natural-pdf 0.1.11__py3-none-any.whl → 0.1.12__py3-none-any.whl

natural_pdf/search/searchable_mixin.py

@@ -4,7 +4,6 @@ from abc import ABC, abstractmethod
 from typing import TYPE_CHECKING, Any, Dict, Generator, Iterable, List, Optional, Type, Union
 
 # Now import the flag from the canonical source - this import should always work
-from .haystack_utils import HAS_HAYSTACK_EXTRAS
 
 DEFAULT_SEARCH_COLLECTION_NAME = "default_collection"
 
@@ -108,7 +107,6 @@ class SearchableMixin(ABC):
             logger.info(
                 f"Attaching provided SearchService instance (Collection: '{getattr(service, 'collection_name', '<Unknown>')}')."
             )
-            # TODO: Add stricter type check? isinstance(service, SearchServiceProtocol) requires runtime_checkable
             self._search_service = service
         else:
             # Create new service
@@ -125,28 +123,17 @@ class SearchableMixin(ABC):
             logger.info(
                 f"Creating new SearchService: name='{effective_collection_name}', persist={effective_persist}, model={embedding_model or 'default'}"
             )
-            try:
-                service_args = {
-                    "collection_name": effective_collection_name,
-                    "persist": effective_persist,
-                    **kwargs,
-                }
-                if embedding_model:
-                    service_args["embedding_model"] = embedding_model
-                self._search_service = get_search_service(**service_args)
-            except ImportError as ie:  # Catch the specific ImportError first
-                logger.error(f"Failed to create SearchService due to missing dependency: {ie}")
-                raise ie  # Re-raise the original ImportError
-            except Exception as e:
-                logger.error(
-                    f"Failed to create SearchService due to unexpected error: {e}", exc_info=True
-                )
-                # Keep the RuntimeError for other unexpected creation errors
-                raise RuntimeError(
-                    "Could not create SearchService instance due to an unexpected error."
-                ) from e
+            
+            # Direct creation without try/except
+            service_args = {
+                "collection_name": effective_collection_name,
+                "persist": effective_persist,
+                **kwargs,
+            }
+            if embedding_model:
+                service_args["embedding_model"] = embedding_model
+            self._search_service = get_search_service(**service_args)
 
-        # --- Optional Immediate Indexing (with safety check for persistent) ---
         if index:
             if not self._search_service:  # Should not happen if logic above is correct
                 raise RuntimeError(
@@ -176,8 +163,6 @@ class SearchableMixin(ABC):
                 logger.warning(
                     f"Proceeding with index=True and force_reindex=True for persistent index '{collection_name}'. Existing data will be deleted."
                 )
-            # else: # Not persistent, safe to proceed without existence check
-            #     logger.debug("Proceeding with index=True for non-persistent index.")
 
             # Proceed with indexing if checks passed or not applicable
             logger.info(
@@ -197,12 +182,8 @@ class SearchableMixin(ABC):
             f"Starting internal indexing process into SearchService collection '{collection_name}'..."
         )
 
-        # Use the abstract method to get items
-        try:
-            indexable_items = list(self.get_indexable_items())  # Consume iterator
-        except Exception as e:
-            logger.error(f"Error calling get_indexable_items: {e}", exc_info=True)
-            raise RuntimeError("Failed to retrieve indexable items for indexing.") from e
+        # Get indexable items without try/except
+        indexable_items = list(self.get_indexable_items())  # Consume iterator
 
         if not indexable_items:
             logger.warning(
@@ -211,27 +192,19 @@ class SearchableMixin(ABC):
             return
 
