From 9a5003d5c8b03c9ae53f32d7b3fc987726cd5617 Mon Sep 17 00:00:00 2001
From: Gavriel Loria <gtloria@protonmail.com>
Date: Wed, 16 Jan 2019 07:44:16 -0500
Subject: [PATCH] iob converter: add 'exception' for error 'too many values'
 (#3159)

* added contributor agreement

* issue #3128 throw exception on bad IOB/2 formatting

* Update spacy/cli/converters/iob2json.py with ValueError

Co-Authored-By: gavrieltal <gtloria@protonmail.com>
---
 spacy/cli/converters/iob2json.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/spacy/cli/converters/iob2json.py b/spacy/cli/converters/iob2json.py
index 3f38a6e25..e159bfef9 100644
--- a/spacy/cli/converters/iob2json.py
+++ b/spacy/cli/converters/iob2json.py
@@ -35,9 +35,11 @@ def read_iob(raw_sents):
         tokens = [re.split('[^\w\-]', line.strip())]
         if len(tokens[0]) == 3:
             words, pos, iob = zip(*tokens)
-        else:
+        elif len(tokens[0]) == 2:
             words, iob = zip(*tokens)
             pos = ['-'] * len(words)
+        else:
+            raise ValueError('The iob/iob2 file is not formatted correctly. Try checking whitespace and delimiters.')
         biluo = iob_to_biluo(iob)
         sentences.append([
             {'orth': w, 'tag': p, 'ner': ent}