kreuzberg 3.11.1__py3-none-any.whl → 3.11.3__py3-none-any.whl

kreuzberg/_gmft.py

@@ -444,14 +444,26 @@ def _extract_tables_in_process(
                 cropped_image.save(img_bytes, format="PNG")
                 img_bytes.seek(0)
 
-                results.append(
-                    {
-                        "cropped_image_bytes": img_bytes.getvalue(),
-                        "page_number": cropped_table.page.page_number,
-                        "text": data_frame.to_markdown(),
-                        "df_csv": data_frame.to_csv(index=False),
-                    }
-                )
+                if data_frame.empty:
+                    results.append(
+                        {
+                            "cropped_image_bytes": img_bytes.getvalue(),
+                            "page_number": cropped_table.page.page_number,
+                            "text": data_frame.to_markdown(),
+                            "df_columns": data_frame.columns.tolist(),
+                            "df_csv": None,
+                        }
+                    )
+                else:
+                    results.append(
+                        {
+                            "cropped_image_bytes": img_bytes.getvalue(),
+                            "page_number": cropped_table.page.page_number,
+                            "text": data_frame.to_markdown(),
+                            "df_columns": None,
+                            "df_csv": data_frame.to_csv(index=False),
+                        }
+                    )
 
             result_queue.put((True, results))
 
@@ -532,7 +544,10 @@ def _extract_tables_isolated(
                 img = Image.open(io.BytesIO(table_dict["cropped_image_bytes"]))
                 import pandas as pd  # noqa: PLC0415
 
-                df = pd.read_csv(StringIO(table_dict["df_csv"]))
+                if table_dict["df_csv"] is None:
+                    df = pd.DataFrame(columns=table_dict["df_columns"])
+                else:
+                    df = pd.read_csv(StringIO(table_dict["df_csv"]))
 
                 tables.append(
                     TableData(
@@ -638,7 +653,10 @@ async def _extract_tables_isolated_async(
                 img = Image.open(io.BytesIO(table_dict["cropped_image_bytes"]))
                 import pandas as pd  # noqa: PLC0415
 
-                df = pd.read_csv(StringIO(table_dict["df_csv"]))
+                if table_dict["df_csv"] is None:
+                    df = pd.DataFrame(columns=table_dict["df_columns"])
+                else:
+                    df = pd.read_csv(StringIO(table_dict["df_csv"]))
 
                 tables.append(
                     TableData(

{kreuzberg-3.11.1.dist-info → kreuzberg-3.11.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kreuzberg
-Version: 3.11.1
+Version: 3.11.3
 Summary: Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats
 Project-URL: documentation, https://kreuzberg.dev
 Project-URL: homepage, https://github.com/Goldziher/kreuzberg
@@ -32,7 +32,7 @@ Requires-Dist: anyio>=4.10.0
 Requires-Dist: chardetng-py>=0.3.5
 Requires-Dist: exceptiongroup>=1.2.2; python_version < '3.11'
 Requires-Dist: html-to-markdown[lxml]>=1.9.0
-Requires-Dist: mcp>=1.12.4
+Requires-Dist: mcp>=1.13.0
 Requires-Dist: msgspec>=0.18.0
 Requires-Dist: playa-pdf>=0.7.0
 Requires-Dist: psutil>=7.0.0
@@ -52,9 +52,9 @@ Requires-Dist: gmft>=0.4.2; extra == 'all'
 Requires-Dist: keybert>=0.9.0; extra == 'all'
 Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.17.0; extra == 'all'
 Requires-Dist: mailparse>=1.0.15; extra == 'all'
-Requires-Dist: paddleocr>=3.1.0; extra == 'all'
-Requires-Dist: paddlepaddle>=3.1.0; extra == 'all'
-Requires-Dist: pandas>=2.3.1; extra == 'all'
+Requires-Dist: paddleocr>=3.2.0; extra == 'all'
+Requires-Dist: paddlepaddle>=3.1.1; extra == 'all'
+Requires-Dist: pandas>=2.3.2; extra == 'all'
 Requires-Dist: playa-pdf[crypto]>=0.7.0; extra == 'all'
 Requires-Dist: rich>=14.1.0; extra == 'all'
 Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'all'
@@ -73,7 +73,7 @@ Provides-Extra: crypto
 Requires-Dist: playa-pdf[crypto]>=0.7.0; extra == 'crypto'
 Provides-Extra: document-classification
 Requires-Dist: deep-translator>=1.11.4; extra == 'document-classification'
-Requires-Dist: pandas>=2.3.1; extra == 'document-classification'
+Requires-Dist: pandas>=2.3.2; extra == 'document-classification'
 Provides-Extra: easyocr
 Requires-Dist: easyocr>=1.7.2; extra == 'easyocr'
 Provides-Extra: entity-extraction
@@ -84,8 +84,8 @@ Requires-Dist: gmft>=0.4.2; extra == 'gmft'
 Provides-Extra: langdetect
 Requires-Dist: fast-langdetect>=0.3.2; extra == 'langdetect'
 Provides-Extra: paddleocr
-Requires-Dist: paddleocr>=3.1.0; extra == 'paddleocr'
-Requires-Dist: paddlepaddle>=3.1.0; extra == 'paddleocr'
+Requires-Dist: paddleocr>=3.2.0; extra == 'paddleocr'
+Requires-Dist: paddlepaddle>=3.1.1; extra == 'paddleocr'
 Requires-Dist: setuptools>=80.9.0; extra == 'paddleocr'
 Description-Content-Type: text/markdown
 

