fix(release): repair ARM64 package builds (#411)

Define the ARMv8 assembler macro for legacy AArch64 cross-compilers used by the npm and PyPI release matrices, and keep independent targets running when one fails.

.github/workflows/ci.yml

@@ -180,18 +180,31 @@ jobs:
           test -n "$ort_path"
           echo "ORT_DYLIB_PATH=$ort_path" >> "$GITHUB_ENV"
 
+      - name: Configure isolated model cache
+        shell: bash
+        run: echo "PDF_INSPECTOR_MODEL_CACHE=$RUNNER_TEMP/pdf-inspector-models" >> "$GITHUB_ENV"
+
       - name: Build OCR CLI
         run: cargo build --features ocr --bin pdf2md
 
       - name: Test PDFium runtime
         run: cargo test --features ocr --test local_render_tests
 
+      - name: Provision OCR model cache
+        shell: bash
+        run: |
+          target/debug/pdf2md \
+            tests/fixtures/scan_with_native_header_text.pdf \
+            --ocr force \
+            --json > /dev/null
+
       - name: Run OCR CLI
         shell: bash
         run: |
           target/debug/pdf2md \
             tests/fixtures/scan_with_native_header_text.pdf \
             --ocr auto \
+            --ocr-offline \
             --json > "$RUNNER_TEMP/ocr-result.json"
 
       - name: Validate OCR JSON contract
@@ -213,6 +226,12 @@ jobs:
           assert "layout_ms" not in result["pages"][0]["timings"]
           PY
 
+      - name: Run OCR launch smoke set
+        shell: bash
+        run: |
+          export PDF_INSPECTOR_OCR_TEST_MODELS="$PDF_INSPECTOR_MODEL_CACHE/pp-ocrv6-small/oar-ocr-v0.7.0"
+          cargo test --features ocr --test ocr_tests -- --nocapture
+
       - name: Build Node binding
         working-directory: napi
         run: |

.github/workflows/publish-pypi.yml

@@ -86,12 +86,14 @@ jobs:
     name: Build ${{ matrix.target }}
     runs-on: ${{ matrix.os }}
     strategy:
+      fail-fast: false
       matrix:
         include:
           - os: ubuntu-latest
             target: x86_64-unknown-linux-gnu
           - os: ubuntu-latest
             target: aarch64-unknown-linux-gnu
+            docker-options: -e CFLAGS_aarch64_unknown_linux_gnu=-D__ARM_ARCH=8
           # macos-13 was retired by GitHub; macos-15-intel is the remaining
           # Intel runner label (available through 2027).
           - os: macos-15-intel
@@ -113,6 +115,9 @@ jobs:
           target: ${{ matrix.target }}
           args: --release --out dist
           manylinux: auto
+          # The manylinux AArch64 GCC omits this macro while preprocessing
+          # ring's assembly. AArch64 is ARMv8 by definition.
+          docker-options: ${{ matrix.docker-options }}
 
       - name: Upload wheel
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1

.github/workflows/publish.yml

@@ -60,6 +60,7 @@ jobs:
     name: Build ${{ matrix.target }}
     runs-on: ${{ matrix.os }}
     strategy:
+      fail-fast: false
       matrix:
         include:
           - os: ubuntu-latest
@@ -70,6 +71,7 @@ jobs:
           - os: ubuntu-latest
             target: aarch64-unknown-linux-gnu
             build-flags: --use-napi-cross
+            cflags: -D__ARM_ARCH=8
           - os: ubuntu-latest
             target: x86_64-unknown-linux-musl
             build-flags: -x
@@ -126,6 +128,10 @@ jobs:
 
       - name: Build native addon
         working-directory: napi
+        env:
+          # napi-cross's old AArch64 GCC omits this predefined macro while
+          # preprocessing ring's assembly. AArch64 is ARMv8 by definition.
+          CFLAGS_aarch64_unknown_linux_gnu: ${{ matrix.cflags }}
         run: bunx napi build --platform --release --target ${{ matrix.target }} ${{ matrix.build-flags }}
 
       - name: Upload native binary

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "pdf-inspector"
-version = "1.14.2"
+version = "1.15.0"
 edition = "2021"
 autobins = false
 authors = ["Firecrawl Team"]

