pycaption 2.2.5__tar.gz → 2.2.7__tar.gz

{pycaption-2.2.5/pycaption.egg-info → pycaption-2.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pycaption
-Version: 2.2.5
+Version: 2.2.7
 Summary: Closed caption converter
 Author: Joe Norton
 Author-email: joey@nortoncrew.com

{pycaption-2.2.5 → pycaption-2.2.7}/pycaption/scc/__init__.py

@@ -81,11 +81,11 @@ http://www.theneitherworld.com/mcpoodle/SCC_TOOLS/DOCS/SCC_FORMAT.HTML
 import math
 import re
 import textwrap
-from collections import deque
+from collections import deque, defaultdict
 from copy import deepcopy
 
 from pycaption.base import (
-    BaseReader, BaseWriter, CaptionSet, CaptionNode,
+    BaseReader, BaseWriter, CaptionSet
 )
 from pycaption.exceptions import CaptionReadNoCaptions, InvalidInputError, \
     CaptionReadTimingError, CaptionLineLengthError
@@ -232,16 +232,24 @@ class SCCReader(BaseReader):
         captions = CaptionSet({lang: self.caption_stash.get_all()})
 
         # check captions for incorrect lengths
-        lines = []
+        lines_too_long = defaultdict(list)
         for caption in self.caption_stash._collection:
+            caption_start = caption.to_real_caption().format_start()
             caption_text = "".join(caption.to_real_caption().get_text_nodes())
-            lines.extend(caption_text.split("\n"))
-        lines_too_long = [line for line in lines if len(line) > 32]
-
-        if bool(lines_too_long):
-            msg = ""
-            for line in lines_too_long:
-                msg += line + f" - Length { len(line)}" + "\n"
+            text_too_long = [line for line in caption_text.split("\n") if len(line) > 32]
+            if caption_start in lines_too_long:
+                lines_too_long[caption_start] = text_too_long
+            else:
+                lines_too_long[caption_start].extend(text_too_long)
+
+        msg = ""
+        if bool(lines_too_long.keys()):
+            for key in lines_too_long:
+                if lines_too_long[key]:
+                    msg += f"around {key} - "
+                    for line in lines_too_long[key]:
+                        msg += line + f" - Length { len(line)}" + "\n"
+        if len(msg):
             raise CaptionLineLengthError(
                 f"32 character limit for caption cue in scc file.\n"
                 f"Lines longer than 32:\n"
@@ -301,27 +309,21 @@ class SCCReader(BaseReader):
         self.time_translator.start_at(parts[0][0])
 
         # loop through each word
-        words = [word.strip() for word in parts[0][2].split(' ') if len(word) == 4]
-
-        for idx, word in enumerate(words):
-            self._translate_word(word, words, idx)
-
-    @staticmethod
-    def get_command(commands, idx):
-        try:
-            return commands[idx]
-        except IndexError:
-            return None
-
-    def _translate_word(self, word, words, idx):
-        if self._skip_double_command(word, words, idx):
+        for word in parts[0][2].split(' '):
+            # ignore empty results or invalid commands
+            word = word.strip()
+            if len(word) == 4:
+                self._translate_word(word)
+
+    def _translate_word(self, word):
+        if self._handle_double_command(word):
             # count frames for timing
             self.time_translator.increment_frames()
             return
         # first check if word is a command
         # TODO - check that all the positioning commands are here, or use
         # some other strategy to determine if the word is a command.
-        if word in COMMANDS or _is_pac_command(word) or word in PAC_TAB_OFFSET_COMMANDS:
+        if word in COMMANDS or _is_pac_command(word):
             self._translate_command(word)
 
         # second, check if word is a special character
@@ -338,39 +340,31 @@ class SCCReader(BaseReader):
         # count frames for timing only after processing a command
         self.time_translator.increment_frames()
 