         logger.info(f"Prepared {len(indexable_items)} indexable items for indexing.")
-        try:
-            logger.debug(
-                f"Calling index() on SearchService for collection '{collection_name}' (force_reindex={force_reindex})."
-            )
-            self._search_service.index(
-                documents=indexable_items,
-                embedder_device=embedder_device,
-                force_reindex=force_reindex,
-            )
-            logger.info(
-                f"Successfully completed indexing into SearchService collection '{collection_name}'."
-            )
-        except IndexConfigurationError as ice:
-            logger.error(
-                f"Indexing failed due to configuration error in collection '{collection_name}': {ice}",
-                exc_info=True,
-            )
-            raise  # Re-raise specific error
-        except Exception as e:  # Catch other indexing errors from the service
-            logger.error(f"Indexing failed for collection '{collection_name}': {e}", exc_info=True)
-            raise RuntimeError(f"Indexing failed for collection '{collection_name}'.") from e
+        logger.debug(
+            f"Calling index() on SearchService for collection '{collection_name}' (force_reindex={force_reindex})."
+        )
+        
+        # Call index without try/except
+        self._search_service.index(
+            documents=indexable_items,
+            embedder_device=embedder_device,
+            force_reindex=force_reindex,
+        )
+        logger.info(
+            f"Successfully completed indexing into SearchService collection '{collection_name}'."
+        )
 
     def index_for_search(
         self,
@@ -254,14 +227,12 @@ class SearchableMixin(ABC):
         Returns:
             Self for method chaining.
         """
-        # --- Ensure Service is Initialized (Use Default if Needed) ---
         if not self._search_service:
             logger.info(
                 "Search service not initialized prior to index_for_search. Initializing default in-memory service."
             )
             self.init_search()  # Call init with defaults
 
-        # --- Perform Indexing ---
         self._perform_indexing(force_reindex=force_reindex, embedder_device=embedder_device)
         return self
 
@@ -289,7 +260,6 @@ class SearchableMixin(ABC):
             RuntimeError: If no search service is configured or provided, or if search fails.
             FileNotFoundError: If the collection managed by the service does not exist.
         """
-        # --- Determine which Search Service to use ---
         effective_service = search_service or self._search_service
         if not effective_service:
             raise RuntimeError(
@@ -302,21 +272,9 @@ class SearchableMixin(ABC):
             f"Searching collection '{collection_name}' via {type(effective_service).__name__}..."
         )
 
-        # --- Prepare Query and Options ---
         query_input = query
-        # Example: Handle Region query - maybe move this logic into HaystackSearchService.search?
-        # If we keep it here, it makes the mixin less generic.
-        # Let's assume the SearchService handles the query type appropriately for now.
-        # if isinstance(query, Region):
-        #     logger.debug("Query is a Region object. Extracting text.")
-        #     query_input = query.extract_text()
-        #     if not query_input or query_input.isspace():
-        #         logger.warning("Region provided for query has no extractable text.")
-        #         return []
-
         effective_options = options if options is not None else TextSearchOptions()
 
-        # --- Call SearchService Search Method ---
         try:
             results = effective_service.search(
                 query=query_input,
@@ -336,7 +294,6 @@ class SearchableMixin(ABC):
             # Consider wrapping in a SearchError?
             raise RuntimeError(f"Search failed in collection '{collection_name}'.") from e
 
-    # --- NEW Sync Method ---
     def sync_index(
         self,
         strategy: str = "full",  # 'full' (add/update/delete) or 'upsert_only'
@@ -378,7 +335,6 @@ class SearchableMixin(ABC):
         )
         summary = {"added": 0, "updated": 0, "deleted": 0, "skipped": 0}
 
-        # --- Check Service Capabilities for 'full' sync ---
         if strategy == "full":
             required_methods = ["list_documents", "delete_documents"]
             missing_methods = [m for m in required_methods if not hasattr(self._search_service, m)]
@@ -388,7 +344,6 @@ class SearchableMixin(ABC):
                     f"is missing required methods for 'full' sync strategy: {', '.join(missing_methods)}"
                 )
 
-        # --- 1. Get Desired State (from current collection) ---
         desired_state: Dict[str, Indexable] = {}  # {id: item}
         desired_hashes: Dict[str, Optional[str]] = {}  # {id: hash or None}
         try:
@@ -426,7 +381,6 @@ class SearchableMixin(ABC):
 
         logger.info(f"Desired state contains {len(desired_state)} indexable items.")
 
