documentation

README.md

@@ -14,6 +14,8 @@ The `pycmx` package parses a CMX 3600 EDL and its most most common variations.
   read. Event number field and source name field sizes are determined
   dynamically for each statement for a high level of compliance at the expense
   of strictness.
+* An more relaxed "tolerant" mode allows parsing of an EDL file where columns
+  use non-standard widths.
 * Preserves relationship between events and individual edits/clips.
 * Remark or comment fields with common recognized forms are read and 
   available to the client, including clip name and source file data.

docs/source/index.rst

@@ -1,7 +1,7 @@
 .. pycmx documentation master file, created by
    sphinx-quickstart on Wed Dec 26 21:51:43 2018.
    You can adapt this file completely to your liking, but it should at least
-contain the root `toctree` directive.
+   contain the root `toctree` directive.
 
 pycmx -  A CMX EDL Parser in Python
 ====================================
@@ -16,6 +16,8 @@ The `pycmx` package parses a CMX 3600 EDL and its most most common variations.
   read. Event number field and source name field sizes are determined
   dynamically for each statement for a high level of compliance at the expense
   of strictness.
+* An more relaxed "tolerant" mode allows parsing of an EDL file where columns
+  use non-standard widths.
 * Preserves relationship between events and individual edits/clips.
 * Remark or comment fields with common recognized forms are read and 
   available to the client, including clip name and source file data.

pycmx/edit_list.py

@@ -15,7 +15,7 @@ class EditList:
     :func:`~pycmx.parse_cmx3600()`.
     """
 
-    def __init__(self, statements):
+    def __init__(self, statements: list):
         self.title_statement: StmtTitle = statements[0]
         self.event_statements = statements[1:]
 

pycmx/event.py

@@ -70,7 +70,6 @@ class Event:
             the_zip.append(trans_names)
         except IndexError:
             the_zip.append([None] * len(edits_audio))
-
         return [Edit(edit_statement=e1[0],
                      audio_ext_statement=e1[1],
                      clip_name_statement=n1,
@@ -105,11 +104,16 @@ class Event:
 
     def _statements_with_audio_ext(self) -> Generator[
             Tuple[StmtEvent, Optional[StmtAudioExt]], None, None]:
-        for (s1, s2) in zip(self.statements, self.statements[1:]):
-            if type(s1) is StmtEvent and type(s2) is StmtAudioExt:
-                yield (s1, s2)
-            elif type(s1) is StmtEvent:
-                yield (s1, None)
+
+        if len(self.statements) == 1 and type(self.statements[0]) is StmtEvent:
+            yield (self.statements[0], None)
+
+        else:
+            for (s1, s2) in zip(self.statements, self.statements[1:]):
+                if type(s1) is StmtEvent and type(s2) is StmtAudioExt:
+                    yield (s1, s2)
+                elif type(s1) is StmtEvent:
+                    yield (s1, None)
 
     def _asc_sop_statement(self) -> Optional[StmtCdlSop]:
         return next((s for s in self.statements if type(s) is StmtCdlSop),

pycmx/parse_cmx_events.py

@@ -7,12 +7,14 @@ from .parse_cmx_statements import (parse_cmx3600_statements)
 from .edit_list import EditList
 
 
-def parse_cmx3600(f: TextIO) -> EditList:
+def parse_cmx3600(f: TextIO, tolerant: bool = False) -> EditList:
     """
     Parse a CMX 3600 EDL.
 
     :param TextIO f: a file-like object, an opened CMX 3600 .EDL file.
+    :param bool tolerant: If `True`, a relaxed event line parsing method will
+        be used, in the case the default method fails.
     :returns: An :class:`pycmx.edit_list.EditList`.
     """
-    statements = parse_cmx3600_statements(f)
+    statements = parse_cmx3600_statements(f, tolerant)
     return EditList(statements)

pycmx/parse_cmx_statements.py

@@ -13,12 +13,13 @@ from .statements import (StmtCdlSat, StmtCdlSop, StmtCorruptRemark, StmtFrmc,
 from .util import collimate
 
 
-def parse_cmx3600_statements(file: TextIO) -> List[object]:
+def parse_cmx3600_statements(file: TextIO,
+                             tolerant: bool = False) -> List[object]:
     """
     Return a list of every statement in the file argument.
     """
     lines = file.readlines()
-    return [_parse_cmx3600_line(line.strip(), line_number)
+    return [_parse_cmx3600_line(line.strip(), line_number, tolerant)
             for (line_number, line) in enumerate(lines)]
 
 
@@ -38,7 +39,8 @@ def _edl_column_widths(event_field_length, source_field_length) -> List[int]:
 #             8,8,1,4,2,1,4,13,3,1,1]
 
 
-def _parse_cmx3600_line(line: str, line_number: int) -> object:
+def _parse_cmx3600_line(line: str, line_number: int,
+                        tolerant: bool = False) -> object:
     """
     Parses a single CMX EDL line.
 
