diff mbox series

[FFmpeg-devel,v2,3/4] avcodec/ttmlenc: add initial support for regions and styles

Message ID 20210414065725.8828-4-jeebjp@gmail.com
State New
Headers show
Series Initial region (styling) support for TTML
Related show

Checks

Context Check Description
andriy/x86_make success Make finished
andriy/x86_make_fate success Make fate finished
andriy/PPC64_make success Make finished
andriy/PPC64_make_fate success Make fate finished

Commit Message

Jan Ekström April 14, 2021, 6:57 a.m. UTC
From: Jan Ekström <jan.ekstrom@24i.com>

Attempts to utilize the TTML cell resolution as a mapping to the
reference resolution, and maps font size to cell size. Additionally
sets the display and text alignment according to the ASS alignment
number.

Signed-off-by: Jan Ekström <jan.ekstrom@24i.com>
---
 libavcodec/ttmlenc.c       | 210 ++++++++++++++++++++++++++++++++++---
 libavcodec/ttmlenc.h       |   3 +-
 tests/ref/fate/sub-ttmlenc |  86 ++++++++-------
 3 files changed, 247 insertions(+), 52 deletions(-)
diff mbox series

Patch

diff --git a/libavcodec/ttmlenc.c b/libavcodec/ttmlenc.c
index e3c155fdd1..c190356683 100644
--- a/libavcodec/ttmlenc.c
+++ b/libavcodec/ttmlenc.c
@@ -100,20 +100,33 @@  static int ttml_encode_frame(AVCodecContext *avctx, uint8_t *buf,
             dialog = ff_ass_split_dialog(s->ass_ctx, ass, 0, &num);
 
             for (; dialog && num--; dialog++) {
-                int ret = ff_ass_split_override_codes(&ttml_callbacks, s,
-                                                      dialog->text);
-                int log_level = (ret != AVERROR_INVALIDDATA ||
-                                 avctx->err_recognition & AV_EF_EXPLODE) ?
-                                AV_LOG_ERROR : AV_LOG_WARNING;
+                if (dialog->style) {
+                    av_bprintf(&s->buffer, "<span region=\"");
+                    av_bprint_escape(&s->buffer, dialog->style, NULL,
+                                     AV_ESCAPE_MODE_XML,
+                                     AV_ESCAPE_FLAG_XML_DOUBLE_QUOTES);
+                    av_bprintf(&s->buffer, "\">");
+                }
 
-                if (ret < 0) {
-                    av_log(avctx, log_level,
-                           "Splitting received ASS dialog failed: %s\n",
-                           av_err2str(ret));
+                {
+                    int ret = ff_ass_split_override_codes(&ttml_callbacks, s,
+                                                          dialog->text);
+                    int log_level = (ret != AVERROR_INVALIDDATA ||
+                                     avctx->err_recognition & AV_EF_EXPLODE) ?
+                                    AV_LOG_ERROR : AV_LOG_WARNING;
 
-                    if (log_level == AV_LOG_ERROR)
-                        return ret;
+                    if (ret < 0) {
+                        av_log(avctx, log_level,
+                               "Splitting received ASS dialog failed: %s\n",
+                               av_err2str(ret));
+
+                        if (log_level == AV_LOG_ERROR)
+                            return ret;
+                    }
                 }
+
+                if (dialog->style)
+                    av_bprintf(&s->buffer, "</span>");
             }
         } else {
 #endif
@@ -121,6 +134,14 @@  static int ttml_encode_frame(AVCodecContext *avctx, uint8_t *buf,
             if (!dialog)
                 return AVERROR(ENOMEM);
 
+            if (dialog->style) {
+                av_bprintf(&s->buffer, "<span region=\"");
+                av_bprint_escape(&s->buffer, dialog->style, NULL,
+                                 AV_ESCAPE_MODE_XML,
+                                 AV_ESCAPE_FLAG_XML_DOUBLE_QUOTES);
+                av_bprintf(&s->buffer, "\">");
+            }
+
             {
                 int ret = ff_ass_split_override_codes(&ttml_callbacks, s,
                                                       dialog->text);
@@ -140,6 +161,9 @@  static int ttml_encode_frame(AVCodecContext *avctx, uint8_t *buf,
                     }
                 }
 
