Merge pull request #303 from VikParuchuri/dev

Fix bug, improve quality

README.md

@@ -147,6 +147,20 @@ METADATA_FILE=../pdf_meta.json NUM_DEVICES=4 NUM_WORKERS=15 marker_chunk_convert
 
 Note that the env variables above are specific to this script, and cannot be set in `local.env`.
 
+
+## Use from python
+
+See the `convert_single_pdf` function for additional arguments that can be passed.
+
+```python
+from marker.convert import convert_single_pdf
+from marker.models import load_all_models
+
+fpath = "FILEPATH"
+model_lst = load_all_models()
+full_text, images, out_meta = convert_single_pdf(fpath, model_lst)
+```
+
 # Output format
 
 The output will be a markdown file, but there will also be a metadata json file that gives information about the conversion process.  It has these fields:

marker/cleaners/headings.py

@@ -115,11 +115,12 @@ def infer_heading_levels(pages: List[Page], height_tol=.99):
                 continue
 
             block_heights = [l.height for l in block.lines] # Account for rotation
-            avg_height = sum(block_heights) / len(block_heights)
-            for idx, (min_height, max_height) in enumerate(heading_ranges):
-                if avg_height >= min_height * height_tol:
-                    block.heading_level = idx + 1
-                    break
+            if len(block_heights) > 0:
+                avg_height = sum(block_heights) / len(block_heights)
+                for idx, (min_height, max_height) in enumerate(heading_ranges):
+                    if avg_height >= min_height * height_tol:
+                        block.heading_level = idx + 1
+                        break
 
             if block.heading_level is None:
                 block.heading_level = settings.HEADING_DEFAULT_LEVEL

marker/layout/layout.py

@@ -63,12 +63,18 @@ def annotate_block_types(pages: List[Page]):
                 if min_dist_idx is None or dist < min_dist:
                     min_dist = dist
                     min_dist_idx = j
+                for line in block2.lines:
+                    dist = block2.distance(line.bbox)
+                    if min_dist_idx is None or dist < min_dist:
+                        min_dist = dist
+                        min_dist_idx = j
+
             if min_dist_idx is not None:
                 block.block_type = page.blocks[min_dist_idx].block_type
 
         for i, block in enumerate(page.blocks):
             if block.block_type is None:
-                block.block_type = "text"
+                block.block_type = "Text"
 
         # Merge blocks together, preserving pdf order
         curr_layout_idx = None