deepdoctection 0.43.5__py3-none-any.whl → 0.43.6__py3-none-any.whl

deepdoctection/__init__.py

@@ -25,7 +25,7 @@ from .utils.logger import LoggingRecord, logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = "0.43.5"
+__version__ = "0.43.6"
 
 _IMPORT_STRUCTURE = {
     "analyzer": ["config_sanity_checks", "get_dd_analyzer", "ServiceFactory"],

deepdoctection/analyzer/config.py

@@ -629,7 +629,7 @@ cfg.PT.ENFORCE_WEIGHTS.ITEM = True
 
 # Specifies the PyTorch model weights for item detection.
 # Use either .pt or .safetensors files.
-cfg.PT.ITEM.WEIGHTS = "deepdoctection/tatr_tab_struct_v2/pytorch_model.bin"
+cfg.PT.ITEM.WEIGHTS = "deepdoctection/tatr_tab_struct_v2/model.safetensors"
 
 # Specifies the TorchScript model for item detection.
 # Use .ts files for deployment without model implementation dependencies.

deepdoctection/configs/profiles.jsonl

@@ -30,3 +30,4 @@
 {"name": "Felix92/doctr-torch-parseq-multilingual-v1/pytorch_model.bin", "description": "", "size": [63286381], "tp_model": false, "config": "Felix92/doctr-torch-parseq-multilingual-v1/config.json", "preprocessor_config": null, "hf_repo_id": "Felix92/doctr-torch-parseq-multilingual-v1", "hf_model_name": "pytorch_model.bin", "hf_config_file": ["config.json"], "urls": null, "categories": {}, "categories_orig": null, "dl_library": "PT", "model_wrapper": "DoctrTextRecognizer", "architecture": "parseq", "padding": null}
 {"name": "doctr/crnn_vgg16_bn/pt/master-fde31e4a.pt", "description": "MASTER", "size": [63286381], "tp_model": false, "config": null, "preprocessor_config": null, "hf_repo_id": null, "hf_model_name": null, "hf_config_file": null, "urls": ["https://doctr-static.mindee.com/models?id=v0.7.0/master-fde31e4a.pt&src=0"], "categories": {}, "categories_orig": null, "dl_library": "PT", "model_wrapper": "DoctrTextRecognizer", "architecture": "master", "padding": null}
 {"name": "Aryn/deformable-detr-DocLayNet/model.safetensors", "description": "Deformable DEtection TRansformer (DETR), trained on DocLayNet (including 80k annotated pages in 11 classes).", "size": [115511753], "tp_model": false, "config": "Aryn/deformable-detr-DocLayNet/config.json", "preprocessor_config": "Aryn/deformable-detr-DocLayNet/preprocessor_config.json", "hf_repo_id": "Aryn/deformable-detr-DocLayNet", "hf_model_name": "model.safetensors", "hf_config_file": ["config.json", "preprocessor_config.json"], "urls": null, "categories": {"1": "default_type", "2": "caption", "11": "text", "12": "title", "3": "footnote", "4": "formula", "5": "list_item", "6": "page_footer", "7": "page_header", "8": "figure", "9": "section_header", "10": "table"}, "categories_orig": null, "dl_library": "PT", "model_wrapper": "HFDetrDerivedDetector", "architecture": null, "padding": null}
+{"name": "deepdoctection/tatr_tab_struct_v2/model.safetensors", "description": "Table Transformer (DETR) model trained on PubTables1M. It was introduced in the paper Aligning benchmark datasets for table structure recognition by Smock et al. This model is devoted to table structure recognition and assumes to receive a slightly croppedtable as input. It will predict rows, column and spanning cells. Use a padding of around 5 pixels. This artefact has been converted from deepdoctection/tatr_tab_struct_v2/pytorch_model.bin and should be used to reduce security issues", "size": [115511753], "tp_model": false, "config": "deepdoctection/tatr_tab_struct_v2/config.json", "preprocessor_config": "deepdoctection/tatr_tab_struct_v2/preprocessor_config.json", "hf_repo_id": "deepdoctection/tatr_tab_struct_v2", "hf_model_name": "model.safetensors", "hf_config_file": ["config.json", "preprocessor_config.json"], "urls": null, "categories": {"1": "table", "2": "column", "3": "row", "4": "column_header", "5": "projected_row_header", "6": "spanning"}, "categories_orig": null, "dl_library": "PT", "model_wrapper": "HFDetrDerivedDetector", "architecture": null, "padding": null}

deepdoctection/datapoint/view.py

@@ -195,7 +195,9 @@ class Word(ImageAnnotationBaseView):
         attr_names = (
             set(WordType)
             .union(super().get_attribute_names())
-            .union({Relationships.READING_ORDER, Relationships.LAYOUT_LINK, Relationships.LINK})
+            .union(
+                {Relationships.READING_ORDER, Relationships.LAYOUT_LINK, Relationships.LINK, Relationships.SUCCESSOR}
+            )
         )
         return {attr_name.value if isinstance(attr_name, ObjectTypes) else attr_name for attr_name in attr_names}
 
