natural-pdf 0.1.3__py3-none-any.whl → 0.1.4__py3-none-any.whl

natural_pdf/collections/pdf_collection.py

@@ -215,8 +215,8 @@ class PDFCollection(SearchableMixin): # Inherit from the mixin
          """Returns the list of PDF objects held by the collection."""
          return self._pdfs
 
-    # --- Other Methods (e.g., apply_ocr_to_pages - could leverage service in future?) ---
-    def apply_ocr_to_pages(self, *args, **kwargs):
+    # --- Other Methods (e.g., apply_ocr - could leverage service in future?) ---
+    def apply_ocr(self, *args, **kwargs):
         PDF = self._get_pdf_class()
         # Delegate to individual PDF objects
         logger.info("Applying OCR to relevant PDFs in collection...")
@@ -225,8 +225,8 @@ class PDFCollection(SearchableMixin): # Inherit from the mixin
              # We need to figure out which pages belong to which PDF if batching here
              # For now, simpler to call on each PDF
              try:
-                 # Assume apply_ocr_to_pages exists on PDF and accepts similar args
-                 pdf.apply_ocr_to_pages(*args, **kwargs)
+                 # Assume apply_ocr exists on PDF and accepts similar args
+                 pdf.apply_ocr(*args, **kwargs)
              except Exception as e:
                  logger.error(f"Failed applying OCR to {pdf.path}: {e}", exc_info=True)
         return self

natural_pdf/core/page.py

@@ -1074,19 +1074,19 @@ class Page:
         device: Optional[str] = None,
     ) -> List[TextElement]:
         """
-        Apply OCR to THIS page and add results to page elements via PDF.apply_ocr_to_pages.
+        Apply OCR to THIS page and add results to page elements via PDF.apply_ocr.
         
         Returns:
             List of created TextElements derived from OCR results for this page.
         """
-        if not hasattr(self._parent, 'apply_ocr_to_pages'):
-             logger.error(f"Page {self.number}: Parent PDF missing 'apply_ocr_to_pages'. Cannot apply OCR.")
+        if not hasattr(self._parent, 'apply_ocr'):
+             logger.error(f"Page {self.number}: Parent PDF missing 'apply_ocr'. Cannot apply OCR.")
              return []
 
-        logger.info(f"Page {self.number}: Delegating apply_ocr to PDF.apply_ocr_to_pages.")
+        logger.info(f"Page {self.number}: Delegating apply_ocr to PDF.apply_ocr.")
         try:
             # Delegate to parent PDF, targeting only this page's index
-            self._parent.apply_ocr_to_pages(
+            self._parent.apply_ocr(
                 pages=[self.index],
                 engine=engine, options=options, languages=languages,
                 min_confidence=min_confidence, device=device

natural_pdf/core/pdf.py

@@ -198,7 +198,7 @@ class PDF:
 
         return self
 
-    def apply_ocr_to_pages(
+    def apply_ocr(
         self,
         pages: Optional[Union[Iterable[int], range, slice]] = None,
         engine: Optional[str] = None,
@@ -598,7 +598,7 @@ class PDF:
         Requires optional dependencies. Install with: pip install "natural-pdf[ocr-save]"
 
         Note: OCR must have been applied to the pages beforehand
-              (e.g., using pdf.apply_ocr_to_pages()).
+              (e.g., using pdf.apply_ocr()).
 
         Args:
             output_path: Path to save the searchable PDF.
@@ -614,7 +614,7 @@ class PDF:
         # For now, we pass through and let the exporter handle pages without OCR elements.
         # if not any(page.get_elements(source='ocr') for page in self.pages):
         #      logger.warning("No OCR elements found on pages. "
-        #                   "Ensure apply_ocr_to_pages() was called. "
+        #                   "Ensure apply_ocr() was called. "
         #                   "Output PDF might not be searchable.")
 
         # Convert pathlib.Path to string if necessary

natural_pdf/elements/collections.py

@@ -1009,8 +1009,7 @@ class PageCollection(Generic[P]):
         """
         Applies OCR to all pages within this collection using batch processing.
 
-        This delegates the work to the parent PDF object's `apply_ocr_to_pages`
-        method for efficiency. The OCR results (TextElements) are added directly
+        This delegates the work to the parent PDF object's `apply_ocr` method for efficiency. The OCR results (TextElements) are added directly
         to the respective Page objects within this collection.
 
