natural-pdf 0.1.7__py3-none-any.whl → 0.1.9__py3-none-any.whl

natural_pdf/utils/debug.py

@@ -3,13 +3,13 @@ OCR debug utilities for natural-pdf.
 """
 
 import base64
+import importlib.resources
+import importlib.util
 import io
 import json
 import os
-import importlib.util
-import importlib.resources
 import webbrowser
-from typing import Dict, List, Any, Optional, Union, Tuple
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 from PIL import Image
 

natural_pdf/utils/identifiers.py

@@ -2,8 +2,8 @@
 Utilities for generating consistent identifiers.
 """
 
-import hashlib
 import base64
+import hashlib
 import os
 
 

natural_pdf/utils/locks.py

@@ -0,0 +1,8 @@
+"""
+Shared locks for thread synchronization across the natural-pdf library.
+"""
+
+import threading
+
+# Global lock for PDF rendering operations to prevent PDFium concurrency issues
+pdf_render_lock = threading.RLock()

natural_pdf/utils/packaging.py

@@ -2,23 +2,25 @@
 Utilities for packaging data for external processes, like correction tasks.
 """
 
-import os
 import base64
 import io
 import json
-import zipfile
-import tempfile
 import logging
+import os
 import shutil
-from typing import Any, List, Union, Iterable, TYPE_CHECKING, Dict
+import tempfile
+import zipfile
+from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Union
+
 from tqdm import tqdm
+
 from natural_pdf.elements.text import TextElement
 
 # Import the specific PDF/Page types if possible, otherwise use Any
 if TYPE_CHECKING:
-    from natural_pdf.core.pdf import PDF
-    from natural_pdf.core.page import Page
     from natural_pdf.collections.pdf_collection import PDFCollection
+    from natural_pdf.core.page import Page
+    from natural_pdf.core.pdf import PDF
 else:
     PDF = Any
     Page = Any

natural_pdf/utils/text_extraction.py

@@ -2,7 +2,12 @@
 import logging
 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
 
-from pdfplumber.utils.geometry import get_bbox_overlap, merge_bboxes, objects_to_bbox
+from pdfplumber.utils.geometry import (
+    cluster_objects,
+    get_bbox_overlap,
+    merge_bboxes,
+    objects_to_bbox,
+)
 from pdfplumber.utils.text import TEXTMAP_KWARGS, WORD_EXTRACTOR_KWARGS, chars_to_textmap
 
 if TYPE_CHECKING:
@@ -11,6 +16,60 @@ if TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 
 
+def _get_layout_kwargs(
+    layout_context_bbox: Optional[Tuple[float, float, float, float]] = None,
+    user_kwargs: Optional[Dict[str, Any]] = None,
+) -> Dict[str, Any]:
+    """
+    Prepares the keyword arguments for pdfplumber's chars_to_textmap based
+    on defaults, context bbox, and allowed user overrides.
+    """
+    # 1. Start with an empty dict for layout kwargs
+    layout_kwargs = {}
+
+    # Build allowed keys set without trying to copy the constants
+    allowed_keys = set(TEXTMAP_KWARGS) | set(WORD_EXTRACTOR_KWARGS)
+
+    # Add common, well-known default values
+    layout_kwargs.update(
+        {
+            "x_tolerance": 5,
+            "y_tolerance": 5,
+            "x_density": 7.25,
+            "y_density": 13,
+            "mode": "box",
+            "min_words_vertical": 1,
+            "min_words_horizontal": 1,
+        }
+    )
+
+    # 2. Apply context if provided
+    if layout_context_bbox:
+        ctx_x0, ctx_top, ctx_x1, ctx_bottom = layout_context_bbox
+        layout_kwargs["layout_width"] = ctx_x1 - ctx_x0
+        layout_kwargs["layout_height"] = ctx_bottom - ctx_top
+        layout_kwargs["x_shift"] = ctx_x0
+        layout_kwargs["y_shift"] = ctx_top
+        # Add layout_bbox itself
+        layout_kwargs["layout_bbox"] = layout_context_bbox
+
+    # 3. Apply user overrides (only for allowed keys)
+    if user_kwargs:
+        for key, value in user_kwargs.items():
+            if key in allowed_keys:
+                layout_kwargs[key] = value
+            elif key == "layout":  # Always allow layout flag
+                layout_kwargs[key] = value
+            else:
+                logger.warning(f"Ignoring unsupported layout keyword argument: '{key}'")
+
+    # 4. Ensure layout flag is present, defaulting to True
+    if "layout" not in layout_kwargs:
+        layout_kwargs["layout"] = True
+
+    return layout_kwargs
+
+
 def filter_chars_spatially(
     char_dicts: List[Dict[str, Any]],
     exclusion_regions: List["Region"],