-    def _skip_double_command(self, word, words, idx):
+    def _handle_double_command(self, word):
         # If the caption is to be broadcast, each of the commands are doubled
         # up for redundancy in case the signal is garbled in transmission.
         # The decoder is programmed to ignore a second command when it is the
         # same as the first.
         # Also like codes, Special Characters are always doubled up,
         # with only one member of each pair being displayed.
-        next_command = self.get_command(words, idx + 1)
-        second_next = self.get_command(words, idx + 2)
-
         if word in COMMANDS or _is_pac_command(word) or word in SPECIAL_CHARS or word in EXTENDED_CHARS:
-            # skip duplicates, execute the last occurrence if not a positioning command
-            if word == self.last_command and not _is_pac_command(word):
-                self.last_command = ''
-                return True
-            # skip consecutive positioning commands, execute the last one
-            elif _is_pac_command(word) and _is_pac_command(next_command):
+            if word == self.last_command:
                 self.last_command = ''
                 return True
-            # Fix for the <position> <tab offset> <position> <tab offset> repetition
-            # execute the last positioning command
-            elif _is_pac_command(word) and next_command in PAC_TAB_OFFSET_COMMANDS and _is_pac_command(second_next):
+            # Fix for the <position> <tab offset> <position> <tab offset>
+            # repetition
+            elif _is_pac_command(word) and word in self.last_command:
                 self.last_command = ''
                 return True
-            # execute offset commands only if previous command is PAC and next is not PAC
             elif word in PAC_TAB_OFFSET_COMMANDS:
-                if _is_pac_command(self.last_command) and not _is_pac_command(next_command):
-                    self.last_command = word
+                if _is_pac_command(self.last_command):
+                    self.last_command += f" {word}"
                     return False
                 else:
                     return True
-            self.last_command = word
-            return False
+
+        self.last_command = word
+        return False
 
     def _translate_special_char(self, word):
         self.buffer.add_chars(SPECIAL_CHARS[word])

{pycaption-2.2.5 → pycaption-2.2.7}/pycaption/scc/constants.py

@@ -1,5 +1,4 @@
 from itertools import product
-from collections import defaultdict
 
 COMMANDS = {
     '9420': '',
@@ -987,8 +986,6 @@ MICROSECONDS_PER_CODEWORD = 1000.0 * 1000.0 / (30.0 * 1000.0 / 1001.0)
 
 HEADER = 'Scenarist_SCC V1.0'
 
-UNHANDLED_COMMANDS = ["9120", "91ae", "912f", "91a1"]
-
 # taken from
 # http://www.theneitherworld.com/mcpoodle/SCC_TOOLS/DOCS/CC_CHARS.HTML
 INCONVERTIBLE_TO_ASCII_EXTENDED_CHARS_ASSOCIATION = {
@@ -1049,3 +1046,9 @@ INCONVERTIBLE_TO_ASCII_EXTENDED_CHARS_ASSOCIATION = {
      '└': ["+"],
      '┘': ["+"]
 }
+
+MID_ROW_CODES = [
+    "9120", "91a1", "91a2", "9123", "91a4", "9125", "9126",
+    "91a7", "91a8", "9129", "912a", "91ab", "912c", "91ad",
+    "97ae", "972f", "91ae", "912f", "94a8"
+]

{pycaption-2.2.5 → pycaption-2.2.7}/pycaption/scc/specialized_collections.py

@@ -8,8 +8,8 @@ from ..geometry import (
 )
 from .constants import (
     PAC_BYTES_TO_POSITIONING_MAP, COMMANDS, PAC_TAB_OFFSET_COMMANDS,
-    MICROSECONDS_PER_CODEWORD, UNHANDLED_COMMANDS,
-    INCONVERTIBLE_TO_ASCII_EXTENDED_CHARS_ASSOCIATION
+    MICROSECONDS_PER_CODEWORD, INCONVERTIBLE_TO_ASCII_EXTENDED_CHARS_ASSOCIATION,
+    MID_ROW_CODES
 )
 
