Skip to content

misc/language: parse forced tag from external subtitle tracks #16061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 31, 2025
Merged

misc/language: parse forced tag from external subtitle tracks #16061

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6c5efbf
misc/language: parse forced tag from external subtitle tracks
Mar 16, 2025
2389df8
misc/language: add a `forced` flag to the track add commands
Mar 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions DOCS/interface-changes/forced.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
add `forced` flag to track add commands
4 changes: 4 additions & 0 deletions DOCS/man/input.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -673,6 +673,10 @@ Track Manipulation

Marks the track as suitable for the visually impaired.

<forced>

Marks the track as forced.

<attached-picture> (only for ``video-add``)

Marks the track as an attached picture, same as ``albumart`` argument
Expand Down
8 changes: 8 additions & 0 deletions common/common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,6 +91,14 @@ enum video_sync {
VS_NONE,
};

enum track_flags {
// starts at 4, for cmd_track_add backwards compatibility
TRACK_HEARING_IMPAIRED = 1 << 2,
TRACK_VISUAL_IMPAIRED = 1 << 3,
TRACK_ATTACHED_PICTURE = 1 << 4,
TRACK_FORCED = 1 << 5,
};

#define VS_IS_DISP(x) ((x) == VS_DISP_RESAMPLE || \
(x) == VS_DISP_RESAMPLE_VDROP || \
(x) == VS_DISP_RESAMPLE_NONE || \
Expand Down
22 changes: 13 additions & 9 deletions misc/language.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -297,15 +297,15 @@ int mp_match_lang(char **langs, const char *lang)
return best_score;
}

bstr mp_guess_lang_from_filename(bstr name, int *lang_start, bool *hearing_impaired)
bstr mp_guess_lang_from_filename(bstr name, int *lang_start, enum track_flags *flags)
{
name = bstr_strip(bstr_strip_ext(name));

if (lang_start)
*lang_start = -1;

if (hearing_impaired)
*hearing_impaired = false;
if (flags)
*flags = 0;

if (name.len < 2)
return (bstr){0};
Expand All @@ -324,26 +324,30 @@ bstr mp_guess_lang_from_filename(bstr name, int *lang_start, bool *hearing_impai
i--;
}

bool *hi = hearing_impaired ? hearing_impaired : &(bool){0};
bool checked_hi = false;
enum track_flags *f = flags ? flags : &(enum track_flags){0};

while (true) {
while (i >= 0 && mp_isalpha(name.start[i])) {
lang_length++;
i--;
}

if (i >= 0 && lang_length >= 2 && !checked_hi && name.start[i] == delimiter) {
checked_hi = true;
if (i >= 0 && lang_length >= 2 && name.start[i] == delimiter) {
bool matched = false;
static const char *const suffixes[] = { "sdh", "hi", "cc" };
bstr tag = { name.start + i + 1, lang_length };
for (int n = 0; n < MP_ARRAY_SIZE(suffixes); n++) {
if (!bstrcasecmp0(tag, suffixes[n])) {
*hi = true;
*f |= TRACK_HEARING_IMPAIRED;
matched = true;
break;
}
}
if (*hi) {
if (!bstrcasecmp0(tag, "forced")) {
*f |= TRACK_FORCED;
matched = true;
}
if (matched) {
lang_length = 0;
i -= (delimiter != '.') ? 2 : 1;
continue;
Expand Down
3 changes: 2 additions & 1 deletion misc/language.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,10 +21,11 @@
#define MP_LANGUAGE_H

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

// Result numerically higher => better match. 0 == no match.
int mp_match_lang(char **langs, const char *lang);
char **mp_get_user_langs(void);
bstr mp_guess_lang_from_filename(bstr name, int *lang_start, bool *hearing_impaired);
bstr mp_guess_lang_from_filename(bstr name, int *lang_start, enum track_flags *flags);

#endif /* MP_LANGUAGE_H */
15 changes: 11 additions & 4 deletions player/command.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6305,6 +6305,7 @@ static void cmd_track_reload(void *p)
flags |= t->attached_picture ? TRACK_ATTACHED_PICTURE : 0;
flags |= t->hearing_impaired_track ? TRACK_HEARING_IMPAIRED : 0;
flags |= t->visual_impaired_track ? TRACK_VISUAL_IMPAIRED : 0;
flags |= t->forced_track ? TRACK_FORCED : 0;
mp_remove_track(mpctx, t);
nt_num = mp_add_external_file(mpctx, filename, type, cmd->abort->cancel,
flags);
Expand All @@ -6319,9 +6320,12 @@ static void cmd_track_reload(void *p)
struct track *nt = mpctx->tracks[nt_num];