natural_pdf/utils/tqdm_utils.py

@@ -0,0 +1,51 @@
+import os
+import sys
+
+# Default to standard tqdm
+try:
+    from tqdm.std import tqdm as selected_tqdm
+except ImportError:
+    # Basic fallback if even std is missing (though unlikely)
+    def selected_tqdm(*args, **kwargs):
+        iterable = args[0] if args else None
+        if iterable:
+            return iterable
+        return None  # Simple passthrough if no iterable
+
+
+# Try to detect notebook environment
+try:
+    # Check 1: Are we running in an IPython kernel?
+    from IPython import get_ipython
+
+    ipython = get_ipython()
+    if ipython and "IPKernelApp" in ipython.config:
+        # Check 2: Is it likely a notebook UI (Jupyter Notebook/Lab, VSCode, etc.)?
+        # This checks for common indicators. Might not be foolproof.
+        if "VSCODE_PID" in os.environ or (
+            "ipykernel" in sys.modules and "spyder" not in sys.modules
+        ):
+            # Check 3: Can we import notebook version?
+            try:
+                from tqdm.notebook import tqdm as notebook_tqdm
+
+                selected_tqdm = notebook_tqdm  # Use notebook version
+            except ImportError:
+                pass  # Stick with std if notebook version missing
+except ImportError:
+    pass  # Stick with std if IPython not available
+
+
+def get_tqdm():
+    """Returns the tqdm class best suited for the detected environment."""
+    return selected_tqdm
+
+
+# Example usage (for testing):
+if __name__ == "__main__":
+    import time
+
+    tqdm_instance = get_tqdm()
+    print(f"Using tqdm class: {tqdm_instance}")
+    for i in tqdm_instance(range(10), desc="Testing tqdm"):
+        time.sleep(0.1)

natural_pdf/utils/visualization.py

@@ -8,6 +8,7 @@ import math
 import random
 from typing import Any, Dict, List, Optional, Set, Tuple, Union
 
+import pypdfium2
 from PIL import Image, ImageDraw, ImageFont
 
 # Define a base list of visually distinct colors for highlighting
@@ -193,6 +194,7 @@ def merge_images_with_legend(
         return image  # Return original image if legend is None or empty
 
     bg_color = (255, 255, 255, 255)  # Always use white for the merged background
+    bg_color = (255, 255, 255, 255)  # Always use white for the merged background
 
     if position == "right":
         # Create a new image with extra width for the legend
@@ -230,3 +232,19 @@ def merge_images_with_legend(
         merged = image
 
     return merged
+
+
+def render_plain_page(page, resolution):
+    doc = pypdfium2.PdfDocument(page._page.pdf.stream)
+
+    pdf_page = doc[page.index]
+
+    bitmap = pdf_page.render(
+        scale=resolution / 72,
+    )
+    image = bitmap.to_pil().convert("RGB")
+
+    pdf_page.close()
+    doc.close()
+
+    return image

natural_pdf/widgets/viewer.py

@@ -3,6 +3,8 @@
 import logging
 import os
 
+from natural_pdf.utils.visualization import render_plain_page
+
 logger = logging.getLogger(__name__)
 
