debase 0.4.0__py3-none-any.whl → 0.4.1__py3-none-any.whl

debase/_version.py

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

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.dist-info → debase-0.4.1.dist-info}/METADATA

@@ -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.dist-info → debase-0.4.1.dist-info}/RECORD

@@ -1,16 +1,16 @@
 debase/__init__.py,sha256=YeKveGj_8fwuu5ozoK2mUU86so_FjiCwsvg1d_lYVZU,586
 debase/__main__.py,sha256=LbxYt2x9TG5Ced7LpzzX_8gkWyXeZSlVHzqHfqAiPwQ,160
-debase/_version.py,sha256=X9pfcQjm1Y8ILtLtdscGnfFKSp5XWTeamXgSHPOw2K0,49
+debase/_version.py,sha256=qJBDmAhFTv4pYwvc3Umy_Lwc_v8doVBVCiysT7Eoh3E,49
 debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
 debase/cleanup_sequence.py,sha256=ngxb_tPekjCWvampAjyuFqK4wLk_meFSj_TwfvOxheQ,33978
 debase/enzyme_lineage_extractor.py,sha256=laIw9A5AuJ_kJe9h6Fp_WzMh_ctCN31bo2b2-RKrFd4,124019
 debase/lineage_format.py,sha256=IS9ig-Uv7KxtI9enZKM6YgQ7sitqwOo4cdXbOy38J3s,34232
 debase/reaction_info_extractor.py,sha256=xRyYoQKqSzer-k8FZwg55nDd0D-6QBc0F-HAyfvisG0,150368
-debase/substrate_scope_extractor.py,sha256=ny4n_J4SDFQnxhCHHHan1xouqM8FkueJm_z-hm6gr-o,103761
+debase/substrate_scope_extractor.py,sha256=JLXHEEeMDFiFQRt8gVCnnhimrxDF23-z0jq3N4-3gn8,101469
 debase/wrapper.py,sha256=TGU5eq0qWTrkRR35ztsp8WMb1E9Nt64BdbHuYHROmYA,24279
-debase-0.4.0.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
-debase-0.4.0.dist-info/METADATA,sha256=Qpvyi4nbq_wmhbl_089pRIlGAubVxjwVfX1eUSK3lLY,10789
-debase-0.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-debase-0.4.0.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
-debase-0.4.0.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
-debase-0.4.0.dist-info/RECORD,,
+debase-0.4.1.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.4.1.dist-info/METADATA,sha256=kSH58QfBv6WGb8Ds3mcei-DUmWQormuSyPHNOmpbcQ8,10789
+debase-0.4.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.4.1.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.4.1.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.4.1.dist-info/RECORD,,