-        # --- 2. Handle Different Strategies ---
         if strategy == "upsert_only":
             # Simple case: just index everything, let the service handle upserts
             items_to_index = list(desired_state.values())

natural_pdf/widgets/viewer.py

@@ -31,20 +31,6 @@ try:
     from PIL import Image
     from traitlets import Dict, List, Unicode, observe
 
-    # --- Read JS code from file (only needed if widgets are defined) --- #
-    _MODULE_DIR = os.path.dirname(__file__)
-    _FRONTEND_JS_PATH = os.path.join(_MODULE_DIR, "frontend", "viewer.js")
-    try:
-        with open(_FRONTEND_JS_PATH, "r", encoding="utf-8") as f:
-            _FRONTEND_JS_CODE = f.read()
-        logger.debug(f"Successfully read frontend JS from: {_FRONTEND_JS_PATH}")
-    except FileNotFoundError:
-        logger.error(f"Frontend JS file not found at {_FRONTEND_JS_PATH}. Widget will likely fail.")
-        _FRONTEND_JS_CODE = "console.error('Frontend JS file not found! Widget cannot load.');"
-    except Exception as e:
-        logger.error(f"Error reading frontend JS file {_FRONTEND_JS_PATH}: {e}")
-        _FRONTEND_JS_CODE = f"console.error('Error reading frontend JS file: {e}');"
-
     # --- Define Widget Classes ONLY if ipywidgets is available ---
     class SimpleInteractiveViewerWidget(widgets.DOMWidget):
         def __init__(self, pdf_data=None, **kwargs):
@@ -631,7 +617,7 @@ try:
 
             # Filter out 'char' elements
             filtered_page_elements = [
-                el for el in page_elements if getattr(el, "type", "").lower() != "char"
+                el for el in page_elements if str(getattr(el, "type", "")).lower() != "char"
             ]
             logger.debug(
                 f"Filtered out char elements, keeping {len(filtered_page_elements)} elements."
@@ -659,19 +645,21 @@ try:
 
             for i, element in enumerate(filtered_page_elements):
                 # Get original coordinates and calculated width/height (always present via base class)
+                # Assuming 'element' is always an object with these attributes now
                 original_x0 = element.x0
                 original_y0 = element.top
                 original_x1 = element.x1
                 original_y1 = element.bottom
                 width = element.width
                 height = element.height
+                current_element_type = element.type  # Direct attribute access
                 scale = 1.0
 
                 # Base element dict with required info
                 elem_dict = {
                     "id": i,
                     # Use the standardized .type property
-                    "type": element.type,
+                    "type": current_element_type,
                     # Scaled coordinates for positioning in HTML/SVG
                     "x0": original_x0 * scale,
                     "y0": original_y0 * scale,
@@ -684,21 +672,24 @@ try:
                 # --- Get Default Attributes --- #
                 attributes_found = set()
                 for attr_name in default_attributes_to_get:
+                    # Assuming 'element' is always an object
                     if hasattr(element, attr_name):
                         try:
-                            value = getattr(element, attr_name)
+                            value_to_process = getattr(element, attr_name)
                             # Convert non-JSON serializable types to string
-                            processed_value = value
+                            processed_value = value_to_process
                             if (
-                                not isinstance(value, (str, int, float, bool, list, dict, tuple))
-                                and value is not None
+                                not isinstance(
+                                    value_to_process, (str, int, float, bool, list, dict, tuple)
+                                )
+                                and value_to_process is not None
                             ):
-                                processed_value = str(value)
+                                processed_value = str(value_to_process)
                             elem_dict[attr_name] = processed_value
                             attributes_found.add(attr_name)
                         except Exception as e:
                             logger.warning(
-                                f"Could not get or process default attribute '{attr_name}' for element {i} ({element.type}): {e}"
+                                f"Could not get or process default attribute '{attr_name}' for element {i} ({current_element_type}): {e}"
                             )
 
