tgedr-dataops 0.0.34__py3-none-any.whl → 0.0.37__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- tgedr/dataops/source/pd_df_s3_source.py +27 -2
- tgedr/dataops/source/s3_file_extended_source.py +39 -0
- tgedr/dataops/source/s3_file_source.py +0 -15
- tgedr/dataops/store/s3_single_partition_parquet.py +1 -1
- tgedr/dataops/validation/pyspark.py +10 -0
- {tgedr_dataops-0.0.34.dist-info → tgedr_dataops-0.0.37.dist-info}/METADATA +2 -1
- {tgedr_dataops-0.0.34.dist-info → tgedr_dataops-0.0.37.dist-info}/RECORD +10 -8
- {tgedr_dataops-0.0.34.dist-info → tgedr_dataops-0.0.37.dist-info}/LICENSE +0 -0
- {tgedr_dataops-0.0.34.dist-info → tgedr_dataops-0.0.37.dist-info}/WHEEL +0 -0
- {tgedr_dataops-0.0.34.dist-info → tgedr_dataops-0.0.37.dist-info}/top_level.txt +0 -0
|
@@ -19,6 +19,7 @@ class PdDfS3Source(AbstractS3FileSource):
|
|
|
19
19
|
CONTEXT_KEY_COLUMN_NAMES = "column_names"
|
|
20
20
|
CONTEXT_KEY_SCHEMA_TYPES = "schema_types"
|
|
21
21
|
DEFAULT_FORMAT = "csv"
|
|
22
|
+
FORMATS = ["csv", "xlsx"]
|
|
22
23
|
DEFAULT_SEPARATOR = ","
|
|
23
24
|
|
|
24
25
|
def __init__(self, config: Optional[Dict[str, Any]] = None):
|
|
@@ -33,6 +34,23 @@ class PdDfS3Source(AbstractS3FileSource):
|
|
|
33
34
|
if self.CONTEXT_KEY_URL not in context:
|
|
34
35
|
raise SourceException(f"you must provide context for {self.CONTEXT_KEY_URL}")
|
|
35
36
|
|
|
37
|
+
format: str = self.DEFAULT_FORMAT
|
|
38
|
+
if self.CONTEXT_KEY_FILE_FORMAT in context:
|
|
39
|
+
format = context[self.CONTEXT_KEY_FILE_FORMAT]
|
|
40
|
+
if format not in self.FORMATS:
|
|
41
|
+
raise SourceException(f"[get] invalid format: {format}")
|
|
42
|
+
|
|
43
|
+
if "csv" == format:
|
|
44
|
+
result = self.__read_csv(context=context)
|
|
45
|
+
else:
|
|
46
|
+
result = self.__read_excel(context=context)
|
|
47
|
+
|
|
48
|
+
logger.info(f"[get|out] => {result}")
|
|
49
|
+
return result
|
|
50
|
+
|
|
51
|
+
def __read_csv(self, context: Optional[Dict[str, Any]] = None) -> pd.DataFrame:
|
|
52
|
+
logger.info(f"[__read_csv|in] ({context})")
|
|
53
|
+
|
|
36
54
|
protocol, bucket, key = process_s3_url(context[self.CONTEXT_KEY_URL])
|
|
37
55
|
|
|
38
56
|
obj = self._client.get_object(Bucket=bucket, Key=key)
|
|
@@ -45,7 +63,14 @@ class PdDfS3Source(AbstractS3FileSource):
|
|
|
45
63
|
self.DEFAULT_SEPARATOR if self.CONTEXT_KEY_SEPARATOR not in context else context[self.CONTEXT_KEY_SEPARATOR]
|
|
46
64
|
)
|
|
47
65
|
|
|
48
|
-
result = pd.read_csv(StringIO(data), sep=sep, header=header, names=names, dtype=dtype)
|
|
66
|
+
result: pd.DataFrame = pd.read_csv(StringIO(data), sep=sep, header=header, names=names, dtype=dtype)
|
|
49
67
|
|
|
50
|
-
logger.info(f"[
|
|
68
|
+
logger.info(f"[__read_csv|out] => {result}")
|
|
69
|
+
return result
|
|
70
|
+
|
|
71
|
+
def __read_excel(self, context: Optional[Dict[str, Any]] = None) -> pd.DataFrame:
|
|
72
|
+
logger.info(f"[__read_excel|in] ({context})")
|
|
73
|
+
src = context[self.CONTEXT_KEY_URL]
|
|
74
|
+
result: pd.DataFrame = pd.read_excel(src, engine="openpyxl")
|
|
75
|
+
logger.info(f"[__read_excel|out] => {result}")
|
|
51
76
|
return result
|
|
@@ -0,0 +1,39 @@
|
|
|
1
|
+
import logging
|
|
2
|
+
from typing import Any, Dict, Optional
|
|
3
|
+
|
|
4
|
+
from tgedr.dataops.source.s3_file_source import S3FileSource
|
|
