User:Teapeat/segregate-refs.js
Appearance
Code that you insert on this page could contain malicious content capable of compromising your account. If you import a script from another page with "importScript", "mw.loader.load", "iusc", or "lusc", take note that this causes you to dynamically load a remote script, which could be changed by others. Editors are responsible for all edits and actions they perform, including by scripts. User scripts are not centrally supported and may malfunction or become inoperable due to software changes. A guide to help you find broken scripts is available. If you are unsure whether code you are adding to this page is safe, you can ask at the appropriate village pump. This code will be executed when previewing this page. |
![]() | This user script seems to have a documentation page at User:Teapeat/segregate-refs. |
//<pre><nowiki>
/* segregate-refs.js: A user script to simplify editing of articles
using inline ref tags with the Cite.php extension to MediaWiki.
Copyright (c) 2010, PleaseStand
Copyright (c) 2011, Teapeat
This software is licensed under these licenses:
1. Creative Commons Attribution-Share Alike 3.0 Unported License
(see <http://creativecommons.org/licenses/by-sa/3.0/> for the text)
2. GNU Free Documentation License, any published version.
(see <http://www.gnu.org/copyleft/fdl.html> for the text)
3. Permission to use, copy, modify, and/or distribute this software for any
purpose with or without fee is hereby granted, provided that the above
copyright notice and this permission notice appear in all copies.
THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
You may select the license(s) of your choice if you wish to copy, modify, or
distribute this software. If you modify the software and do not wish to
license your changes under one or more of the licenses, please remove
the license(s) from the list above.
*/
/*global window, addOnloadHook, SegregateRefsJsL10n,
SegregateRefsJsEmptyRefsWarningGiven, SegregateRefsJsAllowConversion,
SegregateRefsJsCompleteSearch, wikEdUseWikEd, WikEdUpdateTextarea,
WikEdUpdateFrame*/
// Translate the right-hand side of these if necessary.
// Put translations in a separate file, changing the first line to:
// var SegregateRefsJsL10n = {
var SegregateRefsJsMsgs = {
version: 1.11,
buttonText: "Segregate refs for editing",
buttonStyle: "background: #dfd;",
buttonConvertText: "Migrate article to LDR",
buttonConvertStyle: "background: #fdd;",
autoWord: "Auto",
emptyRefsWarning: "IMPORTANT: This page includes one or more named " +
"footnotes of which the first occurrence(s) have no contents, which is " +
"not best practice. This script does not harm such footnotes, however " +
"you should be aware that this script ONLY CHECKS THE FIRST REF TAG " +
"it finds for the actual citation or note text, and you must work within " +
"this limitation. Any change to the empty ref tag will replace the " +
"footnote entirely and leave the old note text hidden.\n\n" +
"BEFORE concluding from the footnotes list that a ref is in fact empty, " +
"please manually check all identically-named ref tags for the contents. " +
"\n\nDo you acknowledge this limitation of the script? DO NOT CLICK OK " +
"UNTIL YOU HAVE READ THE ABOVE INFORMATION.",
convertRefsWarning: "WARNING: You need consensus to migrate an article " +
"to list-defined references format (LDR) BEFORE you do so.\n\nClick " +
"Cancel now if consensus has not been established in favor of this " +
"migration. If there is consensus to make the conversion, click OK to " +
"do so.",
groupPrompt: "Please enter the name of a group (as it appears in the " +
"wikitext, including any quotes). Leave this blank if unsure.",
refsHeader: "Inline footnotes",
convertHeader: "Generated refs list",
refsCommentIncomplete: "<!-- This list of footnotes may be incomplete. " +
"Do not use for conversion purposes. -->\n\n",
refsCommentComplete: "<!-- Converted to LDR format\n" +
" using [[User:PleaseStand/References segregator]] -->\n\n",
convertSummary: "Converted footnotes to LDR format (using " +
"[[User:PleaseStand/References segregator|segregate-refs]])",
convertFurther: "This script has done most of the work. However, you still " +
"need to do the following:\n\n* Insert the refs list in the new textbox " +
"into the proper place in the wikitext.\n* If converting a special " +
"group, optionally remove the group attributes.\n* Replace all " +
"autogenerated names with human-generated names.\n\nYou can do the above " +
"with the Find/Replace command in many text editors. (Always use the " +
"quoted form of the attributes.) Then, paste the text back into the edit " +
"form and save the page.",
integrateWarning: "The refs listed below are missing from the text. If you " +
"continue, they will be permanently deleted. Are you sure?\n\nUnused refs: "
};
// Begin encapsulation (prevent interference with other scripts)
(function(){
// Semi-global variables (private to this script)
var editForm, refsDiv, refsH2, mainTextbox, refsTextbox, randPrefix, messages,
refsButton, convertButton, complete, unloadHandlerRegistered = false;
// Define a (very important) function that is better than hasOwnProperty
function has(obj, key) {
return Object.hasOwnProperty.call(obj, key);
}
// Extend the string object with new methods
// Begin with the prefix "Ps" to avoid name clashes
// Add support for setting a slice of a string.