 PopOnCue = collections.namedtuple("PopOnCue", "buffer, start, end")
@@ -255,7 +255,7 @@ class CaptionCreator:
                 layout_info = _get_layout_from_tuple(instruction.position)
                 caption.nodes.append(
                     CaptionNode.create_text(
-                        instruction.get_text(), layout_info=layout_info),
+                        instruction.text, layout_info=layout_info),
                 )
                 caption.layout_info = layout_info
 
@@ -343,9 +343,16 @@ class InstructionNodeCreator:
 
         :type command: str
         """
-        if command not in UNHANDLED_COMMANDS:
-            self._update_positioning(command)
+        self._update_positioning(command)
+
         text = COMMANDS.get(command, '')
+
+        if command in MID_ROW_CODES:
+            for node in self._collection[::-1]:
+                if node.is_text_node():
+                    node.text += ' '
+                    break
+
         if 'italic' in text:
             if 'end' not in text:
                 self._collection.append(

{pycaption-2.2.5 → pycaption-2.2.7/pycaption.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pycaption
-Version: 2.2.5
+Version: 2.2.7
 Summary: Closed caption converter
 Author: Joe Norton
 Author-email: joey@nortoncrew.com

{pycaption-2.2.5 → pycaption-2.2.7}/setup.py

@@ -24,7 +24,7 @@ transcript_dependencies = [
 
 setup(
     name='pycaption',
-    version='2.2.5',
+    version='2.2.7',
     description='Closed caption converter',
     long_description=open(README_PATH).read(),
     author='Joe Norton',

{pycaption-2.2.5 → pycaption-2.2.7}/tests/conftest.py

@@ -61,8 +61,6 @@ from tests.fixtures.scc import (  # noqa: F401
     sample_scc_duplicate_tab_offset, sample_scc_duplicate_special_characters,
     sample_scc_tab_offset, sample_scc_with_unknown_commands,
     sample_scc_special_and_extended_characters,
-    sample_scc_with_consecutive_pac_commands,
-    sample_scc_special_and_extended_characters,
     sample_scc_with_line_too_long
 )
 from tests.fixtures.srt import (  # noqa: F401

{pycaption-2.2.5 → pycaption-2.2.7}/tests/fixtures/dfxp.py

@@ -920,10 +920,10 @@ def sample_dfxp_from_scc_output():
    <region tts:displayAlign="before" tts:origin="40% 53%" tts:textAlign="left" xml:id="r5"/>
    <region tts:displayAlign="before" tts:origin="70% 17%" tts:textAlign="left" xml:id="r6"/>
    <region tts:displayAlign="before" tts:origin="20% 35%" tts:textAlign="left" xml:id="r7"/>
-   <region tts:displayAlign="before" tts:origin="25% 83%" tts:textAlign="left" xml:id="r8"/>
+   <region tts:displayAlign="before" tts:origin="20% 83%" tts:textAlign="left" xml:id="r8"/>
    <region tts:displayAlign="before" tts:origin="70% 11%" tts:textAlign="left" xml:id="r9"/>
    <region tts:displayAlign="before" tts:origin="40% 41%" tts:textAlign="left" xml:id="r10"/>
-   <region tts:displayAlign="before" tts:origin="25% 71%" tts:textAlign="left" xml:id="r11"/>
+   <region tts:displayAlign="before" tts:origin="20% 71%" tts:textAlign="left" xml:id="r11"/>
   </layout>
  </head>
  <body>

{pycaption-2.2.5 → pycaption-2.2.7}/tests/fixtures/scc.py

@@ -24,33 +24,6 @@ Scenarist_SCC V1.0
 """
 
