fix(make-pdf): Bun.which-based binary resolution for browse + pdftotext on Windows

Extends v1.24.0.0's Bun.which + GSTACK_*_BIN override pattern (introduced in
browse/src/claude-bin.ts via #1252) to the two other binary resolvers in the
codebase: make-pdf/src/browseClient.ts:resolveBrowseBin and
make-pdf/src/pdftotext.ts:resolvePdftotext.

Same Windows quirks (fs.accessSync(X_OK) degrades to existence-check; `which`
isn't available outside Git Bash; bun --compile --outfile X emits X.exe), same
Bun.which-based fix shape, same env override convention.

Changes:
  - GSTACK_BROWSE_BIN / GSTACK_PDFTOTEXT_BIN as the v1.24-aligned overrides;
    BROWSE_BIN / PDFTOTEXT_BIN remain as back-compat aliases.
  - Bun.which() replaces execFileSync('which', ...) for PATH lookup. Handles
    Windows PATHEXT natively; no more `where`-vs-`which` branch.
  - findExecutable(base) helper exported from each module, probes .exe/.cmd/.bat
    after the bare-path miss on win32. Linux/macOS behavior is bit-identical
    (isExecutable short-circuits before the win32 branch ever runs).
  - macCandidates renamed posixCandidates (always was — /opt/homebrew, /usr/local,
    /usr/bin). No Windows candidates added; Poppler installs scatter across
    Scoop/Chocolatey/portable zips and guessing causes false positives.
  - Error messages get a Windows install hint (scoop install poppler / oschwartz10612)
    and `setx` example for GSTACK_*_BIN.
  - Pre-existing test 'honors BROWSE_BIN when it points at a real executable'
    was hardcoded /bin/sh — made cross-platform via a REAL_EXE constant
    (cmd.exe on win32, /bin/sh on POSIX). Was a Windows-CI blocker on its own.

Coordination: PR #1094 (@BkashJEE) covered browseClient.ts independently with a
narrower scope; this PR's pdftotext + cross-platform tests + GSTACK_*_BIN naming
are additive. Either order of merge works.

