worm-scraper
Version:
Scrapes the web serial Worm and its sequel Ward into an ebook format
974 lines (812 loc) • 43.5 kB
JavaScript
"use strict";
const workerpool = require("workerpool");
const fs = require("fs");
const { JSDOM } = require("jsdom");
workerpool.worker({ convertChapter });
function convertChapter(chapter, bookTitle, inputPath, outputPath, chapterSubstitutions) {
const contents = fs.readFileSync(inputPath, { encoding: "utf-8" });
const rawChapterJSDOM = new JSDOM(contents);
const { output, warnings } = getChapterString(
chapter,
bookTitle,
chapterSubstitutions,
rawChapterJSDOM.window.document
);
// TODO: this should probably not be necessary... jsdom bug I guess!?
rawChapterJSDOM.window.close();
fs.writeFileSync(outputPath, output);
return warnings;
}
function getChapterString(chapter, bookTitle, chapterSubstitutions, rawChapterDoc) {
const { xml, warnings } =
getBodyXML(chapter, bookTitle, chapterSubstitutions, rawChapterDoc.querySelector(".entry-content"));
const output = `xml version="1.0" encoding="utf-8"
<html xmlns="http://www.w3.org/1999/xhtml" lang="en"
itemscope="itemscope" itemtype="https://schema.org/Chapter"
itemid="${chapter.url}" class="chapter ${bookTitle}">
<head>
<meta charset="utf-8"/>
<title>${chapter.usedTitle}</title>
<meta itemprop="datePublished" content="${chapter.datePublished}"/>
<link rel="stylesheet" href="../chapter.css"/>
</head>
${xml}
</html>`;
return { output, warnings };
}
function getBodyXML(chapter, bookTitle, chapterSubstitutions, contentEl) {
const warnings = [];
// Remove initial Next Chapter and Previous Chapter <p>
contentEl.firstElementChild.remove();
// Remove everything after the last <p> (e.g. analytics <div>s)
const lastP = contentEl.querySelector("p:last-of-type");
while (contentEl.lastElementChild !== lastP) {
contentEl.lastElementChild.remove();
}
// Remove empty <p>s or Last Chapter/Next Chapter <p>s
while (isEmptyOrGarbage(contentEl.firstChild)) {
contentEl.firstChild.remove();
}
while (isEmptyOrGarbage(contentEl.lastChild)) {
contentEl.lastChild.remove();
}
// Remove redundant attributes and style
for (const child of contentEl.children) {
if (child.getAttribute("dir") === "ltr") {
child.removeAttribute("dir");
}
// Only ever appears with align="LEFT" (useless) or align="CENTER" overridden by style="text-align: left;" (also
// useless)
child.removeAttribute("align");
const style = child.getAttribute("style");
if (style === "text-align:left;" || style === "text-align: left;") {
child.removeAttribute("style");
}
// Worm uses 30px; Ward mostly uses 40px but sometimes uses 30px/60px. Let's standardize on 30px.
if (style === "text-align:left;padding-left:30px;" ||
style === "text-align: left;padding-left: 40px;" ||
style === "text-align: left; padding-left: 40px;" ||
style === "padding-left: 40px;") {
child.setAttribute("style", "padding-left: 30px;");
}
}
// Remove empty inline elements.
// Remove style attributes from inline elements, as they're always messed up.
for (const el of contentEl.querySelectorAll("em, i, strong, b")) {
const { textContent } = el;
if (textContent === "") {
el.remove();
} else if (textContent.trim() === "") {
if (el.childElementCount === 0) {
el.replaceWith(" ");
} else if (el.childElementCount === 1 && el.children[0].localName === "br") {
el.outerHTML = "<br />\n";
}
} else {
el.removeAttribute("style");
}
}
// In https://parahumans.wordpress.com/2013/01/05/monarch-16-13/ there are some <address>s that should be <p>s O_o
for (const address of contentEl.querySelectorAll("address")) {
const p = contentEl.ownerDocument.createElement("p");
p.innerHTML = address.innerHTML;
address.replaceWith(p);
}
// Every <span> except underline ones is pointless at best and frequently messed up. (Weird font size, line spacing,
// etc.)
