natural-pdf 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

natural_pdf/analyzers/guides.py

@@ -3,7 +3,7 @@
 import json
 import logging
 from collections import UserList
-from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Any, Callable, Dict, List, Literal, Optional, Tuple, Union
 
 import numpy as np
 from PIL import Image, ImageDraw
@@ -16,6 +16,7 @@ if TYPE_CHECKING:
     from natural_pdf.elements.element_collection import ElementCollection
     from natural_pdf.elements.region import Region
     from natural_pdf.flows.region import FlowRegion
+    from natural_pdf.tables.result import TableResult
 
 logger = logging.getLogger(__name__)
 
@@ -131,6 +132,15 @@ class GuidesList(UserList):
         self._parent = parent_guides
         self._axis = axis
 
+    def __getitem__(self, i):
+        """Override to handle slicing properly."""
+        if isinstance(i, slice):
+            # Return a new GuidesList with the sliced data
+            return self.__class__(self._parent, self._axis, self.data[i])
+        else:
+            # For single index, return the value directly
+            return self.data[i]
+
     def from_content(
         self,
         markers: Union[str, List[str], "ElementCollection", None],
@@ -140,6 +150,7 @@ class GuidesList(UserList):
         tolerance: float = 5,
         *,
         append: bool = False,
+        apply_exclusions: bool = True,
     ) -> "Guides":
         """
         Create guides from content markers and add to this axis.
@@ -154,6 +165,7 @@ class GuidesList(UserList):
             align: How to align guides relative to found elements
             outer: Whether to add outer boundary guides
             tolerance: Tolerance for snapping to element edges
+            apply_exclusions: Whether to apply exclusion zones when searching for text
 
         Returns:
             Parent Guides object for chaining
@@ -178,6 +190,7 @@ class GuidesList(UserList):
                     align=align,
                     outer=outer,
                     tolerance=tolerance,
+                    apply_exclusions=apply_exclusions,
                 )
 
                 # Collect guides from this region
@@ -260,6 +273,7 @@ class GuidesList(UserList):
             align=align,
             outer=outer,
             tolerance=tolerance,
+            apply_exclusions=apply_exclusions,
         )
 
         # Replace or append based on parameter
@@ -1398,6 +1412,7 @@ class Guides:
         align: Literal["left", "right", "center", "between"] = "left",
         outer: bool = True,
         tolerance: float = 5,
+        apply_exclusions: bool = True,
     ) -> "Guides":
         """
         Create guides based on text content positions.
@@ -1413,6 +1428,7 @@ class Guides:
             align: Where to place guides relative to found text
             outer: Whether to add guides at the boundaries
             tolerance: Maximum distance to search for text
+            apply_exclusions: Whether to apply exclusion zones when searching for text
 
         Returns:
             New Guides object aligned to text content
@@ -1431,6 +1447,7 @@ class Guides:
                     align=align,
                     outer=outer,
                     tolerance=tolerance,
+                    apply_exclusions=apply_exclusions,
                 )
 
                 # Store in flow guides
@@ -1469,7 +1486,7 @@ class Guides:
         # Find each marker and determine guide position
         for marker in marker_texts:
             if hasattr(obj, "find"):
-                element = obj.find(f'text:contains("{marker}")')
+                element = obj.find(f'text:contains("{marker}")', apply_exclusions=apply_exclusions)
                 if element:
                     if axis == "vertical":
                         if align == "left":
@@ -1498,7 +1515,9 @@ class Guides:
             marker_bounds = []
             for marker in marker_texts:
                 if hasattr(obj, "find"):
-                    element = obj.find(f'text:contains("{marker}")')
+                    element = obj.find(
+                        f'text:contains("{marker}")', apply_exclusions=apply_exclusions
+                    )
                     if element:
                         if axis == "vertical":
                             marker_bounds.append((element.x0, element.x1))
@@ -3285,6 +3304,7 @@ class Guides:
         align: Literal["left", "right", "center", "between"] = "left",
         outer: bool = True,
         tolerance: float = 5,
+        apply_exclusions: bool = True,
     ) -> "Guides":
         """
         Instance method: Add guides from content, allowing chaining.
@@ -3301,6 +3321,7 @@ class Guides:
             align: How to align guides relative to found elements
             outer: Whether to add outer boundary guides
             tolerance: Tolerance for snapping to element edges
+            apply_exclusions: Whether to apply exclusion zones when searching for text
 
         Returns:
             Self for method chaining
@@ -3318,6 +3339,7 @@ class Guides:
             align=align,
             outer=outer,
             tolerance=tolerance,
+            apply_exclusions=apply_exclusions,
         )
 
