Skip to content

Unicron fix backfill script #4875

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lukaszgryglicki merged 4 commits into from
Nov 25, 2025
Merged

Unicron fix backfill script #4875

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
eeb8c04
Fix the backfill script
lukaszgryglicki Nov 25, 2025
f2bdbf0
Fix the backfill script 2
lukaszgryglicki Nov 25, 2025
0638a36
One more util script
lukaszgryglicki Nov 25, 2025
967dfe9
Merge branch 'dev' into unicron-fix-backfill-script
lukaszgryglicki Nov 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
65 changes: 51 additions & 14 deletions cla-backend-go/cmd/signatures_timestamp_backfill/main.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -408,17 +408,15 @@ func firstPassScanAndUpdate(

updateExpr := setPrefix
vals := map[string]*dynamodb.AttributeValue{":empty": {S: aws.String("")}}
names := map[string]*string{
"#date_created": aws.String(attrDateCreated),
"#date_modified": aws.String(attrDateModified),
}
names := map[string]*string{}
first := true
if setCreated {
if !first {
updateExpr += commaSep
}
updateExpr += exprSetDateCreated
vals[":date_created"] = &dynamodb.AttributeValue{S: aws.String(finalC)}
names["#date_created"] = aws.String(attrDateCreated)
first = false
}
if setModified {
Expand All @@ -427,6 +425,7 @@ func firstPassScanAndUpdate(
}
updateExpr += exprSetDateModified
vals[":date_modified"] = &dynamodb.AttributeValue{S: aws.String(finalM)}
names["#date_modified"] = aws.String(attrDateModified)
}

if debug {
Expand All @@ -450,7 +449,8 @@ func firstPassScanAndUpdate(
}

// Build CLI (always emitted in dry-run; emitted on failure in live-run)
cmd := buildAwsCliUpdate(region, stage, tableName, sig.SignatureID, updateExpr, names, vals, condAnyMissing)
condExpr := buildConditionExpression(names)
cmd := buildAwsCliUpdate(region, stage, tableName, sig.SignatureID, updateExpr, names, vals, condExpr)
dbg(" CLI: %s", cmd)

if dryRun {
Expand All @@ -468,7 +468,7 @@ func firstPassScanAndUpdate(
UpdateExpression: aws.String(updateExpr),
ExpressionAttributeNames: names,
ExpressionAttributeValues: vals,
ConditionExpression: aws.String(condAnyMissing),
ConditionExpression: aws.String(condExpr),
})
if uerr != nil {
log.Printf("Update failed %s: %v", sig.SignatureID, uerr)
Expand Down Expand Up @@ -604,12 +604,7 @@ func snowflakeFix(

updateExpr := setPrefix
vals := map[string]*dynamodb.AttributeValue{":empty": {S: aws.String("")}}
names := map[string]*string{
"#date_created": aws.String(attrDateCreated),
"#date_modified": aws.String(attrDateModified),
"#approx_date_created": aws.String(attrApproxDateCreated),
"#approx_date_modified": aws.String(attrApproxDateModified),
}
names := map[string]*string{}
first := true
if setCreated {
if !first {
Expand All @@ -619,9 +614,11 @@ func snowflakeFix(
if srcC == labelFivetranSynced {
updateExpr += exprSetApproxDateCreated
vals[":approx_date_created"] = &dynamodb.AttributeValue{S: aws.String(finalC)}
names["#approx_date_created"] = aws.String(attrApproxDateCreated)
} else {
updateExpr += exprSetDateCreated
vals[":date_created"] = &dynamodb.AttributeValue{S: aws.String(finalC)}
names["#date_created"] = aws.String(attrDateCreated)
}
first = false
}
Expand All @@ -633,9 +630,11 @@ func snowflakeFix(
if srcM == labelFivetranSynced {
updateExpr += exprSetApproxDateModified
vals[":approx_date_modified"] = &dynamodb.AttributeValue{S: aws.String(finalM)}
names["#approx_date_modified"] = aws.String(attrApproxDateModified)
} else {
updateExpr += exprSetDateModified
vals[":date_modified"] = &dynamodb.AttributeValue{S: aws.String(finalM)}
names["#date_modified"] = aws.String(attrDateModified)
}
}

