mpv/demux/cue.c

/*
 * This file is part of mpv.
 *
 * mpv is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * mpv is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License along
 * with mpv.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <stdlib.h>
#include <stdbool.h>
#include <string.h>
#include <inttypes.h>

#include "talloc.h"

#include "misc/bstr.h"
#include "common/common.h"

#include "cue.h"

#define SECS_PER_CUE_FRAME (1.0/75.0)

enum cue_command {
    CUE_ERROR = -1,     // not a valid CUE command, or an unknown extension
    CUE_EMPTY,          // line with whitespace only
    CUE_UNUSED,         // valid CUE command, but ignored by this code
    CUE_FILE,
    CUE_TRACK,
    CUE_INDEX,
    CUE_TITLE,
};

static const struct {
    enum cue_command command;
    const char *text;
} cue_command_strings[] = {
    { CUE_FILE, "FILE" },
    { CUE_TRACK, "TRACK" },
    { CUE_INDEX, "INDEX" },
    { CUE_TITLE, "TITLE" },
    { CUE_UNUSED, "CATALOG" },
    { CUE_UNUSED, "CDTEXTFILE" },
    { CUE_UNUSED, "FLAGS" },
    { CUE_UNUSED, "ISRC" },
    { CUE_UNUSED, "PERFORMER" },
    { CUE_UNUSED, "POSTGAP" },
    { CUE_UNUSED, "PREGAP" },
    { CUE_UNUSED, "REM" },
    { CUE_UNUSED, "SONGWRITER" },
    { CUE_UNUSED, "MESSAGE" },
    { -1 },
};

static enum cue_command read_cmd(struct bstr *data, struct bstr *out_params)
{
    struct bstr line = bstr_strip_linebreaks(bstr_getline(*data, data));
    line = bstr_lstrip(line);
    if (line.len == 0)
        return CUE_EMPTY;
    for (int n = 0; cue_command_strings[n].command != -1; n++) {
        struct bstr name = bstr0(cue_command_strings[n].text);
        if (bstr_startswith(line, name)) {
            struct bstr rest = bstr_cut(line, name.len);
            if (rest.len && !strchr(WHITESPACE, rest.start[0]))
                continue;
            if (out_params)
                *out_params = rest;
            return cue_command_strings[n].command;
        }
    }
    return CUE_ERROR;
}

static bool eat_char(struct bstr *data, char ch)
{
    if (data->len && data->start[0] == ch) {
        *data = bstr_cut(*data, 1);
        return true;
    } else {
        return false;
    }
}

static char *read_quoted(void *talloc_ctx, struct bstr *data)
{
    *data = bstr_lstrip(*data);
    if (!eat_char(data, '"'))
        return NULL;
    int end = bstrchr(*data, '"');
    if (end < 0)
        return NULL;
    struct bstr res = bstr_splice(*data, 0, end);
    *data = bstr_cut(*data, end + 1);
    return bstrto0(talloc_ctx, res);
}

// Read a 2 digit unsigned decimal integer.
// Return -1 on failure.
static int read_int_2(struct bstr *data)
{
    *data = bstr_lstrip(*data);
    if (data->len && data->start[0] == '-')
        return -1;
    struct bstr s = *data;
    int res = (int)bstrtoll(s, &s, 10);
    if (data->len == s.len || data->len - s.len > 2)
        return -1;
    *data = s;
    return res;
}

static double read_time(struct bstr *data)
{
    struct bstr s = *data;
    bool ok = true;
    double t1 = read_int_2(&s);
    ok = eat_char(&s, ':') && ok;
    double t2 = read_int_2(&s);
    ok = eat_char(&s, ':') && ok;
    double t3 = read_int_2(&s);
    ok = ok && t1 >= 0 && t2 >= 0 && t3 >= 0;
    return ok ? t1 * 60.0 + t2 + t3 * SECS_PER_CUE_FRAME : 0;
}

static struct bstr skip_utf8_bom(struct bstr data)
{
    return bstr_startswith0(data, "\xEF\xBB\xBF") ? bstr_cut(data, 3) : data;
}

// Check if the text in data is most likely CUE data. This is used by the
// demuxer code to check the file type.
// data is the start of the probed file, possibly cut off at a random point.
bool mp_probe_cue(struct bstr data)
{
    bool valid = false;
    data = skip_utf8_bom(data);
    for (;;) {
        enum cue_command cmd = read_cmd(&data, NULL);
        // End reached. Since the line was most likely cut off, don't use the
        // result of the last parsing call.
        if (data.len == 0)
            break;
        if (cmd == CUE_ERROR)
            return false;
        if (cmd != CUE_EMPTY)
            valid = true;
    }
    return valid;
}

struct cue_file *mp_parse_cue(struct bstr data)
{
    struct cue_file *f = talloc_zero(NULL, struct cue_file);

    data = skip_utf8_bom(data);

    char *filename = NULL;
    // Global metadata, and copied into new tracks.
    struct cue_track proto_track = {0};
    struct cue_track *cur_track = &proto_track;

    while (data.len) {
        struct bstr param;
        switch (read_cmd(&data, &param)) {
        case CUE_ERROR:
            talloc_free(f);
            return NULL;
        case CUE_TRACK: {
            MP_TARRAY_GROW(f, f->tracks, f->num_tracks);
            f->num_tracks += 1;
            cur_track = &f->tracks[f->num_tracks - 1];
            *cur_track = proto_track;
            break;
        }
        case CUE_TITLE:
            cur_track->title = read_quoted(f, &param);
            break;
        case CUE_INDEX: {
            int type = read_int_2(&param);
            double time = read_time(&param);
            if (type == 1) {
                cur_track->start = time;
                cur_track->filename = filename;
            } else if (type == 0) {
                cur_track->pregap_start = time;
            }
            break;
        }
        case CUE_FILE:
            // NOTE: FILE comes before TRACK, so don't use cur_track->filename
            filename = read_quoted(f, &param);
            break;
        }
    }

    return f;
}