5
|
+
from tgedr.dataops.source.source import SourceException
|
|
6
|
+
from tgedr.dataops.commons.utils_fs import process_s3_path
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
logger = logging.getLogger(__name__)
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
class S3FileExtendedSource(S3FileSource):
|
|
13
|
+
"""class used to retrieve objects/files from s3 bucket to local fs location"""
|
|
14
|
+
|
|
15
|
+
METADATA_KEYS = ["LastModified", "ContentLength", "ETag", "VersionId", "ContentType"]
|
|
16
|
+
|
|
17
|
+
def __init__(self, config: Optional[Dict[str, Any]] = None):
|
|
18
|
+
super().__init__(config=config)
|
|
19
|
+
|
|
20
|
+
def get_metadata(self, context: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
|
|
21
|
+
logger.info(f"[get_metadata|in] ({context})")
|
|
22
|
+
|
|
23
|
+
result: Dict[str, Any] = {}
|
|
24
|
+
if self.CONTEXT_KEY_SOURCE not in context:
|
|
25
|
+
raise SourceException(f"you must provide context for {self.CONTEXT_KEY_SOURCE}")
|
|
26
|
+
|
|
27
|
+
bucket, key = process_s3_path(context[self.CONTEXT_KEY_SOURCE])
|
|
28
|
+
|
|
29
|
+
o = self._client.head_object(Bucket=bucket, Key=key)
|
|
30
|
+
|
|
31
|
+
for key in list(o.keys()):
|
|
32
|
+
if key in self.METADATA_KEYS:
|
|
33
|
+
if key == "LastModified":
|
|
34
|
+
result[key] = int(o[key].timestamp())
|
|
35
|
+
else:
|
|
36
|
+
result[key] = o[key]
|
|
37
|
+
|
|
38
|
+
logger.info(f"[get_metadata|out] => result len: {result}")
|
|
39
|
+
return result
|
|
@@ -22,21 +22,6 @@ class S3FileSource(Source, S3Connector):
|
|
|
22
22
|
Source.__init__(self, config=config)
|
|
23
23
|
S3Connector.__init__(self)
|
|
24
24
|
|
|
25
|
-
def __derive_local_file(self, target: str, isdir: bool, file: str):
|
|
26
|
-
logger.debug(f"[__derive_local_file|in] ({target}, {isdir}, {file})")
|
|
27
|
-
|
|
28
|
-
if isdir:
|
|
29
|
-
result = os.path.join(target, file)
|
|
30
|
-
basedir = os.path.dirname(result)
|
|
31
|
-
if not os.path.exists(basedir):
|
|
32
|
-
logger.debug(f"[__derive_local_file] creating folder: {basedir}")
|
|
33
|
-
os.mkdir(basedir)
|
|
34
|
-
else:
|
|
35
|
-
result = target
|
|
36
|
-
|
|
37
|
-
logger.debug(f"[__derive_local_file|out] => {result}")
|
|
38
|
-
return result
|
|
39
|
-
|
|
40
25
|
def list(self, context: Optional[Dict[str, Any]] = None) -> List[str]:
|
|
41
26
|
logger.info(f"[list|in] ({context})")
|
|
42
27
|
|
|
@@ -6,7 +6,7 @@ import pandas as pd
|
|
|
6
6
|
import pyarrow as pa
|
|
7
7
|
|
|
8
8
|
from tgedr.dataops.store.fs_single_partition_parquet import FsSinglePartitionParquetStore
|
|
9
|
-
from
|
|
9
|
+
from tgedr.dataops.commons.utils_fs import remove_s3_protocol
|
|
10
10
|
|
|
11
11
|
|
|
12
12
|
logger = logging.getLogger(__name__)
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
from typing import Any
|
|
2
|
+
from great_expectations.dataset.dataset import Dataset
|
|
3
|
+
|
|
4
|
+
from tgedr.dataops.validation.abs import DataValidation
|
|
5
|
+
from great_expectations.dataset.sparkdf_dataset import SparkDFDataset
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class Impl(DataValidation):
|
|
9
|
+
def _get_dataset(self, df: Any) -> Dataset:
|
|
10
|
+
return SparkDFDataset(df)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: tgedr-dataops
|
|
3
|
-
Version: 0.0.
