributeValue("pages", Num, 0)
var language = p.attributeValue("title")[9..-1]
results.add([language, numTasks])
}
}
var cel = doc.root.element("continue")
if (!cel) break
var gcmcont = "&gcmcontinue=%(cel.attribute("gcmcontinue").value)"
var cont = "&continue=%(cel.attribute("continue").value)"
url = urlBase + gcmcont + cont
}
results.sort { |a, b| a[1] > b[1] }
var date = "%(Now.day) %(Now.monthName), %(Now.year)"
System.print("Languages with most tasks completed as at %(date):\n")
var rank = 0
var lastScore = 0
var lastRank = 0
for (i in 0..29) { // just show top 30
var pair = results[i]
var eq = " "
rank = i + 1
if (lastScore == pair[1]) {
eq = "="
rank = lastRank
} else {
lastScore = pair[1]
lastRank = rank
}
Fmt.print("$-2d$s $-11s $4d", rank, eq, pair[0], pair[1])
}