docling-ibm-models 1.1.4__py3-none-any.whl → 1.1.6__py3-none-any.whl

docling_ibm_models/tableformer/data_management/tf_cell_matcher.py

@@ -127,13 +127,14 @@ class CellMatcher:
             Dictionary with all details about the mathings between the table and pdf cells
         """
         pdf_cells = copy.deepcopy(iocr_page["tokens"])
-        for word in pdf_cells:
-            word["bbox"] = [
-                word["bbox"]["l"],
-                word["bbox"]["t"],
-                word["bbox"]["r"],
-                word["bbox"]["b"],
-            ]
+        if len(pdf_cells) > 0:
+            for word in pdf_cells:
+                word["bbox"] = [
+                    word["bbox"]["l"],
+                    word["bbox"]["t"],
+                    word["bbox"]["r"],
+                    word["bbox"]["b"],
+                ]
         table_bboxes = prediction["bboxes"]
         table_classes = prediction["classes"]
         # BBOXES transformed...
@@ -145,9 +146,13 @@ class CellMatcher:
         table_cells = self._build_table_cells(
             html_seq, otsl_seq, table_bboxes_page, table_classes
         )
-        matches, matches_counter = self._intersection_over_pdf_match(
-            table_cells, pdf_cells
-        )
+
+        matches = {}
+        matches_counter = 0
+        if len(pdf_cells) > 0:
+            matches, matches_counter = self._intersection_over_pdf_match(
+                table_cells, pdf_cells
+            )
 
         self._log().debug("matches_counter: {}".format(matches_counter))
 
@@ -188,13 +193,14 @@ class CellMatcher:
             Dictionary with all details about the mathings between the table and pdf cells
         """
         pdf_cells = copy.deepcopy(iocr_page["tokens"])
-        for word in pdf_cells:
-            word["bbox"] = [
-                word["bbox"]["l"],
-                word["bbox"]["t"],
-                word["bbox"]["r"],
-                word["bbox"]["b"],
-            ]
+        if len(pdf_cells) > 0:
+            for word in pdf_cells:
+                word["bbox"] = [
+                    word["bbox"]["l"],
+                    word["bbox"]["t"],
+                    word["bbox"]["r"],
+                    word["bbox"]["b"],
+                ]
 
         table_bboxes = prediction["bboxes"]
         table_classes = prediction["classes"]

docling_ibm_models/tableformer/data_management/tf_predictor.py

@@ -696,7 +696,12 @@ class TFPredictor:
             prediction["bboxes"] = corrected_bboxes
 
         # Match the cells
-        matching_details = {"table_cells": [], "matches": {}}
+        matching_details = {
+            "table_cells": [],
+            "matches": {},
+            "pdf_cells": [],
+            "prediction_bboxes_page": [],
+        }
 
         # Table bbox upscaling will scale predicted bboxes too within cell matcher
         scaled_table_bbox = [
@@ -803,7 +808,12 @@ class TFPredictor:
             prediction["bboxes"] = corrected_bboxes
 
         # Match the cells
-        matching_details = {"table_cells": [], "matches": {}}
+        matching_details = {
+            "table_cells": [],
+            "matches": {},
+            "pdf_cells": [],
+            "prediction_bboxes_page": [],
+        }
 
         # Table bbox upscaling will scale predicted bboxes too within cell matcher
         scaled_table_bbox = [
@@ -819,10 +829,13 @@ class TFPredictor:
             )
         # Post-processing
         if len(prediction["bboxes"]) > 0:
-            if self.enable_post_process:
-                AggProfiler().begin("post_process", self._prof)
-                matching_details = self._post_processor.process(matching_details)
-                AggProfiler().end("post_process", self._prof)
+            if (
+                len(iocr_page["tokens"]) > 0
+            ):  # There are at least some pdf cells to match with
+                if self.enable_post_process:
+                    AggProfiler().begin("post_process", self._prof)
+                    matching_details = self._post_processor.process(matching_details)
+                    AggProfiler().end("post_process", self._prof)
 
