[FFmpeg-devel] [PATCH v2 22/26] avutil/ass_split: Add parsing of hard-space tags (\h)

[ffmpegagent <ffmpegagent@gmail.com>]

From: softworkz <softworkz@hotmail.com>

The \h tag in ASS/SSA is indicating a non-breaking space. See
https://github.com/Aegisub/aegisite/blob/master/source/docs/3.2/
ASS_Tags.html.md

The ass_split implementation is used by almost all text subtitle
encoders and it didn't handle this tag. Interestingly, several
tests are testing for \h parsing and had incorrect reference data
for those tests.

The \h tag is specific to ASS and doesn't have any meaning outside
of ASS.
Still, the reference data for ttmlenc, textenc and webvttenc were
full of \h tags even though this tag doesn't have a meaning there.

Signed-off-by: softworkz <softworkz@hotmail.com>
---
 libavutil/ass_split.c            |  7 +++++++
 tests/ref/fate/.gitattributes    |  3 +++
 tests/ref/fate/mov-mp4-ttml-dfxp |  8 ++++----
 tests/ref/fate/mov-mp4-ttml-stpp |  8 ++++----
 tests/ref/fate/sub-textenc       | 10 +++++-----
 tests/ref/fate/sub-ttmlenc       |  8 ++++----
 tests/ref/fate/sub-webvttenc     | 10 +++++-----
 7 files changed, 32 insertions(+), 22 deletions(-)
 create mode 100644 tests/ref/fate/.gitattributes

diff --git a/libavutil/ass_split.c b/libavutil/ass_split.c
index c5963351fc..30512dfc74 100644
--- a/libavutil/ass_split.c
+++ b/libavutil/ass_split.c
@@ -484,6 +484,7 @@ int avpriv_ass_split_override_codes(const ASSCodesCallbacks *callbacks, void *pr
     while (buf && *buf) {
         if (text && callbacks->text &&
             (sscanf(buf, "\\%1[nN]", new_line) == 1 ||
+             sscanf(buf, "\\%1[hH]", new_line) == 1 ||
              !strncmp(buf, "{\\", 2))) {
             callbacks->text(priv, text, text_len);
             text = NULL;
@@ -492,6 +493,12 @@ int avpriv_ass_split_override_codes(const ASSCodesCallbacks *callbacks, void *pr
             if (callbacks->new_line)
                 callbacks->new_line(priv, new_line[0] == 'N');
             buf += 2;
+        } else if (sscanf(buf, "\\%1[hH]", new_line) == 1) {
+            if (callbacks->hard_space)
+                callbacks->hard_space(priv);
+            else if (callbacks->text)
+                callbacks->text(priv, " ", 1);
+            buf += 2;
         } else if (!strncmp(buf, "{\\", 2)) {
             buf++;
             while (*buf == '\\') {
diff --git a/tests/ref/fate/.gitattributes b/tests/ref/fate/.gitattributes
new file mode 100644
index 0000000000..19be64d085
--- /dev/null
+++ b/tests/ref/fate/.gitattributes
@@ -0,0 +1,3 @@
+sub-textenc -diff
+sub-ttmlenc -diff
+sub-webvttenc -diff
diff --git a/tests/ref/fate/mov-mp4-ttml-dfxp b/tests/ref/fate/mov-mp4-ttml-dfxp
index e24b5d618b..e565ffa1f6 100644
--- a/tests/ref/fate/mov-mp4-ttml-dfxp
+++ b/tests/ref/fate/mov-mp4-ttml-dfxp
@@ -1,9 +1,9 @@
-2e7e01c821c111466e7a2844826b7f6d *tests/data/fate/mov-mp4-ttml-dfxp.mp4
-8519 tests/data/fate/mov-mp4-ttml-dfxp.mp4
+658884e1b789e75c454b25bdf71283c9 *tests/data/fate/mov-mp4-ttml-dfxp.mp4
+8486 tests/data/fate/mov-mp4-ttml-dfxp.mp4
 #tb 0: 1/1000
 #media_type 0: data
 #codec_id 0: none
-0,          0,          0,    68500,     7866, 0x456c36b7
+0,          0,          0,    68500,     7833, 0x31b22193
 {
     "packets": [
         {
@@ -15,7 +15,7 @@
             "dts_time": "0.000000",
             "duration": 68500,
             "duration_time": "68.500000",
-            "size": "7866",
+            "size": "7833",
             "pos": "44",
             "flags": "K_"
         }
diff --git a/tests/ref/fate/mov-mp4-ttml-stpp b/tests/ref/fate/mov-mp4-ttml-stpp
index 77bd23b7bf..f25b5b2d28 100644
--- a/tests/ref/fate/mov-mp4-ttml-stpp
+++ b/tests/ref/fate/mov-mp4-ttml-stpp
@@ -1,9 +1,9 @@
-cbd2c7ff864a663b0d893deac5a0caec *tests/data/fate/mov-mp4-ttml-stpp.mp4
-8547 tests/data/fate/mov-mp4-ttml-stpp.mp4
+c9570de0ccebc858b0c662a7e449582c *tests/data/fate/mov-mp4-ttml-stpp.mp4
+8514 tests/data/fate/mov-mp4-ttml-stpp.mp4
 #tb 0: 1/1000
 #media_type 0: data
 #codec_id 0: none
-0,          0,          0,    68500,     7866, 0x456c36b7
+0,          0,          0,    68500,     7833, 0x31b22193
 {
     "packets": [
         {
@@ -15,7 +15,7 @@ cbd2c7ff864a663b0d893deac5a0caec *tests/data/fate/mov-mp4-ttml-stpp.mp4
             "dts_time": "0.000000",
             "duration": 68500,
             "duration_time": "68.500000",
-            "size": "7866",
+            "size": "7833",
             "pos": "44",
             "flags": "K_"
         }
diff --git a/tests/ref/fate/sub-textenc b/tests/ref/fate/sub-textenc
index 3ea56b38f0..910ca3d6e3 100644
--- a/tests/ref/fate/sub-textenc
+++ b/tests/ref/fate/sub-textenc
@@ -160,18 +160,18 @@ but show this: {normal text}
 \ N is a forced line break
 \ h is a hard space
 Normal spaces at the start and at the end of the line are trimmed while hard spaces are not trimmed.
-The\hline\hwill\hnever\hbreak\hautomatically\hright\hbefore\hor\hafter\ha\hhard\hspace.\h:-D
+The line will never break automatically right before or after a hard space. :-D
 
 31
 00:00:54,501 --> 00:00:56,500
 
-\h\h\h\h\hA (05 hard spaces followed by a letter)
+     A (05 hard spaces followed by a letter)
 A (Normal  spaces followed by a letter)
 A (No hard spaces followed by a letter)
 
 32
 00:00:56,501 --> 00:00:58,500
-\h\h\h\h\hA (05 hard spaces followed by a letter)
+     A (05 hard spaces followed by a letter)
 A (Normal  spaces followed by a letter)
 A (No hard spaces followed by a letter)
 Show this: \TEST and this: \-)
@@ -179,10 +179,10 @@ Show this: \TEST and this: \-)
 33
 00:00:58,501 --> 00:01:00,500
 
-A letter followed by 05 hard spaces: A\h\h\h\h\h
+A letter followed by 05 hard spaces: A     
 A letter followed by normal  spaces: A
 A letter followed by no hard spaces: A
-05 hard  spaces between letters: A\h\h\h\h\hA
+05 hard  spaces between letters: A     A
 5 normal spaces between letters: A     A
 
 ^--Forced line break
diff --git a/tests/ref/fate/sub-ttmlenc b/tests/ref/fate/sub-ttmlenc
index 4df8f8796f..aea09bb31e 100644
--- a/tests/ref/fate/sub-ttmlenc
+++ b/tests/ref/fate/sub-ttmlenc
@@ -109,16 +109,16 @@
         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"><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>
+        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 line will never break automatically right before or after a hard space. :-D</span></p>
       <p
         begin="00:00:54.501"
-        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>
+        end="00:00:56.500"><span region="Default"><br/>     A (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"><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>
+        end="00:00:58.500"><span region="Default">     A (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"><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>
+        end="00:01:00.500"><span region="Default"><br/>A letter followed by 05 hard spaces: A     <br/>A letter followed by normal  spaces: A<br/>A letter followed by no hard spaces: A<br/>05 hard  spaces between letters: A     A<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"><span region="Default">Both line should be strikethrough,<br/>yes.<br/>Correctly closed tags<br/>should be hidden.</span></p>
diff --git a/tests/ref/fate/sub-webvttenc b/tests/ref/fate/sub-webvttenc
index 45ae0b6131..f4172dcc84 100644
--- a/tests/ref/fate/sub-webvttenc
+++ b/tests/ref/fate/sub-webvttenc
@@ -132,26 +132,26 @@ but show this: {normal text}
 \ N is a forced line break
 \ h is a hard space
 Normal spaces at the start and at the end of the line are trimmed while hard spaces are not trimmed.
-The\hline\hwill\hnever\hbreak\hautomatically\hright\hbefore\hor\hafter\ha\hhard\hspace.\h:-D
+The line will never break automatically right before or after a hard space. :-D
 
 00:54.501 --> 00:56.500
 
-\h\h\h\h\hA (05 hard spaces followed by a letter)
+     A (05 hard spaces followed by a letter)
 A (Normal  spaces followed by a letter)
 A (No hard spaces followed by a letter)
 
 00:56.501 --> 00:58.500
-\h\h\h\h\hA (05 hard spaces followed by a letter)
+     A (05 hard spaces followed by a letter)
 A (Normal  spaces followed by a letter)
 A (No hard spaces followed by a letter)
 Show this: \TEST and this: \-)
 
 00:58.501 --> 01:00.500
 
-A letter followed by 05 hard spaces: A\h\h\h\h\h
+A letter followed by 05 hard spaces: A     
 A letter followed by normal  spaces: A
 A letter followed by no hard spaces: A
-05 hard  spaces between letters: A\h\h\h\h\hA
+05 hard  spaces between letters: A     A
 5 normal spaces between letters: A     A
 
 ^--Forced line break
-- 
ffmpeg-codebot

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".