From a4e5a12fe4b8eb4ceb858698c5795a339b96341f Mon Sep 17 00:00:00 2001
From: Domenic Denicola <d@domenic.me>
Date: Thu, 7 May 2015 23:17:12 +0200
Subject: [PATCH] Use sortable filenames, and fix output filenames

---
 lib/download.js     | 21 ++++++---------------
 lib/worm-scraper.js | 15 +++++++++------
 package.json        |  3 ++-
 3 files changed, 17 insertions(+), 22 deletions(-)

diff --git a/lib/download.js b/lib/download.js
index 30fa7ff..3664092 100644
--- a/lib/download.js
+++ b/lib/download.js
@@ -3,6 +3,7 @@ const path = require("path");
 const fs = require("mz/fs");
 const mkdirp = require("mkdirp-then");
 const request = require("requisition");
+const zfill = require("zfill");
 const jsdom = require("./jsdom.js");
 
 const FILENAME_PREFIX = "chapter";
@@ -11,19 +12,9 @@ const URL_SUFFIX = "-url.txt";
 module.exports = function (startChapterUrl, cachePath) {
   return fs.readdir(cachePath).then(
     function (filenames) {
-      const lastChapter = filenames.filter(function (f) {
-        return f.endsWith(URL_SUFFIX);
-      })
-      .map(function (f) {
-        return [getChapterNumber(f), f];
-      })
-      .sort(function (a, b) {
-        return b[0] - a[0];
-      })
-      [0];
-
-      const lastChapterNumber = lastChapter[0];
-      const lastChapterUrlFile = lastChapter[1];
+      const sorted = filenames.filter(function (f) { return f.endsWith(URL_SUFFIX); }).sort();
+      const lastChapterUrlFile = sorted[sorted.length - 1];
+      const lastChapterNumber = getChapterNumber(lastChapterUrlFile);
 
       return fs.readFile(path.resolve(cachePath, lastChapterUrlFile), { encoding: "utf-8" }).then(function (url) {
         return downloadAllChapters(url, lastChapterNumber, cachePath);
@@ -46,7 +37,7 @@ function downloadAllChapters(startChapterUrl, startChapterNumber, cachePath) {
   return mkdirp(cachePath).then(loop);
 
   function loop() {
-    const filename = `${FILENAME_PREFIX}${chapterCounter}.html`;
+    const filename = `${FILENAME_PREFIX}${zfill(chapterCounter, 3)}.html`;
 
     console.log(`Downloading ${currentChapter}`);
 
@@ -117,5 +108,5 @@ function urlFilename(filename) {
 }
 
 function getChapterNumber(filename) {
-  return Number(filename.substring(FILENAME_PREFIX.length, filename.indexOf(".html")));
+  return Number(/0?0?(\d+)\./.exec(filename)[1]);
 }
diff --git a/lib/worm-scraper.js b/lib/worm-scraper.js
index 6fb45f3..44b904a 100644
--- a/lib/worm-scraper.js
+++ b/lib/worm-scraper.js
@@ -38,21 +38,24 @@ function getChapterFilePaths() {
   });
 }
 
-function convertChapter(filePath, i) {
-  console.log(`- Reading ${filePath}`);
+function convertChapter(filePath) {
+  const filename = path.basename(filePath);
+
+  console.log(`- Reading ${filename}`);
   return fs.readFile(filePath, { encoding: "utf-8" }).then(function (contents) {
-    console.log(`- Read ${filePath}`);
+    console.log(`- Read ${filename}`);
     const rawChapterDoc = jsdom(contents);
     const output = getChapterString(rawChapterDoc);
 
     // TODO: this should probably not be necessary... jsdom bug I guess!?
     rawChapterDoc.defaultView.close();
 
-    const destFilename = path.resolve(contentPath, `chapter${i + 1}.xhtml`);
-    return fs.writeFile(destFilename, output);
+    const destFileName = `${path.basename(filename, ".html")}.xhtml`;
+    const destFilePath = path.resolve(contentPath, destFileName);
+    return fs.writeFile(destFilePath, output);
   })
   .then(function () {
-    console.log(`- Finished converting ${filePath}`);
+    console.log(`- Finished converting ${filename}`);
   });
 }
 
diff --git a/package.json b/package.json
index e92f975..903f4e3 100644
--- a/package.json
+++ b/package.json
@@ -23,7 +23,8 @@
     "mkdirp-then": "^1.0.1",
     "requisition": "^1.5.0",
     "rimraf-then": "^1.0.0",
-    "xtend": "^4.0.0"
+    "xtend": "^4.0.0",
+    "zfill": "0.0.2"
   },
   "devDependencies": {
     "eslint": "0.20.0",