// (Only works with positive indices.)
String.prototype.PsSetSlice = function(replacement, indexFrom, indexTo) {
if(typeof indexTo == "undefined") {
return this.slice(0, indexFrom) + replacement;
}
return this.slice(0, indexFrom) + replacement + this.slice(indexTo);
};
// Add support for unquoting from HTML-quoted form.
String.prototype.PsHTMLUnquote = function() {
// Let's use the browser's functionality for the hard work,
// since MediaWiki/PHP supports many different HTML entities.
// (Note: innerHTML is not W3C-standard)
var d = window.document.createElement("div");
d.innerHTML = "<input value=" + this + "></input>";
return d.firstChild.value;
};
// Add support for quoting using HTML quotes. Chooses single quotes versus
// double quotes depending on which is shorter.
String.prototype.PsHTMLQuote = function() {
// Escape ampersands
var s = this.replace(/\&/g, "&");
// Try both kinds of quotes
var sQ = "'" + s.replace(/'/g, "'") + "'",
dQ = '"' + s.replace(/"/g, """) + '"';
// Choose the shorter, preferring double quotes if equal in length
return (sQ.length < dQ.length ? sQ : dQ);
};
// OBJECTS
// RefScanner: Use for identifying ref tags in text. (No nested refs please)
function RefScanner(argWikiText) {
this.wikiText = argWikiText;
// The tags listed below other than "ref" are there for an obvious reason.
// NB: "references" is here to prevent out-of-line refs from being returned.
this.refScanRegex = /(?:<!--[\s\S]*?-->|<(nowiki|source|references|ref)(?:\s|(?:[^"']|"[^"]*"|'[^']*')*?)(?:\/>|(?:>[\s\S]*?<\/\1(?:|\s[^>]*)>)))/gi;
}
RefScanner.prototype = {
// Returns the next ref found in the text
getRef: function getRef() {
var results;
do {
results = this.refScanRegex.exec(this.wikiText);
if(!results) {
return null;
}
if(typeof results[1] == "undefined") {
results = [0,0];
}
} while(results[1].toString().toLowerCase() != "ref");
return results[0];
}
};
// RefParser: Use for extracting attributes from ref tags
function RefParser(argWikiText) {
this.wikiText = argWikiText;
// The below regex is mostly a copy of the refScanRegex above, except that
// the whole string must be a ref, and no more, and two parts are extracted:
// $1=attributes, $2=remaining portion of ref
var refParseRegex = /^<ref(|\s(?:[^"']|"[^"]*"|'[^']*')*?)(\/>|(?:>[\s\S]*?<\/ref(?:|\s[^>]*)>))$/i;
this.parsedRef = refParseRegex.exec(this.wikiText);
if(!this.parsedRef) {
throw new Error("invalid ref");
}
}
RefParser.prototype = {
getAttributes: function getAttributes() {
// In this regex, we need to extract a single name-value pair at a time.
var attParseRegex = /\s([^\s=>]+)\s*=\s*("[^"]*"|'[^']*'|[^\s"']*)/g;
if(!this.parsedRef) {
return null;
}
var attributes = {}, results;
while((results = attParseRegex.exec(this.parsedRef[1]))) {
attributes[results[1].toLowerCase()] = results[2].PsHTMLUnquote();
}
return attributes;
}
};
// FUNCTIONS
// segregateRefs: Use for segregating refs from content.
