Update setup.py

Added 3.9

.coveragerc

@@ -0,0 +1,13 @@
+[run]
+branch = True
+source = wavinfo 
+
+[report]
+exclude_lines =
+    if self.debug:
+    pragma: no cover
+    raise NotImplementedError
+    if __name__ == .__main__.:
+ignore_errors = True
+omit =
+    tests/*

.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 +1,9 @@
+<component name="ProjectDictionaryState">
+  <dictionary name="jamiehardt">
+    <words>
+      <w>bext</w>
+      <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 3.8 (wavinfo)" 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 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.8" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.travis.yml

@@ -1,20 +1,27 @@
 dist: xenial
 language: python
 python:
+#    - "2.7"
+#    - "3.5"
     - "3.6"
-    - "3.5"
+    - "3.7"
+    - "3.8"
+    - "3.9"
 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 pytest"
+    - "pip install lxml"
     - "pip install coverage"
-#    - "pip install coverage==4.4"
+    - "pip install codecov"
     - "pip install pytest-cov==2.5.0"
-    - "pip install python-coveralls"
+    - "pip install coverage==4.4"
 install:
     - "pip install setuptools"
 after_success:
-    - coveralls
+    - "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

@@ -1,34 +1,35 @@
 [![Build Status](https://travis-ci.com/iluvcapra/wavinfo.svg?branch=master)](https://travis-ci.com/iluvcapra/wavinfo)
-[![Coverage Status](https://coveralls.io/repos/github/iluvcapra/wavinfo/badge.svg?branch=master)](https://coveralls.io/github/iluvcapra/wavinfo?branch=master)
+[![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)
 
+<!-- ![Test](https://github.com/iluvcapra/wavinfo/workflows/Upload%20Python%20Package/badge.svg) -->
 
 # wavinfo
 
-
-The `wavinfo` package allows you to probe WAVE files and extract extended metadata, with an emphasis on 
-production metadata. 
+The `wavinfo` package allows you to probe WAVE and [RF64/WAVE files][eburf64] and extract extended metadata, with an emphasis on film, video and professional music production metadata.
 
 `wavinfo` reads:
 
-* __Broadcast-WAVE__ metadata, compliant with [EBU Tech 3285v2 (2011)][ebu], including embedded program 
-  loudness and coding history, if extant. This also includes the [SMPTE 330M __UMID__][smpte_330m2011] 
-  Unique Materials Identifier.
-* [__iXML__ production recorder metadata][ixml], including project, scene, and take tags, recorder notes 
+* __Broadcast-WAVE__ metadata<sup>[1][ebu]</sup>, including embedded program
+  loudness and coding history, if extant. This also includes the SMPTE UMID<sup>[2][smpte_330m2011]</sup>.
+* __iXML__ production recorder metadata<sup>[3][ixml]</sup>, including project, scene, and take tags, recorder notes
   and file family information.
-* Most of the common __RIFF INFO__ metadata fields.
-* The __wav format__ is also parsed, so you can access the basic sample rate and channel count 
+* Most of the common __RIFF INFO__<sup>[4][info-tags]</sup> metadata fields.
+* The __wav format__ is also parsed, so you can access the basic sample rate and channel count
   information.
 
 In progress:
+* ADM metadata consilient with the output of the __Dolby RMU__, perhaps later fully complaint with [ITU BS.2076-2][adm].
 * iXML `STEINBERG` sound library attributes.
+* __NetMix__ library attributes.
 * Pro Tools __embedded regions__.
 
 [ebu]:https://tech.ebu.ch/docs/tech/tech3285.pdf
+[adm]:https://www.itu.int/dms_pubrec/itu-r/rec/bs/R-REC-BS.2076-2-201910-I!!PDF-E.pdf
 [smpte_330m2011]:http://standards.smpte.org/content/978-1-61482-678-1/st-330-2011/SEC1.abstract
 [ixml]:http://www.ixml.info
-
-
+[eburf64]:https://tech.ebu.ch/docs/tech/tech3306v1_1.pdf
+[info-tags]:https://exiftool.org/TagNames/RIFF.html#Info
 
