kylesoda/go-migrate-db
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add validation feature for row count comparison

Browse Source 
Add a validate command that compares row counts between source and target tables after a migration.
This commit is contained in:
Kylesoda
2026-05-12 17:00:00 -05:00
parent 6f8a332719
commit 5ee132a1ce
21 changed files with 2072 additions and 200 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
internal/app/etl/table_analyzers/mssql.go
View File

@@ -196,17 +196,65 @@ GROUP BY t.name`
return rowsCount, nil
}
func (ta *MssqlTableAnalyzer) QueryMaxMinFromColumn(
ctx context.Context,
tableInfo config.TableInfo,
columnName string,
) (etl.MaxMinColumnResult, error) {
query := fmt.Sprintf(`
SELECT
MIN([%s]) AS min_value,
MAX([%s]) AS max_value
FROM [%s].[%s]`, columnName, columnName, tableInfo.Schema, tableInfo.Table)
ctxTimeout, cancel := context.WithTimeout(ctx, 1*time.Minute)
defer cancel()
result := etl.MaxMinColumnResult{}
err := ta.db.QueryRow(ctxTimeout, query).Scan(&result.Min, &result.Max)
if err != nil {
return etl.MaxMinColumnResult{}, err
}
return result, nil
}
func (ta *MssqlTableAnalyzer) CalculatePartitionRanges(
ctx context.Context,
tableInfo config.TableInfo,
partitionColumn string,
maxPartitions int64,
rangeConstraint config.RangeConfig,
) ([]models.Partition, error) {
whereClause := ""
args := []any{sql.Named("maxPartitions", maxPartitions)}
if rangeConstraint.Min != nil || rangeConstraint.Max != nil {
var conditions []string
if rangeConstraint.Min != nil {
minOp := ">"
if rangeConstraint.IsMinInclusive {
minOp = ">="
}
conditions = append(conditions, fmt.Sprintf("[%s] %s @rangeMin", partitionColumn, minOp))
args = append(args, sql.Named("rangeMin", *rangeConstraint.Min))
}
if rangeConstraint.Max != nil {
maxOp := "<"
if rangeConstraint.IsMaxInclusive {
maxOp = "<="
}
conditions = append(conditions, fmt.Sprintf("[%s] %s @rangeMax", partitionColumn, maxOp))
args = append(args, sql.Named("rangeMax", *rangeConstraint.Max))
}
whereClause = "WHERE " + strings.Join(conditions, " AND ")
}
query := fmt.Sprintf(`
SELECT
MIN([%s]) AS lower_limit,
MAX([%s]) AS upper_limit
FROM (SELECT [%s], NTILE(@maxPartitions) OVER (ORDER BY [%s]) AS batch_id FROM [%s].[%s]) AS T
FROM (SELECT [%s], NTILE(@maxPartitions) OVER (ORDER BY [%s]) AS batch_id FROM [%s].[%s] %s) AS T
GROUP BY batch_id
ORDER BY batch_id`,
partitionColumn,
@@ -214,12 +262,13 @@ ORDER BY batch_id`,
partitionColumn,
partitionColumn,
tableInfo.Schema,
tableInfo.Table)
tableInfo.Table,
whereClause)
ctxTimeout, cancel := context.WithTimeout(ctx, 1*time.Minute)
defer cancel()
rows, err := ta.db.Query(ctxTimeout, query, sql.Named("maxPartitions", maxPartitions))
rows, err := ta.db.Query(ctxTimeout, query, args...)
if err != nil {
return nil, err
}