xref: /aosp_15_r20/external/licenseclassifier/tools/license_serializer/license_serializer.go (revision 46c4c49da23cae783fa41bf46525a6505638499a)
1// Copyright 2017 Google Inc.
2//
3// Licensed under the Apache License, Version 2.0 (the "License");
4// you may not use this file except in compliance with the License.
5// You may obtain a copy of the License at
6//
7//     http://www.apache.org/licenses/LICENSE-2.0
8//
9// Unless required by applicable law or agreed to in writing, software
10// distributed under the License is distributed on an "AS IS" BASIS,
11// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12// See the License for the specific language governing permissions and
13// limitations under the License.
14
15// The license_serializer program normalizes and serializes the known
16// licenseclassifier licenses into a compressed archive. The hash values for
17// the licenses are calculated and added to the archive. These can then be used
18// to determine where in unknown text is a good offset to run through the
19// Levenshtein Distance algorithm.
20package main
21
22import (
23	"flag"
24	"fmt"
25	"log"
26	"os"
27	"path/filepath"
28	"strings"
29
30	"github.com/google/licenseclassifier"
31	"github.com/google/licenseclassifier/serializer"
32)
33
34var (
35	forbiddenOnly = flag.Bool("forbidden", false, "serialize only forbidden licenses")
36	outputDir     = flag.String("output", "", "output directory")
37)
38
39func init() {
40	flag.Usage = func() {
41		fmt.Fprintf(os.Stderr, `Usage: %s [OPTIONS]
42
43Calculate the hash values for files and serialize them into a database.
44See go/license-classifier
45
46Options:
47`, filepath.Base(os.Args[0]))
48		flag.PrintDefaults()
49	}
50}
51
52func main() {
53	flag.Parse()
54
55	archiveName := licenseclassifier.LicenseArchive
56	if *forbiddenOnly {
57		archiveName = licenseclassifier.ForbiddenLicenseArchive
58	}
59
60	fn := filepath.Join(*outputDir, archiveName)
61	out, err := os.Create(fn)
62	if err != nil {
63		log.Fatalf("error: cannot create file %q: %v", fn, err)
64	}
65	defer out.Close()
66
67	lics, err := licenseclassifier.ReadLicenseDir()
68	if err != nil {
69		log.Fatalf("error: cannot read licenses directory: %v", err)
70	}
71
72	var licenses []string
73	for _, lic := range lics {
74		if !*forbiddenOnly || licenseclassifier.LicenseType(strings.TrimSuffix(lic.Name(), ".txt")) == "FORBIDDEN" {
75			licenses = append(licenses, lic.Name())
76		}
77	}
78
79	if err := serializer.ArchiveLicenses(licenses, out); err != nil {
80		log.Fatalf("error: cannot create database: %v", err)
81	}
82}
83