Merge pull request #320 from pbs/OCTO-10912-Add-new-substitute-charac…

…ter-to-ignore-before-extended-character-in-SCC Add-new-substitute-character-to-ignore-before-extended-character-in-SCC
pbs · Jan 30, 2024 · ec21f9d · ec21f9d
2 parents 19755dc + 6144e28
commit ec21f9d
Show file tree

Hide file tree

Showing 5 changed files with 69 additions and 65 deletions.
diff --git a/docs/changelog.rst b/docs/changelog.rst
@@ -1,5 +1,10 @@
 Changelog
 ---------
+2.2.3.dev
+^^^^^
+- Add new substitute character to ignore before extended character
+    in SCC input files
+
 2.2.2
 ^^^^^
 - Remove support for Python 3.6 & 3.7

diff --git a/docs/conf.py b/docs/conf.py
@@ -53,9 +53,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = '2.2.0'
+version = '2.2.3.dev'
 # The full version, including alpha/beta/rc tags.
-release = '2.2.0'
+release = '2.2.3.dev'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

diff --git a/pycaption/scc/constants.py b/pycaption/scc/constants.py
@@ -990,60 +990,60 @@ 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 = {
-    '¡': "!",   # inverted exclamation mark
-     '¤': "C",  # currency
-     '¥': "Y",  # yen
-     '¦': "-",  # broken bar
-     '©': "c",  # copyright sign
-     '«': '"',  # left pointing double angle quotation mark
-     '»': '"',  # right pointing double angle quotation mark
-     'À': "A",
-     'Á': "A",
-     'Â': "A",
-     'Ã': "A",
-     'Ä': "A",
-     'Å': "A",
-     'Ç': "C",
-     'È': "E",
-     'É': "E",
-     'Ê': "E",
-     'Ë': "E",
-     'Ì': "I",
-     'Í': "I",
-     'Î': "I",
-     'Ï': "I",
-     'Ò': "O",
-     'Ó': "O",
-     'Ô': ")",
-     'Õ': "O",
-     'Ö': "O",
-     'Ø': "O",
-     'Ù': "U",
-     'Ú': "U",
-     'Û': "U",
-     'Ü': "U",
-     'ß': "s",
-     'ã': "a",
-     'ä': "a",
-     'å': "a",
-     'ë': "e",
-     'ì': "i",
-     'ï': "i",
-     'ò': "o",
-     'õ': "o",
-     'ö': "o",
-     'ø': "o",
-     'ù': "u",
-     'ü': "u",
-     '—': "-",  # em dash
-     '‘': "'",
-     '’': "'",
-     '“': '"',
-     '”': '"',
-     '•': ".",
-     '℠': "s",
-     '┌': "+",
-     '┐': "+",
-     '└': "+",
-     '┘': "+"
+    '¡': ["!", "i"],   # inverted exclamation mark
+     '¤': ["C"],  # currency
+     '¥': ["Y"],  # yen
+     '¦': ["-"],  # broken bar
+     '©': ["c"],  # copyright sign
+     '«': ['"'],  # left pointing double angle quotation mark
+     '»': ['"'],  # right pointing double angle quotation mark
+     'À': ["A"],
+     'Á': ["A"],
+     'Â': ["A"],
+     'Ã': ["A"],
+     'Ä': ["A"],
+     'Å': ["A"],
+     'Ç': ["C"],
+     'È': ["E"],
+     'É': ["E"],
+     'Ê': ["E"],
+     'Ë': ["E"],
+     'Ì': ["I"],
+     'Í': ["I"],
+     'Î': ["I"],
+     'Ï': ["I"],
+     'Ò': ["O"],
+     'Ó': ["O"],
+     'Ô': [")"],
+     'Õ': ["O"],
+     'Ö': ["O"],
+     'Ø': ["O"],
+     'Ù': ["U"],
+     'Ú': ["U"],
+     'Û': ["U"],
+     'Ü': ["U"],
+     'ß': ["s"],
+     'ã': ["a"],
+     'ä': ["a"],
+     'å': ["a"],
+     'ë': ["e"],
+     'ì': ["i"],
+     'ï': ["i"],
+     'ò': ["o"],
+     'õ': ["o"],
+     'ö': ["o"],
+     'ø': ["o"],
+     'ù': ["u"],
+     'ü': ["u"],
+     '—': ["-"],  # em dash
+     '‘': ["'"],
+     '’': ["'"],
+     '“': ['"'],
+     '”': ['"'],
+     '•': ["."],
+     '℠': ["s"],
+     '┌': ["+"],
+     '┐': ["+"],
+     '└': ["+"],
+     '┘': ["+"]
 }
diff --git a/pycaption/scc/specialized_collections.py b/pycaption/scc/specialized_collections.py
@@ -430,18 +430,17 @@ def remove_ascii_duplicate(self, accented_character):
                 )
         if is_text_node:
             try:
-                ascii_char = unicodedata.normalize('NFD', accented_character) \
+                ascii_char = [
+                    unicodedata.normalize('NFD', accented_character)
                     .encode('ascii', 'strict').decode("utf-8")
-            except (UnicodeEncodeError, UnicodeDecodeError):
-                ascii_char = INCONVERTIBLE_TO_ASCII_EXTENDED_CHARS_ASSOCIATION[
-                    accented_character
                 ]
+            except (UnicodeEncodeError, UnicodeDecodeError):
+                ascii_char = INCONVERTIBLE_TO_ASCII_EXTENDED_CHARS_ASSOCIATION.get(accented_character)
 
-            if ascii_char and self._collection[-1].text[-1] == ascii_char:
+            if ascii_char and self._collection[-1].text[-1] in ascii_char:
                 self._collection[-1].text = self._collection[-1].text[:-1]
 
 
-
 def _get_layout_from_tuple(position_tuple):
     """Create a Layout object from the positioning information given
 

diff --git a/setup.py b/setup.py
@@ -24,7 +24,7 @@
 
 setup(
     name='pycaption',
-    version='2.2.2',
+    version='2.2.3.dev',
     description='Closed caption converter',
     long_description=open(README_PATH).read(),
     author='Joe Norton',