 # Initialize flag and module/class variables to None
@@ -615,31 +617,7 @@ try:
 
             from PIL import Image  # Ensure Image is imported
 
-            # Render page to image using the correct method and parameter
-            scale = 1.0  # Define scale factor used for rendering
-            try:
-                img_object = page.to_image(resolution=int(72 * scale))  # Call to_image
-                # Check if .original attribute exists, otherwise assume img_object is the PIL Image
-                if hasattr(img_object, "original") and isinstance(img_object.original, Image.Image):
-                    img = img_object.original
-                elif isinstance(img_object, Image.Image):
-                    img = img_object
-                else:
-                    # If it's neither, maybe it's the raw bytes? Try opening it.
-                    try:
-                        img = Image.open(BytesIO(img_object)).convert("RGB")
-                    except Exception:
-                        raise TypeError(
-                            f"page.to_image() returned unexpected type: {type(img_object)}"
-                        )
-                logger.debug(f"Successfully rendered page {page.index} using to_image()")
-            except Exception as render_err:
-                logger.error(
-                    f"Error rendering page {page.index} image for widget: {render_err}",
-                    exc_info=True,
-                )
-                # Return None or raise the error? Let's raise for now to make it clear.
-                raise ValueError(f"Failed to render page image: {render_err}") from render_err
+            img = render_plain_page(page, resolution=72)
 
             buffered = BytesIO()
             img.save(buffered, format="PNG")
@@ -687,6 +665,7 @@ try:
                 original_y1 = element.bottom
                 width = element.width
                 height = element.height
+                scale = 1.0
 
                 # Base element dict with required info
                 elem_dict = {

{natural_pdf-0.1.7.dist-info → natural_pdf-0.1.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: natural-pdf
-Version: 0.1.7
+Version: 0.1.9
 Summary: A more intuitive interface for working with PDFs
 Author-email: Jonathan Soma <jonathan.soma@gmail.com>
 License-Expression: MIT
@@ -17,11 +17,13 @@ Requires-Dist: colour
 Requires-Dist: numpy
 Requires-Dist: urllib3
 Requires-Dist: tqdm
+Requires-Dist: pydantic
 Provides-Extra: interactive
 Requires-Dist: ipywidgets<9.0.0,>=7.0.0; extra == "interactive"
 Provides-Extra: haystack
 Requires-Dist: haystack-ai; extra == "haystack"
-Requires-Dist: chroma-haystack; extra == "haystack"
+Requires-Dist: lancedb-haystack; extra == "haystack"
+Requires-Dist: lancedb; extra == "haystack"
 Requires-Dist: sentence-transformers; extra == "haystack"
 Requires-Dist: natural-pdf[core-ml]; extra == "haystack"
 Provides-Extra: easyocr
@@ -36,6 +38,9 @@ Requires-Dist: natural-pdf[core-ml]; extra == "layout-yolo"
 Provides-Extra: surya
 Requires-Dist: surya-ocr; extra == "surya"
 Requires-Dist: natural-pdf[core-ml]; extra == "surya"
+Provides-Extra: doctr
+Requires-Dist: python-doctr[torch]; extra == "doctr"
+Requires-Dist: natural-pdf[core-ml]; extra == "doctr"
 Provides-Extra: qa
 Requires-Dist: natural-pdf[core-ml]; extra == "qa"
 Provides-Extra: docling
@@ -43,7 +48,10 @@ Requires-Dist: docling; extra == "docling"
 Requires-Dist: natural-pdf[core-ml]; extra == "docling"
 Provides-Extra: llm
 Requires-Dist: openai>=1.0; extra == "llm"
-Requires-Dist: pydantic; extra == "llm"
+Provides-Extra: classification
+Requires-Dist: sentence-transformers; extra == "classification"
+Requires-Dist: timm; extra == "classification"
+Requires-Dist: natural-pdf[core-ml]; extra == "classification"
 Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Provides-Extra: dev
@@ -59,6 +67,9 @@ Requires-Dist: pipdeptree; extra == "dev"
 Requires-Dist: nbformat; extra == "dev"
 Requires-Dist: jupytext; extra == "dev"
 Requires-Dist: nbclient; extra == "dev"
+Provides-Extra: deskew
+Requires-Dist: deskew>=1.5; extra == "deskew"
+Requires-Dist: img2pdf; extra == "deskew"
 Provides-Extra: all
 Requires-Dist: natural-pdf[interactive]; extra == "all"
 Requires-Dist: natural-pdf[haystack]; extra == "all"
@@ -66,10 +77,13 @@ Requires-Dist: natural-pdf[easyocr]; extra == "all"
 Requires-Dist: natural-pdf[paddle]; extra == "all"
 Requires-Dist: natural-pdf[layout_yolo]; extra == "all"
 Requires-Dist: natural-pdf[surya]; extra == "all"
+Requires-Dist: natural-pdf[doctr]; extra == "all"
 Requires-Dist: natural-pdf[qa]; extra == "all"
 Requires-Dist: natural-pdf[ocr-export]; extra == "all"
 Requires-Dist: natural-pdf[docling]; extra == "all"
 Requires-Dist: natural-pdf[llm]; extra == "all"
+Requires-Dist: natural-pdf[classification]; extra == "all"
+Requires-Dist: natural-pdf[deskew]; extra == "all"
 Requires-Dist: natural-pdf[test]; extra == "all"
 Provides-Extra: core-ml
 Requires-Dist: torch; extra == "core-ml"

