Update pythonpublish.yml

Added note on command-line entry point

.github/workflows/pythonpublish.yml

@@ -0,0 +1,26 @@
+name: Upload Python Package
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v1
+    - name: Set up Python
+      uses: actions/setup-python@v1
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools wheel twine lxml
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+      run: |
+        python setup.py sdist bdist_wheel
+        twine upload dist/*

.gitignore

@@ -105,3 +105,4 @@ venv.bak/
 
 # vim swap
 *.swp
+.DS_Store

.idea/.gitignore

@@ -0,0 +1,3 @@
+
+# Default ignored files
+/workspace.xml

.idea/dictionaries/jamiehardt.xml

@@ -0,0 +1,8 @@
+<component name="ProjectDictionaryState">
+  <dictionary name="jamiehardt">
+    <words>
+      <w>ident</w>
+      <w>umid</w>
+    </words>
+  </dictionary>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/wavinfo.iml" filepath="$PROJECT_DIR$/.idea/wavinfo.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

.idea/wavinfo.iml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.7" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="TestRunnerService">
+    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
+  </component>
+</module>

.travis.yml

@@ -5,19 +5,22 @@ python:
     - "3.6"
     - "3.5"
     - "3.7"
+    - "3.8"
 script:
     - "gunzip tests/test_files/rf64/*.gz"
     - "python setup.py test"
-#    - "py.test tests/ -v --cov wavinfo --cov-report term-missing"
+#    - "python -m pytest tests/ -v --cov wavinfo --cov-report term-missing"
 before_install:
     - "sudo apt-get update"
     - "sudo add-apt-repository universe"
     - "sudo apt-get install -y ffmpeg"
-    - "pip install coverage"
+    - "pip install pytest"
-    - "pip install codecov"
+    - "pip install lxml"
-    - "pip install pytest-cov==2.5.0"
+#     - "pip install coverage"
-#    - "pip install coverage==4.4"
+#     - "pip install codecov"
+#     - "pip install pytest-cov==2.5.0"
+#     - "pip install coverage==4.4"
 install:
     - "pip install setuptools"
-after_success:
+# after_success:
-    - "codecov"
+#     - "codecov"

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2018 Jamie Hardt
+Copyright (c) 2020 Jamie Hardt
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -1,5 +1,4 @@
 [![Build Status](https://travis-ci.com/iluvcapra/wavinfo.svg?branch=master)](https://travis-ci.com/iluvcapra/wavinfo)
-[![codecov](https://codecov.io/gh/iluvcapra/wavinfo/branch/master/graph/badge.svg)](https://codecov.io/gh/iluvcapra/wavinfo)
 [![Documentation Status](https://readthedocs.org/projects/wavinfo/badge/?version=latest)](https://wavinfo.readthedocs.io/en/latest/?badge=latest) ![](https://img.shields.io/github/license/iluvcapra/wavinfo.svg) ![](https://img.shields.io/pypi/pyversions/wavinfo.svg) [![](https://img.shields.io/pypi/v/wavinfo.svg)](https://pypi.org/project/wavinfo/) ![](https://img.shields.io/pypi/wheel/wavinfo.svg)
 
 
@@ -42,6 +41,12 @@ path = '../tests/test_files/A101_1.WAV'
 info = WavInfoReader(path)
 ```
 
+The package also installs a shell command:
+
+```sh
+$ wavinfo test_files/A101_1.WAV
+```
+
 ### Basic WAV Data
 
 The length of the file in frames (interleaved samples) and bytes is available, as is the contents of the format chunk.
@@ -53,6 +58,10 @@ The length of the file in frames (interleaved samples) and bytes is available, a
 >>> (48000, 2, 6, 24)
 ```
 
+## Other Resources
+
+* For other file formats and ID3 decoding, look at [audio-metadata](https://github.com/thebigmunch/audio-metadata).
+
 
