docling 2.16.0__py3-none-any.whl → 2.18.0__py3-none-any.whl

docling/models/tesseract_ocr_model.py

@@ -8,6 +8,7 @@ from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import TesseractOcrOptions
 from docling.datamodel.settings import settings
 from docling.models.base_ocr_model import BaseOcrModel
+from docling.utils.ocr_utils import map_tesseract_script
 from docling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
@@ -20,6 +21,7 @@ class TesseractOcrModel(BaseOcrModel):
 
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
         self.reader = None
+        self.osd_reader = None
 
         if self.enabled:
             install_errmsg = (
@@ -47,8 +49,8 @@ class TesseractOcrModel(BaseOcrModel):
             except:
                 raise ImportError(install_errmsg)
 
-            _, tesserocr_languages = tesserocr.get_languages()
-            if not tesserocr_languages:
+            _, self._tesserocr_languages = tesserocr.get_languages()
+            if not self._tesserocr_languages:
                 raise ImportError(missing_langs_errmsg)
 
             # Initialize the tesseractAPI
@@ -57,7 +59,7 @@ class TesseractOcrModel(BaseOcrModel):
 
             self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
 
-            if any([l.startswith("script/") for l in tesserocr_languages]):
+            if any([l.startswith("script/") for l in self._tesserocr_languages]):
                 self.script_prefix = "script/"
             else:
                 self.script_prefix = ""
@@ -72,14 +74,14 @@ class TesseractOcrModel(BaseOcrModel):
                 tesserocr_kwargs["path"] = self.options.path
 
             if lang == "auto":
-                self.reader = tesserocr.PyTessBaseAPI(
+                self.reader = tesserocr.PyTessBaseAPI(**tesserocr_kwargs)
+                self.osd_reader = tesserocr.PyTessBaseAPI(
                     **{"lang": "osd", "psm": tesserocr.PSM.OSD_ONLY} | tesserocr_kwargs
                 )
             else:
                 self.reader = tesserocr.PyTessBaseAPI(
                     **{"lang": lang} | tesserocr_kwargs,
                 )
-
             self.reader_RIL = tesserocr.RIL
 
     def __del__(self):
@@ -96,8 +98,6 @@ class TesseractOcrModel(BaseOcrModel):
             yield from page_batch
             return
 
-        import tesserocr
-
         for page in page_batch:
             assert page._backend is not None
             if not page._backend.is_valid():
@@ -105,6 +105,7 @@ class TesseractOcrModel(BaseOcrModel):
             else:
                 with TimeRecorder(conv_res, "ocr"):
                     assert self.reader is not None
+                    assert self._tesserocr_languages is not None
 
                     ocr_rects = self.get_ocr_rects(page)
 
@@ -117,43 +118,42 @@ class TesseractOcrModel(BaseOcrModel):
                             scale=self.scale, cropbox=ocr_rect
                         )
 
-                        # Retrieve text snippets with their bounding boxes
-                        self.reader.SetImage(high_res_image)
+                        local_reader = self.reader
+                        if "auto" in self.options.lang:
+                            assert self.osd_reader is not None
 
-                        if self.options.lang == ["auto"]:
-                            osd = self.reader.DetectOrientationScript()
+                            self.osd_reader.SetImage(high_res_image)
+                            osd = self.osd_reader.DetectOrientationScript()
 