Test plan:
  - bun test make-pdf/test/browseClient.test.ts make-pdf/test/pdftotext.test.ts
    on win32 — 29 pass, 0 fail (12 new assertions: findExecutable POSIX/win32/null,
    resolveBrowseBin GSTACK_BROWSE_BIN + BROWSE_BIN + precedence + quote-strip,
    same shape for resolvePdftotext + Windows install hint in error message).
  - POSIX branch unchanged — fs.accessSync(X_OK) on Linux/macOS short-circuits
    before any win32 logic runs, matching the v1.24 claude-bin.ts pattern.
This commit is contained in:
Samuel Carson
2026-05-03 15:50:03 -05:00
parent bf65487162
commit b0c138c545
4 changed files with 329 additions and 88 deletions
+56 -26
View File
@@ -13,11 +13,14 @@
* between paragraphs, and homoglyph substitution. We add a word-token
* diff and a paragraph-boundary assertion on top.
*
* Resolution order for the pdftotext binary:
* 1. $PDFTOTEXT_BIN env override
* 2. `which pdftotext` on PATH
* 3. standard Homebrew paths on macOS
* 4. throws a friendly "install poppler" error
* Resolution order for the pdftotext binary (v1.24-aligned):
* 1. $GSTACK_PDFTOTEXT_BIN env override (preferred, matches v1.24 GSTACK_*_BIN pattern)
* 2. $PDFTOTEXT_BIN env override (back-compat alias)
* 3. PATH lookup via Bun.which('pdftotext') — handles Windows PATHEXT natively
* 4. standard POSIX paths (Homebrew + distro) — no Windows candidates because
* Poppler scatters across Scoop / Chocolatey / oschwartz10612-poppler-windows
* and guessing causes false positives. Set GSTACK_PDFTOTEXT_BIN explicitly.
* 5. throws a friendly "install poppler" error
*
* The wrapper is *optional at runtime*: production renders don't need it.
* Only the CI gate and unit tests invoke pdftotext.
@@ -41,30 +44,53 @@ export interface PdftotextInfo {
flavor: "poppler" | "xpdf" | "unknown";
}
/**
* Probe a base path for executability, honoring Windows extension suffixes.
* Matches browseClient.ts:findExecutable — duplicated rather than shared
* because the two modules already duplicate isExecutable for compile-isolation.
*/
export function findExecutable(base: string): string | null {
if (isExecutable(base)) return base;
if (process.platform === "win32") {
for (const ext of [".exe", ".cmd", ".bat"]) {
const withExt = base + ext;
if (isExecutable(withExt)) return withExt;
}
}
return null;
}
function resolveOverride(value: string | undefined, env: NodeJS.ProcessEnv): string | null {
if (!value?.trim()) return null;
const trimmed = value.trim().replace(/^"(.*)"$/, '$1');
if (path.isAbsolute(trimmed)) return findExecutable(trimmed);
const PATH = env.PATH ?? env.Path ?? '';
return Bun.which(trimmed, { PATH }) ?? null;
}
/**
* Locate pdftotext. Throws PdftotextUnavailableError if none is found.
*/
export function resolvePdftotext(): PdftotextInfo {
const envOverride = process.env.PDFTOTEXT_BIN;
if (envOverride && isExecutable(envOverride)) {
return describeBinary(envOverride);
}
export function resolvePdftotext(env: NodeJS.ProcessEnv = process.env): PdftotextInfo {
// 1 + 2: env overrides (GSTACK_PDFTOTEXT_BIN preferred, PDFTOTEXT_BIN back-compat).
const overrideRaw = env.GSTACK_PDFTOTEXT_BIN ?? env.PDFTOTEXT_BIN;
const override = resolveOverride(overrideRaw, env);
if (override) return describeBinary(override);
// Try PATH
try {
const which = execFileSync("which", ["pdftotext"], { encoding: "utf8" }).trim();
if (which && isExecutable(which)) return describeBinary(which);
} catch {
// fall through
}
// 3: PATH lookup via Bun.which — handles Windows PATHEXT natively.
const PATH = env.PATH ?? env.Path ?? '';
const onPath = Bun.which('pdftotext', { PATH });
if (onPath) return describeBinary(onPath);
// Common macOS Homebrew locations
const macCandidates = [
"/opt/homebrew/bin/pdftotext", // Apple Silicon
// 4: POSIX-only standard locations. No Windows candidates — Poppler installs
// scatter across Scoop/Chocolatey/portable zips and guessing causes false
// positives. Windows users set GSTACK_PDFTOTEXT_BIN explicitly.
const posixCandidates = [
"/opt/homebrew/bin/pdftotext", // Apple Silicon Homebrew
"/usr/local/bin/pdftotext", // Intel Mac or Linuxbrew
"/usr/bin/pdftotext", // distro package
];
for (const candidate of macCandidates) {
for (const candidate of posixCandidates) {
if (isExecutable(candidate)) return describeBinary(candidate);
}
@@ -75,12 +101,16 @@ export function resolvePdftotext(): PdftotextInfo {
"(Runtime rendering does NOT need it. This only affects tests.)",
"",
"To install:",
" macOS: brew install poppler",
" Ubuntu: sudo apt-get install poppler-utils",
" Fedora: sudo dnf install poppler-utils",
" macOS: brew install poppler",
" Ubuntu: sudo apt-get install poppler-utils",
" Fedora: sudo dnf install poppler-utils",
" Windows: scoop install poppler (or download from",
" https://github.com/oschwartz10612/poppler-windows)",
"",
"Or set PDFTOTEXT_BIN to an explicit path:",
" export PDFTOTEXT_BIN=/path/to/pdftotext",
"Or set GSTACK_PDFTOTEXT_BIN to an explicit path:",
process.platform === "win32"
? ' setx GSTACK_PDFTOTEXT_BIN "C:\\path\\to\\pdftotext.exe"'
: " export GSTACK_PDFTOTEXT_BIN=/path/to/pdftotext",
].join("\n"));
}