// If completeSearch == true, the function looks in all occurrences for ref
// contents. If completeSearch == false, the function only checks the first.
// group is the reference group to limit the operation to. The empty string
// refers to all ungrouped refs.
function segregateRefs(argWikiText, completeSearch, group) {
// Create a random prefix for autogenerated ref names.
// in theory this has a 1/1296 probability of collision - extremely low
var prefixChars = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ",
randNo = Math.floor(Math.random() *
(prefixChars.length * prefixChars.length));
randPrefix = messages.autoWord + prefixChars.charAt(Math.floor(randNo /
prefixChars.length)) + prefixChars.charAt(randNo % prefixChars.length) +
"-";
// Create the beginning of the code for a preferred ref location
var refPreferred = "<ref ";
// Variables for the main code
var scanner = new RefScanner(argWikiText), unnamedRefs = 0, refNames = {},
ref, refStored, parser, attributes, refName, refLong, refShort,
refCodes = [], refEmpty, emptyRefsWarningGiven = false, refGroup;
// Disable the empty refs warning (see below) if the user has disabled it
if(typeof SegregateRefsJsEmptyRefsWarningGiven != "undefined" &&
SegregateRefsJsEmptyRefsWarningGiven) {
emptyRefsWarningGiven = true;
}
while((ref = scanner.getRef())) {
parser = new RefParser(ref);
attributes = parser.getAttributes();
// First make sure that the ref is in the right group.
refGroup = has(attributes, "group") ? attributes.group : "";
if(group != refGroup) {
continue;
}
// Does the ref have a name?
// (Note: No matter how incorrect it seems, the empty string is
// an acceptable ref name to the MediaWiki parser, as verified by
// informal testing.)
if(!has(attributes, "name")) {
// Bad: it doesn't have one - create a name for it
refStored = false;
refEmpty = false;
refName = false; // randPrefix + (++unnamedRefs).toString(10);
refLong = ref;
// Change the corresponding ref code
//refLong = "<ref name=" + refName.PsHTMLQuote() +
// parser.parsedRef[1] + parser.parsedRef[2];
} else {
// Good: it has a name.
refName = attributes.name;
refLong = ref;
// Check if the ref name has already been seen.
refStored = has(refNames, refName);
// Check if the ref has no contents.
refEmpty = (parser.parsedRef[2].slice(-2) == "/>") ||
(parser.parsedRef[2].slice(0, 3) == "></");
// Since this script, when not set in complete search mode, checks
// only the first occurrence of a ref for contents, inform the user
// of this limitation if it may pose a problem.
// if(!completeSearch && !emptyRefsWarningGiven && !refStored) {
// if(refEmpty) {
// if(!window.confirm(messages.emptyRefsWarning)) {
// return false;
// }
// emptyRefsWarningGiven = true;
// }
// }
}
// Is the ref's name unique?
if ((!refStored) && (!refName == false) && (!refEmpty)) {
// Unique: add it to the list of refs
refNames[refName] = {
code: refCodes.length,
empty: refEmpty
};
refCodes[refNames[refName].code] = refLong;
// Make a short code for the ref
if(refEmpty) {
refShort = refLong;
} else if(!refGroup.length) {
refShort = refPreferred + "name=" +
refName.PsHTMLQuote() + "/>";
} else {
refShort = refPreferred + "name=" + refName.PsHTMLQuote() +
" " + "group=" + refGroup.PsHTMLQuote() + "/>";
}
// is this an unnamed reference?
} else if (refName == false) {
// yes, igmore it
refShort = refLong;
// Otherwise, is the current longcode not empty?