if (!nt->lang) {
enum track_flags flags = 0;
bstr lang = mp_guess_lang_from_filename(bstr0(nt->external_filename), NULL,
&nt->hearing_impaired_track);
&flags);
nt->lang = bstrto0(nt, lang);
nt->hearing_impaired_track = flags & TRACK_HEARING_IMPAIRED;
nt->forced_track = flags & TRACK_FORCED;
}

mp_switch_track(mpctx, nt->type, nt, 0);
Expand Down Expand Up @@ -7155,7 +7159,8 @@ const struct mp_cmd_def mp_cmds[] = {
{"flags", OPT_FLAGS(v.i,
{"select", 0}, {"auto", 1}, {"cached", 2},
{"hearing-impaired", TRACK_HEARING_IMPAIRED},
{"visual-impaired", TRACK_VISUAL_IMPAIRED}),
{"visual-impaired", TRACK_VISUAL_IMPAIRED},
{"forced", TRACK_FORCED}),
.flags = MP_CMD_OPT_ARG},
{"title", OPT_STRING(v.s), .flags = MP_CMD_OPT_ARG},
{"lang", OPT_STRING(v.s), .flags = MP_CMD_OPT_ARG},
Expand All @@ -7171,7 +7176,8 @@ const struct mp_cmd_def mp_cmds[] = {
{"flags", OPT_FLAGS(v.i,
{"select", 0}, {"auto", 1}, {"cached", 2},
{"hearing-impaired", TRACK_HEARING_IMPAIRED},
{"visual-impaired", TRACK_VISUAL_IMPAIRED}),
{"visual-impaired", TRACK_VISUAL_IMPAIRED},
{"forced", TRACK_FORCED}),
.flags = MP_CMD_OPT_ARG},
{"title", OPT_STRING(v.s), .flags = MP_CMD_OPT_ARG},
{"lang", OPT_STRING(v.s), .flags = MP_CMD_OPT_ARG},
Expand All @@ -7188,7 +7194,8 @@ const struct mp_cmd_def mp_cmds[] = {
{"select", 0}, {"auto", 1}, {"cached", 2},
{"hearing-impaired", TRACK_HEARING_IMPAIRED},
{"visual-impaired", TRACK_VISUAL_IMPAIRED},
{"attached-picture", TRACK_ATTACHED_PICTURE}),
{"attached-picture", TRACK_ATTACHED_PICTURE},
{"forced", TRACK_FORCED}),
.flags = MP_CMD_OPT_ARG},
{"title", OPT_STRING(v.s), .flags = MP_CMD_OPT_ARG},
{"lang", OPT_STRING(v.s), .flags = MP_CMD_OPT_ARG},
Expand Down
7 changes: 0 additions & 7 deletions player/core.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -491,13 +491,6 @@ struct mp_abort_entry {
#define WHITE_CIRCLE "\xe2\x97\x8b"
#define BLACK_CIRCLE "\xe2\x97\x8f"

enum track_flags {
// starts at 4, for cmd_track_add backwards compatibility
TRACK_HEARING_IMPAIRED = 1 << 2,
TRACK_VISUAL_IMPAIRED = 1 << 3,
TRACK_ATTACHED_PICTURE = 1 << 4,
};

// audio.c
void reset_audio_state(struct MPContext *mpctx);
void reinit_audio_chain(struct MPContext *mpctx);
Expand Down
6 changes: 3 additions & 3 deletions player/external_files.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,8 +155,8 @@ static void append_dir_subtitles(struct mpv_global *global, struct MPOpts *opts,

bstr lang = {0};
int start = 0;
bool hearing_impaired = false;
lang = mp_guess_lang_from_filename(dename, &start, &hearing_impaired);
enum track_flags flags = 0;
lang = mp_guess_lang_from_filename(dename, &start, &flags);
if (bstr_case_startswith(tmp_fname_trim, f_fname_trim)) {
if (lang.len && start == f_fname_trim.len)
prio |= 16; // exact movie name + followed by lang
Expand Down Expand Up @@ -201,7 +201,7 @@ static void append_dir_subtitles(struct mpv_global *global, struct MPOpts *opts,
sub->priority = prio;
sub->fname = subpath;
sub->lang = lang.len ? bstrdup0(*slist, lang) : NULL;
sub->hearing_impaired = hearing_impaired;
sub->flags = flags;
} else
talloc_free(subpath);
}
Expand Down
4 changes: 3 additions & 1 deletion player/external_files.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,12 +20,14 @@