                             # No text, probably
                             if osd is None:
                                 continue
 
                             script = osd["script_name"]
-
-                            if script == "Katakana" or script == "Hiragana":
-                                script = "Japanese"
-                            elif script == "Han":
-                                script = "HanS"
-                            elif script == "Korean":
-                                script = "Hangul"
-
-                            _log.debug(
-                                f'Using model for the detected script "{script}"'
-                            )
-
-                            if script not in self.script_readers:
-                                self.script_readers[script] = tesserocr.PyTessBaseAPI(
-                                    path=self.reader.GetDatapath(),
-                                    lang=f"{self.script_prefix}{script}",
-                                    psm=tesserocr.PSM.AUTO,
-                                    init=True,
-                                    oem=tesserocr.OEM.DEFAULT,
-                                )
-
-                            local_reader = self.script_readers[script]
-                            local_reader.SetImage(high_res_image)
-                        else:
-                            local_reader = self.reader
-
+                            script = map_tesseract_script(script)
+                            lang = f"{self.script_prefix}{script}"
+
+                            # Check if the detected languge is present in the system
+                            if lang not in self._tesserocr_languages:
+                                msg = f"Tesseract detected the script '{script}' and language '{lang}'."
+                                msg += " However this language is not installed in your system and will be ignored."
+                                _log.warning(msg)
+                            else:
+                                if script not in self.script_readers:
+                                    import tesserocr
+
+                                    self.script_readers[script] = (
+                                        tesserocr.PyTessBaseAPI(
+                                            path=self.reader.GetDatapath(),
+                                            lang=lang,
+                                            psm=tesserocr.PSM.AUTO,
+                                            init=True,
+                                            oem=tesserocr.OEM.DEFAULT,
+                                        )
+                                    )
+                                local_reader = self.script_readers[script]
+
+                        local_reader.SetImage(high_res_image)
                         boxes = local_reader.GetComponentImages(
                             self.reader_RIL.TEXTLINE, True
                         )

docling/pipeline/base_pipeline.py

@@ -141,7 +141,9 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
         with TimeRecorder(conv_res, "doc_build", scope=ProfilingScope.DOCUMENT):
 
             for i in range(0, conv_res.input.page_count):
-                conv_res.pages.append(Page(page_no=i))
+                start_page, end_page = conv_res.input.limits.page_range
+                if (start_page - 1) <= i <= (end_page - 1):
+                    conv_res.pages.append(Page(page_no=i))
 
             try:
                 # Iterate batches of pages (page_batch_size) in the doc

docling/utils/glm_utils.py

@@ -307,6 +307,10 @@ def to_docling_document(doc_glm, update_name_label=False) -> DoclingDocument:
                 current_list = None
 
                 doc.add_code(text=text, prov=prov)
+            elif label == DocItemLabel.FORMULA:
+                current_list = None
+
+                doc.add_text(label=DocItemLabel.FORMULA, text="", orig=text, prov=prov)
             else:
                 current_list = None
 

docling/utils/ocr_utils.py

@@ -0,0 +1,9 @@
+def map_tesseract_script(script: str) -> str:
+    r""" """
+    if script == "Katakana" or script == "Hiragana":
+        script = "Japanese"
+    elif script == "Han":
+        script = "HanS"
+    elif script == "Korean":
+        script = "Hangul"
+    return script

{docling-2.16.0.dist-info → docling-2.18.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.16.0
+Version: 2.18.0
 Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -19,6 +19,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: ocrmac
 Provides-Extra: rapidocr
@@ -26,7 +27,7 @@ Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=1.0.0,<2.0.0)
-Requires-Dist: docling-core[chunking] (>=2.15.1,<3.0.0)
+Requires-Dist: docling-core[chunking] (>=2.17.0,<3.0.0)
 Requires-Dist: docling-ibm-models (>=3.3.0,<4.0.0)
 Requires-Dist: docling-parse (>=3.1.0,<4.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
@@ -48,7 +49,8 @@ Requires-Dist: python-pptx (>=1.0.2,<2.0.0)
 Requires-Dist: rapidocr-onnxruntime (>=1.4.0,<2.0.0) ; (python_version < "3.13") and (extra == "rapidocr")
 Requires-Dist: requests (>=2.32.2,<3.0.0)
 Requires-Dist: rtree (>=1.3.0,<2.0.0)
-Requires-Dist: scipy (>=1.6.0,<2.0.0)
+Requires-Dist: scipy (>=1.6.0,<1.14.0) ; python_version < "3.10"
+Requires-Dist: scipy (>=1.6.0,<2.0.0) ; python_version >= "3.10"
 Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
 Requires-Dist: typer (>=0.12.5,<0.13.0)
 Project-URL: Repository, https://github.com/DS4SD/docling
@@ -78,23 +80,25 @@ Description-Content-Type: text/markdown
 [![License MIT](https://img.shields.io/github/license/DS4SD/docling)](https://opensource.org/licenses/MIT)
 [![PyPI Downloads](https://static.pepy.tech/badge/docling/month)](https://pepy.tech/projects/docling)
 
