admin/mars
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'develop'

Browse Source
This commit is contained in:
Grzegorz Michalski
2026-02-11 21:32:47 +01:00
parent 26aba08759 f8213b76ab
commit f4e9fb9cb2
27 changed files with 8496 additions and 141 deletions
Download Patch File Download Diff File Expand all files Collapse all files

421
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/new_version/DATA_EXPORTER.pkb
View File

@@ -597,12 +597,14 @@ AS
----------------------------------------------------------------------------------------------------
PROCEDURE EXPORT_TABLE_DATA (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pTemplateTableName IN VARCHAR2 default NULL,
pRegisterExport IN BOOLEAN default FALSE,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
)
IS
-- Type definition for key values
@@ -621,7 +623,14 @@ AS
vBucketUri VARCHAR2(4000);
vProcessedColumnList VARCHAR2(32767);
vCurrentCol VARCHAR2(128);
vAllColumnsList VARCHAR2(32767);
-- Variables for file registration (when pRegisterExport=TRUE)
vConfigKey NUMBER;
vSourceKey VARCHAR2(100);
vTableId VARCHAR2(100);
vSlashPos1 NUMBER;
vSlashPos2 NUMBER;
vSourceFileReceivedKey NUMBER;
BEGIN
vParameters := ENV_MANAGER.FORMAT_PARAMETERS(SYS.ODCIVARCHAR2LIST( 'pSchemaName => '''||nvl(pSchemaName, 'NULL')||''''
@@ -629,6 +638,8 @@ AS
,'pKeyColumnName => '''||nvl(pKeyColumnName, 'NULL')||''''
,'pBucketArea => '''||nvl(pBucketArea, 'NULL')||''''
,'pFolderName => '''||nvl(pFolderName, 'NULL')||''''
,'pTemplateTableName => '''||nvl(pTemplateTableName, 'NULL')||''''
,'pRegisterExport => '''||CASE WHEN pRegisterExport THEN 'TRUE' ELSE 'FALSE' END||''''
,'pCredentialName => '''||nvl(pCredentialName, 'NULL')||''''
));
ENV_MANAGER.LOG_PROCESS_EVENT('Start','INFO', vParameters);
@@ -670,20 +681,85 @@ AS
AND column_name = vKeyColumnName
AND owner = vSchemaName;
-- Build list of all columns for the table (including key column for aliasing)
SELECT LISTAGG(column_name, ', ') WITHIN GROUP (ORDER BY column_id)
INTO vAllColumnsList
FROM all_tab_columns
WHERE table_name = vTableName
AND owner = vSchemaName;
-- Validate template table if provided
IF pTemplateTableName IS NOT NULL THEN
DECLARE
vTemplateSchema VARCHAR2(128);
vTemplateTable VARCHAR2(128);
vTemplateCount NUMBER;
BEGIN
-- Parse template table name (SCHEMA.TABLE or just TABLE)
IF INSTR(pTemplateTableName, '.') > 0 THEN
vTemplateSchema := UPPER(SUBSTR(pTemplateTableName, 1, INSTR(pTemplateTableName, '.') - 1));
vTemplateTable := UPPER(SUBSTR(pTemplateTableName, INSTR(pTemplateTableName, '.') + 1));
ELSE
vTemplateSchema := vSchemaName;
vTemplateTable := UPPER(pTemplateTableName);
END IF;
-- Check if template table exists
SELECT COUNT(*) INTO vTemplateCount
FROM all_tables
WHERE table_name = vTemplateTable
AND owner = vTemplateSchema;
IF vTemplateCount = 0 THEN
vgMsgTmp := ENV_MANAGER.MSG_TABLE_NOT_EXISTS || ': Template table ' || vTemplateSchema || '.' || vTemplateTable;
ENV_MANAGER.LOG_PROCESS_EVENT(vgMsgTmp, 'ERROR', vParameters);
RAISE_APPLICATION_ERROR(ENV_MANAGER.CODE_TABLE_NOT_EXISTS, vgMsgTmp);
END IF;
ENV_MANAGER.LOG_PROCESS_EVENT('Template table validated: ' || vTemplateSchema || '.' || vTemplateTable, 'DEBUG', vParameters);
END;
END IF;
-- Build query with TO_CHAR for date columns (per-column format support)
vProcessedColumnList := buildQueryWithDateFormats(NULL, vTableName, vSchemaName, vKeyColumnName, pTemplateTableName);
-- Process column list to add T. prefix and alias key column as A_WORKFLOW_HISTORY_KEY
vProcessedColumnList := processColumnList(vAllColumnsList, vTableName, vSchemaName, vKeyColumnName);
ENV_MANAGER.LOG_PROCESS_EVENT('Dynamic column list built: ' || vAllColumnsList, 'DEBUG', vParameters);
ENV_MANAGER.LOG_PROCESS_EVENT('Processed column list with T. prefix: ' || vProcessedColumnList, 'DEBUG', vParameters);
ENV_MANAGER.LOG_PROCESS_EVENT('Processed column list with TO_CHAR for date columns: ' || vProcessedColumnList, 'DEBUG', vParameters);
ENV_MANAGER.LOG_PROCESS_EVENT('Template table: ' || NVL(pTemplateTableName, 'NULL - using global default for all dates'), 'INFO', vParameters);
vTableName := DBMS_ASSERT.SCHEMA_NAME(vSchemaName) || '.' || DBMS_ASSERT.simple_sql_name(vTableName);
-- Lookup A_SOURCE_FILE_CONFIG_KEY based on pFolderName parsing if pRegisterExport is enabled
IF pRegisterExport THEN
-- Format: {BUCKET_AREA}/{SOURCE_KEY}/{TABLE_ID}
-- Example: 'ODS/CSDB/CSDB_DEBT_DAILY' -> SOURCE_KEY='CSDB', TABLE_ID='CSDB_DEBT_DAILY'
-- Parse pFolderName to extract SOURCE_KEY and TABLE_ID
vSlashPos1 := INSTR(pFolderName, '/', 1, 1); -- First '/' position
vSlashPos2 := INSTR(pFolderName, '/', 1, 2); -- Second '/' position
IF vSlashPos1 > 0 AND vSlashPos2 > 0 THEN
-- Extract segment 2 (SOURCE_KEY) and segment 3 (TABLE_ID)
vSourceKey := SUBSTR(pFolderName, vSlashPos1 + 1, vSlashPos2 - vSlashPos1 - 1);
vTableId := SUBSTR(pFolderName, vSlashPos2 + 1);
-- Find configuration based on SOURCE_KEY and TABLE_ID
BEGIN
SELECT A_SOURCE_FILE_CONFIG_KEY
INTO vConfigKey
FROM CT_MRDS.A_SOURCE_FILE_CONFIG
WHERE A_SOURCE_KEY = vSourceKey
AND TABLE_ID = vTableId
AND SOURCE_FILE_TYPE = 'INPUT'
AND ROWNUM = 1;
ENV_MANAGER.LOG_PROCESS_EVENT('Found config key: ' || vConfigKey || ' for SOURCE=' || vSourceKey || ', TABLE=' || vTableId, 'DEBUG', vParameters);
EXCEPTION
WHEN NO_DATA_FOUND THEN
vConfigKey := -1;
ENV_MANAGER.LOG_PROCESS_EVENT('No config found for SOURCE=' || vSourceKey || ', TABLE=' || vTableId || ' - using default (-1)', 'INFO', vParameters);
END;
ELSE
-- Cannot parse folder name - use default
vConfigKey := -1;
ENV_MANAGER.LOG_PROCESS_EVENT('Cannot parse pFolderName: ' || pFolderName || ' - using default (-1)', 'WARNING', vParameters);
END IF;
ENV_MANAGER.LOG_PROCESS_EVENT('File registration enabled with config key: ' || vConfigKey, 'INFO', vParameters);
END IF;
-- Fetch unique key values from A_LOAD_HISTORY
vSql := 'SELECT DISTINCT L.A_ETL_LOAD_SET_KEY' ||
' FROM ' || vTableName || ' T, CT_ODS.A_LOAD_HISTORY L' ||
@@ -733,7 +809,136 @@ AS
query => vQuery,
format => json_object('type' VALUE 'CSV', 'header' VALUE true)
);
-- Register exported file to A_SOURCE_FILE_RECEIVED if requested
IF pRegisterExport THEN
DECLARE
vChecksum VARCHAR2(128);
vCreated TIMESTAMP WITH TIME ZONE;
vBytes NUMBER;
vActualFileName VARCHAR2(1000); -- Actual filename with Oracle suffix
vSanitizedFileName VARCHAR2(1000);
vFileName VARCHAR2(1000);
vRetryCount NUMBER := 0;
vMaxRetries NUMBER := 1; -- One retry after initial attempt
vRetryDelay NUMBER := 2; -- 2 seconds delay
BEGIN
-- Extract filename from URI (after last '/')
vFileName := SUBSTR(vUri, INSTR(vUri, '/', -1) + 1);
-- Sanitize filename first (PL/SQL function cannot be used directly in SQL)
vSanitizedFileName := sanitizeFilename(vFileName);
-- Remove .csv extension for LIKE pattern matching (Oracle adds suffixes BEFORE .csv)
-- Example: keyvalue.csv becomes keyvalue_1_20260211T102621591769Z.csv
vSanitizedFileName := REGEXP_REPLACE(vSanitizedFileName, '\.csv$', '', 1, 0, 'i');
-- Try to get file metadata with retry logic
<<metadata_retry_loop>>
LOOP
BEGIN
SELECT object_name, checksum, created, bytes
INTO vActualFileName, vChecksum, vCreated, vBytes
FROM TABLE(DBMS_CLOUD.LIST_OBJECTS(
credential_name => pCredentialName,
location_uri => vBucketUri
))
WHERE object_name LIKE CASE WHEN pFolderName IS NOT NULL THEN pFolderName || '/' ELSE '' END || vSanitizedFileName || '%'
ORDER BY created DESC, bytes DESC
FETCH FIRST 1 ROW ONLY;
-- Extract filename only from full path (remove bucket folder prefix)
vActualFileName := SUBSTR(vActualFileName, INSTR(vActualFileName, '/', -1) + 1);
-- Success - exit retry loop
EXIT metadata_retry_loop;
EXCEPTION
WHEN NO_DATA_FOUND THEN
vRetryCount := vRetryCount + 1;
IF vRetryCount <= vMaxRetries THEN
-- Log retry attempt
ENV_MANAGER.LOG_PROCESS_EVENT('File not found in bucket (attempt ' || vRetryCount || '/' || (vMaxRetries + 1) || '), retrying after ' || vRetryDelay || ' seconds: ' || vFileName, 'DEBUG', vParameters);
-- Wait before retry using DBMS_SESSION.SLEEP (alternative to DBMS_LOCK)
DBMS_SESSION.SLEEP(vRetryDelay);
ELSE
-- Max retries exceeded - re-raise exception
RAISE;
END IF;
END;
END LOOP metadata_retry_loop;
-- Create A_SOURCE_FILE_RECEIVED record for this export with metadata
vSourceFileReceivedKey := CT_MRDS.A_SOURCE_FILE_RECEIVED_KEY_SEQ.NEXTVAL;
INSERT INTO CT_MRDS.A_SOURCE_FILE_RECEIVED (
A_SOURCE_FILE_RECEIVED_KEY,
A_SOURCE_FILE_CONFIG_KEY,
SOURCE_FILE_NAME,
CHECKSUM,
CREATED,
BYTES,
RECEPTION_DATE,
PROCESSING_STATUS,
PARTITION_YEAR,
PARTITION_MONTH,
ARCH_FILE_NAME
) VALUES (
vSourceFileReceivedKey,
NVL(vConfigKey, -1), -- Use config key if found, otherwise -1
vActualFileName, -- Use actual filename with Oracle suffix
vChecksum,
vCreated,
vBytes,
SYSDATE,
'INGESTED',
NULL, -- PARTITION_YEAR not used for single-file exports
NULL, -- PARTITION_MONTH not used for single-file exports
NULL -- ARCH_FILE_NAME not used for single-file exports
);
ENV_MANAGER.LOG_PROCESS_EVENT('Registered file: FileReceivedKey=' || vSourceFileReceivedKey || ', File=' || vActualFileName || ', Size=' || vBytes || ' bytes', 'DEBUG', vParameters);
EXCEPTION
WHEN NO_DATA_FOUND THEN
-- File not found after retries - log warning and continue without metadata
ENV_MANAGER.LOG_PROCESS_EVENT('WARNING: File not found in bucket after ' || (vMaxRetries + 1) || ' attempts: ' || vFileName, 'WARNING', vParameters);
