From 351f352cdc7ffe2d6c41675e45c1d75ec84180c8 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Fri, 2 Oct 2020 10:12:44 +0200
Subject: [PATCH] Update Japanese docs and pin for sudachipy

---
 setup.cfg                    | 2 +-
 website/docs/usage/models.md | 9 ++++-----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/setup.cfg b/setup.cfg
index 36ab64bd9..babe5fe8b 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -84,7 +84,7 @@ cuda102 =
     cupy-cuda102>=5.0.0b4,<9.0.0
 # Language tokenizers with external dependencies
 ja =
-    sudachipy>=0.4.5
+    sudachipy>=0.4.9
     sudachidict_core>=20200330
 ko =
     natto-py==0.9.0
diff --git a/website/docs/usage/models.md b/website/docs/usage/models.md
index 5e9bd688f..6792f691c 100644
--- a/website/docs/usage/models.md
+++ b/website/docs/usage/models.md
@@ -199,20 +199,19 @@ nlp.tokenizer.initialize(pkuseg_model="/path/to/pkuseg_model")
 >
 > # Load SudachiPy with split mode B
 > cfg = {"split_mode": "B"}
-> nlp = Japanese(meta={"tokenizer": {"config": cfg}})
+> nlp = Japanese.from_config({"nlp": {"tokenizer": cfg}})
 > ```
 
 The Japanese language class uses
 [SudachiPy](https://github.com/WorksApplications/SudachiPy) for word
 segmentation and part-of-speech tagging. The default Japanese language class and
-the provided Japanese pipelines use SudachiPy split mode `A`. The `meta`
-argument of the `Japanese` language class can be used to configure the split
-mode to `A`, `B` or `C`.
+the provided Japanese pipelines use SudachiPy split mode `A`. The tokenizer
+config can be used to configure the split mode to `A`, `B` or `C`.
 
 <Infobox variant="warning">
 
 If you run into errors related to `sudachipy`, which is currently under active
-development, we suggest downgrading to `sudachipy==0.4.5`, which is the version
+development, we suggest downgrading to `sudachipy==0.4.9`, which is the version
 used for training the current [Japanese pipelines](/models/ja).
 
 </Infobox>