for (const span of contentEl.querySelectorAll("span")) {
const style = span.getAttribute("style");
if (style === "text-decoration:underline;" || style === "text-decoration: underline;") {
continue;
}
if (span.textContent.trim() === "") {
span.remove();
} else {
const docFrag = contentEl.ownerDocument.createDocumentFragment();
while (span.firstChild) {
docFrag.appendChild(span.firstChild);
}
span.replaceWith(docFrag);
}
}
// In Ward, CloudFlare email protection obfuscates the email addresses:
// https://usamaejaz.com/cloudflare-email-decoding/
for (const emailEl of contentEl.querySelectorAll("[data-cfemail]")) {
const decoded = decodeCloudFlareEmail(emailEl.dataset.cfemail);
emailEl.replaceWith(contentEl.ownerDocument.createTextNode(decoded));
}
// Synthesize a <body> tag to serialize
const bodyEl = contentEl.ownerDocument.createElement("body");
const h1El = contentEl.ownerDocument.createElement("h1");
h1El.textContent = chapter.usedTitle;
bodyEl.append(h1El, "\n\n");
while (contentEl.firstChild) {
bodyEl.append(contentEl.firstChild);
}
bodyEl.append("\n");
const xmlSerializer = new contentEl.ownerDocument.defaultView.XMLSerializer();
let xml = xmlSerializer.serializeToString(bodyEl);
// Fix recurring strange pattern of extra <br> in <p>...<em>...<br>\n</em></p>
xml = xml.replace(/<br \/>\s*<\/em><\/p>/vg, "</em></p>");
// Replace single-word <i>s with <em>s. Other <i>s are probably erroneous too, but these are known-bad.
xml = xml.replace(/<i>([^ ]+)<\/i>/vg, "<em>$1</em>");
xml = xml.replace(/<i>([^ ]+)( +)<\/i>/vg, "<em>$1</em>$2");
// There are way too many nonbreaking spaces where they don't belong. If they show up three in a row, then let them
// live; they're maybe being used for alignment or something. Otherwise, they die.
//
// Also, normalize spaces after a period/quote mark to two (normal) spaces. The second one is invisible when
// rendered, but it helps future heuristics detect end of sentences.
xml = xml.replace(/\xA0{1,2}(?!\x20\xA0)/vg, " ");
xml = xml.replace(/([.”])\x20*\xA0[\xA0\x20]*/vg, "$1 ");
xml = xml.replace(/([.”])\x20{3,}/vg, "$1 ");
function fixEms() {
// Fix recurring broken-up or erroneous <em>s
xml = xml.replace(/<\/em>‘s/vg, "’s</em>");
xml = xml.replace(/<em><\/em>/vg, "");
xml = xml.replace(/<\/em><em>/vg, "");
xml = xml.replace(/<em>(\s?\s?[^A-Za-z]\s?\s?)<\/em>/vg, "$1");
xml = xml.replace(/<\/em>(\s?\s?[^A-Za-z]\s?\s?)<em>/vg, "$1");
xml = xml.replace(/“<em>([^>]+)<\/em>(!|\?|\.)”/vg, "“<em>$1$2</em>”");
xml = xml.replace(/<p><em>([^>]+)<\/em>(!|\?|\.)<\/p>/vg, "<p><em>$1$2</em></p>");
xml = xml.replace(/(!|\?|\.)\s{2}<\/em><\/p>/vg, "$1</em></p>");
xml = xml.replace(/<em>([a-z]+)(\?|\.)<\/em>/vg, "<em>$1</em>$2");
xml = xml.replace(/<em>([^>]+?)( +)<\/em>/vg, "<em>$1</em>$2");
xml = xml.replace(/<em> ([a-zA-Z]+)<\/em>/vg, " <em>$1</em>");
xml = xml.replace(/<em>‘\s*([^<]+)\s*’<\/em>/vg, "‘<em>$1</em>’");
xml = xml.replace(/<em>‘\s*([^<]+)\s*<\/em>\s*’/vg, "‘<em>$1</em>’");
xml = xml.replace(/‘\s*<em>\s*([^<]+)\s*’<\/em>/vg, "‘<em>$1</em>’");
xml = xml.replace(/<em>“\s*([^<”]+)\s*”<\/em>/vg, "“<em>$1</em>”");
xml = xml.replace(/<em>“\s*([^<”]+)\s*<\/em>\s*”/vg, "“<em>$1</em>”");
xml = xml.replace(/“\s*<em>\s*([^<”]+)\s*”<\/em>/vg, "“<em>$1</em>”");
xml = xml.replace(/([^\n>])<em> ?/vg, "$1 <em>");
xml = xml.replace(/ ?<\/em>/vg, "</em> ");
xml = xml.replace(/<p([^>]+)> <em>/vg, "<p$1><em>");
xml = xml.replace(/<\/em> <\/p>/vg, "</em></p>");
xml = xml.replace(/<em>([a-z]+),<\/em>/vg, "<em>$1</em>,");
}
// These quote/apostrophe/em fixes interact with each other. TODO: try to disentangle so we don't repeat all of
// fixEms.