-- Sanitize filename for fallback INSERT (function cannot be used in SQL)
vSanitizedFileName := sanitizeFilename(vFileName);
-- Insert without metadata using theoretical filename
vSourceFileReceivedKey := CT_MRDS.A_SOURCE_FILE_RECEIVED_KEY_SEQ.NEXTVAL;
INSERT INTO CT_MRDS.A_SOURCE_FILE_RECEIVED (
A_SOURCE_FILE_RECEIVED_KEY,
A_SOURCE_FILE_CONFIG_KEY,
SOURCE_FILE_NAME,
RECEPTION_DATE,
PROCESSING_STATUS,
PARTITION_YEAR,
PARTITION_MONTH,
ARCH_FILE_NAME
) VALUES (
vSourceFileReceivedKey,
NVL(vConfigKey, -1), -- Use config key if found, otherwise -1
vSanitizedFileName, -- Use pre-calculated sanitized filename
SYSDATE,
'INGESTED',
NULL, -- PARTITION_YEAR not used for single-file exports
NULL, -- PARTITION_MONTH not used for single-file exports
NULL -- ARCH_FILE_NAME not used for single-file exports
);
ENV_MANAGER.LOG_PROCESS_EVENT('Registered file without metadata: FileReceivedKey=' || vSourceFileReceivedKey || ', File=' || vSanitizedFileName, 'DEBUG', vParameters);
END;
END IF;
END LOOP;
-- Log summary of file registration if enabled
IF pRegisterExport THEN
ENV_MANAGER.LOG_PROCESS_EVENT('Registered ' || vKeyValues.COUNT || ' exported files to A_SOURCE_FILE_RECEIVED with config key: ' || vConfigKey, 'INFO', vParameters);
END IF;
ENV_MANAGER.LOG_PROCESS_EVENT('End','INFO',vParameters);
EXCEPTION
WHEN ENV_MANAGER.ERR_TABLE_NOT_EXISTS THEN
@@ -1032,6 +1237,7 @@ AS
pParallelDegree IN NUMBER default 1,
pTemplateTableName IN VARCHAR2 default NULL,
pMaxFileSize IN NUMBER default 104857600,
pRegisterExport IN BOOLEAN default FALSE,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
)
IS
@@ -1045,6 +1251,15 @@ AS
vBucketUri VARCHAR2(4000);
vCurrentCol VARCHAR2(128);
vPartitions partition_tab;
vSourceFileReceivedKey NUMBER;
vFileName VARCHAR2(1000);
vFileUri VARCHAR2(4000);
-- Variables for A_SOURCE_FILE_CONFIG lookup
vSourceKey VARCHAR2(100);
vTableId VARCHAR2(200);
vConfigKey NUMBER := -1;
vSlashPos1 NUMBER;
vSlashPos2 NUMBER;
BEGIN
vParameters := ENV_MANAGER.FORMAT_PARAMETERS(SYS.ODCIVARCHAR2LIST( 'pSchemaName => '''||nvl(pSchemaName, 'NULL')||''''
@@ -1059,6 +1274,7 @@ AS
,'pParallelDegree => '''||nvl(TO_CHAR(pParallelDegree), 'NULL')||''''
,'pTemplateTableName => '''||nvl(pTemplateTableName, 'NULL')||''''
,'pMaxFileSize => '''||nvl(TO_CHAR(pMaxFileSize), 'NULL')||''''
,'pRegisterExport => '''||CASE WHEN pRegisterExport THEN 'TRUE' ELSE 'FALSE' END||''''
,'pCredentialName => '''||nvl(pCredentialName, 'NULL')||''''
));
ENV_MANAGER.LOG_PROCESS_EVENT('Start','INFO', vParameters);
@@ -1250,6 +1466,175 @@ AS
END;
END IF;
END IF;
-- Note: File registration handled by EXPORT_SINGLE_PARTITION when pRegisterExport=TRUE
-- Each partition calls pRegisterExport logic independently during serial/parallel execution
-- Register exported files to A_SOURCE_FILE_RECEIVED if requested (after successful export)
IF pRegisterExport THEN
-- Lookup A_SOURCE_FILE_CONFIG_KEY based on pFolderName parsing
-- Format: {BUCKET_AREA}/{SOURCE_KEY}/{TABLE_ID}
-- Example: 'ODS/CSDB/CSDB_DEBT_DAILY' -> SOURCE_KEY='CSDB', TABLE_ID='CSDB_DEBT_DAILY'
-- Parse pFolderName to extract SOURCE_KEY and TABLE_ID
vSlashPos1 := INSTR(pFolderName, '/', 1, 1); -- First '/' position
vSlashPos2 := INSTR(pFolderName, '/', 1, 2); -- Second '/' position
IF vSlashPos1 > 0 AND vSlashPos2 > 0 THEN
-- Extract segment 2 (SOURCE_KEY) and segment 3 (TABLE_ID)
vSourceKey := SUBSTR(pFolderName, vSlashPos1 + 1, vSlashPos2 - vSlashPos1 - 1);
vTableId := SUBSTR(pFolderName, vSlashPos2 + 1);
-- Find configuration based on SOURCE_KEY and TABLE_ID
BEGIN
SELECT A_SOURCE_FILE_CONFIG_KEY
INTO vConfigKey
FROM CT_MRDS.A_SOURCE_FILE_CONFIG
WHERE A_SOURCE_KEY = vSourceKey
AND TABLE_ID = vTableId
AND SOURCE_FILE_TYPE = 'INPUT'
AND ROWNUM = 1;
ENV_MANAGER.LOG_PROCESS_EVENT('Found config key: ' || vConfigKey || ' for SOURCE=' || vSourceKey || ', TABLE=' || vTableId, 'DEBUG', vParameters);
EXCEPTION
WHEN NO_DATA_FOUND THEN
vConfigKey := -1;
ENV_MANAGER.LOG_PROCESS_EVENT('No config found for SOURCE=' || vSourceKey || ', TABLE=' || vTableId || ' - using default (-1)', 'INFO', vParameters);
END;
ELSE
-- Cannot parse folder name - use default
vConfigKey := -1;
ENV_MANAGER.LOG_PROCESS_EVENT('Cannot parse pFolderName: ' || pFolderName || ' - using default (-1)', 'WARNING', vParameters);
END IF;
ENV_MANAGER.LOG_PROCESS_EVENT('Registering ' || vPartitions.COUNT || ' exported files to A_SOURCE_FILE_RECEIVED with config key: ' || vConfigKey, 'INFO', vParameters);
FOR i IN 1 .. vPartitions.COUNT LOOP
-- Construct filename and URI for this partition
vFileName := NVL(vFileBaseName, UPPER(REPLACE(vTableName, vSchemaName || '.', ''))) || '_' || vPartitions(i).year || vPartitions(i).month || '.csv';
vFileUri := vBucketUri || CASE WHEN pFolderName IS NOT NULL THEN pFolderName || '/' ELSE '' END || sanitizeFilename(vFileName);
-- Get file metadata from OCI bucket (CHECKSUM, CREATED, BYTES) with retry logic
DECLARE
vChecksum VARCHAR2(128);
vCreated TIMESTAMP WITH TIME ZONE;
vBytes NUMBER;
vActualFileName VARCHAR2(1000); -- Actual filename with Oracle suffix
vSanitizedFileName VARCHAR2(1000);
vRetryCount NUMBER := 0;
vMaxRetries NUMBER := 1; -- One retry after initial attempt
vRetryDelay NUMBER := 2; -- 2 seconds delay
BEGIN
-- Sanitize filename first (PL/SQL function cannot be used directly in SQL)
vSanitizedFileName := sanitizeFilename(vFileName);
-- Remove .csv extension for LIKE pattern matching (Oracle adds suffixes BEFORE .csv)
-- Example: LEGACY_DEBT_202508.csv becomes LEGACY_DEBT_202508_1_20260211T102621591769Z.csv
vSanitizedFileName := REGEXP_REPLACE(vSanitizedFileName, '\.csv$', '', 1, 0, 'i');
-- Try to get file metadata with retry logic
<<metadata_retry_loop>>
LOOP
BEGIN
SELECT object_name, checksum, created, bytes
INTO vActualFileName, vChecksum, vCreated, vBytes
FROM TABLE(DBMS_CLOUD.LIST_OBJECTS(
credential_name => pCredentialName,
location_uri => vBucketUri
))
WHERE object_name LIKE CASE WHEN pFolderName IS NOT NULL THEN pFolderName || '/' ELSE '' END || vSanitizedFileName || '%'
ORDER BY created DESC, bytes DESC
FETCH FIRST 1 ROW ONLY;
-- Extract filename only from full path (remove bucket folder prefix)
-- vActualFileName contains: 'ODS/CSDB/CSDB_DEBT/LEGACY_DEBT_202508_1_20260211T111341375171Z.csv'
-- Extract only: 'LEGACY_DEBT_202508_1_20260211T111341375171Z.csv'
vActualFileName := SUBSTR(vActualFileName, INSTR(vActualFileName, '/', -1) + 1);
-- Success - exit retry loop
EXIT metadata_retry_loop;
EXCEPTION
WHEN NO_DATA_FOUND THEN
vRetryCount := vRetryCount + 1;
IF vRetryCount <= vMaxRetries THEN
-- Log retry attempt
ENV_MANAGER.LOG_PROCESS_EVENT('File not found in bucket (attempt ' || vRetryCount || '/' || (vMaxRetries + 1) || '), retrying after ' || vRetryDelay || ' seconds: ' || vFileName, 'DEBUG', vParameters);
-- Wait before retry using DBMS_SESSION.SLEEP (alternative to DBMS_LOCK)
DBMS_SESSION.SLEEP(vRetryDelay);
ELSE
-- Max retries exceeded - re-raise exception
RAISE;
END IF;
END;
END LOOP metadata_retry_loop;
-- Create A_SOURCE_FILE_RECEIVED record for this export with metadata
vSourceFileReceivedKey := CT_MRDS.A_SOURCE_FILE_RECEIVED_KEY_SEQ.NEXTVAL;
INSERT INTO CT_MRDS.A_SOURCE_FILE_RECEIVED (
A_SOURCE_FILE_RECEIVED_KEY,
A_SOURCE_FILE_CONFIG_KEY,
SOURCE_FILE_NAME,
CHECKSUM,
CREATED,
BYTES,
RECEPTION_DATE,
PROCESSING_STATUS,
PARTITION_YEAR,
PARTITION_MONTH,
ARCH_FILE_NAME
) VALUES (
vSourceFileReceivedKey,
vConfigKey, -- Config key from A_SOURCE_FILE_CONFIG lookup
vActualFileName, -- Use actual filename with Oracle suffix
vChecksum,
vCreated,
vBytes,
SYSDATE,
'INGESTED',
NULL, -- PARTITION_YEAR not used for CSV exports
NULL, -- PARTITION_MONTH not used for CSV exports
NULL -- ARCH_FILE_NAME not used for CSV exports
);
ENV_MANAGER.LOG_PROCESS_EVENT('Registered file: FileReceivedKey=' || vSourceFileReceivedKey || ', File=' || vActualFileName || ', Size=' || vBytes || ' bytes', 'DEBUG', vParameters);
EXCEPTION
WHEN NO_DATA_FOUND THEN
-- File not found after retries - log warning and continue without metadata
ENV_MANAGER.LOG_PROCESS_EVENT('WARNING: File not found in bucket after ' || (vMaxRetries + 1) || ' attempts: ' || vFileName, 'WARNING', vParameters);
-- Sanitize filename for fallback INSERT (function cannot be used in SQL)
vSanitizedFileName := sanitizeFilename(vFileName);
-- Insert without metadata
vSourceFileReceivedKey := CT_MRDS.A_SOURCE_FILE_RECEIVED_KEY_SEQ.NEXTVAL;
INSERT INTO CT_MRDS.A_SOURCE_FILE_RECEIVED (
A_SOURCE_FILE_RECEIVED_KEY,
A_SOURCE_FILE_CONFIG_KEY,
SOURCE_FILE_NAME,
RECEPTION_DATE,
PROCESSING_STATUS,
PARTITION_YEAR,
PARTITION_MONTH,
ARCH_FILE_NAME
) VALUES (
vSourceFileReceivedKey,
vConfigKey, -- Config key from A_SOURCE_FILE_CONFIG lookup
vSanitizedFileName, -- Fallback: use theoretical filename if actual not found
SYSDATE,
'INGESTED',
NULL, -- PARTITION_YEAR not used for CSV exports
NULL, -- PARTITION_MONTH not used for CSV exports
NULL -- ARCH_FILE_NAME not used for CSV exports
);
END;
END LOOP;
COMMIT;
ENV_MANAGER.LOG_PROCESS_EVENT('Successfully registered all ' || vPartitions.COUNT || ' files', 'INFO', vParameters);
END IF;
ENV_MANAGER.LOG_PROCESS_EVENT('Export completed successfully for ' || vPartitions.COUNT || ' files', 'INFO', vParameters);
ENV_MANAGER.LOG_PROCESS_EVENT('End','INFO',vParameters);

