Compare commits

...

5 Commits

6 changed files with 254 additions and 130 deletions

View File

@@ -46,6 +46,16 @@ DECLARE
cMaxPrint CONSTANT NUMBER := 1000;
vPrinted NUMBER;
FUNCTION IS_EXTERNAL_TABLE_EMPTY_ERROR(
pSqlCode NUMBER,
pSqlErrm VARCHAR2
) RETURN BOOLEAN
IS
BEGIN
RETURN pSqlCode IN (-29913, -29400)
OR INSTR(pSqlErrm, 'KUP-05002') > 0;
END;
BEGIN
FOR config_rec IN (
@@ -79,7 +89,7 @@ BEGIN
INTO vTableExists;
EXCEPTION
WHEN OTHERS THEN
IF SQLCODE = -29913 THEN
IF IS_EXTERNAL_TABLE_EMPTY_ERROR(SQLCODE, SQLERRM) THEN
vBucketEmpty := TRUE;
ELSE
RAISE;
@@ -97,6 +107,7 @@ BEGIN
vInBothNoKey := 0;
ELSE
BEGIN
-- ----------------------------------------------------------------
-- [A] In ODS bucket but NOT in A_SOURCE_FILE_RECEIVED
-- ----------------------------------------------------------------
@@ -154,6 +165,22 @@ BEGIN
' WHERE t.file$name = sfr.SOURCE_FILE_NAME)'
INTO vInBothNoKey
USING config_rec.A_SOURCE_FILE_CONFIG_KEY;
EXCEPTION
WHEN OTHERS THEN
IF IS_EXTERNAL_TABLE_EMPTY_ERROR(SQLCODE, SQLERRM) THEN
vBucketEmpty := TRUE;
vOnlyInBucket := 0;
SELECT COUNT(*) INTO vOnlyInDB
FROM CT_MRDS.A_SOURCE_FILE_RECEIVED sfr
WHERE sfr.A_SOURCE_FILE_CONFIG_KEY = config_rec.A_SOURCE_FILE_CONFIG_KEY
AND sfr.PROCESSING_STATUS IN ('VALIDATED','READY_FOR_INGESTION','INGESTED','ARCHIVED','ARCHIVED_AND_TRASHED','ARCHIVED_AND_PURGED');
vInBothWithKey := 0;
vInBothNoKey := 0;
DBMS_OUTPUT.PUT_LINE(' NOTE: ODS bucket became empty/inaccessible during diagnostics for ' || vTableName || '. Falling back to DB-only counts for [B].');
ELSE
RAISE;
END IF;
END;
END IF; -- vBucketEmpty
@@ -204,6 +231,16 @@ BEGIN
vConfigsWithIssues := vConfigsWithIssues + 1;
DBMS_OUTPUT.PUT_LINE(' [B] Registered files not found in bucket:');
vPrinted := 0;
BEGIN
IF vBucketEmpty THEN
OPEN vRefCursor FOR
'SELECT sfr.SOURCE_FILE_NAME, sfr.PROCESSING_STATUS, sfr.A_WORKFLOW_HISTORY_KEY ' ||
'FROM CT_MRDS.A_SOURCE_FILE_RECEIVED sfr ' ||
'WHERE sfr.A_SOURCE_FILE_CONFIG_KEY = :1 ' ||
' AND sfr.PROCESSING_STATUS IN (''VALIDATED'',''READY_FOR_INGESTION'',''INGESTED'',''ARCHIVED'',''ARCHIVED_AND_TRASHED'',''ARCHIVED_AND_PURGED'') ' ||
'ORDER BY sfr.SOURCE_FILE_NAME'
USING config_rec.A_SOURCE_FILE_CONFIG_KEY;
ELSE
OPEN vRefCursor FOR
'SELECT sfr.SOURCE_FILE_NAME, sfr.PROCESSING_STATUS, sfr.A_WORKFLOW_HISTORY_KEY ' ||
'FROM CT_MRDS.A_SOURCE_FILE_RECEIVED sfr ' ||
@@ -214,6 +251,23 @@ BEGIN
' WHERE t.file$name = sfr.SOURCE_FILE_NAME) ' ||
'ORDER BY sfr.SOURCE_FILE_NAME'
USING config_rec.A_SOURCE_FILE_CONFIG_KEY;
END IF;
EXCEPTION
WHEN OTHERS THEN
IF IS_EXTERNAL_TABLE_EMPTY_ERROR(SQLCODE, SQLERRM) THEN
vBucketEmpty := TRUE;
DBMS_OUTPUT.PUT_LINE(' NOTE: Skipping ODS anti-join details due to empty/inaccessible external table for ' || vTableName || '.');
OPEN vRefCursor FOR
'SELECT sfr.SOURCE_FILE_NAME, sfr.PROCESSING_STATUS, sfr.A_WORKFLOW_HISTORY_KEY ' ||
'FROM CT_MRDS.A_SOURCE_FILE_RECEIVED sfr ' ||
'WHERE sfr.A_SOURCE_FILE_CONFIG_KEY = :1 ' ||
' AND sfr.PROCESSING_STATUS IN (''VALIDATED'',''READY_FOR_INGESTION'',''INGESTED'',''ARCHIVED'',''ARCHIVED_AND_TRASHED'',''ARCHIVED_AND_PURGED'') ' ||
'ORDER BY sfr.SOURCE_FILE_NAME'
USING config_rec.A_SOURCE_FILE_CONFIG_KEY;
ELSE
RAISE;
END IF;
END;
LOOP
DECLARE
vStatus VARCHAR2(50);