README.md

@@ -48,8 +48,7 @@ Use the [paired benchmark harness](docs/benchmarking.md) to compare two local bu
 ### Python
 
 ```bash
-pip install maturin
-maturin develop --release
+pip install pdf-inspector
 ```
 
 ```python
@@ -182,8 +181,9 @@ and confidence, warnings, and pages recommended for the hosted document
 pipeline. Native Python and Node packages expose the same pipeline without a
 source-build feature. All native entry points still require separately
 installed PDFium and ONNX Runtime libraries only when OCR is routed. See the
-[Rust API guide](docs/rust-api.md#complete-ocr-api) for model cache and offline
-configuration.
+[OCR runtime setup guide](docs/ocr-runtime.md) for pinned downloads, platform
+support, model-cache behavior, and hosted-fallback integration. See the
+[Rust API guide](docs/rust-api.md#complete-ocr-api) for lower-level controls.
 
 From a source checkout, use `cargo run --bin pdf2md -- document.pdf` or `cargo run --bin detect-pdf -- document.pdf` instead.
 

docs/ocr-runtime.md

@@ -0,0 +1,97 @@
+# OCR runtime setup
+
+Selective OCR is available from the Rust library and CLI, Python, and Node.js.
+Clean native-text documents do not load an OCR dependency or download a model.
+When `auto` routes at least one page, the process needs PDFium, ONNX Runtime,
+and the pinned PP-OCRv6 Small model set.
+
+## Validated versions
+
+The reproducible runtime path uses these builds:
+
+- [Firecrawl PDFium `native-v7988`](https://github.com/firecrawl/pdfium-rs/releases/tag/native-v7988),
+  containing PDFium `153.0.7988.0`
+- [ONNX Runtime `1.27.0`](https://github.com/microsoft/onnxruntime/releases/tag/v1.27.0)
+- PP-OCRv6 Small artifact revision `oar-ocr-v0.7.0`
+
+Use these versions for the reproducible path. Other compatible shared-library
+builds may work, but are not part of the release smoke test.
+
+## Install the shared libraries
+
+Download and extract the matching archives:
+
+| Platform | PDFium asset | ONNX Runtime asset |
+|---|---|---|
+| Linux x64 | `firecrawl-pdfium-linux-x64.tgz` | `onnxruntime-linux-x64-1.27.0.tgz` |
+| Linux ARM64 | `firecrawl-pdfium-linux-arm64.tgz` | `onnxruntime-linux-aarch64-1.27.0.tgz` |
+| macOS Apple Silicon | `firecrawl-pdfium-mac-arm64.tgz` | `onnxruntime-osx-arm64-1.27.0.tgz` |
+| Windows x64 | `firecrawl-pdfium-win-x64.tgz` | `onnxruntime-win-x64-1.27.0.zip` |
+
+The PDFium release publishes `SHA256SUMS`, build provenance, license files,
+and an SPDX document for every platform archive. GitHub publishes a SHA-256
+digest with each ONNX Runtime asset.
+
+Point pdf-inspector at the extracted shared libraries when they are not on the
+platform library search path:
+
+```bash
+export PDFIUM_LIB_PATH=/absolute/path/to/libpdfium.so
+export ORT_DYLIB_PATH=/absolute/path/to/libonnxruntime.so
+pdf2md scan.pdf --ocr auto --json
+```
+
+On macOS the filenames end in `.dylib`. On Windows, use PowerShell and point
+the variables at `pdfium.dll` and `onnxruntime.dll`:
+
+```powershell
+$env:PDFIUM_LIB_PATH = "C:\absolute\path\to\pdfium.dll"
+$env:ORT_DYLIB_PATH = "C:\absolute\path\to\onnxruntime.dll"
+pdf2md scan.pdf --ocr auto --json
+```
+
+The native extraction packages also support platforms without these exact
+runtime assets. In particular, the Python package has an Intel macOS wheel,
+but ONNX Runtime 1.27.0 does not publish an Intel macOS archive; local OCR on
+that target requires a compatible custom ONNX Runtime build.
+
+The full OCR path is exercised end to end on Linux x64 in CI. macOS and
+Windows compile and run the feature's platform-independent tests, while their
+external-runtime paths should be treated as preview until equivalent smoke
+jobs are added.
+
+## Model cache and offline mode
+
+The first routed page downloads and SHA-256-verifies three pinned artifacts:
+the detection model, recognition model, and character dictionary. Together
