From 5ac1f198db9287cd5c2becadc5ceeb29a180ba4d Mon Sep 17 00:00:00 2001
From: shenwei41 <shenwei41@huawei.com>
Date: Thu, 12 Nov 2020 15:42:45 +0800
Subject: [PATCH] Add API info about Cases not supported by Windows

---
 mindspore/dataset/text/transforms.py | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/mindspore/dataset/text/transforms.py b/mindspore/dataset/text/transforms.py
index 7c1990b5c4..56ceb736b0 100644
--- a/mindspore/dataset/text/transforms.py
+++ b/mindspore/dataset/text/transforms.py
@@ -417,6 +417,9 @@ if platform.system().lower() != 'windows':
         """
         Tokenize a scalar tensor of UTF-8 string on ICU4C defined whitespaces, such as: ' ', '\\\\t', '\\\\r', '\\\\n'.
 
+        Note:
+            The WhitespaceTokenizer is not supported on windows platform yet.
+
         Args:
             with_offsets (bool, optional): If or not output offsets of tokens (default=False).
 
@@ -445,6 +448,9 @@ if platform.system().lower() != 'windows':
         """
         Tokenize a scalar tensor of UTF-8 string on Unicode script boundaries.
 
+        Note:
+            The UnicodeScriptTokenizer is not supported on windows platform yet.
+
         Args:
             keep_whitespace (bool, optional): If or not emit whitespace tokens (default=False).
             with_offsets (bool, optional): If or not output offsets of tokens (default=False).
@@ -475,6 +481,9 @@ if platform.system().lower() != 'windows':
         """
         Apply case fold operation on utf-8 string tensor.
 
+        Note:
+            The CaseFold is not supported on windows platform yet.
+
         Examples:
             >>> import mindspore.dataset.text as text
             >>>
@@ -495,6 +504,9 @@ if platform.system().lower() != 'windows':
         """
         Apply normalize operation on utf-8 string tensor.
 
+        Note:
+            The NormalizeUTF8 is not supported on windows platform yet.
+
         Args:
             normalize_form (NormalizeForm, optional): Valid values can be any of [NormalizeForm.NONE,
                 NormalizeForm.NFC, NormalizeForm.NFKC, NormalizeForm.NFD,
@@ -528,6 +540,9 @@ if platform.system().lower() != 'windows':
 
         See http://userguide.icu-project.org/strings/regexp for support regex pattern.
 
+        Note:
+            The RegexReplace is not supported on windows platform yet.
+
         Args:
             pattern (str): the regex expression patterns.
             replace (str): the string to replace matched element.
@@ -556,6 +571,9 @@ if platform.system().lower() != 'windows':
 
         See http://userguide.icu-project.org/strings/regexp for support regex pattern.
 
+        Note:
+            The RegexTokenizer is not supported on windows platform yet.
+
         Args:
             delim_pattern (str): The pattern of regex delimiters.
                 The original string will be split by matched elements.
@@ -591,6 +609,9 @@ if platform.system().lower() != 'windows':
         """
         Tokenize a scalar tensor of UTF-8 string by specific rules.
 
+        Note:
+            The BasicTokenizer is not supported on windows platform yet.
+
         Args:
             lower_case (bool, optional): If True, apply CaseFold, NormalizeUTF8(NFD mode), RegexReplace operation
                 on input text to fold the text to lower case and strip accents characters. If False, only apply
@@ -644,6 +665,9 @@ if platform.system().lower() != 'windows':
         """
         Tokenizer used for Bert text process.
 
+        Note:
+            The BertTokenizer is not supported on windows platform yet.
+
         Args:
             vocab (Vocab): A vocabulary object.
             suffix_indicator (str, optional): Used to show that the subword is the last part of a word (default='##').