-Docling parses documents and exports them to the desired format with ease and speed.
+Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.
 
 ## Features
 
-* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc & Markdown) and exports to HTML, Markdown and JSON (with embedded and referenced images)
-* 📑 Advanced PDF document understanding including page layout, reading order & table structures
-* 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
-* 🤖 Plug-and-play [integrations](https://ds4sd.github.io/docling/integrations/) incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
-* 🔍 OCR support for scanned PDFs
+* 🗂️ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, XLSX, HTML, images, and more
+* 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more
+* 🧬 Unified, expressive [DoclingDocument][docling_document] representation format
+* ↪️ Various [export formats][supported_formats] and options, including Markdown, HTML, and lossless JSON
+* 🔒 Local execution capabilities for sensitive data and air-gapped environments
+* 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
+* 🔍 Extensive OCR support for scanned PDFs and images
 * 💻 Simple and convenient CLI
 
-Explore the [documentation](https://ds4sd.github.io/docling/) to discover plenty examples and unlock the full power of Docling!
-
 ### Coming soon
 
-* ♾️ Equation & code extraction
 * 📝 Metadata extraction, including title, authors, references & language
+* 📝 Inclusion of Visual Language Models ([SmolDocling](https://huggingface.co/blog/smolervlm#smoldocling))
+* 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)
+* 📝 Complex chemistry understanding (Molecular structures)
 
 ## Installation
 
@@ -177,3 +181,7 @@ For individual model usage, please refer to the model licenses found in the orig
 
 Docling has been brought to you by IBM.
 
+[supported_formats]: https://ds4sd.github.io/docling/supported_formats/
+[docling_document]: https://ds4sd.github.io/docling/concepts/docling_document/
+[integrations]: https://ds4sd.github.io/docling/integrations/
+

