From 1f6538b44c64d3defc28bbd34de195360c9c53d6 Mon Sep 17 00:00:00 2001
From: "Gerber, Mike" <mike.gerber@sbb.spk-berlin.de>
Date: Thu, 11 Jun 2020 17:43:30 +0200
Subject: [PATCH] =?UTF-8?q?=F0=9F=9A=A7=20dinglehopper:=20Extract=20text?=
 =?UTF-8?q?=20while=20retaining=20segment=20id=20info?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 qurator/dinglehopper/ocr_files.py | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/qurator/dinglehopper/ocr_files.py b/qurator/dinglehopper/ocr_files.py
index a5187c5..fd89b03 100644
--- a/qurator/dinglehopper/ocr_files.py
+++ b/qurator/dinglehopper/ocr_files.py
@@ -148,21 +148,35 @@ def page_text(tree):
     return page_extract(tree).text
 
 
-def text(filename):
-    """Read the text from the given file.
+def plain_extract(filename):
+    with open(filename, 'r') as f:
+        return ExtractedText(
+                (ExtractedTextSegment('line %d' % no, line) for no, line in enumerate(f.readlines())),
+                '\n'
+        )
+
+
+def plain_text(filename):
+    return plain_extract(filename).text
+
+
+def extract(filename):
+    """Extract the text from the given file.
 
     Supports PAGE, ALTO and falls back to plain text.
     """
-
     try:
         tree = ET.parse(filename)
     except XMLSyntaxError:
-        with open(filename, 'r') as f:
-            return f.read()
+        return plain_extract(filename)
     try:
-        return page_text(tree)
+        return page_extract(tree)
     except ValueError:
-        return alto_text(tree)
+        return alto_extract(tree)
+
+
+def text(filename):
+    return extract(filename).text
 
 
 if __name__ == '__main__':