feat: 实现 Pandoc DOCX 转换服务

2026-07-30 15:05:50 +08:00
parent fa159d916f
commit bf43433d38
32 changed files with 2908 additions and 61 deletions
@@ -0,0 +1,124 @@
+import { spawn } from "node:child_process";
+
+export type PandocProcessOutcome =
+  | "completed"
+  | "not-found"
+  | "not-executable"
+  | "timeout"
+  | "aborted"
+  | "output-limit";
+
+export interface PandocProcessResult {
+  outcome: PandocProcessOutcome;
+  exitCode: number | null;
+  stdout: Uint8Array;
+  stderr: string;
+}
+
+export interface PandocProcessOptions {
+  cwd?: string;
+  env?: NodeJS.ProcessEnv;
+  timeoutMs: number;
+  maxStdoutBytes: number;
+  maxStderrBytes: number;
+  signal?: AbortSignal;
+}
+
+export type PandocProcessRunner = (
+  executablePath: string,
+  arguments_: readonly string[],
+  options: PandocProcessOptions
+) => Promise<PandocProcessResult>;
+
+function decodeStderr(chunks: Buffer[]) {
+  return Buffer.concat(chunks).toString("utf8");
+}
+
+export const runPandocProcess: PandocProcessRunner = (
+  executablePath,
+  arguments_,
+  options
+) =>
+  new Promise((resolve) => {
+    const child = spawn(executablePath, [...arguments_], {
+      cwd: options.cwd,
+      env: options.env,
+      shell: false,
+      windowsHide: true,
+      stdio: ["ignore", "pipe", "pipe"]
+    });
+    const stdout: Buffer[] = [];
+    const stderr: Buffer[] = [];
+    let stdoutBytes = 0;
+    let stderrBytes = 0;
+    let settled = false;
+    let forcedOutcome: PandocProcessOutcome | undefined;
+
+    const settle = (
+      outcome: PandocProcessOutcome,
+      exitCode: number | null
+    ) => {
+      if (settled) {
+        return;
+      }
+      settled = true;
+      clearTimeout(timeout);
+      options.signal?.removeEventListener("abort", abort);
+      resolve({
+        outcome,
+        exitCode,
+        stdout: Buffer.concat(stdout),
+        stderr: decodeStderr(stderr)
+      });
+    };
+    const stop = (outcome: PandocProcessOutcome) => {
+      if (settled || forcedOutcome) {
+        return;
+      }
+      forcedOutcome = outcome;
+      child.kill();
+    };
+    const abort = () => stop("aborted");
+    const timeout = setTimeout(
+      () => stop("timeout"),
+      options.timeoutMs
+    );
+    timeout.unref();
+
+    if (options.signal?.aborted) {
+      abort();
+    } else {
+      options.signal?.addEventListener("abort", abort, {
+        once: true
+      });
+    }
+
+    child.stdout.on("data", (chunk: Buffer) => {
+      stdoutBytes += chunk.byteLength;
+      if (stdoutBytes > options.maxStdoutBytes) {
+        stop("output-limit");
+        return;
+      }
+      stdout.push(chunk);
+    });
+    child.stderr.on("data", (chunk: Buffer) => {
+      stderrBytes += chunk.byteLength;
+      if (stderrBytes > options.maxStderrBytes) {
+        stop("output-limit");
+        return;
+      }
+      stderr.push(chunk);
+    });
+    child.on("error", (error: NodeJS.ErrnoException) => {
+      const outcome =
+        error.code === "ENOENT"
+          ? "not-found"
+          : error.code === "EACCES" || error.code === "EPERM"
+            ? "not-executable"
+            : "not-executable";
+      settle(outcome, null);
+    });
+    child.on("close", (exitCode) => {
+      settle(forcedOutcome ?? "completed", exitCode);
+    });
+  });