         # Generate the expected Docling responses
         AggProfiler().begin("generate_docling_response", self._prof)

{docling_ibm_models-1.1.4.dist-info → docling_ibm_models-1.1.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-ibm-models
-Version: 1.1.4
+Version: 1.1.6
 Summary: This package contains the AI models used by the Docling PDF conversion package
 License: MIT
 Keywords: docling,convert,document,pdf,layout model,segmentation,table structure,table former
@@ -18,9 +18,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Dist: Distance (>=0.1.3,<0.2.0)
 Requires-Dist: Pillow (>=10.0.0,<11.0.0)
-Requires-Dist: apted (>=1.0.3,<2.0.0)
 Requires-Dist: jsonlines (>=3.1.0,<4.0.0)
 Requires-Dist: lxml (>=4.9.1,<5.0.0)
 Requires-Dist: mean_average_precision (>=2021.4.26.0,<2022.0.0.0)

{docling_ibm_models-1.1.4.dist-info → docling_ibm_models-1.1.6.dist-info}/RECORD

@@ -5,9 +5,9 @@ docling_ibm_models/tableformer/data_management/__init__.py,sha256=47DEQpj8HBSa-_
 docling_ibm_models/tableformer/data_management/data_transformer.py,sha256=lNKkAk0VALbixapCuDDSIQKtA0QPCGQF8AGO3D64new,18263
 docling_ibm_models/tableformer/data_management/functional.py,sha256=UrXsEm4DSc1QXdUPb0tZ7nvbg7mGVjpQhX3pGL6C5bA,20633
 docling_ibm_models/tableformer/data_management/matching_post_processor.py,sha256=-82B4xUJ9uxMDcsX2DJINTy3J0OB9rKXzHKtf-J3GHI,57205
-docling_ibm_models/tableformer/data_management/tf_cell_matcher.py,sha256=DFu428Cr84maT9WehdoZkpkJKeahwe5JlclvTC6fuVY,20870
+docling_ibm_models/tableformer/data_management/tf_cell_matcher.py,sha256=kzOjSmXkYrxc0de8wHbDJMvwKXelxYf4OccHTRqnpco,21081
 docling_ibm_models/tableformer/data_management/tf_dataset.py,sha256=6_qSsYt6qoE2JBzUNrJfCDX3Kgg7tyrv3kimGLdEQ5o,49890
-docling_ibm_models/tableformer/data_management/tf_predictor.py,sha256=LxRme9AWLZhQw7xP5Tpxwa5XFTY66m5IFS5v9VC30GA,38978
+docling_ibm_models/tableformer/data_management/tf_predictor.py,sha256=O0cDcOWJU39aKoQi1oDKAdLmilhmNBoTZzt1TWdJ8m4,39334
 docling_ibm_models/tableformer/data_management/transforms.py,sha256=_i1HXkX8LAuHbeGRrg8kF9yFNJRQZOKmWzxKt559ABQ,13268
 docling_ibm_models/tableformer/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling_ibm_models/tableformer/models/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -26,7 +26,7 @@ docling_ibm_models/tableformer/utils/app_profiler.py,sha256=13dvwo5byzfP2ejqGBFw
 docling_ibm_models/tableformer/utils/torch_utils.py,sha256=uN0rK9mSXy1ewBnBnILrWebJhhVU4N-XJZBqNiLJwlQ,8893
 docling_ibm_models/tableformer/utils/utils.py,sha256=8Bxf1rEn977lFbY9NX0r5xh9PvxIRipQZX_EZW92XfA,10980
 docling_ibm_models/tableformer/utils/variance.py,sha256=USjRwaMsCmzvc6PeWskaAJnUjbliRVd_MqNKLjMDQw8,4675
-docling_ibm_models-1.1.4.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
-docling_ibm_models-1.1.4.dist-info/METADATA,sha256=l9nER_iz8jIVbACT8dVjW9nVvXo9pOTqQ9g8ojH5-I8,7251
-docling_ibm_models-1.1.4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling_ibm_models-1.1.4.dist-info/RECORD,,
+docling_ibm_models-1.1.6.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
+docling_ibm_models-1.1.6.dist-info/METADATA,sha256=3TIbhffZPFPwIH8oaKnEviMergfpg4Wppoas7bC36yU,7172
+docling_ibm_models-1.1.6.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling_ibm_models-1.1.6.dist-info/RECORD,,