Octo 10316 expose the first timestamp from input

pycaption/base.py

@@ -48,6 +48,19 @@ def detect(self, content):
     def read(self, content):
         return CaptionSet({DEFAULT_LANGUAGE_CODE: []})
 
+    def get_initial_timestamp(self, content):
+        """
+        return the start time of first caption in xx:xx:xx.xxx format
+        invocation: reader.get_initial_timestamp(content)
+        :param content: caption file content
+        """
+        try:
+            caps = self.read(content)
+            lang = list(caps._captions.keys())[0]
+            return caps._captions[lang][0].format_start()
+        except (AttributeError, IndexError):
+            return None
+
 
 class BaseWriter:
     def __init__(self, relativize=True, video_width=None, video_height=None,

pycaption/scc/__init__.py

@@ -85,7 +85,7 @@
 from copy import deepcopy
 
 from pycaption.base import (
-    BaseReader, BaseWriter, CaptionSet, CaptionNode,
+    BaseReader, BaseWriter, CaptionSet
 )
 from pycaption.exceptions import CaptionReadNoCaptions, InvalidInputError, \
     CaptionReadTimingError, CaptionLineLengthError
@@ -94,7 +94,7 @@
     MICROSECONDS_PER_CODEWORD, CHARACTER_TO_CODE,
     SPECIAL_OR_EXTENDED_CHAR_TO_CODE, PAC_BYTES_TO_POSITIONING_MAP,
     PAC_HIGH_BYTE_BY_ROW, PAC_LOW_BYTE_BY_ROW_RESTRICTED,
-    PAC_TAB_OFFSET_COMMANDS,
+    PAC_TAB_OFFSET_COMMANDS
 )
 from .specialized_collections import (  # noqa: F401
     TimingCorrectingCaptionList, NotifyingDict, CaptionCreator,

tests/test_base.py

@@ -1,6 +1,9 @@
 import pytest
 
 from pycaption.base import CaptionList, Caption
+from pycaption import (
+    DFXPReader, SAMIReader, SCCReader
+)
 
 
 class TestCaption:
@@ -56,3 +59,15 @@ def test_add_two_caption_lists(self):
 
         with pytest.raises(ValueError):
             newcaps = self.caps + CaptionList([4], layout_info="Other Layout")
+
+
+class TestBaseReader:
+
+    def test_get_initial_timestamp_dfxp(self, sample_dfxp):
+        assert DFXPReader().get_initial_timestamp(sample_dfxp) == "00:00:09.209"
+
+    def test_get_initial_timestamp_sami(self, sample_sami):
+        assert SAMIReader().get_initial_timestamp(sample_sami) == "00:00:09.209"
+
+    def test_get_initial_timestamp_scc(self, sample_scc_pop_on):
+        assert SCCReader().get_initial_timestamp(sample_scc_pop_on) == "00:00:09.743"