xml = xml.replace(/,” <\/em>/vg, "</em>,” ");
fixEms();
xml = xml.replace(/<p>”/vg, "<p>“");
xml = xml.replace(/“\s*<\/p>/vg, "”</p>");
xml = xml.replace(/“\s*<\/em><\/p>/vg, "</em>”</p>");
xml = xml.replace(/‘\s*<\/p>/vg, "’</p>");
xml = xml.replace(/‘\s*<\/em><\/p>/vg, "’</em></p>");
xml = xml.replace(/,” <\/em>/vg, "</em>,” ");
xml = xml.replace(/′/vg, "’");
xml = xml.replace(/″/vg, "”");
xml = xml.replace(/([A-Za-z])‘s(\s?)/vg, "$1’s$2");
xml = xml.replace(/I‘m/vg, "I’m");
xml = xml.replace(/<p>“\s+/vg, "<p>“");
xml = xml.replace(/\s+”/vg, "”");
xml = xml.replace(/'/vg, "’");
xml = xml.replace(/’([A-Za-z]+)’/vg, "‘$1’");
xml = xml.replace(/([a-z])”<\/p>/vg, "$1.”</p>");
fixEms();
xml = xml.replace(/‘<em>([^<]+)<\/em>‘/vg, "‘<em>$1</em>’");
xml = xml.replace(/<em>([a-z]+)!<\/em>/vg, "<em>$1</em>!");
xml = xml.replace(/(?<! {2})<em>([\w ’]+)([!.?])”<\/em>/vg, "<em>$1</em>$2”");
xml = xml.replace(/<em>([\w ’]+[!.?])”<\/em>/vg, "<em>$1</em>”");
xml = xml.replace(/I”(m|ll)/vg, "I’$1");
xml = xml.replace(/””<\/p>/vg, "”</p>");
xml = xml.replace(/^([^“]+?) ?”(?![ —<])/vgm, "$1 “");
xml = xml.replace(/(?<!“)<em>([A-Za-z]+),<\/em>(?!”| +[A-Za-z]+ thought)/vg, "<em>$1</em>,");
xml = xml.replace(/‘([Kk])ay(?!’)/vg, "’$1ay");
xml = xml.replace(/<em>(Why|What|Who|How|Where|When)<\/em>\?/vg, "<em>$1?</em>");
xml = xml.replace(/,<\/em>/vg, "</em>,");
xml = xml.replace(/,”<\/p>/vg, ".”</p>");
xml = xml.replace(/<p>(.*),<\/p>/vg, "<p>$1.</p>");
xml = xml.replace(/‘(\w+)‘(\w+)’/vg, "‘$1’$2’");
xml = xml.replace(/<em>([a-z]+), ([a-z]+)<\/em>/vg, "<em>$1</em>, <em>$2</em>");
// Similar problems occur in Ward with <b> and <strong> as do in Worm with <em>s
xml = xml.replace(/<b \/>/vg, "");
xml = xml.replace(/<b>(\s*<br \/>\s*)<\/b>/vg, "$1");
xml = xml.replace(/<strong>(\s*<br \/>\s*)<\/strong>/vg, "$1");
xml = xml.replace(/<\/strong>(\s*)<strong>/vg, "$1");
xml = xml.replace(/<strong>@<\/strong>/vg, "@");
xml = xml.replace(/<br \/>(\s*)<\/strong>/vg, "</strong><br />$1");
xml = xml.replace(/(\s*)<\/strong>/vg, "</strong>$1");
xml = xml.replace(/><strong>(.*)<\/strong>:</vg, "><strong>$1:</strong><");
xml = xml.replace(/<strong><br \/>\n/vg, "<br />\n<strong>");
// No need for line breaks before paragraph ends or after paragraph starts
// These often occur with the <br>s inside <b>/<strong>/<em>/<i> fixed above.