         # Add the appropriate coordinates to this object
@@ -3421,6 +3443,140 @@ class Guides:
 
         return self
 
+    def extract_table(
+        self,
+        target: Optional[Union["Page", "Region"]] = None,
+        source: str = "guides_temp",
+        cell_padding: float = 0.5,
+        include_outer_boundaries: bool = False,
+        method: Optional[str] = None,
+        table_settings: Optional[dict] = None,
+        use_ocr: bool = False,
+        ocr_config: Optional[dict] = None,
+        text_options: Optional[Dict] = None,
+        cell_extraction_func: Optional[Callable[["Region"], Optional[str]]] = None,
+        show_progress: bool = False,
+        content_filter: Optional[Union[str, Callable[[str], bool], List[str]]] = None,
+        *,
+        multi_page: Literal["auto", True, False] = "auto",
+    ) -> "TableResult":
+        """
+        Extract table data directly from guides without leaving temporary regions.
+
+        This method:
+        1. Creates table structure using build_grid()
+        2. Extracts table data from the created table region
+        3. Cleans up all temporary regions
+        4. Returns the TableResult
+
+        Args:
+            target: Page or Region to create regions on (uses self.context if None)
+            source: Source label for temporary regions (will be cleaned up)
+            cell_padding: Internal padding for cell regions in points
+            include_outer_boundaries: Whether to add boundaries at edges if missing
+            method: Table extraction method ('tatr', 'pdfplumber', 'text', etc.)
+            table_settings: Settings for pdfplumber table extraction
+            use_ocr: Whether to use OCR for text extraction
+            ocr_config: OCR configuration parameters
+            text_options: Dictionary of options for the 'text' method
+            cell_extraction_func: Optional callable for custom cell text extraction
+            show_progress: Controls progress bar for text method
+            content_filter: Content filtering function or patterns
+            multi_page: Controls multi-region table creation for FlowRegions
+
+        Returns:
+            TableResult: Extracted table data
+
+        Raises:
+            ValueError: If no table region is created from the guides
+
+        Example:
+            ```python
+            from natural_pdf.analyzers import Guides
+
+            # Create guides from detected lines
+            guides = Guides.from_lines(page, source_label="detected")
+
+            # Extract table directly - no temporary regions left behind
+            table_data = guides.extract_table()
+
+            # Convert to pandas DataFrame
+            df = table_data.to_df()
+            ```
+        """
+        target_obj = target or self.context
+        if not target_obj:
+            raise ValueError("No target object available. Provide target parameter or context.")
+
+        # Get the page for cleanup later
+        if hasattr(target_obj, "x0") and hasattr(target_obj, "top"):  # Region
+            page = target_obj._page
+            element_manager = page._element_mgr
+        elif hasattr(target_obj, "_element_mgr"):  # Page
+            page = target_obj
+            element_manager = page._element_mgr
+        else:
+            raise ValueError(f"Target object {target_obj} is not a Page or Region")
+
+        try:
+            # Step 1: Build grid structure (creates temporary regions)
+            grid_result = self.build_grid(
+                target=target_obj,
+                source=source,
+                cell_padding=cell_padding,
+                include_outer_boundaries=include_outer_boundaries,
+                multi_page=multi_page,
+            )
+
+            # Step 2: Get the table region and extract table data
+            table_region = grid_result["regions"]["table"]
+            if table_region is None:
+                raise ValueError(
+                    "No table region was created from the guides. Check that you have both vertical and horizontal guides."
+                )
+
+            # Handle multi-page case where table_region might be a list
+            if isinstance(table_region, list):
+                if not table_region:
+                    raise ValueError("No table regions were created from the guides.")
+                # Use the first table region for extraction
+                table_region = table_region[0]
+
+            # Step 3: Extract table data using the region's extract_table method
+            table_result = table_region.extract_table(
+                method=method,
+                table_settings=table_settings,
+                use_ocr=use_ocr,
+                ocr_config=ocr_config,
+                text_options=text_options,
+                cell_extraction_func=cell_extraction_func,
+                show_progress=show_progress,
+                content_filter=content_filter,
+            )
+
+            return table_result
+
+        finally:
+            # Step 4: Clean up all temporary regions created by build_grid
+            # This ensures no regions are left behind regardless of success/failure
+            try:
+                regions_to_remove = [
+                    r
+                    for r in element_manager.regions
+                    if getattr(r, "source", None) == source
+                    and getattr(r, "region_type", None)
+                    in {"table", "table_row", "table_column", "table_cell"}
+                ]
+
+                for region in regions_to_remove:
+                    element_manager.remove_element(region, element_type="regions")
+
+                if regions_to_remove:
+                    logger.debug(f"Cleaned up {len(regions_to_remove)} temporary regions")
+
+            except Exception as cleanup_err:
+                logger.warning(f"Failed to clean up temporary regions: {cleanup_err}")
+
     def _get_flow_orientation(self) -> Literal["vertical", "horizontal", "unknown"]:
         """Determines if a FlowRegion's constituent parts are arranged vertically or horizontally."""
         if not self.is_flow_region or len(self.context.constituent_regions) < 2:

natural_pdf/core/highlighting_service.py

@@ -689,7 +689,7 @@ class HighlightingService:
         logger.debug(f"Added highlight to page {page_index}: {highlight}")
 
         # --- Invalidate page-level image cache --------------------------------
-        # The Page.to_image method maintains an internal cache keyed by rendering
+        # The Page.render method maintains an internal cache keyed by rendering
         # parameters.  Because the cache key currently does **not** incorporate
         # any information about the highlights themselves, it can return stale
         # images after highlights are added or removed.  To ensure the next
@@ -700,11 +700,11 @@ class HighlightingService:
             if hasattr(page_obj, "_to_image_cache"):
                 page_obj._to_image_cache.clear()
                 logger.debug(
-                    f"Cleared cached to_image renders for page {page_index} after adding a highlight."
+                    f"Cleared cached render images for page {page_index} after adding a highlight."
                 )
         except Exception as cache_err:  # pragma: no cover – never fail highlight creation
             logger.warning(
-                f"Failed to invalidate to_image cache for page {page_index}: {cache_err}",
+                f"Failed to invalidate render cache for page {page_index}: {cache_err}",
                 exc_info=True,
             )
 
@@ -737,11 +737,11 @@ class HighlightingService:
             if hasattr(page_obj, "_to_image_cache"):
                 page_obj._to_image_cache.clear()
                 logger.debug(
-                    f"Cleared cached to_image renders for page {page_index} after removing highlights."
+                    f"Cleared cached render images for page {page_index} after removing highlights."
                 )
         except Exception as cache_err:  # pragma: no cover
             logger.warning(
-                f"Failed to invalidate to_image cache for page {page_index}: {cache_err}",
+                f"Failed to invalidate render cache for page {page_index}: {cache_err}",
                 exc_info=True,
             )
 
@@ -760,7 +760,7 @@ class HighlightingService:
         labels: bool = True,
         legend_position: str = "right",
         render_ocr: bool = False,
-        **kwargs,  # Pass other args to pdfplumber.page.to_image if needed
+        **kwargs,  # Pass other args to pdfplumber.page.to_image if needed (internal API)
     ) -> Optional[Image.Image]:
         """
         Renders a specific page with its highlights.
@@ -773,7 +773,7 @@ class HighlightingService:
             labels: Whether to include a legend for highlights.
             legend_position: Position of the legend.
             render_ocr: Whether to render OCR text on the image.
-            kwargs: Additional keyword arguments for pdfplumber's page.to_image (e.g., width, height).
+            kwargs: Additional keyword arguments for pdfplumber's internal page.to_image (e.g., width, height).
 
         Returns:
             A PIL Image object of the rendered page, or None if rendering fails.
@@ -957,7 +957,7 @@ class HighlightingService:
             crop_bbox: Optional bounding box (x0, top, x1, bottom) in PDF coordinate
                 space to crop the output image to, before legends or other overlays are
                 applied. If None, no cropping is performed.
-            **kwargs: Additional args for pdfplumber's to_image (e.g., width, height).
+            **kwargs: Additional args for pdfplumber's internal to_image (e.g., width, height).
 
         Returns:
             PIL Image of the preview, or None if rendering fails.

natural_pdf/core/page.py

@@ -341,6 +341,26 @@ class Page(
                     for elem in elements:
                         spec.add_highlight(element=elem, color=group_color, label=group_label)
 
+            # Handle exclusions visualization
+            exclusions_param = kwargs.get("exclusions")
+            if exclusions_param:
+                # Get exclusion regions
+                exclusion_regions = self._get_exclusion_regions(include_callable=True)
+
+                if exclusion_regions:
+                    # Determine color for exclusions
+                    exclusion_color = (
+                        exclusions_param if isinstance(exclusions_param, str) else "red"
+                    )
+
+                    # Add exclusion regions as highlights
+                    for region in exclusion_regions:
+                        spec.add_highlight(
+                            element=region,
+                            color=exclusion_color,
+                            label=f"Exclusion: {region.label or 'unnamed'}",
+                        )
+
         return [spec]
 