natural_pdf-0.1.9.dist-info/RECORD

@@ -0,0 +1,80 @@
+natural_pdf/__init__.py,sha256=LBrQcFOGooaUsTSAk6zrPCQqu0IM-ClvJLasexEk64k,2728
+natural_pdf/analyzers/__init__.py,sha256=dIXjsMqoxKmd9OOnSBzn12wvdIz7D7YNQRAnXslpJSM,142
+natural_pdf/analyzers/text_options.py,sha256=nE2E1pp4psDPpxmtarvNtEQsgozPkyFRjv0TVP2HTyU,2865
+natural_pdf/analyzers/text_structure.py,sha256=Uhxc7aYB1jddkiwRTEPOg_Te2HfOua4z_OtgP1m3org,12794
+natural_pdf/analyzers/utils.py,sha256=PYbzJzSAHZ7JsMes84WIrSbA0zkjJGs0CLvIeINsf_k,2100
+natural_pdf/analyzers/layout/__init__.py,sha256=oq1uJ5UkGGMbBKGirV1aRKK3hxAUyjTLywYkPCQH1f0,33
+natural_pdf/analyzers/layout/base.py,sha256=bYawhmc_0xqKG-xbxUSiazIU1om-aBox5Jh8qDqv-eM,6451
+natural_pdf/analyzers/layout/docling.py,sha256=4BJYyNVR6VegZGxyisvNIBBRvVk6YKPyDVs7ZdVfzEU,12676
+natural_pdf/analyzers/layout/gemini.py,sha256=iuq-zZYkTS7fdAjD3ULRhqYTP9Ky2NgVHaXSLppDidw,11751
+natural_pdf/analyzers/layout/layout_analyzer.py,sha256=n327Zjuf7aSzKQKChPHeiCVHinzeDGaWNyKiwQ-DkJk,15571
+natural_pdf/analyzers/layout/layout_manager.py,sha256=RiVq6gUA8t9OLj-HojdzQkJtabM32iBWEBoLtS7_TjY,8115
+natural_pdf/analyzers/layout/layout_options.py,sha256=Jsm4MfD_vedXvS7NCpVmuIRsIuyNyKOjvdgoRYOKZpI,4133
+natural_pdf/analyzers/layout/paddle.py,sha256=gTI9ZqNd5-t4H5IByGfL32WgcE6JrdchW6jRiGI6ulM,13375
+natural_pdf/analyzers/layout/pdfplumber_table_finder.py,sha256=Tk0Q7wv7nGYPo69lh6RoezjdepTnMl90SaNIrP29Pwc,5902
+natural_pdf/analyzers/layout/surya.py,sha256=4RdnhRxSS3i3Ns5mFhOA9-P0xd7Ms19uZuKvUGQfEBI,9789
+natural_pdf/analyzers/layout/tatr.py,sha256=cVr0ZyhY2mNLAKZ4DGMm-b7XNJpILKh8x8ZpyDeUhLk,15032
+natural_pdf/analyzers/layout/yolo.py,sha256=ANo2U4EZgeN2eYKM1bZIuysiuJLgwl4JeQchrRxOKwA,8388
+natural_pdf/classification/manager.py,sha256=CvZd3-lN3fEhcaLXr8gYfrdBGoBgzkIeE14EqjrOAzU,17730
+natural_pdf/classification/mixin.py,sha256=llari9AIMNGy9sTaR7y1g5vtVNUwuCutbKnjbJRMYx4,6903