 
 

pypi_upload.sh

@@ -1,2 +0,0 @@
-#!/bin/bash
-python3 -m twine upload --repository-url https://upload.pypi.org/legacy/ dist/*

setup.py

@@ -1,23 +1,40 @@
 from setuptools import setup
+from wavinfo import __author__, __license__, __version__
 
 with open("README.md", "r") as fh:
     long_description = fh.read()
 
 setup(name='wavinfo',
-      version='1.2',
+      version=__version__,
-      author='Jamie Hardt',
+      author=__author__,
       author_email='jamiehardt@me.com',
       description='Probe WAVE Files for iXML, Broadcast-WAVE and other metadata.',
       long_description_content_type="text/markdown",
       long_description=long_description,
+      license=__license__,
       url='https://github.com/iluvcapra/wavinfo',
+      project_urls={
+          'Source':
+              'https://github.com/iluvcapra/wavinfo',
+          'Documentation':
+              'https://wavinfo.readthedocs.io/',
+          'Issues':
+              'https://github.com/iluvcapra/wavinfo/issues',
+      },
+      packages=['wavinfo'],
       classifiers=['Development Status :: 5 - Production/Stable',
           'License :: OSI Approved :: MIT License',
           'Topic :: Multimedia',
-	  'Topic :: Multimedia :: Sound/Audio',
+          'Topic :: Multimedia :: Sound/Audio',
           "Programming Language :: Python :: 3.5",
           "Programming Language :: Python :: 3.6",
-          "Programming Language :: Python :: 3.7"],
+          "Programming Language :: Python :: 3.7",
-      packages=['wavinfo'],
+          "Programming Language :: Python :: 3.8"],
-      install_requires=['lxml']
+      keywords='waveform metadata audio ebu smpte avi library film tv editing editorial',
+      install_requires=['lxml'],
+      entry_points={
+          'console_scripts': [
+              'wavinfo = wavinfo.__main__:main'
+          ]
+      }
       )

tests/test_wave_parsing.py

@@ -87,3 +87,10 @@ class TestWaveInfo(TestCase):
                 self.assertEqual( e['take'], info.ixml.take )
                 self.assertEqual( e['tape'], info.ixml.tape )
                 self.assertEqual( e['family_uid'], info.ixml.family_uid )
+
+                for track in info.ixml.track_list:
+                    self.assertIsNotNone(track.channel_index)
+                    if basename == 'A101_4.WAV' and track.channel_index == '1':
+                        self.assertTrue(track.name == 'MKH516 A')
+
+

wavinfo/__init__.py

@@ -1,14 +1,12 @@
-# -*- coding: utf-8 -*-
+"""
-
+methods to probe a WAV file for various kinds of production metadata.
-# :module:`wavinfo` provides methods to probe a WAV file for
-# various kinds of production metadata.
-#
-#
-#
-#
 
+Go to the documentation for wavinfo.WavInfoReader for more information.
+"""
 
 from .wave_reader import WavInfoReader
+from .riff_parser import WavInfoEOFError
 
-__version__ = '1.1'
+__version__ = '1.5'
-__author__ = 'Jamie Hardt'
+__author__ = 'Jamie Hardt <jamiehardt@gmail.com>'
+__license__ = "MIT"

wavinfo/__main__.py

@@ -0,0 +1,32 @@
+from optparse import OptionParser, OptionGroup
+import datetime
+from . import WavInfoReader
+import sys
+import json
+
+def main():
+    parser = OptionParser()
+
+    parser.usage = 'wavinfo [FILE.wav]*'
+
+    # parser.add_option('-f', dest='output_format', help='Set the output format',
+    #                   default='json',
+    #                   metavar='FORMAT')
+
+    (options, args) = parser.parse_args(sys.argv)
+    for arg in args[1:]:
+        try:
+            this_file = WavInfoReader(path=arg)
+            ret_dict = {'file_argument': arg, 'run_date': datetime.datetime.now().isoformat() , 'scopes': {}}
+            for scope, name, value in this_file.walk():
+                if scope not in ret_dict['scopes'].keys():
+                    ret_dict['scopes'][scope] = {}
+
+                ret_dict['scopes'][scope][name] = value
+
+            json.dump(ret_dict, fp=sys.stdout, indent=2)
+        except Exception as e:
+            print(e)
+
+if __name__ == "__main__":
+    main()

wavinfo/riff_parser.py

@@ -1,70 +1,72 @@
 
 import struct
-import pdb
 from collections import namedtuple
 from .rf64_parser import parse_rf64
 
-class ListChunkDescriptor(namedtuple('ListChunkDescriptor' , 'signature children')):
 
-    def find(chunk_path):
+class WavInfoEOFError(EOFError):
+    def __init__(self, identifier, chunk_start):
+        self.identifier = identifier
+        self.chunk_start = chunk_start
+
+
+class ListChunkDescriptor(namedtuple('ListChunkDescriptor', 'signature children')):
+    def find(self, chunk_path):
         if len(chunk_path) > 1:
             for chunk in self.children:
                 if type(chunk) is ListChunkDescriptor and \
                         chunk.signature is chunk_path[0]:
-                            return chunk.find(chunk_path[1:])
+                    return chunk.find(chunk_path[1:])
         else:
             for chunk in self.children:
                 if type(chunk) is ChunkDescriptor and \
                         chunk.ident is chunk_path[0]:
-                            return chunk
+                    return chunk
 
