0% found this document useful (0 votes)
9 views2 pages

BCT We Inc MX BCT Hs Idc HDR TNDR Hs Config

The document describes the workflow tasks for extracting incremental data from the IDC_HEADER_TENDER table from BCT for a specific interval. The workflow extracts the data from MSSQL to lake storage on GCP, loads it from lake storage to the raw layer and then to the catalog layer in Hive, archives the data, and creates a done file upon completion.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
9 views2 pages

BCT We Inc MX BCT Hs Idc HDR TNDR Hs Config

The document describes the workflow tasks for extracting incremental data from the IDC_HEADER_TENDER table from BCT for a specific interval. The workflow extracts the data from MSSQL to lake storage on GCP, loads it from lake storage to the raw layer and then to the catalog layer in Hive, archives the data, and creates a done file upon completion.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

#Walmart de México

# Autor : Krissel Mejia <Bluetab>


# UserID : vn52l97
# Creación : 04-Diciembre-2023
# ver 1.0 : 04-Diciembre-2023
#------------------------------------------------------------#
# Propósito : Extración delta de 30 días de la tabla de IDC_HEADER_TENDER de BCT
para un intervalo especifico.
# Proyecto: Datamesh
#------------------------------------------------------------#
---
name: "bct-we-inc-mx_bct_hs-idc_hdr_tndr-hs"
version: "1.0"
cluster_name: "bct-we-inc-mx-bct-hs-master-extraction"
cluster_profile: "medium"
data_group: "core_hs"
path: "incremental/mx_bct_hs/we/idc_hdr_tndr/"
properties_file: "inc_mx_bct_hs_idc_hdr_tndr_properties.yaml"

# Workflow Tasks
tasks:

- name: "start"
type: "START"
description: ""
long_name: "start"
curr_id: 1
properties: {}

- name: "bct_get_days"
type: "SCRIPT"
description: "execute dtmsh_get_bct_dates_idc_hdr_tndr to get extraction dates
for bct incremental process"
long_name:
"$config_bucket/scripts/dtmsh_general_scripts/bct/idc_hdr_tndr/dtmsh_get_bct_dates_
idc_hdr_tndr.sh"
curr_id: 2
parents:
- "start"
properties:
params:
"target_schema=$target_schema,target_table=$target_table,process_type=$process_type
,division_code=$division_code"
script_file: "dtmsh_get_bct_dates_idc_hdr_tndr.sh"
script_location:
"$config_bucket/scripts/dtmsh_general_scripts/bct/idc_hdr_tndr/"

- name: "bct_mssql_to_lakestorage"
type: "SQOOP"
description: "Sqoop Load to GCP"
long_name: "01_inc_mx_bct_hs_idc_hdr_tndr_sql_to_gcs"
curr_id: 3
parents:
- "bct_get_days"
properties_file: "01_inc_mx_bct_hs_idc_hdr_tndr_sql_to_gcs.yaml"

- name: "bct_lakestorage_to_raw"
type: "HIVE"
description: "Hive Yaml Raw Load"
long_name: "02_inc_mx_bct_hs_idc_hdr_tndr_gcs_to_raw"
curr_id: 4
parents:
- "bct_mssql_to_lakestorage"
properties_file: "02_inc_mx_bct_hs_idc_hdr_tndr_gcs_to_raw.yaml"

- name: "bct_raw_to_ctg"
type: "HIVE"
description: "Hive Yaml Ctg Load"
long_name: "03_inc_mx_bct_hs_idc_hdr_tndr_raw_to_ctg"
curr_id: 5
parents:
- "bct_lakestorage_to_raw"
properties_file: "03_inc_mx_bct_hs_idc_hdr_tndr_raw_to_ctg.yaml"

- name: "bct_archive"
type: "SCRIPT"
description: "execute dtmsh_gcp_utils_idc_hdr_tndr to copy data to archive
folder."
long_name:
"$config_bucket/scripts/dtmsh_general_scripts/bct/idc_hdr_tndr/dtmsh_gcp_utils_idc_
hdr_tndr.sh"
curr_id: 6
parents:
- "bct_raw_to_ctg"
properties:
params:
"operation_type=6,archive_flag=$archive_flag,delete_flag=$delete_flag,source_bucket
=$raw_bucket,target_bucket=$archive_bucket,source_path_object=landing/$load_type/
$target_schema/$target_table/$division_code/$end_date,target_path_object=landing/
archive/$load_type/$target_schema/$target_table/$division_code/"
script_file: "dtmsh_gcp_utils_idc_hdr_tndr.sh"
script_location:
"$config_bucket/scripts/dtmsh_general_scripts/bct/idc_hdr_tndr/"

- name: "end"
type: "END"
description: "end"
long_name: "end"
curr_id: 7
parents:
- "bct_archive"
properties:
done_file_path: "$done_bucket/$target_schema/$target_table/$geo_region_cd"
done_file_name: "$target_schema_$target_table_YYYYMMddHHmmss.done"

You might also like