lastModified (#1051)

* tests * document * fileAttachment knows about lastModified * build tests know about lastModified * lastModified * lastModified and content hash are now based on a data loader's cached payload * minimize diff * lowercase comment * Apply suggestions from code review Co-authored-by: Mike Bostock <mbostock@gmail.com> * fix LoaderResolver.getLastModified logic & add tests * okay this is a fake data loader, but let's keep it consistent * restore default mime-type but on render instead of in the client/stdlib * move the default mime-type back to the client; the test doesn't have it anymore * javadoc comment --------- Co-authored-by: Mike Bostock <mbostock@gmail.com>
observablehq · Mar 15, 2024 · 6586877 · 6586877
1 parent 1971b56
commit 6586877
Show file tree

Hide file tree

Showing 22 changed files with 129 additions and 53 deletions.
diff --git a/docs/javascript/files.md b/docs/javascript/files.md
@@ -10,7 +10,7 @@ Load files — whether static or generated dynamically by a [data loader](../loa
 import {FileAttachment} from "npm:@observablehq/stdlib";
 ```
 
-The `FileAttachment` function takes a path and returns a file handle. This handle exposes the file’s name and [MIME type](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/MIME_types).
+The `FileAttachment` function takes a path and returns a file handle. This handle exposes the file’s name, [MIME type](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/MIME_types), and last modification date as the number of milliseconds since UNIX epoch.
 
 ```js echo
 FileAttachment("volcano.json")
@@ -32,7 +32,7 @@ volcano
 
 ### Static analysis
 
-The `FileAttachment` function can _only_ be passed a static string literal; constructing a dynamic path such as `FileAttachment("my" + "file.csv")` is invalid syntax. Static analysis is used to invoke [data loaders](../loaders) at build time, and ensures that only referenced files are included in the generated output during build. In the future [#260](https://github.com/observablehq/framework/issues/260), it will also allow content hashes for cache breaking during deploy.
+The `FileAttachment` function can _only_ be passed a static string literal; constructing a dynamic path such as `FileAttachment("my" + "file.csv")` is invalid syntax. Static analysis is used to invoke [data loaders](../loaders) at build time, and ensures that only referenced files are included in the generated output during build. This also allows a content hash in the file name for cache breaking during deploy.
 
 If you have multiple files, you can enumerate them explicitly like so:
 
@@ -52,6 +52,8 @@ const frames = [
 
 None of the files in `frames` above are loaded until a [content method](#supported-formats) is invoked, for example by saying `frames[0].image()`.
 
+For missing files, `file.lastModified` is undefined. The `file.mimeType` is determined by checking the file extension against the [`mime-db` media type database](https://github.com/jshttp/mime-db); it defaults to `application/octet-stream`.
+
 ## Supported formats
 
 `FileAttachment` supports a variety of methods for loading file contents:

diff --git a/src/client/stdlib/fileAttachment.js b/src/client/stdlib/fileAttachment.js
@@ -11,8 +11,8 @@ export function FileAttachment(name, base = location.href) {
   const url = new URL(name, base).href;
   const file = files.get(url);
   if (!file) throw new Error(`File not found: ${name}`);
-  const {path, mimeType} = file;
-  return new FileAttachmentImpl(new URL(path, location).href, name.split("/").pop(), mimeType);
+  const {path, mimeType, lastModified} = file;
+  return new FileAttachmentImpl(new URL(path, location).href, name.split("/").pop(), mimeType, lastModified);
 }
 
 async function remote_fetch(file) {
@@ -28,9 +28,10 @@ async function dsv(file, delimiter, {array = false, typed = false} = {}) {
 }
 
 export class AbstractFile {
-  constructor(name, mimeType = "application/octet-stream") {
-    Object.defineProperty(this, "name", {value: `${name}`, enumerable: true});
+  constructor(name, mimeType = "application/octet-stream", lastModified) {
     Object.defineProperty(this, "mimeType", {value: `${mimeType}`, enumerable: true});
+    Object.defineProperty(this, "name", {value: `${name}`, enumerable: true});
+    if (lastModified !== undefined) Object.defineProperty(this, "lastModified", {value: Number(lastModified), enumerable: true}); // prettier-ignore
   }
   async blob() {
     return (await remote_fetch(this)).blob();
@@ -95,8 +96,8 @@ export class AbstractFile {
 }
 
 class FileAttachmentImpl extends AbstractFile {
-  constructor(url, name, mimeType) {
-    super(name, mimeType);
+  constructor(url, name, mimeType, lastModified) {
+    super(name, mimeType, lastModified);
     Object.defineProperty(this, "_url", {value: url});
   }
   async url() {

diff --git a/src/dataloader.ts b/src/dataloader.ts
@@ -7,7 +7,7 @@ import JSZip from "jszip";
 import {extract} from "tar-stream";
 import {maybeStat, prepareOutput} from "./files.js";
 import {FileWatchers} from "./fileWatchers.js";
-import {getFileHash} from "./javascript/module.js";
+import {getFileHash, getFileInfo} from "./javascript/module.js";
 import type {Logger, Writer} from "./logger.js";
 import {cyan, faint, green, red, yellow} from "./tty.js";
 