+                if (dialog->style)
+                    av_bprintf(&s->buffer, "</span>");
+
                 ff_ass_free_dialog(&dialog);
             }
 #if FF_API_ASS_TIMING
@@ -173,17 +197,175 @@  static av_cold int ttml_encode_close(AVCodecContext *avctx)
     return 0;
 }
 
+static const char *ttml_get_display_alignment(int alignment)
+{
+    switch (alignment) {
+    case 1:
+    case 2:
+    case 3:
+        return "after";
+    case 4:
+    case 5:
+    case 6:
+        return "center";
+    case 7:
+    case 8:
+    case 9:
+        return "before";
+    default:
+        return NULL;
+    }
+}
+
+static const char *ttml_get_text_alignment(int alignment)
+{
+    switch (alignment) {
+    case 1:
+    case 4:
+    case 7:
+        return "left";
+    case 2:
+    case 5:
+    case 8:
+        return "center";
+    case 3:
+    case 6:
+    case 9:
+        return "right";
+    default:
+        return NULL;
+    }
+}
+
+static int ttml_write_region(AVCodecContext *avctx, AVBPrint *buf,
+                             ASSStyle *style)
+{
+    const char *display_alignment = NULL;
+    const char *text_alignment = NULL;
+
+    if (!style)
+        return AVERROR_INVALIDDATA;
+
+    if (!style->name) {
+        av_log(avctx, AV_LOG_ERROR, "Subtitle style name not set!\n");
+        return AVERROR_INVALIDDATA;
+    }
+
+    if (style->font_size < 0) {
+        av_log(avctx, AV_LOG_ERROR, "Invalid font size for TTML: %d!\n",
+               style->font_size);
+        return AVERROR_INVALIDDATA;
+    }
+
+    display_alignment = ttml_get_display_alignment(style->alignment);
+    text_alignment = ttml_get_text_alignment(style->alignment);
+    if (!display_alignment || !text_alignment) {
+        av_log(avctx, AV_LOG_ERROR,
+               "Failed to convert ASS style alignment %d of style %s to "
+               "TTML display and text alignment!\n",
+               style->alignment,
+               style->name);
+        return AVERROR_INVALIDDATA;
+    }
+
+    av_bprintf(buf, "      <region xml:id=\"");
+    av_bprint_escape(buf, style->name, NULL, AV_ESCAPE_MODE_XML,
+                     AV_ESCAPE_FLAG_XML_DOUBLE_QUOTES);
+    av_bprintf(buf, "\"\n");
+
+    av_bprintf(buf, "        tts:displayAlign=\"");
+    av_bprint_escape(buf, display_alignment, NULL, AV_ESCAPE_MODE_XML,
+                     AV_ESCAPE_FLAG_XML_DOUBLE_QUOTES);
+    av_bprintf(buf, "\"\n");
+
+    av_bprintf(buf, "        tts:textAlign=\"");
+    av_bprint_escape(buf, text_alignment, NULL, AV_ESCAPE_MODE_XML,
+                     AV_ESCAPE_FLAG_XML_DOUBLE_QUOTES);
+    av_bprintf(buf, "\"\n");
+
+    // if we set cell resolution to our script reference resolution,
+    // then a single line is a single "point" on our canvas. Thus, by setting
+    // our font size to font size in cells, we should gain a similar enough
+    // scale without resorting to explicit pixel based font sizing, which is
+    // frowned upon in the TTML community.
+    av_bprintf(buf, "        tts:fontSize=\"%dc\"\n",
+               style->font_size);
+
+    if (style->font_name) {
+        av_bprintf(buf, "        tts:fontFamily=\"");
+        av_bprint_escape(buf, style->font_name, NULL, AV_ESCAPE_MODE_XML,
+                         AV_ESCAPE_FLAG_XML_DOUBLE_QUOTES);
+        av_bprintf(buf, "\"\n");
+    }
+
+    av_bprintf(buf, "        tts:overflow=\"visible\" />\n");
+
+    return 0;
+}
+
 static int ttml_write_header_content(AVCodecContext *avctx)
 {
-    if (!(avctx->extradata = av_mallocz(TTMLENC_EXTRADATA_SIGNATURE_SIZE +
-                                        1 + AV_INPUT_BUFFER_PADDING_SIZE))) {
+    TTMLContext *s = avctx->priv_data;
+    ASS *ass = (ASS *)s->ass_ctx;
+    ASSScriptInfo script_info = ass->script_info;
+    const size_t base_extradata_size = TTMLENC_EXTRADATA_SIGNATURE_SIZE + 1 +
+                                       AV_INPUT_BUFFER_PADDING_SIZE;
+    size_t additional_extradata_size = 0;
+
+    if (script_info.play_res_x <= 0 || script_info.play_res_y <= 0) {
+        av_log(avctx, AV_LOG_ERROR,
+               "Invalid subtitle reference resolution %dx%d!\n",
+               script_info.play_res_x, script_info.play_res_y);
+        return AVERROR_INVALIDDATA;
+    }
+
+    // write the first string in extradata, attributes in the base "tt" element.
+    av_bprintf(&s->buffer, ttml_default_namespacing);
+    // the cell resolution is in character cells, so not exactly 1:1 against
+    // a pixel based resolution, but as the tts:extent in the root
+    // "tt" element is frowned upon (and disallowed in the EBU-TT profile),
+    // we mimic the reference resolution by setting it as the cell resolution.
+    av_bprintf(&s->buffer, "  ttp:cellResolution=\"%d %d\"\n",
+               script_info.play_res_x, script_info.play_res_y);
+    av_bprint_chars(&s->buffer, '\0', 1);
+
+    // write the second string in extradata, head element containing the styles
+    av_bprintf(&s->buffer, "  <head>\n");
+    av_bprintf(&s->buffer, "    <layout>\n");
+
+    for (int i = 0; i < ass->styles_count; i++) {
+        ASSStyle *style = &ass->styles[i];
+        int ret = ttml_write_region(avctx, &s->buffer, style);
+        if (ret < 0)
+            return ret;
+    }
+
+    av_bprintf(&s->buffer, "    </layout>\n");
+    av_bprintf(&s->buffer, "  </head>\n");
+    av_bprint_chars(&s->buffer, '\0', 1);
+
+    if (!av_bprint_is_complete(&s->buffer)) {
         return AVERROR(ENOMEM);
     }
 