View File

@@ -53,6 +53,43 @@ END;
/
WHENEVER SQLERROR CONTINUE
PROMPT
PROMPT ============================================================================
PROMPT PREREQUISITE CHECK: Verifying MARS-1409 objects
PROMPT ============================================================================
WHENEVER SQLERROR EXIT SQL.SQLCODE
DECLARE
vColCount NUMBER;
vTableCount NUMBER;
BEGIN
SELECT COUNT(*)
INTO vColCount
FROM ALL_TAB_COLUMNS
WHERE OWNER = 'CT_MRDS'
AND TABLE_NAME = 'A_SOURCE_FILE_RECEIVED'
AND COLUMN_NAME = 'A_WORKFLOW_HISTORY_KEY';
IF vColCount = 0 THEN
RAISE_APPLICATION_ERROR(-20001,
'Prerequisite failed: CT_MRDS.A_SOURCE_FILE_RECEIVED.A_WORKFLOW_HISTORY_KEY not found. Install MARS-1409 first (or do not run POSTHOOK after rollback).');
END IF;
SELECT COUNT(*)
INTO vTableCount
FROM ALL_TABLES
WHERE OWNER = 'CT_MRDS'
AND TABLE_NAME = 'A_WORKFLOW_HISTORY';
IF vTableCount = 0 THEN
RAISE_APPLICATION_ERROR(-20002,
'Prerequisite failed: CT_MRDS.A_WORKFLOW_HISTORY table not found.');
END IF;
DBMS_OUTPUT.PUT_LINE('OK: Prerequisites satisfied (MARS-1409 schema changes detected).');
END;
/
WHENEVER SQLERROR CONTINUE
PROMPT
PROMPT ============================================================================
PROMPT STEP 1: Backfill A_WORKFLOW_HISTORY_KEY for existing records

View File

@@ -58,14 +58,15 @@ AS
BEGIN
vParameters := CT_MRDS.ENV_MANAGER.FORMAT_PARAMETERS(SYS.ODCIVARCHAR2LIST('pSourceFileConfigKey => '||nvl(to_char(pSourceFileConfigKey),NULL)));
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('Start','DEBUG', vParameters);
SELECT count(*) , min(SOURCE_FILE_TYPE)
-- LEFT JOIN ensures SOURCE_FILE_TYPE is retrieved from config even when no stats exist yet
SELECT count(s.A_SOURCE_FILE_CONFIG_KEY), min(c.SOURCE_FILE_TYPE)
INTO vCount, vSourceFileType
FROM CT_MRDS.A_TABLE_STAT s
JOIN CT_MRDS.A_SOURCE_FILE_CONFIG c
FROM CT_MRDS.A_SOURCE_FILE_CONFIG c
LEFT JOIN CT_MRDS.A_TABLE_STAT s
ON s.A_SOURCE_FILE_CONFIG_KEY = c.A_SOURCE_FILE_CONFIG_KEY
WHERE s.A_SOURCE_FILE_CONFIG_KEY = pSourceFileConfigKey;
WHERE c.A_SOURCE_FILE_CONFIG_KEY = pSourceFileConfigKey;
IF vCount=0 and vSourceFileType='INPUT' THEN
IF vCount = 0 AND vSourceFileType = 'INPUT' THEN
GATHER_TABLE_STAT(pSourceFileConfigKey);
END IF;
@@ -74,9 +75,13 @@ AS
INTO vTableStat
FROM CT_MRDS.A_TABLE_STAT
WHERE A_SOURCE_FILE_CONFIG_KEY = pSourceFileConfigKey;
-- EXCEPTION
-- WHEN NO_DATA_FOUND THEN
--
EXCEPTION
WHEN NO_DATA_FOUND THEN
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT(
'No statistics found in A_TABLE_STAT for config key ' || pSourceFileConfigKey
|| ' (SOURCE_FILE_TYPE=' || NVL(vSourceFileType, 'NULL') || '). Cannot proceed with archival.',
'ERROR', vParameters);
RAISE;
END;
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('End','DEBUG',vParameters);
@@ -171,13 +176,14 @@ AS
;
-- Get all files that will be archived into "vfiles" collection ("regular data files")
-- MARS-1468: Handle ORA-29913 - no files in ODS bucket (empty external table location)
-- MARS-1468: Handle ORA-29913/ORA-12801 - no files in ODS bucket (empty external table location)
-- ORA-29913 may come directly or wrapped in ORA-12801 (parallel query) with KUP-05002 root cause
BEGIN
execute immediate vQuery bulk collect into vfiles;
EXCEPTION
WHEN OTHERS THEN
IF SQLCODE = -29913 THEN
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('No files found in ODS bucket (ORA-29913: empty location). Nothing to archive.', 'INFO', vParameters);
IF SQLCODE IN (-29913, -12801) AND DBMS_UTILITY.FORMAT_ERROR_STACK LIKE '%KUP-05002%' THEN
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('No files found in ODS bucket (empty location, SQLCODE=' || SQLCODE || '). Nothing to archive.', 'INFO', vParameters);
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('End','INFO',vParameters);
RETURN;
ELSE
@@ -185,6 +191,18 @@ AS
END IF;
END;
-- Check if any files match archival criteria
IF vfiles.COUNT = 0 THEN
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT(
'No files matching archival criteria found (strategy: ' || vSourceFileConfig.ARCHIVAL_STRATEGY
|| ', IS_WORKFLOW_SUCCESS_REQUIRED: ' || vSourceFileConfig.IS_WORKFLOW_SUCCESS_REQUIRED || '). Nothing to archive.',
'INFO', vParameters);
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('End','INFO',vParameters);
RETURN;
END IF;
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('Files matching archival criteria: ' || vfiles.COUNT, 'INFO', vParameters);
-- Start EXPORT "regular data files" to parquet and DROP "csv"
FOR ym_loop IN (select distinct year, month from table(vfiles) order by 1,2) LOOP
dbms_output.put_line('year: '||ym_loop.year||' - '||'month: '||ym_loop.month);
@@ -538,13 +556,14 @@ AS
on t.filename = r.object_name'
;
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('vQuery:', 'DEBUG', vQuery);
-- MARS-1468: Handle ORA-29913 - no files in ODS bucket (empty external table location)
-- MARS-1468: Handle ORA-29913/ORA-12801 - no files in ODS bucket (empty external table location)
-- ORA-29913 may come directly or wrapped in ORA-12801 (parallel query) with KUP-05002 root cause
BEGIN
execute immediate vQuery into vStats;
EXCEPTION
WHEN OTHERS THEN
IF SQLCODE = -29913 THEN
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('No files found in ODS bucket (ORA-29913: empty location). Saving zero statistics.', 'INFO', vParameters);
IF SQLCODE IN (-29913, -12801) AND DBMS_UTILITY.FORMAT_ERROR_STACK LIKE '%KUP-05002%' THEN
CT_MRDS.ENV_MANAGER.LOG_PROCESS_EVENT('No files found in ODS bucket (empty location, SQLCODE=' || SQLCODE || '). Saving zero statistics.', 'INFO', vParameters);
vStats.A_SOURCE_FILE_CONFIG_KEY := pSourceFileConfigKey;
vStats.TABLE_NAME := vTableName;
vStats.FILE_COUNT := 0;