69
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/new_version/DATA_EXPORTER.pkg
View File

@@ -9,23 +9,21 @@ AS
**/
-- Package Version Information
PACKAGE_VERSION CONSTANT VARCHAR2(10) := '2.6.3';
PACKAGE_BUILD_DATE CONSTANT VARCHAR2(19) := '2026-01-28 19:30:00';
PACKAGE_AUTHOR CONSTANT VARCHAR2(50) := 'MRDS Development Team';
PACKAGE_VERSION CONSTANT VARCHAR2(10) := '2.7.5';
PACKAGE_BUILD_DATE CONSTANT VARCHAR2(20) := '2026-02-11 12:15:00';
PACKAGE_AUTHOR CONSTANT VARCHAR2(100) := 'Grzegorz Michalski';
-- Version History (last 3-5 changes)
VERSION_HISTORY CONSTANT VARCHAR2(4000) :=
'v2.6.3 (2026-01-28): COMPILATION FIX - Resolved ORA-00904 error in EXPORT_PARTITION_PARALLEL. SQLERRM and DBMS_UTILITY.FORMAT_ERROR_BACKTRACE cannot be used directly in SQL UPDATE statements. Now properly assigned to vgMsgTmp variable before UPDATE.' || CHR(10) ||
'v2.6.2 (2026-01-28): CRITICAL FIX - Race condition when multiple exports run simultaneously. Changed DELETE to filter by age (>24h) instead of deleting all COMPLETED chunks. Prevents concurrent sessions from deleting each other chunks. Session-safe cleanup with TASK_NAME filtering. Enables true parallel execution of multiple export jobs.' || CHR(10) ||
'v2.6.1 (2026-01-28): Added DELETE_FAILED_EXPORT_FILE procedure to clean up partial/corrupted files before retry. When partition fails mid-export, partial file is deleted before retry to prevent Oracle from creating _1 suffixed duplicates. Ensures clean retry without orphaned files in OCI bucket.' || CHR(10) ||
'v2.6.0 (2026-01-28): CRITICAL FIX - Added STATUS tracking to A_PARALLEL_EXPORT_CHUNKS table to prevent data duplication on retry. System now restarts ONLY failed partitions instead of re-exporting all data. Added ERROR_MESSAGE and EXPORT_TIMESTAMP columns for better error handling and monitoring. Prevents duplicate file creation when parallel tasks fail (e.g., 22 partitions with 16 threads, 3 failures no longer duplicates 19 successful exports).' || CHR(10) ||
'v2.5.0 (2026-01-26): Added recorddelimiter parameter with CRLF (CHR(13)||CHR(10)) for CSV exports to ensure Windows-compatible line endings. Improves cross-platform compatibility when CSV files are opened in Windows applications (Notepad, Excel).' || CHR(10) ||
'v2.4.0 (2026-01-11): Added pTemplateTableName parameter for per-column date format configuration. Implements dynamic query building with TO_CHAR for each date/timestamp column using FILE_MANAGER.GET_DATE_FORMAT. Supports 3-tier hierarchy: column-specific, template DEFAULT, global fallback. Eliminates single dateformat limitation of DBMS_CLOUD.EXPORT_DATA.' || CHR(10) ||
'v2.3.0 (2025-12-20): Added parallel partition processing using DBMS_PARALLEL_EXECUTE. New pParallelDegree parameter (1-16, default 1) for EXPORT_TABLE_DATA_BY_DATE and EXPORT_TABLE_DATA_TO_CSV_BY_DATE procedures. Each year/month partition processed in separate thread for improved performance.' || CHR(10) ||
'v2.2.0 (2025-12-19): DRY refactoring - extracted shared helper functions (sanitizeFilename, VALIDATE_TABLE_AND_COLUMNS, GET_PARTITIONS, EXPORT_SINGLE_PARTITION worker procedure). Reduced code duplication by ~400 lines. Prepared architecture for v2.3.0 parallel processing.' || CHR(10) ||
'v2.1.1 (2025-12-04): Fixed JOIN column reference A_WORKFLOW_HISTORY_KEY -> A_ETL_LOAD_SET_KEY, added consistent column mapping and dynamic column list to EXPORT_TABLE_DATA procedure, enhanced DEBUG logging for all export operations' || CHR(10) ||
'v2.1.0 (2025-10-22): Added version tracking and PARTITION_YEAR/PARTITION_MONTH support' || CHR(10) ||
'v2.0.0 (2025-10-01): Separated export functionality from FILE_MANAGER package' || CHR(10);
'v2.7.5 (2026-02-11): Added pRegisterExport parameter to EXPORT_TABLE_DATA procedure. When TRUE, registers each exported CSV file in A_SOURCE_FILE_RECEIVED.' || CHR(10) ||
'v2.7.4 (2026-02-11): ACTUAL FILENAME STORAGE - Store real filename with Oracle suffix in SOURCE_FILE_NAME instead of theoretical filename.' || CHR(10) ||
'v2.7.3 (2026-02-11): FIX LIKE pattern for DBMS_CLOUD.LIST_OBJECTS - Removed .csv extension from filename before pattern matching.' || CHR(10) ||
'v2.7.2 (2026-02-11): FIX pRegisterExport in EXPORT_TABLE_DATA_TO_CSV_BY_DATE - Added missing pRegisterExport parameter to EXPORT_SINGLE_PARTITION call.' || CHR(10) ||
'v2.7.1 (2026-02-11): AUTO-LOOKUP A_SOURCE_FILE_CONFIG_KEY - Parse pFolderName to automatically find config key from A_SOURCE_FILE_CONFIG.' || CHR(10) ||
'v2.7.0 (2026-02-10): Added pRegisterExport parameter to EXPORT_TABLE_DATA_TO_CSV_BY_DATE. When TRUE, registers each exported CSV file in A_SOURCE_FILE_RECEIVED.' || CHR(10) ||
'v2.6.3 (2026-01-28): COMPILATION FIX - Resolved ORA-00904 error in EXPORT_PARTITION_PARALLEL. SQLERRM properly assigned to vgMsgTmp variable.' || CHR(10) ||
'v2.6.2 (2026-01-28): CRITICAL FIX - Race condition when multiple exports run simultaneously. Session-safe cleanup with TASK_NAME filtering.' || CHR(10) ||
'v2.6.0 (2026-01-28): CRITICAL FIX - Added STATUS tracking to A_PARALLEL_EXPORT_CHUNKS table to prevent data duplication on retry.' || CHR(10);
cgBL CONSTANT VARCHAR2(2) := CHR(13)||CHR(10);
vgMsgTmp VARCHAR2(32000);
@@ -75,24 +73,36 @@ AS
* @desc Wrapper procedure for DBMS_CLOUD.EXPORT_DATA.
* Exports data into CSV file on OCI infrustructure.
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* Supports template table for column order and per-column date formatting.
* When pRegisterExport=TRUE, successfully exported files are registered in:
* - CT_MRDS.A_SOURCE_FILE_RECEIVED (tracks file location, size, checksum, and metadata)
* @param pTemplateTableName - Optional template table (SCHEMA.TABLE or TABLE) for:
* - Column order control (template defines CSV structure)
* - Per-column date formatting via FILE_MANAGER.GET_DATE_FORMAT
* - NULL = use source table columns in natural order
* @param pRegisterExport - When TRUE, registers each exported CSV file in A_SOURCE_FILE_RECEIVED table
* @example
* begin
* DATA_EXPORTER.EXPORT_TABLE_DATA(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'csv_exports'
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'csv_exports',
* pTemplateTableName => 'CT_ET_TEMPLATES.MY_TEMPLATE', -- Optional
* pRegisterExport => TRUE -- Optional, default FALSE
* );
* end;
**/
PROCEDURE EXPORT_TABLE_DATA (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pTemplateTableName IN VARCHAR2 default NULL,
pRegisterExport IN BOOLEAN default FALSE,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
@@ -146,6 +156,8 @@ AS
* but exports to CSV format instead of Parquet.
* Supports parallel partition processing via pParallelDegree parameter (1-16).
* File naming pattern: {pFileName}_YYYYMM.csv or {TABLENAME}_YYYYMM.csv (if pFileName is NULL)
* When pRegisterExport=TRUE, successfully exported files are registered in:
* - CT_MRDS.A_SOURCE_FILE_RECEIVED (tracks file location, size, checksum, and metadata)
* @example
* begin
* -- With custom filename
@@ -158,7 +170,8 @@ AS
* pFileName => 'my_export.csv',
* pMinDate => DATE '2024-01-01',
* pMaxDate => SYSDATE,
* pParallelDegree => 8 -- Optional, default 1, range 1-16
* pParallelDegree => 8, -- Optional, default 1, range 1-16
* pRegisterExport => TRUE -- Optional, default FALSE, registers to A_SOURCE_FILE_RECEIVED
* );
*
* -- With auto-generated filename (based on table name only)
@@ -169,7 +182,8 @@ AS
* pBucketArea => 'ARCHIVE',
* pFolderName => 'exports',
* pMinDate => DATE '2025-09-01',
* pMaxDate => DATE '2025-09-17'
* pMaxDate => DATE '2025-09-17',
* pRegisterExport => TRUE -- Registers each export to A_SOURCE_FILE_RECEIVED table
* );
* -- This will create files like: AGGREGATED_ALLOTMENT_202509.csv, etc.
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
@@ -188,6 +202,7 @@ AS
pParallelDegree IN NUMBER default 1,
pTemplateTableName IN VARCHAR2 default NULL,
pMaxFileSize IN NUMBER default 104857600,
pRegisterExport IN BOOLEAN default FALSE,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);

1313
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/rollback_version/v.2.6.3/DATA_EXPORTER.pkb Normal file
View File

File diff suppressed because it is too large Load Diff

218
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/rollback_version/v.2.6.3/DATA_EXPORTER.pkg Normal file
View File

@@ -0,0 +1,218 @@
create or replace PACKAGE CT_MRDS.DATA_EXPORTER
AUTHID CURRENT_USER
AS
/**
* Data Export Package: Provides comprehensive data export capabilities to various formats (CSV, Parquet)
* with support for cloud storage integration via Oracle Cloud Infrastructure (OCI).
* The structure of comment is used by GET_PACKAGE_DOCUMENTATION function
* which returns documentation text for confluence page (to Copy-Paste it).
**/
-- Package Version Information
PACKAGE_VERSION CONSTANT VARCHAR2(10) := '2.6.3';
PACKAGE_BUILD_DATE CONSTANT VARCHAR2(19) := '2026-01-28 19:30:00';
PACKAGE_AUTHOR CONSTANT VARCHAR2(50) := 'MRDS Development Team';
-- Version History (last 3-5 changes)
VERSION_HISTORY CONSTANT VARCHAR2(4000) :=
'v2.6.3 (2026-01-28): COMPILATION FIX - Resolved ORA-00904 error in EXPORT_PARTITION_PARALLEL. SQLERRM and DBMS_UTILITY.FORMAT_ERROR_BACKTRACE cannot be used directly in SQL UPDATE statements. Now properly assigned to vgMsgTmp variable before UPDATE.' || CHR(10) ||
'v2.6.2 (2026-01-28): CRITICAL FIX - Race condition when multiple exports run simultaneously. Changed DELETE to filter by age (>24h) instead of deleting all COMPLETED chunks. Prevents concurrent sessions from deleting each other chunks. Session-safe cleanup with TASK_NAME filtering. Enables true parallel execution of multiple export jobs.' || CHR(10) ||
'v2.6.1 (2026-01-28): Added DELETE_FAILED_EXPORT_FILE procedure to clean up partial/corrupted files before retry. When partition fails mid-export, partial file is deleted before retry to prevent Oracle from creating _1 suffixed duplicates. Ensures clean retry without orphaned files in OCI bucket.' || CHR(10) ||
'v2.6.0 (2026-01-28): CRITICAL FIX - Added STATUS tracking to A_PARALLEL_EXPORT_CHUNKS table to prevent data duplication on retry. System now restarts ONLY failed partitions instead of re-exporting all data. Added ERROR_MESSAGE and EXPORT_TIMESTAMP columns for better error handling and monitoring. Prevents duplicate file creation when parallel tasks fail (e.g., 22 partitions with 16 threads, 3 failures no longer duplicates 19 successful exports).' || CHR(10) ||
'v2.5.0 (2026-01-26): Added recorddelimiter parameter with CRLF (CHR(13)||CHR(10)) for CSV exports to ensure Windows-compatible line endings. Improves cross-platform compatibility when CSV files are opened in Windows applications (Notepad, Excel).' || CHR(10) ||
'v2.4.0 (2026-01-11): Added pTemplateTableName parameter for per-column date format configuration. Implements dynamic query building with TO_CHAR for each date/timestamp column using FILE_MANAGER.GET_DATE_FORMAT. Supports 3-tier hierarchy: column-specific, template DEFAULT, global fallback. Eliminates single dateformat limitation of DBMS_CLOUD.EXPORT_DATA.' || CHR(10) ||
'v2.3.0 (2025-12-20): Added parallel partition processing using DBMS_PARALLEL_EXECUTE. New pParallelDegree parameter (1-16, default 1) for EXPORT_TABLE_DATA_BY_DATE and EXPORT_TABLE_DATA_TO_CSV_BY_DATE procedures. Each year/month partition processed in separate thread for improved performance.' || CHR(10) ||
'v2.2.0 (2025-12-19): DRY refactoring - extracted shared helper functions (sanitizeFilename, VALIDATE_TABLE_AND_COLUMNS, GET_PARTITIONS, EXPORT_SINGLE_PARTITION worker procedure). Reduced code duplication by ~400 lines. Prepared architecture for v2.3.0 parallel processing.' || CHR(10) ||
'v2.1.1 (2025-12-04): Fixed JOIN column reference A_WORKFLOW_HISTORY_KEY -> A_ETL_LOAD_SET_KEY, added consistent column mapping and dynamic column list to EXPORT_TABLE_DATA procedure, enhanced DEBUG logging for all export operations' || CHR(10) ||
'v2.1.0 (2025-10-22): Added version tracking and PARTITION_YEAR/PARTITION_MONTH support' || CHR(10) ||
'v2.0.0 (2025-10-01): Separated export functionality from FILE_MANAGER package' || CHR(10);
cgBL CONSTANT VARCHAR2(2) := CHR(13)||CHR(10);
vgMsgTmp VARCHAR2(32000);
---------------------------------------------------------------------------------------------------------------------------
-- TYPE DEFINITIONS FOR PARTITION HANDLING
---------------------------------------------------------------------------------------------------------------------------
/**
* Record type for year/month partition information
**/
TYPE partition_rec IS RECORD (
year VARCHAR2(4),
month VARCHAR2(2)
);
/**
* Table type for collection of partition records
**/
TYPE partition_tab IS TABLE OF partition_rec;
---------------------------------------------------------------------------------------------------------------------------
-- INTERNAL PARALLEL PROCESSING CALLBACK
---------------------------------------------------------------------------------------------------------------------------
/**
* @name EXPORT_PARTITION_PARALLEL
* @desc Internal callback procedure for DBMS_PARALLEL_EXECUTE.
* Processes single partition (year/month) chunk in parallel task.
* Called by DBMS_PARALLEL_EXECUTE framework for each chunk.
* This procedure is PUBLIC because DBMS_PARALLEL_EXECUTE requires it,
* but should NOT be called directly by external code.
* @param pStartId - Chunk start ID (CHUNK_ID from A_PARALLEL_EXPORT_CHUNKS table)
* @param pEndId - Chunk end ID (same as pStartId for single-row chunks)
**/
PROCEDURE EXPORT_PARTITION_PARALLEL (
pStartId IN NUMBER,
pEndId IN NUMBER
);
---------------------------------------------------------------------------------------------------------------------------
-- MAIN EXPORT PROCEDURES
---------------------------------------------------------------------------------------------------------------------------
/**
* @name EXPORT_TABLE_DATA
* @desc Wrapper procedure for DBMS_CLOUD.EXPORT_DATA.
* Exports data into CSV file on OCI infrustructure.
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* @example
* begin
* DATA_EXPORTER.EXPORT_TABLE_DATA(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'csv_exports'
* );
* end;
**/
PROCEDURE EXPORT_TABLE_DATA (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
/**
* @name EXPORT_TABLE_DATA_BY_DATE
* @desc Wrapper procedure for DBMS_CLOUD.EXPORT_DATA.
* Exports data into PARQUET files on OCI infrustructure.
* Each YEAR_MONTH pair goes to seperate file (implicit partitioning).
* Allows specifying custom column list or uses T.* if pColumnList is NULL.
* Validates that all columns in pColumnList exist in the target table.
* Automatically adds 'T.' prefix to column names in pColumnList.
* Supports parallel partition processing via pParallelDegree parameter (default 1, range 1-16).
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* @example
* begin
* DATA_EXPORTER.EXPORT_TABLE_DATA_BY_DATE(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'parquet_exports',
* pColumnList => 'COLUMN1, COLUMN2, COLUMN3', -- Optional
* pMinDate => DATE '2024-01-01',
* pMaxDate => SYSDATE,
* pParallelDegree => 8 -- Optional, default 1, range 1-16
* );
* end;
**/
PROCEDURE EXPORT_TABLE_DATA_BY_DATE (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pColumnList IN VARCHAR2 default NULL,
pMinDate IN DATE default DATE '1900-01-01',
pMaxDate IN DATE default SYSDATE,
pParallelDegree IN NUMBER default 1,
pTemplateTableName IN VARCHAR2 default NULL,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
/**
* @name EXPORT_TABLE_DATA_TO_CSV_BY_DATE
* @desc Exports data to separate CSV files partitioned by year and month.
* Creates one CSV file for each year/month combination found in the data.
* Uses the same date filtering mechanism with CT_ODS.A_LOAD_HISTORY as EXPORT_TABLE_DATA_BY_DATE,
* but exports to CSV format instead of Parquet.
* Supports parallel partition processing via pParallelDegree parameter (1-16).
* File naming pattern: {pFileName}_YYYYMM.csv or {TABLENAME}_YYYYMM.csv (if pFileName is NULL)
* @example
* begin
* -- With custom filename
* DATA_EXPORTER.EXPORT_TABLE_DATA_TO_CSV_BY_DATE(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'exports',
* pFileName => 'my_export.csv',
* pMinDate => DATE '2024-01-01',
* pMaxDate => SYSDATE,
* pParallelDegree => 8 -- Optional, default 1, range 1-16
* );
*
* -- With auto-generated filename (based on table name only)
* DATA_EXPORTER.EXPORT_TABLE_DATA_TO_CSV_BY_DATE(
* pSchemaName => 'OU_TOP',
* pTableName => 'AGGREGATED_ALLOTMENT',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'ARCHIVE',
* pFolderName => 'exports',
* pMinDate => DATE '2025-09-01',
* pMaxDate => DATE '2025-09-17'
* );
* -- This will create files like: AGGREGATED_ALLOTMENT_202509.csv, etc.
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* end;
**/
PROCEDURE EXPORT_TABLE_DATA_TO_CSV_BY_DATE (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pFileName IN VARCHAR2 DEFAULT NULL,
pColumnList IN VARCHAR2 default NULL,
pMinDate IN DATE default DATE '1900-01-01',
pMaxDate IN DATE default SYSDATE,
pParallelDegree IN NUMBER default 1,
pTemplateTableName IN VARCHAR2 default NULL,
pMaxFileSize IN NUMBER default 104857600,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
---------------------------------------------------------------------------------------------------------------------------
-- VERSION MANAGEMENT FUNCTIONS
---------------------------------------------------------------------------------------------------------------------------
/**
* Returns the current package version number
* return: Version string in format X.Y.Z (e.g., '2.1.0')
**/
FUNCTION GET_VERSION RETURN VARCHAR2;
/**
* Returns comprehensive build information including version, date, and author
* return: Formatted string with complete build details
**/
FUNCTION GET_BUILD_INFO RETURN VARCHAR2;
/**
* Returns the version history with recent changes
* return: Multi-line string with version history
**/
FUNCTION GET_VERSION_HISTORY RETURN VARCHAR2;
END;
/