                 # --- Get User-Requested Attributes (if any) --- #
@@ -707,23 +698,23 @@ try:
                         # Only process if not already added and exists
                         if attr_name not in attributes_found and hasattr(element, attr_name):
                             try:
-                                value = getattr(element, attr_name)
-                                processed_value = value
+                                value_to_process = getattr(element, attr_name)
+                                processed_value = value_to_process
                                 if (
                                     not isinstance(
-                                        value, (str, int, float, bool, list, dict, tuple)
+                                        value_to_process, (str, int, float, bool, list, dict, tuple)
                                     )
-                                    and value is not None
+                                    and value_to_process is not None
                                 ):
-                                    processed_value = str(value)
+                                    processed_value = str(value_to_process)
                                 elem_dict[attr_name] = processed_value
                             except Exception as e:
                                 logger.warning(
-                                    f"Could not get or process requested attribute '{attr_name}' for element {i} ({element.type}): {e}"
+                                    f"Could not get or process requested attribute '{attr_name}' for element {i} ({current_element_type}): {e}"
                                 )
-                for attr_name in elem_dict:
-                    if isinstance(elem_dict[attr_name], float):
-                        elem_dict[attr_name] = round(elem_dict[attr_name], 2)
+                for attr_name_val in elem_dict:  # Renamed to avoid conflict
+                    if isinstance(elem_dict[attr_name_val], float):
+                        elem_dict[attr_name_val] = round(elem_dict[attr_name_val], 2)
                 elements.append(elem_dict)
 
             logger.debug(

{natural_pdf-0.1.11.dist-info → natural_pdf-0.1.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: natural-pdf
-Version: 0.1.11
+Version: 0.1.12
 Summary: A more intuitive interface for working with PDFs
 Author-email: Jonathan Soma <jonathan.soma@gmail.com>
 License-Expression: MIT
@@ -12,20 +12,16 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pdfplumber
-Requires-Dist: Pillow
+Requires-Dist: pillow
 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: lancedb-haystack; extra == "haystack"
-Requires-Dist: lancedb; extra == "haystack"
-Requires-Dist: sentence-transformers; extra == "haystack"
-Requires-Dist: natural-pdf[core-ml]; extra == "haystack"
+Requires-Dist: jenkspy
+Requires-Dist: pikepdf>=9.7.0
+Provides-Extra: viewer
+Requires-Dist: ipywidgets<9.0.0,>=7.0.0; extra == "viewer"
 Provides-Extra: easyocr
 Requires-Dist: easyocr; extra == "easyocr"
 Requires-Dist: natural-pdf[core-ml]; extra == "easyocr"
@@ -41,19 +37,25 @@ 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
 Requires-Dist: docling; extra == "docling"
 Requires-Dist: natural-pdf[core-ml]; extra == "docling"
 Provides-Extra: llm
 Requires-Dist: openai>=1.0; 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: search
+Requires-Dist: lancedb; extra == "search"
+Requires-Dist: pyarrow; extra == "search"
+Provides-Extra: favorites
+Requires-Dist: natural-pdf[deskew]; extra == "favorites"
+Requires-Dist: natural-pdf[llm]; extra == "favorites"
+Requires-Dist: natural-pdf[surya]; extra == "favorites"
+Requires-Dist: natural-pdf[easyocr]; extra == "favorites"
+Requires-Dist: natural-pdf[layout_yolo]; extra == "favorites"
+Requires-Dist: natural-pdf[ocr-export]; extra == "favorites"
+Requires-Dist: natural-pdf[viewer]; extra == "favorites"
+Requires-Dist: natural-pdf[search]; extra == "favorites"
 Provides-Extra: dev
 Requires-Dist: black; extra == "dev"
 Requires-Dist: isort; extra == "dev"
@@ -67,29 +69,32 @@ Requires-Dist: pipdeptree; extra == "dev"
 Requires-Dist: nbformat; extra == "dev"
 Requires-Dist: jupytext; extra == "dev"
 Requires-Dist: nbclient; extra == "dev"
+Requires-Dist: ipykernel; 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"
+Requires-Dist: natural-pdf[viewer]; extra == "all"
 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[core-ml]; extra == "all"
 Requires-Dist: natural-pdf[deskew]; extra == "all"
 Requires-Dist: natural-pdf[test]; extra == "all"
+Requires-Dist: natural-pdf[search]; extra == "all"
 Provides-Extra: core-ml
 Requires-Dist: torch; extra == "core-ml"
 Requires-Dist: torchvision; extra == "core-ml"
 Requires-Dist: transformers[sentencepiece]; extra == "core-ml"
 Requires-Dist: huggingface_hub; extra == "core-ml"
+Requires-Dist: sentence-transformers; extra == "core-ml"
+Requires-Dist: numpy; extra == "core-ml"
+Requires-Dist: timm; extra == "core-ml"
 Provides-Extra: ocr-export
 Requires-Dist: pikepdf; extra == "ocr-export"
 Provides-Extra: export-extras
@@ -114,26 +119,11 @@ Natural PDF lets you find and extract content from PDFs using simple code that m
 pip install natural-pdf
 ```
 
-For optional features like specific OCR engines, layout analysis models, or the interactive Jupyter widget, you can install extras:
+For optional features like specific OCR engines, layout analysis models, or the interactive Jupyter widget, you can install one to two million different extras. If you just want the greatest hits:
 