View File

@@ -1634,7 +1634,7 @@ AS
,pEncoding IN CT_MRDS.A_SOURCE_FILE_CONFIG.ENCODING%TYPE DEFAULT NULL -- MARS-1049
,pIsWorkflowSuccessRequired IN CT_MRDS.A_SOURCE_FILE_CONFIG.IS_WORKFLOW_SUCCESS_REQUIRED%TYPE DEFAULT 'Y' -- MARS-1409
,pIsArchiveEnabled IN CT_MRDS.A_SOURCE_FILE_CONFIG.IS_ARCHIVE_ENABLED%TYPE DEFAULT 'N' -- MARS-828
,pIsKeepInTrash IN CT_MRDS.A_SOURCE_FILE_CONFIG.IS_KEPT_IN_TRASH%TYPE DEFAULT 'Y' -- MARS-828
,pIsKeptInTrash IN CT_MRDS.A_SOURCE_FILE_CONFIG.IS_KEPT_IN_TRASH%TYPE DEFAULT 'Y' -- MARS-828
,pArchivalStrategy IN CT_MRDS.A_SOURCE_FILE_CONFIG.ARCHIVAL_STRATEGY%TYPE DEFAULT 'THRESHOLD_BASED' -- MARS-828
,pMinimumAgeMonths IN CT_MRDS.A_SOURCE_FILE_CONFIG.MINIMUM_AGE_MONTHS%TYPE DEFAULT 0 -- MARS-828
) IS
@@ -1654,13 +1654,13 @@ AS
,'pEncoding => '''||nvl(to_char(pEncoding), 'NULL')||'''' -- MARS-1049: NOWY
,'pIsWorkflowSuccessRequired => '''||nvl(to_char(pIsWorkflowSuccessRequired), 'NULL')||'''' -- MARS-1409
,'pIsArchiveEnabled => '''||nvl(to_char(pIsArchiveEnabled), 'NULL')||'''' -- MARS-828
,'pIsKeepInTrash => '''||nvl(to_char(pIsKeepInTrash), 'NULL')||'''' -- MARS-828
,'pIsKeptInTrash => '''||nvl(to_char(pIsKeptInTrash), 'NULL')||'''' -- MARS-828
,'pArchivalStrategy => '''||nvl(to_char(pArchivalStrategy), 'NULL')||'''' -- MARS-828
,'pMinimumAgeMonths => '''||nvl(to_char(pMinimumAgeMonths), 'NULL')||'''' -- MARS-828
));
ENV_MANAGER.LOG_PROCESS_EVENT('Start','INFO', vParameters);
INSERT INTO CT_MRDS.A_SOURCE_FILE_CONFIG(A_SOURCE_KEY, SOURCE_FILE_TYPE, SOURCE_FILE_ID, SOURCE_FILE_DESC, SOURCE_FILE_NAME_PATTERN, TABLE_ID, TEMPLATE_TABLE_NAME, CONTAINER_FILE_KEY, ENCODING, IS_WORKFLOW_SUCCESS_REQUIRED, IS_ARCHIVE_ENABLED, IS_KEPT_IN_TRASH, ARCHIVAL_STRATEGY, MINIMUM_AGE_MONTHS)
VALUES (pSourceKey, pSourceFileType, pSourceFileId, pSourceFileDesc, pSourceFileNamePattern, pTableId, pTemplateTableName, pContainerFileKey, pEncoding, pIsWorkflowSuccessRequired, pIsArchiveEnabled, pIsKeepInTrash, pArchivalStrategy, pMinimumAgeMonths);
VALUES (pSourceKey, pSourceFileType, pSourceFileId, pSourceFileDesc, pSourceFileNamePattern, pTableId, pTemplateTableName, pContainerFileKey, pEncoding, pIsWorkflowSuccessRequired, pIsArchiveEnabled, pIsKeptInTrash, pArchivalStrategy, pMinimumAgeMonths);
COMMIT;
ENV_MANAGER.LOG_PROCESS_EVENT('End','INFO',vParameters);
EXCEPTION

