package docparser

import (
	"context"
	"fmt"
	"net/http"
	"strings"

	regexp "github.com/wasilibs/go-re2"

	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detector_typepb"
)

type Scanner struct{}

// Ensure the Scanner satisfies the interface at compile time
var _ detectors.Detector = (*Scanner)(nil)

var (
	client = common.SaneHttpClient()

	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives
	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"docparser"}) + `\b([a-f0-9]{40})\b`)
)

// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
	return []string{"docparser"}
}

// FromData will find and optionally verify Docparser secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
	dataStr := string(data)

	matches := keyPat.FindAllStringSubmatch(dataStr, -1)

	for _, match := range matches {
		resMatch := strings.TrimSpace(match[1])

		s1 := detectors.Result{
			DetectorType: detector_typepb.DetectorType_Docparser,
			Raw:          []byte(resMatch),
			SecretParts:  map[string]string{"key": resMatch},
		}

		if verify {
			url := fmt.Sprintf("https://api.docparser.com/v1/parsers?api_key=%s", resMatch)
			req, err := http.NewRequestWithContext(ctx, "GET", url, nil)
			if err != nil {
				continue
			}
			res, err := client.Do(req)
			if err == nil {

				defer func() { _ = res.Body.Close() }()
				if res.StatusCode >= 200 && res.StatusCode < 300 {
					s1.Verified = true
				}
			}
		}

		results = append(results, s1)
	}

	return results, nil
}

func (s Scanner) Type() detector_typepb.DetectorType {
	return detector_typepb.DetectorType_Docparser
}

func (s Scanner) Description() string {
	return "Docparser is a document processing service that extracts data from PDFs and scanned documents. Docparser API keys can be used to access and manipulate this data."
}