@@ -129,12 +129,35 @@ export class LoaderResolver {
     return FileWatchers.of(this, path, watchPaths, callback);
   }
 
-  getFileHash(path: string): string {
+  /**
+   * Get the actual path of a file. For data loaders, it is the output if
+   * already available (cached). In build this is always the case (unless the
+   * corresponding data loader fails). However in preview we return the page
+   * before running the data loaders (which will run on demand from the page),
+   * so there might be a temporary discrepancy when a cache is stale.
+   */
+  private getFilePath(name: string): string {
+    let path = name;
     if (!existsSync(join(this.root, path))) {
       const loader = this.find(path);
-      if (loader) path = relative(this.root, loader.path);
+      if (loader) {
+        path = relative(this.root, loader.path);
+        if (name !== path) {
+          const cachePath = join(".observablehq", "cache", name);
+          if (existsSync(join(this.root, cachePath))) path = cachePath;
+        }
+      }
     }
-    return getFileHash(this.root, path);
+    return path;
+  }
+
+  getFileHash(name: string): string {
+    return getFileHash(this.root, this.getFilePath(name));
+  }
+
+  getLastModified(name: string): number | undefined {
+    const entry = getFileInfo(this.root, this.getFilePath(name));
+    return entry && Math.floor(entry.mtimeMs);
   }
 
   resolveFilePath(path: string): string {

diff --git a/src/render.ts b/src/render.ts
@@ -8,7 +8,7 @@ import {transpileJavaScript} from "./javascript/transpile.js";
 import type {MarkdownPage} from "./markdown.js";
 import type {PageLink} from "./pager.js";
 import {findLink, normalizePath} from "./pager.js";
-import {relativePath} from "./path.js";
+import {relativePath, resolvePath} from "./path.js";
 import type {Resolvers} from "./resolvers.js";
 import {getResolvers} from "./resolvers.js";
 import {rollupClient} from "./rollup.js";
@@ -25,7 +25,8 @@ type RenderInternalOptions =
 
 export async function renderPage(page: MarkdownPage, options: RenderOptions & RenderInternalOptions): Promise<string> {
   const {data} = page;
-  const {root, md, base, path, pages, title, preview, search, resolvers = await getResolvers(page, options)} = options;
+  const {root, md, base, path, pages, title, preview, search} = options;
+  const {loaders, resolvers = await getResolvers(page, options)} = options;
   const {normalizeLink} = md;
   const sidebar = data?.sidebar !== undefined ? Boolean(data.sidebar) : options.sidebar;
   const toc = mergeToc(data?.toc, options.toc);
@@ -63,7 +64,9 @@ import ${preview || page.code.length ? `{${preview ? "open, " : ""}define} from
         )};`
       : ""
   }${data?.sql ? `\nimport {registerTable} from ${JSON.stringify(resolveImport("npm:@observablehq/duckdb"))};` : ""}${
-    files.size ? `\n${renderFiles(files, resolveFile)}` : ""
+    files.size
+      ? `\n${renderFiles(files, resolveFile, (name: string) => loaders.getLastModified(resolvePath(path, name)))}`
+      : ""
   }${
     data?.sql
       ? `\n${Object.entries<string>(data.sql)
@@ -84,18 +87,19 @@ ${html.unsafe(rewriteHtml(page.html, resolvers))}</main>${renderFooter(path, opt
 `);
 }
 
-function renderFiles(files: Iterable<string>, resolve: (name: string) => string): string {
+function renderFiles(files: Iterable<string>, resolve: (name: string) => string, getLastModified): string {
   return Array.from(files)
     .sort()
-    .map((f) => renderFile(f, resolve))
+    .map((f) => renderFile(f, resolve, getLastModified))
     .join("");
 }
 
-function renderFile(name: string, resolve: (name: string) => string): string {
+function renderFile(name: string, resolve: (name: string) => string, getLastModified): string {
   return `\nregisterFile(${JSON.stringify(name)}, ${JSON.stringify({
     name,
     mimeType: mime.getType(name) ?? undefined,
-    path: resolve(name)
+    path: resolve(name),
+    lastModified: getLastModified(name)
   })});`;
 }
 

diff --git a/src/resolvers.ts b/src/resolvers.ts
@@ -114,8 +114,7 @@ export async function getResolvers(
     }
   }
 
-  // Compute the content hash. TODO In build, this needs to consider the output
-  // of data loaders, rather than the source of data loaders.
+  // Compute the content hash.
   for (const f of assets) hash.update(loaders.getFileHash(resolvePath(path, f)));
   for (const f of files) hash.update(loaders.getFileHash(resolvePath(path, f)));
   for (const i of localImports) hash.update(getModuleHash(root, resolvePath(path, i)));

diff --git a/test/build-test.ts b/test/build-test.ts
@@ -101,6 +101,7 @@ class TestEffects extends FileBuildEffects {
   async writeFile(outputPath: string, contents: string | Buffer): Promise<void> {
     if (typeof contents === "string" && outputPath.endsWith(".html")) {
       contents = contents.replace(/^(\s*<script>\{).*(\}<\/script>)$/gm, "$1/* redacted init script */$2");
+      contents = contents.replace(/^(registerFile\(.*,"lastModified":)\d+(\}\);)$/gm, "$1/* ts */1706742000000$2");
     }
     return super.writeFile(outputPath, contents);
   }

diff --git a/test/dataloaders-test.ts b/test/dataloaders-test.ts
@@ -1,5 +1,5 @@
 import assert from "node:assert";
-import {readFile, stat, unlink, utimes} from "node:fs/promises";
+import {mkdir, readFile, rmdir, stat, unlink, utimes, writeFile} from "node:fs/promises";
 import os from "node:os";
 import type {LoadEffects} from "../src/dataloader.js";
 import {LoaderResolver} from "../src/dataloader.js";
@@ -113,3 +113,34 @@ describe("LoaderResolver.getFileHash(path)", () => {
     assert.strictEqual(loaders.getFileHash("does-not-exist.csv"), "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"); // prettier-ignore
   });
 });
+
+describe("LoaderResolver.getLastModified(path)", () => {
+  const time1 = new Date(Date.UTC(2023, 11, 1));
+  const time2 = new Date(Date.UTC(2024, 2, 1));
+  const loaders = new LoaderResolver({root: "test"});
+  it("returns the last modification time for a simple file", async () => {
+    await utimes("test/input/loader/simple.txt", time1, time1);
+    assert.strictEqual(loaders.getLastModified("input/loader/simple.txt"), +time1);
+  });
+  it("returns an undefined last modification time for a missing file", async () => {
+    assert.strictEqual(loaders.getLastModified("input/loader/missing.txt"), undefined);
+  });
+  it("returns the last modification time for a cached data loader", async () => {
+    await utimes("test/input/loader/cached.txt.sh", time1, time1);
+    await mkdir("test/.observablehq/cache/input/loader/", {recursive: true});
+    await writeFile("test/.observablehq/cache/input/loader/cached.txt", "2024-03-01 00:00:00");
+    await utimes("test/.observablehq/cache/input/loader/cached.txt", time2, time2);
+    assert.strictEqual(loaders.getLastModified("input/loader/cached.txt"), +time2);
+    // clean up
+    try {
+      await unlink("test/.observablehq/cache/input/loader/cached.txt");
+      await rmdir("test/.observablehq/cache/input/loader", {recursive: true});
+    } catch {
+      // ignore;
+    }
+  });
+  it("returns the last modification time for a data loader that has no cache", async () => {
+    await utimes("test/input/loader/not-cached.txt.sh", time1, time1);
+    assert.strictEqual(loaders.getLastModified("input/loader/not-cached.txt"), +time1);
+  });
+});
diff --git a/test/input/build/files/files.md b/test/input/build/files/files.md
@@ -14,6 +14,10 @@ FileAttachment("subsection/file-sub.csv")
 FileAttachment("observable logo.png")
 ```
 
+```js
+FileAttachment("unknown-mime-extension.really")
+```
+
 ![](observable%20logo%20small.png)
 
 
diff --git a/test/input/loader/cached.txt.sh b/test/input/loader/cached.txt.sh
@@ -0,0 +1 @@
+date -u "+%Y-%m-%d %H:%M:%S"
diff --git a/test/input/loader/not-cached.txt.sh b/test/input/loader/not-cached.txt.sh
@@ -0,0 +1 @@
+date -u "+%Y-%m-%d %H:%M:%S"
diff --git a/test/input/loader/simple.txt b/test/input/loader/simple.txt
@@ -0,0 +1 @@
+HELLO
diff --git a/test/output/build/archives.posix/tar.html b/test/output/build/archives.posix/tar.html
@@ -15,13 +15,13 @@
 import {define} from "./_observablehq/client.js";
 import {registerFile} from "./_observablehq/stdlib.js";
 
-registerFile("./dynamic-tar-gz/does-not-exist.txt", {"name":"./dynamic-tar-gz/does-not-exist.txt","mimeType":"text/plain","path":"./dynamic-tar-gz/does-not-exist.txt"});
-registerFile("./dynamic-tar-gz/file.txt", {"name":"./dynamic-tar-gz/file.txt","mimeType":"text/plain","path":"./_file/dynamic-tar-gz/file.c93138d8.txt"});
-registerFile("./dynamic-tar/does-not-exist.txt", {"name":"./dynamic-tar/does-not-exist.txt","mimeType":"text/plain","path":"./dynamic-tar/does-not-exist.txt"});
-registerFile("./dynamic-tar/file.txt", {"name":"./dynamic-tar/file.txt","mimeType":"text/plain","path":"./_file/dynamic-tar/file.c93138d8.txt"});
-registerFile("./static-tar/does-not-exist.txt", {"name":"./static-tar/does-not-exist.txt","mimeType":"text/plain","path":"./static-tar/does-not-exist.txt"});
-registerFile("./static-tar/file.txt", {"name":"./static-tar/file.txt","mimeType":"text/plain","path":"./_file/static-tar/file.c93138d8.txt"});
-registerFile("./static-tgz/file.txt", {"name":"./static-tgz/file.txt","mimeType":"text/plain","path":"./_file/static-tgz/file.c93138d8.txt"});
+registerFile("./dynamic-tar-gz/does-not-exist.txt", {"name":"./dynamic-tar-gz/does-not-exist.txt","mimeType":"text/plain","path":"./dynamic-tar-gz/does-not-exist.txt","lastModified":/* ts */1706742000000});
+registerFile("./dynamic-tar-gz/file.txt", {"name":"./dynamic-tar-gz/file.txt","mimeType":"text/plain","path":"./_file/dynamic-tar-gz/file.c93138d8.txt","lastModified":/* ts */1706742000000});
+registerFile("./dynamic-tar/does-not-exist.txt", {"name":"./dynamic-tar/does-not-exist.txt","mimeType":"text/plain","path":"./dynamic-tar/does-not-exist.txt","lastModified":/* ts */1706742000000});
+registerFile("./dynamic-tar/file.txt", {"name":"./dynamic-tar/file.txt","mimeType":"text/plain","path":"./_file/dynamic-tar/file.c93138d8.txt","lastModified":/* ts */1706742000000});
+registerFile("./static-tar/does-not-exist.txt", {"name":"./static-tar/does-not-exist.txt","mimeType":"text/plain","path":"./static-tar/does-not-exist.txt","lastModified":/* ts */1706742000000});
+registerFile("./static-tar/file.txt", {"name":"./static-tar/file.txt","mimeType":"text/plain","path":"./_file/static-tar/file.c93138d8.txt","lastModified":/* ts */1706742000000});
+registerFile("./static-tgz/file.txt", {"name":"./static-tgz/file.txt","mimeType":"text/plain","path":"./_file/static-tgz/file.c93138d8.txt","lastModified":/* ts */1706742000000});
 
 define({id: "d5134368", inputs: ["FileAttachment","display"], body: async (FileAttachment,display) => {
 display(await(

diff --git a/test/output/build/archives.posix/zip.html b/test/output/build/archives.posix/zip.html
@@ -15,10 +15,10 @@
 import {define} from "./_observablehq/client.js";
 import {registerFile} from "./_observablehq/stdlib.js";
 
-registerFile("./dynamic/file.txt", {"name":"./dynamic/file.txt","mimeType":"text/plain","path":"./_file/dynamic/file.c93138d8.txt"});
-registerFile("./dynamic/not-found.txt", {"name":"./dynamic/not-found.txt","mimeType":"text/plain","path":"./dynamic/not-found.txt"});
-registerFile("./static/file.txt", {"name":"./static/file.txt","mimeType":"text/plain","path":"./_file/static/file.d9014c46.txt"});
-registerFile("./static/not-found.txt", {"name":"./static/not-found.txt","mimeType":"text/plain","path":"./static/not-found.txt"});
+registerFile("./dynamic/file.txt", {"name":"./dynamic/file.txt","mimeType":"text/plain","path":"./_file/dynamic/file.c93138d8.txt","lastModified":/* ts */1706742000000});
+registerFile("./dynamic/not-found.txt", {"name":"./dynamic/not-found.txt","mimeType":"text/plain","path":"./dynamic/not-found.txt","lastModified":/* ts */1706742000000});