+they are about 31 MB. They are stored below the platform cache directory.
+Set `PDF_INSPECTOR_MODEL_CACHE` to choose a managed cache root.
+
+For hermetic deployments, populate the model directory ahead of time and use
+the language-specific offline option:
+
+- CLI: `--ocr-offline --ocr-model-dir /models/pp-ocrv6-small`
+- Rust: `ModelDownloadPolicy::Offline` with `OcrOptions::model_directory`
+- Python: `offline=True, model_directory="/models/pp-ocrv6-small"`
+- Node.js: `offline: true, modelDirectory: "/models/pp-ocrv6-small"`
+
+The model artifacts come from
+[`GreatV/oar-ocr`](https://github.com/GreatV/oar-ocr/releases/tag/v0.7.0),
+whose OCR implementation and upstream PaddleOCR project use Apache-2.0
+licensing. Models are downloaded at runtime and are not embedded in any
+pdf-inspector package.
+
+## Hosted fallback boundary
+
+`pages_recommending_hosted` is available after the local pipeline completes.
+It marks pages whose completed OCR result is empty, low-confidence, or still
+appears incomplete.
+
+Setup and execution failures happen before that result exists. A missing or
+incompatible PDFium/ONNX Runtime library, failed model acquisition, or OCR
+execution error is returned as an error. A downstream integration that has a
+hosted parser should catch that error and route the document to the hosted
+path. This keeps deployment problems distinct from page-quality judgments.
+
+In `auto`, documents with no routed pages return successfully without touching
+PDFium, ONNX Runtime, the model cache, or the network.

docs/python.md

@@ -44,7 +44,9 @@ OCR calls that route work require compatible PDFium and ONNX Runtime shared
 libraries. Set `PDFIUM_LIB_PATH` and `ORT_DYLIB_PATH` when they are not on the
 platform library search path. The pinned OCR model set is downloaded and
 checksum-verified on the first routed page; use `offline=True` with a warm
-cache or `model_directory` to prohibit network access.
+cache or `model_directory` to prohibit network access. See the
+[OCR runtime setup guide](https://github.com/firecrawl/pdf-inspector/blob/main/docs/ocr-runtime.md)
+for pinned downloads, supported platforms, and hosted-fallback behavior.
 
 ## Usage
 

docs/rust-api.md

@@ -383,6 +383,10 @@ shape; `Force` renders every selected page. OCR uses the existing deterministic
 table, column, reading-order, and Markdown assembly path; no learned layout
 model is included.
 
+The [OCR runtime setup guide](https://github.com/firecrawl/pdf-inspector/blob/main/docs/ocr-runtime.md)
+lists the pinned PDFium and ONNX Runtime builds, environment variables, model
+cache behavior, and the error boundary downstream hosted fallbacks should use.
+
 For ambiguous mixed pages, `Auto` privately retains clean native fragments
 instead of discarding them when OCR is selected. After recognition it compares
 script-agnostic text quality, OCR confidence, character overlap, and material

napi/Cargo.lock

@@ -2089,7 +2089,7 @@ checksum = "2ee67f1008b1ba2321834326597b8e186293b049a023cdef258527550b9935b4"
 
 [[package]]
 name = "pdf-inspector"
-version = "1.14.2"
+version = "1.15.0"
 dependencies = [
  "dirs",
  "env_logger",
@@ -2114,7 +2114,7 @@ dependencies = [
 
 [[package]]
 name = "pdf-inspector-napi"
-version = "1.14.2"
+version = "1.15.0"
 dependencies = [
  "napi",
  "napi-build",

napi/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "pdf-inspector-napi"
-version = "1.14.2"
+version = "1.15.0"
 edition = "2021"
 
 [lib]

napi/README.md

@@ -41,7 +41,9 @@ OCR calls that route work require compatible PDFium and ONNX Runtime shared
 libraries. Set `PDFIUM_LIB_PATH` and `ORT_DYLIB_PATH` when they are not on the
 platform library search path. The pinned OCR model set is downloaded and
 checksum-verified on the first routed page; use `offline: true` with a warm
-cache or `modelDirectory` to prohibit network access.
+cache or `modelDirectory` to prohibit network access. See the