#include <stdbool.h>

#include "common/common.h"

struct subfn {
int type; // STREAM_SUB/STREAM_AUDIO/STREAM_VIDEO(coverart)
int priority;
char *fname;
char *lang;
bool hearing_impaired;
enum track_flags flags;
};

struct mpv_global;
Expand Down
4 changes: 2 additions & 2 deletions player/loadfile.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -917,6 +917,7 @@ int mp_add_external_file(struct MPContext *mpctx, char *filename,
t->no_auto_select = t->no_default;
t->hearing_impaired_track = flags & TRACK_HEARING_IMPAIRED;
t->visual_impaired_track = flags & TRACK_VISUAL_IMPAIRED;
t->forced_track = flags & TRACK_FORCED;
// if we found video, and we are loading cover art, flag as such.
t->attached_picture = t->type == STREAM_VIDEO && (flags & TRACK_ATTACHED_PICTURE);
if (first_num < 0 && (filter == STREAM_TYPE_COUNT || sh->type == filter))
Expand Down Expand Up @@ -987,8 +988,7 @@ void autoload_external_files(struct MPContext *mpctx, struct mp_cancel *cancel)
if (e->type == STREAM_VIDEO && (sc[STREAM_VIDEO] || !sc[STREAM_AUDIO]))
goto skip;

enum track_flags flags = 0;
flags |= e->hearing_impaired ? TRACK_HEARING_IMPAIRED : 0;
enum track_flags flags = e->flags;
// when given filter is set to video, we are loading up cover art
flags |= e->type == STREAM_VIDEO ? TRACK_ATTACHED_PICTURE : 0;
int first = mp_add_external_file(mpctx, e->fname, e->type, cancel, flags);
Expand Down
85 changes: 49 additions & 36 deletions test/language.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,47 +57,60 @@ int main(void)

void *ta_ctx = talloc_new(NULL);

#define TEST_LANG_GUESS(filename, expected_lang, expected_start, expected_hi) \
do { \
int start; \
bool hearing_impaired; \
bstr lang = mp_guess_lang_from_filename(bstr0(filename), &start, \
&hearing_impaired); \
assert_string_equal(bstrto0(ta_ctx, lang), expected_lang); \
assert_int_equal(start, expected_start); \
assert_true(hearing_impaired == expected_hi); \
#define TEST_LANG_GUESS(filename, expected_lang, expected_start, expected_flags) \
do { \
int start; \
enum track_flags flags; \
bstr lang = mp_guess_lang_from_filename(bstr0(filename), &start, &flags); \
assert_string_equal(bstrto0(ta_ctx, lang), expected_lang); \
assert_int_equal(start, expected_start); \
assert_int_equal(flags, expected_flags); \
} while (0)

TEST_LANG_GUESS("foo.en.srt", "en", 3, false);
TEST_LANG_GUESS("foo.eng.srt", "eng", 3, false);
TEST_LANG_GUESS("foo.e.srt", "", -1, false);
TEST_LANG_GUESS("foo.engg.srt", "", -1, false);
TEST_LANG_GUESS("foo.00.srt", "", -1, false);
TEST_LANG_GUESS("foo.srt", "", -1, false);
TEST_LANG_GUESS(NULL, "", -1, false);
TEST_LANG_GUESS("foo.en.srt", "en", 3, 0);
TEST_LANG_GUESS("foo.eng.srt", "eng", 3, 0);
TEST_LANG_GUESS("foo.e.srt", "", -1, 0);
TEST_LANG_GUESS("foo.engg.srt", "", -1, 0);
TEST_LANG_GUESS("foo.00.srt", "", -1, 0);
TEST_LANG_GUESS("foo.srt", "", -1, 0);
TEST_LANG_GUESS(NULL, "", -1, 0);

