From 6f0eeefefd76712e98e458b37e28d28ad19eaff5 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Sat, 26 Sep 2020 23:19:48 +0200
Subject: [PATCH] Try 'context' concept in ChineseTokenizer

---
 spacy/lang/zh/__init__.py | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/spacy/lang/zh/__init__.py b/spacy/lang/zh/__init__.py
index 5d3bd2a96..4b97548bb 100644
--- a/spacy/lang/zh/__init__.py
+++ b/spacy/lang/zh/__init__.py
@@ -71,9 +71,9 @@ class ChineseTokenizer(DummyTokenizer):
         self.pkuseg_user_dict = pkuseg_user_dict
         self.pkuseg_seg = None
         self.jieba_seg = None
-        self.configure_segmenter(segmenter)
+        self.configure_segmenter(segmenter, _context=nlp._context)
 
-    def configure_segmenter(self, segmenter: str):
+    def configure_segmenter(self, segmenter: str, *, _context: str=""):
         if segmenter not in Segmenter.values():
             warn_msg = Warnings.W103.format(
                 lang="Chinese",
@@ -84,11 +84,14 @@ class ChineseTokenizer(DummyTokenizer):
             warnings.warn(warn_msg)
             self.segmenter = Segmenter.char
         self.jieba_seg = try_jieba_import(self.segmenter)
-        self.pkuseg_seg = try_pkuseg_import(
-            self.segmenter,
-            pkuseg_model=self.pkuseg_model,
-            pkuseg_user_dict=self.pkuseg_user_dict,
-        )
+        if _context == "loading":
+            self.pkuseg_seg = None
+        else:
+            self.pkuseg_seg = try_pkuseg_import(
+                self.segmenter,
+                pkuseg_model=self.pkuseg_model,
+                pkuseg_user_dict=self.pkuseg_user_dict
+            )
 
     def __call__(self, text: str) -> Doc:
         if self.segmenter == Segmenter.jieba: