From da8e095bd3229d2c0971d1eb44ddd13d69099176 Mon Sep 17 00:00:00 2001
From: xulei2020 <“xulei83@huawei.com”>
Date: Thu, 30 Apr 2020 11:02:47 +0800
Subject: [PATCH] add jieba c++ code

---
 cmake/external_libs/cppjieba.cmake              |  4 ++--
 .../dataset/transforms/text/c_transforms.py     | 17 ++++++++++-------
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/cmake/external_libs/cppjieba.cmake b/cmake/external_libs/cppjieba.cmake
index 80f34f6ade9..7de0e8b4972 100644
--- a/cmake/external_libs/cppjieba.cmake
+++ b/cmake/external_libs/cppjieba.cmake
@@ -3,8 +3,8 @@ set(cppjieba_CFLAGS "-D_FORTIFY_SOURCE=2 -O2")
 mindspore_add_pkg(cppjieba
         VER 5.0.3
         HEAD_ONLY ./
-        URL https://codeload.github.com/yanyiwu/cppjieba/zip/v5.0.3
-        MD5 0dfef44bd32328c221f128b401e1a45c
+        URL https://codeload.github.com/yanyiwu/cppjieba/tar.gz/v5.0.3
+        MD5 b8b3f7a73032c9ce9daafa4f67196c8c
         PATCHES ${CMAKE_SOURCE_DIR}/third_party/patch/cppjieba/cppjieba.patch001)
 include_directories(${cppjieba_INC}include)
 include_directories(${cppjieba_INC}deps)
diff --git a/mindspore/dataset/transforms/text/c_transforms.py b/mindspore/dataset/transforms/text/c_transforms.py
index f17def79bbc..24795edb146 100644
--- a/mindspore/dataset/transforms/text/c_transforms.py
+++ b/mindspore/dataset/transforms/text/c_transforms.py
@@ -33,9 +33,13 @@ class JiebaTokenizer(cde.JiebaTokenizerOp):
     Tokenize Chinese string into words based on dictionary.
 
     Args:
-        mode (Enum):  [Default "MIX"], "MP" model will tokenize with MPSegment algorithm, "HMM" mode will
-            tokenize with Hiddel Markov Model Segment algorithm, "MIX" model will tokenize with a mix of MPSegment and
-            HMMSegment algorithm.
+        hmm_path (str): the dictionary file is used by  HMMSegment algorithm,
+            the dictionary can be obtained on the official website of cppjieba.
+        mp_path(str): the dictionary file is used by MPSegment algorithm,
+            the dictionary can be obtained on the official website of cppjieba.
+        mode (Enum):  [Default "MIX"], "MP" model will tokenize with MPSegment algorithm,
+            "HMM" mode will tokenize with Hiddel Markov Model Segment algorithm,
+            "MIX" model will tokenize with a mix of MPSegment and HMMSegment algorithm.
     """
     @check_jieba_init
     def __init__(self, hmm_path, mp_path, mode=JiebaMode.MIX):
@@ -52,9 +56,8 @@ class JiebaTokenizer(cde.JiebaTokenizerOp):
         Args:
             word(required, string): The word to be added to the JiebaTokenizer instance.
                 The added word will not be written into the built-in dictionary on disk.
-            freq(optional, int): The frequency of the word to be added,
-                The higher the frequency, the better change the word will be tokenized(default None,
-                use default frequency)
+            freq(optional, int): The frequency of the word to be added, The higher the frequency,
+                the better change the word will be tokenized(default None, use default frequency).
         """
         if freq is None:
             super().add_word(word, 0)
@@ -67,7 +70,7 @@ class JiebaTokenizer(cde.JiebaTokenizerOp):
         Add user defined word to JiebaTokenizer's dictionary
         Args:
             user_dict(path/dict):Dictionary to be added, file path or Python dictionary,
-            Python Dict format is {word1:freq1, word2:freq2,...}
+            Python Dict format: {word1:freq1, word2:freq2,...}
             Jieba dictionary format : word(required), freq(optional), such as:
                 word1 freq1
                 word2