OCTO-11094-always-skip-special-characters

docs/changelog.rst

@@ -1,5 +1,9 @@
 Changelog
 ---------
+2.2.15
+^^^^^^
+- Always skip doubled special characters, not just in case the cue starters are doubled.
+
 2.2.14
 ^^^^^^
 - Fix an issue with WebVTT writer text positioning on break inside a cue.

pycaption/scc/__init__.py

@@ -367,13 +367,12 @@ def _handle_double_command(self, word):
         # doubled special characters and doubled extended characters
         # with only one member of each pair being displayed.
 
-        doubled_types = word != "94a1" and word in COMMANDS or _is_pac_command(word)
+        doubled_types = (word != "94a1" and word in COMMANDS) or _is_pac_command(word) or word in SPECIAL_CHARS
         if self.double_starter:
             doubled_types = (
                 doubled_types
                 or word in EXTENDED_CHARS
                 or word == "94a1"
-                or word in SPECIAL_CHARS
             )
 
         if word in CUE_STARTING_COMMAND and word != self.last_command:

pycaption/scc/constants.py

@@ -988,7 +988,7 @@ def _restructure_bytes_to_position_map(byte_to_pos_map):
 
 # taken from
 # http://www.theneitherworld.com/mcpoodle/SCC_TOOLS/DOCS/CC_CHARS.HTML
-INCONVERTIBLE_TO_ASCII_EXTENDED_CHARS_ASSOCIATION = {
+SUBSTITUTE_CHARACTERS = {
     '¡': ["!", "i"],   # inverted exclamation mark
      '¤': ["C"],  # currency
      '¥': ["Y"],  # yen

setup.py

@@ -20,7 +20,7 @@
 
 setup(
     name="pycaption",
-    version="2.2.14",
+    version="2.2.15.dev1",
     description="Closed caption converter",
     long_description=open(README_PATH).read(),
     author="Joe Norton",

tests/fixtures/scc.py

@@ -144,6 +144,14 @@ def sample_scc_roll_up_ru2():
 
 00:00:13;07    9425 9425 94ad 94ad 9470 9470 c1c2 c3c4 c580 91bf
 
+00:00:13;15    9425 9425 94ad 94ad 9470 9470 9137 
+
+00:00:13;20    9425 9425 94ad 94ad 9470 9470 9137 9137
+
+00:00:13;25    9425 9425 94ad 94ad 9470 9470 9137 9137 9137
+
+00:00:13;40    9425 9425 94ad 94ad 9470 9470 9137 9137 9137 9137
+
 00:00:14;07    9425 9425 94ad 94ad 9470 9470 9220 9220 92a1 92a2 92a7
 
 00:00:17;01    9426 9426 94ad 94ad 9470 9470 57c8 4552 4520 d94f d5a7 5245 20d3 54c1 cec4 49ce c720 ce4f 572c

tests/test_scc.py

@@ -419,8 +419,12 @@ def test_freeze_rollup_captions_contents(self, sample_scc_roll_up_ru2):
             "AND IMPROVING THE LIVES OF ALL",
             "WE SERVE.",
             "®°½",
-            "®°½½",
+            "®°½",
             "ABû",
+            '♪',
+            '♪',
+            '♪♪',
+            '♪♪',
             "ÁÉÓ¡",
             "WHERE YOU'RE STANDING NOW,",
             "LOOKING OUT THERE, THAT'S AL",
@@ -430,6 +434,8 @@ def test_freeze_rollup_captions_contents(self, sample_scc_roll_up_ru2):
             "And wildlife.",
             ">> Bike Iowa, your source for",
         ]
+        for x in actual_texts:
+            print(x)
         assert expected_texts == actual_texts
 
     def test_multiple_formats(self, sample_scc_multiple_formats):