-
Notifications
You must be signed in to change notification settings - Fork 3
feat: Lucene query parser with sql and dynamodb support #124
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
Open
Lutherwaves
wants to merge
11
commits into
main
Choose a base branch
from
dev
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
11 commits
Select commit
Hold shift + click to select a range
e9cb930
feat: implement Lucene query parser with PostgreSQL and DynamoDB support
Lutherwaves 1a066d6
refactor: simplify parser
Lutherwaves e399459
refactor: simplify Lucene parser API and architecture
Lutherwaves daa91c8
refactor: make Lucene parser SQL generation generic for PostgreSQL, M…
Lutherwaves 6cba442
feat: add SearchQuery schema with Lucene search examples to OpenAPI d…
Lutherwaves 4acb4b4
chore: update grindlemire/go-lucene deps
Lutherwaves 09450f8
chore: add unit tests for parser
Lutherwaves 7d55c2a
fix: stricter validation for duplicates, escapes to prevent injection
Lutherwaves 235e353
fix: linting errors
Lutherwaves cec6427
fix(parser): fix OpenAPI validation, improve error handling with erro…
Lutherwaves d486307
fix(sqlstorage): fix cursor pagination with json tag lookup and place…
Lutherwaves File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Some comments aren't visible on the classic Files Changed page.
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,137 @@ | ||
| package lucene | ||
|
|
||
| import ( | ||
| "fmt" | ||
| "regexp" | ||
| "strings" | ||
|
|
||
| "github.com/aws/aws-sdk-go-v2/service/dynamodb/types" | ||
| "github.com/grindlemire/go-lucene/pkg/driver" | ||
| "github.com/grindlemire/go-lucene/pkg/lucene/expr" | ||
| ) | ||
|
|
||
| // DynamoDBPartiQLDriver converts Lucene queries to DynamoDB PartiQL. | ||
| type DynamoDBPartiQLDriver struct { | ||
| driver.Base | ||
| fields map[string]FieldInfo | ||
| } | ||
|
|
||
| func NewDynamoDBDriver(fields []FieldInfo) (*DynamoDBPartiQLDriver, error) { | ||
| fieldMap, err := buildFieldMap(fields) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
|
|
||
| fns := map[expr.Operator]driver.RenderFN{ | ||
| expr.Literal: driver.Shared[expr.Literal], | ||
| expr.And: driver.Shared[expr.And], | ||
| expr.Or: driver.Shared[expr.Or], | ||
| expr.Not: driver.Shared[expr.Not], | ||
| expr.Equals: driver.Shared[expr.Equals], | ||
| expr.Range: driver.Shared[expr.Range], | ||
| expr.Must: driver.Shared[expr.Must], | ||
| expr.MustNot: driver.Shared[expr.MustNot], | ||
| expr.Wild: driver.Shared[expr.Wild], | ||
| expr.Regexp: driver.Shared[expr.Regexp], | ||
| expr.Like: dynamoDBLike, // Custom LIKE for DynamoDB functions | ||
| expr.Greater: driver.Shared[expr.Greater], | ||
| expr.GreaterEq: driver.Shared[expr.GreaterEq], | ||
| expr.Less: driver.Shared[expr.Less], | ||
| expr.LessEq: driver.Shared[expr.LessEq], | ||
| expr.In: driver.Shared[expr.In], | ||
| expr.List: driver.Shared[expr.List], | ||
| } | ||
|
|
||
| return &DynamoDBPartiQLDriver{ | ||
| Base: driver.Base{ | ||
| RenderFNs: fns, | ||
| }, | ||
| fields: fieldMap, | ||
| }, nil | ||
| } | ||
|
|
||
| // RenderPartiQL renders the expression to DynamoDB PartiQL with AttributeValue parameters. | ||
| func (d *DynamoDBPartiQLDriver) RenderPartiQL(e *expr.Expression) (string, []types.AttributeValue, error) { | ||
| // Use base rendering with ? placeholders | ||
| str, params, err := d.RenderParam(e) | ||
| if err != nil { | ||
| return "", nil, err | ||
