From ca17be329ed886cb0f4c83a2823bd394a11b6859 Mon Sep 17 00:00:00 2001 From: Lilian Gasser <gasserli@ethz.ch> Date: Tue, 22 Jan 2019 15:04:49 +0100 Subject: [PATCH] WIP: fix bug in splitting speaker from text on first line --- data/lists/not_names.txt | 1 + src/python/utils_annot.py | 2 ++ 2 files changed, 3 insertions(+) diff --git a/data/lists/not_names.txt b/data/lists/not_names.txt index de9a8b58..bbd1d59d 100644 --- a/data/lists/not_names.txt +++ b/data/lists/not_names.txt @@ -2,6 +2,7 @@ Alinea Alter Ari Art +besser bietet Fällen fasse diff --git a/src/python/utils_annot.py b/src/python/utils_annot.py index 5d6a854f..e251f692 100644 --- a/src/python/utils_annot.py +++ b/src/python/utils_annot.py @@ -300,8 +300,10 @@ def label_speechstart(XML_new, ind_p, ind_t, text, ind_tl_colon, df_names, list_ thattext = XML_new[ind_p][ind_t][0].text colon_index = thattext.index(':') + print(thattext) # get last font information of thattext fontstart = re.findall('\[font.*?\]', thattext)[-1] + print(fontstart) try: # write speaker to first line -- GitLab