@@ -54,9 +56,20 @@ def _parse_cmx3600_line(line: str, line_number: int) -> object:
         return _parse_fcm(line, line_number)
     if line_matcher is not None:
         event_field_len = len(line_matcher.group(1))
+
         source_field_len = len(line) - (event_field_len + 65)
-        return _parse_columns_for_standard_form(line, event_field_len,
-                                                source_field_len, line_number)
+
+        try:
+            return _parse_columns_for_standard_form(line, event_field_len,
+                                                    source_field_len,
+                                                    line_number)
+
+        except EventFormError:
+            if tolerant:
+                return _parse_columns_tolerant(line, line_number)
+            else:
+                return StmtUnrecognized(line, line_number)
+
     if line.startswith("AUD"):
         return _parse_extended_audio_channels(line, line_number)
     if line.startswith("*"):
@@ -186,6 +199,10 @@ def _parse_split(line: str, line_number):
 #     return StmtMotionMemory(source="", fps="")
 #
 
+class EventFormError(RuntimeError):
+    pass
+
+
 def _parse_unrecognized(line, line_number):
     return StmtUnrecognized(content=line, line_number=line_number)
 
@@ -193,17 +210,24 @@ def _parse_unrecognized(line, line_number):
 def _parse_columns_for_standard_form(line: str, event_field_length: int,
                                      source_field_length: int,
                                      line_number: int):
+    # breakpoint()
     col_widths = _edl_column_widths(event_field_length, source_field_length)
 
     if sum(col_widths) > len(line):
-        return StmtUnrecognized(content=line, line_number=line_number)
+        raise EventFormError()
 
     column_strings = collimate(line, col_widths)
 
+    channels = column_strings[4].strip()
+    trans = column_strings[6].strip()
+
+    if len(channels) == 0 or len(trans) == 0:
+        raise EventFormError()
+
     return StmtEvent(event=column_strings[0],
                      source=column_strings[2].strip(),
-                     channels=column_strings[4].strip(),
-                     trans=column_strings[6].strip(),
+                     channels=channels,
+                     trans=trans,
                      trans_op=column_strings[8].strip(),
                      source_in=column_strings[10].strip(),
                      source_out=column_strings[12].strip(),
@@ -213,6 +237,26 @@ def _parse_columns_for_standard_form(line: str, event_field_length: int,
                      source_field_size=source_field_length)
 
 
+def _parse_columns_tolerant(line: str, line_number: int):
+    pattern = re.compile(r'^\s*(\d+)\s+(.{8,128}?)\s+'
+                         r'(V|A|A2|AA|NONE|AA/V|A2/V|B)\s+'
+                         r'(C|D|W|KB|K|KO)\s+(\d*)\s+(\d\d.\d\d.\d\d.\d\d)\s'
+                         r'(\d\d.\d\d.\d\d.\d\d)\s(\d\d.\d\d.\d\d.\d\d)\s'
+                         r'(\d\d.\d\d.\d\d.\d\d)'
+                         )
+
+    match = pattern.match(line)
+    if match:
+        return StmtEvent(event=int(match.group(1)), source=match.group(2),
+                         channels=match.group(3), trans=match.group(4),
+                         trans_op=match.group(5), source_in=match.group(6),
+                         source_out=match.group(7), record_in=match.group(8),
+                         record_out=match.group(9), line_number=line_number,
+                         source_field_size=len(match.group(2)))
+    else:
+        return StmtUnrecognized(line, line_number)
+
+
 def _parse_source_umid_statement(line, line_number):
     # trimmed = line[3:].strip()
     # return StmtSourceUMID(name=None, umid=None, line_number=line_number)