xml = xml.replace(/<br \/>\s*<\/p>/vg, "</p>");
xml = xml.replace(/<p><br \/>\s*/vg, "<p>");
// This is another quote fix but it needs to happen after the line break deletion... so entangled, ugh.
xml = xml.replace(/<\/em>\s*“\s*<\/p>/vg, "</em>”</p>");
// Fix missing spaces after commas
xml = xml.replace(/([a-zA-Z]+),([a-zA-Z]+)/vg, "$1, $2");
// Fix bad periods and spacing/markup surrounding them
xml = xml.replace(/\.\.<\/p>/vg, ".</p>");
xml = xml.replace(/\.\.”<\/p>/vg, ".”</p>");
xml = xml.replace(/ \. /vg, ". ");
xml = xml.replace(/ \.<\/p>/vg, ".</p>");
xml = xml.replace(/\.<em>\.\./vg, "<em>…");
xml = xml.replace(/\.\. {2}/vg, ". ");
xml = xml.replace(/\.\./vg, "…");
xml = xml.replace(/(?.
xml = xml.replaceAll(
`<body xmlns="http://www.w3.org/1999/xhtml">`,
`<body>\n`
);
return { xml, warnings };
}
function fixTruncatedWords(xml) {
xml = xml.replace(/‘Sup/vg, "’Sup");
xml = xml.replace(/‘cuz/vg, "’cuz");
// Short for "Sidepeace"
xml = xml.replace(/[‘’][Pp]iece(?![a-z])/vg, "’Piece");
// Short for "Disjoint"
xml = xml.replace(/[‘’][Jj]oint(?![a-z])/vg, "’Joint");
// Short for "Contender"
xml = xml.replace(/[‘’][Tt]end(?![a-z])/vg, "’Tend");
// Short for "Anelace"
xml = xml.replace(/[‘’][Ll]ace(?![a-z])/vg, "’Lace");
// Short for "Birdcage"
xml = xml.replace(/[‘’][Cc]age(?![a-z])/vg, "’Cage");
// We can't do "’Clear" (short for Crystalclear) here because it appears too much as a normal word preceded by an
// open quote, so we do that in the substitutions file.
return xml;
}
function fixDialogueTags(xml) {
// Fix recurring miscapitalization with questions
xml = xml.replace(/\?”\s\s?She asked/vg, "?” she asked");
xml = xml.replace(/\?”\s\s?He asked/vg, "?” he asked");
// The author often fails to terminate a sentence, instead using a comma after a dialogue tag. For example,
// > “I didn’t get much done,” Greg said, “I got distracted by...
// This should instead be
// > “I didn’t get much done,” Greg said. “I got distracted by...
//
// Our heuristic is to try to automatically fix this if the dialogue tag is two words (X said/admitted/sighed/etc.).
//
// This sometimes overcorrects, as in the following example:
// > “Basically,” Alec said, “For your powers to manifest, ...
// Here instead we should lowercase the "f". We handle that via one-offs in the substitutions file.