{kreuzberg-3.11.1.dist-info → kreuzberg-3.11.3.dist-info}/RECORD

@@ -5,7 +5,7 @@ kreuzberg/_config.py,sha256=Au521UiR7vcQs_8_hhoWIfmDDMJIrDM3XZUB_qHfCmo,14035
 kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
 kreuzberg/_document_classification.py,sha256=qFGmwvUMhnNAvNNJO7E-huPx-Ps-_DWxdNxsozIzgaw,6870
 kreuzberg/_entity_extraction.py,sha256=Oa1T-9mptimpOHtcda-GtrVYH9PFy7DSJj3thJZUD7k,7902
-kreuzberg/_gmft.py,sha256=HdQ7Xpuixxl2Y0jY8C3KfyQEU0mN4yQdqErWCv4TnFY,25573
+kreuzberg/_gmft.py,sha256=6P4gSSmU39puaYAKmdGr9ALf0USYTwRDuvvhG1LmI24,26441
 kreuzberg/_language_detection.py,sha256=_Ng2aHgPxOHFgd507gVNiIGVmnxxbpgYwsO0bD0yTzg,3315
 kreuzberg/_mime_types.py,sha256=2warRVqfBUNIg8JBg8yP4pRqaMPvwINosHMkJwtH_Fc,8488
 kreuzberg/_playa.py,sha256=_IPrUSWwSfDQlWXOpKlauV0D9MhGrujGP5kmQ0U3L0g,12188
@@ -47,8 +47,8 @@ kreuzberg/_utils/_string.py,sha256=bCzO3UO6nXupxvtMWvHqfp1Vd9CTzEH9jmpJXQ7upAU,6
 kreuzberg/_utils/_sync.py,sha256=7LSavBmxVKQUzdjfx9fYRAI9IbJtRw8iGf_Q8B7RX9g,4923
 kreuzberg/_utils/_table.py,sha256=IomrfQBP85DZI8RmQjOVs2Siq7VP9FUTYPaZR4t3yRw,8199
 kreuzberg/_utils/_tmp.py,sha256=hVn-VVijIg2FM7EZJ899gc7wZg-TGoJZoeAcxMX-Cxg,1044
-kreuzberg-3.11.1.dist-info/METADATA,sha256=4b51JDwqoS-gjitz5PEpOlDxZ1-lO2C3BR5X2pec4g0,12136
-kreuzberg-3.11.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-kreuzberg-3.11.1.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
-kreuzberg-3.11.1.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
-kreuzberg-3.11.1.dist-info/RECORD,,
+kreuzberg-3.11.3.dist-info/METADATA,sha256=JOaIdR8UamST2qu5b0zJnk8qvyg5ly8LI7DKaFszUEs,12136
+kreuzberg-3.11.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kreuzberg-3.11.3.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
+kreuzberg-3.11.3.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
+kreuzberg-3.11.3.dist-info/RECORD,,