1493
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/rollback_version/v2.7.4/DATA_EXPORTER.pkb Normal file
View File

File diff suppressed because it is too large Load Diff

227
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/rollback_version/v2.7.4/DATA_EXPORTER.pkg Normal file
View File

@@ -0,0 +1,227 @@
create or replace PACKAGE CT_MRDS.DATA_EXPORTER
AUTHID CURRENT_USER
AS
/**
* Data Export Package: Provides comprehensive data export capabilities to various formats (CSV, Parquet)
* with support for cloud storage integration via Oracle Cloud Infrastructure (OCI).
* The structure of comment is used by GET_PACKAGE_DOCUMENTATION function
* which returns documentation text for confluence page (to Copy-Paste it).
**/
-- Package Version Information
PACKAGE_VERSION CONSTANT VARCHAR2(10) := '2.7.4';
PACKAGE_BUILD_DATE CONSTANT VARCHAR2(20) := '2026-02-11 12:10:00';
PACKAGE_AUTHOR CONSTANT VARCHAR2(100) := 'Grzegorz Michalski';
-- Version History (last 3-5 changes)
VERSION_HISTORY CONSTANT VARCHAR2(4000) :=
'v2.7.4 (2026-02-11): ACTUAL FILENAME STORAGE - Store real filename with Oracle suffix in SOURCE_FILE_NAME instead of theoretical filename. Changes LIST_OBJECTS query to SELECT object_name and stores actual filename like LEGACY_DEBT_202508_1_20260211T111341375171Z.csv instead of LEGACY_DEBT_202508.csv. Enables accurate file tracking.' || CHR(10) ||
'v2.7.3 (2026-02-11): FIX LIKE pattern for DBMS_CLOUD.LIST_OBJECTS - Removed .csv extension from filename before pattern matching. Oracle EXPORT_DATA creates files with suffixes BEFORE .csv so LIKE pattern should be filename% not filename.csv%. Enables proper metadata retrieval (CHECKSUM, CREATED, BYTES).' || CHR(10) ||
'v2.7.2 (2026-02-11): FIX pRegisterExport in EXPORT_TABLE_DATA_TO_CSV_BY_DATE - Added missing pRegisterExport parameter to EXPORT_SINGLE_PARTITION call. Previously files were not registered because parameter was not passed through.' || CHR(10) ||
'v2.7.1 (2026-02-11): AUTO-LOOKUP A_SOURCE_FILE_CONFIG_KEY - Parse pFolderName to automatically find config key from A_SOURCE_FILE_CONFIG. Example: ODS/CSDB/CSDB_DEBT_DAILY extracts SOURCE_KEY=CSDB, TABLE_ID=CSDB_DEBT_DAILY.' || CHR(10) ||
'v2.7.0 (2026-02-10): Added pRegisterExport parameter to EXPORT_TABLE_DATA_TO_CSV_BY_DATE. When TRUE, registers each exported CSV file in A_SOURCE_FILE_RECEIVED with metadata from DBMS_CLOUD.LIST_OBJECTS. Enables file tracking and integrity verification.' || CHR(10);
'v2.6.3 (2026-01-28): COMPILATION FIX - Resolved ORA-00904 error in EXPORT_PARTITION_PARALLEL. SQLERRM and DBMS_UTILITY.FORMAT_ERROR_BACKTRACE cannot be used directly in SQL UPDATE statements. Now properly assigned to vgMsgTmp variable before UPDATE.' || CHR(10) ||
'v2.6.2 (2026-01-28): CRITICAL FIX - Race condition when multiple exports run simultaneously. Changed DELETE to filter by age (>24h) instead of deleting all COMPLETED chunks. Prevents concurrent sessions from deleting each other chunks. Session-safe cleanup with TASK_NAME filtering. Enables true parallel execution of multiple export jobs.' || CHR(10) ||
'v2.6.0 (2026-01-28): CRITICAL FIX - Added STATUS tracking to A_PARALLEL_EXPORT_CHUNKS table to prevent data duplication on retry. System now restarts ONLY failed partitions instead of re-exporting all data. Added ERROR_MESSAGE and EXPORT_TIMESTAMP columns for better error handling and monitoring. Prevents duplicate file creation when parallel tasks fail (e.g., 22 partitions with 16 threads, 3 failures no longer duplicates 19 successful exports).' || CHR(10) ||
'v2.5.0 (2026-01-26): Added recorddelimiter parameter with CRLF (CHR(13)||CHR(10)) for CSV exports to ensure Windows-compatible line endings. Improves cross-platform compatibility when CSV files are opened in Windows applications (Notepad, Excel).' || CHR(10) ||
'v2.4.0 (2026-01-11): Added pTemplateTableName parameter for per-column date format configuration. Implements dynamic query building with TO_CHAR for each date/timestamp column using FILE_MANAGER.GET_DATE_FORMAT. Supports 3-tier hierarchy: column-specific, template DEFAULT, global fallback. Eliminates single dateformat limitation of DBMS_CLOUD.EXPORT_DATA.' || CHR(10) ||
'v2.3.0 (2025-12-20): Added parallel partition processing using DBMS_PARALLEL_EXECUTE. New pParallelDegree parameter (1-16, default 1) for EXPORT_TABLE_DATA_BY_DATE and EXPORT_TABLE_DATA_TO_CSV_BY_DATE procedures. Each year/month partition processed in separate thread for improved performance.' || CHR(10) ||
'v2.2.0 (2025-12-19): DRY refactoring - extracted shared helper functions (sanitizeFilename, VALIDATE_TABLE_AND_COLUMNS, GET_PARTITIONS, EXPORT_SINGLE_PARTITION worker procedure). Reduced code duplication by ~400 lines. Prepared architecture for v2.3.0 parallel processing.' || CHR(10) ||
'v2.1.1 (2025-12-04): Fixed JOIN column reference A_WORKFLOW_HISTORY_KEY -> A_ETL_LOAD_SET_KEY, added consistent column mapping and dynamic column list to EXPORT_TABLE_DATA procedure, enhanced DEBUG logging for all export operations' || CHR(10) ||
'v2.1.0 (2025-10-22): Added version tracking and PARTITION_YEAR/PARTITION_MONTH support' || CHR(10) ||
'v2.0.0 (2025-10-01): Separated export functionality from FILE_MANAGER package' || CHR(10);
cgBL CONSTANT VARCHAR2(2) := CHR(13)||CHR(10);
vgMsgTmp VARCHAR2(32000);
---------------------------------------------------------------------------------------------------------------------------
-- TYPE DEFINITIONS FOR PARTITION HANDLING
---------------------------------------------------------------------------------------------------------------------------
/**
* Record type for year/month partition information
**/
TYPE partition_rec IS RECORD (
year VARCHAR2(4),
month VARCHAR2(2)
);
/**
* Table type for collection of partition records
**/
TYPE partition_tab IS TABLE OF partition_rec;
---------------------------------------------------------------------------------------------------------------------------
-- INTERNAL PARALLEL PROCESSING CALLBACK
---------------------------------------------------------------------------------------------------------------------------
/**
* @name EXPORT_PARTITION_PARALLEL
* @desc Internal callback procedure for DBMS_PARALLEL_EXECUTE.
* Processes single partition (year/month) chunk in parallel task.
* Called by DBMS_PARALLEL_EXECUTE framework for each chunk.
* This procedure is PUBLIC because DBMS_PARALLEL_EXECUTE requires it,
* but should NOT be called directly by external code.
* @param pStartId - Chunk start ID (CHUNK_ID from A_PARALLEL_EXPORT_CHUNKS table)
* @param pEndId - Chunk end ID (same as pStartId for single-row chunks)
**/
PROCEDURE EXPORT_PARTITION_PARALLEL (
pStartId IN NUMBER,
pEndId IN NUMBER
);
---------------------------------------------------------------------------------------------------------------------------
-- MAIN EXPORT PROCEDURES
---------------------------------------------------------------------------------------------------------------------------
/**
* @name EXPORT_TABLE_DATA
* @desc Wrapper procedure for DBMS_CLOUD.EXPORT_DATA.
* Exports data into CSV file on OCI infrustructure.
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* @example
* begin
* DATA_EXPORTER.EXPORT_TABLE_DATA(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'csv_exports'
* );
* end;
**/
PROCEDURE EXPORT_TABLE_DATA (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
/**
* @name EXPORT_TABLE_DATA_BY_DATE
* @desc Wrapper procedure for DBMS_CLOUD.EXPORT_DATA.
* Exports data into PARQUET files on OCI infrustructure.
* Each YEAR_MONTH pair goes to seperate file (implicit partitioning).
* Allows specifying custom column list or uses T.* if pColumnList is NULL.
* Validates that all columns in pColumnList exist in the target table.
* Automatically adds 'T.' prefix to column names in pColumnList.
* Supports parallel partition processing via pParallelDegree parameter (default 1, range 1-16).
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* @example
* begin
* DATA_EXPORTER.EXPORT_TABLE_DATA_BY_DATE(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'parquet_exports',
* pColumnList => 'COLUMN1, COLUMN2, COLUMN3', -- Optional
* pMinDate => DATE '2024-01-01',
* pMaxDate => SYSDATE,
* pParallelDegree => 8 -- Optional, default 1, range 1-16
* );
* end;
**/
PROCEDURE EXPORT_TABLE_DATA_BY_DATE (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pColumnList IN VARCHAR2 default NULL,
pMinDate IN DATE default DATE '1900-01-01',
pMaxDate IN DATE default SYSDATE,
pParallelDegree IN NUMBER default 1,
pTemplateTableName IN VARCHAR2 default NULL,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
/**
* @name EXPORT_TABLE_DATA_TO_CSV_BY_DATE
* @desc Exports data to separate CSV files partitioned by year and month.
* Creates one CSV file for each year/month combination found in the data.
* Uses the same date filtering mechanism with CT_ODS.A_LOAD_HISTORY as EXPORT_TABLE_DATA_BY_DATE,
* but exports to CSV format instead of Parquet.
* Supports parallel partition processing via pParallelDegree parameter (1-16).
* File naming pattern: {pFileName}_YYYYMM.csv or {TABLENAME}_YYYYMM.csv (if pFileName is NULL)
* When pRegisterExport=TRUE, successfully exported files are registered in:
* - CT_MRDS.A_SOURCE_FILE_RECEIVED (tracks file location, size, checksum, and metadata)
* @example
* begin
* -- With custom filename
* DATA_EXPORTER.EXPORT_TABLE_DATA_TO_CSV_BY_DATE(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'exports',
* pFileName => 'my_export.csv',
* pMinDate => DATE '2024-01-01',
* pMaxDate => SYSDATE,
* pParallelDegree => 8, -- Optional, default 1, range 1-16
* pRegisterExport => TRUE -- Optional, default FALSE, registers to A_SOURCE_FILE_RECEIVED
* );
*
* -- With auto-generated filename (based on table name only)
* DATA_EXPORTER.EXPORT_TABLE_DATA_TO_CSV_BY_DATE(
* pSchemaName => 'OU_TOP',
* pTableName => 'AGGREGATED_ALLOTMENT',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'ARCHIVE',
* pFolderName => 'exports',
* pMinDate => DATE '2025-09-01',
* pMaxDate => DATE '2025-09-17',
* pRegisterExport => TRUE -- Registers each export to A_SOURCE_FILE_RECEIVED table
* );
* -- This will create files like: AGGREGATED_ALLOTMENT_202509.csv, etc.
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* end;
**/
PROCEDURE EXPORT_TABLE_DATA_TO_CSV_BY_DATE (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pFileName IN VARCHAR2 DEFAULT NULL,
pColumnList IN VARCHAR2 default NULL,
pMinDate IN DATE default DATE '1900-01-01',
pMaxDate IN DATE default SYSDATE,
pParallelDegree IN NUMBER default 1,
pTemplateTableName IN VARCHAR2 default NULL,
pMaxFileSize IN NUMBER default 104857600,
pRegisterExport IN BOOLEAN default FALSE,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
---------------------------------------------------------------------------------------------------------------------------
-- VERSION MANAGEMENT FUNCTIONS
---------------------------------------------------------------------------------------------------------------------------
/**
* Returns the current package version number
* return: Version string in format X.Y.Z (e.g., '2.1.0')
**/
FUNCTION GET_VERSION RETURN VARCHAR2;
/**
* Returns comprehensive build information including version, date, and author
* return: Formatted string with complete build details
**/
FUNCTION GET_BUILD_INFO RETURN VARCHAR2;
/**
* Returns the version history with recent changes
* return: Multi-line string with version history
**/
FUNCTION GET_VERSION_HISTORY RETURN VARCHAR2;
END;
/

