Improve merge_columns documentation, pass metadata to TRs

knaw-huc · Sep 27, 2023 · eb444ef · eb444ef
1 parent 602c4ca
commit eb444ef
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 3 deletions.
diff --git a/pagexml/column_parser.py b/pagexml/column_parser.py
@@ -187,9 +187,11 @@ def make_derived_column(lines: List[pdm.PageXMLTextLine], metadata: dict, page_i
 
 def merge_columns(columns: List[pdm.PageXMLColumn],
                   doc_id: str, metadata: dict) -> pdm.PageXMLColumn:
-    """Merge two columns into one, sorting lines by baseline height."""
+    """Merge a list of columns into one. First, all text regions of all columns are
+    checked for spatial overlap, whereby overlapping text regions are merged.
+    Within the merged text regions, lines are sorted by baseline height."""
     trs = [tr for col in columns for tr in col.text_regions]
-    merged_tr = pagexml_helper.merge_textregions(trs)
+    merged_tr = pagexml_helper.merge_textregions(trs, metadata)
     merged_coords = copy.deepcopy(merged_tr.coords)
     merged_col = pdm.PageXMLColumn(doc_id=doc_id, doc_type='index_column',
                                    metadata=metadata, coords=merged_coords,

diff --git a/pagexml/helper/pagexml_helper.py b/pagexml/helper/pagexml_helper.py
@@ -104,7 +104,7 @@ def merge_sets(sets: List[Set[any]], min_overlap: int = 1) -> List[Set[any]]:
 
 
 def merge_textregions(text_regions: List[pdm.PageXMLTextRegion],
-                      metadata: dict, doc_id: str = None) -> Union[pdm.PageXMLTextRegion, None]:
+                      metadata: dict = None, doc_id: str = None) -> Union[pdm.PageXMLTextRegion, None]:
     """Merge two text_regions into one, sorting lines by baseline height."""
     if len(text_regions) == 0:
         return None