+natural_pdf/classification/results.py,sha256=Ia26BQxObL5sURpFmg66bfjFPCxjcO_jeP2G-S9wRgo,2289
+natural_pdf/collections/mixins.py,sha256=ufetdzHmd2_WLGBPW4eBQrzZTFpjXyVsVwBquIE47zw,4476
+natural_pdf/collections/pdf_collection.py,sha256=JnsJugE-vxYsW1ZJWmMlVv_jbyG37X-9rZK1RQyKWAY,30020
+natural_pdf/core/__init__.py,sha256=QC8H4M3KbXwMFiQORZ0pdPlzx1Ix6oKKQSS7Ib2KEaA,38
+natural_pdf/core/element_manager.py,sha256=knRN6qXxV-6KZCj2GUOyiqRi83DjJzL77TmKGeiD08Y,25144
+natural_pdf/core/highlighting_service.py,sha256=wINdRxq63_CYYA81EwuCRqhNKimn0dNKyoKWuzkirc0,31959
+natural_pdf/core/page.py,sha256=icJLu6jRbkD3iOE8r60XPkQZ8FN3ZcKo5TT5MVGkGl0,105122
+natural_pdf/core/pdf.py,sha256=Vw-L5149wO6RSfvb9sAfPDLqd9M1TdYoPHNEePh65y8,61201
+natural_pdf/elements/__init__.py,sha256=S8XeiNWJ1WcgnyYKdYV1yxQlAxCCO3FfITT8MQwNbyk,41
+natural_pdf/elements/base.py,sha256=7vVCPQyEHifh4LyBuv0kLTqr_gNbbEMc4SoiJmLfEUQ,37585
+natural_pdf/elements/collections.py,sha256=YRaJxNbJrBjgwzwuSoOtEotOKh6RaTi7NRCqKiGl514,92955
+natural_pdf/elements/line.py,sha256=7cow3xMUKhAj7zoQz7OaB1eIH2_a8B__LB7iGJ4Mb0o,4612
+natural_pdf/elements/rect.py,sha256=kiVa3e377ZnqIOXc89d9ZSY4EcmDxtccdtUw-HOQzpw,3796
+natural_pdf/elements/region.py,sha256=LfyB_9DCw5Tzn_G9xsjFz2FfKBOHRqGIND4DQWoA7KM,97324
+natural_pdf/elements/text.py,sha256=13HvVZGinj2Vm_fFCAnqi7hohtoKvnpCp3VCfkpeAbc,11146
+natural_pdf/export/mixin.py,sha256=L1q3MIEFWuvie4j4_EmW7GT3NerbZ1as0XMUoqTS7gM,5083
+natural_pdf/exporters/__init__.py,sha256=7MnvRLLQdwtg-ULu-8uK8C84GsKiJamyhRw_GgWhw7k,151
+natural_pdf/exporters/base.py,sha256=XhR1xlkHOh7suOuX7mWbsj1h2o1pZNet-OAS5YCJyeI,2115
+natural_pdf/exporters/paddleocr.py,sha256=BYpdtJI7S8rBkI2dkRESx2epVAZOTfzqU-rjJnUQ5jQ,16249
+natural_pdf/exporters/searchable_pdf.py,sha256=qsaPsnbOOaZHA_aplfZbwQnBoK9KghWm-wzbyRRomeY,16859
+natural_pdf/extraction/manager.py,sha256=mUBbfgLG5Pl31wmajXwyipdEJb_dZ5I-y8GnWw7IzGo,4969