1171
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/rollback_version/v2.7.4/ENV_MANAGER.pkb Normal file
View File

File diff suppressed because it is too large Load Diff

625
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/rollback_version/v2.7.4/ENV_MANAGER.pkg Normal file
View File

@@ -0,0 +1,625 @@
create or replace PACKAGE CT_MRDS.ENV_MANAGER
AUTHID CURRENT_USER
AS
/**
* General comment for package: Please put comments for functions and procedures as shown in below example.
* It is a standard.
* The structure of comment is used by GET_PACKAGE_DOCUMENTATION function
* which returns documentation text for confluence page (to Copy-Paste it).
**/
-- Example comment:
/**
* @name EX_PROCEDURE_NAME
* @desc Procedure description
* @example select ENV_MANAGER.EX_PROCEDURE_NAME(pParameter => 129) from dual;
* @ex_rslt Example Result
**/
-- Package Version Information (Semantic Versioning: MAJOR.MINOR.PATCH)
PACKAGE_VERSION CONSTANT VARCHAR2(10) := '3.2.0';
PACKAGE_BUILD_DATE CONSTANT VARCHAR2(20) := '2025-12-20 10:00:00';
PACKAGE_AUTHOR CONSTANT VARCHAR2(100) := 'Grzegorz Michalski';
-- Version History (Latest changes first)
VERSION_HISTORY CONSTANT VARCHAR2(4000) :=
'3.2.0 (2025-12-20): Added error codes for parallel execution support (CODE_INVALID_PARALLEL_DEGREE -20110, CODE_PARALLEL_EXECUTION_FAILED -20111)' || CHR(13)||CHR(10) ||
'3.1.0 (2025-10-22): Added package hash tracking and automatic change detection system (SHA256 hashing)' || CHR(13)||CHR(10) ||
'3.0.0 (2025-10-22): Added package versioning system with centralized version management functions' || CHR(13)||CHR(10) ||
'2.1.0 (2025-10-15): Added ANALYZE_VALIDATION_ERRORS function for comprehensive CSV validation analysis' || CHR(13)||CHR(10) ||
'2.0.0 (2025-10-01): Added LOG_PROCESS_ERROR procedure with enhanced error diagnostics and stack traces' || CHR(13)||CHR(10) ||
'1.5.0 (2025-09-20): Added console logging support with gvConsoleLoggingEnabled configuration' || CHR(13)||CHR(10) ||
'1.0.0 (2025-09-01): Initial release with error management and configuration system';
TYPE Error_Record IS RECORD (
code PLS_INTEGER,
message VARCHAR2(4000)
);
TYPE tErrorList IS TABLE OF Error_Record INDEX BY PLS_INTEGER;
Errors tErrorList;
guid VARCHAR2(32);
gvEnv VARCHAR2(200);
gvUsername VARCHAR2(128);
gvOsuser VARCHAR2(128);
gvMachine VARCHAR2(64);
gvModule VARCHAR2(64);
gvNameSpace VARCHAR2(200);
gvRegion VARCHAR2(200);
gvDataBucketName VARCHAR2(200);
gvInboxBucketName VARCHAR2(200);
gvArchiveBucketName VARCHAR2(200);
gvDataBucketUri VARCHAR2(200);
gvInboxBucketUri VARCHAR2(200);
gvArchiveBucketUri VARCHAR2(200);
gvCredentialName VARCHAR2(200);
-- Overwritten by variable "LoggingEnabled" in A_FILE_MANAGER_CONFIG.CONFIG_VARIABLE table
gvLoggingEnabled VARCHAR2(3) := 'ON'; -- 'ON' or 'OFF'
-- Overwritten by variable "MinLogLevel" in A_FILE_MANAGER_CONFIG.CONFIG_VARIABLE table
-- Possible values: DEBUG ,INFO ,WARNING ,ERROR
gvMinLogLevel VARCHAR2(10) := 'DEBUG';
-- Overwritten by variable "DefaultDateFormat" in A_FILE_MANAGER_CONFIG.CONFIG_VARIABLE table
gvDefaultDateFormat VARCHAR2(200) := 'DD/MM/YYYY HH24:MI:SS';
-- Overwritten by variable "ConsoleLoggingEnabled" in A_FILE_MANAGER_CONFIG.CONFIG_VARIABLE table
gvConsoleLoggingEnabled VARCHAR2(3) := 'ON'; -- 'ON' or 'OFF'
cgBL CONSTANT VARCHAR2(2) := CHR(13)||CHR(10);
vgSourceFileConfigKey PLS_INTEGER;
vgMsgTmp VARCHAR2(32000);
--Exceptions
ERR_EMPTY_FILEURI_AND_RECKEY EXCEPTION;
CODE_EMPTY_FILEURI_AND_RECKEY CONSTANT PLS_INTEGER := -20001;
MSG_EMPTY_FILEURI_AND_RECKEY VARCHAR2(4000) := 'Either pFileUri or pSourceFileReceivedKey must be not null';
PRAGMA EXCEPTION_INIT( ERR_EMPTY_FILEURI_AND_RECKEY
,CODE_EMPTY_FILEURI_AND_RECKEY);
ERR_NO_CONFIG_MATCH_FOR_FILEURI EXCEPTION;
CODE_NO_CONFIG_MATCH_FOR_FILEURI CONSTANT PLS_INTEGER := -20002;
MSG_NO_CONFIG_MATCH_FOR_FILEURI VARCHAR2(4000) := 'No match for source file in A_SOURCE_FILE_CONFIG table'
||cgBL||' The file provided in parameter: pFileUri does not have '
||cgBL||' coresponding configuration in A_SOURCE_FILE_CONFIG table';
PRAGMA EXCEPTION_INIT( ERR_NO_CONFIG_MATCH_FOR_FILEURI
,CODE_NO_CONFIG_MATCH_FOR_FILEURI);
ERR_MULTIPLE_MATCH_FOR_SRCFILE EXCEPTION;
CODE_MULTIPLE_MATCH_FOR_SRCFILE CONSTANT PLS_INTEGER := -20003;
MSG_MULTIPLE_MATCH_FOR_SRCFILE VARCHAR2(4000) := 'Multiple match for source file in A_SOURCE_FILE_CONFIG table';
PRAGMA EXCEPTION_INIT( ERR_MULTIPLE_MATCH_FOR_SRCFILE
,CODE_MULTIPLE_MATCH_FOR_SRCFILE);
ERR_MISSING_COLUMN_DATE_FORMAT EXCEPTION;
CODE_MISSING_COLUMN_DATE_FORMAT CONSTANT PLS_INTEGER := -20004;
MSG_MISSING_COLUMN_DATE_FORMAT VARCHAR2(4000) := 'Missing entry in config table: A_COLUMN_DATE_FORMAT primary key(TEMPLATE_TABLE_NAME, COLUMN_NAME)'
||cgBL||' Remember: each column which data_type IN (''DATE'', ''TIMESTAMP'')'
||cgBL||' should have DateFormat specified in A_COLUMN_DATE_FORMAT table '
||cgBL||' for example: ''YYYY-MM-DD''';
PRAGMA EXCEPTION_INIT( ERR_MISSING_COLUMN_DATE_FORMAT
,CODE_MISSING_COLUMN_DATE_FORMAT);
ERR_MULTIPLE_COLUMN_DATE_FORMAT EXCEPTION;
CODE_MULTIPLE_COLUMN_DATE_FORMAT CONSTANT PLS_INTEGER := -20005;
MSG_MULTIPLE_COLUMN_DATE_FORMAT VARCHAR2(4000) := 'Multiple records for date format in A_COLUMN_DATE_FORMAT table'
||cgBL||' There should be only one format specified for each DAT/TIMESTAMP column';
PRAGMA EXCEPTION_INIT( ERR_MULTIPLE_COLUMN_DATE_FORMAT
,CODE_MULTIPLE_COLUMN_DATE_FORMAT);
ERR_DIDNT_GET_LOAD_OPERATION_ID EXCEPTION;
CODE_DIDNT_GET_LOAD_OPERATION_ID CONSTANT PLS_INTEGER := -20006;
MSG_DIDNT_GET_LOAD_OPERATION_ID VARCHAR2(4000) := 'Didnt get load operation id from external table validation';
PRAGMA EXCEPTION_INIT( ERR_DIDNT_GET_LOAD_OPERATION_ID
,CODE_DIDNT_GET_LOAD_OPERATION_ID);
ERR_NO_CONFIG_FOR_RECEIVED_FILE EXCEPTION;
CODE_NO_CONFIG_FOR_RECEIVED_FILE CONSTANT PLS_INTEGER := -20007;
MSG_NO_CONFIG_FOR_RECEIVED_FILE VARCHAR2(4000) := 'No match for received source file in A_SOURCE_FILE_CONFIG '
||cgBL||' or missing data in A_SOURCE_FILE_RECEIVED table for provided pSourceFileReceivedKey parameter';
PRAGMA EXCEPTION_INIT( ERR_NO_CONFIG_FOR_RECEIVED_FILE
,CODE_NO_CONFIG_FOR_RECEIVED_FILE);
ERR_MULTI_CONFIG_FOR_RECEIVED_FILE EXCEPTION;
CODE_MULTI_CONFIG_FOR_RECEIVED_FILE CONSTANT PLS_INTEGER := -20008;
MSG_MULTI_CONFIG_FOR_RECEIVED_FILE VARCHAR2(4000) := 'Multiple matchs for received source file in A_SOURCE_FILE_CONFIG';
PRAGMA EXCEPTION_INIT( ERR_MULTI_CONFIG_FOR_RECEIVED_FILE
,CODE_MULTI_CONFIG_FOR_RECEIVED_FILE);
ERR_FILE_NOT_FOUND_ON_CLOUD EXCEPTION;
CODE_FILE_NOT_FOUND_ON_CLOUD CONSTANT PLS_INTEGER := -20009;
MSG_FILE_NOT_FOUND_ON_CLOUD VARCHAR2(4000) := 'File not found on the cloud';
PRAGMA EXCEPTION_INIT( ERR_FILE_NOT_FOUND_ON_CLOUD
,CODE_FILE_NOT_FOUND_ON_CLOUD);
ERR_FILE_VALIDATION_FAILED EXCEPTION;
CODE_FILE_VALIDATION_FAILED CONSTANT PLS_INTEGER := -20010;
MSG_FILE_VALIDATION_FAILED VARCHAR2(4000) := 'File validation failed';
PRAGMA EXCEPTION_INIT( ERR_FILE_VALIDATION_FAILED
,CODE_FILE_VALIDATION_FAILED);
ERR_EXCESS_COLUMNS_DETECTED EXCEPTION;
CODE_EXCESS_COLUMNS_DETECTED CONSTANT PLS_INTEGER := -20011;
MSG_EXCESS_COLUMNS_DETECTED VARCHAR2(4000) := 'CSV file contains more columns than template allows';
PRAGMA EXCEPTION_INIT( ERR_EXCESS_COLUMNS_DETECTED
,CODE_EXCESS_COLUMNS_DETECTED);
ERR_NO_CONFIG_MATCH EXCEPTION;
CODE_NO_CONFIG_MATCH CONSTANT PLS_INTEGER := -20012;
MSG_NO_CONFIG_MATCH VARCHAR2(4000) := 'No match for specified parameters in A_SOURCE_FILE_CONFIG table';
PRAGMA EXCEPTION_INIT( ERR_NO_CONFIG_MATCH
,CODE_NO_CONFIG_MATCH);
ERR_UNKNOWN_PREFIX EXCEPTION;
CODE_UNKNOWN_PREFIX CONSTANT PLS_INTEGER := -20013;
MSG_UNKNOWN_PREFIX VARCHAR2(4000) := 'Unknown prefix';
PRAGMA EXCEPTION_INIT( ERR_UNKNOWN_PREFIX
,CODE_UNKNOWN_PREFIX);
ERR_TABLE_NOT_EXISTS EXCEPTION;
CODE_TABLE_NOT_EXISTS CONSTANT PLS_INTEGER := -20014;
MSG_TABLE_NOT_EXISTS VARCHAR2(4000) := 'Table does not exist';
PRAGMA EXCEPTION_INIT( ERR_TABLE_NOT_EXISTS
,CODE_TABLE_NOT_EXISTS);
ERR_COLUMN_NOT_EXISTS EXCEPTION;
CODE_COLUMN_NOT_EXISTS CONSTANT PLS_INTEGER := -20015;
MSG_COLUMN_NOT_EXISTS VARCHAR2(4000) := 'Column does not exist in table';
PRAGMA EXCEPTION_INIT( ERR_COLUMN_NOT_EXISTS
,CODE_COLUMN_NOT_EXISTS);
ERR_UNSUPPORTED_DATA_TYPE EXCEPTION;
CODE_UNSUPPORTED_DATA_TYPE CONSTANT PLS_INTEGER := -20016;
MSG_UNSUPPORTED_DATA_TYPE VARCHAR2(4000) := 'Unsupported data type';
PRAGMA EXCEPTION_INIT( ERR_UNSUPPORTED_DATA_TYPE
,CODE_UNSUPPORTED_DATA_TYPE);
ERR_MISSING_SOURCE_KEY EXCEPTION;
CODE_MISSING_SOURCE_KEY CONSTANT PLS_INTEGER := -20017;
MSG_MISSING_SOURCE_KEY VARCHAR2(4000) := 'The Source was not found in parent table A_SOURCE';
PRAGMA EXCEPTION_INIT( ERR_MISSING_SOURCE_KEY
,CODE_MISSING_SOURCE_KEY);
ERR_NULL_SOURCE_FILE_CONFIG_KEY EXCEPTION;
CODE_NULL_SOURCE_FILE_CONFIG_KEY CONSTANT PLS_INTEGER := -20018;
MSG_NULL_SOURCE_FILE_CONFIG_KEY VARCHAR2(4000) := 'No entry in A_SOURCE_FILE_CONFIG table for specified A_SOURCE_FILE_CONFIG_KEY';
PRAGMA EXCEPTION_INIT( ERR_NULL_SOURCE_FILE_CONFIG_KEY
,CODE_NULL_SOURCE_FILE_CONFIG_KEY);
ERR_DUPLICATED_SOURCE_KEY EXCEPTION;
CODE_DUPLICATED_SOURCE_KEY CONSTANT PLS_INTEGER := -20019;
MSG_DUPLICATED_SOURCE_KEY VARCHAR2(4000) := 'The Source already exists in the A_SOURCE table';
PRAGMA EXCEPTION_INIT( ERR_DUPLICATED_SOURCE_KEY
,CODE_DUPLICATED_SOURCE_KEY);
ERR_MISSING_CONTAINER_CONFIG EXCEPTION;
CODE_MISSING_CONTAINER_CONFIG CONSTANT PLS_INTEGER := -20020;
MSG_MISSING_CONTAINER_CONFIG VARCHAR2(4000) := 'No match in A_SOURCE_FILE_CONFIG table where SOURCE_FILE_TYPE=''CONTAINER'' and specified SOURCE_FILE_ID';
PRAGMA EXCEPTION_INIT( ERR_MISSING_CONTAINER_CONFIG
,CODE_MISSING_CONTAINER_CONFIG);
ERR_MULTIPLE_CONTAINER_ENTRIES EXCEPTION;
CODE_MULTIPLE_CONTAINER_ENTRIES CONSTANT PLS_INTEGER := -20021;
MSG_MULTIPLE_CONTAINER_ENTRIES VARCHAR2(4000) := 'Multiple matches in A_SOURCE_FILE_CONFIG table where SOURCE_FILE_TYPE=''CONTAINER'' and specified SOURCE_FILE_ID';
PRAGMA EXCEPTION_INIT( ERR_MULTIPLE_CONTAINER_ENTRIES
,CODE_MULTIPLE_CONTAINER_ENTRIES);
ERR_WRONG_DESTINATION_PARAM EXCEPTION;
CODE_WRONG_DESTINATION_PARAM CONSTANT PLS_INTEGER := -20022;
MSG_WRONG_DESTINATION_PARAM VARCHAR2(4000) := 'Wrong destination parameter provided.';
PRAGMA EXCEPTION_INIT( ERR_WRONG_DESTINATION_PARAM
,CODE_WRONG_DESTINATION_PARAM);
ERR_FILE_NOT_EXISTS_ON_CLOUD EXCEPTION;
CODE_FILE_NOT_EXISTS_ON_CLOUD CONSTANT PLS_INTEGER := -20023;
MSG_FILE_NOT_EXISTS_ON_CLOUD VARCHAR2(4000) := 'File not exists on cloud.';
PRAGMA EXCEPTION_INIT( ERR_FILE_NOT_EXISTS_ON_CLOUD
,CODE_FILE_NOT_EXISTS_ON_CLOUD);
ERR_FILE_ALREADY_REGISTERED EXCEPTION;
CODE_FILE_ALREADY_REGISTERED CONSTANT PLS_INTEGER := -20024;
MSG_FILE_ALREADY_REGISTERED VARCHAR2(4000) := 'File already registered in A_SOURCE_FILE_RECEIVED table.';
PRAGMA EXCEPTION_INIT( ERR_FILE_ALREADY_REGISTERED
,CODE_FILE_ALREADY_REGISTERED);
ERR_WRONG_DATE_TIMESTAMP_FORMAT EXCEPTION;
CODE_WRONG_DATE_TIMESTAMP_FORMAT CONSTANT PLS_INTEGER := -20025;
MSG_WRONG_DATE_TIMESTAMP_FORMAT VARCHAR2(4000) := 'Provided DATE or TIMESTAMP format has errors (possible duplicated codes, ex: ''DD'').';
PRAGMA EXCEPTION_INIT( ERR_WRONG_DATE_TIMESTAMP_FORMAT
,CODE_WRONG_DATE_TIMESTAMP_FORMAT);
ERR_ENVIRONMENT_NOT_SET EXCEPTION;
CODE_ENVIRONMENT_NOT_SET CONSTANT PLS_INTEGER := -20026;
MSG_ENVIRONMENT_NOT_SET VARCHAR2(4000) := 'EnvironmentID not set'
||cgBL||' Information about environment is needed to get proper configuration values.'
||cgBL||' It can be set up in two different ways:'
||cgBL||' 1. Set it on session level: execute DBMS_SESSION.SET_IDENTIFIER (client_id => ''dev'')'
||cgBL||' 2. Set it on configuration level: Insert into CT_MRDS.A_FILE_MANAGER_CONFIG (ENVIRONMENT_ID,CONFIG_VARIABLE,CONFIG_VARIABLE_VALUE) values (''default'',''environment_id'',''dev'')'
||cgBL||' Session level setup (1.) takes precedence over configuration level one (2.)'
;
PRAGMA EXCEPTION_INIT( ERR_ENVIRONMENT_NOT_SET
,CODE_ENVIRONMENT_NOT_SET);
ERR_CONFIG_VARIABLE_NOT_SET EXCEPTION;
CODE_CONFIG_VARIABLE_NOT_SET CONSTANT PLS_INTEGER := -20027;
MSG_CONFIG_VARIABLE_NOT_SET VARCHAR2(4000) := 'Missing configuration value in A_FILE_MANAGER_CONFIG';
PRAGMA EXCEPTION_INIT( ERR_CONFIG_VARIABLE_NOT_SET
,CODE_CONFIG_VARIABLE_NOT_SET);
ERR_NOT_INPUT_SOURCE_FILE_TYPE EXCEPTION;
CODE_NOT_INPUT_SOURCE_FILE_TYPE CONSTANT PLS_INTEGER := -20028;
MSG_NOT_INPUT_SOURCE_FILE_TYPE VARCHAR2(4000) := 'Archival can be executed only for A_SOURCE_FILE_CONFIG_KEY where SOURCE_FILE_TYPE=''INPUT''';
PRAGMA EXCEPTION_INIT( ERR_NOT_INPUT_SOURCE_FILE_TYPE
,CODE_NOT_INPUT_SOURCE_FILE_TYPE);
ERR_EXP_DATA_FOR_ARCH_FAILED EXCEPTION;
CODE_EXP_DATA_FOR_ARCH_FAILED CONSTANT PLS_INTEGER := -20029;
MSG_EXP_DATA_FOR_ARCH_FAILED VARCHAR2(4000) := 'Export data for archival failed.';
PRAGMA EXCEPTION_INIT( ERR_EXP_DATA_FOR_ARCH_FAILED
,CODE_EXP_DATA_FOR_ARCH_FAILED);
ERR_RESTORE_FILE_FROM_TRASH EXCEPTION;
CODE_RESTORE_FILE_FROM_TRASH CONSTANT PLS_INTEGER := -20030;
MSG_RESTORE_FILE_FROM_TRASH VARCHAR2(4000) := 'Unexpected issues occured while archival process. Restoration of exported files failed.';
PRAGMA EXCEPTION_INIT( ERR_RESTORE_FILE_FROM_TRASH
,CODE_RESTORE_FILE_FROM_TRASH);
ERR_CHANGE_STAT_TO_ARCHIVED_FAILED EXCEPTION;
CODE_CHANGE_STAT_TO_ARCHIVED_FAILED CONSTANT PLS_INTEGER := -20031;
MSG_CHANGE_STAT_TO_ARCHIVED_FAILED VARCHAR2(4000) := 'Failed to change file status to: ARCHIVED in A_SOURCE_FILE_RECEIVED table.';
PRAGMA EXCEPTION_INIT( ERR_CHANGE_STAT_TO_ARCHIVED_FAILED
,CODE_CHANGE_STAT_TO_ARCHIVED_FAILED);
ERR_MOVE_FILE_TO_TRASH_FAILED EXCEPTION;
CODE_MOVE_FILE_TO_TRASH_FAILED CONSTANT PLS_INTEGER := -20032;
MSG_MOVE_FILE_TO_TRASH_FAILED VARCHAR2(4000) := 'FAILED to move file to TRASH before DROPPING it.';
PRAGMA EXCEPTION_INIT( ERR_MOVE_FILE_TO_TRASH_FAILED
,CODE_MOVE_FILE_TO_TRASH_FAILED);
ERR_DROP_EXPORTED_FILES_FAILED EXCEPTION;
CODE_DROP_EXPORTED_FILES_FAILED CONSTANT PLS_INTEGER := -20033;
MSG_DROP_EXPORTED_FILES_FAILED VARCHAR2(4000) := 'FAILED to move file to TRASH before DROPPING it.';
PRAGMA EXCEPTION_INIT( ERR_DROP_EXPORTED_FILES_FAILED
,CODE_DROP_EXPORTED_FILES_FAILED);
ERR_INVALID_BUCKET_AREA EXCEPTION;
CODE_INVALID_BUCKET_AREA CONSTANT PLS_INTEGER := -20034;
MSG_INVALID_BUCKET_AREA VARCHAR2(4000) := 'Invalid bucket area specified. Valid values: INBOX, ODS, DATA, ARCHIVE';
PRAGMA EXCEPTION_INIT( ERR_INVALID_BUCKET_AREA
,CODE_INVALID_BUCKET_AREA);
ERR_INVALID_PARALLEL_DEGREE EXCEPTION;
CODE_INVALID_PARALLEL_DEGREE CONSTANT PLS_INTEGER := -20110;
MSG_INVALID_PARALLEL_DEGREE VARCHAR2(4000) := 'Invalid parallel degree parameter. Must be between 1 and 16';
PRAGMA EXCEPTION_INIT( ERR_INVALID_PARALLEL_DEGREE
,CODE_INVALID_PARALLEL_DEGREE);
ERR_PARALLEL_EXECUTION_FAILED EXCEPTION;
CODE_PARALLEL_EXECUTION_FAILED CONSTANT PLS_INTEGER := -20111;
MSG_PARALLEL_EXECUTION_FAILED VARCHAR2(4000) := 'Parallel execution failed';
PRAGMA EXCEPTION_INIT( ERR_PARALLEL_EXECUTION_FAILED
,CODE_PARALLEL_EXECUTION_FAILED);
ERR_UNKNOWN EXCEPTION;
CODE_UNKNOWN CONSTANT PLS_INTEGER := -20999;
MSG_UNKNOWN VARCHAR2(4000) := 'Unknown Error Occured';
PRAGMA EXCEPTION_INIT( ERR_UNKNOWN
,CODE_UNKNOWN);
---------------------------------------------------------------------------------------------------------------------------
---------------------------------------------------------------------------------------------------------------------------
/**
* @name LOG_PROCESS_EVENT
* @desc Insert a new log record into A_PROCESS_LOG table.
* Also outputs to console if gvConsoleLoggingEnabled = 'ON'.
* Respects logging level configuration (gvMinLogLevel).
* @example ENV_MANAGER.LOG_PROCESS_EVENT('Process completed successfully', 'INFO', 'pParam1=value1');
* @ex_rslt Record inserted into A_PROCESS_LOG table and optionally displayed in console output
**/
PROCEDURE LOG_PROCESS_EVENT (
pLogMessage VARCHAR2
,pLogLevel VARCHAR2 DEFAULT 'ERROR'
,pParameters VARCHAR2 DEFAULT NULL
,pProcessName VARCHAR2 DEFAULT 'FILE_MANAGER'
);
/**
* @name LOG_PROCESS_ERROR
* @desc Insert a detailed error record into A_PROCESS_LOG table with full stack trace, backtrace, and call stack.
* This procedure captures comprehensive error information for debugging purposes while
* allowing clean user-facing error messages to be raised separately.
* @param pLogMessage - Base error message description
* @param pParameters - Procedure parameters for context
* @param pProcessName - Name of the calling process/package
* @ex_rslt Record inserted into A_PROCESS_LOG table with complete error stack information
*/
PROCEDURE LOG_PROCESS_ERROR (
pLogMessage VARCHAR2
,pParameters VARCHAR2 DEFAULT NULL
,pProcessName VARCHAR2 DEFAULT 'FILE_MANAGER'
);
/**
* @name INIT_ERRORS
* @desc Loads data into Errors array.
* Errors array is a list of Record(Error_Code, Error_Message) index by Error_Code.
* Called automatically during package initialization.
* @example Called automatically when package is first referenced
* @ex_rslt Errors array populated with all error codes and messages
**/
PROCEDURE INIT_ERRORS;
/**
* @name GET_DEFAULT_ENV
* @desc It returns string with name of default environment.
* Return string is A_FILE_MANAGER_CONFIG.ENVIRONMENT_ID value.
* @example select ENV_MANAGER.GET_DEFAULT_ENV() from dual;
* @ex_rslt dev
**/
FUNCTION GET_DEFAULT_ENV
RETURN VARCHAR2;
/**
* @name INIT_VARIABLES
* @desc For specified pEnv parameter (A_FILE_MANAGER_CONFIG.ENVIRONMENT_ID)
* Assign values to following global package variables:
* - gvNameSpace
* - gvRegion
* - gvCredentialName
* - gvInboxBucketName
* - gvDataBucketName
* - gvArchiveBucketName
* - gvInboxBucketUri
