cells2table 0.2.2__tar.gz → 0.2.3__tar.gz

{cells2table-0.2.2 → cells2table-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cells2table
-Version: 0.2.2
+Version: 0.2.3
 Summary: Table image parsing with cell detection models
 Keywords: docling,plugin
 Author: jspast

cells2table-0.2.3/cells2table/cli.py

@@ -0,0 +1,49 @@
+import argparse
+import logging
+from pathlib import Path
+
+import cv2
+
+from cells2table import DefaultPipeline
+from cells2table.utils.visualize import visualize_table
+
+logger = logging.getLogger(__name__)
+
+
+def main() -> None:
+    """Basic CLI program for testing."""
+
+    log_format = "%(asctime)s\t%(levelname)s\t%(name)s: %(message)s"
+    logging.basicConfig(level=logging.DEBUG, format=log_format)
+
+    parser = argparse.ArgumentParser(description="Load an image from a given path using OpenCV")
+    parser.add_argument("image_path", type=Path, help="Path to the image file")
+
+    args = parser.parse_args()
+
+    if not args.image_path.exists():
+        raise FileNotFoundError(f"File does not exist: {args.image_path}")
+
+    image = cv2.imread(str(args.image_path))
+
+    if image is None:
+        raise ValueError(f"Failed to load image: {args.image_path}")
+
+    logger.info("Image loaded successfully from %s", args.image_path)
+    logger.debug(
+        "Image proprieties: width=%d, height=%d, channels=%d, datatype=%s",
+        image.shape[1],
+        image.shape[0],
+        image.shape[2],
+        str(image.dtype),
+    )
+
+    table_pipeline = DefaultPipeline()
+    tables = table_pipeline([image])
+
+    for table in tables:
+        visualize_table(image, table)  # type: ignore
+
+
+if __name__ == "__main__":
+    main()

{cells2table-0.2.2/src → cells2table-0.2.3}/cells2table/models/PaddlePaddle/cell_detection.py

@@ -58,22 +58,24 @@ class PaddlePaddleCellDetectionModel(DetectionModel, OnnxModel):
         scale_factors: Sequence[tuple[int, int]],
     ) -> list[Iterator[DetectionResult]]:
         last_cell_idx = 0
-        batch_size = len(pred[1])
-        generators = []
         cells = pred[0]
 
-        for i in range(batch_size):
-            c = cells[last_cell_idx : last_cell_idx + pred[1][i]]
+        generators = []
+
+        for i, count in enumerate(pred[1]):
+            c = cells[last_cell_idx : last_cell_idx + count]
             c = c[c[:, 1] > CONFIDENCE_THRESHOLD]
+            last_cell_idx += count
 
-            last_cell_idx += pred[1][i]
+            if not c.size:
+                generators.append(iter([]))
+                continue
 
-            if c.size:
-                sx, sy = scale_factors[i]
-                scores = c[:, 0]
-                boxes = c[:, 2:]
-                boxes[:, [0, 2]] *= sy
-                boxes[:, [1, 3]] *= sx
+            sx, sy = scale_factors[i]
+            scores = c[:, 0]
+            boxes = c[:, 2:]
+            boxes[:, [0, 2]] *= sy
+            boxes[:, [1, 3]] *= sx
 
             generators.append((DetectionResult(box, score) for box, score in zip(boxes, scores)))
 

{cells2table-0.2.2 → cells2table-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cells2table"
-version = "0.2.2"
+version = "0.2.3"
 description = "Table image parsing with cell detection models"
 readme = "README.md"
 requires-python = ">=3.12,<4.0"
@@ -24,7 +24,7 @@ Homepage = "https://github.com/jspast/cells2table"
 Issues = "https://github.com/jspast/cells2table/issues"
 
 [project.scripts]
-cells2table = "cli:main"
+cells2table = "cells2table.cli:main"
 
 [project.entry-points.docling]
 cells2table = "cells2table.docling"
@@ -69,3 +69,7 @@ conflicts = [
     { extra = "onnx_openvino" }
   ]
 ]
+
+[tool.uv.build-backend]
+module-name = "cells2table"
+module-root = ""