Merge pull request #78 from sillsdev/76_ImageFilename

fix: #76 - Prevent image filename thrashing after Notion url change

Author: andrew-polk

src/MakeImagePersistencePlan.ts

@@ -12,14 +12,12 @@ export function makeImagePersistencePlan(
     // Since most images come from pasting screenshots, there isn't normally a filename. That's fine, we just make a hash of the url
     // Images that are stored by notion come to us with a complex url that changes over time, so we pick out the UUID that doesn't change. Example:
     //    https://s3.us-west-2.amazonaws.com/secure.notion-static.com/d1058f46-4d2f-4292-8388-4ad393383439/Untitled.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIAT73L2G45EIPT3X45%2F20220516%2Fus-west-2%2Fs3%2Faws4_request&X-Amz-Date=20220516T233630Z&X-Amz-Expires=3600&X-Amz-Signature=f215704094fcc884d37073b0b108cf6d1c9da9b7d57a898da38bc30c30b4c4b5&X-Amz-SignedHeaders=host&x-id=GetObject
+    // But around Sept 2023, they changed the url to be something like:
+    //    https://prod-files-secure.s3.us-west-2.amazonaws.com/d9a2b712-cf69-4bd6-9d65-87a4ceeacca2/d1bcdc8c-b065-4e40-9a11-392aabeb220e/Untitled.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIAT73L2G45EIPT3X45%2F20230915%2Fus-west-2%2Fs3%2Faws4_request&X-Amz-Date=20230915T161258Z&X-Amz-Expires=3600&X-Amz-Signature=28fca48e65fba86d539c3c4b7676fce1fa0857aa194f7b33dd4a468ecca6ab24&X-Amz-SignedHeaders=host&x-id=GetObject
+    // The thing we want is the last UUID before the ?
 
-    let thingToHash = imageSet.primaryUrl;
-    const m = /.*secure\.notion-static\.com\/(.*)\//gm.exec(
-      imageSet.primaryUrl
-    );
-    if (m && m.length > 1) {
-      thingToHash = m[1];
-    }
+    const urlBeforeQuery = imageSet.primaryUrl.split("?")[0];
+    const thingToHash = findLastUuid(urlBeforeQuery) ?? urlBeforeQuery;
 
     const hash = hashOfString(thingToHash);
     imageSet.outputFileName = `${hash}.${imageSet.fileType.ext}`;
@@ -50,7 +48,18 @@ export function makeImagePersistencePlan(
   }
 }
 
-function hashOfString(s: string) {
+function findLastUuid(url: string): string | null {
+  // Regex for a UUID surrounded by slashes
+  const uuidPattern =
+    /(?<=\/)[0-9a-f]{8}-[0-9a-f]{4}-[0-5][0-9a-f]{3}-[089ab][0-9a-f]{3}-[0-9a-f]{12}(?=\/)/gi;
+
+  // Find all UUIDs
+  const uuids = url.match(uuidPattern);
+  // Return the last UUID if any exist, else return null
+  return uuids ? uuids[uuids.length - 1].trim() : null;
+}
+
+export function hashOfString(s: string): number {
   let hash = 0;
   for (let i = 0; i < s.length; ++i)
     hash = Math.imul(31, hash) + s.charCodeAt(i);

src/makeImagePersistencePlan.spec.ts

@@ -1,4 +1,7 @@
-import { makeImagePersistencePlan } from "./MakeImagePersistencePlan";
+import {
+  hashOfString,
+  makeImagePersistencePlan,
+} from "./MakeImagePersistencePlan";
 import { ImageSet } from "./images";
 