+natural_pdf/extraction/mixin.py,sha256=eKbr70VibpbtfjvCE80lTFuYHzq_BoVtOHjznL_GMRA,11719
+natural_pdf/extraction/result.py,sha256=c1vLguCR6l95cvg-BJJmZvL_MPg2McJaczge55bKZMg,934
+natural_pdf/ocr/__init__.py,sha256=VY8hhvDPf7Gh2lB-d2QRmghLLyTy6ydxlgo1cS4dOSk,2482
+natural_pdf/ocr/engine.py,sha256=ZBC1tZNM5EDbGDJJmZI9mNHr4nCMLEZvUFhiJq8GdF4,8741
+natural_pdf/ocr/engine_doctr.py,sha256=519WpvSHgwP6Hv24tci_YHFX7XPlaxOnlREN_YG-Yys,16331
+natural_pdf/ocr/engine_easyocr.py,sha256=9TbxJjmhWFrzM8mcNnZjoRtIDr6gwpuwKm4-Zfub2-8,9281
+natural_pdf/ocr/engine_paddle.py,sha256=2nIrvLBBAiZG1BxVo3eFVJulA6YGoOTXw_RN98p_BUk,6184
+natural_pdf/ocr/engine_surya.py,sha256=iySjG-Dahgh0cLICfbMtOcwUpRFcZjo-5Ed5Zwz-o5Y,4805
+natural_pdf/ocr/ocr_factory.py,sha256=gBFXdFs7E4aCynHz06sQsAhaO3s8yhgoFgN5nyxtg9c,5221
+natural_pdf/ocr/ocr_manager.py,sha256=f0q68ynGYVPkF4D3WnufxmHWD5R1jW5Z_1czTEi9JVU,13931
+natural_pdf/ocr/ocr_options.py,sha256=ZvtnFn1kPkFEoWveQ13uy6B-ofquP0gHEi4tBHrjqCE,6438
+natural_pdf/ocr/utils.py,sha256=OxuHwDbHWj6setvnC0QYwMHrAjxGkhmLzWHpMqqGupA,4397
+natural_pdf/qa/__init__.py,sha256=Pjo62JTnUNEjGNsC437mvsS5KQ5m7X_BibGvavR9AW0,108
+natural_pdf/qa/document_qa.py,sha256=Jw4yyq3Vifn57D0ANmOfUlZeG8CJjBkItZBV-8ZAmos,15111
+natural_pdf/search/__init__.py,sha256=gdGlW3kTCw87iXMwcIesbLkUsnv5UKJmF-_1ZMR0pfQ,3339
+natural_pdf/search/haystack_search_service.py,sha256=UHr2UWNBetG3MZ1n_1LnV9oUe5fC-rY9p-V0j00JjQM,30339
+natural_pdf/search/haystack_utils.py,sha256=6Hv5DeLSF4AVDrB_aFJZGB3XpSCLQ45dXLKEd4yG2tU,18978
+natural_pdf/search/search_options.py,sha256=sq_e8_jSROicD94b_xtDtLnjEr_Zsy4icjzPkK0a8QA,3566
+natural_pdf/search/search_service_protocol.py,sha256=Dl-Q-CrutkhZwI69scbW9EWPeYM63qxB60_EA7YqIYo,6699
+natural_pdf/search/searchable_mixin.py,sha256=M2a6FaFVM0vcfh7FgjDH6BLhS-7ggeVpcfft4OOBDxY,26390
+natural_pdf/selectors/__init__.py,sha256=oZGeqSv53EqmIZOhcnawuaGGlRg1h79vArXuZCWKm4A,123
+natural_pdf/selectors/parser.py,sha256=oI3ezkB6sIyrq_nLJrbaBaBZktXwEp_HG_gKQlVSVcs,24447