Expand All @@ -659,7 +658,9 @@ func snowflakeFix(
}
}

cmd := buildAwsCliUpdate(region, stage, tableName, id, updateExpr, names, vals, condAnyMissing)
// Build condition expression with names that are actually defined
condExpr := buildConditionExpression(names)
cmd := buildAwsCliUpdate(region, stage, tableName, id, updateExpr, names, vals, condExpr)
dbg(" SF CLI: %s", cmd)

if dryRun {
Expand All @@ -672,13 +673,16 @@ func snowflakeFix(
continue
}

// Build condition expression with names that are actually defined
condExpr = buildConditionExpression(names)

_, uerr := ddb.UpdateItem(&dynamodb.UpdateItemInput{
TableName: aws.String(tableName),
Key: map[string]*dynamodb.AttributeValue{"signature_id": {S: aws.String(id)}},
UpdateExpression: aws.String(updateExpr),
ExpressionAttributeNames: names,
ExpressionAttributeValues: vals,
ConditionExpression: aws.String(condAnyMissing),
ConditionExpression: aws.String(condExpr),
})
if uerr != nil {
log.Printf("Update failed (SF) %s: %v", id, uerr)
Expand Down Expand Up @@ -1058,6 +1062,39 @@ func parseSnowflakeCSV(b []byte) map[string]string {
return res
}

// buildConditionExpression builds a condition expression using only the attribute names
// that are actually defined in the names map to avoid DynamoDB validation errors
func buildConditionExpression(names map[string]*string) string {
var conditions []string

// Check for regular date_created field
if _, hasDateCreated := names["#date_created"]; hasDateCreated {
conditions = append(conditions, "attribute_not_exists(#date_created) OR #date_created = :empty")
}

// Check for regular date_modified field
if _, hasDateModified := names["#date_modified"]; hasDateModified {
conditions = append(conditions, "attribute_not_exists(#date_modified) OR #date_modified = :empty")
}

// Check for approx_date_created field
if _, hasApproxDateCreated := names["#approx_date_created"]; hasApproxDateCreated {
conditions = append(conditions, "attribute_not_exists(#approx_date_created) OR #approx_date_created = :empty")
}

// Check for approx_date_modified field
if _, hasApproxDateModified := names["#approx_date_modified"]; hasApproxDateModified {
conditions = append(conditions, "attribute_not_exists(#approx_date_modified) OR #approx_date_modified = :empty")
}

// If no specific conditions, use a basic condition that should always allow updates
if len(conditions) == 0 {
return "attribute_exists(signature_id)"
}

return strings.Join(conditions, " OR ")
}

// -----------------------------------------------------------------------------
// AWS CLI builder & stats print
// -----------------------------------------------------------------------------
Expand Down
5 changes: 5 additions & 0 deletions utils/signature_dates_stats.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
#!/bin/bash
aws --profile lfproduct-prod dynamodb scan --table-name cla-prod-signatures --filter-expression "attribute_not_exists(#a) OR #a = :nullval" --expression-attribute-names '{"#a":"date_created"}' --expression-attribute-values '{":nullval":{"NULL":true}}' --select "COUNT"
aws --profile lfproduct-prod dynamodb scan --table-name cla-prod-signatures --filter-expression "attribute_exists(#a)" --expression-attribute-names '{"#a":"approx_date_created"}' --select "COUNT"
aws --profile lfproduct-prod dynamodb scan --table-name cla-prod-signatures --filter-expression "attribute_not_exists(#a) OR #a = :nullval" --expression-attribute-names '{"#a":"date_modified"}' --expression-attribute-values '{":nullval":{"NULL":true}}' --select "COUNT"
aws --profile lfproduct-prod dynamodb scan --table-name cla-prod-signatures --filter-expression "attribute_exists(#a)" --expression-attribute-names '{"#a":"approx_date_modified"}' --select "COUNT"
Loading