merged OCTO-10932-honor-spaces-before-inline-italic-commands

pycaption/scc/constants.py

@@ -1,5 +1,4 @@
 from itertools import product
-from collections import defaultdict
 
 COMMANDS = {
     '9420': '',

tests/conftest.py

@@ -62,6 +62,7 @@
     sample_scc_tab_offset, sample_scc_with_unknown_commands,
     sample_scc_special_and_extended_characters,
     sample_scc_with_line_too_long,
+    sample_scc_with_spaces,
     sample_scc_with_break_and_repositioning
 )
 from tests.fixtures.srt import (  # noqa: F401

tests/fixtures/scc.py

@@ -468,3 +468,16 @@ def sample_scc_with_break_and_repositioning():
 
 00:23:15;11	942c
 """
+
+
+@pytest.fixture(scope="session")
+def sample_scc_with_spaces():
+    return """\
+Scenarist_SCC V1.0
+
+00:00:55;25	9420 942c 942f 9420 9470 97a1 57e5 ece3 ef6d e520 f4ef 9723 2080 2080 2080 91ae 5468 e520 4675 f475 f2e5 20ef e620 57ef f26b ae80
+
+00:00:58;08	942c
+
+00:00:59;10	9420 942c 942f
+"""

tests/test_scc.py

@@ -282,6 +282,20 @@ def test_line_not_breaking_on_break_and_repositioning(
 
         assert expected_lines == actual_lines
 
+    def test_spaces_are_respected(self, sample_scc_with_spaces):
+        expected_lines = ['Welcome to   ', 'The Future of Work.']
+
+        caption_set = SCCReader().read(sample_scc_with_spaces)
+        actual_lines = [
+            node.content
+            for cap_ in caption_set.get_captions('en-US')
+            for node in cap_.nodes
+            if node.type_ == CaptionNode.TEXT
+        ]
+
+        assert expected_lines == actual_lines
+        assert actual_lines[0][-3:] == " " * 3
+
 
 class TestCoverageOnly:
     """In order to refactor safely, we need coverage of 95% or more.