 ```bash
-# Example: Install with EasyOCR support
-pip install natural-pdf[easyocr]
-pip install natural-pdf[surya]
-pip install natural-pdf[paddle]
-
-# Example: Install support for features using Large Language Models (e.g., via OpenAI-compatible APIs)
-pip install natural-pdf[llm]
-# (May require setting API key environment variables, e.g., GOOGLE_API_KEY for Gemini)
-
-# Example: Install with interactive viewer support
-pip install natural-pdf[interactive]
-
-# Example: Install with semantic search support (Haystack)
-pip install natural-pdf[haystack]
-
-# Install everything
-pip install natural-pdf[all]
+# deskewing, OCR (surya) + layout analysis (yolo), interactive browsing
+pip install natural-pdf[favorites]
 ```
 
 See the [installation guide](https://jsoma.github.io/natural-pdf/installation/) for more details on extras.
@@ -147,25 +137,26 @@ from natural_pdf import PDF
 pdf = PDF('document.pdf')
 page = pdf.pages[0]
 
+# Extract all of the text on the page
+page.extract_text()
+
 # Find elements using CSS-like selectors
 heading = page.find('text:contains("Summary"):bold')
 
 # Extract content below the heading
 content = heading.below().extract_text()
-print("Content below Summary:", content[:100] + "...")
 
-# Exclude headers/footers automatically (example)
-# You might define these based on common text or position
-page.add_exclusion(page.find('text:contains("CONFIDENTIAL")').above())
-page.add_exclusion(page.find_all('line')[-1].below())
+# Examine all the bold text on the page
+page.find_all('text:bold').show()
 
-# Extract clean text from the page
-clean_text = page.extract_text()
-print("\nClean page text:", clean_text[:200] + "...")
+# Exclude parts of the page from selectors/extractors
+header = page.find('text:contains("CONFIDENTIAL")').above()
+footer = page.find_all('line')[-1].below()
+page.add_exclusion(header)
+page.add_exclusion(footer)
 
-# Highlight the heading and view the page
-heading.highlight(color='red')
-page.to_image()
+# Extract clean text from the page ignoring exclusions
+clean_text = page.extract_text()
 ```
 
 And as a fun bonus, `page.viewer()` will provide an interactive method to explore the PDF.
@@ -186,3 +177,17 @@ Natural PDF offers a range of features for working with PDFs:
 ## Learn More
 
 Dive deeper into the features and explore advanced usage in the [**Complete Documentation**](https://jsoma.github.io/natural-pdf).
+
+## Best friends
+
+Natural PDF sits on top of a *lot* of fantastic tools and mdoels, some of which are:
+
+- [pdfplumber](https://github.com/jsvine/pdfplumber)
+- [EasyOCR](https://www.jaided.ai/easyocr/)
+- [PaddleOCR](https://paddlepaddle.github.io/PaddleOCR/latest/en/index.html)
+- [Surya](https://github.com/VikParuchuri/surya)
+- A specific [YOLO](https://github.com/opendatalab/DocLayout-YOLO)
+- [deskew](https://github.com/sbrunner/deskew)
+- [doctr](https://github.com/mindee/doctr)
+- [docling](https://github.com/docling-project/docling)
+- [Hugging Face](https://huggingface.co/models)