 ## Demonstration
 
@@ -42,6 +43,12 @@ 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.
@@ -53,104 +60,10 @@ The length of the file in frames (interleaved samples) and bytes is available, a
 >>> (48000, 2, 6, 24)
 ```
 
-### Broadcast WAV Extension
+## Platform Lifecycle Stuff
 
-A WAV file produced to Broadcast-WAV specifications will have the broadcast metadata extension,
-which includes a 256-character free text descrption, creating entity identifier (usually the 
-recording application or equipment), the date and time of recording and a time reference for 
-timecode synchronization.
-
-The `coding_history` is designed to contain a record of every conversion performed on the audio
-file.
-
-In this example (from a Sound Devices 702T) the bext metadata contains scene/take slating
-information in the `description`. Here also the `originator_ref` is a serial number conforming
-to EBU Rec 99.
-
-If the bext metadata conforms to EBU 3285 v1, it will contain the WAV's 32 or 64 byte SMPTE 
-330M UMID. The 32-byte version of the UMID is usually just a random number, while the 64-byte 
-UMID will also have information on the recording date and time, recording equipment and entity, 
-and geolocation data.
-
-If the bext metadata conforms to EBU 3285 v2, it will hold precomputed program loudness values
-as described by EBU Rec 128.
-
-```python
-print(info.bext.description)
-print("----------")
-print("Originator:", info.bext.originator)
-print("Originator Ref:", info.bext.originator_ref)
-print("Originator Date:", info.bext.originator_date)
-print("Originator Time:", info.bext.originator_time)
-print("Time Reference:", info.bext.time_reference)
-print(info.bext.coding_history)
-```
-
-    sSPEED=023.976-ND
-    sTAKE=1
-    sUBITS=$12311801
-    sSWVER=2.67
-    sPROJECT=BMH
-    sSCENE=A101
-    sFILENAME=A101_1.WAV
-    sTAPE=18Y12M31
-    sTRK1=MKH516 A
-    sTRK2=Boom
-    sNOTE=
-    
-    ----------
-    Originator: Sound Dev: 702T S#GR1112089007
-    Originator Ref: USSDVGR1112089007124001008206301
-    Originator Date: 2018-12-31
-    Originator Time: 12:40:00
-    Time Reference: 2190940753
-    A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch
-
-
-
-### iXML Production Recorder Metadata
-
-iXML allows an XML document to be embedded in a WAV file.
-
-The iXML website recommends a schema for recorder information but 
-there is no official DTD and vendors mostly do their own thing, apart from 
-hitting a few key xpaths. iXML is used by most location/production recorders 
-to save slating information, timecode and sync points in a reliable way.
-
-iXML is also used to link "families" of WAV files together, so WAV files
-recorded simultaneously or contiguously can be related by a receiving client.
-
-```python
-print("iXML Project:", info.ixml.project)
-print("iXML Scene:", info.ixml.scene)
-print("iXML Take:", info.ixml.take)
-print("iXML Tape:", info.ixml.tape)
-print("iXML File Family Name:", info.ixml.family_name)
-print("iXML File Family UID:", info.ixml.family_uid)
-```
-
-    iXML Project: BMH
-    iXML Scene: A101
-    iXML Take: 1
-    iXML Tape: 18Y12M31
-    iXML File Family Name: None
-    iXML File Family UID: USSDVGR1112089007124001008206300
-
-
-### INFO Metadata
-
-INFO Metadata is a standard method for saving tagged text data in a WAV or AVI
-file. INFO fields are often read by the file explorer and host OS, and used in 
-music library software.
-
-```python
-bullet_path = '../tests/test_files/BULLET Impact Plastic LCD TV Screen Shatter Debris 2x.wav'
-
-bullet = WavInfoReader(bullet_path)
-```
-
-    print("INFO Artist:",    bullet.info.artist)
-    print("INFO Copyright:", bullet.info.copyright)
-    print("INFO Comment:",   bullet.info.comment)
+Python 3.5 support is deprecated.
 
+## Other Resources
 
+* For other file formats and ID3 decoding, look at [audio-metadata](https://github.com/thebigmunch/audio-metadata).

docs/conf.py

@@ -26,7 +26,7 @@ author = u'Jamie Hardt'
 # The short X.Y version
 version = u''
 # The full version, including alpha/beta/rc tags
-release = u'v1.0'
+release = u'v1.1'
 
 
 # -- General configuration ---------------------------------------------------

docs/index.rst

@@ -6,9 +6,6 @@
 Welcome to wavinfo's documentation!
 ===================================
 
-.. toctree::
-   :maxdepth: 2
-   :caption: Contents:
 
 .. module:: wavinfo
 
@@ -24,6 +21,17 @@ Welcome to wavinfo's documentation!
 .. autoclass:: wavinfo.wave_reader.WavDataDescriptor
    :members:
 
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Notes:
+   
+   metadata_scopes/bext.rst
+   metadata_scopes/ixml.rst
+   metadata_scopes/info.rst
+
+
+
 Indices and tables
 ==================
 

docs/metadata_scopes/bext.rst

@@ -0,0 +1,65 @@
+Broadcast WAV Extension
+=======================
+
+.. module:: wavinfo
+
+.. autoclass:: wavinfo.wave_bext_reader.WavBextReader
+   :members:
+
+
+Notes
+-----
+A WAV file produced to Broadcast-WAV specifications will have the broadcast metadata extension,
+which includes a 256-character free text descrption, creating entity identifier (usually the 
+recording application or equipment), the date and time of recording and a time reference for 
+timecode synchronization.
+
+The `coding_history` is designed to contain a record of every conversion performed on the audio
+file.
+
+In this example (from a Sound Devices 702T) the bext metadata contains scene/take slating
+information in the `description`. Here also the `originator_ref` is a serial number conforming
+to EBU Rec 99.
+
+If the bext metadata conforms to EBU 3285 v1, it will contain the WAV's 32 or 64 byte SMPTE 
+330M UMID. The 32-byte version of the UMID is usually just a random number, while the 64-byte 
+UMID will also have information on the recording date and time, recording equipment and entity, 
+and geolocation data.
+
+If the bext metadata conforms to EBU 3285 v2, it will hold precomputed program loudness values
+as described by EBU Rec 128.
+
+..  code:: python
+
+    print(info.bext.description)
+    print("----------")
+    print("Originator:", info.bext.originator)
+    print("Originator Ref:", info.bext.originator_ref)
+    print("Originator Date:", info.bext.originator_date)
+    print("Originator Time:", info.bext.originator_time)
+    print("Time Reference:", info.bext.time_reference)
+    print(info.bext.coding_history)
+
+Result: 
+
+::
+
+    sSPEED=023.976-ND
+    sTAKE=1
+    sUBITS=$12311801
+    sSWVER=2.67
+    sPROJECT=BMH
+    sSCENE=A101
+    sFILENAME=A101_1.WAV
+    sTAPE=18Y12M31
+    sTRK1=MKH516 A
+    sTRK2=Boom
+    sNOTE=
+    
+    ----------
+    Originator: Sound Dev: 702T S#GR1112089007
+    Originator Ref: USSDVGR1112089007124001008206301
+    Originator Date: 2018-12-31
+    Originator Time: 12:40:00
+    Time Reference: 2190940753
+    A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch

docs/metadata_scopes/info.rst

@@ -0,0 +1,32 @@
+INFO Metadata
+=============
+
+
+.. module:: wavinfo
+
+.. autoclass:: wavinfo.wave_info_reader.WavInfoChunkReader
+   :members:
+
+
+
+Notes
+-----
+
+INFO Metadata is a standard method for saving tagged text data in a WAV or AVI
+file. INFO fields are often read by the file explorer and host OS, and used in 
+music library software.
+
+
+..  code:: python
+
+    bullet_path = '../tests/test_files/BULLET Impact Plastic LCD TV Screen Shatter Debris 2x.wav'
+
+    bullet = WavInfoReader(bullet_path)
+
+    print("INFO Artist:",    bullet.info.artist)
+    print("INFO Copyright:", bullet.info.copyright)
+    print("INFO Comment:",   bullet.info.comment)
+
+
+
+

docs/metadata_scopes/ixml.rst

@@ -0,0 +1,44 @@
+iXML Production Recorder Metadata
+=================================
+
+
+.. module:: wavinfo
+
+.. autoclass:: wavinfo.wave_ixml_reader.WavIXMLFormat
+   :members:
+
+
+Notes
+-----
+iXML allows an XML document to be embedded in a WAV file.
+
+The iXML website recommends a schema for recorder information but 
+there is no official DTD and vendors mostly do their own thing, apart from 
+hitting a few key xpaths. iXML is used by most location/production recorders 
+to save slating information, timecode and sync points in a reliable way.
+
+iXML is also used to link "families" of WAV files together, so WAV files
+recorded simultaneously or contiguously can be related by a receiving client.
+
+..  code:: python
+
+    print("iXML Project:", info.ixml.project)
+    print("iXML Scene:", info.ixml.scene)
+    print("iXML Take:", info.ixml.take)
+    print("iXML Tape:", info.ixml.tape)
+    print("iXML File Family Name:", info.ixml.family_name)
+    print("iXML File Family UID:", info.ixml.family_uid)
+
+Result:
+
+::
+
+    iXML Project: BMH
+    iXML Scene: A101
+    iXML Take: 1
+    iXML Tape: 18Y12M31
+    iXML File Family Name: None
+    iXML File Family UID: USSDVGR1112089007124001008206300
+
+
+

pypi_upload.sh

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

requirements.txt

@@ -0,0 +1,3 @@
+lxml~=4.5.2
+setuptools~=49.6.0
+ear~=2.0.0

setup.py

@@ -1,20 +1,41 @@
 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='1.1',
-      author='Jamie Hardt',
+      version=__version__,
+      author=__author__,
       author_email='jamiehardt@me.com',
-      description='WAVE sound file metadata parser.',
+      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',
-          "Programming Language :: Python :: 3.5",
-          "Programming Language :: Python :: 3.6"],
-      packages=['wavinfo'])
+          'Topic :: Multimedia :: Sound/Audio',
+#           "Programming Language :: Python :: 3.5",
+          "Programming Language :: Python :: 3.6",
+          "Programming Language :: Python :: 3.7",
+          "Programming Language :: Python :: 3.8",
+          "Programming Language :: Python :: 3.9"],
+      keywords='waveform metadata audio ebu smpte avi library film tv editing editorial',
+      install_requires=['lxml', 'ear'],
+      entry_points={
+          'console_scripts': [
+              'wavinfo = wavinfo.__main__:main'
+          ]
+      }
+      )

tests/__init__.py

@@ -1,2 +1,3 @@
 from . import test_wave_parsing
 
+

tests/test_walk.py

@@ -0,0 +1,25 @@
+import unittest
+import wavinfo
+
+
+class TestWalk(unittest.TestCase):
+    def test_walk_metadata(self):
+        test_file = 'tests/test_files/protools/PT A101_4.A1.wav'
+        info = wavinfo.WavInfoReader(test_file)
+
+        tested_data , tested_format = False, False
+        for scope, key, value in info.walk():
+            if scope == 'fmt':
+                if key == 'channel_count':
+                    tested_format = True
+                    self.assertEqual(value, 2)
+            if scope == 'data':
+                if key == 'frame_count':
+                    tested_data = True
+                    self.assertEqual(value, 144140)
+
+        self.assertTrue(tested_data and tested_format)
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_wave_parsing.py

@@ -1,108 +1,114 @@
 import os.path
-import json
-import subprocess
-from subprocess import PIPE
+import sys
 
 from unittest import TestCase
 
+from .utils import all_files, ffprobe
+
 import wavinfo
 
-FFPROBE='ffprobe'
-
-
-def ffprobe(path):
-
-    arguments = [ FFPROBE , "-of", "json" , "-show_format", "-show_streams", path ]
-
-    process = subprocess.run(arguments, stdin=None, stdout=PIPE, stderr=PIPE)
-
-    if process.returncode == 0:
-        output_str = process.stdout.decode('utf-8')
-        return json.loads(output_str)
-    else:
-        return None
-
 
 class TestWaveInfo(TestCase):
-
-
-    def all_files(self):
-        for dirpath, dirnames, filenames in os.walk('tests/test_files'):
-            for filename in filenames:
-                name, ext = os.path.splitext(filename)
-                if ext in ['.wav','.WAV']:
-                    yield os.path.join(dirpath, filename)
-
-
     def test_sanity(self):
-        for wav_file in self.all_files():
+        for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
-            self.assertTrue(info is not None)
+            self.assertEqual(info.__repr__(), 'WavInfoReader(%s, %s, %s)'.format(wav_file, 'latin_1', 'ascii'))
+            self.assertIsNotNone(info)
 
     def test_fmt_against_ffprobe(self):
-        for wav_file in self.all_files():
+        for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
 
-            self.assertEqual( info.fmt.channel_count , ffprobe_info['streams'][0]['channels']  )
-            self.assertEqual( info.fmt.sample_rate   , int(ffprobe_info['streams'][0]['sample_rate'])  )
-            self.assertEqual( info.fmt.bits_per_sample, int(ffprobe_info['streams'][0]['bits_per_raw_sample']) )
+            self.assertEqual(info.fmt.channel_count, ffprobe_info['streams'][0]['channels'])
+            self.assertEqual(info.fmt.sample_rate, int(ffprobe_info['streams'][0]['sample_rate']))
+            self.assertEqual(info.fmt.bits_per_sample, int(ffprobe_info['streams'][0]['bits_per_raw_sample']))
 
             if info.fmt.audio_format == 1:
-                self.assertTrue(ffprobe_info['streams'][0]['codec_name'].startswith('pcm')  )
-                byte_rate = int(ffprobe_info['streams'][0]['sample_rate']) \
-                        * ffprobe_info['streams'][0]['channels'] \
-                        * int(ffprobe_info['streams'][0]['bits_per_raw_sample']) / 8
-                self.assertEqual( info.fmt.byte_rate     , byte_rate  )
+                self.assertTrue(ffprobe_info['streams'][0]['codec_name'].startswith('pcm'))
+                streams = ffprobe_info['streams'][0]
+                byte_rate = int(streams['sample_rate']) * streams['channels'] * int(streams['bits_per_raw_sample']) / 8
+                self.assertEqual(info.fmt.byte_rate, byte_rate)
 
     def test_data_against_ffprobe(self):
-        for wav_file in self.all_files():
+        for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
-
-            self.assertEqual( info.data.frame_count, int(ffprobe_info['streams'][0]['duration_ts'] ))
+            self.assertEqual(info.data.frame_count, int(ffprobe_info['streams'][0]['duration_ts']))
 
     def test_bext_against_ffprobe(self):
-        for wav_file in self.all_files():
+        for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
             if info.bext:
-                self.assertEqual( info.bext.description, ffprobe_info['format']['tags']['comment']  )
-                self.assertEqual( info.bext.originator, ffprobe_info['format']['tags']['encoded_by']  )
-                if 'originator_reference' in ffprobe_info['format']['tags']:
-                    self.assertEqual( info.bext.originator_ref, ffprobe_info['format']['tags']['originator_reference']  )
+                if 'comment' in ffprobe_info['format']['tags']:
+                    self.assertEqual(info.bext.description, ffprobe_info['format']['tags']['comment'])
                 else:
-                    self.assertEqual( info.bext.originator_ref, '')
+                    self.assertEqual(info.bext.description, '')
+
+                if 'encoded_by' in ffprobe_info['format']['tags']:
+                    self.assertEqual(info.bext.originator, ffprobe_info['format']['tags']['encoded_by'])
+                else:
+                    self.assertEqual(info.bext.originator, '')
+
+                if 'originator_reference' in ffprobe_info['format']['tags']:
+                    self.assertEqual(info.bext.originator_ref, ffprobe_info['format']['tags']['originator_reference'])
+                else:
+                    self.assertEqual(info.bext.originator_ref, '')
 
                 # these don't always reflect the bext info
-                # self.assertEqual( info.bext.originator_date, ffprobe_info['format']['tags']['date']  )
-                # self.assertEqual( info.bext.originator_time, ffprobe_info['format']['tags']['creation_time']  )
-                self.assertEqual( info.bext.time_reference, int(ffprobe_info['format']['tags']['time_reference'])  )
+                # self.assertEqual(info.bext.originator_date, ffprobe_info['format']['tags']['date'])
+                # self.assertEqual(info.bext.originator_time, ffprobe_info['format']['tags']['creation_time'])
+                self.assertEqual(info.bext.time_reference, int(ffprobe_info['format']['tags']['time_reference']))
 
                 if 'coding_history' in ffprobe_info['format']['tags']:
-                    self.assertEqual( info.bext.coding_history, ffprobe_info['format']['tags']['coding_history']  )
+                    self.assertEqual(info.bext.coding_history, ffprobe_info['format']['tags']['coding_history'])
                 else:
-                    self.assertEqual( info.bext.coding_history, '' )
+                    self.assertEqual(info.bext.coding_history, '')
 
     def test_ixml(self):
-        expected = {'A101_4.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '4',
-                        'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124015008231000'},
-                    'A101_3.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '3',
-                        'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124014008228300'},
-                    'A101_2.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '2',
-                        'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124004008218600'},
-                    'A101_1.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '1',
-                        'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124001008206300'},
-                }
+        expected = {'A101_4.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '4',
+                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124015008231000'},
+                    'A101_3.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '3',
+                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124014008228300'},
+                    'A101_2.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '2',
+                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124004008218600'},
+                    'A101_1.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '1',
+                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124001008206300'},
+                    }
 
-        for wav_file in self.all_files():
-            basename =  os.path.basename(wav_file)
+        for wav_file in all_files():
+            basename = os.path.basename(wav_file)
             if basename in expected:
                 info = wavinfo.WavInfoReader(wav_file)
                 e = expected[basename]
 
-                self.assertEqual( e['project'], info.ixml.project )
-                self.assertEqual( e['scene'], info.ixml.scene )
-                self.assertEqual( e['take'], info.ixml.take )
-                self.assertEqual( e['tape'], info.ixml.tape )
-                self.assertEqual( e['family_uid'], info.ixml.family_uid )
+                self.assertEqual(e['project'], info.ixml.project)
+                self.assertEqual(e['scene'], info.ixml.scene)
+                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.assertEqual(track.name, 'MKH516 A')
+
+    def test_metadata(self):
+        file_with_metadata = 'tests/test_files/sound_grinder_pro/new_camera bumb 1.wav'
+        self.assertTrue(os.path.exists(file_with_metadata))
+        info = wavinfo.WavInfoReader(file_with_metadata).info
+        self.assertEqual(info.title, 'camera bumb 1')
+        self.assertEqual(info.artist, 'Jamie Hardt')
+        self.assertEqual(info.copyright, '© 2010 Jamie Hardt')
+        self.assertEqual(info.product, 'Test Sounds')  # album
+        self.assertEqual(info.album, info.product)
+        self.assertEqual(info.comment, 'Comments')
+        self.assertEqual(info.software, 'Sound Grinder Pro')
+        self.assertEqual(info.created_date, '2010-12-28')
+        self.assertEqual(info.engineer, 'JPH')
+        self.assertEqual(info.keywords, 'Sound Effect, movement, microphone, bump')
+        self.assertEqual(info.title, 'camera bumb 1')
+        self.assertEqual(type(info.to_dict()), dict)
+        self.assertEqual(type(info.__repr__()), str)
+

tests/test_zoom_f8.py

@@ -0,0 +1,13 @@
+import os.path
+import sys
+import json
+import subprocess
+from subprocess import PIPE
+
+from unittest import TestCase
+
+import wavinfo
+
+
+class TestZoomF8(TestCase):
+    pass

tests/utils.py

@@ -0,0 +1,36 @@
+import os.path
+import sys
+import subprocess
+from subprocess import PIPE
+import json
+
+FFPROBE = 'ffprobe'
+
+
+def ffprobe(path):
+    arguments = [FFPROBE, "-of", "json", "-show_format", "-show_streams", path]
+    if int(sys.version[0]) <  3:
+        process = subprocess.Popen(arguments, stdout=PIPE)
+        process.wait()
+        if process.returncode == 0:
+            output = process.communicate()[0]
+            if output:
+                output_str = output.decode('utf-8')
+                return json.loads(output_str)
+        else:
+            return None
+    else: 
+        process = subprocess.run(arguments, stdin=None, stdout=PIPE, stderr=PIPE)
+        if process.returncode == 0:
+            output_str = process.stdout.decode('utf-8')
+            return json.loads(output_str)
+        else:
+            return None
+
+
+def all_files():
+    for dirpath, _, filenames in os.walk('tests/test_files'):
+        for filename in filenames:
+            _, ext = os.path.splitext(filename)
+            if ext in ['.wav', '.WAV']:
+                yield os.path.join(dirpath, filename)

wavinfo/__init__.py

@@ -1,14 +1,12 @@
-# -*- coding: utf-8 -*-
-
-# :module:`wavinfo` provides methods to probe a WAV file for
-# various kinds of production metadata.
-#
-#
-#
-#
+"""
+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'
-__author__ = 'Jamie Hardt'
+__version__ = '1.6'
+__author__ = 'Jamie Hardt <jamiehardt@gmail.com>'
+__license__ = "MIT"

wavinfo/__main__.py

@@ -0,0 +1,34 @@
+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/dolby_parser.py

@@ -0,0 +1,188 @@
+# Dolby RMU Metadata per EBU Tech 3285 Supp 6
+#
+# https://tech.ebu.ch/docs/tech/tech3285s6.pdf
+#
+
+from struct import unpack, calcsize
+from enum import (Enum, IntEnum)
+
+CHUNK_IDENT = "dbmd"
+DOLBY_VERSION = "1.0.0.6"
+
+
+class _DPPGenericDownMixLevel(Enum):
+    PLUS_3DB = 0b000
+    PLUS_1_5DB = 0b001
+    UNITY = 0b010
+    MINUS_1_5DB = 0b011
