scriptorium/internal/validate/standard_validator.go

package validate

import (
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"os"
	"path/filepath"
	"strings"

	"gitea.maximumdirect.net/eric/scriptorium/internal/domain"
	"github.com/santhosh-tekuri/jsonschema/v6"
)

// StandardValidator provides basic, JSON, and JSON Schema output validation.
type StandardValidator struct {
	schemaBaseDir string
}

func NewStandardValidator(schemaBaseDir string) Validator {
	return &StandardValidator{schemaBaseDir: schemaBaseDir}
}

func (v *StandardValidator) Validate(ctx context.Context, artifact *domain.Artifact, contract domain.OutputContract) (domain.ValidationResult, error) {
	select {
	case <-ctx.Done():
		return domain.ValidationResult{}, ctx.Err()
	default:
	}

	res := domain.ValidationResult{
		Mode:           contract.ValidationMode,
		SchemaPath:     contract.SchemaPath,
		RepairAttempts: contract.RepairAttempts,
	}

	if artifact == nil {
		return domain.ValidationResult{}, errors.New("artifact is required for validation")
	}

	switch contract.ValidationMode {
	case domain.ValidationNone:
		res.Status = domain.ValidationSkipped
		res.IsValid = true
		return res, nil
	case domain.ValidationBasic:
		if strings.TrimSpace(string(artifact.Body)) == "" {
			res.Status = domain.ValidationFailed
			res.IsValid = false
			res.Errors = []string{"output is empty"}
			return res, nil
		}
		res.Status = domain.ValidationPassed
		res.IsValid = true
		return res, nil
	case domain.ValidationJSON:
		_, jsonErr := parseJSON(artifact.Body)
		if jsonErr != nil {
			res.Status = domain.ValidationFailed
			res.IsValid = false
			res.Errors = []string{fmt.Sprintf("invalid JSON: %v", jsonErr)}
			return res, nil
		}
		res.Status = domain.ValidationPassed
		res.IsValid = true
		return res, nil
	case domain.ValidationJSONSchema:
		instance, jsonErr := parseJSON(artifact.Body)
		if jsonErr != nil {
			res.Status = domain.ValidationFailed
			res.IsValid = false
			res.Errors = []string{fmt.Sprintf("invalid JSON: %v", jsonErr)}
			return res, nil
		}

		schemaPath, err := v.resolveSchemaPath(contract.SchemaPath)
		if err != nil {
			return domain.ValidationResult{}, err
		}

		compiler := jsonschema.NewCompiler()
		schema, err := compiler.Compile(schemaPath)
		if err != nil {
			return domain.ValidationResult{}, fmt.Errorf("failed to compile JSON schema %q: %w", schemaPath, err)
		}

		if err := schema.Validate(instance); err != nil {
			res.Status = domain.ValidationFailed
			res.IsValid = false
			res.Errors = []string{fmt.Sprintf("json schema validation failed: %v", err)}
			return res, nil
		}

		res.Status = domain.ValidationPassed
		res.IsValid = true
		return res, nil
	default:
		return domain.ValidationResult{}, fmt.Errorf("unsupported validation mode: %q", contract.ValidationMode)
	}
}

func parseJSON(body []byte) (any, error) {
	var v any
	if err := json.Unmarshal(body, &v); err != nil {
		return nil, err
	}
	return v, nil
}

func (v *StandardValidator) LoadSchemaDocument(ctx context.Context, schemaPath string) (any, error) {
	select {
	case <-ctx.Done():
		return nil, ctx.Err()
	default:
	}

	resolved, err := v.resolveSchemaPath(schemaPath)
	if err != nil {
		return nil, err
	}

	raw, err := os.ReadFile(resolved)
	if err != nil {
		return nil, fmt.Errorf("failed to read schema file %q: %w", resolved, err)
	}

	var doc any
	if err := json.Unmarshal(raw, &doc); err != nil {
		return nil, fmt.Errorf("failed to decode JSON schema %q: %w", resolved, err)
	}
	return doc, nil
}

func (v *StandardValidator) resolveSchemaPath(schemaPath string) (string, error) {
	if strings.TrimSpace(schemaPath) == "" {
		return "", errors.New("schema path is required for json_schema validation")
	}

	resolved := schemaPath
	if !filepath.IsAbs(schemaPath) {
		resolved = filepath.Join(v.schemaBaseDir, schemaPath)
	}

	resolved = filepath.Clean(resolved)
	if _, err := os.Stat(resolved); err != nil {
		return "", fmt.Errorf("failed to access schema file %q: %w", resolved, err)
	}

	return resolved, nil
}