TEST_LANG_GUESS("foo.en-US.srt", "en-US", 3, false);
TEST_LANG_GUESS("foo.en-US.hi.srt", "en-US", 3, true);
TEST_LANG_GUESS("foo.en-US.sdh.srt", "en-US", 3, true);
TEST_LANG_GUESS("foo.en-simple.srt", "en-simple", 3, false);
TEST_LANG_GUESS("foo.sgn-FSL.srt", "sgn-FSL", 3, false);
TEST_LANG_GUESS("foo.gsw-u-sd-chzh.srt", "gsw-u-sd-chzh", 3, false);
TEST_LANG_GUESS("foo.en-.srt", "", -1, false);
TEST_LANG_GUESS("foo.en-US-.srt", "", -1, false);
TEST_LANG_GUESS("foo.en-aaaaaaaaa.srt", "", -1, false);
TEST_LANG_GUESS("foo.en-0.srt", "", -1, false);
TEST_LANG_GUESS("foo.en-US.srt", "en-US", 3, 0);
TEST_LANG_GUESS("foo.en-US.hi.srt", "en-US", 3, TRACK_HEARING_IMPAIRED);
TEST_LANG_GUESS("foo.en-US.sdh.srt", "en-US", 3, TRACK_HEARING_IMPAIRED);
TEST_LANG_GUESS("foo.en-US.forced.srt", "en-US", 3, TRACK_FORCED);
TEST_LANG_GUESS("foo.en-US.forced.sdh.srt", "en-US", 3, TRACK_HEARING_IMPAIRED | TRACK_FORCED);
TEST_LANG_GUESS("foo.en-US.sdh.forced.srt", "en-US", 3, TRACK_HEARING_IMPAIRED | TRACK_FORCED);
TEST_LANG_GUESS("foo.en-simple.srt", "en-simple", 3, 0);
TEST_LANG_GUESS("foo.sgn-FSL.srt", "sgn-FSL", 3, 0);
TEST_LANG_GUESS("foo.gsw-u-sd-chzh.srt", "gsw-u-sd-chzh", 3, 0);
TEST_LANG_GUESS("foo.en-.srt", "", -1, 0);
TEST_LANG_GUESS("foo.en-US-.srt", "", -1, 0);
TEST_LANG_GUESS("foo.en-aaaaaaaaa.srt", "", -1, 0);
TEST_LANG_GUESS("foo.en-0.srt", "", -1, 0);

TEST_LANG_GUESS("foo[en].srt", "en", 3, false);
TEST_LANG_GUESS("foo[en-US].srt", "en-US", 3, false);
TEST_LANG_GUESS("foo[en-US][hi].srt", "en-US", 3, true);
TEST_LANG_GUESS("foo[en-US][sdh].srt", "en-US", 3, true);
TEST_LANG_GUESS("foo[].srt", "", -1, false);
TEST_LANG_GUESS("foo[en].srt", "en", 3, 00);
TEST_LANG_GUESS("foo[en-US].srt", "en-US", 3, 0);
TEST_LANG_GUESS("foo[en-US][hi].srt", "en-US", 3, TRACK_HEARING_IMPAIRED);
TEST_LANG_GUESS("foo[en-US][sdh].srt", "en-US", 3, TRACK_HEARING_IMPAIRED);
TEST_LANG_GUESS("foo[en-US][forced].srt", "en-US", 3, TRACK_FORCED);
TEST_LANG_GUESS("foo[en-US][forced][sdh].srt", "en-US", 3, TRACK_HEARING_IMPAIRED | TRACK_FORCED);
TEST_LANG_GUESS("foo[en-US][sdh][forced].srt", "en-US", 3, TRACK_HEARING_IMPAIRED | TRACK_FORCED);
TEST_LANG_GUESS("foo[].srt", "", -1, 0);

TEST_LANG_GUESS("foo(en).srt", "en", 3, false);
TEST_LANG_GUESS("foo(en-US).srt", "en-US", 3, false);
TEST_LANG_GUESS("foo(en-US)(hi).srt", "en-US", 3, true);
TEST_LANG_GUESS("foo(en-US)(sdh).srt", "en-US", 3, true);
TEST_LANG_GUESS("foo().srt", "", -1, false);
TEST_LANG_GUESS("foo(en).srt", "en", 3, 0);
TEST_LANG_GUESS("foo(en-US).srt", "en-US", 3, 0);
TEST_LANG_GUESS("foo(en-US)(hi).srt", "en-US", 3, TRACK_HEARING_IMPAIRED);
TEST_LANG_GUESS("foo(en-US)(sdh).srt", "en-US", 3, TRACK_HEARING_IMPAIRED);
TEST_LANG_GUESS("foo(en-US)(forced).srt", "en-US", 3, TRACK_FORCED);
TEST_LANG_GUESS("foo(en-US)(forced)(sdh).srt", "en-US", 3, TRACK_HEARING_IMPAIRED | TRACK_FORCED);
TEST_LANG_GUESS("foo(en-US)(sdh)(forced).srt", "en-US", 3, TRACK_HEARING_IMPAIRED | TRACK_FORCED);
TEST_LANG_GUESS("foo().srt", "", -1, 0);

TEST_LANG_GUESS("foo.hi.forced.srt", "", -1, TRACK_HEARING_IMPAIRED | TRACK_FORCED);
TEST_LANG_GUESS("foo.forced.hi.srt", "", -1, TRACK_HEARING_IMPAIRED | TRACK_FORCED);
TEST_LANG_GUESS("foo.hi.srt", "", -1, TRACK_HEARING_IMPAIRED);
TEST_LANG_GUESS("foo.forced.srt", "", -1, TRACK_FORCED);

talloc_free(ta_ctx);
}
Loading