@@ -384,16 +386,10 @@ class Table(Layout):
         Returns:
             A list of a table cells.
         """
-        all_relation_ids = self.get_relationship(Relationships.CHILD)
-        cell_anns: list[Cell] = self.base_page.get_annotation(  # type: ignore
-            annotation_ids=all_relation_ids,
-            category_names=[
-                LayoutType.CELL,
-                CellType.HEADER,
-                CellType.BODY,
-                CellType.SPANNING,
-            ],
-        )
+        cell_anns: list[Cell] = []
+        for row_number in range(1, self.number_of_rows + 1):  # type: ignore
+            cell_anns.extend(self.row(row_number))  # type: ignore
+
         return cell_anns
 
     @property
@@ -592,6 +588,16 @@ class Table(Layout):
             )
         return table_list
 
+    @property
+    def csv_(self) -> list[list[list[Text_]]]:
+        cells = self.cells
+        table_list = [[[] for _ in range(self.number_of_columns)] for _ in range(self.number_of_rows)]  # type: ignore
+        for cell in cells:
+            table_list[cell.row_number - 1][cell.column_number - 1].append(cell.text_)  # type: ignore
+        return table_list
+
+
+
     def __str__(self) -> str:
         out = " ".join([" ".join(row + ["\n"]) for row in self.csv])
         return out
@@ -599,7 +605,13 @@ class Table(Layout):
     @property
     def text(self) -> str:
         try:
-            return str(self)
+            cells = self.cells
+            if not cells:
+                return super().text
+            text_list: list[str] = []
+            for cell in cells:
+                text_list.append(cell.text)
+            return " ".join(text_list)
         except (TypeError, AnnotationError):
             return super().text
 
@@ -616,7 +628,7 @@ class Table(Layout):
         token_class_ids: list[str] = []
         token_tag_ids: list[str] = []
         for cell in cells:
-            text.extend(cell.text_["text"])
+            text.append(cell.text_["text"])
             words.extend(cell.text_["words"])
             ann_ids.extend(cell.text_["ann_ids"])
             token_classes.extend(cell.text_["token_classes"])

deepdoctection/extern/model.py

@@ -306,7 +306,7 @@ class ModelCatalog:
 
 # Loading default profiles
 dd_profile_path = maybe_copy_config_to_cache(
-    get_package_path(), get_cache_dir_path(), "deepdoctection/configs/profiles.jsonl", False
+    get_package_path(), get_cache_dir_path(), "deepdoctection/configs/profiles.jsonl", True
 )
 ModelCatalog.load_profiles_from_file(dd_profile_path)
 # Additional profiles can be added

{deepdoctection-0.43.5.dist-info → deepdoctection-0.43.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.43.5
+Version: 0.43.6
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -321,7 +321,7 @@ For a simple setup which is enough to parse documents with the default setting,
 
 ```
 pip install transformers
-pip install python-doctr
+pip install python-doctr==0.9.0
 pip install deepdoctection
 ```
 
@@ -329,7 +329,7 @@ pip install deepdoctection
 
 ```
 pip install tensorpack
-pip install python-doctr
+pip install python-doctr==0.9.0
 pip install deepdoctection
 ```
 