     @property
@@ -391,7 +411,9 @@ class Page(
 
     def add_exclusion(
         self,
-        exclusion_func_or_region: Union[Callable[["Page"], "Region"], "Region", Any],
+        exclusion_func_or_region: Union[
+            Callable[["Page"], "Region"], "Region", List[Any], Tuple[Any, ...], Any
+        ],
         label: Optional[str] = None,
         method: str = "region",
     ) -> "Page":
@@ -401,7 +423,8 @@ class Page(
 
         Args:
             exclusion_func_or_region: Either a callable function returning a Region,
-                                      a Region object, or another object with a valid .bbox attribute.
+                                      a Region object, a list/tuple of regions or elements,
+                                      or another object with a valid .bbox attribute.
             label: Optional label for this exclusion (e.g., 'header', 'footer').
             method: Exclusion method - 'region' (exclude all elements in bounding box) or
                     'element' (exclude only the specific elements). Default: 'region'.
@@ -551,10 +574,53 @@ class Page(
                     raise TypeError(
                         f"Failed to convert exclusion object {exclusion_func_or_region} with bbox {getattr(exclusion_func_or_region, 'bbox', 'N/A')} to Region: {e}"
                     ) from e
+        elif isinstance(exclusion_func_or_region, (list, tuple)):
+            # Handle lists/tuples of regions or elements
+            if not exclusion_func_or_region:
+                logger.warning(f"Page {self.index}: Empty list provided for exclusion, ignoring.")
+                return self
+
+            if method == "element":
+                # Store each element directly
+                for item in exclusion_func_or_region:
+                    if hasattr(item, "bbox") and len(getattr(item, "bbox", [])) == 4:
+                        self._exclusions.append((item, label, method))
+                        logger.debug(
+                            f"Page {self.index}: Added element exclusion from list -> {item}"
+                        )
+                    else:
+                        logger.warning(
+                            f"Page {self.index}: Skipping item without valid bbox in list: {item}"
+                        )
+            else:  # method == "region"
+                # Convert each item to a Region and add
+                for item in exclusion_func_or_region:
+                    try:
+                        if isinstance(item, Region):
+                            item.label = label
+                            self._exclusions.append((item, label, method))
+                            logger.debug(f"Page {self.index}: Added Region from list: {item}")
+                        elif hasattr(item, "bbox") and len(getattr(item, "bbox", [])) == 4:
+                            bbox_coords = tuple(float(v) for v in item.bbox)
+                            region = Region(self, bbox_coords, label=label)
+                            self._exclusions.append((region, label, method))
+                            logger.debug(
+                                f"Page {self.index}: Added exclusion region from list item {bbox_coords}"
+                            )
+                        else:
+                            logger.warning(
+                                f"Page {self.index}: Skipping item without valid bbox in list: {item}"
+                            )
+                    except Exception as e:
+                        logger.error(
+                            f"Page {self.index}: Failed to convert list item to Region: {e}"
+                        )
+                        continue
+            return self
         else:
             # Reject invalid types
             raise TypeError(
-                f"Invalid exclusion type: {type(exclusion_func_or_region)}. Must be callable, Region, or have a valid .bbox attribute."
+                f"Invalid exclusion type: {type(exclusion_func_or_region)}. Must be callable, Region, list/tuple of regions/elements, or have a valid .bbox attribute."
             )
 
