From 3073e3c43799ae3e87079ed8f293f9cb134067b7 Mon Sep 17 00:00:00 2001 From: EvaBardou <bardou@teklia.com> Date: Tue, 23 Jan 2024 12:10:55 +0100 Subject: [PATCH] Nit --- dan/datasets/extract/arkindex.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/dan/datasets/extract/arkindex.py b/dan/datasets/extract/arkindex.py index 93742351..12dff600 100644 --- a/dan/datasets/extract/arkindex.py +++ b/dan/datasets/extract/arkindex.py @@ -106,9 +106,10 @@ class ArkindexExtractor: raise NoTranscriptionError(element.id) transcription = random.choice(transcriptions) + stripped_text = transcription.text.strip() if not self.tokens: - return transcription.text.strip() + return stripped_text entities = get_transcription_entities( transcription.id, @@ -117,7 +118,7 @@ class ArkindexExtractor: ) if not entities.count(): - return transcription.text.strip() + return stripped_text return self.translate( entities_to_xml( -- GitLab