View File

@@ -23,7 +23,7 @@ AS
-- Version History (Latest changes first)
VERSION_HISTORY CONSTANT VARCHAR2(4000) :=
'3.6.3 (2026-03-17): MARS-828 - Added pIsArchiveEnabled, pIsKeepInTrash, pArchivalStrategy, pMinimumAgeMonths to ADD_SOURCE_FILE_CONFIG; FORMAT_CONFIG now shows all A_SOURCE_FILE_CONFIG columns' || CHR(13)||CHR(10) ||
'3.6.3 (2026-03-17): MARS-828 - Added pIsArchiveEnabled, pIsKeptInTrash, pArchivalStrategy, pMinimumAgeMonths to ADD_SOURCE_FILE_CONFIG; FORMAT_CONFIG now shows all A_SOURCE_FILE_CONFIG columns' || CHR(13)||CHR(10) ||
'3.6.2 (2026-03-17): MARS-1409 - Added pIsWorkflowSuccessRequired parameter to ADD_SOURCE_FILE_CONFIG; IS_WORKFLOW_SUCCESS_REQUIRED shown in GET_DET_SOURCE_FILE_CONFIG_INFO output' || CHR(13)||CHR(10) ||
'3.6.1 (2026-03-13): MARS-1468 - Fixed CHAR/NCHAR/NVARCHAR2 column definitions in GENERATE_EXTERNAL_TABLE_PARAMS: CHAR now uses char_used/char_length semantics; NCHAR/NVARCHAR2 use char_length (data_length stores bytes in AL16UTF16)' || CHR(13)||CHR(10) ||
'3.6.0 (2026-02-27): MARS-1409 - Added A_WORKFLOW_HISTORY_KEY tracking in A_SOURCE_FILE_RECEIVED. Each file now stores its workflow execution key extracted during VALIDATE_SOURCE_FILE_RECEIVED' || CHR(13)||CHR(10) ||
@@ -446,13 +446,13 @@ AS
* @desc Insert a new record to A_SOURCE_FILE_CONFIG table.
* MARS-1049: Added pEncoding parameter for CSV character set specification.
* MARS-1409: Added pIsWorkflowSuccessRequired parameter.
* MARS-828: Added pIsArchiveEnabled, pIsKeepInTrash, pArchivalStrategy, pMinimumAgeMonths.
* MARS-828: Added pIsArchiveEnabled, pIsKeptInTrash, pArchivalStrategy, pMinimumAgeMonths.
* @param pEncoding - Character set encoding for CSV files (e.g., 'UTF8', 'WE8MSWIN1252', 'EE8ISO8859P2')
* If NULL, no CHARACTERSET clause is added to external table definitions
* @param pIsWorkflowSuccessRequired - 'Y' (default) = archivization requires WORKFLOW_SUCCESSFUL='Y' (standard DBT flow)
* 'N' = archive regardless of workflow status (bypass for manual/non-DBT sources)
* @param pIsArchiveEnabled - 'Y' = enable automatic archivization for this config; 'N' (default) = disabled
* @param pIsKeepInTrash - 'Y' = move files to trash before purge; 'N' (default) = purge directly
* @param pIsKeptInTrash - 'Y' = move files to trash before purge; 'N' (default) = purge directly
* @param pArchivalStrategy - Archival strategy: 'MINIMUM_AGE_MONTHS' or NULL
* @param pMinimumAgeMonths - Minimum age in months before file eligible for archivization (used with MINIMUM_AGE_MONTHS strategy)
* @example CALL CT_MRDS.FILE_MANAGER.ADD_SOURCE_FILE_CONFIG(
@@ -460,7 +460,7 @@ AS
* pSourceFileId => 'UC_DISSEM', pTableId => 'METADATA_LOADS',
* pTemplateTableName => 'CT_ET_TEMPLATES.C2D_A_UC_DISSEM_METADATA_LOADS',
* pEncoding => 'UTF8', pIsWorkflowSuccessRequired => 'Y',
* pIsArchiveEnabled => 'Y', pIsKeepInTrash => 'N',
* pIsArchiveEnabled => 'Y', pIsKeptInTrash => 'N',
* pArchivalStrategy => 'MINIMUM_AGE_MONTHS', pMinimumAgeMonths => 3
* );
**/
@@ -476,7 +476,7 @@ AS
,pEncoding IN CT_MRDS.A_SOURCE_FILE_CONFIG.ENCODING%TYPE DEFAULT NULL -- MARS-1049
,pIsWorkflowSuccessRequired IN CT_MRDS.A_SOURCE_FILE_CONFIG.IS_WORKFLOW_SUCCESS_REQUIRED%TYPE DEFAULT 'Y' -- MARS-1409
,pIsArchiveEnabled IN CT_MRDS.A_SOURCE_FILE_CONFIG.IS_ARCHIVE_ENABLED%TYPE DEFAULT 'N' -- MARS-828
,pIsKeepInTrash IN CT_MRDS.A_SOURCE_FILE_CONFIG.IS_KEPT_IN_TRASH%TYPE DEFAULT 'Y' -- MARS-828
,pIsKeptInTrash IN CT_MRDS.A_SOURCE_FILE_CONFIG.IS_KEPT_IN_TRASH%TYPE DEFAULT 'Y' -- MARS-828
,pArchivalStrategy IN CT_MRDS.A_SOURCE_FILE_CONFIG.ARCHIVAL_STRATEGY%TYPE DEFAULT 'THRESHOLD_BASED' -- MARS-828
,pMinimumAgeMonths IN CT_MRDS.A_SOURCE_FILE_CONFIG.MINIMUM_AGE_MONTHS%TYPE DEFAULT 0 -- MARS-828
);