 
-@pytest.fixture(scope="session")
-def sample_scc_with_consecutive_pac_commands():
-    return """\
-Scenarist_SCC V1.0
-
-00:00:00;15	942c
-
-00:11:45;10	9420 94d0 94ce 5b20 cec1 5252 c154 4f52 205d 9470 946e cd4f cecb 45d9 d320 4c4f d645 2054 c849 cec7 d320 54c8 c154 2046 4cd9 ae80 942c 8080 8080 942f
-
-00:11:47;28	9420 9454 9723 d9c1 d9a1 94f4 9723 5b20 c84f 4f54 49ce c720 5d80 942c 8080 8080 942f
-
-00:11:50;08	9420 94d0 94ce 45d3 d045 4349 c14c 4cd9 2049 4620 54c8 45d9 a752 4520 54c8 4520 4fce 45d3 9470 946e 57c8 4f20 c745 5420 544f 2046 4cd9 2054 c845 cdae 942c 8080 8080 942f
-
-00:11:54;06	942c
-
-00:23:00;13	9420 1370 136e 5b20 43c8 494c c420 5d80 94d0 94ce c745 4f52 c745 20cd c1c4 4520 c120 cdc1 43c8 49ce 4580 9470 946e 464f 5220 c84f 5749 4520 544f 942c 8080 8080 942f
-
-00:23:02;04	9420 91d0 91ce 544f 2046 49ce c420 43d5 5249 4fd5 d320 c745 4f52 c745 9170 916e c1ce c420 c849 d320 4652 4945 cec4 d380 92d0 92ce 45d6 4552 d920 c4c1 d920 4fce 4c49 ce45 2c80 942c 8080 8080 942f
-
-00:23:05;00	9420 9152 91ae d357 49ce c720 c2d9 20d0 c2d3 cb49 c4d3 ae4f 52c7 9170 916e 544f 20d0 4cc1 d920 46d5 ce20 c7c1 cd45 d320 c1ce c420 57c1 5443 c880 92d0 9723 91ae d94f d552 2046 c1d6 4f52 4954 4520 d649 c445 4fd3 ae80 942c 8080 8080 942f
-
-
-00:23:05;00	9420 9152 91ae d357 49ce c720 c2d9 20d0 c2d3 cb49 c4d3 ae4f 52c7 9170 916e 544f 20d0 4cc1 d920 46d5 ce20 c7c1 cd45 d320 c1ce c420 57c1 5443 c880 92d0 9723 91ae d94f d552 2046 c1d6 4f52 4954 4520 d649 c445 4fd3 ae80 942c 8080 8080 942f
-
-"""
-
-
 @pytest.fixture(scope="session")
 def scc_that_generates_webvtt_with_proper_newlines():
     return """\
@@ -462,7 +435,7 @@ Scenarist_SCC V1.0
 
 00:00:00;03	942c
 
-00:00:01;45	9420 91f4 cb45 4c4c d920 4ac1 cd45 d3ba 20c8 eff7 9254 f468 e520 7368 eff7d3ba 20c8 eff7 9254 f468 e520 7368 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 eff7 2073 f461 f2f4 e564 942c 8080 8080 942f
+00:00:01;45	9420 91f4 cb45 4c4c d920 4ac1 cd45 d3ba 20c8 eff7 9254 f468 e520 7368 eff7 2073 f461 f2f4 e564 942c 8080 8080 942f
 
 00:00:02;55	9420 91e0 9723 f761 7320 4361 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 ec20 c4e5 6ee9 73ef 6e2c 2061 20e6 f2e9 e56e 6480 9240 9723 efe6 20ef 75f2 732c 20f7 6173 2064 efe9 6e67 206d 7920 43c4 73ae 942c 8080 8080 942f
 

{pycaption-2.2.5 → pycaption-2.2.7}/tests/test_scc.py

@@ -77,10 +77,10 @@ class TestSCCReader(ReaderTestingMixIn):
             ((40.0, UnitEnum.PERCENT), (53.0, UnitEnum.PERCENT)),
             ((70.0, UnitEnum.PERCENT), (17.0, UnitEnum.PERCENT)),
             ((20.0, UnitEnum.PERCENT), (35.0, UnitEnum.PERCENT)),
-            ((25.0, UnitEnum.PERCENT), (83.0, UnitEnum.PERCENT)),
+            ((20.0, UnitEnum.PERCENT), (83.0, UnitEnum.PERCENT)),
             ((70.0, UnitEnum.PERCENT), (11.0, UnitEnum.PERCENT)),
             ((40.0, UnitEnum.PERCENT), (41.0, UnitEnum.PERCENT)),
-            ((25.0, UnitEnum.PERCENT), (71.0, UnitEnum.PERCENT))
+            ((20.0, UnitEnum.PERCENT), (71.0, UnitEnum.PERCENT))
         ]
 
