1 files changed, 117 insertions, 0 deletions
diff --git a/src/features/markdown/logic/text-file.test.ts b/src/features/markdown/logic/text-file.test.ts
new file mode 100644
index 0000000..5649b2f
--- /dev/null
+++ b/src/features/markdown/logic/text-file.test.ts
@@ -0,0 +1,117 @@
+import { describe, expect, it } from "vitest";
+import { splitTextFiles, textFilePath, textFilePreview } from "./text-file";
+
+const reference = (text: string, streaming = false) =>
+  splitTextFiles(text, streaming).filter((part) => part.kind === "text-file");
+describe("text-file opt-in parser", () => {
+  it.each([
+    ["[Plan](text-file:notes/plan.md)", "notes/plan.md"],
+    ["[Plan](text-file:/tmp/plan.md)", "/tmp/plan.md"],
+    ["[Plan](<text-file:notes/my plan.md>)", "notes/my plan.md"],
+    ["[Plan](text-file:notes/my%20plan.md)", "notes/my plan.md"],
+    ["[Plan](text-file:notes/100%25.md)", "notes/100%.md"],
+    ["[Plan](text-file:notes/literal%2520.md)", "notes/literal%20.md"],
+    [String.raw`[Plan](text-file:notes/plan\(1\).md)`, "notes/plan(1).md"],
+    [String.raw`[Plan](text-file:notes/a\_b.md)`, "notes/a_b.md"],
+  ])("parses %s", (text, path) =>
+    expect(reference(text)).toEqual([{ kind: "text-file", reference: { label: "Plan", path } }]));
+  it.each([
+    "[web](https://example.com)",
+    "![image](text-file:notes/a.md)",
+    "[file](file:///tmp/a.md)",
+    "see [Plan](text-file:a.md)",
+    "[Plan](text-file:a.md) suffix",
+    "`[Plan](text-file:a.md)`",
+    "```md\n[Plan](text-file:a.md)\n```",
+    "~~~\n[Plan](text-file:a.md)\n~~~",
+    "    [Plan](text-file:a.md)",
+    "> [Plan](text-file:a.md)",
+    "- [Plan](text-file:a.md)",
+    "[Plan](text-file:a.md",
+    "[Plan](text-file:",
+    "[Plan][p]\n\n[p]: text-file:a.md",
+    '[Plan](text-file:a.md "title")',
+    "<div data-text-file='a.md'>Plan</div>",
+  ])("does not opt in: %s", (text) => expect(reference(text)).toEqual([]));
+  it.each([
+    "file:///tmp/a",
+    "https://evil/a",
+    "//host/a",
+    "~/a",
+    "~user/a",
+    "a\\b",
+    "%00",
+    "%0a",
+    "%7f",
+    "a%5cb",
+    "%2f%2fhost/a",
+    "%68ttps://evil/a",
+    "bad%",
+    "",
+    " a",
+    "a ",
+  ])("rejects unsafe path %s", (path) => expect(textFilePath(`text-file:${path}`)).toBeNull());
+  it("waits for complete streaming paragraph boundary and keeps settled embeds", () => {
+    const complete = "[Plan](text-file:a.md)";
+    for (let i = 0; i <= complete.length; i++)
+      expect(reference(complete.slice(0, i), true)).toHaveLength(0);
+    expect(reference(`${complete}\n`, true)).toHaveLength(0);
+    expect(reference(`${complete}\n\n`, true)).toHaveLength(1);
+    expect(reference(`${complete}\n\ntail`, true)).toHaveLength(1);
+    expect(reference(`${complete} suffix`, true)).toHaveLength(0);
+    expect(reference(complete)).toHaveLength(1);
+  });
+  it("bounds per-message document count", () => {
+    const result = splitTextFiles(
+      Array.from({ length: 30 }, (_, i) => `[p](text-file:${i}.md)`).join("\n\n"),
+    );
+    expect(result.filter((p) => p.kind === "text-file")).toHaveLength(8);
+    expect(JSON.stringify(result)).toContain("embed limit reached");
+  });
+});
+describe("source-line preview", () => {
+  it.each([1, 6, 12])("does not overlap %i source lines", (n) => {
+    const text = Array.from({ length: n }, (_, i) => `${i}`).join("\n");
+    expect(textFilePreview(text, true)).toEqual({ head: text, tail: "", omitted: 0 });
+  });
+  it("takes first six and last six source lines, ignoring final newline", () => {
+    const result = textFilePreview(
+      `${Array.from({ length: 20 }, (_, i) => `line${i + 1}`).join("\n")}\n`,
+      true,
+    );
+    expect(result).toEqual({
+      head: "line1\nline2\nline3\nline4\nline5\nline6",
+      tail: "line15\nline16\nline17\nline18\nline19\nline20",
+      omitted: 8,
+    });
+  });
+  it("restores top-level fence context at fragment edges", () => {
+    const text = `\`\`\`js\n${Array.from({ length: 20 }, () => "const x = 1;").join("\n")}\n\`\`\``;
+    const result = textFilePreview(text, true);
+    expect(result.head).toMatch(/\n```$/);
+    expect(result.tail).toMatch(/^```js\n/);
+    expect(result.tail).toMatch(/\n```$/);
+    expect(textFilePreview(text, false).tail).not.toMatch(/^```js/);
+  });
+});
+
+describe("text-file parser boundary compatibility", () => {
+  it("preserves document-wide ordinary reference definitions across embed splits", () => {
+    const parts = splitTextFiles(
+      "[before][web]\n\n[Plan](text-file:a.md)\n\n[after][web]\n\n[web]: https://example.com",
+    );
+    expect(parts.filter((part) => part.kind === "text-file")).toHaveLength(1);
+    for (const part of parts) {
+      if (part.kind === "markdown") expect(part.text).toContain("[web]: https://example.com");
+    }
+  });
+  it.each([
+    "%C2%85",
+    "a".repeat(4097),
+  ])("rejects backend-unsupported controls or overlong paths", (path) => {
+    expect(textFilePath(`text-file:${path}`)).toBeNull();
+  });
+  it("accepts encoded filename delimiters without treating them as a URL query/fragment", () => {
+    expect(textFilePath("text-file:notes/a%23b%3Fc.md")).toBe("notes/a#b?c.md");
+  });
+});