From f94747ea7ee6e51ad2c1efc780e531313ea1a3b9 Mon Sep 17 00:00:00 2001
From: Sam Wilkins <35748010+samwilkins333@users.noreply.github.com>
Date: Wed, 12 Feb 2020 14:45:23 -0500
Subject: importer tweaks

---
 src/scraping/buxton/final/BuxtonImporter.ts | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'src/scraping/buxton/final')

diff --git a/src/scraping/buxton/final/BuxtonImporter.ts b/src/scraping/buxton/final/BuxtonImporter.ts
index d9d48d68c..f9726872c 100644
--- a/src/scraping/buxton/final/BuxtonImporter.ts
+++ b/src/scraping/buxton/final/BuxtonImporter.ts
@@ -115,7 +115,7 @@ const RegexMap = new Map<keyof DeviceDocument, Processor<any>>([
     }],
     ["year", {
         exp: /Year:\s+([^\|]*)\s+\|/,
-        transformer: Utilities.numberValue
+        transformer: (raw: string) => Utilities.numberValue(/[0-9]{4}/.exec(raw)![0])
     }],
     ["primaryKey", {
         exp: /Primary:\s+(.*)(Secondary|Additional):/,
@@ -254,10 +254,9 @@ async function extractFileContents(pathToDocument: string): Promise<DocumentCont
     strictEqual(length % 3 === 0, true, "Improper caption formatting.");
 
     for (let i = 3; i < captionTargets.length; i += 3) {
-        const [image, fileName, caption] = captionTargets.slice(i, i + 3);
-        strictEqual(image, "", `The image cell in one row was not the empty string: ${image}`);
-        captions.push(caption);
-        embeddedFileNames.push(fileName);
+        const row = captionTargets.slice(i, i + 3);
+        captions.push(row[1]);
+        embeddedFileNames.push(row[2]);
     }
 
     // extract all hyperlinks embedded in the document
-- 
cgit v1.2.3-70-g09d2