{natural_pdf-0.1.11.dist-info → natural_pdf-0.1.12.dist-info}/RECORD

@@ -1,7 +1,7 @@
-natural_pdf/__init__.py,sha256=HIYdzHD7QBRssIseUX_oDJYvVJs646tNSYhKHqk0HeA,2495
+natural_pdf/__init__.py,sha256=0sCYgb9BAV5OnpD_1AswMuOLuXNmpe3OLJpv_6p3tgw,2449
 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/text_options.py,sha256=qEkDaYWla0rIM_gszEOsu52q7C_dAfV81P2HLJZM2sw,3333
+natural_pdf/analyzers/text_structure.py,sha256=VfKTsTFrK877sC0grsis9jK3rrgp0Mbp13VWEbukTcs,28437
 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
@@ -15,31 +15,34 @@ natural_pdf/analyzers/layout/pdfplumber_table_finder.py,sha256=Tk0Q7wv7nGYPo69lh
 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=RxJch8xVu8Me6_T2Kh7ZqUNaAKlXvfyCZD0hRc4Hk6w,17929
+natural_pdf/classification/manager.py,sha256=4iHoZQ6W541efFvwJt38K-4n5svYH3uYk0ixWPCt7do,17922
 natural_pdf/classification/mixin.py,sha256=hhX9qWPShpOq_-mgoEq0GUWnutBnNMo3YdUlxwyNWMA,6781
 natural_pdf/classification/results.py,sha256=El1dY7cBQVOB5lP-uj52dWgH6Y7TeQgJOVcZD-OLjes,2778
 natural_pdf/collections/mixins.py,sha256=sj76Cn6EdBtb5f-bdAV-1qpdixX8tI4BzPccPiYLI1w,5117
 natural_pdf/collections/pdf_collection.py,sha256=obHizc2KR4ZiAspodaPOeMgfpoW3aKg_G0goBHlrFJI,32018
 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=S7Uj3DVksX7o3Qg7hpNulYuxHmqzSJIJ0yXVytPhFqY,105158
-natural_pdf/core/pdf.py,sha256=qpZx5LXZ5Oq1fZ4mzDXBDOIcsApRinMEH0CjVY6jNvM,69273
+natural_pdf/core/element_manager.py,sha256=_UdXu51sLi6STzc8Pj4k8R721G3yJixXDLuRHn3hmr8,25731
+natural_pdf/core/highlighting_service.py,sha256=F1s9KEVkZb3Srtp1_ayQJayp1ZvDf9FcChsZdLk4yWk,37138
+natural_pdf/core/page.py,sha256=XoHPdsg7YUQIkayD0U1cQ7pNR8NCgV9xkV0rVAO7n3s,105167
+natural_pdf/core/pdf.py,sha256=ssXJviTVKyVZuyiSKv1vE0GW7BACNXBhovIUbPm5MZ4,69511
 natural_pdf/elements/__init__.py,sha256=S8XeiNWJ1WcgnyYKdYV1yxQlAxCCO3FfITT8MQwNbyk,41
-natural_pdf/elements/base.py,sha256=7vVCPQyEHifh4LyBuv0kLTqr_gNbbEMc4SoiJmLfEUQ,37585
-natural_pdf/elements/collections.py,sha256=HsNt_4x-yqNI_bDGeNEiih3hotAfrbppmp_O7rq9HGs,107141
+natural_pdf/elements/base.py,sha256=qKU95sJMw6uiIuez57i-3SmMIHvi9ctv7jwIWJI9qnQ,38415
+natural_pdf/elements/collections.py,sha256=gPj_7eONu6zLyYHnWdPRvgHd___FfTW9mg8iwEBsgxg,112383
 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=XYWUym7hgkzMMfmXw0hEz_iGJ6Sdyf6DRz6XjgMVwN0,97250
+natural_pdf/elements/region.py,sha256=HWqO_Or_wi7pu82w_LUoKHa7r_64AEOJDdmBXSWeZ50,98848
 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/hocr.py,sha256=wilmVyBgmBNp2ZEdbKijk9ag8E1AGMMl6rBtsAOzp-Y,20201
-natural_pdf/exporters/hocr_font.py,sha256=e9QdxeCExxpY_dpzwGxFlT_3TcvNejw9qpkNc1NVa4Y,4612
-natural_pdf/exporters/original_pdf.py,sha256=vZeqBsCZh3JRRWwtfHzM78fxvhKkAI4QK3LLkeXidUM,5082