         Args:
@@ -1028,8 +1027,8 @@ class PageCollection(Generic[P]):
         Raises:
             RuntimeError: If pages in the collection lack a parent PDF object
                           or if the parent PDF object lacks the required
-                          `apply_ocr_to_pages` method.
-            (Propagates exceptions from PDF.apply_ocr_to_pages)
+                          `apply_ocr` method.
+            (Propagates exceptions from PDF.apply_ocr)
         """
         if not self.pages:
             logger.warning("Cannot apply OCR to an empty PageCollection.")
@@ -1042,16 +1041,17 @@ class PageCollection(Generic[P]):
 
         parent_pdf = first_page._parent
 
-        if not hasattr(parent_pdf, 'apply_ocr_to_pages') or not callable(parent_pdf.apply_ocr_to_pages):
-             raise RuntimeError("Parent PDF object does not have the required 'apply_ocr_to_pages' method.")
+        # Updated check for renamed method
+        if not hasattr(parent_pdf, 'apply_ocr') or not callable(parent_pdf.apply_ocr):
+             raise RuntimeError("Parent PDF object does not have the required 'apply_ocr' method.")
 
         # Get the 0-based indices of the pages in this collection
         page_indices = [p.index for p in self.pages]
 
         logger.info(f"Applying OCR via parent PDF to page indices: {page_indices} in collection.")
 
-        # Delegate the batch call to the parent PDF object
-        parent_pdf.apply_ocr_to_pages(
+        # Delegate the batch call to the parent PDF object (using renamed method)
+        parent_pdf.apply_ocr(
             pages=page_indices,
             engine=engine,
             options=options,

{natural_pdf-0.1.3.dist-info → natural_pdf-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: natural-pdf
-Version: 0.1.3
+Version: 0.1.4
 Summary: A more intuitive interface for working with PDFs
 Author-email: Jonathan Soma <jonathan.soma@gmail.com>
 License-Expression: MIT
@@ -8,24 +8,24 @@ Project-URL: Homepage, https://github.com/jsoma/natural-pdf
 Project-URL: Repository, https://github.com/jsoma/natural-pdf
 Classifier: Programming Language :: Python :: 3
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.7
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: pdfplumber>=0.7.0
-Requires-Dist: Pillow>=8.0.0
-Requires-Dist: colour>=0.1.5
-Requires-Dist: numpy>=1.20.0
-Requires-Dist: urllib3>=1.26.0
-Requires-Dist: torch>=2.0.0
-Requires-Dist: torchvision>=0.15.0
-Requires-Dist: transformers>=4.30.0
-Requires-Dist: huggingface_hub>=0.19.0
-Requires-Dist: ocrmypdf>=16.0.0
-Requires-Dist: pikepdf>=10.0.0
+Requires-Dist: pdfplumber
+Requires-Dist: Pillow
+Requires-Dist: colour
+Requires-Dist: numpy
+Requires-Dist: urllib3
+Requires-Dist: torch
+Requires-Dist: torchvision
+Requires-Dist: transformers
+Requires-Dist: huggingface_hub
+Requires-Dist: ocrmypdf
+Requires-Dist: pikepdf
 Provides-Extra: interactive
 Requires-Dist: ipywidgets<9.0.0,>=7.0.0; extra == "interactive"
 Provides-Extra: haystack
-Requires-Dist: haystack-ai>=2.0.0b5; extra == "haystack"
+Requires-Dist: haystack-ai; extra == "haystack"
 Requires-Dist: chroma-haystack; extra == "haystack"
 Requires-Dist: sentence-transformers; extra == "haystack"
 Provides-Extra: easyocr
@@ -45,7 +45,7 @@ Requires-Dist: paddlepaddle; extra == "all"
 Requires-Dist: paddleocr; extra == "all"
 Requires-Dist: doclayout_yolo; extra == "all"
 Requires-Dist: surya-ocr; extra == "all"
-Requires-Dist: haystack-ai>=2.0.0b5; extra == "all"
+Requires-Dist: haystack-ai; extra == "all"
 Requires-Dist: chroma-haystack; extra == "all"
 Requires-Dist: sentence-transformers; extra == "all"
 Dynamic: license-file

