avcodec: add a subcharenc mode that disables UTF-8 check

This is for applications which want to explicitly check for invalid
UTF-8 manually, and take actions that are better than dropping invalid
subtitles silently. (It's pretty much silent because sporadic avcodec
error messages are so common that you can't reasonably display them in a
prominent and meaningful way in a application GUI.)

5 files changed, 8 insertions, 2 deletions

diff --git a/doc/APIchanges b/doc/APIchanges
index a099afd9bc..95b5cd772f 100644
--- a/doc/APIchanges
+++ b/doc/APIchanges
@@ -15,6 +15,9 @@ libavutil:     2017-10-21
 
 API changes, most recent first:
 
+2018-03-xx - xxxxxxx - lavc 58.16.100 - avcodec.h
+  Add FF_SUB_CHARENC_MODE_IGNORE.
+
 2018-xx-xx - xxxxxxx - lavu 56.8.100 - encryption_info.h
   Add AVEncryptionInitInfo and AVEncryptionInfo structures to hold new side-data
   for encryption info.
diff --git a/libavcodec/avcodec.h b/libavcodec/avcodec.h
index 495242faf0..50c34dbff9 100644
--- a/libavcodec/avcodec.h
+++ b/libavcodec/avcodec.h
@@ -3092,6 +3092,7 @@ typedef struct AVCodecContext {
 #define FF_SUB_CHARENC_MODE_DO_NOTHING  -1  ///< do nothing (demuxer outputs a stream supposed to be already in UTF-8, or the codec is bitmap for instance)
 #define FF_SUB_CHARENC_MODE_AUTOMATIC    0  ///< libavcodec will select the mode itself
 #define FF_SUB_CHARENC_MODE_PRE_DECODER  1  ///< the AVPacket data needs to be recoded to UTF-8 before being fed to the decoder, requires iconv
+#define FF_SUB_CHARENC_MODE_IGNORE       2  ///< neither convert the subtitles, nor check them for valid UTF-8
 
     /**
      * Skip processing alpha if supported by codec.
diff --git a/libavcodec/decode.c b/libavcodec/decode.c
index ea2168ad0c..40c8a8855c 100644
--- a/libavcodec/decode.c
+++ b/libavcodec/decode.c
@@ -1057,7 +1057,8 @@ int avcodec_decode_subtitle2(AVCodecContext *avctx, AVSubtitle *sub,
                 sub->format = 1;
 
             for (i = 0; i < sub->num_rects; i++) {
-                if (sub->rects[i]->ass && !utf8_check(sub->rects[i]->ass)) {
+                if (avctx->sub_charenc_mode != FF_SUB_CHARENC_MODE_IGNORE &&
+                    sub->rects[i]->ass && !utf8_check(sub->rects[i]->ass)) {
                     av_log(avctx, AV_LOG_ERROR,
                            "Invalid UTF-8 in decoded subtitles text; "
                            "maybe missing -sub_charenc option\n");
diff --git a/libavcodec/options_table.h b/libavcodec/options_table.h
index 5a5eae65fb..099261e168 100644
--- a/libavcodec/options_table.h
+++ b/libavcodec/options_table.h
@@ -447,6 +447,7 @@ static const AVOption avcodec_options[] = {
 {"do_nothing",  NULL, 0, AV_OPT_TYPE_CONST, {.i64 = FF_SUB_CHARENC_MODE_DO_NOTHING},  INT_MIN, INT_MAX, S|D, "sub_charenc_mode"},
 {"auto",        NULL, 0, AV_OPT_TYPE_CONST, {.i64 = FF_SUB_CHARENC_MODE_AUTOMATIC},   INT_MIN, INT_MAX, S|D, "sub_charenc_mode"},
 {"pre_decoder", NULL, 0, AV_OPT_TYPE_CONST, {.i64 = FF_SUB_CHARENC_MODE_PRE_DECODER}, INT_MIN, INT_MAX, S|D, "sub_charenc_mode"},
+{"ignore",      NULL, 0, AV_OPT_TYPE_CONST, {.i64 = FF_SUB_CHARENC_MODE_IGNORE},      INT_MIN, INT_MAX, S|D, "sub_charenc_mode"},
 #if FF_API_ASS_TIMING
 {"sub_text_format", "set decoded text subtitle format", OFFSET(sub_text_format), AV_OPT_TYPE_INT, {.i64 = FF_SUB_TEXT_FMT_ASS_WITH_TIMINGS}, 0, 1, S|D, "sub_text_format"},
 #else
diff --git a/libavcodec/version.h b/libavcodec/version.h
index a5b7f752d1..8ac4626da7 100644
--- a/libavcodec/version.h
+++ b/libavcodec/version.h
@@ -28,7 +28,7 @@
 #include "libavutil/version.h"
 
 #define LIBAVCODEC_VERSION_MAJOR  58
-#define LIBAVCODEC_VERSION_MINOR  15
+#define LIBAVCODEC_VERSION_MINOR  16
 #define LIBAVCODEC_VERSION_MICRO 100
 
 #define LIBAVCODEC_VERSION_INT  AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \