74 lines
2.2 KiB
TypeScript
74 lines
2.2 KiB
TypeScript
import { assertEquals } from "@std/assert";
|
|
import {
|
|
findTitlePage,
|
|
findTitlePages,
|
|
normalizePdfText,
|
|
} from "./index_builder.ts";
|
|
|
|
Deno.test("normalizes title whitespace and line breaks", () => {
|
|
assertEquals(normalizePdfText("工人\n 解放 报"), "工人解放报");
|
|
});
|
|
|
|
Deno.test("normalizes PDF compatibility ideographs", () => {
|
|
assertEquals(
|
|
normalizePdfText("⼯⼚通讯:⼀个发展巴布⽯金式⼯人同志的案\n例"),
|
|
"工厂通讯一个发展巴布石金式工人同志的案例",
|
|
);
|
|
});
|
|
|
|
Deno.test("finds multiple titles on the same printable page", () => {
|
|
const pages = ["封面", "文章甲正文 文章乙正文", "文章丙正文"];
|
|
assertEquals(findTitlePage("文章甲", pages), 2);
|
|
assertEquals(findTitlePage("文章乙", pages), 2);
|
|
assertEquals(findTitlePage("文章丙", pages), 3);
|
|
assertEquals(findTitlePage("不存在", pages), undefined);
|
|
});
|
|
|
|
Deno.test("supports single-jump, sequential, and page-window search modes", () => {
|
|
const pages = ["文章甲正文 文章乙正文", "中间内容", "文章丙正文"];
|
|
assertEquals(
|
|
findTitlePages(["文章甲", "文章乙", "文章丙"], pages),
|
|
[1, undefined, 3],
|
|
);
|
|
assertEquals(
|
|
findTitlePages(
|
|
["封面文章", "文章甲", "文章乙"],
|
|
["封面文章", "目录页", "文章甲正文", "文章甲续页 文章乙正文"],
|
|
),
|
|
[1, 3, 4],
|
|
);
|
|
assertEquals(
|
|
findTitlePages(
|
|
["文章甲", "文章乙"],
|
|
["封面文章甲和文章乙目录", "文章甲正文", "文章乙正文"],
|
|
{ mode: "single_jump" },
|
|
),
|
|
[1, 3],
|
|
);
|
|
assertEquals(
|
|
findTitlePages(["文章甲", "文章乙", "文章丙"], pages, {
|
|
mode: "sequential",
|
|
}),
|
|
[1, 1, 3],
|
|
);
|
|
assertEquals(
|
|
findTitlePages(["文章甲", "文章乙", "文章丙"], pages, {
|
|
mode: "window",
|
|
beforePages: 0,
|
|
afterPages: 2,
|
|
}),
|
|
[1, 1, 3],
|
|
);
|
|
});
|
|
|
|
Deno.test("empty index merge is a no-op", async () => {
|
|
const { IndexBuilder } = await import("./index_builder.ts");
|
|
const builder = new IndexBuilder("/does/not/need/to/exist.pdf", {
|
|
journal: {
|
|
build_mode: "flat",
|
|
from_directory: ".",
|
|
},
|
|
});
|
|
assertEquals(await builder.combine_index_pdf_to_main_pdf(), 0);
|
|
});
|