// (only when in complete search mode, and when another non-empty,
// same-named ref has not been encountered)
} else if (completeSearch && !refEmpty && refNames[refName].empty) {
// Not empty: fill in the long code and make a short code
refCodes[refNames[refName].code] = refLong;
refNames[refName].empty = false;
if(!refGroup.length) {
refShort = refPreferred + "name=" +
refName.PsHTMLQuote() + "/>";
} else {
refShort = refPreferred + "name=" + refName.PsHTMLQuote() +
" " + "group=" + refGroup.PsHTMLQuote() + "/>";
}
} else {
// Always leave the ref as is if we're not truncating due to being named- teapeat
refShort = refLong;
}
// Replace the long code with the short code
scanner.wikiText = scanner.wikiText.PsSetSlice(refShort,
scanner.refScanRegex.lastIndex - ref.length,
scanner.refScanRegex.lastIndex);
// Update lastIndex accordingly
scanner.refScanRegex.lastIndex += refShort.length - ref.length;
}
return {
wikiText: scanner.wikiText,
refCodes: refCodes,
randPrefix: randPrefix
};
}
// integrateRefs: Use for inserting ref contents back into text
function integrateRefs(argWikiText, argRefText, randPrefix) {
// A function to remove an autogenerated ref name (if possible)
function cleanRefLong(dirtyRef) {
var cleanRegex = /^<(ref) name=(?:"[^"]*"|'[^']*'|[^\s"']*)/i;
return dirtyRef.replace(cleanRegex, "<$1");
}
// Variables for the main code
var scanner, ref, parser, attributes, refCodes = {}, usageFreq = {},
preferredRef = {}, refLong;
// First, we build an associative array of all the ref codes
// that we might need to put back into the text.
// NOTE: JavaScript does not actually offer real associative array
// functionality, so we emulate it using objects and the has() function
// we defined earlier that is used to verify a property's existence.
scanner = new RefScanner(argRefText);
while((ref = scanner.getRef())) {
parser = new RefParser(ref);
attributes = parser.getAttributes();
if(has(attributes, "name")) {
// Only use the first ref with each name
if(!refCodes.hasOwnProperty(attributes.name)) {
refCodes[attributes.name] = ref;
}
}
}
// Next, we build an associative array that holds the usage frequency
// of every ref name used in text
scanner = new RefScanner(argWikiText);
while((ref = scanner.getRef())) {
parser = new RefParser(ref);
attributes = parser.getAttributes();
if(has(attributes, "name")) {
if(!has(usageFreq, attributes.name)) {
// We found a new name
usageFreq[attributes.name] = 1;
} else {
// We already found this name
usageFreq[attributes.name]++;
}
}
}
// Finally, we go through the text again and this time we insert the
// ref codes where we need to, but only in the first place
// a ref name appears (or the first preferred location).
scanner = new RefScanner(argWikiText);
while((ref = scanner.getRef())) {
parser = new RefParser(ref);
attributes = parser.getAttributes();
if(has(attributes, "name")) {
// Is this name on the replacement list?
if(has(refCodes, attributes.name)) {
// Is this name an autogenerated name?
if(attributes.name.slice(0, randPrefix.length) == randPrefix) {
// Yes: is the name used multiple times?
if(usageFreq[attributes.name] > 1) {
// Multiple: the replacement code should be the same
// as that stored in the ref textbox.
refLong = refCodes[attributes.name];
} else {
// Single: replacement code must not include the name,
// at least not if the citation was untouched.
// (We don't want to add unnecessary autonames)
refLong = cleanRefLong(refCodes[attributes.name]);
}
} else {
// No: the replacement code should be the same
// as that stored in the ref textbox.
// (We want to preserve all human-generated names)
refLong = refCodes[attributes.name];
}
// Replace the short code with the long code
scanner.wikiText = scanner.wikiText.PsSetSlice(refLong,
scanner.refScanRegex.lastIndex - ref.length,
scanner.refScanRegex.lastIndex);
// Update lastIndex accordingly
scanner.refScanRegex.lastIndex += refLong.length - ref.length;
// Delete the name from the replacement list
delete refCodes[attributes.name];
}
}
}
// Return both the combined output and the ref codes that were not used.
return {wikiText: scanner.wikiText, unusedRefs: refCodes};
}
// Clears the undo history of a textarea by removing it
// from the DOM and then inserting it again.
