debase 0.4.0__tar.gz → 0.4.1__tar.gz

{debase-0.4.0/src/debase.egg-info → debase-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.4.0
+Version: 0.4.1
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.4.0 → debase-0.4.1}/src/debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.4.0"
+__version__ = "0.4.1"

{debase-0.4.0 → debase-0.4.1}/src/debase/substrate_scope_extractor.py

@@ -309,68 +309,28 @@ def extract_figure_image(pdf_paths: List[Path], figure_ref: str) -> Optional[str
                 
                 log.info("Found figure caption on page %d at y=%.0f", page_num + 1, caption_rect.y0)
                 
-                # Extract multi-page region including the figure and content below
-                # The figure should be between the top of the viewable area and extend to subsequent pages
+                # Extract just the figure with its caption, avoiding excessive white space
                 page_rect = page.rect
                 
-                # Define the region to extract
-                # Extract everything above the caption plus additional content from subsequent pages
-                top_margin = 0  # Start from the very top of the page
-                additional_pages = 2  # Number of additional pages to include
-                left_margin = 0  # Use full page width
-                right_margin = 0
-                
-                # Calculate the figure region for the first page
-                fig_top = top_margin
-                fig_bottom = max(caption_rect.y0 + 150, page_rect.height)  # At least 150px below caption or full page
-                fig_left = left_margin
-                fig_right = page_rect.width - right_margin
-                
-                # Create list to store all page images
-                page_images = []
+                # Calculate the figure region on current page only
+                # Extract from top of page to just below the caption
+                fig_top = 0  # Start from top of page
+                fig_bottom = min(caption_rect.y0 + 200, page_rect.height)  # 200px below caption, but not more than page height
+                fig_left = 0  # Full width
+                fig_right = page_rect.width
                 
-                # Extract first page (from top to bottom)
+                # Extract only the figure region (no additional pages to avoid white space)
                 clip_rect = fitz.Rect(fig_left, fig_top, fig_right, fig_bottom)
                 mat = fitz.Matrix(2, 2)  # 2x zoom for better quality
                 pix = page.get_pixmap(clip=clip_rect, matrix=mat)
-                page_images.append(pix)
                 
-                # Extract additional pages if they exist
-                for additional_page_offset in range(1, additional_pages + 1):
-                    next_page_num = page_num + additional_page_offset
-                    if next_page_num < doc.page_count:
-                        next_page = doc.load_page(next_page_num)
-                        next_page_rect = next_page.rect
-                        
-                        # Extract full page for additional pages
-                        next_clip_rect = fitz.Rect(0, 0, next_page_rect.width, next_page_rect.height)
-                        next_pix = next_page.get_pixmap(clip=next_clip_rect, matrix=mat)
-                        page_images.append(next_pix)
-                        log.info("Added page %d to multi-page extraction", next_page_num + 1)
-                
-                # Combine all page images vertically
-                if len(page_images) == 1:
-                    # Single page extraction
-                    combined_pix = page_images[0]
-                else:
-                    # Multi-page extraction - combine vertically
-                    total_width = max(pix.width for pix in page_images)
-                    total_height = sum(pix.height for pix in page_images)
-                    
-                    # Create a new pixmap to hold the combined image
-                    combined_pix = fitz.Pixmap(fitz.csRGB, fitz.IRect(0, 0, total_width, total_height))
-                    combined_pix.clear_with(255)  # White background
-                    
-                    current_y = 0
-                    for pix in page_images:
-                        # Copy each page image to the combined image
-                        combined_pix.copy(pix, fitz.IRect(0, current_y, pix.width, current_y + pix.height))
-                        current_y += pix.height
+                log.info("Extracted figure region: %.0fx%.0f pixels from page %d", 
+                         pix.width, pix.height, page_num + 1)
                 
                 # Convert to PNG
-                img_bytes = combined_pix.tobytes("png")
-                log.info("Extracted multi-page figure region: %dx%d pixels from %d pages starting at page %d", 
-                         combined_pix.width, combined_pix.height, len(page_images), page_num + 1)
+                img_bytes = pix.tobytes("png")
+                log.info("Extracted figure region: %dx%d pixels from page %d", 
+                         pix.width, pix.height, page_num + 1)
                 
                 return b64encode(img_bytes).decode()
                 

{debase-0.4.0 → debase-0.4.1/src/debase.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.4.0
+Version: 0.4.1
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team