-    avctx->extradata_size = TTMLENC_EXTRADATA_SIGNATURE_SIZE;
+    additional_extradata_size = s->buffer.len;
+
+    if (!(avctx->extradata =
+            av_mallocz(base_extradata_size + additional_extradata_size))) {
+        return AVERROR(ENOMEM);
+    }
+
+    avctx->extradata_size =
+        TTMLENC_EXTRADATA_SIGNATURE_SIZE + additional_extradata_size;
     memcpy(avctx->extradata, TTMLENC_EXTRADATA_SIGNATURE,
            TTMLENC_EXTRADATA_SIGNATURE_SIZE);
 
+    if (additional_extradata_size)
+        memcpy(avctx->extradata + TTMLENC_EXTRADATA_SIGNATURE_SIZE,
+               s->buffer.str, additional_extradata_size);
+
+    av_bprint_clear(&s->buffer);
+
     return 0;
 }
 
diff --git a/libavcodec/ttmlenc.h b/libavcodec/ttmlenc.h
index c3bb11478d..467f35c7a6 100644
--- a/libavcodec/ttmlenc.h
+++ b/libavcodec/ttmlenc.h
@@ -28,6 +28,7 @@ 
 static const char ttml_default_namespacing[] =
 "  xmlns=\"http://www.w3.org/ns/ttml\"\n"
 "  xmlns:ttm=\"http://www.w3.org/ns/ttml#metadata\"\n"
-"  xmlns:tts=\"http://www.w3.org/ns/ttml#styling\"\n";
+"  xmlns:tts=\"http://www.w3.org/ns/ttml#styling\"\n"
+"  xmlns:ttp=\"http://www.w3.org/ns/ttml#parameter\"\n";
 