 
-class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length rf64_context') ):
+class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length rf64_context')):
     def read_data(self, from_stream):
         from_stream.seek(self.start)
         return from_stream.read(self.length)
 
-def parse_list_chunk(stream, length, rf64_context =None):
-    start = stream.tell()
 
+def parse_list_chunk(stream, length, rf64_context=None):
+    start = stream.tell()
     signature = stream.read(4)
 
-    #print("Parsing list chunk with siganture: ", signature)
     children = []
-    while (stream.tell() - start) < length:
+    while (stream.tell() - start + 8) < length:
-        child_chunk = parse_chunk(stream, rf64_context= rf64_context)
+        child_chunk = parse_chunk(stream, rf64_context=rf64_context)
-        if child_chunk:
+        children.append(child_chunk)
-             children.append(child_chunk)
+
-        else: 
+    stream.seek(start + length)
-             break
 
     return ListChunkDescriptor(signature=signature, children=children)
 
-def parse_chunk(stream, rf64_context=None):
-    ident = stream.read(4)
-    if len(ident) != 4:
-        return
 
-    sizeb = stream.read(4)
+def parse_chunk(stream, rf64_context=None):
-    size  = struct.unpack('<I',sizeb)[0]
+    header_start = stream.tell()
-    
+    ident = stream.read(4)
-    if size == 0xFFFFFFFF:
+    size_bytes = stream.read(4)
+
+    if len(ident) != 4 or len(size_bytes) != 4:
+        raise WavInfoEOFError(identifier=ident, chunk_start=header_start)
+
+    data_size = struct.unpack('<I', size_bytes)[0]
+
+    if data_size == 0xFFFFFFFF:
         if rf64_context is None and ident == b'RF64':
             rf64_context = parse_rf64(stream=stream)
         
-        size = rf64_context.bigchunk_table[ident] 
+        data_size = rf64_context.bigchunk_table[ident]
             
-    displacement = size
+    displacement = data_size
     if displacement % 2 is not 0:
         displacement = displacement + 1
 
-    if ident in [b'RIFF',b'LIST', b'RF64']:
+    if ident in [b'RIFF', b'LIST', b'RF64']:
-        #print("Parsing list chunk with ident: ", ident)
+        return parse_list_chunk(stream=stream, length=data_size, rf64_context=rf64_context)
-        return parse_list_chunk(stream=stream, length=size, rf64_context=rf64_context)
     else:
-        start = stream.tell()
+        data_start = stream.tell()
-        stream.seek(displacement,1)
+        stream.seek(displacement, 1)
-        #print("Parsing chunk with start=%i, ident=%s" % (start, ident))
+        return ChunkDescriptor(ident=ident, start=data_start, length=data_size, rf64_context=rf64_context)
-        return ChunkDescriptor(ident=ident, start=start, length=size, rf64_context=rf64_context)
-
-