| } | ||
|
|
||
| // Convert params to DynamoDB AttributeValues | ||
| attrValues := make([]types.AttributeValue, len(params)) | ||
| for i, param := range params { | ||
| attrValues[i] = &types.AttributeValueMemberS{Value: fmt.Sprintf("%v", param)} | ||
| } | ||
|
|
||
| return str, attrValues, nil | ||
| } | ||
|
|
||
| // escapePartiQLString escapes a string value for safe use in PartiQL string literals. | ||
| // Escapes single quotes by doubling them (PartiQL standard). | ||
| func escapePartiQLString(s string) string { | ||
| return strings.ReplaceAll(s, "'", "''") | ||
| } | ||
|
|
||
| var ( | ||
| // partiQLIdentifierPattern matches valid PartiQL identifiers (alphanumeric and underscore only) | ||
| partiQLIdentifierPattern = regexp.MustCompile(`^[a-zA-Z0-9_]+$`) | ||
| ) | ||
|
|
||
| // escapePartiQLIdentifier escapes a field name for safe use in PartiQL. | ||
| // Validates that the identifier contains only safe characters (alphanumeric, underscore). | ||
| // Returns error if identifier contains potentially dangerous characters. | ||
| func escapePartiQLIdentifier(identifier string) (string, error) { | ||
| if !partiQLIdentifierPattern.MatchString(identifier) { | ||
| return "", fmt.Errorf("invalid identifier: contains unsafe characters (only alphanumeric and underscore allowed)") | ||
| } | ||
| return identifier, nil | ||
| } | ||
|
|
||
| // unquotePartiQLString safely removes surrounding quotes from a PartiQL string literal. | ||
| // Handles already-escaped quotes correctly. | ||
| func unquotePartiQLString(s string) string { | ||
| if len(s) >= 2 && s[0] == '\'' && s[len(s)-1] == '\'' { | ||
| return s[1 : len(s)-1] | ||
| } | ||
| return s | ||
| } | ||
|
|
||
| // dynamoDBLike implements LIKE using DynamoDB's begins_with and contains functions. | ||
| func dynamoDBLike(left, right string) (string, error) { | ||
| // Validate and escape field name (left) | ||
| safeLeft, err := escapePartiQLIdentifier(left) | ||
| if err != nil { | ||
| return "", fmt.Errorf("invalid field name: %w", err) | ||
| } | ||
|
|
||
| // Extract the raw value from the right side (remove quotes if present) | ||
| rawValue := unquotePartiQLString(right) | ||
|
|
||
| // Analyze pattern for wildcards | ||
| hasPrefix := strings.HasPrefix(rawValue, "%") | ||
| hasSuffix := strings.HasSuffix(rawValue, "%") | ||
|
|
||
| if hasPrefix && hasSuffix { | ||
| // %value% -> contains(field, value) | ||
| value := strings.Trim(rawValue, "%") | ||
| escapedValue := escapePartiQLString(value) | ||
| return fmt.Sprintf("contains(%s, '%s')", safeLeft, escapedValue), nil | ||
| } | ||
| if !hasPrefix && hasSuffix { | ||
| // value% -> begins_with(field, value) | ||
| value := strings.TrimSuffix(rawValue, "%") | ||
| escapedValue := escapePartiQLString(value) | ||
| return fmt.Sprintf("begins_with(%s, '%s')", safeLeft, escapedValue), nil | ||
| } | ||
| if hasPrefix && !hasSuffix { | ||
| // %value -> contains(field, value) (DynamoDB doesn't have ends_with) | ||
| value := strings.TrimPrefix(rawValue, "%") | ||
| escapedValue := escapePartiQLString(value) | ||
| return fmt.Sprintf("contains(%s, '%s')", safeLeft, escapedValue), nil | ||
| } | ||
|
|
||
| // Exact match - escape the value and wrap in quotes | ||
| escapedValue := escapePartiQLString(rawValue) | ||
| return fmt.Sprintf("%s = '%s'", safeLeft, escapedValue), nil | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.