Remove Japanese support because of UIF issue

dataiku · Sep 30, 2020 · 987b449 · 987b449
1 parent 38552ef
commit 987b449
Show file tree

Hide file tree

Showing 5 changed files with 3 additions and 50,008 deletions.
diff --git a/code-env/python/spec/requirements.txt b/code-env/python/spec/requirements.txt
@@ -4,8 +4,6 @@ symspellpy==6.7.0
 spacy==2.3.2
 spacy-lookups-data==0.3.2
 jieba==0.42.1
-SudachiPy==0.4.9 
-SudachiDict-core==20200722
 natto-py==0.9.2
 pymorphy2==0.9.1
 pymorphy2-dicts==2.4.393442.3710985

diff --git a/custom-recipes/nlp-preparation-spell-checker/recipe.json b/custom-recipes/nlp-preparation-spell-checker/recipe.json
@@ -1,7 +1,7 @@
 {
     "meta": {
         "label": "Spell Checking",
-        "description": "Identify and correct misspellings in a text column for 36 languages",
+        "description": "Identify and correct misspellings in a text column for 35 languages",
         "icon": "icon-strikethrough",
         "displayOrderRank": 2
     },

diff --git a/plugin.json b/plugin.json
@@ -1,6 +1,6 @@
 {
     "id": "nlp-preparation",
-    "version": "1.0.0",
+    "version": "1.0.1",
     "meta": {
         "label": "Text preparation",
         "category": "Natural Language Processing",

diff --git a/python-lib/language_dict.py b/python-lib/language_dict.py
@@ -166,7 +166,6 @@
     "id": "Indonesian",
     "is": "Icelandic",
     "it": "Italian",
-    "ja": "Japanese",
     "lt": "Lithuanian",
     "lv": "Latvian",
     "nl": "Dutch",
@@ -216,7 +215,6 @@
     "id": "Indonesian",
     "is": "Icelandic",
     "it": "Italian",
-    "ja": "Japanese",
     "kn": "Kannada",
     "lb": "Luxembourgish",
     "lt": "Lithuanian",
@@ -249,7 +247,7 @@
 """dict: Languages supported by spaCy: https://spacy.io/usage/models#languages
 
 Dictionary with ISO 639-1 language code (key) and language name (value).
-Korean and Ukrainian not included because they require system-level package installations
+Japanese, Korean and Ukrainian not included because they require system-level operations
 """
 
 SPACY_LANGUAGE_MODELS = {