Skip to content
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.

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

Implement deletion handling in CDC iterator #13

Merged
merged 6 commits into from
Oct 25, 2022
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
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
34 changes: 26 additions & 8 deletions hubspot/list.go
Original file line number Diff line number Diff line change
Expand Up @@ -35,18 +35,36 @@ const UpdatedAtListSortKey = "updatedAt"
type TimestampResource struct {
CreatedAtFieldName string
UpdatedAtFieldName string
DeletedAtFieldName string
}

// TimestampResources holds a list of resources that support timestamp-based filtering.
var TimestampResources = map[string]TimestampResource{
"cms.blogs.authors": {CreatedAtFieldName: "created", UpdatedAtFieldName: "updated"},
"cms.blogs.posts": {CreatedAtFieldName: "created", UpdatedAtFieldName: "updated"},
"cms.blogs.tags": {CreatedAtFieldName: "created", UpdatedAtFieldName: "updated"},
"cms.pages.landing": {CreatedAtFieldName: "createdAt", UpdatedAtFieldName: "updatedAt"},
"cms.pages.site": {CreatedAtFieldName: "createdAt", UpdatedAtFieldName: "updatedAt"},
"cms.hubdb.tables": {CreatedAtFieldName: "createdAt", UpdatedAtFieldName: "updatedAt"},
"cms.domains": {CreatedAtFieldName: "createdAt", UpdatedAtFieldName: "updatedAt"},
"cms.urlRedirects": {CreatedAtFieldName: "createdAt", UpdatedAtFieldName: "updatedAt"},
"cms.blogs.authors": {
CreatedAtFieldName: "created",
UpdatedAtFieldName: "updated",
DeletedAtFieldName: "deletedAt",
},
"cms.blogs.posts": {
CreatedAtFieldName: "created",
UpdatedAtFieldName: "updated",
DeletedAtFieldName: "deletedAt",
},
"cms.blogs.tags": {
CreatedAtFieldName: "created",
UpdatedAtFieldName: "updated",
DeletedAtFieldName: "deletedAt",
},
"cms.pages.landing": {
CreatedAtFieldName: "createdAt",
UpdatedAtFieldName: "updatedAt",
DeletedAtFieldName: "deletedAt",
},
"cms.pages.site": {
CreatedAtFieldName: "createdAt",
UpdatedAtFieldName: "updatedAt",
DeletedAtFieldName: "deletedAt",
},
}

// ResourcesListPaths holds a mapping of supported resources and their list endpoints.
Expand Down
60 changes: 49 additions & 11 deletions source/iterator/cdc.go
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,9 @@ import (
"fmt"
"time"

"github.com/conduitio-labs/conduit-connector-hubspot/hubspot"
sdk "github.com/conduitio/conduit-connector-sdk"

"github.com/conduitio-labs/conduit-connector-hubspot/hubspot"
)

// CDC is an implementation of a CDC iterator for the HubSpot API.
Expand Down Expand Up @@ -58,7 +59,7 @@ func NewCDC(ctx context.Context, params CDCParams) (*CDC, error) {
}

if cdc.position == nil || cdc.position.Timestamp == nil {
now := time.Now()
now := time.Now().UTC()
cdc.position = &Position{
Mode: CDCPositionMode,
Timestamp: &now,
Expand Down Expand Up @@ -149,6 +150,7 @@ func (c *CDC) fetchTimestampBasedItems(
Limit: c.bufferSize,
UpdatedAfter: &updatedAfter,
Sort: hubspot.UpdatedAtListSortKey,
Archived: true,
}

listResp, err := c.hubspotClient.List(ctx, c.resource, listOpts)
Expand All @@ -157,7 +159,11 @@ func (c *CDC) fetchTimestampBasedItems(
}

for _, item := range listResp.Results {
err = c.routeItem(item, resource.CreatedAtFieldName, resource.UpdatedAtFieldName, updatedAfter)
err = c.routeItem(item,
resource.CreatedAtFieldName,
resource.UpdatedAtFieldName,
resource.DeletedAtFieldName,
updatedAfter)
if err != nil {
return fmt.Errorf("route timestamp based item: %w", err)
}
Expand All @@ -178,7 +184,7 @@ func (c *CDC) fetchSearchBasedItems(
}

for _, item := range listResp.Results {
err = c.routeItem(item, resource.CreatedAtFieldName, resource.UpdatedAtFieldName, updatedAfter)
err = c.routeItem(item, resource.CreatedAtFieldName, resource.UpdatedAtFieldName, "", updatedAfter)
if err != nil {
return fmt.Errorf("route search based item: %w", err)
}
Expand All @@ -192,7 +198,8 @@ func (c *CDC) fetchSearchBasedItems(
func (c *CDC) routeItem(
item hubspot.ListResponseResult,
createdAtFieldName,
updatedAtFieldName string,
updatedAtFieldName,
deletedAtFieldName string,
updatedAfter time.Time,
) error {
itemCreatedAt, err := item.GetTimeField(createdAtFieldName)
Expand Down Expand Up @@ -220,23 +227,54 @@ func (c *CDC) routeItem(
return fmt.Errorf("marshal sdk position: %w", err)
}

var itemDeletedAt time.Time
oykmnk marked this conversation as resolved.
Show resolved Hide resolved
if deletedAtFieldName != "" {
itemDeletedAt, err = item.GetTimeField(deletedAtFieldName)
if err != nil {
return fmt.Errorf("get item's update date: %w", err)
oykmnk marked this conversation as resolved.
Show resolved Hide resolved
}
}

c.records <- c.GetRecord(item,
itemCreatedAt,
itemUpdatedAt,
itemDeletedAt,
updatedAfter,
sdkPosition,
metadata)

return nil
}

func (c *CDC) GetRecord(item hubspot.ListResponseResult,
itemCreatedAt,
itemUpdatedAt,
itemDeletedAt,
updatedAfter time.Time,
sdkPosition sdk.Position,
metadata sdk.Metadata,
) sdk.Record {
if itemDeletedAt != (time.Time{}) {
if itemDeletedAt == itemUpdatedAt && itemDeletedAt.Unix() > 0 {
return sdk.Util.Source.NewRecordDelete(sdkPosition, metadata,
sdk.StructuredData{hubspot.ResultsFieldID: item[hubspot.ResultsFieldID]},
)
}
}
oykmnk marked this conversation as resolved.
Show resolved Hide resolved

// if the item's createdAt is after the timestamp after which we're searching items
// we consider the item's operation to be sdk.OperationCreate.
if itemCreatedAt.After(updatedAfter) {
c.records <- sdk.Util.Source.NewRecordCreate(sdkPosition, metadata,
return sdk.Util.Source.NewRecordCreate(sdkPosition, metadata,
sdk.StructuredData{hubspot.ResultsFieldID: item[hubspot.ResultsFieldID]},
sdk.StructuredData(item),
)

return nil
}

c.records <- sdk.Util.Source.NewRecordUpdate(sdkPosition, metadata,
return sdk.Util.Source.NewRecordUpdate(sdkPosition, metadata,
sdk.StructuredData{hubspot.ResultsFieldID: item[hubspot.ResultsFieldID]},
nil, sdk.StructuredData(item),
)

return nil
}

// Stop stops the iterator.
Expand Down