function clearUndoHistory(ta) {
var pn = ta.parentNode, ns = ta.nextSibling;
pn.insertBefore(pn.removeChild(ta), ns);
}
function unloadHandler(evt) {
// Local variables
var result, refName, unusedRefNamesQuoted = [];
// wikEd compatibility (frame -> textarea)
if(typeof wikEdUseWikEd != "undefined" && wikEdUseWikEd) {
WikEdUpdateTextarea();
}
// Do the actual integration work
result = integrateRefs(mainTextbox.value, refsTextbox.value,
randPrefix, complete);
// Find all unused ref names
for(refName in result.unusedRefs) {
if(has(result.unusedRefs, refName)) {
unusedRefNamesQuoted.push(refName.PsHTMLQuote());
}
}
// If any refs are unused, warn and allow the user to cancel;
// we do not do this on unload because it is not really possible.
if(evt.type == "submit" && unusedRefNamesQuoted.length) {
if(!window.confirm(messages.integrateWarning +
unusedRefNamesQuoted.join(", "))) {
// Don't submit form
evt.preventDefault();
return false;
}
}
// Otherwise, update the textbox.
mainTextbox.value = result.wikiText;
// wikEd compatibility (textarea -> frame)
if(typeof wikEdUseWikEd != "undefined" && wikEdUseWikEd) {
WikEdUpdateFrame();
}
// Deactivate this event handler
window.removeEventListener("submit", unloadHandler, false);
window.removeEventListener("unload", unloadHandler, false);
unloadHandlerRegistered = false;
// We can delete the header and refs textbox now
refsDiv.removeChild(refsH2);
refsDiv.removeChild(refsTextbox);
return true;
}
function refsButtonHandler() { // Called when script activated by button click
// Both buttons should disappear
if(convertButton.parentNode){
convertButton.parentNode.removeChild(convertButton);
}
if(refsButton.parentNode) {
refsButton.parentNode.removeChild(refsButton);
}
// Allow for disabling usage of the complete search mode
// when segregating refs for editing.
if(typeof SegregateRefsJsCompleteSearch != "undefined" &&
!SegregateRefsJsCompleteSearch) {
complete = false;
} else {
complete = true;
}
// wikEd compatibility (frame -> textarea)
if(typeof wikEdUseWikEd != "undefined" && wikEdUseWikEd) {
WikEdUpdateTextarea();
}
// Do the actual segregation work and save the random prefix
var segFormat = segregateRefs(mainTextbox.value, complete, "");
if(!segFormat) {
return false;
}
randPrefix = segFormat.randPrefix;
// Update the textbox
mainTextbox.value = segFormat.wikiText;
clearUndoHistory(mainTextbox);
// wikEd compatibility (textarea -> frame)
if(typeof wikEdUseWikEd != "undefined" && wikEdUseWikEd) {
WikEdUpdateFrame();
}
// Inline refs header
refsH2 = window.document.createElement("h2");
refsH2.appendChild(window.document.createTextNode(messages.refsHeader));
// Inline refs textbox
refsTextbox = window.document.createElement("textarea");
refsTextbox.id = "PsRefsTextbox";
if(!complete) {
refsTextbox.value = messages.refsCommentIncomplete +
segFormat.refCodes.join("\n\n");
} else {
refsTextbox.value = segFormat.refCodes.join("\n\n");
}
refsTextbox.rows = Math.floor(mainTextbox.rows / 2);
refsTextbox.cols = mainTextbox.cols;
// Add to document
refsDiv.appendChild(refsH2);
refsDiv.appendChild(refsTextbox);
// Set up the submit handler (to integrate refs when done editing)
window.addEventListener("submit", unloadHandler, false);
window.addEventListener("unload", unloadHandler, false);
unloadHandlerRegistered = true;
// Don't submit form
return false;
}
function convertButtonHandler() { // Called when script activated by button click
// Display warning
if(!window.confirm(messages.convertRefsWarning)) {
return false;
}
// Which group?