//
// This applies to ~800 instances, so although we have to correct back in the substitutions file a decent number of
// times, it definitely pays for itself. Most of the instances we have to correct back we also need to fix the
// capitalization anyway, and that's harder to do automatically, since proper names/"I"/etc. stay capitalized.
xml = xml.replace(/,” ([A-Za-z]+ [A-Za-z]+), “([A-Z])/vg, ",” $1. “$2");
return xml;
}
function fixForeignNames(xml) {
// This is consistently missing diacritics
xml = xml.replace(/Yangban/vg, "Yàngbǎn");
// These are usually not italicized, but sometimes are. Other foreign-language names (like Yàngbǎn) are not
// italicized, so we go in the direction of removing the italics.
xml = xml.replace(/<em>Garama<\/em>/vg, "Garama");
xml = xml.replace(/<em>Thanda<\/em>/vg, "Thanda");
xml = xml.replace(/<em>Sifara([^<]*)<\/em>/vg, "Sifara$1");
xml = xml.replace(/<em>Moord Nag([^<]*)<\/em>/vg, "Moord Nag$1");
xml = xml.replace(/<em>Califa de Perro([^<]*)<\/em>/vg, "Califa de Perro$1");
xml = xml.replace(/<em>Turanta([^<]*)<\/em>/vg, "Turanta$1");
return xml;
}
function standardizeNames(xml) {
// 197 instances of "Mrs." to 21 of "Ms."
xml = xml.replace(/Ms\. Yamada/vg, "Mrs. Yamada");
// 25 instances of "Amias" to 3 of "Amais"
xml = xml.replace(/Amais/vg, "Amias");
// 185 instances of Juliette to 4 of Juliet
xml = xml.replace(/Juliet(?=\b)/vg, "Juliette");
// Earlier chapters have a space; later ones do not. They're separate words, so side with the earlier chapters.
// One location is missing the "k".
xml = xml.replace(/Crock? o[‘’]Shit/vg, "Crock o’ Shit");
// 5 instances of "Jotun" to 2 of "Jotunn"
xml = xml.replace(/Jotunn/vg, "Jotun");
// 13 instances of Elman to 1 of Elmann
xml = xml.replace(/Elmann/vg, "Elman");
// Thousands of instances of Tattletale to 4 instances of Tatteltale
xml = xml.replace(/Tatteltale/vg, "Tattletale");
// 73 instances of Über to 2 of Uber
xml = xml.replace(/Uber/vg, "Über");
// 5 instances of Johnsonjar to 2 instances of JohnsonJar
xml = xml.replace(/JohnsonJar/vg, "Johnsonjar");
// 4 instances of Flying_Kevin to 2 instances of FlyingKevin
xml = xml.replace(/FlyingKevin/vg, "Flying_Kevin");
return xml;
}
function fixEmDashes(xml) {
xml = xml.replace(/ – /vg, "—");
xml = xml.replace(/“((?:<em>)?)-/vg, "“$1—");
xml = xml.replace(/-[,.]?”/vg, "—”");
xml = xml.replace(/-(!|\?)”/vg, "—$1”");
xml = xml.replace(/-[,.]?<\/([a-z]+)>”/vg, "—</$1>”");
xml = xml.replace(/-“/vg, "—”");
xml = xml.replace(/<p>-/vg, "<p>—");
xml = xml.replace(/-<\/p>/vg, "—</p>");
xml = xml.replace(/-<br \/>/vg, "—<br />");
xml = xml.replace(/-<\/([a-z]+)><\/p>/vg, "—</$1></p>");
xml = xml.replace(/\s?\s?–\s?\s?/vg, "—");
xml = xml.replace(/-\s\s?/vg, "—");
xml = xml.replace(/\s?\s-/vg, "—");
xml = xml.replace(/\s+—”/vg, "—”");
xml = xml.replace(/I-I/vg, "I—I");
xml = xml.replace(/I-uh/vg, "I—uh");
xml = xml.replace(/-\?/vg, "—?");
return xml;
}
function enDashJointNames(xml) {
// Joint names should use en dashes
xml = xml.replace(/Dallon-Pelham/vg, "Dallon–Pelham");
xml = xml.replace(/Bet-Gimel/vg, "Bet–Gimel");
xml = xml.replace(/Cheit-Gimel/vg, "Bet–Gimel");
xml = xml.replace(/Tristan-Capricorn/vg, "Tristan–Capricorn");
xml = xml.replace(/Capricorn-Byron/vg, "Capricorn–Byron");
