pycaption 2.2.22__tar.gz → 2.2.24__tar.gz

{pycaption-2.2.22/pycaption.egg-info → pycaption-2.2.24}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycaption
-Version: 2.2.22
+Version: 2.2.24
 Summary: Closed caption converter
 Author: Joe Norton
 Author-email: joey@nortoncrew.com
@@ -27,7 +27,7 @@ Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-lazy-fixture; extra == "dev"
 Provides-Extra: transcript
-Requires-Dist: nltk==3.9.1; extra == "transcript"
+Requires-Dist: nltk==3.9.4; extra == "transcript"
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier

{pycaption-2.2.22 → pycaption-2.2.24}/pycaption/dfxp/base.py

@@ -147,9 +147,13 @@ class DFXPReader(BaseReader):
     def _convert_div_to_caption_list(self, div):
         return CaptionList(
             [
-                self._convert_p_tag_to_caption(p_tag)
-                for p_tag in div.find_all("p")
-                if p_tag.get_text().strip()
+                caption
+                for caption in (
+                    self._convert_p_tag_to_caption(p_tag)
+                    for p_tag in div.find_all("p")
+                    if p_tag.get_text().strip()
+                )
+                if caption is not None
             ],
             div.layout_info,
         )

{pycaption-2.2.22 → pycaption-2.2.24}/pycaption/scc/__init__.py

@@ -332,7 +332,15 @@ class SCCReader(BaseReader):
         for idx, word in enumerate(word_list):
             word = word.strip()
             if len(word) == 4:
-                next_command = word_list[idx + 1] if idx + 1 < len(word_list) else None
+                # Look ahead for the next command, skipping the duplicate
+                # that SCC uses for error-correction (same word repeated).
+                next_idx = idx + 1
+                if (next_idx < len(word_list)
+                        and word_list[next_idx].strip() == word):
+                    next_idx += 1
+                next_command = (
+                    word_list[next_idx] if next_idx < len(word_list) else None
+                )
                 self._translate_word(word=word, next_command=next_command)
 
     def _translate_word(self, word, next_command=None):
@@ -584,11 +592,12 @@ class SCCWriter(BaseWriter):
             code_words = len(code) / 5 + 8
             code_time_microseconds = code_words * MICROSECONDS_PER_CODEWORD
             code_start = start - code_time_microseconds
-            if index == 0:
-                continue
-            previous_code, previous_start, previous_end = codes[index - 1]
-            if previous_end + 3 * MICROSECONDS_PER_CODEWORD >= code_start:
-                codes[index - 1] = (previous_code, previous_start, None)
+            if index > 0:
+                previous_code, previous_start, previous_end = codes[index - 1]
+                if code_start < previous_start:
+                    code_start = previous_start
+                if previous_end + 3 * MICROSECONDS_PER_CODEWORD >= code_start:
+                    codes[index - 1] = (previous_code, previous_start, None)
             codes[index] = (code, code_start, end)
 
         # PASS 3:

{pycaption-2.2.22 → pycaption-2.2.24/pycaption.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycaption
-Version: 2.2.22
+Version: 2.2.24
 Summary: Closed caption converter
 Author: Joe Norton
 Author-email: joey@nortoncrew.com
@@ -27,7 +27,7 @@ Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-lazy-fixture; extra == "dev"
 Provides-Extra: transcript
-Requires-Dist: nltk==3.9.1; extra == "transcript"
+Requires-Dist: nltk==3.9.4; extra == "transcript"
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier

{pycaption-2.2.22 → pycaption-2.2.24}/pycaption.egg-info/requires.txt

@@ -7,4 +7,4 @@ pytest
 pytest-lazy-fixture
 
 [transcript]
-nltk==3.9.1
+nltk==3.9.4

{pycaption-2.2.22 → pycaption-2.2.24}/setup.py

@@ -16,11 +16,11 @@ dependencies = [
 
 dev_dependencies = ["pytest", "pytest-lazy-fixture"]
 
-transcript_dependencies = ["nltk==3.9.1"]
+transcript_dependencies = ["nltk==3.9.4"]
 
 setup(
     name="pycaption",
-    version="2.2.22",
+    version="2.2.24",
     description="Closed caption converter",
     long_description=open(README_PATH).read(),
     author="Joe Norton",

