1 // tofuproxy -- flexible HTTP/HTTPS proxy, TLS terminator, X.509 TOFU
2 // manager, WARC/geminispace browser
3 // Copyright (C) 2021-2024 Sergey Matveev <stargrave@stargrave.org>
5 // This program is free software: you can redistribute it and/or modify
6 // it under the terms of the GNU General Public License as published by
7 // the Free Software Foundation, version 3 of the License.
9 // This program is distributed in the hope that it will be useful,
10 // but WITHOUT ANY WARRANTY; without even the implied warranty of
11 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 // GNU General Public License for more details.
14 // You should have received a copy of the GNU General Public License
15 // along with this program. If not, see <http://www.gnu.org/licenses/>.
38 func NewReader(warcPath string) (*Reader, error) {
39 rrr, err := Open(warcPath, nil, 0)
46 br: bufio.NewReader(rrr),
50 func (r *Reader) next() error {
54 if _, err := r.br.Discard(int(r.prevRec.Size)); err != nil {
57 r.offset += int64(r.prevRec.HdrLen) + r.prevRec.Size
58 for i := 0; i < 2; i++ {
59 line, err := r.br.ReadString('\n')
63 r.offset += int64(len(line))
65 return fmt.Errorf("non-CRLF: %q", line)
71 func (r *Reader) ReadRecord() (*Record, io.Reader, error) {
73 line, err := r.br.ReadString('\n')
77 if !strings.HasPrefix(line, "WARC/") {
78 return nil, nil, fmt.Errorf("non-WARC header: %q", line)
80 hdrLines := []string{line}
84 line, err := r.br.ReadString('\n')
92 hdrLines = append(hdrLines, line)
95 size, err := strconv.ParseUint(hdr.Get("Content-Length"), 10, 64)
108 return rec, &io.LimitedReader{R: r.br, N: int64(size)}, nil
111 func (r *Reader) RecordWasRead() {
116 func (r *Reader) Close() error {
118 r.offsets = r.rrr.Offsets()