xml = xml.replace(/Tristan-Byron/vg, "Tristan–Byron");
xml = xml.replace(/Gimel-Europe/vg, "Gimel–Europe");
xml = xml.replace(/G-N/vg, "G–N");
xml = xml.replace(/Imp-Damsel/vg, "Imp–Damsel");
xml = xml.replace(/Damsel-Ashley/vg, "Damsel–Ashley");
xml = xml.replace(/Antares-Anelace/vg, "Antares–Anelace");
xml = xml.replace(/Challenger-Gallant/vg, "Challenger–Gallant");
xml = xml.replace(/Undersider(s?)-(Breakthrough|Ambassador)/vg, "Undersider$1–$2");
xml = xml.replace(/Norwalk-Fairfield/vg, "Norwalk–Fairfield");
xml = xml.replace(/East-West/vg, "east–west");
xml = xml.replace(/Creutzfeldt-Jakob/vg, "Creutzfeldt–Jakob");
xml = xml.replace(/Astaroth-Nidhug/vg, "Astaroth–Nidhug");
xml = xml.replace(/Capulet-Montague/vg, "Capulet–Montague");
xml = xml.replace(/Weaver-Clockblocker/vg, "Weaver–Clockblocker");
xml = xml.replace(/Alexandria-Pretender/vg, "Alexandria–Pretender");
xml = xml.replace(/Night Hag-Nyx/vg, "Night Hag–Nyx");
xml = xml.replace(/Crawler-Breed/vg, "Crawler–Breed");
xml = xml.replace(/Simurgh-Myrddin-plant/vg, "Simurgh–Myrddin–plant");
xml = xml.replace(/Armsmaster-Defiant/vg, "Armsmaster–Defiant");
xml = xml.replace(/Matryoshka-Valentin/vg, "Matryoshka–Valentin");
xml = xml.replace(/Gaea-Eden/vg, "Gaea–Eden");
xml = xml.replace(/([Aa])gent-parahuman/vg, "$1gent–parahuman");
xml = xml.replace(/([Pp])arahuman-agent/vg, "$1arahuman–agent");
return xml;
}
function fixPossessives(xml) {
// Fix possessive of names ending in "s".
xml = xml.replace(
// eslint-disable-next-line max-len
/(?<!‘)(Judas|Brutus|Jess|Aegis|Dauntless|Circus|Sirius|Brooks|Genesis|Atlas|Lucas|Gwerrus|Chris|Eligos|Animos|Mags|Huntress|Hephaestus|Lord of Loss|John Combs|Mama Mathers|Monokeros|Goddess|Boundless|Paris|Tress|Harris|Antares|Nieves|Backwoods|Midas|Mrs. Sims|Ms. Stillons|Chuckles|Amias|Semiramis|Mother of Mothers)’(?!s)/vg,
"$1’s"
);
// Note: if the "s" is unvoiced, as in Marquis, then it doesn't get the second "s".
xml = xml.replace(/Marquis’s/vg, "Marquis’");
// These have their apostrophe misplaced sometimes.
xml = xml.replace(/Warden’s/vg, "Wardens’");
xml = xml.replace(/Traveller’s/vg, "Travellers’");
// This is basically a mispelling.
xml = xml.replace(/Alzheimers/vg, "Alzheimer’s");
return xml;
}
function cleanSceneBreaks(xml) {
// Normalize scene breaks. <hr> would be more semantically appropriate, but loses the author's intent. This is
// especially the case in Ward, which uses a variety of different scene breaks.
xml = xml.replace(/<p(?:[^>]*)>■<\/p>/vg, `<p style="text-align: center;">■</p>`);
xml = xml.replace(
/<p style="text-align: center;"><strong>⊙<\/strong><\/p>/vg,
`<p style="text-align: center;">⊙</p>`
);
xml = xml.replace(
/<p style="text-align: center;"><em><strong>⊙<\/strong><\/em><\/p>/vg,
`<p style="text-align: center;">⊙</p>`
);
xml = xml.replace(
/<p style="text-align: center;"><strong>⊙⊙<\/strong><\/p>/vg,
`<p style="text-align: center;">⊙</p>`
);
xml = xml.replace(
/<p style="text-align: center;"><strong>⊙ *⊙ *⊙ *⊙ *⊙<\/strong><\/p>/vg,
`<p style="text-align: center;">⊙ ⊙ ⊙ ⊙ ⊙</p>`
);
return xml;
}
function fixCapitalization(xml, bookTitle) {
// This occurs enough times it's better to do here than in one-off fixes. We correct the single instance where
// it's incorrect to capitalize in the one-off fixes.
