From 8b01d9e671d1527bdf52983ddd0799bcb1f4feda Mon Sep 17 00:00:00 2001
From: "Gerber, Mike" <mike.gerber@sbb.spk-berlin.de>
Date: Wed, 5 Aug 2020 17:16:40 +0200
Subject: [PATCH] =?UTF-8?q?=F0=9F=90=9B=20sbb=5Ftextline=5Fdetection:=20Se?=
 =?UTF-8?q?t=20pcGtsId?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Newest OCR-D workspace validation requires that the pcGtsId of a
PAGE-XML file matches its METS mets:file/ID. Fix this by setting
it correctly.
---
 qurator/sbb_textline_detector/ocrd_cli.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/qurator/sbb_textline_detector/ocrd_cli.py b/qurator/sbb_textline_detector/ocrd_cli.py
index a42027c..ea1b4e3 100644
--- a/qurator/sbb_textline_detector/ocrd_cli.py
+++ b/qurator/sbb_textline_detector/ocrd_cli.py
@@ -77,6 +77,7 @@ class OcrdSbbTextlineDetectorRecognize(Processor):
 
             # Create a new PAGE file from the input file
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            pcgts.set_pcGtsId(file_id)
             page = pcgts.get_Page()
 
             # Merge results → PAGE file