tests/__init__.py

@@ -1 +1,2 @@
 from . import test_parse
+from . import test_issue_19

tests/edls/ISSUE_19_unusual01.edl

@@ -0,0 +1,39 @@
+TITLE: Final Master Generated by LTedlMixer...
+0001  Z125C001_220217_ROLX    V     C         15:51:58:10 15:52:02:16 00:00:00:00 00:00:04:06
+0002  B505C014_230224_RNBP    V     C         20:19:58:21 20:20:00:21 00:00:04:06 00:00:06:06
+0003  B505C014_230224_RNBP    V     C         20:19:59:21 20:20:01:22 00:00:06:06 00:00:08:07
+0004  B505C014_230224_RNBP    V     C         20:20:01:23 20:20:02:01 00:00:08:07 00:00:08:09
+0005  B505C014_230224_RNBP    V     C         20:20:02:01 20:20:06:10 00:00:08:09 00:00:12:18
+0006  B505C011_230224_RNBP    V     C         19:44:21:04 19:44:27:08 00:00:12:18 00:00:18:22
+0007  B505C016_230224_RNBP    V     C         20:24:54:14 20:24:58:19 00:00:18:22 00:00:23:03
+0008  Y022C029_211201_YNJI    V     C         12:42:37:04 12:42:39:14 00:00:23:03 00:00:25:13
+0009  A054C025_211022_R24B    V     C         12:30:50:11 12:30:54:16 00:00:25:13 00:00:29:18
+0010  Z040C026_211206_ROLX    V     C         14:42:25:21 14:42:28:17 00:00:29:18 00:00:32:14
+0011  J001_C002_20211007_R    V     C         12:38:48:18 12:38:51:13 00:00:32:14 00:00:35:09
+0012  C006C005_211007_RO2A    V     C         11:49:08:02 11:49:15:13 00:00:35:09 00:00:42:20
+0013  A021C020_211007_R24B    V     C         18:14:52:00 18:14:58:22 00:00:42:20 00:00:49:18
+0014  A023C013_211008_R24B    V     C         11:12:57:23 11:12:59:18 00:00:49:18 00:00:51:13
+0015  U001C010_211029_R268    V     C         04:38:42:21 04:38:49:21 00:00:51:13 00:00:58:13
+0016  A021C009_211007_R24B    V     C         17:06:12:10 17:06:19:14 00:00:58:13 00:01:05:17
+0017  A055C008_211022_R24B    V     C         15:16:03:10 15:16:05:09 00:01:05:17 00:01:07:16
+0018  A055C008_211022_R24B    V     C         15:16:05:09 15:16:12:20 00:01:07:16 00:01:15:03
+0019  A055C008_211022_R24B    V     C         15:16:12:20 15:16:14:19 00:01:15:03 00:01:17:02
+0020  A056C011_211022_R24B    V     C         17:40:13:01 17:40:16:04 00:01:17:02 00:01:20:05
+0021  A024C011_211008_R24B    V     C         17:32:07:02 17:32:10:01 00:01:20:05 00:01:23:04
+0022  B070C001_211203_RP40    V     C         17:39:20:20 17:39:22:14 00:01:23:04 00:01:24:22
+0023  A055C019_211022_R24B    V     C         16:31:05:06 16:31:12:10 00:01:24:22 00:01:32:02
+0024  A248C012_220224_R1Y2    V     C         16:01:35:08 16:01:40:04 00:01:32:02 00:01:36:22
+0025  A127C005_211206_R24B    V     C         10:58:23:06 10:58:24:09 00:01:36:22 00:01:38:01
+0026  A040C006_211015_R24B    V     C         13:00:09:04 13:00:23:17 00:01:38:01 00:01:52:14
+0027  A041C006_211015_R24B    V     C         16:10:32:08 16:10:35:12 00:01:52:14 00:01:55:18
+0028  A040C006_211015_R24B    V     C         13:00:34:13 13:00:37:03 00:01:55:18 00:01:58:08
+0029  A041C005_211015_R24B    V     C         15:57:22:05 15:57:27:11 00:01:58:08 00:02:03:14
+0030  A040C008_211015_R24B    V     C         13:09:51:18 13:09:55:07 00:02:03:14 00:02:07:03
+0031  A040C016_211015_R24B    V     C         14:09:15:11 14:09:20:02 00:02:07:03 00:02:11:18
+0032  Z089C007_220122_ROLX    V     C         17:03:34:23 17:03:59:15 00:02:11:18 00:02:36:10
+0033  A507C008_230227_RNHZ    V     C         09:55:35:10 09:55:41:02 00:02:36:10 00:02:42:02
+0034  B049C021_211111_RP40    V     C         17:38:55:11 17:38:56:17 00:02:42:02 00:02:43:08
+0035  Z036C012_211202_ROLX    V     C         17:30:23:12 17:30:25:05 00:02:43:08 00:02:45:01
+0036  A157C023_220112_R24B    V     C         14:13:18:04 14:13:20:06 00:02:45:01 00:02:47:03
+0037  A095C014_211110_R24B    V     C         19:34:35:16 19:34:37:10 00:02:47:03 00:02:48:21
+0038  Z089C010_220122_ROLX    V     C         17:28:55:21 17:28:58:09 00:02:48:21 00:02:51:09

tests/test_issue_19.py

@@ -0,0 +1,25 @@
+from unittest import TestCase
+
+from pycmx import parse_cmx3600
+
+
+class Issue19Test(TestCase):
+    def setUp(self):
+        self.f = open("tests/edls/ISSUE_19_unusual01.edl")
+
+    def test_parse(self):
+        edl = parse_cmx3600(self.f, tolerant=True)
+        for event in edl.events:
+            self.assertIsNotNone(event.edits)
+            if event.number == 1:
+                self.assertEqual(len(event.edits), 1)
+                self.assertEqual(event.edits[0].source, "Z125C001_220217_ROLX")
+                self.assertEqual(event.edits[0].channels.v, True)
+                self.assertEqual(event.edits[0].transition.kind, "C")
+                self.assertEqual(event.edits[0].transition.operand, "")
+                self.assertEqual(event.edits[0].source_in, "15:51:58:10")
+                self.assertEqual(event.edits[0].record_out, "00:00:04:06")
+                break
+
+    def tearDown(self):
+        self.f.close()