From e1b25a41d1a8f1778ef3d29777851edcfb2424a2 Mon Sep 17 00:00:00 2001
From: Lilian Gasser <gasserli@ethz.ch>
Date: Thu, 28 Feb 2019 10:20:33 +0100
Subject: [PATCH] ugly workaround for Z'graggen
---
src/python/utils_annot.py | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/src/python/utils_annot.py b/src/python/utils_annot.py
index e714180c..6d5905be 100644
--- a/src/python/utils_annot.py
+++ b/src/python/utils_annot.py
@@ -444,6 +444,10 @@ def label_speechstart(XML_new, ind_p, ind_t, text, ind_tl_colon, df_names, list_
# add attribute speech_start to textbox
XML_new[ind_p][ind_t].attrib['text_type'] = 'speech_start'
+ # MP Z'graggen causes problem in xml because of '
+ if 'graggen' in str_name:
+ str_name = 'Zgraggen Max Johann (Basel-Stadt BS)'
+
# add speaker as attribute to first textline
XML_new[ind_p][ind_t][0].attrib['speaker'] = (str_name, str_role, list_uniqueID, str_canton)
@@ -1097,6 +1101,7 @@ def collect_info(XML_root, bln_print=False):
# construct key
key = '_'.join((index_page, speaker, index_start, index_end))
+
# add to dictionary
dict_speeches[key] = (speaker_tpl, complete_text)
--
GitLab