{pycaption-2.2.22 → pycaption-2.2.24}/tests/conftest.py

@@ -45,6 +45,7 @@ from tests.fixtures.dfxp import (  # noqa: F401
     sample_dfxp_with_relativized_positioning,
     sample_dfxp_with_templated_style,
     sample_dfxp_without_region_and_style,
+    sample_dfxp_concurrent_with_empty_p,
 )
 from tests.fixtures.microdvd import missing_fps_sample_microdvd  # noqa: F401
 from tests.fixtures.microdvd import (
@@ -90,6 +91,7 @@ from tests.fixtures.scc import (  # noqa: F401
     sample_no_positioning_at_all_scc,
     sample_scc_created_dfxp_with_wrongly_closing_spans,
     sample_scc_duplicate_special_characters,
+    sample_scc_doubled_mid_row_before_punctuation,
     sample_scc_duplicate_tab_offset,
     sample_scc_empty,
     sample_scc_eoc_first_command,

{pycaption-2.2.22 → pycaption-2.2.24}/tests/fixtures/dfxp.py

@@ -1521,3 +1521,31 @@ def sample_dfxp_default_styling_p_tags():
   </div>
  </body>
 </tt>"""
+
+
+@pytest.fixture(scope="session")
+def sample_dfxp_concurrent_with_empty_p():
+    return """\
+<?xml version="1.0" encoding="utf-8"?>
+<tt xml:lang="en" xmlns="http://www.w3.org/ns/ttml"
+    xmlns:tts="http://www.w3.org/ns/ttml#styling">
+ <head>
+  <styling>
+   <style xml:id="basic" tts:color="white"/>
+  </styling>
+  <layout>
+   <region xml:id="pop1" tts:origin="17.5% 84.66%" tts:extent="62.5% 5.33%"/>
+   <region xml:id="pop2" tts:origin="50% 84.66%" tts:extent="0% 5.33%"/>
+  </layout>
+ </head>
+ <body>
+  <div xml:lang="en">
+   <p region="pop1" style="basic" begin="01:55:05:08" end="01:55:11:14"
+      tts:origin="17.5% 84.66%" tts:extent="62.5% 5.33%">Subtitle End
+   </p>
+   <p region="pop2" style="basic" begin="01:55:05:08" end="01:55:11:14"
+      tts:origin="50% 84.66%" tts:extent="0% 5.33%">
+   </p>
+  </div>
+ </body>
+</tt>"""

{pycaption-2.2.22 → pycaption-2.2.24}/tests/fixtures/scc.py

@@ -659,3 +659,13 @@ Scenarist_SCC V1.0
 00:00:04;00	942c
 
 """
+
+
+@pytest.fixture(scope="session")
+def sample_scc_doubled_mid_row_before_punctuation():
+    return """\
+Scenarist_SCC V1.0
+
+00:26:48;29\t9420 9420 94d0 94d0 97a1 97a1 3e3e 2057 e5a7 ecec 2062 e520 6261 e36b 206e e5f8 f420 f7e5 e56b 20f7 e9f4 6880 9470 9470 616e eff4 68e5 f220 e570 e973 ef64 e520 efe6 91ae 91ae 4361 6e61 6461 2046 e9ec e573 9120 9120 ae80 942c 942c 8080 8080 942f 942f
+
+"""

{pycaption-2.2.22 → pycaption-2.2.24}/tests/test_dfxp.py

@@ -1,6 +1,7 @@
 import pytest
 
-from pycaption import CaptionReadNoCaptions, DFXPReader
+from pycaption import CaptionReadNoCaptions, DFXPReader, SRTWriter
+from pycaption.base import merge_concurrent_captions
 from pycaption.exceptions import (
     CaptionReadError,
     CaptionReadSyntaxError,
@@ -230,3 +231,44 @@ class TestDFXPReader(ReaderTestingMixIn):
         caps = caption_set.get_captions("en-US")
 