View File

@@ -288,11 +288,11 @@ WHERE SOURCE_FILE_TYPE = 'INPUT'
ORDER BY SOURCE_FILE_ID, TABLE_ID;
```
### IS_KEEP_IN_TRASH Column
### IS_KEPT_IN_TRASH Column
Controls TRASH folder retention policy for archived files.
**Column**: `A_SOURCE_FILE_CONFIG.IS_KEEP_IN_TRASH` (CHAR(1), DEFAULT 'N' NOT NULL)
**Column**: `A_SOURCE_FILE_CONFIG.IS_KEPT_IN_TRASH` (CHAR(1), DEFAULT 'N' NOT NULL)
**Values**:
- `'Y'` - CSV files kept in TRASH folder after archival (status: ARCHIVED_AND_TRASHED)
@@ -312,7 +312,7 @@ Controls TRASH folder retention policy for archived files.
```sql
-- Production: Keep files in TRASH (recommended)
UPDATE CT_MRDS.A_SOURCE_FILE_CONFIG
SET IS_KEEP_IN_TRASH = 'Y'
SET IS_KEPT_IN_TRASH = 'Y'
WHERE SOURCE_FILE_TYPE = 'INPUT'
AND SOURCE_FILE_ID = 'LM'
AND TABLE_ID LIKE 'LM_%';
@@ -320,14 +320,14 @@ COMMIT;
-- Test environment: Cleanup TRASH to save storage
UPDATE CT_MRDS.A_SOURCE_FILE_CONFIG
SET IS_KEEP_IN_TRASH = 'N'
SET IS_KEPT_IN_TRASH = 'N'
WHERE SOURCE_FILE_TYPE = 'INPUT'
AND SOURCE_FILE_ID = 'TEST_SOURCE';
COMMIT;
-- Bulk configuration by source
UPDATE CT_MRDS.A_SOURCE_FILE_CONFIG
SET IS_KEEP_IN_TRASH = 'Y'
SET IS_KEPT_IN_TRASH = 'Y'
WHERE SOURCE_FILE_TYPE = 'INPUT'
AND SOURCE_FILE_ID IN ('CSDB', 'C2D', 'LM');
COMMIT;
@@ -393,7 +393,7 @@ INGESTED → ARCHIVED_AND_TRASHED → ARCHIVED_AND_PURGED (optional)
**Status Descriptions**:
- **INGESTED**: File successfully processed through Airflow+DBT, residing in ODS bucket
- **ARCHIVED_AND_TRASHED**: File archived to Parquet in ARCHIVE bucket, CSV retained in TRASH folder (DATA bucket)
- **ARCHIVED_AND_PURGED**: File archived to Parquet, CSV deleted from TRASH folder (when IS_KEEP_IN_TRASH='N')
- **ARCHIVED_AND_PURGED**: File archived to Parquet, CSV deleted from TRASH folder (when IS_KEPT_IN_TRASH='N')
**Associated Columns Updated During Archival**:
```sql
@@ -435,9 +435,9 @@ https://objectstorage.eu-frankfurt-1.oraclecloud.com/n/namespace/b/archive/o/ARC
2.1 TRASH Subfolder (DATA Bucket - File Retention)
├─ Located in DATA bucket (e.g., TRASH/LM/TABLE_NAME)
├─ Stores CSV files after archival to Parquet
├─ Status: ARCHIVED_AND_TRASHED (default, controlled by IS_KEEP_IN_TRASH config)
├─ Status: ARCHIVED_AND_TRASHED (default, controlled by IS_KEPT_IN_TRASH config)
├─ Enables rollback if archival issues occur
└─ Optional cleanup: ARCHIVED_AND_PURGED (when IS_KEEP_IN_TRASH = 'N')
└─ Optional cleanup: ARCHIVED_AND_PURGED (when IS_KEPT_IN_TRASH = 'N')
3. ARCHIVE Bucket (Long-term Storage)
├─ Historical data in Parquet format
@@ -447,24 +447,35 @@ https://objectstorage.eu-frankfurt-1.oraclecloud.com/n/namespace/b/archive/o/ARC
**Key Procedures**:
- `ARCHIVE_TABLE_DATA(pSourceFileConfigKey)` - Main archival procedure using strategy-specific WHERE clause
- TRASH folder retention controlled by `IS_KEEP_IN_TRASH` column in A_SOURCE_FILE_CONFIG
- TRASH folder retention controlled by `IS_KEPT_IN_TRASH` column in A_SOURCE_FILE_CONFIG
- `ARCHIVE_ALL(pSourceFileConfigKey, pSourceKey, pArchiveAll)` - Batch archival with 3-level granularity and error handling
- **Level 3 (Highest Priority)**: Single configuration via `pSourceFileConfigKey`
- **Level 2 (Medium Priority)**: All configurations for source via `pSourceKey`
- **Level 1 (Lowest Priority)**: All configurations system-wide via `pArchiveAll`
- **Error Handling**: Continues processing other tables on individual failures
- **Filtering**: Respects `IS_ARCHIVE_ENABLED='Y'` (skips disabled configurations)