+registerFile("./static/file.txt", {"name":"./static/file.txt","mimeType":"text/plain","path":"./_file/static/file.d9014c46.txt","lastModified":/* ts */1706742000000});
+registerFile("./static/not-found.txt", {"name":"./static/not-found.txt","mimeType":"text/plain","path":"./static/not-found.txt","lastModified":/* ts */1706742000000});
 
 define({id: "d3b9d0ee", inputs: ["FileAttachment","display"], body: async (FileAttachment,display) => {
 display(await(

diff --git a/test/output/build/archives.win32/tar.html b/test/output/build/archives.win32/tar.html
@@ -15,9 +15,9 @@
 import {define} from "./_observablehq/client.js";
 import {registerFile} from "./_observablehq/stdlib.js";
 
-registerFile("./static-tar/does-not-exist.txt", {"name":"./static-tar/does-not-exist.txt","mimeType":"text/plain","path":"./static-tar/does-not-exist.txt"});
-registerFile("./static-tar/file.txt", {"name":"./static-tar/file.txt","mimeType":"text/plain","path":"./_file/static-tar/file.c93138d8.txt"});
-registerFile("./static-tgz/file.txt", {"name":"./static-tgz/file.txt","mimeType":"text/plain","path":"./_file/static-tgz/file.c93138d8.txt"});
+registerFile("./static-tar/does-not-exist.txt", {"name":"./static-tar/does-not-exist.txt","mimeType":"text/plain","path":"./static-tar/does-not-exist.txt","lastModified":/* ts */1706742000000});
+registerFile("./static-tar/file.txt", {"name":"./static-tar/file.txt","mimeType":"text/plain","path":"./_file/static-tar/file.c93138d8.txt","lastModified":/* ts */1706742000000});
+registerFile("./static-tgz/file.txt", {"name":"./static-tgz/file.txt","mimeType":"text/plain","path":"./_file/static-tgz/file.c93138d8.txt","lastModified":/* ts */1706742000000});
 
 define({id: "d5134368", inputs: ["FileAttachment","display"], body: async (FileAttachment,display) => {
 display(await(

diff --git a/test/output/build/archives.win32/zip.html b/test/output/build/archives.win32/zip.html
@@ -15,8 +15,8 @@
 import {define} from "./_observablehq/client.js";
 import {registerFile} from "./_observablehq/stdlib.js";
 
-registerFile("./static/file.txt", {"name":"./static/file.txt","mimeType":"text/plain","path":"./_file/static/file.d9014c46.txt"});
-registerFile("./static/not-found.txt", {"name":"./static/not-found.txt","mimeType":"text/plain","path":"./static/not-found.txt"});
+registerFile("./static/file.txt", {"name":"./static/file.txt","mimeType":"text/plain","path":"./_file/static/file.d9014c46.txt","lastModified":/* ts */1706742000000});
+registerFile("./static/not-found.txt", {"name":"./static/not-found.txt","mimeType":"text/plain","path":"./static/not-found.txt","lastModified":/* ts */1706742000000});
 
 define({id: "d3b9d0ee", inputs: ["FileAttachment","display"], body: async (FileAttachment,display) => {
 display(await(

diff --git a/test/output/build/fetches/foo.html b/test/output/build/fetches/foo.html
@@ -16,8 +16,8 @@
 import {define} from "./_observablehq/client.js";
 import {registerFile} from "./_observablehq/stdlib.js";
 
-registerFile("./foo/foo-data.csv", {"name":"./foo/foo-data.csv","mimeType":"text/csv","path":"./_file/foo/foo-data.24ef4634.csv"});
-registerFile("./foo/foo-data.json", {"name":"./foo/foo-data.json","mimeType":"application/json","path":"./_file/foo/foo-data.67358ed8.json"});
+registerFile("./foo/foo-data.csv", {"name":"./foo/foo-data.csv","mimeType":"text/csv","path":"./_file/foo/foo-data.24ef4634.csv","lastModified":/* ts */1706742000000});
+registerFile("./foo/foo-data.json", {"name":"./foo/foo-data.json","mimeType":"application/json","path":"./_file/foo/foo-data.67358ed8.json","lastModified":/* ts */1706742000000});
 
 define({id: "47a695da", inputs: ["display"], outputs: ["fooJsonData","fooCsvData"], body: async (display) => {
 const {fooJsonData, fooCsvData} = await import("./_import/foo/foo.6fd063d5.js");