+    MINUS_3DB = 0b100
+    MINUS_4_5DB = 0b101
+    MINUS_6DB = 0b110
+    MUTE = 0b111
+
+
+class DPPDolbySurroundEncodingMode(Enum):
+    RESERVED = 0b11
+    IN_USE = 0b10
+    NOT_IN_USE = 0b01
+    NOT_INDICATED = 0b00
+
+# DPPLoRoDownMixCenterLevel
+# DPPLtRtCenterMixLevel
+# DPPLtRtSurroundMixLevel
+
+class DolbyMetadataSegmentTypes(IntEnum):
+    END_MARKER = 0
+    DOLBY_E_METADATA = 1
+    DOLBY_DIGITAL_METADATA = 3
+    DOLBY_DIGITAL_PLUS_METADATA = 7
+    AUDIO_INFO = 8
+
+
+class DDPBitStreamMode(Enum):
+    """
+    Dolby Digital Plus `bsmod` field
+    § 4.3.2.2
+    """
+    COMPLETE_MAIN = 0b000
+    MUSIC_AND_EFFECTS = 0b001
+    VISUALLY_IMPAIRED = 0b010
+    HEARING_IMPAIRED = 0b011
+    DIALOGUE_ONLY = 0b100
+    COMMENTARY = 0b101
+    EMERGENCY = 0b110
+    VOICEOVER = 0b111 # if audioconfigmode is 1_0
+    KARAOKE = 0b1000  # if audioconfigmode is not 1_0
+
+
+class DDPAudioCodingMode(Enum):
+    """
+    Dolby Digital Plus `acmod` field
+    § 4.3.2.3
+    """
+    RESERVED = 0b000
+    CH_ORD_1_0 = 0b001
+    CH_ORD_2_0 = 0b010
+    CH_ORD_3_0 = 0b011
+    CH_ORD_2_1 = 0b100
+    CH_ORD_3_1 = 0b101
+    CH_ORD_2_2 = 0b110
+    CH_ORD_3_2 = 0b111
+
+
+class DPPCenterDownMixLevel(Enum):
+    """
+    § 4.3.3.1
+    """
+    DOWN_3DB = 0b00
+    DOWN_45DB = 0b01
+    DOWN_6DB = 0b10
+    RESERVED = 0b11
+
+
+class DPPSurroundDownMixLevel(Enum):
+    """
+    Dolby Digital Plus `surmixlev` field
+    § 4.3.3.2
+    """
+    DOWN_3DB = 0b00
+    DOWN_6DB = 0b01
+    MUTE = 0b10
+    RESERVED = 0b11
+
+
+class DPPLanguageCode(Enum):
+    """
+    § 4.3.4.1 , 4.3.5 (always 0xFF)
+    """
+    # this is removed in https://www.atsc.org/wp-content/uploads/2015/03/A52-201212-17.pdf § 5.4.2.12
+    # It should just be 0xff
+    pass
+
+
+class DPPMixLevel(int):
+    pass
+
+
+class DPPDialnormLevel(int):
+    pass
+
+
+class DPPRoomTime(Enum):
+    """
+    `roomtyp` 4.3.6.3
+    """
+    NOT_INDICATED = 0b00
+    LARGE_ROOM_X_CURVE = 0b01
+    SMALL_ROOM_FLAT_CURVE = 0b10
+    RESERVED = 0b11
+
+
+class DPPPreferredDownMixMode(Enum):
+    """
+    § 4.3.8.1
+    """
+    NOT_INDICATED = 0b00
+    PRO_LOGIC = 0b01
+    STEREO = 0b10
+    PRO_LOGIC_2 = 0b11
+
+
+# class DPPLtRtCenterMixLevel(_DPPGenericDownMixLevel):
+#     pass
+#
+#
+# class DPPLtRtSurroundMixLevel(_DPPGenericDownMixLevel):
+#     pass
+#
+#
+# class DPPSurroundEXMode(_DPPGenericInUseIndicator):
+#     pass
+#
+#
+# class DPPHeadphoneMode(_DPPGenericInUseIndicator):
+#     pass
+
+
+class DPPADConverterType(Enum):
+    STANDARD = 0
+    HDCD = 1
+
+
+class DDPStreamDependency(Enum):
+    """
+    Encodes `ddplus_info1.stream_type` field § 4.3.12.1
+    """
+    INDEPENDENT = 0
+    DEPENDENT = 1
+    INDEPENDENT_FROM_DOLBY_DIGITAL = 2
+    RESERVED = 3
+
+
+class DDPDataRate(int):
+    pass
+
+
+class DPPRFCompressionProfile(Enum):
+    NONE = 0
+    FILM_STANDARD = 1
+    FILM_LIGHT = 2
+    MUSIC_STANDARD = 3
+    MUSIC_LIGHT = 4
+    SPEECH = 5
+
+
+class DolbyDigitalPlusMetadata:
+
+    @classmethod
+    def parse(cls, binary_data):
+        binary_format = "<BBxxBBBBBBBBBBBBBxxxBxxxxxH"
+        assert len(binary_data >= calcsize(binary_format))
+        fields = unpack(binary_format, binary_data)
+
+
+class WavDolbyReader:
+    def __init__(self, dolby_data):
+        version, remainder = unpack("<U", dolby_data[0]), dolby_data[1:]
+
+        ## FIXME continues...

wavinfo/rf64_parser.py

@@ -0,0 +1,40 @@
+import struct
+from collections import namedtuple
+from . import riff_parser
+
+RF64Context = namedtuple('RF64Context','sample_count bigchunk_table')
+
+
+def parse_rf64(stream, signature = b'RF64'):
+    # print("starting parse_rf64")
+    start = stream.tell()
+    assert( stream.read(4) == b'WAVE' )
+
+    ds64_chunk = riff_parser.parse_chunk(stream)
+
+    ds64_field_spec = "<QQQI"
+    ds64_fields_size = struct.calcsize(ds64_field_spec)
+    assert(ds64_chunk.ident == b'ds64')
+
+    ds64_data = ds64_chunk.read_data(stream)
+    assert(len(ds64_data) >= ds64_fields_size )
+
+    # print("Read ds64 chunk: len()",len(ds64_data))
+    riff_size, data_size, sample_count, length_lookup_table = struct.unpack( ds64_field_spec , ds64_data[0:ds64_fields_size] )
+
+    bigchunk_table = {}
+    chunksize64format = "<4sL"
+    chunksize64size = struct.calcsize(chunksize64format)
+    # print("Found chunks64s:", length_lookup_table)
+
+    for n in range(length_lookup_table):
+        bigname, bigsize = struct.unpack_from( chunksize64format , ds64_data, offset= ds64_fields_size )
+        bigchunk_table[bigname] = bigsize
+
+    bigchunk_table[b'data'] = data_size
+    bigchunk_table[signature] = riff_size
+
+    stream.seek(start, 0)
+    # print("returning from parse_rf64, context: ", RF64Context(sample_count=sample_count, bigchunk_table=bigchunk_table))
+    return RF64Context( sample_count=sample_count, bigchunk_table=bigchunk_table )
+

wavinfo/riff_parser.py

@@ -1,64 +1,73 @@
 
 import struct
-import pdb
 from collections import namedtuple
-
-class ListChunkDescriptor(namedtuple('ListChunkDescriptor' , 'signature children')):
-
-    def find(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:])
-        else:
-            for chunk in self.children:
-                if type(chunk) is ChunkDescriptor and \
-                        chunk.ident is chunk_path[0]:
-                            return chunk
+from .rf64_parser import parse_rf64
 
 
-class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length') ):
+class WavInfoEOFError(EOFError):
+    def __init__(self, identifier, chunk_start):
+        self.identifier = identifier
+        self.chunk_start = chunk_start
+
+
+class ListChunkDescriptor(namedtuple('ListChunkDescriptor', 'signature children')):
+    pass
+    # 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:])
+    #     else:
+    #         for chunk in self.children:
+    #             if type(chunk) is ChunkDescriptor and \
+    #                     chunk.ident is chunk_path[0]:
+    #                 return chunk
+
+
+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):
-    start = stream.tell()
 
+def parse_list_chunk(stream, length, rf64_context=None):
+    start = stream.tell()
     signature = stream.read(4)
 
     children = []
-    while (stream.tell() - start) < length:
-        child_chunk = parse_chunk(stream)
-        if child_chunk:
-             children.append(child_chunk)
-        else: 
-             break
+    while stream.tell() - start + 8 < length:
+        child_chunk = parse_chunk(stream, rf64_context=rf64_context)
+        children.append(child_chunk)
+
+    stream.seek(start + length)
 
     return ListChunkDescriptor(signature=signature, children=children)
 
-def parse_chunk(stream):
-    #breakpoint()
+
+def parse_chunk(stream, rf64_context=None):
+    header_start = stream.tell()
     ident = stream.read(4)
-    if len(ident) != 4:
-        return
+    size_bytes = stream.read(4)
 
-    sizeb = stream.read(4)
-    size  = struct.unpack('<I',sizeb)[0]
+    if len(ident) != 4 or len(size_bytes) != 4:
+        raise WavInfoEOFError(identifier=ident, chunk_start=header_start)
 
-    displacement = size
-    if displacement % 2 is not 0:
-        displacement = displacement + 1
+    data_size = struct.unpack('<I', size_bytes)[0]
 
-    if ident in [b'RIFF',b'LIST']:
-        return parse_list_chunk(stream=stream, length=size)
+    if data_size == 0xFFFFFFFF:
+        if rf64_context is None and ident in {b'RF64', b'BW64'}:
+            rf64_context = parse_rf64(stream=stream, signature=ident)
+
+        data_size = rf64_context.bigchunk_table[ident]
+
+    displacement = data_size
+    if displacement % 2:
+        displacement += 1
+
+    if ident in {b'RIFF', b'LIST', b'RF64', b'BW64'}:
+        return parse_list_chunk(stream=stream, length=data_size, rf64_context=rf64_context)
     else:
-        start = stream.tell()
-        stream.seek(displacement,1)
-        return ChunkDescriptor(ident=ident, start=start, length=size)
-
-
-
-
-
+        data_start = stream.tell()
+        stream.seek(displacement, 1)
+        return ChunkDescriptor(ident=ident, start=data_start, length=data_size, rf64_context=rf64_context)

wavinfo/umid_parser.py

@@ -0,0 +1,123 @@
+from typing import Union
+import binascii
+from functools import reduce
+
+
+def binary_to_string(binary_value):
+    return reduce(lambda val, el: val + "{:02x}".format(el), binary_value, '')
+
+
+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
+    #
+    # @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 binary_to_string(self.raw_umid[0:32])
+    #
+    # @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_axml_reader.py

@@ -0,0 +1,9 @@
+from lxml import etree as ET
+from collections import namedtuple
+
+from ear.fileio.bw64 import Bw64Reader
+
+
+
+
+

wavinfo/wave_bext_reader.py

@@ -1,83 +1,89 @@
 import struct
+import binascii
+from .umid_parser import UMIDParser
+
 
 class WavBextReader:
-    def __init__(self,bext_data,encoding):
-        # description[256]
-
-        # originator[32]
-        # originatorref[32]
-        # originatordate[10]   "YYYY:MM:DD"
-        # originatortime[8]    "HH:MM:SS"
-        # lowtimeref U32
-        # hightimeref U32
-        # version U16
-        #
-        # V1 field
-        # umid[64]
-        #
-        # V2 fields
-        # loudnessvalue S16    (in LUFS*100)
-        # loudnessrange S16    (in LUFS*100)
-        # maxtruepeak   S16    (in dbTB*100)
-        # maxmomentaryloudness S16 (LUFS*100)
-        # maxshorttermloudness S16 (LUFS*100)
-        #
-        # reserved[180]
-        # codinghistory []
-        packstring = "<256s"+ "32s" + "32s" + "10s" + "8s" + "QH" + "64s" + "hhhhh" + "180s"
+    def __init__(self, bext_data, encoding):
+        """
+        Read Broadcast-WAV extended metadata.
+        :param bext_data: The bytes-like data.
+        :param encoding: The encoding to use when decoding the text fields of the
+                 BEXT metadata scope. According to EBU Rec 3285 this shall be ASCII.
+        """
+        packstring = "<256s" + "32s" + "32s" + "10s" + "8s" + "QH" + "64s" + "hhhhh" + "180s"
 
         rest_starts = struct.calcsize(packstring)
         unpacked = struct.unpack(packstring, bext_data[:rest_starts])
 
-        def sanatize_bytes(bytes):
-            first_null = next( (index for index, byte in enumerate(bytes) if byte == 0 ), None )
-            if first_null is not None:
-                trimmed = bytes[:first_null]
-            else:
-                trimmed = bytes
-
+        def sanitize_bytes(b):
+            first_null = next((index for index, byte in enumerate(b) if byte == 0), None)
+            trimmed = b if first_null is None else b[:first_null]
             decoded = trimmed.decode(encoding)
             return decoded
 
-        self.description     = sanatize_bytes(unpacked[0])
-        self.originator      = sanatize_bytes(unpacked[1])
-        self.originator_ref  = sanatize_bytes(unpacked[2])
-        self.originator_date = sanatize_bytes(unpacked[3])
-        self.originator_time = sanatize_bytes(unpacked[4])
-        self.time_reference  = unpacked[5]
-        self.version         = unpacked[6]
-        self.umid            = None
-        self.loudness_value          = None
-        self.loudness_range          = None
-        self.max_true_peak           = None
-        self.max_momentary_loudness  = None
-        self.max_shortterm_loudness  = None
-        self.coding_history  = sanatize_bytes(bext_data[rest_starts:])
+        #: Description. A free-text field up to 256 characters long.
+        self.description = sanitize_bytes(unpacked[0])
+        #: Originator. Usually the name of the encoding application, sometimes
+        #: a artist name.
+        self.originator = sanitize_bytes(unpacked[1])
+        #: A unique identifier for the file, a serial number.
+        self.originator_ref = sanitize_bytes(unpacked[2])
+        #: Date of the recording, in the format YYY-MM-DD
+        self.originator_date = sanitize_bytes(unpacked[3])
+        #: Time of the recording, in the format HH:MM:SS.
+        self.originator_time = sanitize_bytes(unpacked[4])
+        #: The sample offset of the start of the file relative to an
+        #: epoch, usually midnight the day of the recording. 
+        self.time_reference = unpacked[5]
+        #: A variable-length text field containing a list of processes and
+        #: and conversions performed on the file.
+        self.coding_history = sanitize_bytes(bext_data[rest_starts:])
+        #: BEXT version. 
+        self.version = unpacked[6]
+        #: SMPTE 330M UMID of this audio file, 64 bytes are allocated though the UMID
+        #: may only be 32 bytes long.
+        self.umid = None
+        #: EBU R128 Integrated loudness, in LUFS.
+        self.loudness_value = None
+        #: EBU R128 Loudness rante, in LUFS.
+        self.loudness_range = None
+        #: True peak level, in dBFS TP
+        self.max_true_peak = None
+        #: EBU R128 Maximum momentary loudness, in LUFS
+        self.max_momentary_loudness = None
+        #: EBU R128 Maximum short-term loudness, in LUFS.
+        self.max_shortterm_loudness = None
 
         if self.version > 0:
             self.umid = unpacked[7]
 
         if self.version > 1:
-            self.loudness_value          = unpacked[8] / 100.0
-            self.loudness_range          = unpacked[9] / 100.0
-            self.max_true_peak           = unpacked[10] / 100.0
-            self.max_momentary_loudness  = unpacked[11] / 100.0
-            self.max_shortterm_loudness  = unpacked[12] / 100.0
-
+            self.loudness_value = unpacked[8] / 100.0
+            self.loudness_range = unpacked[9] / 100.0
+            self.max_true_peak = unpacked[10] / 100.0
+            self.max_momentary_loudness = unpacked[11] / 100.0
+            self.max_shortterm_loudness = unpacked[12] / 100.0
 
     def to_dict(self):
-        return {'description':      self.description,
-                'originator':       self.originator,
-                'originator_ref':   self.originator_ref,
-                'originator_date':  self.originator_date,
-                'originator_time':  self.originator_time,
-                'time_reference':   self.time_reference,
-                'version':          self.version,
-                'coding_history':   self.coding_history,
-                'loudness_value':   self.loudness_value,
-                'loudness_range':   self.loudness_range,
-                'max_true_peak':    self.max_true_peak,
-                'max_momentary_loudness':   self.max_momentary_loudness,
-                'max_shortterm_loudness':   self.max_shortterm_loudness
-                }
+        if self.umid is not None:
+            umid_parsed = UMIDParser(self.umid)
+            umid_str = umid_parsed.basic_umid_to_str()
+        else:
+            umid_str = None
 