|
|
3
|
+
Version: 0.0.37
|
|
4
4
|
Summary: data operations related code
|
|
5
5
|
Home-page: https://github.com/jtviegas-sandbox/dataops
|
|
6
6
|
Author: joao tiago viegas
|
|
@@ -17,4 +17,5 @@ Requires-Dist: s3fs ==2024.5.0
|
|
|
17
17
|
Requires-Dist: boto3 ==1.34.106
|
|
18
18
|
Requires-Dist: great-expectations ==0.18.10
|
|
19
19
|
Requires-Dist: deltalake ~=0.16.4
|
|
20
|
+
Requires-Dist: openpyxl ==3.1.2
|
|
20
21
|
|
|
@@ -17,20 +17,22 @@ tgedr/dataops/source/abstract_s3_file_source.py,sha256=AMnTWxs57Jni46jz5PvrZTRjd
|
|
|
17
17
|
tgedr/dataops/source/delta_table_source.py,sha256=tXeJCM-QhssztEpyKGzb6zcM1AlaUwV1Y5d2RHCiOTU,1653
|
|
18
18
|
tgedr/dataops/source/local_delta_table.py,sha256=Z9413skOSsNGfSNeBs-ETVXQJcW4bhS3MYmCwySo9Tc,1545
|
|
19
19
|
tgedr/dataops/source/local_fs_file_source.py,sha256=wihK_wVV6xb8AlkCmZHSRlRmqqm6w9Aq-PI0oOnhn_k,2570
|
|
20
|
-
tgedr/dataops/source/pd_df_s3_source.py,sha256=
|
|
20
|
+
tgedr/dataops/source/pd_df_s3_source.py,sha256=Bfnj363MZtmMJB4W32DKEaYYG0v7NeG-m66C5i8bxsc,3103
|
|
21
21
|
tgedr/dataops/source/s3_delta_table.py,sha256=d_FoFDNogjZifRQv8V2OmTXbPYymx9QaQcW15uX34pI,2974
|
|
22
22
|
tgedr/dataops/source/s3_file_copy.py,sha256=DbHvstAqi23cywoG6nHpQxvzerrnepApOsv6zsELYNQ,3930
|
|
23
|
-
tgedr/dataops/source/
|
|
23
|
+
tgedr/dataops/source/s3_file_extended_source.py,sha256=B6m84DWV45E1V3XsLkHARp9YVNvmsDi54ikd2__9q5Q,1384
|
|
24
|
+
tgedr/dataops/source/s3_file_source.py,sha256=ayQ-gPxARFc1xINFOM0_hQFUn6odpts_uFaDZYs7RC4,3520
|
|
24
25
|
tgedr/dataops/source/source.py,sha256=REeqluMGLMjoDWtdZthzUYkmVeHemSV7t9wjc6eTpJE,1350
|
|
25
26
|
tgedr/dataops/store/fs_single_partition_parquet.py,sha256=CR3406emhxn33jjObnMotXEmZGfh4Iu5Ygv30FvkY6Y,9695
|
|
26
27
|
tgedr/dataops/store/local_fs_single_partition_parquet.py,sha256=N_I96fqxQAp2fWBngoDci3aR1-kcmkWjIVRD0nUi07U,683
|
|
27
|
-
tgedr/dataops/store/s3_single_partition_parquet.py,sha256=
|
|
28
|
+
tgedr/dataops/store/s3_single_partition_parquet.py,sha256=2vSyLb-mZ2mAbRhaDoCcsOEnKzQ30AsUYTlqhKQCroc,3249
|
|
28
29
|
tgedr/dataops/store/spark_delta.py,sha256=AHqIKDi9axOKpMJHt4AiBGX8V2mFV_7vNPRpaw37rDY,15101
|
|
29
30
|
tgedr/dataops/store/store.py,sha256=uAuR7MWVdKRaisQ69rFqliLnJrsgpTzbsOh7uPmLSlI,1315
|
|
30
31
|
tgedr/dataops/validation/abs.py,sha256=84HGUuh6k_uG-ON0bauR4lDBTfUeI3GmxOiWsMkTu3E,1521
|
|
31
32
|
tgedr/dataops/validation/pandas.py,sha256=Vfr38f3txbTy098ufPUcRsCgrYu47Rg35upZ9IXcLSk,315
|
|
32
|
-
|
|
33
|
-
tgedr_dataops-0.0.
|
|
34
|
-
tgedr_dataops-0.0.
|
|
35
|
-
tgedr_dataops-0.0.
|
|
36
|
-
tgedr_dataops-0.0.
|
|
33
|
+
tgedr/dataops/validation/pyspark.py,sha256=4OEnA21_vSwB5HjaD5KZdfIjBnTn3KUAqvVGHnY-zNI,317
|
|
34
|
+
tgedr_dataops-0.0.37.dist-info/LICENSE,sha256=awOCsWJ58m_2kBQwBUGWejVqZm6wuRtCL2hi9rfa0X4,1211
|
|
35
|
+
tgedr_dataops-0.0.37.dist-info/METADATA,sha256=OGYBz2HJOKVIl5NlRqzjqjG4zHXmgFA2sErmeFCIAYk,639
|
|
36
|
+
tgedr_dataops-0.0.37.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
|
|
37
|
+
tgedr_dataops-0.0.37.dist-info/top_level.txt,sha256=acugNvvENatFXbPxKQD9YI5PpzzehbAwyY1keiIkR7I,6
|
|
38
|
+
tgedr_dataops-0.0.37.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|