 #endif /* AVCODEC_TTMLENC_H */
diff --git a/tests/ref/fate/sub-ttmlenc b/tests/ref/fate/sub-ttmlenc
index 51eab97817..6d0a8067fc 100644
--- a/tests/ref/fate/sub-ttmlenc
+++ b/tests/ref/fate/sub-ttmlenc
@@ -3,120 +3,132 @@ 
   xmlns="http://www.w3.org/ns/ttml"
   xmlns:ttm="http://www.w3.org/ns/ttml#metadata"
   xmlns:tts="http://www.w3.org/ns/ttml#styling"
+  xmlns:ttp="http://www.w3.org/ns/ttml#parameter"
+  ttp:cellResolution="384 288"
   xml:lang="">
+  <head>
+    <layout>
+      <region xml:id="Default"
+        tts:displayAlign="after"
+        tts:textAlign="center"
+        tts:fontSize="16c"
+        tts:fontFamily="Arial"
+        tts:overflow="visible" />
+    </layout>
+  </head>
   <body>
     <div>
       <p
         begin="00:00:00.000"
-        end="00:00:00.000">Don't show this text it may be used to insert hidden data</p>
+        end="00:00:00.000"><span region="Default">Don't show this text it may be used to insert hidden data</span></p>
       <p
         begin="00:00:01.500"
-        end="00:00:04.500">SubRip subtitles capability tester 1.3o by ale5000<br/>Use VLC 1.1 or higher as reference for most things and MPC Home Cinema for others<br/>This text should be blue<br/>This text should be red<br/>This text should be black<br/>If you see this with the normal font, the player don't (fully) support font face</p>
+        end="00:00:04.500"><span region="Default">SubRip subtitles capability tester 1.3o by ale5000<br/>Use VLC 1.1 or higher as reference for most things and MPC Home Cinema for others<br/>This text should be blue<br/>This text should be red<br/>This text should be black<br/>If you see this with the normal font, the player don't (fully) support font face</span></p>
       <p
         begin="00:00:04.500"
-        end="00:00:04.500">Hidden</p>
+        end="00:00:04.500"><span region="Default">Hidden</span></p>
       <p
         begin="00:00:04.501"
-        end="00:00:07.500">This text should be small<br/>This text should be normal<br/>This text should be big</p>
+        end="00:00:07.500"><span region="Default">This text should be small<br/>This text should be normal<br/>This text should be big</span></p>
       <p
         begin="00:00:07.501"
-        end="00:00:11.500">This should be an E with an accent: È<br/>日本語<br/>This text should be bold, italics and underline<br/>This text should be small and green<br/>This text should be small and red<br/>This text should be big and brown</p>
+        end="00:00:11.500"><span region="Default">This should be an E with an accent: È<br/>日本語<br/>This text should be bold, italics and underline<br/>This text should be small and green<br/>This text should be small and red<br/>This text should be big and brown</span></p>
       <p
         begin="00:00:11.501"
-        end="00:00:14.500">This line should be bold<br/>This line should be italics<br/>This line should be underline<br/>This line should be strikethrough<br/>Both lines<br/>should be underline</p>
+        end="00:00:14.500"><span region="Default">This line should be bold<br/>This line should be italics<br/>This line should be underline<br/>This line should be strikethrough<br/>Both lines<br/>should be underline</span></p>
       <p
         begin="00:00:14.501"
-        end="00:00:17.500">&gt;<br/>It would be a good thing to<br/>hide invalid html tags that are closed and show the text in them<br/>but show un-closed invalid html tags<br/>Show not opened tags<br/>&lt;</p>
+        end="00:00:17.500"><span region="Default">&gt;<br/>It would be a good thing to<br/>hide invalid html tags that are closed and show the text in them<br/>but show un-closed invalid html tags<br/>Show not opened tags<br/>&lt;</span></p>
       <p
         begin="00:00:17.501"
-        end="00:00:20.500">and also<br/>hide invalid html tags with parameters that are closed and show the text in them<br/>but show un-closed invalid html tags<br/>This text should be showed underlined without problems also: 2&lt;3,5&gt;1,4&lt;6<br/>This shouldn't be underlined</p>
+        end="00:00:20.500"><span region="Default">and also<br/>hide invalid html tags with parameters that are closed and show the text in them<br/>but show un-closed invalid html tags<br/>This text should be showed underlined without problems also: 2&lt;3,5&gt;1,4&lt;6<br/>This shouldn't be underlined</span></p>
