2 tofuproxy -- flexible HTTP/WARC proxy with TLS certificates management
3 Copyright (C) 2021 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/>.
39 func NewReader(warcPath string) (*Reader, error) {
40 rrr, err := Open(warcPath, nil, 0)
47 br: bufio.NewReader(rrr),
51 func (r *Reader) next() error {
55 if _, err := r.br.Discard(int(r.prevRec.Size)); err != nil {
58 r.offset += int64(r.prevRec.HdrLen) + r.prevRec.Size
59 for i := 0; i < 2; i++ {
60 line, err := r.br.ReadString('\n')
64 r.offset += int64(len(line))
66 return fmt.Errorf("non-CRLF: %q", line)
72 func (r *Reader) ReadRecord() (*Record, io.Reader, error) {
74 line, err := r.br.ReadString('\n')
78 if !strings.HasPrefix(line, "WARC/") {
79 return nil, nil, fmt.Errorf("non-WARC header: %q", line)
81 hdrLines := []string{line}
85 line, err := r.br.ReadString('\n')
93 hdrLines = append(hdrLines, line)
96 size, err := strconv.ParseUint(hdr.Get("Content-Length"), 10, 64)
109 return rec, &io.LimitedReader{R: r.br, N: int64(size)}, nil
112 func (r *Reader) RecordWasRead() {
117 func (r *Reader) Close() error {
119 r.offsets = r.rrr.Offsets()