wavinfo/umid_parser.py

@@ -0,0 +1,129 @@
+import struct
+from typing import Union
+
+class UMIDParser:
+    """
+    Parse a raw binary SMPTE 330M Universal Materials Identifier
+
+    This implementation is based on SMPTE ST 330:2011
+    """
+    def __init__(self, raw_umid: bytearray):
+        self.raw_umid = raw_umid
+
+    @classmethod
+    def binary_to_string(cls, binary_value):
+        result_str = ''
+        for n in range(len(binary_value)):
+            result_str = f'{binary_value[n]:x}' + result_str
+
+        return result_str
+
+    @property
+    def universal_label(self) -> bytearray:
+        return self.raw_umid[0:12]
+
+    @property
+    def basic_umid(self):
+        return self.raw_umid[0:32]
+
+    def basic_umid_to_str(self):
+        return "%024x-%06x-%032x" % (self.binary_to_string(self.universal_label),
+                                     self.binary_to_string(self.instance_number),
+                                     self.binary_to_string(self.material_number))
+
+    @property
+    def universal_label_is_valid(self) -> bool:
+        valid_preamble = b'\x06\x0a\x2b\x34\x01\x01\x01\x05\x01\x01'
+        return self.universal_label[0:len(valid_preamble)] == valid_preamble
+
+    @property
+    def material_type(self) -> str:
+        material_byte = self.raw_umid[10]
+        if material_byte == 0x1:
+            return 'picture'
+        elif material_byte == 0x2:
+            return 'audio'
+        elif material_byte == 0x3:
+            return 'data'
+        elif material_byte == 0x4:
+            return 'other'
+        elif material_byte == 0x5:
+            return 'picture_single_component'
+        elif material_byte == 0x6:
+            return 'picture_multiple_component'
+        elif material_byte == 0x7:
+            return 'audio_single_component'
+        elif material_byte == 0x9:
+            return 'audio_multiple_component'
+        elif material_byte == 0xb:
+            return 'auxiliary_single_component'
+        elif material_byte == 0xc:
+            return 'auxiliary_multiple_component'
+        elif material_byte == 0xd:
+            return 'mixed_components'
+        elif material_byte == 0xf:
+            return 'not_identified'
+        else:
+            return 'not_recognized'
+
+    @property
+    def material_number_creation_method(self) -> str:
+        method_byte = self.raw_umid[11]
+        method_byte = (method_byte << 4) & 0xf
+        if method_byte == 0x0:
+            return 'undefined'
+        elif method_byte == 0x1:
+            return 'smpte'
+        elif method_byte == 0x2:
+            return 'uuid'
+        elif method_byte == 0x3:
+            return 'masked'
+        elif method_byte == 0x4:
+            return 'ieee1394'
+        elif 0x5 <= method_byte <= 0x7:
+            return 'reserved_undefined'
+        else:
+            return 'unrecognized'
+
+    @property
+    def instance_number_creation_method(self) -> str:
+        method_byte = self.raw_umid[11]
+        method_byte = method_byte & 0xf
+        if method_byte == 0x0:
+            return 'undefined'
+        elif method_byte == 0x01:
+            return 'local_registration'
+        elif method_byte == 0x02:
+            return '24_bit_prs'
+        elif method_byte == 0x03:
+            return 'copy_number_and_16_bit_prs'
+        elif 0x04 <= method_byte <= 0x0e:
+            return 'reserved_undefined'
+        elif method_byte == 0x0f:
+            return 'live_stream'
+        else:
+            return 'unrecognized'
+
+    @property
+    def indicated_length(self) -> str:
+        if self.raw_umid[12] == 0x13:
+            return 'basic'
+        elif self.raw_umid[12] == 0x33:
+            return 'extended'
+
+    @property
+    def instance_number(self) -> bytearray:
+        return self.raw_umid[13:3]
+
+    @property
+    def material_number(self) -> bytearray:
+        return self.raw_umid[16:16]
+
+    @property
+    def source_pack(self) -> Union[bytearray, None]:
+        if self.indicated_length == 'extended':
+            return self.raw_umid[32:32]
+        else:
+            return None
+
+

wavinfo/wave_ixml_reader.py

@@ -1,6 +1,10 @@
 #import xml.etree.ElementTree as ET
 from lxml import etree as ET
 import io
+from collections import namedtuple
+
+
+IXMLTrack = namedtuple('IXMLTrack', ['channel_index', 'interleave_index', 'name', 'function'])
 
 class WavIXMLFormat:
     """
@@ -27,6 +31,26 @@ class WavIXMLFormat:
         if e is not None:
             return e.text
 
+    @property
+    def raw_xml(self):
+        """
+        The root entity of the iXML document.
+        """
+        return self.parsed
+
+    @property
+    def track_list(self):
+        """
+        A description of each track.
+        :return: An Iterator
+        """
+        for track in self.parsed.find("./TRACK_LIST").iter():
+            if track.tag == 'TRACK':
+                yield IXMLTrack(channel_index=track.xpath('string(CHANNEL_INDEX/text())'),
+                                interleave_index=track.xpath('string(INTERLEAVE_INDEX/text())'),
+                                name=track.xpath('string(NAME/text())'),
+                                function=track.xpath('string(FUNCTION/text())'))
+
     @property
     def project(self):
         """

wavinfo/wave_reader.py

@@ -147,9 +147,13 @@ class WavInfoReader():
         metadata field, and the value.
         """
 
-        scopes = ('fmt','data')#,'bext','ixml','info')
+        scopes = ('fmt', 'data') #'bext', 'ixml', 'info')
 
         for scope in scopes:
             attr = self.__getattribute__(scope)
             for field in attr._fields:
                 yield scope, field, attr.__getattribute__(field)
+
+            bext_dict = self.bext.to_dict()
+            for key in bext_dict.keys():
+                yield 'bext', key, bext_dict[key]