Renaming and cleanup

Signed-off-by: Christoph Auer <[email protected]>

Author: cau-git

README.md

@@ -82,7 +82,7 @@ for page_no, pred_page in pdf_doc.iterate_pages():
         print(word.rect, ": ", word.text)
 
         # create a PIL image with the char cells
-    img = pred_page.render_as_image(label=TextCellUnit.CHAR)
+    img = pred_page.render_as_image(cell_unit=TextCellUnit.CHAR)
     img.show()
 ```
 

docling_parse/pdf_parser.py

@@ -14,7 +14,7 @@
     PdfLine,
     PdfMetaData,
     PdfPageBoundaryType,
-    PdfPageDimensions,
+    PdfPageGeometry,
     PdfTableOfContents,
     PdfTextCell,
     SegmentedPdfPage,
@@ -157,7 +157,7 @@ def load_all_pages(self, create_words: bool = True, create_lines: bool = True):
                 create_textlines=create_lines,
             )  # put on cache
 
-    def _to_dimension(self, dimension: dict) -> PdfPageDimensions:
+    def _to_page_geometry(self, dimension: dict) -> PdfPageGeometry:
 
         boundary_type: PdfPageBoundaryType = PdfPageBoundaryType(
             dimension["page_boundary"]
@@ -217,7 +217,7 @@ def _to_dimension(self, dimension: dict) -> PdfPageDimensions:
             coord_origin=CoordOrigin.BOTTOMLEFT,
         )
 
-        return PdfPageDimensions(
+        return PdfPageGeometry(
             angle=dimension["angle"],
             boundary_type=boundary_type,
             rect=rect,
@@ -319,7 +319,7 @@ def _to_segmented_page(
     ) -> SegmentedPdfPage:
 
         segmented_page = SegmentedPdfPage(
-            dimension=self._to_dimension(page["dimension"]),
+            dimension=self._to_page_geometry(page["dimension"]),
             char_cells=self._to_cells(page["cells"]),
             word_cells=[],
             textline_cells=[],

docling_parse/visualize.py

@@ -147,7 +147,7 @@ def visualise_py(
         if category in ["all", "char"]:
 
             img = pdf_page.render_as_image(
-                label=TextCellUnit.CHAR,
+                cell_unit=TextCellUnit.CHAR,
                 draw_cells_bbox=(not display_text),
                 draw_cells_text=display_text,
             )
@@ -162,7 +162,7 @@ def visualise_py(
 
             if log_text:
                 lines = pdf_page.export_to_textlines(
-                    label=TextCellUnit.CHAR,
+                    cell_unit=TextCellUnit.CHAR,
                     add_fontkey=True,
                     add_fontname=False,
                 )
@@ -171,7 +171,7 @@ def visualise_py(
 
         if category in ["all", "word"]:
             img = pdf_page.render_as_image(
-                label=TextCellUnit.WORD,
+                cell_unit=TextCellUnit.WORD,
                 draw_cells_bbox=(not display_text),
                 draw_cells_text=display_text,
             )
@@ -186,7 +186,7 @@ def visualise_py(
 
             if log_text:
                 lines = pdf_page.export_to_textlines(
-                    label=TextCellUnit.WORD,
+                    cell_unit=TextCellUnit.WORD,
                     add_fontkey=True,
                     add_fontname=False,
                 )
@@ -195,7 +195,7 @@ def visualise_py(
 
         if category in ["all", "line"]:
             img = pdf_page.render_as_image(
-                label=TextCellUnit.LINE,
+                cell_unit=TextCellUnit.LINE,
                 draw_cells_bbox=(not display_text),
                 draw_cells_text=display_text,
             )
@@ -210,7 +210,7 @@ def visualise_py(
 
             if log_text:
                 lines = pdf_page.export_to_textlines(
-                    label=TextCellUnit.LINE,
+                    cell_unit=TextCellUnit.LINE,
                     add_fontkey=True,
                     add_fontname=False,
                 )

poetry.lock

@@ -243,11 +243,11 @@ def test_reference_documents_from_filenames():
                 true_page = SegmentedPdfPage.load_from_json(fname)
                 verify_SegmentedPdfPage(true_page, pred_page, filename=fname)
 
-            img = pred_page.render_as_image(label=TextCellUnit.CHAR)
+            img = pred_page.render_as_image(cell_unit=TextCellUnit.CHAR)
             # img.show()
-            img = pred_page.render_as_image(label=TextCellUnit.WORD)
+            img = pred_page.render_as_image(cell_unit=TextCellUnit.WORD)
             # img.show()
-            img = pred_page.render_as_image(label=TextCellUnit.LINE)
+            img = pred_page.render_as_image(cell_unit=TextCellUnit.LINE)
             # img.show()
 
         toc: PdfTableOfContents = pdf_doc.get_table_of_contents()