Use article link markers for PDF indexing

This commit is contained in:
Nobody committed 2026-11-17 16:26:01 +08:00
1 parent 09af3bd8c0
commit 33f15d9ce0
20 files changed
+1137 -293

No files matched your search

+102
View File
@@ -0,0 +1,102 @@
import { assertEquals, assertStringIncludes } from "@std/assert";
import {
convertDocument,
EpubOutput,
type HtmlDocument,
HtmlInput,
PdfOutput,
PublicationInput,
TextOutput,
textOutputPath,
} from "./mod.ts";
import { inspectEpub } from "../epub_builder/epub_builder.ts";
Deno.test("publication input renders chapter HTML once and preserves metadata", async () => {
const root = await Deno.makeTempDir();
try {
await Deno.mkdir(`${root}/1::Column`);
await Deno.writeTextFile(
`${root}/1::Column/1::Title.md`,
"# {{ document.title }}\n\n{{ greeting }}",
);
const document = await new PublicationInput({
journal: {
from_directory: root,
template_directory: root,
build_mode: "detached",
build_js_script: false,
},
}, { greeting: "Hello" }).read();
assertEquals(document.chapters[0].id, "article-1");
assertEquals(document.chapters[0].column.name, "Column");
assertStringIncludes(document.chapters[0].html, "Hello");
assertEquals(document.chapters[0].html.includes("article-start-"), false);
} finally {
await Deno.remove(root, { recursive: true });
}
});
Deno.test("HTML input exports text and EPUB without reading publication sources", async () => {
const root = await Deno.makeTempDir();
const document: HtmlDocument = {
kind: "html",
metadata: { title: "Book", author: "Author", language: "en" },
baseDirectory: root,
assetBase: root,
chapters: [{
id: "article-1",
title: "Title",
index: 1,
sourcePath: `${root}/missing.md`,
column: { name: "Column", index: 1 },
html: "<h1>Title</h1><p>Hello <strong>world</strong></p>",
}],
layout: { cover: "", styles: "", before: "", after: "" },
};
const original = JSON.stringify(document);
const config = {
journal: {
from_directory: `${root}/does-not-exist`,
build_js_script: false as const,
},
md: { path: `${root}/book.md` },
};
try {
for (const format of ["html", "md", "txt"] as const) {
const result = await convertDocument(
new HtmlInput(document),
new TextOutput(config, format),
);
const content = await Deno.readTextFile(result.path);
assertStringIncludes(content, "Hello");
assertEquals(content.includes("article-start-"), false);
}
const result = await convertDocument(
new HtmlInput(document),
new EpubOutput(config),
);
const archive = inspectEpub(await Deno.readFile(result.path));
assertStringIncludes(
new TextDecoder().decode(archive["EPUB/text/0001-title.xhtml"]),
"Hello",
);
assertEquals(JSON.stringify(document), original);
assertEquals(
textOutputPath({ ...config, html: { path: "custom.html" } }, "html"),
"custom.html",
);
if (Deno.env.get("CHROMIUM_PATH")) {
const pdf = await convertDocument(
new HtmlInput(document),
new PdfOutput({
...config,
pdf: { generate_index: false },
playwright: { path: `${root}/book.pdf`, format: "A4" },
}),
);
assertEquals((await Deno.stat(pdf.path)).size > 0, true);
}
} finally {
await Deno.remove(root, { recursive: true });
}
});