{deepdoctection-0.43.5.dist-info → deepdoctection-0.43.6.dist-info}/RECORD

@@ -1,13 +1,13 @@
-deepdoctection/__init__.py,sha256=ackdlzoLcoHJAmWtxrkE2PnYgG-3q9bL2c1d3kqFgTY,12964
+deepdoctection/__init__.py,sha256=AwVtfVry6NA7FttBvL3GdHV-05TK3fcvhx87bjHwWko,12964
 deepdoctection/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 deepdoctection/analyzer/__init__.py,sha256=wg0BcFwdCeREwzZfa--Yx8HUJ9LPv5z5PmLwtkZdPH8,772
-deepdoctection/analyzer/config.py,sha256=DToaXs59w7SpEi2vkeBEyrBwyyGiXUST_N99wL9nHoI,41762
+deepdoctection/analyzer/config.py,sha256=lTfBKwzm9iVKCZoq7-FcoYUfrcgWmRknwYUzD5Jx-0U,41762
 deepdoctection/analyzer/dd.py,sha256=2BGvZpl9o9khcaOV52-DPHMrs0DsqUO8cpdqFVHHzDQ,5176
 deepdoctection/analyzer/factory.py,sha256=DI0S38KAG2sIROrSximsWJsMbem91a9zXaeWsDNvkGg,37574
 deepdoctection/configs/__init__.py,sha256=TX_P6tqDOF1LK1mi9ruAl7x0mtv1Asm8cYWCz3Pe2dk,646
 deepdoctection/configs/conf_dd_one.yaml,sha256=DHqAIKH3jRam54QO7qib2zutmpyFA8TqdV5UvIV191A,3688
 deepdoctection/configs/conf_tesseract.yaml,sha256=oF6szDyoi15FHvq7yFUNIEjfA_jNLhGxoowiRsz_zY4,35
-deepdoctection/configs/profiles.jsonl,sha256=zhMpsJWdfeSj2oq2J0BbiKhHnE7PIq47PA8-I1Th0pA,30266
+deepdoctection/configs/profiles.jsonl,sha256=8O1WTnsD0vhrdiY3RXzYoPe4mU_5C8TMafEjk0zHw9g,31438
 deepdoctection/dataflow/__init__.py,sha256=pY4lhjTes2BU-0AdIIRMnRqo9Sv6TopVE_SNfLmpgnc,828
 deepdoctection/dataflow/base.py,sha256=ZLRijyHI1J7tBfnE-q7eqUieYMMERjtK-c1oK40dBkk,6556
 deepdoctection/dataflow/common.py,sha256=DKD_pRZBCt2vO3oNZcOvdoC3jThabTNcNbTS16mpVR0,10351
@@ -21,7 +21,7 @@ deepdoctection/datapoint/annotation.py,sha256=f32BNmzUGJoNMeGst2RGC2jmjJpzzjxyBR
 deepdoctection/datapoint/box.py,sha256=QAS8sK2Ge4_ysW6zOYkLlzNwhSyw_mhYcYsxscClEno,31453
 deepdoctection/datapoint/convert.py,sha256=6ENXX3tBdY8ogb2NBPxsOsQMGnQux8ol5nrUfWS5tYE,7352
 deepdoctection/datapoint/image.py,sha256=kqwCz8DSc19hQpkl_4L1_Ek7_2KrH5KsV9e0S-R4n5w,35147
-deepdoctection/datapoint/view.py,sha256=YtoqafStrHqbfyD628-W1HOA2Gb0kUI2oaEiteBHjbA,57902
+deepdoctection/datapoint/view.py,sha256=cc-6WekGht1cU9Cgwfp7crwDlK71sUg_cCR48SmHrVY,58339
 deepdoctection/datasets/__init__.py,sha256=4ifjIwWCPYiS31GzUlVDScrkNOrb1eo5xHlRXNyg_58,994
 deepdoctection/datasets/adapter.py,sha256=VSLM_980aHi4TpgOxfxiBHiF_fUXyh348PXet6zTo-4,7779
 deepdoctection/datasets/base.py,sha256=Qfh52aVtBd2df2ZY0hjLz4D1jrExnPuu_8uYpolVNks,23181
@@ -59,7 +59,7 @@ deepdoctection/extern/fastlang.py,sha256=4D9A-_hTXUcvXG6IJJknX34LrD71v08XtNdWgvX
 deepdoctection/extern/hfdetr.py,sha256=N3eLNI5BsQS9_7YZyBeWndSgUydJij7ugZA9p4V1xaQ,14316
 deepdoctection/extern/hflayoutlm.py,sha256=3mZZ3byn00jSrLWO2vZFas9j4VrhbYQNmF1mwPG2ElQ,59642
 deepdoctection/extern/hflm.py,sha256=y-9brzmT2NYtFoNcWHABNg2ZZQXSOP9CyqtT1OoeV9U,9754
-deepdoctection/extern/model.py,sha256=-GbnuhLFq7jpBOvtpJe6IhGXxQdqwiM8epEd7IRELoU,18234
+deepdoctection/extern/model.py,sha256=kMIlx07_kdwZHLYB3QUG0DT_VSv2aZuKIIbv3fs0WqA,18233
 deepdoctection/extern/pdftext.py,sha256=ljzPQn3yYAlS6MoZqzixD-fO2GlHwu1aMiOQ6qMIzbg,7513
 deepdoctection/extern/tessocr.py,sha256=SuPmngsJg38riL4b09z6_FIzJH6H3RIwoighG2GPMYM,17457
 deepdoctection/extern/texocr.py,sha256=wVOuu6eUGao0mUbC8vrgdCsKfY1GqA1Am9560YgWyXU,5915
@@ -142,8 +142,8 @@ deepdoctection/utils/transform.py,sha256=jgeCyQWLN9q79jCGW7jysyKUKcJ1AVMk8OslF-3
 deepdoctection/utils/types.py,sha256=ti4WdtIJSg3TGK_YPkkoY9PYGMnR2tTX6Xfik8U1pNk,2986
 deepdoctection/utils/utils.py,sha256=NBUb1qbx8Jm-AvYN1Sdbk0huXhbAKxZ-ZtOcMespsMM,7064
 deepdoctection/utils/viz.py,sha256=bujRIujvX317rPz4jBrj0yd3WP8wPjDUiI5GUrw9MzQ,27339
-deepdoctection-0.43.5.dist-info/licenses/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
-deepdoctection-0.43.5.dist-info/METADATA,sha256=EeIEGN2SrcUzSny93poDmEM7Fogqqiep_XDHOs--XpM,14782
-deepdoctection-0.43.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-deepdoctection-0.43.5.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
-deepdoctection-0.43.5.dist-info/RECORD,,
+deepdoctection-0.43.6.dist-info/licenses/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
+deepdoctection-0.43.6.dist-info/METADATA,sha256=tOH9kBOEUncGe0sI1hU-h28u4gIHcqVjzbBYV3PiJ8I,14796
+deepdoctection-0.43.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+deepdoctection-0.43.6.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
+deepdoctection-0.43.6.dist-info/RECORD,,