Update the TAG_MAP

spacy/ja/__init__.py

@@ -87,9 +87,6 @@ class JapaneseTagger(object):
         # 1. get raw JP tags
         # 2. add features to tags as necessary for UD
 
-        # TODO: if the text has been tokenized, this info is already available
-        # How to set the data when tokenizing or save it for the tagger to find?
-
         dtokens = detailed_tokens(self.tokenizer, tokens.text)
         rawtags = list(map(resolve_pos, dtokens))
         self.tagger.tag_from_strings(tokens, rawtags)

spacy/ja/tag_map.py

@@ -81,7 +81,8 @@ TAG_MAP = {
     "名詞,普通名詞,助数詞可能,*":{POS: NOUN}, # counter / unit
     "名詞,普通名詞,副詞可能,*":{POS: NOUN},
 
-    "連体詞,*,*,*":{POS: ADJ}, # XXX note この、その etc. should be DET
+    "連体詞,*,*,*":{POS: ADJ}, # XXX this has exceptions based on literal token
     "連体詞,*,*,*,ADJ":{POS: ADJ}, 
+    "連体詞,*,*,*,PRON":{POS: PRON}, 
     "連体詞,*,*,*,DET":{POS: DET}, 
 }