Jump to content

User:Alien333/test

From Wikisource

(I stuff here various snippets of code, functional to diverse degrees.)

Transclusion guessing from TOC

[edit]
n = ;
s =``.replaceAll("\t", "\n").split("\n");
e = []; p = [];
for (let i=0;i<s.length;i++) {
  if (i%2) {
    p.push(Number(s[i])+n)
  } else
    e.push(s[i].trim())
};
for (let i=0;i<p.length;i++) {
  e[i] += "/" + p[i]+"-";
  if (i<p.length-1) {
    if (p[i+1] == p[i]) {
      e[i] += p[i] + "  a"
    } else {
      e[i] += p[i+1]-1
    }
  };
  if (i && e[i-1].slice(-1) == "a")
    e[i] += " b";
  e[i] = e[i].replace(/\/(\d+)-\1($| )/, "/$1$2")
};
console.log(e.join("\n"))

Works update

[edit]
// do the first line, then preview, then do the rest
$("#wpTextbox1").val($("#wpTextbox1").val().replaceAll(/(?<=\|)\d+(?=\||\}\})/g, "")); // empty all
l = $(".wst-progress-bar");
l = l.map(x => l[x].dataset);
n = [];
for (let i=0;i<l.length;i++) {
y = l[i];
f = x => x=="0"?"":x;
n.push([f(y.total), f(y.q4), f(y.q3), f(y.q2), f(y.q1), f(y.q0)])}
for (let x of n) {
    $("#wpTextbox1").val(
    $("#wpTextbox1").val()
    .replace(/(\{\{User:Alien333\/Poemrow\|.*?)\|\|\|\|\|\}\}/, "$1"+x.join("|")+"}}") // inject data
    )
}

Regex editing

[edit]
api.get({action:"query",generator:"search",gsrsearch:'',gsrlimit:200,prop:"info|revisions",rvprop:"content"}).done((a) => {
	etd = Object.values(a.query.pages).map(x => [x.title,x.revisions[0]["*"],x.revisions[0]["*"].replace("", "")]);
	console.log(etd.lengh)
	let f = (i) => {
		console.log(i);
		if (i >= etd.length) {
			return console.log("over");
		} else {
			api.post({action:"edit",title:etd[i][0],summary:"",text:etd[i][2],token:mw.user.tokens.get("csrfToken")})
			.done((a) => {console.log(a);f(i+1)}).fail(console.log)
		}
	}
	f(0);
}).fail(console.log)

Mass actions

[edit]
massaction = (a, l, r, t, s={}) => {
  let api = new mw.Api();
  let f = (i) => {
    if (i < l.length) {
      let base = {
        action: a,
        title: l[i],
        reason: r,
        token:t,
      };
      let par = { ...base, ...s };
      api.post(par).done((a)=>console(a));
      f(i+1);
    }
  };
  f(0);
}
l.forEach((s) => api.post({action:"delete", reason:r, title:s,token:token}).done(console.log).fail(console.log))

Deleting Index: & all Page:s

[edit]
index = ""; // index name, without ns prefix
n = ; // largest page number
l = Array.from(new Array(n), (x, i) => "Page:"+index+"/"+(i+1));
massaction("delete", l,[[WS:PD#Index:"+index+"|WS:PD discussion]]", mw.user.tokens.get("csrfToken"));

all poems in a Poems

[edit]
<templatestyles src="User:Alien333/NoHeaderOrSimilar.css"/>
{{#invoke:String|replace|{{#invoke:Parse|main|{{#invoke:Transclude list|main|Poems {{#invoke:String|replace|{{#invoke:String|replace|{{#invoke:String|sub|{{User:Alien333/Expand list|{{{1}}}}}|2|-2}}|
||all|false}}|{{!}}(|;Poems (}}}}}}|{{!}}|{{ppb}}}}

Getting hathi scan images

[edit]

(The delays are TBD. It's sure that it works with 2000, but might be able to put less.) 

next = $(`[aria-label="Next Page"]`);
down = $("p.mb-3 button");
page = $("#toolbar-seq");
page.value = "1";
page.dispatchEvent(new KeyboardEvent('blur'));
n = Number(page.parentElement.children[3].innerHTML);
f = (i) => {if (i == n+1) return; down.click(); setTimeout(() => {next.click();setTimeout(() => f(i+1), 1000)}, 1000)};
setTimeout(() => f(1), 1000);

Or, another way, which is probably better: 

n = Number($("#toolbar-seq").parentElement.children[3].innerHTML);
f = (i) => {
	if (i == n+1) return;
	p = $("#p"+i); // page parent item
	console.log(i);
	p.scrollIntoView();
	setTimeout(() => { // give image time to load
	x = $("#p"+i+" figure div img"); // img element
	canvas = document.createElement("canvas"); // draw it on a canvas
	document.body.appendChild(canvas);
	context = canvas.getContext("2d");
	canvas.height = x.clientHeight;
	canvas.width = x.clientWidth;
	context.drawImage(x, 0, 0);
	setTimeout(()=>{ // (giving it time)
	url = (x.src.startsWith("blob:"))?canvas.toDataURL("image/jpg"):(x.src); // to be able to get a file from the blob: url
	a = document.createElement("a"); // need to create a link to fake a click on it
	a.href = url;
	a.download = i;
	a.target = "_blank";
	document.body.appendChild(a);
	a.click()},2000)
	f(i+1);},2000)
}
f(1);

333Bot

[edit]
import pywikibot as pwb 
from pywikibot.pagegenerators import SearchPageGenerator
from pywikibot.data import api
import re
enws = pwb.Site("en", "wikisource")
wd = enws.data_repository()
### regular sitelinks, for pages that explicitly give it ###
gen = SearchPageGenerator("insource:/[wW]ikidata *= *Q[0-9]+/", site=enws, namespaces=[102,100,0])
for page in gen:
	title = page.title()
	content = page.text
	try:
		page.data_item() # means that it's correctly linked and we don't care
	except:
		qid = re.match(r"(.|\n)*[wW]ikidata *= *(Q[0-9]+)", content, re.M).groups()[1]
		item = pwb.ItemPage(wd, qid)
		try:
			item.getSitelink("enwikisource") # the item already has another enws sitelink
		except:
			try:
				item.setSitelink(sitelink={"site":"enwikisource", "title":title}, summary="added missing sitelink to English Wikisource (bot)")
				print("Added sitelink "+title+" to the item "+qid)
			except:
				print("Error: Addition of sitelink "+title+" to the item "+qid+" was skipped")
print("All pages with user-givn QIDs done.\nStarting the surname cats...")
### specific case for surname categories ###
def getitemforname(label):
	params = {'action': 'wbsearchentities', 'format': 'json',
			'language': 'en', 'type': 'item', 'limit':1,
			'search': label}
	request = api.Request(site=wd, **params)
	result = request.submit()
	for p in [pwb.ItemPage(wd, p["id"]) for p in result['search']]:
		print(p)
		if dict(p.get()["claims"])["P31"][0].getTarget().getID() == "Q101352": # return only family names
			return p
	return None
catlist = list(pwb.Category(enws, "Surnames").subcategories())
for p in catlist:
	title = p.title()
	try:
		p.data_item()
	except:
		item = getitemforname(p.title(with_ns=False)[:-len(" (surname)")])
		if item:
			try:
				item.getSitelink(sitelink={"site":"enwikisource","title":title})
			except:
				try:
					item.setSitelink(sitelink={"site":"enwikisource", "title":title}, summary="added missing sitelink to English Wikisource (bot)")
					print("Added sitelink "+title+" to the item "+qid)
				except:
					print("Error: Addition of sitelink "+title+" to the item "+qid+" was skipped")
		else:
			print("Item not found for surname cat "+title)
print("Categories done.\nOver and out.")


Transclusion arguments guessing

[edit]
Extended content
n = ;
index = "Poems djvu";
s = new Array(n);
api = new mw.Api();
for (let i=1;i<n;i++) {
  api.get({action:"query", prop:"revisions", rvprop:"content", rvslots:"main", titles:"Page:"+index+"/"+i, format:"json"}).done(q => {for (let o in q.query.pages) {s[i]=(q.query.pages[o])} })
}
e = [];
p = [];
istitle = /\{\{tpp\|/;
capitalize = s => s[0].toUpperCase()+s.slice(1);
rmpunct = s => s.replace(/[\.,;!\?]$/, "");
s.forEach(x => {
    content = x.revisions[0].slots.main["*"];
    if (istitle.test(content)) {
        title = /\{\{tpp\|([^\|\{\n]*)/s.exec(content);
        title = capitalize(rmpunct(title[1].split("\n")[0]).toLowerCase()).replaceAll(target, rep);
        number = Number(/\d+$/.exec(x.title)[0]);
        e.push(title);
        p.push(number);
  }
})
se = new Set(e);
dups = [];
for (let i=0;i<e.length;i++) {
    if (se.has(e[i])) {
        se.delete(e[i]);
    } else {
        dups.push(i);
    }
}
console.log(e.map(s => "* [[/"+s+"/]]").join("\n"))
for (let i=0;i<p.length;i++) {
    e[i] += "/" + p[i] + "-";
    if (i) {
        e[i-1] += p[i]-1;
    }
}
console.log(e.join("\n").replaceAll(/\/(\d+)-\1/g, "/$1"))


Retrieved from "https://en.wikisource.org/w/index.php?title=User:Alien333/test&oldid=14813499"