mathcraft-ocr 0.2.3__tar.gz → 0.2.4__tar.gz

{mathcraft_ocr-0.2.3/mathcraft_ocr.egg-info → mathcraft_ocr-0.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mathcraft-ocr
-Version: 0.2.3
+Version: 0.2.4
 Summary: ONNX-only OCR runtime for mathematical documents
 Author: SakuraMathcraft
 License-Expression: MIT

{mathcraft_ocr-0.2.3 → mathcraft_ocr-0.2.4}/README.md

@@ -6,7 +6,7 @@ MathCraft OCR recognizes formulae, text, and mixed mathematical documents with a
 
 ## Quick Start
 
-Current PyPI release line: `mathcraft-ocr 0.2.3`.
+Current PyPI release line: `mathcraft-ocr 0.2.4`.
 
 Install the library and CLI without choosing an ONNX Runtime backend:
 
@@ -121,11 +121,11 @@ for block in result.blocks:
 
 ## Runtime Release Notes
 
-`mathcraft-ocr 0.2.3` fixes cross-platform hardware sizing. Memory detection now uses optional `psutil`, Windows API, POSIX `sysconf`, and macOS `vm_stat`, so CPU batch sizing no longer falls back to Windows-only memory data on Linux or macOS. It also moves the default writable model cache to platform-native user data locations on macOS and Linux. The active `v1.0.0` ONNX model asset set is unchanged.
+`mathcraft-ocr 0.2.4` fixes DirectML provider handling for RapidOCR text recognition. CUDA and TensorRT providers enable CUDA runtime options, DirectML enables DirectML runtime options, and CPU remains CPU-only. The active `v1.0.0` ONNX model asset set is unchanged.
 
-Earlier `0.2.x` releases improved runtime-side formula post-processing without changing the active `v1.0.0` ONNX model asset set. They keep compact fraction expressions whole, avoid splitting matrix-like wide formulas, add relation-aware `aligned` output, and retry severe segmented-line artifacts with safer whole-line or whole-image recognition.
+`mathcraft-ocr 0.2.3` fixes cross-platform hardware sizing. Memory detection now uses optional `psutil`, Windows API, POSIX `sysconf`, and macOS `vm_stat`, so CPU batch sizing no longer falls back to Windows-only memory data on Linux or macOS. It also moves the default writable model cache to platform-native user data locations on macOS and Linux.
 
-Earlier `0.2.x` releases updated the runtime-side formula recognition path with line-aware formula splitting and reassembly. This improved long multi-line formula handling without changing the active `v1.0.0` ONNX model asset set.
+Earlier `0.2.x` releases improved runtime-side formula post-processing without changing the active `v1.0.0` ONNX model asset set. They keep compact fraction expressions whole, avoid splitting matrix-like wide formulas, add relation-aware `aligned` output, and retry severe segmented-line artifacts with safer whole-line or whole-image recognition.
 
 ## Model Set
 

{mathcraft_ocr-0.2.3 → mathcraft_ocr-0.2.4}/mathcraft_ocr/__init__.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-__version__ = "0.2.3"
+__version__ = "0.2.4"
 
 __all__ = [
     "DoctorReport",

{mathcraft_ocr-0.2.3 → mathcraft_ocr-0.2.4}/mathcraft_ocr/adapters/text_recognizer.py

@@ -54,12 +54,14 @@ def recognize_pp_text_lines(
 
 def _create_pp_text_recognizer(model_dir: Path, provider_info) -> TextRecognizer:
     model_dir = model_dir.resolve()
-    use_cuda = bool(getattr(provider_info, "device", "") == "gpu")
-    return _create_pp_text_recognizer_cached(str(model_dir), use_cuda)
+    active_provider = str(getattr(provider_info, "active_provider", "") or "")
+    use_cuda = active_provider in {"CUDAExecutionProvider", "TensorrtExecutionProvider"}
+    use_dml = active_provider == "DmlExecutionProvider"
+    return _create_pp_text_recognizer_cached(str(model_dir), use_cuda, use_dml)
 
 
 @lru_cache(maxsize=8)
-def _create_pp_text_recognizer_cached(model_dir: str, use_cuda: bool) -> TextRecognizer:
+def _create_pp_text_recognizer_cached(model_dir: str, use_cuda: bool, use_dml: bool) -> TextRecognizer:
     model_dir = Path(model_dir)
     model_candidates = sorted(model_dir.glob("**/*rec*.onnx"))
     if not model_candidates:
@@ -96,7 +98,7 @@ def _create_pp_text_recognizer_cached(model_dir: str, use_cuda: bool) -> TextRec
                 "cudnn_conv_algo_search": "EXHAUSTIVE",
                 "do_copy_in_default_stream": True,
             },
-            "use_dml": False,
+            "use_dml": use_dml,
             "dm_ep_cfg": None,
             "use_cann": False,
             "cann_ep_cfg": {

{mathcraft_ocr-0.2.3 → mathcraft_ocr-0.2.4}/mathcraft_ocr/providers.py

@@ -25,6 +25,14 @@ class ProviderInfo:
     gpu_runtime_ok: bool
     cpu_fallback: bool
 
+    @property
+    def use_cuda(self) -> bool:
+        return self.active_provider in {"CUDAExecutionProvider", "TensorrtExecutionProvider"}
+
+    @property
+    def use_dml(self) -> bool:
+        return self.active_provider == "DmlExecutionProvider"
+
 
 def detect_providers(prefer: str = "auto") -> ProviderInfo:
     prefer_norm = (prefer or "auto").strip().lower()

{mathcraft_ocr-0.2.3 → mathcraft_ocr-0.2.4}/mathcraft_ocr/serialization.py

@@ -72,6 +72,8 @@ def provider_info_to_json(provider_info) -> dict:
         "gpu_requested": provider_info.gpu_requested,
         "gpu_runtime_ok": provider_info.gpu_runtime_ok,
         "cpu_fallback": provider_info.cpu_fallback,
+        "use_cuda": provider_info.use_cuda,
+        "use_dml": provider_info.use_dml,
     }
 
 

{mathcraft_ocr-0.2.3 → mathcraft_ocr-0.2.4/mathcraft_ocr.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mathcraft-ocr
-Version: 0.2.3
+Version: 0.2.4
 Summary: ONNX-only OCR runtime for mathematical documents
 Author: SakuraMathcraft
 License-Expression: MIT

{mathcraft_ocr-0.2.3 → mathcraft_ocr-0.2.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mathcraft-ocr"
-version = "0.2.3"
+version = "0.2.4"
 description = "ONNX-only OCR runtime for mathematical documents"
 readme = "README_MATHCRAFT_OCR.md"
 requires-python = ">=3.10"