{natural_pdf-0.1.3.dist-info → natural_pdf-0.1.4.dist-info}/RECORD

@@ -13,15 +13,15 @@ natural_pdf/analyzers/layout/paddle.py,sha256=QCasH_Z9UITX6wRGlE_HjmwkBuANz9Yyw5
 natural_pdf/analyzers/layout/surya.py,sha256=Ibwo42TioJ-BZP3-2T13KCtH3kLSWQh7C9ZYuk1kUQo,12657
 natural_pdf/analyzers/layout/tatr.py,sha256=H0Xygk9jA46-vlPleoal94cuDyz-LHTSxVb3e6gpmV8,11956
 natural_pdf/analyzers/layout/yolo.py,sha256=NSQK3TcS1qN8D2MDxCvcwTpS_kvzGy3I2LepJDUceoQ,7699
-natural_pdf/collections/pdf_collection.py,sha256=Da8saWBTguxk16pNzMxCrFwatrWk_qrcG0RVPQybro8,12159
+natural_pdf/collections/pdf_collection.py,sha256=LLtixKaKRzPRfZNdDQQ7HY3wyWbBcefPYvf_4Ke-FLw,12123
 natural_pdf/core/__init__.py,sha256=GUuFtj2Apc9biAdUOlnL8leL3BQncEzubvpiAUaU3ss,37
 natural_pdf/core/element_manager.py,sha256=H1896JSt48ASLSmG22xEXMY-xSKcpYsUlYmYMD48i6Q,17117
 natural_pdf/core/highlighting_service.py,sha256=a-40UMohOglYrw4klW1GuQ_p3jZOxnAfPOXPORThr4U,31476
-natural_pdf/core/page.py,sha256=qhumZqmwHoBlGodiCvYE0z34Iu1WSs32V4_Iz_Sfaow,69350
-natural_pdf/core/pdf.py,sha256=MLN-asJ_d5spmCjLz7SDp74t__vioszfKEFooBul7nU,41167
+natural_pdf/core/page.py,sha256=7LSqJbGHhpKQliAdcy7aRQzkr8sO9jUP68bzy7uH54U,69305
+natural_pdf/core/pdf.py,sha256=ALCO7YB_oaMtGZpS6JHJglrIIDbUd63sSso0oNAAP9k,41140
 natural_pdf/elements/__init__.py,sha256=6FGHZm2oONd8zErahMEawuB4AvJR5jOZPt4KtEwbj80,40
 natural_pdf/elements/base.py,sha256=9SQ-O2qbQe9Avbf9JI-p6vWlyThZVch-p1yqXWSrBHw,35750
-natural_pdf/elements/collections.py,sha256=RJf4cBZeLfCtfS0-SjzYFRCtbzYjWsgk3LrcTwJAYMs,62392
+natural_pdf/elements/collections.py,sha256=G6H-6VtCWq_KW-A0y9XhyHLOIWxz-1vHByfC6dq8lmU,62387
 natural_pdf/elements/line.py,sha256=QvVdhf_K6rwJkq3q67JmgdZpDhrBgWuSMF-Q25malP4,4783
 natural_pdf/elements/rect.py,sha256=dls9g-R213O78HvfAJMak3_eV14Zh654Zw7hqTTXxDQ,3949
 natural_pdf/elements/region.py,sha256=5dXHYbbdO1QNgkD6b6I34ezHt-SHKx_aH1ubzbfMHQs,74370
@@ -54,8 +54,8 @@ natural_pdf/utils/visualization.py,sha256=14BM-K4ovDqHniNbxbP_y9KaEYNlkbpELGAv9_
 natural_pdf/widgets/__init__.py,sha256=qckw3DjdVTsASPLJ8uUrGKg3MFhvzHndUpeNGlqwg6A,215
 natural_pdf/widgets/viewer.py,sha256=h_amj_uvf-vRqEsFg4P00fgKxawLAd9jjC1ohUza4BY,37479
 natural_pdf/widgets/frontend/viewer.js,sha256=w8ywfz_IOAAv2nP_qaf2VBUkF1KhjT3zorhJxM1-CfU,4371
-natural_pdf-0.1.3.dist-info/licenses/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
-natural_pdf-0.1.3.dist-info/METADATA,sha256=kBSb1SueOGQFw97pvHBxlJYcuNwxAB-lInLKows0BEs,5069
-natural_pdf-0.1.3.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-natural_pdf-0.1.3.dist-info/top_level.txt,sha256=XtfS3IiR1fTjaQG9TjGDjZsB1Ih2GXQteDbJ2dXlLvQ,12
-natural_pdf-0.1.3.dist-info/RECORD,,
+natural_pdf-0.1.4.dist-info/licenses/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
+natural_pdf-0.1.4.dist-info/METADATA,sha256=Qbj7uNu_w5OfHexqGGFEi1VQCELaidq670nHDArAtqE,4967
+natural_pdf-0.1.4.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+natural_pdf-0.1.4.dist-info/top_level.txt,sha256=XtfS3IiR1fTjaQG9TjGDjZsB1Ih2GXQteDbJ2dXlLvQ,12
+natural_pdf-0.1.4.dist-info/RECORD,,