+        return {'description': self.description,
+                'originator': self.originator,
+                'originator_ref': self.originator_ref,
+                'originator_date': self.originator_date,
+                'originator_time': self.originator_time,
+                'time_reference': self.time_reference,
+                'version': self.version,
+                'umid': umid_str,
+                'coding_history': self.coding_history,
+                'loudness_value': self.loudness_value,
+                'loudness_range': self.loudness_range,
+                'max_true_peak': self.max_true_peak,
+                'max_momentary_loudness': self.max_momentary_loudness,
+                'max_shortterm_loudness': self.max_shortterm_loudness
+                }

wavinfo/wave_info_reader.py

@@ -1,6 +1,6 @@
-
 from .riff_parser import parse_chunk, ListChunkDescriptor
 
+
 class WavInfoChunkReader:
 
     def __init__(self, f, encoding):
@@ -9,30 +9,47 @@ class WavInfoChunkReader:
         f.seek(0)
         parsed_chunks = parse_chunk(f)
 
-        list_chunks = [chunk for chunk in parsed_chunks.children \
-                if type(chunk) is ListChunkDescriptor]
+        list_chunks = [chunk for chunk in parsed_chunks.children if type(chunk) is ListChunkDescriptor]
 
-        self.info_chunk  = next((chunk for chunk in list_chunks \
-                if chunk.signature == b'INFO'), None)
-
-        self.copyright      = self._get_field(f,b'ICOP')
-        self.product        = self._get_field(f,b'IPRD')
-        self.genre          = self._get_field(f,b'IGNR')
-        self.artist         = self._get_field(f,b'IART')
-        self.comment        = self._get_field(f,b'ICMT')
-        self.software       = self._get_field(f,b'ISFT')
-        self.created_date   = self._get_field(f,b'ICRD')
-        self.engineer       = self._get_field(f,b'IENG')
-        self.keywords       = self._get_field(f,b'IKEY')
-        self.title          = self._get_field(f,b'INAM')
-        self.source         = self._get_field(f,b'ISRC')
-        self.tape           = self._get_field(f,b'TAPE')
+        self.info_chunk = next((chunk for chunk in list_chunks if chunk.signature == b'INFO'), None)
 
+        #: 'ICOP' Copyright
+        self.copyright = self._get_field(f, b'ICOP')
+        #: 'IPRD' Product
+        self.product = self._get_field(f, b'IPRD')
+        self.album = self.product
+        #: 'IGNR' Genre
+        self.genre = self._get_field(f, b'IGNR')
+        #: 'ISBJ' Supject
+        self.subject = self._get_field(f, b'ISBJ')
+        #: 'IART' Artist, composer, author
+        self.artist = self._get_field(f, b'IART')
+        #: 'ICMT' Comment
+        self.comment = self._get_field(f, b'ICMT')
+        #: 'ISFT' Software, encoding application
+        self.software = self._get_field(f, b'ISFT')
+        #: 'ICRD' Created date
+        self.created_date = self._get_field(f, b'ICRD')
+        #: 'IENG' Engineer
+        self.engineer = self._get_field(f, b'IENG')
+        #: 'ITCH' Technician
+        self.technician = self._get_field(f, b'ITCH')
+        #: 'IKEY' Keywords, keyword list
+        self.keywords = self._get_field(f, b'IKEY')
+        #: 'INAM' Name, title
+        self.title = self._get_field(f, b'INAM')
+        #: 'ISRC' Source
+        self.source = self._get_field(f, b'ISRC')
+        #: 'TAPE' Tape
+        self.tape = self._get_field(f, b'TAPE')
+        #: 'IARL' Archival Location
+        self.archival_location = self._get_field(f, b'IARL')
+        #: 'ICSM' Commissioned
+        self.commissioned = self._get_field(f, b'ICMS')
 
     def _get_field(self, f, field_ident):
-
-        search = next( ( (chunk.start, chunk.length) for chunk in self.info_chunk.children \
-                if chunk.ident == field_ident ), None)
+        search = next(((chunk.start, chunk.length) for chunk in self.info_chunk.children if chunk.ident == field_ident),
+                      None)
 
         if search is not None:
             f.seek(search[0])
@@ -41,24 +58,30 @@ class WavInfoChunkReader:
         else:
             return None
 
-
     def to_dict(self):
-        return {'copyright':    self.copyright,
-                'product':  self.product,
-                'genre':    self.genre,
-                'artist':   self.artist,
-                'comment':  self.comment,
+        """
+        A dictionary with all of the key/values read from the INFO scope.
+        """
+        return {'copyright': self.copyright,
+                'product': self.product,
+                'album': self.album,
+                'genre': self.genre,
+                'artist': self.artist,
+                'comment': self.comment,
                 'software': self.software,
                 'created_date': self.created_date,
                 'engineer': self.engineer,
                 'keywords': self.keywords,
-                'title':    self.title,
-                'source':   self.source,
-                'tape':     self.tape
+                'title': self.title,
+                'source': self.source,
+                'tape': self.tape,
+                'commissioned': self.commissioned,
+                'archival_location': self.archival_location,
+                'subject': self.subject,
+                'technician': self.technician
                 }
 
-
-
-
-
-
+    def __repr__(self):
+        return_val = self.to_dict()
+        return_val.update({'encoding': self.encoding})
+        return str(return_val)

wavinfo/wave_ixml_reader.py

@@ -1,42 +1,89 @@
-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:
     """
-    iXML recorder metadata, as defined by iXML 2.0
+    iXML recorder metadata.
     """
     def __init__(self, xml):
+        """
+        Parse iXML.
+        :param xml: A bytes-like object containing the iXML payload.
+        """
         self.source = xml
-        xmlBytes = io.BytesIO(xml)
-        self.parsed = ET.parse(xmlBytes)
+        xml_bytes = io.BytesIO(xml)
+        parser = ET.XMLParser(recover=True)
+        self.parsed = ET.parse(xml_bytes, parser=parser)
 
     def _get_text_value(self, xpath):
         e = self.parsed.find("./" + xpath)
         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):
+        """
+        The project/film name entered for the recording.
+        """
         return self._get_text_value("PROJECT")
 
     @property
     def scene(self):
+        """
+        Scene/slate.
+        """
         return self._get_text_value("SCENE")
 
     @property
     def take(self):
+        """
+        Take number.
+        """
         return self._get_text_value("TAKE")
 
     @property
     def tape(self):
+        """
+        Tape name.
+        """
         return self._get_text_value("TAPE")
 
     @property
     def family_uid(self):
+        """
+        The globally-unique ID for this file family. This may be in the format
+        of a GUID, or an EBU Rec 9 source identifier, or some other dumb number.
+        """
         return self._get_text_value("FILE_SET/FAMILY_UID")
 
     @property
     def family_name(self):
+        """
+        The name of this file's file family.
+        """
         return self._get_text_value("FILE_SET/FAMILY_NAME")
-
-

wavinfo/wave_reader.py

@@ -1,21 +1,24 @@
 #-*- coding: utf-8 -*-
 import struct
-
+import os
 from collections import namedtuple
 
+import pathlib
+
 from .riff_parser import parse_chunk, ChunkDescriptor, ListChunkDescriptor