// Note that Ward contains much talk of "the clairvoyants", so we don't want to capitalize plurals.
xml = xml.replace(/([Tt])he clairvoyant(?!s)/vg, "$1he Clairvoyant");
// ReSound's name is sometimes miscapitalized. The word is never used in a non-name context.
xml = xml.replace(/Resound/vg, "ReSound");
// Number Man's "man" is missing its capitalization a couple times.
xml = xml.replace(/Number man/vg, "Number Man");
// The Speedrunners team name is missing its capitalization a couple times.
xml = xml.replace(/speedrunners/vg, "Speedrunners");
// The Machine Army is missing its capitalization a couple times.
xml = xml.replace(/machine army/vg, "Machine Army");
// "patrol block" is capitalized three different ways: "patrol block", "Patrol block", and "Patrol Block". "patrol
// group" is always lowercased. It seems like "Patrol" is a proper name, and is used as a capitalized modifier in
// other contexts (e.g. Patrol leader). So let's standardize on "Patrol <lowercase>".
xml = xml.replace(
/patrol (block|group|leader|guard|student|uniform|squad|soldier|officer|crew|girl|bus|training)/vig,
(_, $1) => `Patrol ${$1.toLowerCase()}`
);
// This usually works in Ward (some instances corrected back in the substitutions file), and has a few false positives
// in Worm, where it is never needed:
if (bookTitle === "Ward") {
xml = xml.replace(/the patrol(?!s|ling)/vg, "the Patrol");
}
// This is sometimes missing its capitalization.
xml = xml.replace(/the birdcage/vg, "the Birdcage");
// There's no reason why these should be capitalized.
xml = xml.replace(/(?<! {2}|“|>)Halberd/vg, "halberd");
xml = xml.replace(/(?<! {2}|“|>)Loft/vg, "loft");
// These are treated as common nouns and not traditionally capitalized. "Krav Maga" remains capitalized,
// interestingly (according to dictionaries and Wikipedia).
xml = xml.replace(/(?<! {2}|“|>)Judo/vg, "judo");
xml = xml.replace(/(?<! {2}|“|>)Aikido/vg, "aikido");
xml = xml.replace(/(?<! {2}|“|>)Karate/vg, "karate");
xml = xml.replace(/(?<! {2}|“|>)Tae Kwon Do/vg, "tae kwon do");
xml = xml.replace(/(?<! {2}|“|>)Track and Field/vg, "track and field");
// There's no reason why university should be capitalized in most contexts, although sometimes it's used as part of
// a compound noun or at the beginning of a sentence.
xml = xml.replace(/(?<! {2}|“|>|Cornell |Nilles )University(?! Road)/vg, "university");
// Organ names (e.g. brain, arm) or scientific names are not capitalized, so the "corona pollentia" and friends should
// not be either. The books are inconsistent.
xml = xml.replace(/(?<! {2}|“|>|-)Corona/vg, "corona");
xml = xml.replace(/Pollentia/vg, "pollentia");
xml = xml.replace(/Radiata/vg, "radiata");
xml = xml.replace(/Gemma/vg, "gemma");
// We de-capitalize Valkyrie's "flock", since most uses are de-capitalized (e.g. the many instances in Gleaming
// Interlude 9, or Dying 15.z). This is a bit surprising; it seems like an organization name. But I guess it's
// informal.
xml = xml.replace(/(?<! {2}|“|>)Flock/vg, "flock");
// Especially early in Worm, PRT designations are capitalized; they should not be. This fixes the cases where we
// can be reasonably sure they don't start a sentence, although more specific instances are done in the substitutions
// file, and some need to be back-corrected.