         # Append the stored data (tuple of object/callable, label, and method)
@@ -668,6 +734,46 @@ class Page(
                         regions.append(region_result)
                         if debug:
                             print(f"    ✓ Added region from callable '{label}': {region_result}")
+                    elif hasattr(region_result, "__iter__") and hasattr(region_result, "__len__"):
+                        # Handle ElementCollection or other iterables
+                        from natural_pdf.elements.element_collection import ElementCollection
+
+                        if isinstance(region_result, ElementCollection) or (
+                            hasattr(region_result, "__iter__") and region_result
+                        ):
+                            if debug:
+                                print(
+                                    f"    Converting {type(region_result)} with {len(region_result)} elements to regions..."
+                                )
+
+                            # Convert each element to a region
+                            for elem in region_result:
+                                try:
+                                    if hasattr(elem, "bbox") and len(elem.bbox) == 4:
+                                        bbox_coords = tuple(float(v) for v in elem.bbox)
+                                        region = Region(self, bbox_coords, label=label)
+                                        regions.append(region)
+                                        if debug:
+                                            print(
+                                                f"      ✓ Added region from element: {bbox_coords}"
+                                            )
+                                    else:
+                                        if debug:
+                                            print(
+                                                f"      ✗ Skipping element without valid bbox: {elem}"
+                                            )
+                                except Exception as e:
+                                    if debug:
+                                        print(f"      ✗ Failed to convert element to region: {e}")
+                                    continue
+
+                            if debug and len(region_result) > 0:
+                                print(
+                                    f"    ✓ Converted {len(region_result)} elements from callable '{label}'"
+                                )
+                        else:
+                            if debug:
+                                print(f"    ✗ Empty iterable returned from callable '{label}'")
                     elif region_result:
                         logger.warning(
                             f"Callable exclusion '{exclusion_label}' returned non-Region object: {type(region_result)}. Skipping."
@@ -1013,6 +1119,22 @@ class Page(
                         "Cannot sort elements in reading order: Missing required attributes (top, x0)."
                     )
 
+            # Handle collection-level pseudo-classes (:first, :last) for OR selectors
+            # Note: We only apply :first/:last if they appear in any of the sub-selectors
+            has_first = False
+            has_last = False
+            for sub_selector in selector_obj.get("selectors", []):
+                for pseudo in sub_selector.get("pseudo_classes", []):
+                    if pseudo.get("name") == "first":
+                        has_first = True
+                    elif pseudo.get("name") == "last":
+                        has_last = True
+
+            if has_first:
+                matching_elements = matching_elements[:1] if matching_elements else []
+            elif has_last:
+                matching_elements = matching_elements[-1:] if matching_elements else []
+
             # Return result collection
             return ElementCollection(matching_elements)
 
@@ -1134,6 +1256,15 @@ class Page(
                     "Cannot sort elements in reading order: Missing required attributes (top, x0)."
                 )
 
+        # Handle collection-level pseudo-classes (:first, :last)
+        for pseudo in selector_obj.get("pseudo_classes", []):
+            name = pseudo.get("name")
+
+            if name == "first":
+                matching_elements = matching_elements[:1] if matching_elements else []
+            elif name == "last":
+                matching_elements = matching_elements[-1:] if matching_elements else []
+
         # Create result collection - exclusions are handled by the calling methods (find, find_all)
         result = ElementCollection(matching_elements)
 
@@ -1944,7 +2075,7 @@ class Page(
             render_ocr: Whether to render OCR text.
             include_highlights: Whether to render highlights.
             resolution: Resolution in DPI for base image rendering (default: 144 DPI, equivalent to previous scale=2.0).
-            **kwargs: Additional args for pdfplumber's to_image.
+            **kwargs: Additional args for pdfplumber's internal to_image.
 
         Returns:
             Self for method chaining.

natural_pdf/core/page_collection.py

@@ -1247,3 +1247,40 @@ class PageCollection(TextMixin, Generic[P], ApplyMixin, ShapeDetectionMixin, Vis
         from natural_pdf.core.highlighting_service import HighlightContext
 
         return HighlightContext(self, show_on_exit=show)
+
+    def groupby(self, by: Union[str, Callable], *, show_progress: bool = True) -> "PageGroupBy":
+        """
+        Group pages by selector text or callable result.
+
+        Args:
+            by: CSS selector string or callable function
+            show_progress: Whether to show progress bar during computation (default: True)
+
+        Returns:
+            PageGroupBy object supporting iteration and dict-like access
+
+        Examples:
+            # Group by header text
+            for title, pages in pdf.pages.groupby('text[size=16]'):
+                print(f"Section: {title}")
+
+            # Group by callable
+            for city, pages in pdf.pages.groupby(lambda p: p.find('text:contains("CITY")').extract_text()):
+                process_city_pages(pages)
+
+            # Quick exploration with indexing
+            grouped = pdf.pages.groupby('text[size=16]')
+            grouped.info()                    # Show all groups
+            first_section = grouped[0]        # First group
+            last_section = grouped[-1]       # Last group
+
+            # Dict-like access by name
+            madison_pages = grouped.get('CITY OF MADISON')
+            madison_pages = grouped['CITY OF MADISON']  # Alternative
+
+            # Disable progress bar for small collections
+            grouped = pdf.pages.groupby('text[size=16]', show_progress=False)
+        """
+        from natural_pdf.core.page_groupby import PageGroupBy
+
+        return PageGroupBy(self, by, show_progress=show_progress)