{docling-2.16.0.dist-info → docling-2.18.0.dist-info}/RECORD

@@ -4,27 +4,27 @@ docling/backend/abstract_backend.py,sha256=1lNxzwDTn303aXduPDVmTyXn-5ZIoWMLYqNxA
 docling/backend/asciidoc_backend.py,sha256=zyHxlG_BvlLwvpdNca3P6aopxOJZw8wbDFkJQQknNXk,14050
 docling/backend/docling_parse_backend.py,sha256=hEEJibI1oJS0LAnFoIs6gMshS3bCqGtVxHnDNvBGZuA,7649
 docling/backend/docling_parse_v2_backend.py,sha256=IpwrBrtLGwNRl5AYO-o3NjEfNRsAkuMhzvDt2HXb9Ko,8655
-docling/backend/html_backend.py,sha256=vUEfx0h24gEaHO2taQyWNs8zCkDox7kopEeMbWBXss0,15560
+docling/backend/html_backend.py,sha256=YTPLZiEEEuGaP6G62skK3wXJ0KftuqBCl8erNXeJyoE,15893
 docling/backend/json/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/json/docling_json_backend.py,sha256=LlFMVoZrrCfVwbDuRbNN4Xg96Lujh4xxrTBt9jGhY9I,1984
-docling/backend/md_backend.py,sha256=ajEooDWNnWPHnPQMgUDh-K44Ch1X-sTBHqa1xBp7yJs,14645
+docling/backend/md_backend.py,sha256=d7XAFHzFO9qhrCJA3raWEmZ8WXSYyy3KOE57oMeqKGc,16502
 docling/backend/msexcel_backend.py,sha256=lyJc4ShJGAN2ZfNTTuhdYTF-44cZsGyn_8Djstp3IEU,12700
-docling/backend/mspowerpoint_backend.py,sha256=kOGawhcn0BFq4M_C6kW0mY8vMIB24_6R6q6GaszbSt0,15957
-docling/backend/msword_backend.py,sha256=WcQmRYmpH8o2snGoWGxNRkCtUI3mf2JL3-9CxAfDAJg,19232
+docling/backend/mspowerpoint_backend.py,sha256=esAyaaQe17BQFweGAGJHvImKETefY0BpvfpUSECC49w,16424
+docling/backend/msword_backend.py,sha256=0iR1l3eLplPv3CPT7iGwQb50LIVf3C32KZFzwAkARrc,20573
 docling/backend/pdf_backend.py,sha256=17Pr8dWsD1C4FYUprrwMM9trDGW-JYLjrcScx1Ul4io,2048
 docling/backend/pypdfium2_backend.py,sha256=QSPfp903ZtSpoNqPmcIek0HmvETrJ1kkwrdxnF5pjS0,9014
 docling/backend/xml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/xml/pubmed_backend.py,sha256=LMnpowjnxa5SydfNC00Ll840BYraL8dCJu-FfC9iSKk,20447
-docling/backend/xml/uspto_backend.py,sha256=2YsnB-WRARIAaHPL6gxHePP24GQGi-Up2_K8ZapD3k4,70974
+docling/backend/xml/uspto_backend.py,sha256=a5GxWLj2SUR5Of8TWJinhef1gKyaQSjHPVXvGiN8yG8,70324
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=NR7NEt8Sf3FE9D7sHpEmABM9mFMTMO5w0VPwYIIvVsk,15481
+docling/cli/main.py,sha256=K5C2yQIoM40_W3YU8a7SmneY-hWbNp_JOFPLk0NPcDI,16098
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/base_models.py,sha256=vewP1X99qfAwiUsiC2m8CBDGiQPsGyp_WkKJHYPoYn4,7026
-docling/datamodel/document.py,sha256=R748mLCFai4MeiE8ougQrQVJF_16t3f4CUrrEes5AV0,13202
-docling/datamodel/pipeline_options.py,sha256=GA5LwywfOkcBDvG2LhDHikqDQYlFlUPJa93tPSx-vFw,7820
-docling/datamodel/settings.py,sha256=Sw0rN_f8rdLV1eNvVeKiyET2Oe6oz9jtW3lJzniW9Do,1302
-docling/document_converter.py,sha256=qtYPEkWuMUUGmFko2in38iSHdYrjAFf_GHNoXRRvEVs,12631
+docling/datamodel/document.py,sha256=HkmvQKW3QSx3tAqPTnXiJbD_y1EVwR-WE3n6Gq8g1NY,13428
+docling/datamodel/pipeline_options.py,sha256=f9-VQFgOdahyclGQgH_T8ZYBopkWsF_fbWbxo39ux3g,7888
+docling/datamodel/settings.py,sha256=uN9jeXMwx--tJb-DFU7nr77g0Iou13YAVDzsymTvbHg,1759
+docling/document_converter.py,sha256=qaldb7Thqk59RdE-RTGtj1M7l5UzaBdnxIvGoQ7lTeo,12876
 docling/exceptions.py,sha256=-FoP46rFJgz_jn5uDv2V052udEEg8gckk6uhoItchXc,85