 from .wave_ixml_reader import WavIXMLFormat
 from .wave_bext_reader import WavBextReader
 from .wave_info_reader import WavInfoChunkReader
 
 #: Calculated statistics about the audio data.
-WavDataDescriptor = namedtuple('WavDataDescriptor','byte_count frame_count')
+WavDataDescriptor = namedtuple('WavDataDescriptor', 'byte_count frame_count')
 
 #: The format of the audio samples.
-WavAudioFormat = namedtuple('WavAudioFormat','audio_format channel_count sample_rate byte_rate block_align bits_per_sample')
+WavAudioFormat = namedtuple('WavAudioFormat',
+                            'audio_format channel_count sample_rate byte_rate block_align bits_per_sample')
 
 
-class WavInfoReader():
+class WavInfoReader:
     """
     Parse a WAV audio file for metadata.
     """
@@ -31,9 +34,17 @@ class WavInfoReader():
 
         :param bext_encoding: The text encoding to use when decoding the string
           fields of the Broadcast-WAV extension. Per EBU 3285 this is ASCII
-          but this parameter is available to you if you encounter a werido.
-
+          but this parameter is available to you if you encounter a weirdo.
         """
+        absolute_path = os.path.abspath(path)
+
+        #: `file://` url for the file.
+        self.url = pathlib.Path(absolute_path).as_uri()
+
+        # for __repr__()
+        self.path = absolute_path
+        self.info_encoding = info_encoding
+        self.bext_encoding = bext_encoding
 
         with open(path, 'rb') as f:
             chunks = parse_chunk(f)
@@ -42,42 +53,31 @@ class WavInfoReader():
             f.seek(0)
 
             #: :class:`wavinfo.wave_reader.WavAudioFormat`
-            self.fmt    = self._get_format(f)
+            self.fmt = self._get_format(f)
 
             #: :class:`wavinfo.wave_bext_reader.WavBextReader` with Broadcast-WAV metadata
-            self.bext   = self._get_bext(f, encoding=bext_encoding)
+            self.bext = self._get_bext(f, encoding=bext_encoding)
 
             #: :class:`wavinfo.wave_ixml_reader.WavIXMLFormat` with iXML metadata
-            self.ixml   = self._get_ixml(f)
+            self.ixml = self._get_ixml(f)
 
             #: :class:`wavinfo.wave_info_reader.WavInfoChunkReader` with RIFF INFO metadata
-            self.info   = self._get_info(f, encoding=info_encoding)
-            self.data   = self._describe_data(f)
+            self.info = self._get_info(f, encoding=info_encoding)
+            self.data = self._describe_data()
 
     def _find_chunk_data(self, ident, from_stream, default_none=False):
-        chunk_descriptor = None
-        top_chunks = (chunk for chunk in self.main_list if type(chunk) is ChunkDescriptor)
+        top_chunks = (chunk for chunk in self.main_list if type(chunk) is ChunkDescriptor and chunk.ident == ident)
+        chunk_descriptor = next(top_chunks, None) if default_none else next(top_chunks)
+        return chunk_descriptor.read_data(from_stream) if chunk_descriptor else None
 
-        if default_none:
-            chunk_descriptor = next((chunk for chunk in top_chunks if chunk.ident == ident),None)
-        else:
-            chunk_descriptor = next((chunk for chunk in top_chunks if chunk.ident == ident))
-
-        if chunk_descriptor:
-            return chunk_descriptor.read_data(from_stream)
-        else:
-            return None
-
-
-    def _describe_data(self,f):
+    def _describe_data(self):
         data_chunk = next(c for c in self.main_list if c.ident == b'data')
 
-        return WavDataDescriptor(byte_count= data_chunk.length,
-                frame_count= int(data_chunk.length / self.fmt.block_align))
+        return WavDataDescriptor(byte_count=data_chunk.length,
+                                 frame_count=int(data_chunk.length / self.fmt.block_align))
 
-
-    def _get_format(self,f):
-        fmt_data = self._find_chunk_data(b'fmt ',f)
+    def _get_format(self, f):
+        fmt_data = self._find_chunk_data(b'fmt ', f)
 
         # The format chunk is
         # audio_format    U16
@@ -91,54 +91,59 @@ class WavInfoReader():
 
         unpacked = struct.unpack(packstring, fmt_data[:rest_starts])
 
-        #0x0001	WAVE_FORMAT_PCM	PCM
-        #0x0003	WAVE_FORMAT_IEEE_FLOAT	IEEE float
-        #0x0006	WAVE_FORMAT_ALAW	8-bit ITU-T G.711 A-law
-        #0x0007	WAVE_FORMAT_MULAW	8-bit ITU-T G.711 µ-law
-        #0xFFFE	WAVE_FORMAT_EXTENSIBLE	Determined by SubFormat
+        # 0x0001	WAVE_FORMAT_PCM	PCM
+        # 0x0003	WAVE_FORMAT_IEEE_FLOAT	IEEE float
+        # 0x0006	WAVE_FORMAT_ALAW	8-bit ITU-T G.711 A-law
+        # 0x0007	WAVE_FORMAT_MULAW	8-bit ITU-T G.711 µ-law
+        # 0xFFFE	WAVE_FORMAT_EXTENSIBLE	Determined by SubFormat
 
-        #https://sno.phy.queensu.ca/~phil/exiftool/TagNames/RIFF.html
-        return WavAudioFormat(audio_format = unpacked[0],
-                    channel_count   = unpacked[1],
-                    sample_rate     = unpacked[2],
-                    byte_rate       = unpacked[3],
-                    block_align     = unpacked[4],
-                    bits_per_sample = unpacked[5]
-                    )
+        # https://sno.phy.queensu.ca/~phil/exiftool/TagNames/RIFF.html
+        return WavAudioFormat(audio_format=unpacked[0],
+                              channel_count=unpacked[1],
+                              sample_rate=unpacked[2],
+                              byte_rate=unpacked[3],
+                              block_align=unpacked[4],
+                              bits_per_sample=unpacked[5]
+                              )
 
     def _get_info(self, f, encoding):
-        finder = (chunk.signature for chunk in self.main_list \
-                if type(chunk) is ListChunkDescriptor)
+        finder = (chunk.signature for chunk in self.main_list if type(chunk) is ListChunkDescriptor)
 
         if b'INFO' in finder:
             return WavInfoChunkReader(f, encoding)
 
     def _get_bext(self, f, encoding):
-        bext_data = self._find_chunk_data(b'bext',f,default_none=True)
-        if bext_data:
-            return WavBextReader(bext_data, encoding)
-        else:
-            return None
+        bext_data = self._find_chunk_data(b'bext', f, default_none=True)
+        return WavBextReader(bext_data, encoding) if bext_data else None
 
-    def _get_ixml(self,f):
-        ixml_data = self._find_chunk_data(b'iXML',f,default_none=True)
-        if ixml_data is None:
-            return None
-
-        ixml_string = ixml_data
-        return WavIXMLFormat(ixml_string)
+    def _get_ixml(self, f):
+        ixml_data = self._find_chunk_data(b'iXML', f, default_none=True)
+        return None if ixml_data is None else WavIXMLFormat(ixml_data.rstrip(b'\0'))
 
     def walk(self):
         """
         Walk all of the available metadata fields.
 
         :yields: a string, the :scope: of the metadatum, the string :name: of the
-        metadata field, and the value
+        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)
+
+            if self.bext is not None:
+                bext_dict = (self.bext or {}).to_dict()
+                for key in bext_dict.keys():
+                    yield 'bext', key, bext_dict[key]
+
+            if self.info is not None:
+                info_dict = self.info.to_dict()
+                for key in info_dict.keys():
+                    yield 'info', key, info_dict[key]
+
+    def __repr__(self):
+        return 'WavInfoReader(%s, %s, %s)'.format(self.path, self.info_encoding, self.bext_encoding)