+[OCR runtime setup guide](https://github.com/firecrawl/pdf-inspector/blob/main/docs/ocr-runtime.md)
+for pinned downloads, supported platforms, and hosted-fallback behavior.
 
 ## API
 

napi/bun.lock

@@ -8,12 +8,12 @@
         "@napi-rs/cli": "^3.4.1",
       },
       "optionalDependencies": {
-        "@firecrawl/pdf-inspector-darwin-arm64": "1.14.2",
-        "@firecrawl/pdf-inspector-linux-arm64-gnu": "1.14.2",
-        "@firecrawl/pdf-inspector-linux-arm64-musl": "1.14.2",
-        "@firecrawl/pdf-inspector-linux-x64-gnu": "1.14.2",
-        "@firecrawl/pdf-inspector-linux-x64-musl": "1.14.2",
-        "@firecrawl/pdf-inspector-win32-x64-msvc": "1.14.2",
+        "@firecrawl/pdf-inspector-darwin-arm64": "1.15.0",
+        "@firecrawl/pdf-inspector-linux-arm64-gnu": "1.15.0",
+        "@firecrawl/pdf-inspector-linux-arm64-musl": "1.15.0",
+        "@firecrawl/pdf-inspector-linux-x64-gnu": "1.15.0",
+        "@firecrawl/pdf-inspector-linux-x64-musl": "1.15.0",
+        "@firecrawl/pdf-inspector-win32-x64-msvc": "1.15.0",
       },
     },
   },

napi/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@firecrawl/pdf-inspector",
-  "version": "1.14.2",
+  "version": "1.15.0",
   "description": "Fast PDF classification and text extraction. Detect text-based vs scanned PDFs, extract text by region with quality checks. Native Rust performance via napi-rs.",
   "main": "index.js",
   "types": "index.d.ts",
@@ -52,11 +52,11 @@
     "@napi-rs/cli": "^3.4.1"
   },
   "optionalDependencies": {
-    "@firecrawl/pdf-inspector-linux-x64-gnu": "1.14.2",
-    "@firecrawl/pdf-inspector-linux-x64-musl": "1.14.2",
-    "@firecrawl/pdf-inspector-linux-arm64-gnu": "1.14.2",
-    "@firecrawl/pdf-inspector-linux-arm64-musl": "1.14.2",
-    "@firecrawl/pdf-inspector-darwin-arm64": "1.14.2",
-    "@firecrawl/pdf-inspector-win32-x64-msvc": "1.14.2"
+    "@firecrawl/pdf-inspector-linux-x64-gnu": "1.15.0",
+    "@firecrawl/pdf-inspector-linux-x64-musl": "1.15.0",
+    "@firecrawl/pdf-inspector-linux-arm64-gnu": "1.15.0",
+    "@firecrawl/pdf-inspector-linux-arm64-musl": "1.15.0",
+    "@firecrawl/pdf-inspector-darwin-arm64": "1.15.0",
+    "@firecrawl/pdf-inspector-win32-x64-msvc": "1.15.0"
   }
 }

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "maturin"
 name = "pdf-inspector"
 # Keep package versions in sync with `python3 scripts/version.py <version>`.
 # CI publishes automatically when the synchronized change lands on main.
-version = "1.14.2"
+version = "1.15.0"
 description = "Fast PDF inspection, classification, and text extraction with smart scanned vs text-based detection"
 readme = "docs/python.md"
 license = { text = "MIT" }

site/index.html

@@ -975,7 +975,7 @@ result = pdf_inspector.<span class="fn">process_pdf</span>(<span class="str">"do
 <script>
   (() => {
     const MAX_FILE_SIZE = 25 * 1024 * 1024;
-    const WASM_MODULE_URL = "https://cdn.jsdelivr.net/npm/@firecrawl/pdf-inspector-wasm@1.14.2/pdf_inspector_wasm.js";
+    const WASM_MODULE_URL = "https://cdn.jsdelivr.net/npm/@firecrawl/pdf-inspector-wasm@1.15.0/pdf_inspector_wasm.js";
     const input = document.querySelector("#pdf-input");
     const dropZone = document.querySelector("#drop-zone");
     const filePanel = document.querySelector("#demo-file");

wasm/Cargo.lock

@@ -724,7 +724,7 @@ checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e"
 
 [[package]]
 name = "pdf-inspector"
-version = "1.14.2"
+version = "1.15.0"
 dependencies = [
  "env_logger",
  "include_dir",
@@ -740,7 +740,7 @@ dependencies = [
 
 [[package]]
 name = "pdf-inspector-wasm"
-version = "1.14.2"
+version = "1.15.0"
 dependencies = [
  "console_error_panic_hook",
  "js-sys",

wasm/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "pdf-inspector-wasm"
-version = "1.14.2"
+version = "1.15.0"
 edition = "2021"
 authors = ["Firecrawl Team"]
 description = "Browser WebAssembly bindings for pdf-inspector"