From 14d9007efd2ca457c6e6549d5599e460e198904c Mon Sep 17 00:00:00 2001 From: himkt Date: Tue, 19 Jun 2018 17:20:57 +0900 Subject: [PATCH] fix wrong indexing (#2416) * fix wrong indexing * add agreement --- .github/contributors/himkt.md | 2 +- spacy/lang/ja/__init__.py | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/.github/contributors/himkt.md b/.github/contributors/himkt.md index d1b60288b..e21aafda5 100644 --- a/.github/contributors/himkt.md +++ b/.github/contributors/himkt.md @@ -101,6 +101,6 @@ mark both statements: | Name | himkt | | Company name (if applicable) | University of Tsukuba | | Title or role (if applicable) | | -| Date | 2018-06-08 | +| Date | 2018-06-07 | | GitHub username | himkt | | Website (optional) | https://himkt.github.io | diff --git a/spacy/lang/ja/__init__.py b/spacy/lang/ja/__init__.py index 1286469de..08b9de758 100644 --- a/spacy/lang/ja/__init__.py +++ b/spacy/lang/ja/__init__.py @@ -60,9 +60,8 @@ def detailed_tokens(tokenizer, text): parts = node.feature.split(',') pos = ','.join(parts[0:4]) - if len(parts) > 6: + if len(parts) > 7: # this information is only available for words in the tokenizer dictionary - reading = parts[6] base = parts[7] words.append( ShortUnitWord(surface, base, pos) )