Address #4324

Offer option to return raw clustering results.

Author: JorjMcKie

docs/page.rst

@@ -438,15 +438,17 @@ In a nutshell, this is what you can do with PyMuPDF:
       .. image:: images/img-markers.*
          :scale: 100
 
-   .. method:: cluster_drawings(clip=None, drawings=None, x_tolerance=3, y_tolerance=3)
+   .. method:: cluster_drawings(clip=None, drawings=None, x_tolerance=3, y_tolerance=3, final_filter=True)
 
       Cluster vector graphics (synonyms are line-art or drawings) based on their geometrical vicinity. The method walks through the output of :meth:`Page.get_drawings` and joins paths whose `path["rect"]` are closer to each other than some tolerance values (given in the arguments). The result is a list of rectangles that each wrap things like tables (with gridlines), pie charts, bar charts, etc.
 
       :arg rect_like clip: only consider paths inside this area. The default is the full page.
 
       :arg list drawings: (optional) provide a previously generated output of :meth:`Page.get_drawings`. If `None` the method will execute the method.
 
-      :arg float x_tolerance: 
+      :arg float x_tolerance / y_tolerance: Assume vector graphics to be close enough neighbors for belonging to the same rectangle. Default is 3 points.
+
+      :arg bool final_filter: If `True` (default), the method will to remove rectangles having width or height smaller than the respective tolerance value. If `False` no such filtering is done.
 
    .. method:: find_tables(clip=None, strategy=None, vertical_strategy=None, horizontal_strategy=None, vertical_lines=None, horizontal_lines=None, snap_tolerance=None, snap_x_tolerance=None, snap_y_tolerance=None, join_tolerance=None, join_x_tolerance=None, join_y_tolerance=None, edge_min_length=3, min_words_vertical=3, min_words_horizontal=1, intersection_tolerance=None, intersection_x_tolerance=None, intersection_y_tolerance=None, text_tolerance=None, text_x_tolerance=None, text_y_tolerance=None, add_lines=None)
 

src/__init__.py

@@ -9117,7 +9117,8 @@ def remove_rotation(self):
         return rot  # the inverse of the generated derotation matrix
 
     def cluster_drawings(
-        self, clip=None, drawings=None, x_tolerance: float = 3, y_tolerance: float = 3
+        self, clip=None, drawings=None, x_tolerance: float = 3, y_tolerance: float = 3,
+        final_filter: bool = True,
     ) -> list:
         """Join rectangles of neighboring vector graphic items.
 
@@ -9210,6 +9211,8 @@ def are_neighbors(r1, r2):
             prects = sorted(set(prects), key=lambda r: (r.y1, r.x0))
 
         new_rects = sorted(set(new_rects), key=lambda r: (r.y1, r.x0))
+        if not final_filter:
+            return new_rects
         return [r for r in new_rects if r.width > delta_x and r.height > delta_y]
 
     def get_fonts(self, full=False):