         actual_positioning = [
@@ -206,10 +206,10 @@ class TestSCCReader(ReaderTestingMixIn):
 
     def test_skip_duplicate_tab_offset(self, sample_scc_duplicate_tab_offset):
         expected_lines = [
-            '[Radio reporter]',
-            'The I-10 Santa Monica Freeway',
+            '[Radio reporter] ',
+            'The I-10 Santa Monica Freeway ',
             'westbound is jammed,',
-            'due to a three-car accident',
+            'due to a three-car accident ',
             'blocking lanes 1 and 2',
         ]
 
@@ -244,46 +244,15 @@ class TestSCCReader(ReaderTestingMixIn):
         assert exc_info.value.args[0].startswith(
             "Unsupported cue duration around 00:00:20.433")
 
-    def test_skip_first_pac_command(self, sample_scc_with_consecutive_pac_commands):
-        caption_set = SCCReader().read(sample_scc_with_consecutive_pac_commands)
-        caption = caption_set.get_captions('en-US')
-        actual_lines = [
-            node.content
-            for cap_ in caption
-            for node in cap_.nodes
-            if node.type_ == CaptionNode.TEXT
-        ]
-        expected_lines = [
-            '[ NARRATOR ]',
-             'MONKEYS LOVE THINGS THAT FLY.',
-             'YAY!',
-             '[ HOOTING ]',
-             "ESPECIALLY IF THEY'RE THE ONES",
-             'WHO GET TO FLY THEM.',
-             '[ CHILD ]',
-             'GEORGE MADE A MACHINE',
-             'FOR HOWIE TO',
-             'TO FIND CURIOUS GEORGE',
-             'AND HIS FRIENDS',
-             'EVERY DAY ONLINE,',
-             'SWING BY PBSKIDS.ORG',
-             'TO PLAY FUN GAMES AND WATCH',
-             'YOUR FAVORITE VIDEOS.',
-             'SWING BY PBSKIDS.ORG',
-             'TO PLAY FUN GAMES AND WATCH',
-             'YOUR FAVORITE VIDEOS.'
-        ]
-        # is not breaking the lines
-        assert expected_lines == actual_lines
-
     def test_line_too_long(self, sample_scc_with_line_too_long):
         with pytest.raises(CaptionLineLengthError) as exc_info:
             SCCReader().read(sample_scc_with_line_too_long)
 
         assert exc_info.value.args[0].startswith(
             "32 character limit for caption cue in scc file.")
-        assert ("was Cal l l l l l l l l l l l l l l l l l l l l l l l l l l l l Denison, a friend - Length 81"
-                in exc_info.value.args[0].split("\n"))
+        str_to_check = ("around 00:00:05.900 - was Cal l l l l l l l l l l l l l l l l l l l l l l l l l l l l "
+                        "Denison, a friend - Length 81")
+        assert str_to_check in exc_info.value.args[0].split("\n")
 
 
 class TestCoverageOnly:
@@ -377,6 +346,7 @@ class TestCoverageOnly:
         ]
 
         actual_timings = [(c_.start, c_.end) for c_ in captions]
+
         assert expected_timings == actual_timings
 
     def test_freeze_colon_spec_time(self, sample_scc_pop_on):
@@ -615,4 +585,4 @@ class TestTimingCorrectingCaptionList:
         # just one caption, first EOC disappears
         num_captions = len(caption_set.get_captions('en-US'))
 
-        assert num_captions == 1
+        assert num_captions == 2