✨ Add a new CLI tool dinglehopper-extract to just give the extracted text

README.md

@@ -76,6 +76,11 @@ parameter:
 ocrd-dinglehopper -I ABBYY-FULLTEXT,OCR-D-OCR-CALAMARI -O OCR-D-OCR-COMPARE-ABBYY-CALAMARI -P metrics false
 ~~~
 
+The tool `dinglehopper-extract` extracts the text of the given input file on
+stdout, for example:
+
+`dinglehopper-extract OCR-D-GT-PAGE/00000024.page.xml`
+
 Developer information
 ---------------------
 *Please refer to [README-DEV.md](README-DEV.md).*

qurator/dinglehopper/cli_extract.py

@@ -0,0 +1,27 @@
+import os
+
+import click
+
+from .extracted_text import ExtractedText
+from .ocr_files import extract
+
+
+@click.command()
+@click.argument('input_file', type=click.Path(exists=True))
+@click.option('--textequiv-level', default='region', help='PAGE TextEquiv level to extract text from', metavar='LEVEL')
+def main(input_file, textequiv_level):
+    """
+    Extract the text of the given INPUT_FILE.
+
+    dinglehopper detects if INPUT_FILE is an ALTO or PAGE XML document to extract
+    its text and falls back to plain text if no ALTO or PAGE is detected.
+
+    By default, the text of PAGE files is extracted on 'region' level. You may
+    use "--textequiv-level line" to extract from the level of TextLine tags.
+    """
+    input_text = extract(input_file, textequiv_level=textequiv_level).text
+    print(input_text)
+
+
+if __name__ == '__main__':
+    main()

setup.py

@@ -22,6 +22,7 @@ setup(
     entry_points={
       'console_scripts': [
         'dinglehopper=qurator.dinglehopper.cli:main',
+        'dinglehopper-extract=qurator.dinglehopper.cli_extract:main',
         'ocrd-dinglehopper=qurator.dinglehopper.ocrd_cli:ocrd_dinglehopper',
       ]
     }