- **Individual TRASH Policy**: Each table's `IS_KEEP_IN_TRASH` setting applied independently
- **Individual TRASH Policy**: Each table's `IS_KEPT_IN_TRASH` setting applied independently
- **Summary Reporting**: Returns counts of Archived/Skipped/Failed tables
- `GET_ARCHIVAL_WHERE_CLAUSE` - Returns WHERE clause based on configured strategy
- `GATHER_TABLE_STAT` - Calculates archival statistics using strategy logic
- `GATHER_TABLE_STAT_ALL(pSourceFileConfigKey, pSourceKey, pGatherAll)` - Batch statistics with 3-level granularity
- `RESTORE_FILE_FROM_TRASH(pSourceFileConfigKey, pSourceKey, pRestoreAll)` - Restore archived files from TRASH
- `PURGE_TRASH_FOLDER(pSourceFileConfigKey, pSourceKey, pPurgeAll)` - Purge TRASH folder with 3-level granularity
- `GATHER_TABLE_STAT(pSourceFileConfigKey)` - Calculates archival statistics using strategy logic
- `GATHER_TABLE_STAT_ALL(pSourceFileConfigKey, pSourceKey, pGatherAll, pOnlyEnabled)` - Batch statistics with 3-level granularity
- `pOnlyEnabled` (DEFAULT TRUE): When TRUE, only processes tables with `IS_ARCHIVE_ENABLED='Y'`
- `RESTORE_FILE_FROM_TRASH(pSourceFileReceivedKey, pSourceFileConfigKey, pRestoreAll)` - Restore archived files from TRASH
- `PURGE_TRASH_FOLDER(pSourceFileReceivedKey, pSourceFileConfigKey, pPurgeAll)` - Purge TRASH folder with 3-level granularity
- `GET_VERSION` / `GET_BUILD_INFO` / `GET_VERSION_HISTORY` - Package version and metadata
**Function Wrappers (Python Integration)**:
All key procedures have `FN_*` function overloads returning `PLS_INTEGER` (SQLCODE: 0=success, error code on failure) for Python library integration:
- `FN_ARCHIVE_TABLE_DATA`, `FN_GATHER_TABLE_STAT`, `FN_ARCHIVE_ALL`, `FN_GATHER_TABLE_STAT_ALL`
- `RESTORE_FILE_FROM_TRASH` and `PURGE_TRASH_FOLDER` also have function overloads returning PLS_INTEGER
**Internal Functions** (not callable externally):
- `GET_ARCHIVAL_WHERE_CLAUSE` - Returns WHERE clause based on configured strategy (private)
- `GET_TABLE_STAT` - Retrieves or auto-generates table statistics (private)
**Archival Execution**:
```sql
-- Single table archival (TRASH retention controlled by IS_KEEP_IN_TRASH config)
-- Single table archival (TRASH retention controlled by IS_KEPT_IN_TRASH config)
BEGIN
CT_MRDS.FILE_ARCHIVER.ARCHIVE_TABLE_DATA(
pSourceFileConfigKey => vSourceFileConfigKey
@@ -500,7 +511,7 @@ END;
- Data matching criteria moved from ODS to ARCHIVE bucket
- CSV files moved to TRASH subfolder in DATA bucket (ODS/ → TRASH/)
- Parquet format with Hive-style partitioning applied to ARCHIVE bucket
- TRASH retention controlled by IS_KEEP_IN_TRASH column in A_SOURCE_FILE_CONFIG
- TRASH retention controlled by IS_KEPT_IN_TRASH column in A_SOURCE_FILE_CONFIG
### Automatic Rollback Mechanism
@@ -510,7 +521,7 @@ FILE_ARCHIVER implements **automatic rollback** to ensure data integrity if arch
1. **Export to ARCHIVE**: Data exported to Parquet format in ARCHIVE bucket
2. **Status Update**: A_SOURCE_FILE_RECEIVED records updated to 'ARCHIVED_AND_TRASHED'
3. **Move to TRASH**: CSV files moved from ODS to TRASH folder (DATA bucket)
4. **Optional Cleanup**: If IS_KEEP_IN_TRASH='N', files deleted from TRASH
4. **Optional Cleanup**: If IS_KEPT_IN_TRASH='N', files deleted from TRASH
**Automatic Rollback Trigger**:
If **any error occurs** during step 3 (Move to TRASH), the system:
@@ -725,7 +736,7 @@ UPDATE CT_MRDS.A_SOURCE_FILE_CONFIG
