Changed indexing of tracks

Removed supplemental metadata for
now

.devcontainer/devcontainer.json

@@ -0,0 +1,26 @@
+{
+	"image": "mcr.microsoft.com/devcontainers/universal:2",
+	"features": {
+    	"ghcr.io/devcontainers/features/anaconda:1": {},
+    	"ghcr.io/devcontainers/features/python:1": {
+    	"version":"3.11"
+    },
+    "ghcr.io/meaningful-ooo/devcontainer-features/fish:1": {}
+},
+"postCreateCommand": "pip3 install -r requirements.txt && pip3 install -r docs/requirements.txt && pip3 install pytest && conda install -y ffmpeg",
+"customizations": {
+	"vscode": {
+		"extensions": [
+			"ms-python.isort",
+			"ms-toolsai.jupyter",
+			"ms-toolsai.vscode-jupyter-cell-tags",
+			"ms-toolsai.jupyter-keymap",
+			"ms-toolsai.jupyter-renderers",
+			"ms-toolsai.vscode-jupyter-slideshow",
+			"ms-python.python",
+			"ms-python.vscode-pylance",
+			"george-alisson.html-preview-vscode"
+		]
+	}
+}
+}

.github/workflows/python-package.yml

@@ -0,0 +1,42 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Python Lint and Test
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
+
+    steps:
+    - uses: actions/checkout@v2.5.0
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4.3.0
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8 pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Setup FFmpeg
+      uses: FedericoCarboni/setup-ffmpeg@v2
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        pytest

.github/workflows/pythonpublish.yml

@@ -0,0 +1,36 @@
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+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: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_APIKEY }}
+      run: |
+        python setup.py sdist bdist_wheel
+        twine upload dist/*
+    - name: Report to Mastodon
+      uses: cbrgm/mastodon-github-action@v1.0.1
+      with:
+        message: |
+          I just released a new version of wavinfo, my library for reading WAVE file metadata!
+          #sounddesign #filmmaking #audio #python
+          ${{ github.server_url }}/${{ github.repository }}
+      env:
+        MASTODON_URL: ${{ secrets.MASTODON_URL }}
+        MASTODON_ACCESS_TOKEN: ${{ secrets.MASTODON_ACCESS_TOKEN }}

.gitignore

@@ -89,6 +89,8 @@ venv/
 ENV/
 env.bak/
 venv.bak/
+docs_venv/
+venv_docs/
 
 # Spyder project settings
 .spyderproject
@@ -105,3 +107,6 @@ venv.bak/
 
 # vim swap
 *.swp
+.DS_Store
+
+.vscode/

.readthedocs.yaml

@@ -0,0 +1,29 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-20.04
+  tools:
+    python: "3.10"
+    # You can also specify other tool versions:
+    # nodejs: "16"
+    # rust: "1.55"
+    # golang: "1.17"
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+   configuration: docs/source/conf.py
+
+#If using Sphinx, optionally build your docs in additional formats such as PDF
+formats:
+   - pdf
+
+#Optionally declare the Python requirements required to build your docs
+python:
+   install:
+   - requirements: requirements.txt

.travis.yml

@@ -1,13 +0,0 @@
-dist: xenial
-language: python
-python:
-    - "3.6"
-    - "3.5"
-script:
-    - "python3 setup.py test"
-before_install:
-    - "sudo apt-get update"
-    - "sudo add-apt-repository universe"
-    - "sudo apt-get install -y ffmpeg" 
-install:
-    - "pip3 install setuptools"

CONTRIBUTING.md

@@ -0,0 +1,15 @@
+# Contributing
+
+Contributions to this project are very welcome!
+
+If you discover a bug or would like better support for a feature, please do the following:
+
+1. Submit an Issue.
+
+   I'm actively developing this project and will review incoming issues.
+1. Check out the source code and submit a PR.
+   
+   If you're facile with Python and understand what you'd like to fix, submit a PR and I'll 
+   review it as soon as I can. There's a `.devcontainer` available so you can creates commits 
+   on this project in a GitHub codespace.
+   

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2018 Jamie Hardt
+Copyright (c) 2022 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

@@ -1,35 +1,38 @@
-[![Build Status](https://travis-ci.com/iluvcapra/wavinfo.svg?branch=master)](https://travis-ci.com/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)
-
+[![Lint and Test](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml/badge.svg)](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml)
 
 # wavinfo
 
+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.
 
-The `wavinfo` package allows you to probe WAVE files and extract extended metadata, with an emphasis on 
-production metadata. 
+
+## Metadata Support
 
 `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__][ebu] metadata, including embedded program
+  loudness, coding history and [__SMPTE UMID__][smpte_330m2011].
+* [__ADM__][adm] track metadata and schema, including channel, pack formats, object, content and programme.
+* [__Dolby Digital Plus__][ebu3285s6] and Dolby Atmos `dbmd` metadata.
+* [__iXML__][ixml] production recorder metadata, 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__][info-tags] metadata fields.
+* The __wav format__ is also parsed, so you can access the basic sample rate and channel count
   information.
 
 In progress:
-* iXML `STEINBERG` sound library attributes.
 * Pro Tools __embedded regions__.
+* iXML `STEINBERG` sound library attributes.
 
 [ebu]:https://tech.ebu.ch/docs/tech/tech3285.pdf
+[ebu3285s6]:https://tech.ebu.ch/docs/tech/tech3285s6.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
+## How To Use
 
 The entry point for wavinfo is the WavInfoReader class.
 
@@ -39,117 +42,17 @@ from wavinfo import WavInfoReader
 path = '../tests/test_files/A101_1.WAV'
 
 info = WavInfoReader(path)
+
+adm_metadata = info.adm
+ixml_metadata = info.ixml
 ```
 
-### Basic WAV Data
+The package also installs a shell command:
 
-The length of the file in frames (interleaved samples) and bytes is available, as is the contents of the format chunk.
-
-```python
-(info.data.frame_count, info.data.byte_count)
->>> (240239, 1441434)
-(info.fmt.sample_rate, info.fmt.channel_count, info.fmt.block_align, info.fmt.bits_per_sample)
->>> (48000, 2, 6, 24)
+```sh
+$ wavinfo test_files/A101_1.WAV
 ```
 
-### Broadcast WAV Extension
-
-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)
-
+## Other Resources
 
+* For other file formats and ID3 decoding, look at [audio-metadata](https://github.com/thebigmunch/audio-metadata).

docs/Makefile

@@ -0,0 +1,19 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/requirements.txt

@@ -0,0 +1,25 @@
+alabaster==0.7.12
+Babel==2.11.0
+certifi==2022.9.24
+charset-normalizer==2.1.1
+docutils==0.17.1
+idna==3.4
+imagesize==1.4.1
+Jinja2==3.1.2
+lxml==4.9.1
+MarkupSafe==2.1.1
+packaging==21.3
+Pygments==2.13.0
+pyparsing==3.0.9
+pytz==2022.6
+requests==2.28.1
+snowballstemmer==2.2.0
+Sphinx==5.3.0
+sphinx-rtd-theme==1.1.1
+sphinxcontrib-applehelp==1.0.2
+sphinxcontrib-devhelp==1.0.2
+sphinxcontrib-htmlhelp==2.0.0
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-qthelp==1.0.3
+sphinxcontrib-serializinghtml==1.1.5
+urllib3==1.26.12

docs/source/classes.rst

@@ -0,0 +1,10 @@
+Other wavinfo Classes
+=====================
+
+
+.. autoclass:: wavinfo.wave_reader.WavAudioFormat
+   :members:
+
+.. autoclass:: wavinfo.wave_reader.WavDataDescriptor
+   :members:
+