+natural_pdf/exporters/hocr.py,sha256=MOb5sTxe-GlMSOtmqp3p4SY_ZigwOtmd4sj_zMRCIQY,19907
+natural_pdf/exporters/hocr_font.py,sha256=1wsGOMj6zoaRN2rxCwrv4MMLGawpNz984WgXpmWekgw,4574
+natural_pdf/exporters/original_pdf.py,sha256=zsZPg_lUoEerKIzzoEw-qGdM5XBg_LZhFJeVKnCUp4o,5054
 natural_pdf/exporters/paddleocr.py,sha256=BYpdtJI7S8rBkI2dkRESx2epVAZOTfzqU-rjJnUQ5jQ,16249
-natural_pdf/exporters/searchable_pdf.py,sha256=-sbjjM4oV2YCiJaVKcUIPXjAs94ouXSyOSlAzv_qM7I,16815
+natural_pdf/exporters/searchable_pdf.py,sha256=G2Tc4tpDXSYIufXJlkA8ppW_3DuzHAaweYKae33pI_c,16290
+natural_pdf/exporters/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+natural_pdf/exporters/data/pdf.ttf,sha256=x4RUIJJaI9iO2DCmOVe4r4Wmao2vjZ_JDoQ2c7LvGlk,572
+natural_pdf/exporters/data/sRGB.icc,sha256=KpLUuuRQt22LCqQhk9-XTXX2Jzjs6_dPAcXnWxKpV5Y,6922
 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
@@ -55,12 +58,12 @@ natural_pdf/ocr/ocr_options.py,sha256=ZvtnFn1kPkFEoWveQ13uy6B-ofquP0gHEi4tBHrjqC
 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/__init__.py,sha256=72n_Mj_AhF_RCIoBBhZ6EZKjbILM8omelXZ99fXw7n4,3688
+natural_pdf/search/lancedb_search_service.py,sha256=tW7ONPcWGY1HKle_7OqCXRnMCI-aKL-AqneKz2YbLlM,13706
+natural_pdf/search/numpy_search_service.py,sha256=3_8fx7NV-15jBokOU73mcxrznxPxzVQnOlDHf3dpo28,10117
 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/search/searchable_mixin.py,sha256=dZbaHv8Go3TJNqxoPtnp9Dr0Ftxuf_44RpBeIRXkPxc,23534
 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
@@ -75,9 +78,9 @@ natural_pdf/utils/text_extraction.py,sha256=z6Jhy11pakYCsEpkvh8ldw6DkUFsYF1hCL9Y
 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-0.1.11.dist-info/licenses/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
-natural_pdf-0.1.11.dist-info/METADATA,sha256=HBEH41sOW2opbRoN_yUq8iw3jB2fvdOXEDj0ZGfmw8g,7354
-natural_pdf-0.1.11.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
-natural_pdf-0.1.11.dist-info/top_level.txt,sha256=Cyw1zmNDlUZfb5moU-WUWGprrwH7ln_8LDGdmMHF1xI,17
-natural_pdf-0.1.11.dist-info/RECORD,,
+natural_pdf/widgets/viewer.py,sha256=ekgXTEfA48GrR-JjpCpgyBCXdf4IubV0pAXDJozcU7A,39196
+natural_pdf-0.1.12.dist-info/licenses/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
+natural_pdf-0.1.12.dist-info/METADATA,sha256=GpzOi_m7e7vOS1vlUsrN0WIc0ncvhxvGvpEuPr5UGY8,7653
+natural_pdf-0.1.12.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
+natural_pdf-0.1.12.dist-info/top_level.txt,sha256=Cyw1zmNDlUZfb5moU-WUWGprrwH7ln_8LDGdmMHF1xI,17
+natural_pdf-0.1.12.dist-info/RECORD,,

{natural_pdf-0.1.11.dist-info → natural_pdf-0.1.12.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.3.1)
+Generator: setuptools (80.7.1)
 Root-Is-Purelib: true
 Tag: py3-none-any