fix table cell creation, refactor reading order generation, remove 'p…

…reserve-reading-order' option

.gitignore

@@ -5,4 +5,6 @@ build
 dist
 *~
 .vscode
-ocrd.log
+ocrd.log
+tests/workspace/OCR-D-IMG
+tests/workspace/OCR-D-SEG-PAGE

tests/workspace/mets.xml

@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <mets:mets xmlns:mets="http://www.loc.gov/METS/" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="info:lc/xmlns/premis-v2 http://www.loc.gov/standards/premis/v2/premis-v2-0.xsd http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-6.xsd http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/mets.xsd http://www.loc.gov/mix/v10 http://www.loc.gov/standards/mix/mix10/mix10.xsd">
-  <mets:metsHdr CREATEDATE="2024-04-12T13:10:28.344894">
+  <mets:metsHdr CREATEDATE="2024-04-24T11:11:46.027506">
     <mets:agent TYPE="OTHER" OTHERTYPE="SOFTWARE" ROLE="CREATOR">
       <mets:name>ocrd/core v2.63.3</mets:name>
     </mets:agent>
@@ -29,6 +29,9 @@
       <mets:file ID="OCR-D-IMG_Lodz_UZS_25_0056" MIMETYPE="image/tiff">
         <mets:FLocat xlink:href="images/Lodz_UZS_25_0056.tif" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
       </mets:file>
+      <mets:file ID="OCR-D-IMG_nd1969-01-21_3" MIMETYPE="image/jpeg">
+        <mets:FLocat xlink:href="images/nd1969-01-21_3.jpg" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
+      </mets:file>
       <mets:file ID="OCR-D-IMG_nowa_doba" MIMETYPE="image/jpeg">
         <mets:FLocat xlink:href="images/nowa_doba.jpg" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
       </mets:file>
@@ -46,6 +49,9 @@
       <mets:file ID="OCR-D-SEG-PAGE_Lodz_UZS_25_0056" MIMETYPE="application/vnd.prima.page+xml">
         <mets:FLocat xlink:href="reference_page_xml/Lodz_UZS_25_0056.xml" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
       </mets:file>
+      <mets:file ID="OCR-D-SEG-PAGE_nd1969-01-21_03" MIMETYPE="application/vnd.prima.page+xml">
+        <mets:FLocat xlink:href="reference_page_xml/nd1969-01-21_03.xml" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
+      </mets:file>
       <mets:file ID="OCR-D-SEG-PAGE_nowa_doba" MIMETYPE="application/vnd.prima.page+xml">
         <mets:FLocat xlink:href="reference_page_xml/nowa_doba.xml" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
       </mets:file>
@@ -69,10 +75,16 @@
         <mets:fptr FILEID="OCR-D-IMG_Lodz_UZS_25_0056"/>
         <mets:fptr FILEID="OCR-D-SEG-PAGE_Lodz_UZS_25_0056"/>
       </mets:div>
+      <mets:div TYPE="page" ID="nd1969-01-21_3">
+        <mets:fptr FILEID="OCR-D-IMG_nd1969-01-21_3"/>
+      </mets:div>
       <mets:div TYPE="page" ID="nowa_doba">
         <mets:fptr FILEID="OCR-D-IMG_nowa_doba"/>
         <mets:fptr FILEID="OCR-D-SEG-PAGE_nowa_doba"/>
       </mets:div>
+      <mets:div TYPE="page" ID="nd1969-01-21_03">
+        <mets:fptr FILEID="OCR-D-SEG-PAGE_nd1969-01-21_03"/>
+      </mets:div>
     </mets:div>
   </mets:structMap>
 </mets:mets>

textract2page/cli.py

@@ -2,27 +2,31 @@
 
 from .convert_aws import convert_file
 
-CONTEXT_SETTINGS = dict(help_option_names=['-h', '--help'])
+CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
 
 
 @click.command(context_settings=CONTEXT_SETTINGS)
-@click.option('-O', '--output-file', default='-', help='Output filename (or "-" for standard output)',
-              type=click.Path(dir_okay=False, writable=True, exists=False, allow_dash=True))
-@click.option('--preserve-textract-reading-order', default=True, help='Preserve reading order of lines as indicated by Textract (default = True)')
-@click.argument('aws-json-file', type=click.Path(dir_okay=False, exists=True))
-@click.argument('image-file', type=click.Path(dir_okay=False, exists=True))
-def cli(output_file, preserve_textract_reading_order, aws_json_file, image_file):
+@click.option(
+    "-O",
+    "--output-file",
+    default="-",
+    help='Output filename (or "-" for standard output)',
+    type=click.Path(dir_okay=False, writable=True, exists=False, allow_dash=True),
+)
+@click.argument("aws-json-file", type=click.Path(dir_okay=False, exists=True))
+@click.argument("image-file", type=click.Path(dir_okay=False, exists=True))
+def cli(output_file, aws_json_file, image_file):
     """Convert an AWS Textract JSON file to a PAGE XML file.
 
     Also requires the original input image of AWS OCR to get absolute image coordinates.
 
     The output file will reference the image file under `Page/@imageFilename`
     with its full path. (So you may want to use a relative path.)
     """
-    if output_file == '-':
+    if output_file == "-":
         output_file = None
-    convert_file(aws_json_file, image_file, output_file, preserve_textract_reading_order)
+    convert_file(aws_json_file, image_file, output_file)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     cli()  # pylint: disable=no-value-for-parameter