From 8b4ee20a40328d0eb0b7f4cc6236341545001788 Mon Sep 17 00:00:00 2001
From: "Gerber, Mike" <mike.gerber@sbb.spk-berlin.de>
Date: Wed, 21 Oct 2020 16:30:48 +0200
Subject: [PATCH] =?UTF-8?q?=E2=9C=A8=20Add=20a=20new=20CLI=20tool=20dingle?=
 =?UTF-8?q?hopper-extract=20to=20just=20give=20the=20extracted=20text?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md                           |  5 +++++
 qurator/dinglehopper/cli_extract.py | 27 +++++++++++++++++++++++++++
 setup.py                            |  1 +
 3 files changed, 33 insertions(+)
 create mode 100644 qurator/dinglehopper/cli_extract.py

diff --git a/README.md b/README.md
index 3cf95a6..8c39217 100644
--- a/README.md
+++ b/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).*
diff --git a/qurator/dinglehopper/cli_extract.py b/qurator/dinglehopper/cli_extract.py
new file mode 100644
index 0000000..a5d36d8
--- /dev/null
+++ b/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()
diff --git a/setup.py b/setup.py
index f7a6113..7b8107a 100644
--- a/setup.py
+++ b/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',
       ]
     }