docs/source/command_line.rst

@@ -0,0 +1,94 @@
+Using `wavinfo` from the Command Line
+=====================================
+
+`wavinfo` installs a command-line entry point that will read wav files
+from the command line and output metadata to stdout.
+
+.. code-block:: shell
+
+    $ wavinfo [--ixml | --adm] INFILE +
+
+By default, `wavinfo` will output a JSON dictionary for each file argument.
+
+
+Options
+-------
+
+Two option flags will change the behavior of the command:
+
+``--ixml``
+    The *\-\-ixml* flag will cause `wavinfo` to output the iXML metadata payload
+    of each input wave file, or will emit an error message to stderr if iXML 
+    metadata is not present.
+
+``--adm``
+    The *\-\-adm* flag will cause `wavinfo` to output the ADM XML metadata 
+    payload of each input wave file, or will emit an error message to stderr if
+    ADM XML metadata is not present.
+
+These options are mutually-exclusive, with `\-\-adm` taking precedence. 
+
+
+Example Output
+--------------
+
+.. code-block:: javascript
+
+    {
+    "filename": "tests/test_files/sounddevices/A101_1.WAV",
+    "run_date": "2022-11-26T17:56:38.342935",
+    "application": "wavinfo 2.1.0",
+    "scopes": {
+        "fmt": {
+        "audio_format": 1,
+        "channel_count": 2,
+        "sample_rate": 48000,
+        "byte_rate": 288000,
+        "block_align": 6,
+        "bits_per_sample": 24
+        },
+        "data": {
+        "byte_count": 1441434,
+        "frame_count": 240239
+        },
+        "ixml": {
+        "track_list": [
+            {
+            "channel_index": "1",
+            "interleave_index": "1",
+            "name": "MKH516 A",
+            "function": ""
+            },
+            {
+            "channel_index": "2",
+            "interleave_index": "2",
+            "name": "Boom",
+            "function": ""
+            }
+        ],
+        "project": "BMH",
+        "scene": "A101",
+        "take": "1",
+        "tape": "18Y12M31",
+        "family_uid": "USSDVGR1112089007124001008206300",
+        "family_name": null
+        },
+        "bext": {
+        "description": "sSPEED=023.976-ND\r\nsTAKE=1\r\nsUBITS=$12311801\r\nsSWVER=2.67\r\nsPROJECT=BMH\r\nsSCENE=A101\r\nsFILENAME=A101_1.WAV\r\nsTAPE=18Y12M31\r\nsTRK1=MKH516 A\r\nsTRK2=Boom\r\nsNOTE=\r\n",
+        "originator": "Sound Dev: 702T S#GR1112089007",
+        "originator_ref": "USSDVGR1112089007124001008206301",
+        "originator_date": "2018-12-31",
+        "originator_time": "12:40:00",
+        "time_reference": 2190940753,
+        "version": 1,
+        "umid": "0000000000000000000000000000000000000000000000000000000000000000",
+        "coding_history": "A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch\r\n",
+        "loudness_value": null,
+        "loudness_range": null,
+        "max_true_peak": null,
+        "max_momentary_loudness": null,
+        "max_shortterm_loudness": null
+        }
+    }
+    }
+