//
// Note: "Master" is specifically omitted because it fails poorly on Worm Interlude 4. Other instances need to be
// corrected via the substitutions file.
//
// This also over-de-capitalizes "The Stranger" in Ward (a titan name). Those also get fixed in the substitutions
// file.
xml = xml.replace(
// eslint-disable-next-line max-len
/(?<! {2}|“|>|\n|: )(Mover|Shaker|Brute|Breaker|Tinker|Blaster|Thinker|Striker|Changer|Trump|Stranger|Shifter|Shaper)(?! [A-Z])/vg,
(_, designation) => designation.toLowerCase()
);
xml = xml.replace(
/(mover|shaker|brute|breaker|tinker|blaster|thinker|master|striker|changer|trump|stranger|shifter|shaper)-(\d+)/vig,
"$1 $2"
);
xml = xml.replace(
// eslint-disable-next-line max-len
/(mover|shaker|brute|breaker|tinker|blaster|thinker|master|striker|changer|trump|stranger|shifter|shaper)[ -\/](mover|shaker|brute|breaker|tinker|blaster|thinker|master|striker|changer|trump|stranger|shifter|shaper)/vig,
"$1–$2"
);
// Capitalization is inconsistent, but shard names seems to usually be capitalized.
xml = xml.replace(/Grasping self/vg, "Grasping Self");
xml = xml.replace(/Cloven stranger/vg, "Cloven Stranger");
xml = xml.replace(/Princess shaper/vg, "Princess Shaper");
xml = xml.replace(/Fragile one/vg, "Fragile One");
// Place names need to always be capitalized
xml = xml.replace(/(Stonemast|Shale) avenue/vg, "$1 Avenue");
xml = xml.replace(/(Lord|Slater) street/vg, "$1 Street");
xml = xml.replace(/(Hollow|Cedar) point/vg, "$1 Point");
xml = xml.replace(/(Norwalk|Fenway|Stratford) station/vg, "$1 Station");
xml = xml.replace(/downtown Brockton Bay/vg, "Downtown Brockton Bay");
xml = xml.replace(/the megalopolis/vg, "the Megalopolis");
xml = xml.replace(/earths(?![a-z])/vg, "Earths");
if (bookTitle === "Ward") {
xml = xml.replace(/the bunker/vg, "the Bunker");
xml = xml.replace(/‘bunker’/vg, "‘Bunker’");
}
// These seem to be used more as generic terms than as place names.
xml = xml.replace(/the Market/vg, "the market");
xml = xml.replace(/the Bay(?! [A-Z])/vg, "the bay");
// "Mom" and "Dad" should be capitalized when used as a proper name. These regexps are tuned to catch a good amount of
// instances, without over-correcting for non-proper-name-like cases. Many other instances are handled in
// the substitutions file.
xml = xml.replace(/(?/vg, "$1:<br />");
// "You have marked yourself as away." has a period, so this one should too.
xml = xml.replace(/(You have marked yourself as back)(?<!\.\s)(?=<br\s*\/?>)/vg, "$1.");
// It's inconsistent to exclude the punctuation from the bolding; fix it.
xml = xml.replace(/<strong>Welcome back to (.+?)<\/strong>!/vg, "<strong>Welcome back to $1!</strong>");
xml = xml.replace(/<p>♦ <strong>(.*)<\/strong><\/p>/vg, `<p><strong>♦ $1</strong></p>`);
return xml;
}
function isEmptyOrGarbage(el) {
const text = el.textContent.trim();
return text === "" ||
text.startsWith("Last Chapter") ||
text.startsWith("Previous Chapter") ||
text.startsWith("Next Chapter");
}
function escapeRegExp(str) {
return str.replace(/[[\]/{}()*+?.\\^$|]/ug, "\\$&");
}
function decodeCloudFlareEmail(hash) {
let email = "";
const xorWithThis = parseInt(hash.substring(0, 2), 16);
for (let i = 2; i < hash.length; i += 2) {
const charCode = parseInt(hash.substring(i, i + 2), 16) ^ xorWithThis;
email += String.fromCharCode(charCode);
}
return email;
}