Merge pull request #32 from VikParuchuri/dev

Fix table bug

README.md

@@ -73,7 +73,7 @@ First, clone the repo:
   - `poetry shell` to activate your poetry venv
 - Update pytorch since poetry doesn't play nicely with it
   - GPU only: run `pip install torch` to install other torch dependencies.
-  - CPU only: Uninstall torch, then follow the [CPU install](https://pytorch.org/get-started/locally/) instructions.
+  - CPU only: Uninstall torch with `poetry remove torch`, then follow the [CPU install](https://pytorch.org/get-started/locally/) instructions.
 
 ## Mac
 

marker/cleaners/table.py

@@ -8,25 +8,24 @@
 
 
 def merge_table_blocks(blocks: List[Page]):
-    last_block = None
     current_lines = []
     current_bbox = None
     for page in blocks:
         new_page_blocks = []
+        pnum = page.pnum
         for block in page.blocks:
             if block.most_common_block_type() != "Table":
                 if len(current_lines) > 0:
                     new_block = Block(
                         lines=deepcopy(current_lines),
-                        pnum=last_block.pnum,
+                        pnum=pnum,
                         bbox=current_bbox
                     )
                     new_page_blocks.append(new_block)
                     current_lines = []
                     current_bbox = None
 
                 new_page_blocks.append(block)
-                last_block = block
                 continue
 
             current_lines.extend(block.lines)
@@ -38,7 +37,7 @@ def merge_table_blocks(blocks: List[Page]):
         if len(current_lines) > 0:
             new_block = Block(
                 lines=deepcopy(current_lines),
-                pnum=last_block.pnum,
+                pnum=pnum,
                 bbox=current_bbox
             )
             new_page_blocks.append(new_block)

marker/debug/data.py

@@ -11,7 +11,7 @@
 
 
 def dump_nougat_debug_data(doc, images, converted_spans):
-    if not settings.DEBUG or not settings.DEBUG_DATA_FOLDER:
+    if not settings.DEBUG_DATA_FOLDER:
         return
 
     # We attempted one conversion per image
@@ -41,7 +41,7 @@ def dump_nougat_debug_data(doc, images, converted_spans):
 
 
 def dump_bbox_debug_data(doc, blocks: List[Page]):
-    if not settings.DEBUG or not settings.DEBUG_DATA_FOLDER:
+    if not settings.DEBUG_DATA_FOLDER:
         return
 
     # Remove extension from doc name