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/base_model.py,sha256=H5X-exVaAN-XMTzxpgUc-rwH-D8Uk7-VuZtq2soNGXI,2567
@@ -37,25 +37,26 @@ docling/models/layout_model.py,sha256=3Fw7OM6g0j7NgItKsQOgFOCd1q6lp1DacN_db7f6QC
 docling/models/ocr_mac_model.py,sha256=bLP14UUmZcSzjDe-HLj-mtksTuBmsCTg2C1wCxUpan0,4502
 docling/models/page_assemble_model.py,sha256=c5KLKwkUIdW0JcDHizWsqrpb5x_3DK28x82Q8o-3VJM,5968
 docling/models/page_preprocessing_model.py,sha256=1gVrZjObKxAvXkkKvXnIFApPOggzgiTFPtt1CGbMbSs,2763
-docling/models/rapid_ocr_model.py,sha256=LOIvczJs3_db2o8mtrKk-pIXgC-xqWqRLu2cjA3wvy4,4980
-docling/models/table_structure_model.py,sha256=fUpCHthO4Uk3BhA99a85BHBm51fmdE9kfqhAk3WjuBw,9392
-docling/models/tesseract_ocr_cli_model.py,sha256=FP9cnSkSyj6-EETHtabV720Fr3x9K_oBP2UuJi4VUwE,6621
-docling/models/tesseract_ocr_model.py,sha256=N27xjo8aPb5x276wKHkf_6VFwJObfosdHLo5_hCuf94,8055
+docling/models/rapid_ocr_model.py,sha256=2HXmurNRPP6qyqn7U5h9NQIs8zi0TMHf56CpcKQk0fU,5038
+docling/models/table_structure_model.py,sha256=qZgoBrBh7H-RJGCTtaRGcj79g2WzZiUBTPnHqJZ-bLA,9557
+docling/models/tesseract_ocr_cli_model.py,sha256=b2Is5x2gZLS6mQWnKe0y7p6UU6hRTHDfoH4D2RQ5mx0,9310
+docling/models/tesseract_ocr_model.py,sha256=BN85u-4a-xzUY7Iw21Ib8L8kx4mgbDGiUtxBelLiJm8,8513
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/pipeline/base_pipeline.py,sha256=J0ZjtincsJr-BbRgqoQozxIhDWxWFlWaS9CTPwypJFk,8621
+docling/pipeline/base_pipeline.py,sha256=lK8PQiydWJ9M16kIVL7U1A2iryTRFrN5WSucVo2ohFQ,8757
 docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoazEDJ_wE,2254
 docling/pipeline/standard_pdf_pipeline.py,sha256=Qefg1JSiFwipypi8TZPJ50WgXTLjwkC0wvYAl02RM2o,10480
 docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/utils/accelerator_utils.py,sha256=ZjULCn-qhxqx3frF-rJmAlWdzqgUMxH5utLHbSPev80,1367
 docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
-docling/utils/glm_utils.py,sha256=Nfxdx0W-sl1owYncTeJmZdiPcn-jpTqK8f8TeQlDOMY,11683
+docling/utils/glm_utils.py,sha256=uyCoFTX9FbS1Ke0aSlkdzGLUt08dZfkgriWadkyLiiA,11856
 docling/utils/layout_postprocessor.py,sha256=urRzeF9PrKiMBvA6DdHHwyLxG06CMhelgJeV5B1l6l0,24258
+docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,263
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
 docling/utils/visualization.py,sha256=4pn-80fVuE04ken7hUg5Ar47ndRSL9MWBgdHM-1g1zU,2735
-docling-2.16.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.16.0.dist-info/METADATA,sha256=wJgRO2R9Szl69jFE8gj-VGIBpkwwMWPfgytz9nDsT_E,7780
-docling-2.16.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.16.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.16.0.dist-info/RECORD,,
+docling-2.18.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.18.0.dist-info/METADATA,sha256=rBP1Z7m0HMpC-HjR360i2JNuIA9lqknRPjUab1mtVic,8403
+docling-2.18.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+docling-2.18.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.18.0.dist-info/RECORD,,

{docling-2.16.0.dist-info → docling-2.18.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.0
+Generator: poetry-core 1.9.1
 Root-Is-Purelib: true
 Tag: py3-none-any