SET ARCHIVAL_STRATEGY = 'MINIMUM_AGE_MONTHS',
MINIMUM_AGE_MONTHS = 6,
IS_ARCHIVE_ENABLED = 'Y', -- Enable archival
IS_KEEP_IN_TRASH = 'Y' -- Keep files in TRASH for safety
IS_KEPT_IN_TRASH = 'Y' -- Keep files in TRASH for safety
WHERE SOURCE_FILE_TYPE = 'INPUT'
AND SOURCE_FILE_ID = 'CSDB'
AND TABLE_ID = 'CSDB_DEBT';
@@ -739,7 +750,7 @@ COMMIT;
-- Configure TRASH cleanup for test environment
UPDATE CT_MRDS.A_SOURCE_FILE_CONFIG
SET IS_KEEP_IN_TRASH = 'N' -- Delete files from TRASH after archival
SET IS_KEPT_IN_TRASH = 'N' -- Delete files from TRASH after archival
WHERE SOURCE_FILE_TYPE = 'INPUT'
AND SOURCE_FILE_ID = 'TEST_SOURCE';
COMMIT;
@@ -751,7 +762,7 @@ SELECT
ARCHIVAL_STRATEGY,
MINIMUM_AGE_MONTHS,
IS_ARCHIVE_ENABLED,
IS_KEEP_IN_TRASH
IS_KEPT_IN_TRASH
FROM CT_MRDS.A_SOURCE_FILE_CONFIG
WHERE SOURCE_FILE_TYPE = 'INPUT'
ORDER BY SOURCE_FILE_ID, TABLE_ID;
@@ -759,12 +770,12 @@ ORDER BY SOURCE_FILE_ID, TABLE_ID;
-- Summary by archival status
SELECT
IS_ARCHIVE_ENABLED,
IS_KEEP_IN_TRASH,
IS_KEPT_IN_TRASH,
COUNT(*) AS TABLE_COUNT
FROM CT_MRDS.A_SOURCE_FILE_CONFIG
WHERE SOURCE_FILE_TYPE = 'INPUT'
GROUP BY IS_ARCHIVE_ENABLED, IS_KEEP_IN_TRASH
ORDER BY IS_ARCHIVE_ENABLED DESC, IS_KEEP_IN_TRASH DESC;
GROUP BY IS_ARCHIVE_ENABLED, IS_KEPT_IN_TRASH
ORDER BY IS_ARCHIVE_ENABLED DESC, IS_KEPT_IN_TRASH DESC;
```
## Release 01 Configuration
@@ -948,7 +959,7 @@ WHERE object_name LIKE 'ARCHIVE/LM/STANDING_FACILITIES/PARTITION_YEAR=2026/PARTI
**Symptoms**: Files not deleted from TRASH after archival
**Cause**: Configuration has `IS_KEEP_IN_TRASH='Y'` (retain files in TRASH)
**Cause**: Configuration has `IS_KEPT_IN_TRASH='Y'` (retain files in TRASH)
**Verification**:
```sql
@@ -956,8 +967,8 @@ WHERE object_name LIKE 'ARCHIVE/LM/STANDING_FACILITIES/PARTITION_YEAR=2026/PARTI
SELECT
SOURCE_FILE_ID,
TABLE_ID,
IS_KEEP_IN_TRASH,
CASE IS_KEEP_IN_TRASH
IS_KEPT_IN_TRASH,
CASE IS_KEPT_IN_TRASH
WHEN 'Y' THEN 'Files RETAINED in TRASH (manual purge required)'
WHEN 'N' THEN 'Files DELETED immediately after archival'
END AS TRASH_BEHAVIOR
@@ -969,7 +980,7 @@ WHERE TABLE_ID = 'YOUR_TABLE';
```sql
-- Option A: Change configuration to auto-delete (permanent change)
UPDATE CT_MRDS.A_SOURCE_FILE_CONFIG
SET IS_KEEP_IN_TRASH = 'N' -- Auto-delete from TRASH after archival
SET IS_KEPT_IN_TRASH = 'N' -- Auto-delete from TRASH after archival
WHERE TABLE_ID = 'YOUR_TABLE';
COMMIT;
@@ -1072,13 +1083,15 @@ BEGIN
WHERE TABLE_ID = 'YOUR_TABLE'
AND ROWNUM = 1;
vWhereClause := CT_MRDS.FILE_ARCHIVER.GET_ARCHIVAL_WHERE_CLAUSE(vConfig);
DBMS_OUTPUT.PUT_LINE('WHERE Clause: ' || vWhereClause);
-- Note: GET_ARCHIVAL_WHERE_CLAUSE is a private function.
-- To test WHERE clause logic, check A_PROCESS_LOG entries from ARCHIVE_TABLE_DATA
-- which logs the generated WHERE clause at INFO level.
DBMS_OUTPUT.PUT_LINE('Config: ' || vConfig.ARCHIVAL_STRATEGY || ', MIN_AGE=' || vConfig.MINIMUM_AGE_MONTHS);
END;
/
```
#### Issue 3: Package Compilation Errors After Upgrade
#### Issue 7: Package Compilation Errors After Upgrade
**Symptoms**: FILE_ARCHIVER package shows INVALID status
@@ -1132,7 +1145,7 @@ SELECT
SFR.FILE_SIZE_BYTES,
SFR.UPDATED_AT AS ARCHIVED_AT,
TRUNC(SYSDATE - SFR.UPDATED_AT) AS DAYS_IN_TRASH,
SFC.IS_KEEP_IN_TRASH AS TRASH_POLICY
SFC.IS_KEPT_IN_TRASH AS TRASH_POLICY
FROM CT_MRDS.A_SOURCE_FILE_RECEIVED SFR
JOIN CT_MRDS.A_SOURCE_FILE_CONFIG SFC ON SFR.A_SOURCE_FILE_CONFIG_KEY = SFC.A_SOURCE_FILE_CONFIG_KEY