var group = window.prompt(messages.groupPrompt, "");
if(group === null) {
return false;
}
group = group.PsHTMLUnquote();
// The first button should disappear
if(refsButton.parentNode) {
refsButton.parentNode.removeChild(refsButton);
}
// Do the actual segregation work and save the random prefix
var segFormat = segregateRefs(mainTextbox.value, true, group);
if(!segFormat) {
return false;
}
randPrefix = segFormat.randPrefix;
// wikEd compatibility (frame -> textarea)
if(typeof wikEdUseWikEd != "undefined" && wikEdUseWikEd) {
WikEdUpdateTextarea();
}
// Update the textbox
mainTextbox.value = segFormat.wikiText;
clearUndoHistory(mainTextbox);
// wikEd compatibility (textarea -> frame)
if(typeof wikEdUseWikEd != "undefined" && wikEdUseWikEd) {
WikEdUpdateFrame();
}
// Inline refs header
refsH2 = window.document.createElement("h2");
refsH2.appendChild(window.document.createTextNode(messages.convertHeader));
// Inline refs textbox
if(!refsTextbox) {
// Does not exist; creating
refsTextbox = window.document.createElement("textarea");
refsTextbox.id = "PsRefsTextbox";
refsTextbox.value = messages.refsCommentComplete +
segFormat.refCodes.join("\n");
refsTextbox.rows = Math.floor(mainTextbox.rows / 2);
refsTextbox.cols = mainTextbox.cols;
// Add to document
refsDiv.appendChild(refsH2);
refsDiv.appendChild(refsTextbox);
} else {
// Already exists
refsTextbox.value = messages.refsCommentComplete +
segFormat.refCodes.join("\n");
}
// Set a default edit summary.
window.document.getElementById("wpSummary").value = messages.convertSummary;
// Show the further instructions.
window.alert(messages.convertFurther);
// Don't submit form
return false;
}
function getEditboxContents() { // ajaxPreview compatibility
if(unloadHandlerRegistered) {
// wikEd compatibility (frame -> textarea)
if(typeof wikEdUseWikEd != "undefined" && wikEdUseWikEd) {
WikEdUpdateTextarea();
}
return integrateRefs(mainTextbox.value, refsTextbox.value,
randPrefix, complete).wikiText;
} else {
return mainTextbox.value;
}
}
// Leave a global for ajaxPreview to use.
window.getEditboxContents = getEditboxContents;
function loadHandler() { // This function is called on page load
try {
// Don't continue if the browser is Internet Explorer
if(window.navigator.appName == "Microsoft Internet Explorer") {
return;
}
// Handle message translations
messages = (typeof SegregateRefsJsL10n == "object" &&
typeof SegregateRefsJsL10n.version != "undefined" &&
SegregateRefsJsL10n.version == 1.11 ? SegregateRefsJsL10n :
SegregateRefsJsMsgs);
// Only activate on edit pages (that are not section edit pages)
if(!window.document.getElementById("editform") ||
window.document.getElementById("editform").wpSection.value.length) {
return;
}
// Get the edit form
editForm = window.document.getElementById("editform");
// Get the edit box
mainTextbox = window.document.getElementById("wpTextbox1");
// Make the "segregate" button
refsButton = window.document.createElement("input");
refsButton.type = "button";
refsButton.value = messages.buttonText;
refsButton.setAttribute("style", messages.buttonStyle);
refsButton.onclick = refsButtonHandler;
// Make the "convert" button
convertButton = window.document.createElement("input");
convertButton.type = "button";
convertButton.value = messages.buttonConvertText;
convertButton.setAttribute("style", messages.buttonConvertStyle);
convertButton.onclick = convertButtonHandler;
if(typeof SegregateRefsJsAllowConversion == "undefined" ||
!SegregateRefsJsAllowConversion) {
convertButton.setAttribute("style", "display: none;");
}
// Add the refs div
refsDiv = window.document.createElement("div");
refsDiv.appendChild(refsButton);
refsDiv.appendChild(convertButton);
editForm.insertBefore(refsDiv,
window.document.getElementById("editpage-copywarn"));
} catch(e) {
}
}
// Register load handler
$(loadHandler);
})();
//</nowiki></pre>