From bf87b1d1fb4ee0eda62a0f3b65ee934239397402 Mon Sep 17 00:00:00 2001
From: qianlong <qianlong3@huawei.com>
Date: Sat, 25 Jul 2020 18:05:53 +0800
Subject: [PATCH] fix cache op core dump

---
 .../dataset/engine/datasetops/dataset_op.cc   |  3 ++
 tests/ut/python/dataset/test_cache_map.py     | 39 ++++++++++++++++---
 2 files changed, 36 insertions(+), 6 deletions(-)

diff --git a/mindspore/ccsrc/minddata/dataset/engine/datasetops/dataset_op.cc b/mindspore/ccsrc/minddata/dataset/engine/datasetops/dataset_op.cc
index dd53e0527d..0e0db663d0 100644
--- a/mindspore/ccsrc/minddata/dataset/engine/datasetops/dataset_op.cc
+++ b/mindspore/ccsrc/minddata/dataset/engine/datasetops/dataset_op.cc
@@ -392,6 +392,9 @@ uint32_t DatasetOp::GenerateCRC(const std::shared_ptr<DatasetOp> &op) {
   ss_str = std::regex_replace(ss_str, std::regex("Num workers.*\n"), "");
   ss_str = std::regex_replace(ss_str, std::regex("\\[workers.*\\]"), "");
 
+  // Filter out Number of rows when generating the check sum
+  ss_str = std::regex_replace(ss_str, std::regex("Number of rows.*\n"), "");
+
   // Filter out the Operator control flags field when generating the check sum
   ss_str = std::regex_replace(ss_str, std::regex("Operator control flags.*\n"), "");
 
diff --git a/tests/ut/python/dataset/test_cache_map.py b/tests/ut/python/dataset/test_cache_map.py
index 5de969db6d..72f33be576 100644
--- a/tests/ut/python/dataset/test_cache_map.py
+++ b/tests/ut/python/dataset/test_cache_map.py
@@ -104,11 +104,11 @@ def test_cache_map_basic3():
     decode_op = c_vision.Decode()
     ds1 = ds1.repeat(4)
     ds1 = ds1.map(input_columns=["image"], operations=decode_op, cache=some_cache)
-    print("ds1.dataset_size is ", ds1.get_dataset_size())
+    logger.info("ds1.dataset_size is ", ds1.get_dataset_size())
 
     num_iter = 0
     for _ in ds1.create_dict_iterator():
-        print("get data from dataset")
+        logger.info("get data from dataset")
         num_iter += 1
 
     logger.info("Number of data in ds1: {} ".format(num_iter))
@@ -116,6 +116,31 @@ def test_cache_map_basic3():
     logger.info('test_cache_basic3 Ended.\n')
 
 
+def test_cache_map_basic4():
+  """
+  Test different rows result in core dump
+  """
+  logger.info("Test cache basic 4")
+  some_cache = ds.DatasetCache(session_id=1, size=0, spilling=True)
+
+  # This DATA_DIR only has 2 images in it
+  ds1 = ds.ImageFolderDatasetV2(dataset_dir=DATA_DIR, cache=some_cache)
+  decode_op = c_vision.Decode()
+  ds1 = ds1.repeat(4)
+  ds1 = ds1.map(input_columns=["image"], operations=decode_op)
+  logger.info("ds1.dataset_size is ", ds1.get_dataset_size())
+  shape = ds1.output_shapes()
+
+  num_iter = 0
+  for _ in ds1.create_dict_iterator():
+      logger.info("get data from dataset")
+      num_iter += 1
+
+  logger.info("Number of data in ds1: {} ".format(num_iter))
+  assert num_iter == 8
+  logger.info('test_cache_basic3 Ended.\n')
+
+
 def test_cache_map_failure1():
     """
     Test nested cache (failure)
@@ -154,10 +179,12 @@ def test_cache_map_failure1():
 
 if __name__ == '__main__':
     test_cache_map_basic1()
-    print("test_cache_map_basic1 success.")
+    logger.info("test_cache_map_basic1 success.")
     test_cache_map_basic2()
-    print("test_cache_map_basic2 success.")
+    logger.info("test_cache_map_basic2 success.")
     test_cache_map_basic3()
-    print("test_cache_map_basic3 success.")
+    logger.info("test_cache_map_basic3 success.")
+    test_cache_map_basic4()
+    logger.info("test_cache_map_basic3 success.")
     test_cache_map_failure1()
-    print("test_cache_map_failure1 success.")
+    logger.info("test_cache_map_failure1 success.")