* - gvDataBucketUri
* - gvArchiveBucketUri
* - gvLoggingEnabled
* - gvMinLogLevel
* - gvDefaultDateFormat
* - gvConsoleLoggingEnabled
**/
PROCEDURE INIT_VARIABLES(
pEnv VARCHAR2
);
/**
* @name GET_ERROR_MESSAGE
* @desc It returns string with error message for specified pCode (Error_Code).
* Error message is take from Errors Array loaded by INIT_ERRORS procedure
* @example select ENV_MANAGER.GET_ERROR_MESSAGE(pCode => -20009) from dual;
* @ex_rslt File not found on the cloud
**/
FUNCTION GET_ERROR_MESSAGE(
pCode PLS_INTEGER
) RETURN VARCHAR2;
/**
* @name GET_ERROR_STACK
* @desc It returns string with all possible error stack info.
* Error message is take from Errors Array loaded by INIT_ERRORS procedure
* @example
* select ENV_MANAGER.GET_ERROR_STACK(
* pFormat => 'OUTPUT'
* ,pCode => -20009
* ,pSourceFileReceivedKey => NULL)
* from dual
* @ex_rslt
* ------------------------------------------------------+
* Error Message:
* ORA-0000: normal, successful completion
* -------------------------------------------------------
* Error Stack:
* -------------------------------------------------------
* Error Backtrace:
* ------------------------------------------------------+
**/
FUNCTION GET_ERROR_STACK(
pFormat VARCHAR2
,pCode PLS_INTEGER
,pSourceFileReceivedKey CT_MRDS.A_SOURCE_FILE_RECEIVED.A_SOURCE_FILE_RECEIVED_KEY%TYPE DEFAULT NULL
) RETURN VARCHAR2;
/**
* @name FORMAT_PARAMETERS
* @desc Formats parameter list for logging purposes.
* Converts SYS.ODCIVARCHAR2LIST to formatted string with proper NULL handling.
* @example select ENV_MANAGER.FORMAT_PARAMETERS(SYS.ODCIVARCHAR2LIST('param1=value1', 'param2=NULL')) from dual;
* @ex_rslt param1=value1 ,
* param2=NULL
**/
FUNCTION FORMAT_PARAMETERS(
pParameterList SYS.ODCIVARCHAR2LIST
) RETURN VARCHAR2;
/**
* @name ANALYZE_VALIDATION_ERRORS
* @desc Analyzes CSV validation errors and generates detailed diagnostic report.
* Compares CSV structure with template table and provides specific error analysis.
* Includes suggested solutions for common validation issues.
* @param pValidationLogTable - Name of validation log table (e.g., VALIDATE$242_LOG)
* @param pTemplateSchema - Schema of template table (e.g., CT_ET_TEMPLATES)
* @param pTemplateTable - Name of template table (e.g., MOCK_PROC_TABLE)
* @param pCsvFileUri - URI of CSV file being validated
* @example SELECT ENV_MANAGER.ANALYZE_VALIDATION_ERRORS('VALIDATE$242_LOG', 'CT_ET_TEMPLATES', 'MOCK_PROC_TABLE', 'https://...') FROM DUAL;
* @ex_rslt Detailed validation analysis report with column mismatches and solutions
**/
FUNCTION ANALYZE_VALIDATION_ERRORS(
pValidationLogTable VARCHAR2,
pTemplateSchema VARCHAR2,
pTemplateTable VARCHAR2,
pCsvFileUri VARCHAR2
) RETURN VARCHAR2;
---------------------------------------------------------------------------------------------------------------------------
-- PACKAGE VERSION MANAGEMENT FUNCTIONS
---------------------------------------------------------------------------------------------------------------------------
/**
* @name GET_VERSION
* @desc Returns the current version number of the ENV_MANAGER package.
* Uses semantic versioning format (MAJOR.MINOR.PATCH).
* @example SELECT ENV_MANAGER.GET_VERSION() FROM DUAL;
* @ex_rslt 3.0.0
**/
FUNCTION GET_VERSION RETURN VARCHAR2;
/**
* @name GET_BUILD_INFO
* @desc Returns comprehensive build information including version, build date, and author.
* Formatted for display in logs or monitoring systems.
* @example SELECT ENV_MANAGER.GET_BUILD_INFO() FROM DUAL;
* @ex_rslt Package: ENV_MANAGER
* Version: 3.0.0
* Build Date: 2025-10-22 16:00:00
* Author: Grzegorz Michalski
**/
FUNCTION GET_BUILD_INFO RETURN VARCHAR2;
/**
* @name GET_VERSION_HISTORY
* @desc Returns complete version history with all releases and changes.
* Shows evolution of package features over time.
* @example SELECT ENV_MANAGER.GET_VERSION_HISTORY() FROM DUAL;
* @ex_rslt ENV_MANAGER Version History:
* 3.0.0 (2025-10-22): Added package versioning system...
* 2.1.0 (2025-10-15): Added ANALYZE_VALIDATION_ERRORS function...
**/
FUNCTION GET_VERSION_HISTORY RETURN VARCHAR2;
/**
* @name GET_PACKAGE_VERSION_INFO
* @desc Universal function to get formatted version information for any package.
* This centralized function is used by all packages in the system.
* @param pPackageName - Name of the package
* @param pVersion - Version string (MAJOR.MINOR.PATCH format)
* @param pBuildDate - Build date timestamp
* @param pAuthor - Package author name
* @example SELECT ENV_MANAGER.GET_PACKAGE_VERSION_INFO('FILE_MANAGER', '2.1.0', '2025-10-22 15:00:00', 'Grzegorz Michalski') FROM DUAL;
* @ex_rslt Package: FILE_MANAGER
* Version: 2.1.0
* Build Date: 2025-10-22 15:00:00
* Author: Grzegorz Michalski
**/
FUNCTION GET_PACKAGE_VERSION_INFO(
pPackageName VARCHAR2,
pVersion VARCHAR2,
pBuildDate VARCHAR2,
pAuthor VARCHAR2
) RETURN VARCHAR2;
/**
* @name FORMAT_VERSION_HISTORY
* @desc Universal function to format version history for any package.
* Adds package name header and proper formatting.
* @param pPackageName - Name of the package
* @param pVersionHistory - Complete version history text
* @example SELECT ENV_MANAGER.FORMAT_VERSION_HISTORY('FILE_MANAGER', '2.1.0 (2025-10-22): Export procedures...') FROM DUAL;
* @ex_rslt FILE_MANAGER Version History:
* 2.1.0 (2025-10-22): Export procedures...
**/
FUNCTION FORMAT_VERSION_HISTORY(
pPackageName VARCHAR2,
pVersionHistory VARCHAR2
) RETURN VARCHAR2;
---------------------------------------------------------------------------------------------------------------------------
-- PACKAGE HASH + CHANGE DETECTION FUNCTIONS
---------------------------------------------------------------------------------------------------------------------------
/**
* @name CALCULATE_PACKAGE_HASH
* @desc Calculates SHA256 hash of package source code from ALL_SOURCE.
* Returns hash for both SPEC and BODY (if exists).
* Used for automatic change detection.
* @param pPackageOwner - Schema owner of the package
* @param pPackageName - Name of the package
* @param pPackageType - Type of package code ('PACKAGE' for SPEC, 'PACKAGE BODY' for BODY)
* @example SELECT ENV_MANAGER.CALCULATE_PACKAGE_HASH('CT_MRDS', 'FILE_MANAGER', 'PACKAGE') FROM DUAL;
* @ex_rslt A7B3C5D9E8F1234567890ABCDEF... (64-character SHA256 hash)
**/
FUNCTION CALCULATE_PACKAGE_HASH(
pPackageOwner VARCHAR2,
pPackageName VARCHAR2,
pPackageType VARCHAR2 -- 'PACKAGE' or 'PACKAGE BODY'
) RETURN VARCHAR2;
/**
* @name TRACK_PACKAGE_VERSION
* @desc Records package version and source code hash in A_PACKAGE_VERSION_TRACKING table.
* Automatically detects if source code changed without version update.
* Should be called after every package deployment.
* @param pPackageOwner - Schema owner of the package
* @param pPackageName - Name of the package
* @param pPackageVersion - Current version from PACKAGE_VERSION constant
* @param pPackageBuildDate - Build date from PACKAGE_BUILD_DATE constant
* @param pPackageAuthor - Author from PACKAGE_AUTHOR constant
* @example EXEC ENV_MANAGER.TRACK_PACKAGE_VERSION('CT_MRDS', 'FILE_MANAGER', '3.2.0', '2025-10-22 16:30:00', 'Grzegorz Michalski');
* @ex_rslt Record inserted into A_PACKAGE_VERSION_TRACKING with change detection status
**/
PROCEDURE TRACK_PACKAGE_VERSION(
pPackageOwner VARCHAR2,
pPackageName VARCHAR2,
pPackageVersion VARCHAR2,
pPackageBuildDate VARCHAR2,
pPackageAuthor VARCHAR2
);
/**
* @name CHECK_PACKAGE_CHANGES
* @desc Checks if package source code has changed since last tracking.
* Compares current hash with last recorded hash in A_PACKAGE_VERSION_TRACKING.
* Returns detailed change detection report.
* @param pPackageOwner - Schema owner of the package
* @param pPackageName - Name of the package
* @example SELECT ENV_MANAGER.CHECK_PACKAGE_CHANGES('CT_MRDS', 'FILE_MANAGER') FROM DUAL;
* @ex_rslt WARNING: Package changed without version update!
* Last Version: 3.2.0
* Current Hash (SPEC): A7B3C5D9...
* Last Hash (SPEC): B8C4D6E0...
* RECOMMENDATION: Update PACKAGE_VERSION and PACKAGE_BUILD_DATE
**/
FUNCTION CHECK_PACKAGE_CHANGES(
pPackageOwner VARCHAR2,
pPackageName VARCHAR2
) RETURN VARCHAR2;
/**
* @name GET_PACKAGE_HASH_INFO
* @desc Returns formatted information about package hash and tracking history.
* Includes current hash, last tracked hash, and change detection status.
* @param pPackageOwner - Schema owner of the package
* @param pPackageName - Name of the package
* @example SELECT ENV_MANAGER.GET_PACKAGE_HASH_INFO('CT_MRDS', 'FILE_MANAGER') FROM DUAL;
* @ex_rslt Package: CT_MRDS.FILE_MANAGER
* Current Version: 3.2.0
* Current Hash (SPEC): A7B3C5D9...
* Last Tracked: 2025-10-22 16:30:00
* Status: OK - No changes detected
**/
FUNCTION GET_PACKAGE_HASH_INFO(
pPackageOwner VARCHAR2,
pPackageName VARCHAR2
) RETURN VARCHAR2;
END ENV_MANAGER;
/

