Changeset 162450 in webkit

Timestamp:

Jan 21, 2014, 10:44:03 AM (12 years ago)

Author:

eric.carlson@apple.com

Message:

Add ‎ ‏ and   to WebVTT parser
​https://bugs.webkit.org/show_bug.cgi?id=85112

Reviewed by Jer Noble.

Source/WebCore:

No new tests, track-webvtt-tc022-entities.html was updated to test this.

• html/track/WebVTTTokenizer.cpp:

(WebCore::WebVTTTokenizer::nextToken): Support RLM, LRM, and NBSP entities.

LayoutTests:

• media/track/captions-webvtt/tc022-entities.vtt:
• media/track/track-webvtt-tc022-entities-expected.txt:
• media/track/track-webvtt-tc022-entities.html:

Location:

trunk

Files:

• LayoutTests/ChangeLog (modified) (1 diff)
• LayoutTests/media/track/captions-webvtt/tc022-entities.vtt (modified) (1 diff)
• LayoutTests/media/track/track-webvtt-tc022-entities-expected.txt (modified) (1 diff)
• LayoutTests/media/track/track-webvtt-tc022-entities.html (modified) (1 diff)
• Source/WebCore/ChangeLog (modified) (1 diff)
• Source/WebCore/html/track/WebVTTTokenizer.cpp (modified) (2 diffs)

trunk/LayoutTests/ChangeLog

@@ +1 @@
+2014-01-21  Eric Carlson  <eric.carlson@apple.com>
+
+        Add &lrm; &rlm; and &nbsp; to WebVTT parser
+        https://bugs.webkit.org/show_bug.cgi?id=85112
+
+        Reviewed by Jer Noble.
+
+        * media/track/captions-webvtt/tc022-entities.vtt:
+        * media/track/track-webvtt-tc022-entities-expected.txt:
+        * media/track/track-webvtt-tc022-entities.html:
+
 2014-01-21  Mihai Tica  <mitica@adobe.com>
 

trunk/LayoutTests/media/track/captions-webvtt/tc022-entities.vtt

@@ -1 +1 @@
 WEBVTT
-Cue content with escape characters for &, <, and >.
+Cue content with escape characters for &, <, >, LRM, RLM and non-breaking space.
 
 1
 00:00:00.000 --> 00:00:30.500 align:start position:20%
-This cue has an amp &amp; character.
+This cue has an amp character: &amp;
 
 2
 00:00:31.000 --> 00:01:00.500 align:start position:20%
-This cue has a less than &lt; character.
+This cue has a less than character: &lt;
 
 3
 00:01:01.000 --> 00:02:00.500 align:start position:20%
-This cue has a greater than &gt; character.
+This cue has a greater than character: &gt;
+
+4
+00:02:01.000 --> 00:03:00.500 align:start position:20%
+This cue has a right-to-left mark (RLM): &rlm;
+
+5
+00:03:01.000 --> 00:04:00.500 align:start position:20%
+This cue has a left-to-right mark (LRM): &lrm;
+
+6
+00:04:01.000 --> 00:05:00.500 align:start position:20%
+This cue has a non-breakable space (NBSP): &nbsp;

trunk/LayoutTests/media/track/track-webvtt-tc022-entities-expected.txt

@@ -4 +4 @@
 
 *** Testing text track 0
-EXPECTED (cues.length == '3') OK
-EXPECTED (cues[0].getCueAsHTML().textContent == 'This cue has an amp & character.') OK
-EXPECTED (cues[1].getCueAsHTML().textContent == 'This cue has a less than < character.') OK
-EXPECTED (cues[2].getCueAsHTML().textContent == 'This cue has a greater than > character.') OK
+EXPECTED (cues.length == '6') OK
+EXPECTED (cues[0].getCueAsHTML().textContent == 'This cue has an amp character: &') OK
+EXPECTED (cues[1].getCueAsHTML().textContent == 'This cue has a less than character: <') OK
+EXPECTED (cues[2].getCueAsHTML().textContent == 'This cue has a greater than character: >') OK
+EXPECTED (cues[3].getCueAsHTML().textContent == 'This cue has a right-to-left mark (RLM): ‏') OK
+EXPECTED (cues[4].getCueAsHTML().textContent == 'This cue has a left-to-right mark (LRM): ‎') OK
+EXPECTED (cues[5].getCueAsHTML().textContent == 'This cue has a non-breakable space (NBSP):  ') OK
 
 *** Testing text track 1

trunk/LayoutTests/media/track/track-webvtt-tc022-entities.html

@@ -25 +25 @@
                 var expected = 
                 {
-                    length : 3,
+                    length : 6,
                     tests:
                     [
                         {
                             property : "getCueAsHTML().textContent",
-                            values : ["This cue has an amp & character.",
-                                      "This cue has a less than < character.",
-                                      "This cue has a greater than > character."],
+                            values : [
+                                        "This cue has an amp character: \u0026",
+                                        "This cue has a less than character: \u003C",
+                                        "This cue has a greater than character: \u003E",
+                                        "This cue has a right-to-left mark (RLM): \u200f",
+                                        "This cue has a left-to-right mark (LRM): \u200e",
+                                        "This cue has a non-breakable space (NBSP): \u00a0"
+                                     ],
                         },
                     ],

trunk/Source/WebCore/ChangeLog

@@ +1 @@
+2014-01-21  Eric Carlson  <eric.carlson@apple.com>
+
+        Add &lrm; &rlm; and &nbsp; to WebVTT parser
+        https://bugs.webkit.org/show_bug.cgi?id=85112
+
+        Reviewed by Jer Noble.
+
+        No new tests, track-webvtt-tc022-entities.html was updated to test this.
+
+        * html/track/WebVTTTokenizer.cpp:
+        (WebCore::WebVTTTokenizer::nextToken): Support RLM, LRM, and NBSP entities.
+
 2014-01-21  Commit Queue  <commit-queue@webkit.org>
 

trunk/Source/WebCore/html/track/WebVTTTokenizer.cpp

@@ -36 +36 @@
 
 #include "MarkupTokenizerInlines.h"
+#include <wtf/unicode/CharacterNames.h>
 
 namespace WebCore {
@@ -108 +109 @@
             else if (vectorEqualsString(m_buffer, "&gt"))
                 bufferCharacter('>');
+            else if (vectorEqualsString(m_buffer, "&lrm"))
+                bufferCharacter(leftToRightMark);
+            else if (vectorEqualsString(m_buffer, "&rlm"))
+                bufferCharacter(rightToLeftMark);
+            else if (vectorEqualsString(m_buffer, "&nbsp"))
+                bufferCharacter(noBreakSpace);
             else {
                 m_buffer.append(static_cast<LChar>(cc));