 test("primary file with explicit file output path and prefix", () => {
@@ -9,11 +12,16 @@ test("primary file with explicit file output path and prefix", () => {
     fileType: { ext: "png", mime: "image/png" },
   };
   makeImagePersistencePlan(imageSet, "./static/notion_imgs", "/notion_imgs");
-  expect(imageSet.outputFileName).toBe("463556435.png");
+  const expectedHash = hashOfString(
+    "https://s3.us-west-2.amazonaws.com/primaryImage"
+  );
+  expect(imageSet.outputFileName).toBe(`${expectedHash}.png`);
   expect(imageSet.primaryFileOutputPath).toBe(
-    "static/notion_imgs/463556435.png"
+    `static/notion_imgs/${expectedHash}.png`
+  );
+  expect(imageSet.filePathToUseInMarkdown).toBe(
+    `/notion_imgs/${expectedHash}.png`
   );
-  expect(imageSet.filePathToUseInMarkdown).toBe("/notion_imgs/463556435.png");
 });
 test("primary file with defaults for image output path and prefix", () => {
   const imageSet: ImageSet = {
@@ -23,13 +31,39 @@ test("primary file with defaults for image output path and prefix", () => {
     fileType: { ext: "png", mime: "image/png" },
   };
   makeImagePersistencePlan(imageSet, "", "");
-  expect(imageSet.outputFileName).toBe("463556435.png");
+  const expectedHash = hashOfString(
+    "https://s3.us-west-2.amazonaws.com/primaryImage"
+  );
+  expect(imageSet.outputFileName).toBe(`${expectedHash}.png`);
 
   // the default behavior is to put the image next to the markdown file
   expect(imageSet.primaryFileOutputPath).toBe(
-    "/pathToParentSomewhere/463556435.png"
+    `/pathToParentSomewhere/${expectedHash}.png`
   );
-  expect(imageSet.filePathToUseInMarkdown).toBe("./463556435.png");
+  expect(imageSet.filePathToUseInMarkdown).toBe(`./${expectedHash}.png`);
+});
+
+test("properly extract UUID from old-style notion image url", () => {
+  const imageSet: ImageSet = {
+    primaryUrl:
+      "https://s3.us-west-2.amazonaws.com/secure.notion-static.com/e1058f46-4d2f-4292-8388-4ad393383439/Untitled.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIAT73L2G45EIPT3X45%2F20220516%2Fus-west-2%2Fs3%2Faws4_request&X-Amz-Date=20220516T233630Z&X-Amz-Expires=3600&X-Amz-Signature=f215704094fcc884d37073b0b108cf6d1c9da9b7d57a898da38bc30c30b4c4b5&X-Amz-SignedHeaders=host&x-id=GetObject",
+    localizedUrls: [],
+    fileType: { ext: "png", mime: "image/png" },
+  };
+  makeImagePersistencePlan(imageSet, "./static/notion_imgs", "/notion_imgs");
+  const expectedHash = hashOfString("e1058f46-4d2f-4292-8388-4ad393383439");
+  expect(imageSet.outputFileName).toBe(`${expectedHash}.png`);
+});
+test("properly extract UUID from new-style (Sept 2023) notion image url", () => {
+  const imageSet: ImageSet = {
+    primaryUrl:
+      "https://prod-files-secure.s3.us-west-2.amazonaws.com/d9a2b712-cf69-4bd6-9d65-87a4ceeacca2/d1bcdc8c-b065-4e40-9a11-392aabeb220e/Untitled.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIAT73L2G45EIPT3X45%2F20230915%2Fus-west-2%2Fs3%2Faws4_request&X-Amz-Date=20230915T161258Z&X-Amz-Expires=3600&X-Amz-Signature=28fca48e65fba86d539c3c4b7676fce1fa0857aa194f7b33dd4a468ecca6ab24&X-Amz-SignedHeaders=host&x-id=GetObject",
+    localizedUrls: [],
+    fileType: { ext: "png", mime: "image/png" },
+  };
+  makeImagePersistencePlan(imageSet, "./static/notion_imgs", "/notion_imgs");
+  const expectedHash = hashOfString("d1bcdc8c-b065-4e40-9a11-392aabeb220e");
+  expect(imageSet.outputFileName).toBe(`${expectedHash}.png`);
 });
 
 // In order to make image fallback work with other languages, we have to have