+natural_pdf/templates/__init__.py,sha256=jYBxzfi73vew0f6yhIh1MlRxw4F_TVN2hKQR0YXOFe0,20
+natural_pdf/utils/__init__.py,sha256=s3M8FggaK1P3EBYn6R_-HgSDjNc9C73gyKe1hihtNWg,43
+natural_pdf/utils/debug.py,sha256=RN7H3E6ph-GtxubCW6psW7TO8o2BxcNLiEzByTVR9fk,995
+natural_pdf/utils/highlighting.py,sha256=EIY6ihVGtUTS_DjWyxpnr_UXpcR4btC1KhSGQ9VUfKg,698
+natural_pdf/utils/identifiers.py,sha256=P7n6owcubnF8oAMa_UfYtENmIaJQdH_AMC9Jbs2bWXo,1117
+natural_pdf/utils/locks.py,sha256=7HJqV0VsNcOfISnbw8goCKWP5ck11uSJo6T_x9XIPKI,215
+natural_pdf/utils/packaging.py,sha256=Jshxp6S1zfcqoZmFhdd7WOpL--b6rBSz-Y9mYqELXIY,21581
+natural_pdf/utils/reading_order.py,sha256=s3DsYq_3g_1YA07qhd4BGEjeIRTeyGtnwc_hNtSzwBY,7290
+natural_pdf/utils/text_extraction.py,sha256=z6Jhy11pakYCsEpkvh8ldw6DkUFsYF1hCL9YDmfXWL4,9605
+natural_pdf/utils/tqdm_utils.py,sha256=wV3RXvqog26eWEFEqjt2LkGnLswmO1GXaVGSqgS7tAY,1601
+natural_pdf/utils/visualization.py,sha256=30pRWQdsRJh2pSObh-brKVsFgC1n8tHmSrta_UDnVPw,8989
+natural_pdf/widgets/__init__.py,sha256=O2fSDo604wDAP6UwUkmBq3eT91RSqHwBpAOQXq92S8s,214
+natural_pdf/widgets/viewer.py,sha256=dC_hlPlosc08gsDc3bdAa8chOKtAoH9QFU6mrGOG9vE,39532
+natural_pdf-0.1.9.dist-info/licenses/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
+natural_pdf-0.1.9.dist-info/METADATA,sha256=10GX2Qesem-n8sPem4lls2EEQen4KyJVdcmQf1mt9mI,7400
+natural_pdf-0.1.9.dist-info/WHEEL,sha256=wXxTzcEDnjrTwFYjLPcsW_7_XihufBwmpiBeiXNBGEA,91
+natural_pdf-0.1.9.dist-info/top_level.txt,sha256=Cyw1zmNDlUZfb5moU-WUWGprrwH7ln_8LDGdmMHF1xI,17
+natural_pdf-0.1.9.dist-info/RECORD,,

{natural_pdf-0.1.7.dist-info → natural_pdf-0.1.9.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (79.0.0)
+Generator: setuptools (80.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{natural_pdf-0.1.7.dist-info → natural_pdf-0.1.9.dist-info}/top_level.txt

@@ -1,4 +1,2 @@
-docs
 natural_pdf
-notebooks
 pdfs