1451
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/rollback_version/v2.8.0-deprecated/DATA_EXPORTER.pkb Normal file
View File

File diff suppressed because it is too large Load Diff

227
MARS_Packages/REL01_ADDITIONS/MARS-835-PREHOOK/rollback_version/v2.8.0-deprecated/DATA_EXPORTER.pkg Normal file
View File

@@ -0,0 +1,227 @@
create or replace PACKAGE CT_MRDS.DATA_EXPORTER
AUTHID CURRENT_USER
AS
/**
* Data Export Package: Provides comprehensive data export capabilities to various formats (CSV, Parquet)
* with support for cloud storage integration via Oracle Cloud Infrastructure (OCI).
* The structure of comment is used by GET_PACKAGE_DOCUMENTATION function
* which returns documentation text for confluence page (to Copy-Paste it).
**/
-- Package Version Information (Semantic Versioning: MAJOR.MINOR.PATCH)
PACKAGE_VERSION CONSTANT VARCHAR2(10) := '2.8.0';
PACKAGE_BUILD_DATE CONSTANT VARCHAR2(20) := '2026-02-10 11:00:00';
PACKAGE_AUTHOR CONSTANT VARCHAR2(100) := 'Grzegorz Michalski';
cgBL CONSTANT VARCHAR2(2) := CHR(13)||CHR(10);
-- Version History (Latest changes first)
VERSION_HISTORY CONSTANT VARCHAR2(4000) :=
'v2.8.0 (2026-02-10): CRITICAL FIX - Removed duplicate post-export registration code that conflicted with per-partition registration. Post-export registration (SERVICE_NAME=DATA_EXPORTER, WORKFLOW_START=SYSTIMESTAMP) removed. Per-partition registration (SERVICE_NAME=CSV_EXPORT, WORKFLOW_START=partition_date) now executes exclusively. Prevents duplicate workflow records and ensures CSV files contain constant workflow keys instead of A_ETL_LOAD_SET_FK aliases.' || cgBL ||
'v2.7.0 (2026-02-09): NEW FEATURE - Added pRegisterExport parameter to EXPORT_TABLE_DATA_TO_CSV_BY_DATE. When TRUE, successfully exported files are registered in A_WORKFLOW_HISTORY (one record per YEAR/MONTH) and A_SOURCE_FILE_RECEIVED tables for tracking and audit purposes.' || cgBL ||
'v2.6.3 (2026-01-28): COMPILATION FIX - Resolved ORA-00904 error in EXPORT_PARTITION_PARALLEL. SQLERRM and DBMS_UTILITY.FORMAT_ERROR_BACKTRACE cannot be used directly in SQL UPDATE statements. Now properly assigned to vgMsgTmp variable before UPDATE.' || cgBL ||
'v2.6.2 (2026-01-28): CRITICAL FIX - Race condition when multiple exports run simultaneously. Changed DELETE to filter by age (>24h) instead of deleting all COMPLETED chunks. Prevents concurrent sessions from deleting each other chunks. Session-safe cleanup with TASK_NAME filtering. Enables true parallel execution of multiple export jobs.' || cgBL ||
'v2.6.1 (2026-01-28): Added DELETE_FAILED_EXPORT_FILE procedure to clean up partial/corrupted files before retry. When partition fails mid-export, partial file is deleted before retry to prevent Oracle from creating _1 suffixed duplicates. Ensures clean retry without orphaned files in OCI bucket.' || cgBL ||
'v2.6.0 (2026-01-28): CRITICAL FIX - Added STATUS tracking to A_PARALLEL_EXPORT_CHUNKS table to prevent data duplication on retry. System now restarts ONLY failed partitions instead of re-exporting all data. Added ERROR_MESSAGE and EXPORT_TIMESTAMP columns for better error handling and monitoring. Prevents duplicate file creation when parallel tasks fail (e.g., 22 partitions with 16 threads, 3 failures no longer duplicates 19 successful exports).' || cgBL ||
'v2.5.0 (2026-01-26): Added recorddelimiter parameter with CRLF (CHR(13)||CHR(10)) for CSV exports to ensure Windows-compatible line endings. Improves cross-platform compatibility when CSV files are opened in Windows applications (Notepad, Excel).' || cgBL ||
'v2.4.0 (2026-01-11): Added pTemplateTableName parameter for per-column date format configuration. Implements dynamic query building with TO_CHAR for each date/timestamp column using FILE_MANAGER.GET_DATE_FORMAT. Supports 3-tier hierarchy: column-specific, template DEFAULT, global fallback. Eliminates single dateformat limitation of DBMS_CLOUD.EXPORT_DATA.' || cgBL ||
'v2.3.0 (2025-12-20): Added parallel partition processing using DBMS_PARALLEL_EXECUTE. New pParallelDegree parameter (1-16, default 1) for EXPORT_TABLE_DATA_BY_DATE and EXPORT_TABLE_DATA_TO_CSV_BY_DATE procedures. Each year/month partition processed in separate thread for improved performance.' || cgBL ||
'v2.2.0 (2025-12-19): DRY refactoring - extracted shared helper functions (sanitizeFilename, VALIDATE_TABLE_AND_COLUMNS, GET_PARTITIONS, EXPORT_SINGLE_PARTITION worker procedure). Reduced code duplication by ~400 lines. Prepared architecture for v2.3.0 parallel processing.' || cgBL ||
'v2.1.1 (2025-12-04): Fixed JOIN column reference A_WORKFLOW_HISTORY_KEY -> A_ETL_LOAD_SET_KEY, added consistent column mapping and dynamic column list to EXPORT_TABLE_DATA procedure, enhanced DEBUG logging for all export operations' || cgBL ||
'v2.1.0 (2025-10-22): Added version tracking and PARTITION_YEAR/PARTITION_MONTH support' || cgBL ||
'v2.0.0 (2025-10-01): Separated export functionality from FILE_MANAGER package';
vgMsgTmp VARCHAR2(32000);
---------------------------------------------------------------------------------------------------------------------------
-- TYPE DEFINITIONS FOR PARTITION HANDLING
---------------------------------------------------------------------------------------------------------------------------
/**
* Record type for year/month partition information
**/
TYPE partition_rec IS RECORD (
year VARCHAR2(4),
month VARCHAR2(2)
);
/**
* Table type for collection of partition records
**/
TYPE partition_tab IS TABLE OF partition_rec;
---------------------------------------------------------------------------------------------------------------------------
-- INTERNAL PARALLEL PROCESSING CALLBACK
---------------------------------------------------------------------------------------------------------------------------
/**
* @name EXPORT_PARTITION_PARALLEL
* @desc Internal callback procedure for DBMS_PARALLEL_EXECUTE.
* Processes single partition (year/month) chunk in parallel task.
* Called by DBMS_PARALLEL_EXECUTE framework for each chunk.
* This procedure is PUBLIC because DBMS_PARALLEL_EXECUTE requires it,
* but should NOT be called directly by external code.
* @param pStartId - Chunk start ID (CHUNK_ID from A_PARALLEL_EXPORT_CHUNKS table)
* @param pEndId - Chunk end ID (same as pStartId for single-row chunks)
**/
PROCEDURE EXPORT_PARTITION_PARALLEL (
pStartId IN NUMBER,
pEndId IN NUMBER
);
---------------------------------------------------------------------------------------------------------------------------
-- MAIN EXPORT PROCEDURES
---------------------------------------------------------------------------------------------------------------------------
/**
* @name EXPORT_TABLE_DATA
* @desc Wrapper procedure for DBMS_CLOUD.EXPORT_DATA.
* Exports data into CSV file on OCI infrustructure.
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* @example
* begin
* DATA_EXPORTER.EXPORT_TABLE_DATA(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'csv_exports'
* );
* end;
**/
PROCEDURE EXPORT_TABLE_DATA (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
/**
* @name EXPORT_TABLE_DATA_BY_DATE
* @desc Wrapper procedure for DBMS_CLOUD.EXPORT_DATA.
* Exports data into PARQUET files on OCI infrustructure.
* Each YEAR_MONTH pair goes to seperate file (implicit partitioning).
* Allows specifying custom column list or uses T.* if pColumnList is NULL.
* Validates that all columns in pColumnList exist in the target table.
* Automatically adds 'T.' prefix to column names in pColumnList.
* Supports parallel partition processing via pParallelDegree parameter (default 1, range 1-16).
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* @example
* begin
* DATA_EXPORTER.EXPORT_TABLE_DATA_BY_DATE(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'parquet_exports',
* pColumnList => 'COLUMN1, COLUMN2, COLUMN3', -- Optional
* pMinDate => DATE '2024-01-01',
* pMaxDate => SYSDATE,
* pParallelDegree => 8 -- Optional, default 1, range 1-16
* );
* end;
**/
PROCEDURE EXPORT_TABLE_DATA_BY_DATE (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pColumnList IN VARCHAR2 default NULL,
pMinDate IN DATE default DATE '1900-01-01',
pMaxDate IN DATE default SYSDATE,
pParallelDegree IN NUMBER default 1,
pTemplateTableName IN VARCHAR2 default NULL,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
/**
* @name EXPORT_TABLE_DATA_TO_CSV_BY_DATE
* @desc Exports data to separate CSV files partitioned by year and month.
* Creates one CSV file for each year/month combination found in the data.
* Uses the same date filtering mechanism with CT_ODS.A_LOAD_HISTORY as EXPORT_TABLE_DATA_BY_DATE,
* but exports to CSV format instead of Parquet.
* Supports parallel partition processing via pParallelDegree parameter (1-16).
* File naming pattern: {pFileName}_YYYYMM.csv or {TABLENAME}_YYYYMM.csv (if pFileName is NULL)
* When pRegisterExport=TRUE, successfully exported files are registered in:
* - CT_MRDS.A_WORKFLOW_HISTORY (one record per YEAR/MONTH with export timestamp)
* - CT_MRDS.A_SOURCE_FILE_RECEIVED (tracks file location and partition info)
* @example
* begin
* -- With custom filename
* DATA_EXPORTER.EXPORT_TABLE_DATA_TO_CSV_BY_DATE(
* pSchemaName => 'CT_MRDS',
* pTableName => 'MY_TABLE',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'DATA',
* pFolderName => 'exports',
* pFileName => 'my_export.csv',
* pMinDate => DATE '2024-01-01',
* pMaxDate => SYSDATE,
* pParallelDegree => 8, -- Optional, default 1, range 1-16
* pRegisterExport => TRUE -- Optional, default FALSE, registers to A_WORKFLOW_HISTORY and A_SOURCE_FILE_RECEIVED
* );
*
* -- With auto-generated filename (based on table name only)
* DATA_EXPORTER.EXPORT_TABLE_DATA_TO_CSV_BY_DATE(
* pSchemaName => 'OU_TOP',
* pTableName => 'AGGREGATED_ALLOTMENT',
* pKeyColumnName => 'A_ETL_LOAD_SET_KEY_FK',
* pBucketArea => 'ARCHIVE',
* pFolderName => 'exports',
* pMinDate => DATE '2025-09-01',
* pMaxDate => DATE '2025-09-17',
* pRegisterExport => TRUE -- Registers each export to tracking tables
* );
* -- This will create files like: AGGREGATED_ALLOTMENT_202509.csv, etc.
* pBucketArea parameter accepts: 'INBOX', 'ODS', 'DATA', 'ARCHIVE'
* end;
**/
PROCEDURE EXPORT_TABLE_DATA_TO_CSV_BY_DATE (
pSchemaName IN VARCHAR2,
pTableName IN VARCHAR2,
pKeyColumnName IN VARCHAR2,
pBucketArea IN VARCHAR2,
pFolderName IN VARCHAR2,
pFileName IN VARCHAR2 DEFAULT NULL,
pColumnList IN VARCHAR2 default NULL,
pMinDate IN DATE default DATE '1900-01-01',
pMaxDate IN DATE default SYSDATE,
pParallelDegree IN NUMBER default 1,
pTemplateTableName IN VARCHAR2 default NULL,
pMaxFileSize IN NUMBER default 104857600,
pRegisterExport IN BOOLEAN default FALSE,
pCredentialName IN VARCHAR2 default ENV_MANAGER.gvCredentialName
);
---------------------------------------------------------------------------------------------------------------------------
-- VERSION MANAGEMENT FUNCTIONS
---------------------------------------------------------------------------------------------------------------------------
/**
* Returns the current package version number
* return: Version string in format X.Y.Z (e.g., '2.1.0')
**/
FUNCTION GET_VERSION RETURN VARCHAR2;
/**
* Returns comprehensive build information including version, date, and author
* return: Formatted string with complete build details
**/
FUNCTION GET_BUILD_INFO RETURN VARCHAR2;
/**
* Returns the version history with recent changes
* return: Multi-line string with version history
**/
FUNCTION GET_VERSION_HISTORY RETURN VARCHAR2;
END;
/

6
MARS_Packages/REL01_ADDITIONS/MARS-835/01_MARS_835_install_step1.sql
View File

@@ -106,7 +106,8 @@ BEGIN
pMaxDate => SYSDATE,
pParallelDegree => 16,
pTemplateTableName => 'CT_ET_TEMPLATES.CSDB_DEBT',
pMaxFileSize => 104857600 -- 100MB in bytes (safe for parallel execution, avoids ORA-04036)
pMaxFileSize => 104857600, -- 100MB in bytes (safe for parallel execution, avoids ORA-04036)
pRegisterExport => TRUE -- Register exported files in A_SOURCE_FILE_RECEIVED with metadata (CHECKSUM, CREATED, BYTES)
);
DBMS_OUTPUT.PUT_LINE('SUCCESS: LEGACY_DEBT exported to DATA bucket with template column order');
@@ -225,7 +226,8 @@ BEGIN
pMaxDate => SYSDATE,
pParallelDegree => 16,
pTemplateTableName => 'CT_ET_TEMPLATES.CSDB_DEBT_DAILY',
pMaxFileSize => 104857600 -- 100MB in bytes (safe for parallel execution, avoids ORA-04036)
pMaxFileSize => 104857600, -- 100MB in bytes (safe for parallel execution, avoids ORA-04036)
pRegisterExport => TRUE -- Register exported files in A_SOURCE_FILE_RECEIVED with metadata (CHECKSUM, CREATED, BYTES)
);
DBMS_OUTPUT.PUT_LINE('SUCCESS: LEGACY_DEBT_DAILY exported to DATA bucket with template column order');