WHERE SFR.PROCESSING_STATUS = 'ARCHIVED_AND_TRASHED'
@@ -1148,17 +1161,17 @@ SELECT
SFC.TABLE_ID,
SFC.ARCHIVAL_STRATEGY,
SFC.IS_ARCHIVE_ENABLED,
SFC.IS_KEEP_IN_TRASH,
SFC.IS_KEPT_IN_TRASH,
COUNT(CASE WHEN SFR.PROCESSING_STATUS = 'INGESTED' THEN 1 END) AS PENDING_ARCHIVE,
COUNT(CASE WHEN SFR.PROCESSING_STATUS = 'ARCHIVED_AND_TRASHED' THEN 1 END) AS IN_TRASH,
COUNT(CASE WHEN SFR.PROCESSING_STATUS = 'ARCHIVED_AND_PURGED' THEN 1 END) AS PURGED,
MAX(SFR.UPDATED_AT) FILTER (WHERE SFR.PROCESSING_STATUS LIKE 'ARCHIVED%') AS LAST_ARCHIVAL
MAX(CASE WHEN SFR.PROCESSING_STATUS LIKE 'ARCHIVED%' THEN SFR.UPDATED_AT END) AS LAST_ARCHIVAL
FROM CT_MRDS.A_SOURCE_FILE_CONFIG SFC
LEFT JOIN CT_MRDS.A_SOURCE_FILE_RECEIVED SFR ON SFC.A_SOURCE_FILE_CONFIG_KEY = SFR.A_SOURCE_FILE_CONFIG_KEY
WHERE SFC.SOURCE_FILE_TYPE = 'INPUT'
GROUP BY
SFC.SOURCE_FILE_ID, SFC.TABLE_ID, SFC.ARCHIVAL_STRATEGY,
SFC.IS_ARCHIVE_ENABLED, SFC.IS_KEEP_IN_TRASH
SFC.IS_ARCHIVE_ENABLED, SFC.IS_KEPT_IN_TRASH
ORDER BY SFC.SOURCE_FILE_ID, SFC.TABLE_ID;
```
@@ -1218,11 +1231,11 @@ SELECT
ROUND(SUM(SFR.FILE_SIZE_BYTES) / 1024 / 1024 / 1024, 2) AS SIZE_GB,
MIN(SFR.UPDATED_AT) AS OLDEST_IN_TRASH,
MAX(SFR.UPDATED_AT) AS NEWEST_IN_TRASH,
SFC.IS_KEEP_IN_TRASH AS POLICY
SFC.IS_KEPT_IN_TRASH AS POLICY
FROM CT_MRDS.A_SOURCE_FILE_RECEIVED SFR
JOIN CT_MRDS.A_SOURCE_FILE_CONFIG SFC ON SFR.A_SOURCE_FILE_CONFIG_KEY = SFC.A_SOURCE_FILE_CONFIG_KEY
WHERE SFR.PROCESSING_STATUS = 'ARCHIVED_AND_TRASHED'
GROUP BY SFC.SOURCE_FILE_ID, SFC.IS_KEEP_IN_TRASH
GROUP BY SFC.SOURCE_FILE_ID, SFC.IS_KEPT_IN_TRASH
ORDER BY SIZE_GB DESC;
```
@@ -1241,7 +1254,7 @@ ORDER BY SIZE_GB DESC;
### v3.3.0 (2026-02-11)
- **BREAKING CHANGE**: Removed `pKeepInTrash` parameter from ARCHIVE_TABLE_DATA
- Added `IS_ARCHIVE_ENABLED` column to A_SOURCE_FILE_CONFIG for selective archiving control
- Added `IS_KEEP_IN_TRASH` column to A_SOURCE_FILE_CONFIG (replaces pKeepInTrash parameter)
- Added `IS_KEPT_IN_TRASH` column to A_SOURCE_FILE_CONFIG (replaces pKeepInTrash parameter)
- Added batch procedures with 3-level granularity (config/source/all):
- ARCHIVE_ALL - Batch archival procedure
- GATHER_TABLE_STAT_ALL - Batch statistics procedure
@@ -1392,7 +1405,7 @@ ORDER BY SIZE_GB DESC;
### TRASH Folder Retention Best Practices
1. **Default Behavior (IS_KEEP_IN_TRASH = 'Y' - Recommended)**:
1. **Default Behavior (IS_KEPT_IN_TRASH = 'Y' - Recommended)**:
- Keeps CSV files in TRASH folder after archival
- Provides safety net for rollback if archival issues occur
- Supports compliance and audit requirements
@@ -1401,11 +1414,11 @@ ORDER BY SIZE_GB DESC;
- Configuration:
```sql
UPDATE CT_MRDS.A_SOURCE_FILE_CONFIG
SET IS_KEEP_IN_TRASH = 'Y'
SET IS_KEPT_IN_TRASH = 'Y'
WHERE SOURCE_FILE_TYPE = 'INPUT' AND TABLE_ID = 'YOUR_TABLE';
```
2. **TRASH Cleanup (IS_KEEP_IN_TRASH = 'N')**:
2. **TRASH Cleanup (IS_KEPT_IN_TRASH = 'N')**:
- Deletes CSV files from TRASH folder after successful archival
- Reduces storage costs in DATA bucket
- Status: ARCHIVED_AND_PURGED
@@ -1413,7 +1426,7 @@ ORDER BY SIZE_GB DESC;
- Configuration:
```sql
UPDATE CT_MRDS.A_SOURCE_FILE_CONFIG
SET IS_KEEP_IN_TRASH = 'N'
SET IS_KEPT_IN_TRASH = 'N'
WHERE SOURCE_FILE_TYPE = 'INPUT' AND TABLE_ID = 'YOUR_TABLE';
```
@@ -1423,7 +1436,7 @@ ORDER BY SIZE_GB DESC;
SELECT
SOURCE_FILE_NAME,
PROCESSING_STATUS,
ARCH_FILE_NAME,
ARCH_PATH,
PARTITION_YEAR,
PARTITION_MONTH
FROM CT_MRDS.A_SOURCE_FILE_RECEIVED
@@ -1446,3 +1459,4 @@ ORDER BY SIZE_GB DESC;
```