       <p
         begin="00:00:20.501"
-        end="00:00:21.500">This text should be in the normal position...</p>
+        end="00:00:21.500"><span region="Default">This text should be in the normal position...</span></p>
       <p
         begin="00:00:21.501"
-        end="00:00:22.500">This text should NOT be in the normal position</p>
+        end="00:00:22.500"><span region="Default">This text should NOT be in the normal position</span></p>
       <p
         begin="00:00:22.501"
-        end="00:00:24.500">Implementation is the same of the ASS tag<br/>This text should be at the<br/>top and horizontally centered</p>
+        end="00:00:24.500"><span region="Default">Implementation is the same of the ASS tag<br/>This text should be at the<br/>top and horizontally centered</span></p>
       <p
         begin="00:00:22.501"
-        end="00:00:24.500">This text should be at the<br/>middle and horizontally centered</p>
+        end="00:00:24.500"><span region="Default">This text should be at the<br/>middle and horizontally centered</span></p>
       <p
         begin="00:00:22.501"
-        end="00:00:24.500">This text should be at the<br/>bottom and horizontally centered</p>
+        end="00:00:24.500"><span region="Default">This text should be at the<br/>bottom and horizontally centered</span></p>
       <p
         begin="00:00:24.501"
-        end="00:00:26.500">This text should be at the<br/>top and horizontally at the left</p>
+        end="00:00:26.500"><span region="Default">This text should be at the<br/>top and horizontally at the left</span></p>
       <p
         begin="00:00:24.501"
-        end="00:00:26.500">This text should be at the<br/>middle and horizontally at the left<br/>(The second position must be ignored)</p>
+        end="00:00:26.500"><span region="Default">This text should be at the<br/>middle and horizontally at the left<br/>(The second position must be ignored)</span></p>
       <p
         begin="00:00:24.501"
-        end="00:00:26.500">This text should be at the<br/>bottom and horizontally at the left</p>
+        end="00:00:26.500"><span region="Default">This text should be at the<br/>bottom and horizontally at the left</span></p>
       <p
         begin="00:00:26.501"
-        end="00:00:28.500">This text should be at the<br/>top and horizontally at the right</p>
+        end="00:00:28.500"><span region="Default">This text should be at the<br/>top and horizontally at the right</span></p>
       <p
         begin="00:00:26.501"
-        end="00:00:28.500">This text should be at the<br/>middle and horizontally at the right</p>
+        end="00:00:28.500"><span region="Default">This text should be at the<br/>middle and horizontally at the right</span></p>
       <p
         begin="00:00:26.501"
-        end="00:00:28.500">This text should be at the<br/>bottom and horizontally at the right</p>
+        end="00:00:28.500"><span region="Default">This text should be at the<br/>bottom and horizontally at the right</span></p>
       <p
         begin="00:00:28.501"
-        end="00:00:31.500">This could be the most difficult thing to implement</p>
+        end="00:00:31.500"><span region="Default">This could be the most difficult thing to implement</span></p>
       <p
         begin="00:00:31.501"
-        end="00:00:50.500">First text</p>
+        end="00:00:50.500"><span region="Default">First text</span></p>
       <p
         begin="00:00:33.500"
-        end="00:00:35.500">Second, it shouldn't overlap first</p>
+        end="00:00:35.500"><span region="Default">Second, it shouldn't overlap first</span></p>
       <p
         begin="00:00:35.501"
-        end="00:00:37.500">Third, it should replace second</p>
+        end="00:00:37.500"><span region="Default">Third, it should replace second</span></p>
       <p
         begin="00:00:36.501"
-        end="00:00:50.500">Fourth, it shouldn't overlap first and third</p>
+        end="00:00:50.500"><span region="Default">Fourth, it shouldn't overlap first and third</span></p>
       <p
         begin="00:00:40.501"
-        end="00:00:45.500">Fifth, it should replace third</p>
+        end="00:00:45.500"><span region="Default">Fifth, it should replace third</span></p>
       <p
         begin="00:00:45.501"
-        end="00:00:50.500">Sixth, it shouldn't be<br/>showed overlapped</p>
+        end="00:00:50.500"><span region="Default">Sixth, it shouldn't be<br/>showed overlapped</span></p>
       <p
         begin="00:00:50.501"
-        end="00:00:52.500">TEXT 1 (bottom)</p>
+        end="00:00:52.500"><span region="Default">TEXT 1 (bottom)</span></p>
       <p
         begin="00:00:50.501"
-        end="00:00:52.500">text 2</p>
+        end="00:00:52.500"><span region="Default">text 2</span></p>
       <p
         begin="00:00:52.501"
-        end="00:00:54.500">Hide these tags:<br/>also hide these tags:<br/>but show this: {normal text}</p>
+        end="00:00:54.500"><span region="Default">Hide these tags:<br/>also hide these tags:<br/>but show this: {normal text}</span></p>
       <p
         begin="00:00:54.501"
-        end="00:01:00.500"><br/>\ N is a forced line break<br/>\ h is a hard space<br/>Normal spaces at the start and at the end of the line are trimmed while hard spaces are not trimmed.<br/>The\hline\hwill\hnever\hbreak\hautomatically\hright\hbefore\hor\hafter\ha\hhard\hspace.\h:-D</p>
+        end="00:01:00.500"><span region="Default"><br/>\ N is a forced line break<br/>\ h is a hard space<br/>Normal spaces at the start and at the end of the line are trimmed while hard spaces are not trimmed.<br/>The\hline\hwill\hnever\hbreak\hautomatically\hright\hbefore\hor\hafter\ha\hhard\hspace.\h:-D</span></p>
       <p
         begin="00:00:54.501"
-        end="00:00:56.500"><br/>\h\h\h\h\hA (05 hard spaces followed by a letter)<br/>A (Normal  spaces followed by a letter)<br/>A (No hard spaces followed by a letter)</p>
+        end="00:00:56.500"><span region="Default"><br/>\h\h\h\h\hA (05 hard spaces followed by a letter)<br/>A (Normal  spaces followed by a letter)<br/>A (No hard spaces followed by a letter)</span></p>
       <p
         begin="00:00:56.501"
-        end="00:00:58.500">\h\h\h\h\hA (05 hard spaces followed by a letter)<br/>A (Normal  spaces followed by a letter)<br/>A (No hard spaces followed by a letter)<br/>Show this: \TEST and this: \-)</p>
+        end="00:00:58.500"><span region="Default">\h\h\h\h\hA (05 hard spaces followed by a letter)<br/>A (Normal  spaces followed by a letter)<br/>A (No hard spaces followed by a letter)<br/>Show this: \TEST and this: \-)</span></p>
       <p
         begin="00:00:58.501"
-        end="00:01:00.500"><br/>A letter followed by 05 hard spaces: A\h\h\h\h\h<br/>A letter followed by normal  spaces: A<br/>A letter followed by no hard spaces: A<br/>05 hard  spaces between letters: A\h\h\h\h\hA<br/>5 normal spaces between letters: A     A<br/><br/>^--Forced line break</p>
+        end="00:01:00.500"><span region="Default"><br/>A letter followed by 05 hard spaces: A\h\h\h\h\h<br/>A letter followed by normal  spaces: A<br/>A letter followed by no hard spaces: A<br/>05 hard  spaces between letters: A\h\h\h\h\hA<br/>5 normal spaces between letters: A     A<br/><br/>^--Forced line break</span></p>
       <p
         begin="00:01:00.501"
-        end="00:01:02.500">Both line should be strikethrough,<br/>yes.<br/>Correctly closed tags<br/>should be hidden.</p>
+        end="00:01:02.500"><span region="Default">Both line should be strikethrough,<br/>yes.<br/>Correctly closed tags<br/>should be hidden.</span></p>
       <p
         begin="00:01:02.501"
-        end="00:01:04.500">It shouldn't be strikethrough,<br/>not opened tag showed as text.<br/>Not opened tag showed as text.</p>
+        end="00:01:04.500"><span region="Default">It shouldn't be strikethrough,<br/>not opened tag showed as text.<br/>Not opened tag showed as text.</span></p>
       <p
         begin="00:01:04.501"
-        end="00:01:06.500">Three lines should be strikethrough,<br/>yes.<br/>Not closed tags showed as text</p>
+        end="00:01:06.500"><span region="Default">Three lines should be strikethrough,<br/>yes.<br/>Not closed tags showed as text</span></p>
       <p
         begin="00:01:06.501"
-        end="00:01:08.500">Both line should be strikethrough but<br/>the wrong closing tag should be showed</p>
+        end="00:01:08.500"><span region="Default">Both line should be strikethrough but<br/>the wrong closing tag should be showed</span></p>
     </div>
   </body>
 </tt>