         assert len(caps) == 1
+
+    def test_concurrent_captions_with_empty_p_no_none_in_list(
+        self, sample_dfxp_concurrent_with_empty_p
+    ):
+        caption_set = DFXPReader().read(sample_dfxp_concurrent_with_empty_p)
+        captions = caption_set.get_captions("en")
+        assert all(c is not None for c in captions)
+        assert len(captions) == 1
+
+    def test_concurrent_captions_with_empty_p_merge_does_not_crash(
+        self, sample_dfxp_concurrent_with_empty_p
+    ):
+        caption_set = DFXPReader().read(sample_dfxp_concurrent_with_empty_p)
+        merged = merge_concurrent_captions(caption_set)
+        captions = merged.get_captions("en")
+        assert len(captions) >= 1
+        assert all(c is not None for c in captions)
+
+    def test_concurrent_captions_with_empty_p_srt_writer_does_not_crash(
+        self, sample_dfxp_concurrent_with_empty_p
+    ):
+        caption_set = DFXPReader().read(sample_dfxp_concurrent_with_empty_p)
+        output = SRTWriter().write(caption_set)
+        assert "Subtitle End" in output
+
+    def test_none_from_convert_p_tag_is_filtered(self, sample_dfxp):
+        reader = DFXPReader()
+        original = reader._convert_p_tag_to_caption
+        call_count = [0]
+
+        def patched(p_tag):
+            call_count[0] += 1
+            if call_count[0] == 2:
+                return None
+            return original(p_tag)
+
+        reader._convert_p_tag_to_caption = patched
+        caption_set = reader.read(sample_dfxp)
+        captions = caption_set.get_captions("en-US")
+        assert all(c is not None for c in captions)
+        assert len(captions) == 6

{pycaption-2.2.22 → pycaption-2.2.24}/tests/test_scc.py

@@ -392,6 +392,24 @@ class TestSCCReader(ReaderTestingMixIn):
             ]
             assert expected_lines == actual_lines
 
+    def test_doubled_mid_row_before_punctuation_no_extra_space(
+        self,
+        sample_scc_doubled_mid_row_before_punctuation,
+    ):
+        caption_set = SCCReader().read(
+            sample_scc_doubled_mid_row_before_punctuation
+        )
+        captions = caption_set.get_captions("en-US")
+        text_nodes = [
+            node.content
+            for cap_ in captions
+            for node in cap_.nodes
+            if node.type_ == CaptionNode.TEXT
+        ]
+        full_text = "".join(text_nodes)
+        assert " ." not in full_text
+        assert full_text.endswith("Files.")
+
     def test_removing_spaces_at_end_of_lines(
         self,
         sample_scc_with_spaces_at_eol_pop,

{pycaption-2.2.22 → pycaption-2.2.24}/tests/test_scc_conversion.py

@@ -1,3 +1,5 @@
+import re
+
 import pytest
 
 from pycaption import (
@@ -6,6 +8,7 @@ from pycaption import (
     SCCWriter,
     SRTReader,
     SRTWriter,
+    WebVTTReader,
     WebVTTWriter,
 )
 from tests.mixins import CaptionSetTestingMixIn
@@ -65,6 +68,36 @@ class TestSCCtoDFXP:
         assert dfxp == sample_dfxp_with_ampersand_character
 
 
+class TestSCCTimestampOrdering:
+    def test_scc_captions_are_in_order_when_short_text_followed_by_long(self):
+        """When short caption text is followed by longer caption text,
+        the SCC output timestamps should remain in chronological order.
+        """
+        vtt_input = (
+            "WEBVTT\n\n"
+            "0\n"
+            "00:00:02.200 --> 00:00:02.359\n"
+            "you know,\n\n"
+            "1\n"
+            "00:00:02.400 --> 00:00:03.760\n"
+            "the way he kind of looked at me.\n\n"
+            "2\n"
+            "00:00:04.700 --> 00:00:05.169\n"
+            "And I said,\n\n"
+            "3\n"
+            "00:00:05.210 --> 00:00:05.520\n"
+            "oh\n"
+        )
+        captions = WebVTTReader().read(vtt_input)
+        scc_output = SCCWriter().write(captions)
+        # SCC timestamps use HH:MM:SS:FF format (FF = frames)
+        timestamps = re.findall(r"(\d+:\d+:\d+:\d+)", scc_output)
+        for i in range(1, len(timestamps)):
+            assert timestamps[i] >= timestamps[i - 1], (
+                f"Timestamps out of order: {timestamps[i - 1]} > {timestamps[i]}"
+            )
+
+
 class TestSCCToWebVTT:
     def test_webvtt_newlines_are_properly_rendered(
         self,