feat(uti): Add some more debug tools

Signed-off-by: Peter Mikus <pmikus@cisco.com>
Change-Id: I1dfe1782334c8415fe5dbcdba24781947076639d

3 files changed, 105 insertions, 0 deletions

diff --git a/resources/tools/dash/app/pal/data/data.py b/resources/tools/dash/app/pal/data/data.py
index 0956333e34..77fd113a9c 100644
--- a/resources/tools/dash/app/pal/data/data.py
+++ b/resources/tools/dash/app/pal/data/data.py
@@ -113,6 +113,48 @@ class Data:
                 f"specified.\n{err}"
             )
 
+    def _get_list_of_files(self,
+        path,
+        last_modified_begin=None,
+        last_modified_end=None,
+        days=None) -> list:
+        """Get list of interested files stored in S3 compatible storage and
+        returns it.
+
+        :param path: S3 prefix (accepts Unix shell-style wildcards)
+            (e.g. s3://bucket/prefix) or list of S3 objects paths
+            (e.g. [s3://bucket/key0, s3://bucket/key1]).
+        :param last_modified_begin: Filter the s3 files by the Last modified
+            date of the object. The filter is applied only after list all s3
+            files.
+        :param last_modified_end: Filter the s3 files by the Last modified date
+            of the object. The filter is applied only after list all s3 files.
+        :param days: Number of days to filter.
+        :type path: Union[str, List[str]]
+        :type last_modified_begin: datetime, optional
+        :type last_modified_end: datetime, optional
+        :type days: integer, optional
+        :returns: List of file names.
+        :rtype: List
+        """
+        if days:
+            last_modified_begin = datetime.now(tz=UTC) - timedelta(days=days)
+        try:
+            file_list = wr.s3.list_objects(
+                path=path,
+                suffix="parquet",
+                last_modified_begin=last_modified_begin,
+                last_modified_end=last_modified_end
+            )
+            if self._debug:
+                logging.info("\n".join(file_list))
+        except NoFilesFound as err:
+            logging.error(f"No parquets found.\n{err}")
+        except EmptyDataFrame as err:
+            logging.error(f"No data.\n{err}")
+
+        return file_list
+
     def _create_dataframe_from_parquet(self,
         path, partition_filter=None,
         columns=None,
@@ -142,12 +184,14 @@ class Data:
             files.
         :param last_modified_end: Filter the s3 files by the Last modified date
             of the object. The filter is applied only after list all s3 files.
+        :param days: Number of days to filter.
         :type path: Union[str, List[str]]
         :type partition_filter: Callable[[Dict[str, str]], bool], optional
         :type columns: List[str], optional
         :type validate_schema: bool, optional
         :type last_modified_begin: datetime, optional
         :type last_modified_end: datetime, optional
+        :type days: integer, optional
         :returns: Pandas DataFrame or None if DataFrame cannot be fetched.
         :rtype: DataFrame
         """
@@ -183,6 +227,16 @@ class Data:
         self._data = df
         return df
 
+    def check_datasets(self, days: int=None):
+        """Read structure from parquet.
+
+        :param days: Number of days back to the past for which the data will be
+            read.
+        :type days: int
+        """
+        self._get_list_of_files(path=self._get_path("trending"), days=days)
+        self._get_list_of_files(path=self._get_path("statistics"), days=days)
+
     def read_stats(self, days: int=None) -> tuple:
         """Read statistics from parquet.
 
diff --git a/resources/tools/dash/app/pal/data/data.yaml b/resources/tools/dash/app/pal/data/data.yaml
index 59533f97a4..396f1b1638 100644
--- a/resources/tools/dash/app/pal/data/data.yaml
+++ b/resources/tools/dash/app/pal/data/data.yaml
@@ -30,6 +30,12 @@ statistics-trending-mrr:
     - passed
     - test_id
     - result_receive_rate_rate_avg
+trending:
+  path: s3://fdio-docs-s3-cloudfront-index/csit/parquet/trending
+  columns:
+    - job
+    - build
+    - start_time
 trending-mrr:
   path: s3://fdio-docs-s3-cloudfront-index/csit/parquet/trending
   columns:
diff --git a/resources/tools/dash/app/pal/debug.py b/resources/tools/dash/app/pal/debug.py
new file mode 100644
index 0000000000..f0543820b1
--- /dev/null
+++ b/resources/tools/dash/app/pal/debug.py
@@ -0,0 +1,45 @@
+# Copyright (c) 2022 Cisco and/or its affiliates.
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at:
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import logging
+
+from data.data import Data
+from utils.constants import Constants as C
+
+
+logging.basicConfig(
+    format=u"%(asctime)s: %(levelname)s: %(message)s",
+    datefmt=u"%Y/%m/%d %H:%M:%S",
+    level=logging.INFO
+)
+
+# Set the time period for data fetch
+if C.TIME_PERIOD is None or C.TIME_PERIOD > C.MAX_TIME_PERIOD:
+    time_period = C.MAX_TIME_PERIOD
+else:
+    time_period = C.TIME_PERIOD
+
+#data_mrr = Data(
+#    data_spec_file=C.DATA_SPEC_FILE,
+#    debug=True
+#).read_trending_mrr(days=time_period)
+#
+#data_ndrpdr = Data(
+#    data_spec_file=C.DATA_SPEC_FILE,
+#    debug=True
+#).read_trending_ndrpdr(days=time_period)
+
+data_list = Data(
+    data_spec_file=C.DATA_SPEC_FILE,
+    debug=True
+).check_datasets(days=time_period)
\ No newline at end of file