docs/source/conf.py

@@ -0,0 +1,187 @@
+# -*- coding: utf-8 -*-
+#
+# Configuration file for the Sphinx documentation builder.
+#
+# This file does only contain a selection of the most common options. For a
+# full list see the documentation:
+# http://www.sphinx-doc.org/en/master/config
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+sys.path.insert(0, os.path.abspath('../..'))
+sys.path.insert(0, os.path.abspath("../../.."))
+print(sys.path)
+
+import wavinfo
+
+# -- Project information -----------------------------------------------------
+
+project = u'wavinfo'
+copyright = u'2022, Jamie Hardt'
+author = u'Jamie Hardt'
+
+# The short X.Y version
+version = wavinfo.__version__
+# The full version, including alpha/beta/rc tags
+release = wavinfo.__version__
+
+
+# -- General configuration ---------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.autodoc',
+    'sphinx.ext.todo',
+    'sphinx.ext.coverage',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = 'en'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = [u'_build', 'Thumbs.db', '.DS_Store']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = None
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_rtd_theme'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# Custom sidebar templates, must be a dictionary that maps document names
+# to template names.
+#
+# The default sidebars (for documents that don't match any pattern) are
+# defined by theme itself.  Builtin themes are using these templates by
+# default: ``['localtoc.html', 'relations.html', 'sourcelink.html',
+# 'searchbox.html']``.
+#
+# html_sidebars = {}
+
+
+# -- Options for HTMLHelp output ---------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'wavinfodoc'
+
+
+# -- Options for LaTeX output ------------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'wavinfo.tex', u'wavinfo Documentation',
+     u'Jamie Hardt', 'manual'),
+]
+
+
+# -- Options for manual page output ------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'wavinfo', u'wavinfo Documentation',
+     [author], 1)
+]
+
+
+# -- Options for Texinfo output ----------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'wavinfo', u'wavinfo Documentation',
+     author, 'wavinfo', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+# -- Options for Epub output -------------------------------------------------
+
+# Bibliographic Dublin Core info.
+epub_title = project
+
+# The unique identifier of the text. This can be a ISBN number
+# or the project homepage.
+#
+# epub_identifier = ''
+
+# A unique identification for the text.
+#
+# epub_uid = ''
+
+# A list of files that should not be packed into the epub file.
+epub_exclude_files = ['search.html']
+
+
+# -- Extension configuration -------------------------------------------------
+
+# -- Options for todo extension ----------------------------------------------
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = True

docs/source/index.rst

@@ -0,0 +1,31 @@
+.. wavinfo documentation master file, created by
+   sphinx-quickstart on Thu Jan  3 17:09:28 2019.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to wavinfo's documentation!
+===================================
+
+The `wavinfo` package allows you to probe WAVE and RF64/WAVE files and 
+extract extended metadata, with an emphasis on film, video and professional 
+music production metadata.
+
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+   :numbered:
+   
+   quickstart
+   command_line
+   scopes/*
+
+   classes
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

docs/source/quickstart.rst

@@ -0,0 +1,24 @@
+wavinfo Quickstart
+====================
+
+All metadata is read by an instance of :class:`WaveInfoReader<wavinfo.wave_reader.WavInfoReader>`.
+Each type of metadata, iXML, Broadcast-WAV etc. is accessible through *scopes*, properties on an 
+instance of :class:`WaveInfoReader`. 
+
+
+.. code-block:: python
+    :caption: Using wavinfo
+
+    import wavinfo
+
+    path = 'path/to/your/wave/audio.wav'
+
+    info = wavinfo.WavInfoReader(path)
+
+
+.. module:: wavinfo
+    :noindex:
+
+.. autoclass:: wavinfo.wave_reader.WavInfoReader
+   :members:
+

docs/source/scopes/adm.rst

@@ -0,0 +1,30 @@
+ADM (Audio Definition Model) Metadata
+=====================================
+
+Notes
+-----
+
+`ADM metadata`_ is used in master recordings to describe the format and content 
+of the tracks. In practice on wave files, ADM tells a client which tracks are 
+members of multichannel stems or "beds" and their speaker assignment, and which 
+tracks are freely-positioned 3D objects. ADM also records the panning moves on
+object tracks and their content group ("Dialogue", "Music", "Effects" etc.)
+
+ADM wave files created with a Dolby Rendering and Mastering Unit are a common 
+deliverable in feature film and television production. The `Dolby Atmos ADM Profile`_ 
+describes how the RMU translates its native Master format into ADM. 
+ 
+
+.. _ADM metadata: https://adm.ebu.io
+.. _Dolby Atmos ADM Profile: https://developer.dolby.com/globalassets/documentation/technology/dolby_atmos_master_adm_profile_v1.0.pdf
+
+Class Reference
+---------------
+
+.. module:: wavinfo
+
+.. autoclass:: wavinfo.wave_adm_reader.WavADMReader
+    :members:
+
+.. autoclass:: wavinfo.wave_adm_reader.ChannelEntry
+    :members:

docs/source/scopes/bext.rst

@@ -0,0 +1,75 @@
+Broadcast WAV Extension Metadata
+================================
+
+
+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 :py:attr:`coding_history<wavinfo.wave_bext_reader.WavBextReader.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 :py:attr:`description<wavinfo.wave_bext_reader.WavBextReader.description>`. 
+Here also the :py:attr:`originator_ref<wavinfo.wave_bext_reader.WavBextReader.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 
+ST 330 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`_.
+
+.. _EBU 3285 v1: https://tech.ebu.ch/publications/tech3285s1
+.. _SMPTE ST 330 UMID: https://standards.globalspec.com/std/1396751/smpte-st-330
+.. _EBU 3285 v2: https://tech.ebu.ch/publications/tech3285s2
+.. _EBU Rec 128: https://tech.ebu.ch/publications/r128
+
+..  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
+
+
+Class Reference
+---------------
+
+.. autoclass:: wavinfo.wave_bext_reader.WavBextReader
+   :members:
+
+

docs/source/scopes/dolby.rst

@@ -0,0 +1,21 @@
+Dolby Metadata
+==============
+
+Notes
+-----
+
+Dolby software and equipment creates detailed hinting metadata that can help
+receiving applications decide how to present the audio content, particularly
+how it should be downmixed, and dialogue normalization settings. 
+
+
+Class Reference
+---------------
+
+.. automodule:: wavinfo.wave_dbmd_reader
+
+.. autoclass:: wavinfo.wave_dbmd_reader.WavDolbyMetadataReader
+    :members:
+
+.. autoclass:: wavinfo.wave_dbmd_reader.DolbyDigitalPlusMetadata
+    :members:

docs/source/scopes/info.rst

@@ -0,0 +1,42 @@
+INFO Metadata
+=============
+
+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)
+
+
+On Encodings
+""""""""""""
+According to Microsoft, the original developers of the RIFF file and RIFF INFO 
+metadata, these fields are always to be interpreted as ISO Latin 1 characters, 
+and this is the default encoding used by `wavinfo` for these fields. You can
+select a different encoding (like Shift-JIS) by passing an encoding name (as 
+would be used by `string.encode()`) to `WavInfoReader.__init__()`'s
+`info_encoding=` parameter.
+ 
+
+
+Class Reference
+---------------
+
+.. autoclass:: wavinfo.wave_info_reader.WavInfoChunkReader
+   :members:
+
+
+
+

docs/source/scopes/ixml.rst

@@ -0,0 +1,43 @@
+iXML Production Recorder Metadata
+=================================
+
+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
+
+
+Class Reference
+---------------
+
+.. autoclass:: wavinfo.wave_ixml_reader.WavIXMLFormat
+   :members:
+
+

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 @@
+lxml==4.9.1

setup.py

@@ -1,20 +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='1.0',
-      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 :: 3.8",
+          "Programming Language :: Python :: 3.9",
+          "Programming Language :: Python :: 3.10",
+          "Programming Language :: Python :: 3.11"],
+      keywords='waveform metadata audio ebu smpte avi library film tv editing editorial',
+      install_requires=['lxml'],
+      entry_points={
+          'console_scripts': [
+              'wavinfo = wavinfo.__main__:main'
+          ]
+      }
+      )

tests/__init__.py

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

tests/test_adm.py

@@ -0,0 +1,51 @@
+from unittest import TestCase
+
+import wavinfo
+
+class TestADMWave(TestCase):
+
+    def setUp(self) -> None:
+        self.protools_adm_wav = "tests/test_files/protools/Test_ADM_ProTools.wav"
+        return super().setUp()
+
+    def test_chna(self):
+        info = wavinfo.WavInfoReader(self.protools_adm_wav)
+        self.assertIsNotNone(info)
+
+        adm = info.adm
+        self.assertIsNotNone(adm)
+
+        self.assertEqual(len(adm.channel_uids), 14)
+
+    def test_to_dict(self):
+        info = wavinfo.WavInfoReader(self.protools_adm_wav)
+        adm = info.adm
+        dict = adm.to_dict()
+        self.assertIsNotNone(dict)
+    
+    def test_programme(self):
+        info = wavinfo.WavInfoReader(self.protools_adm_wav)
+        adm = info.adm
+        pdict = adm.programme()
+        self.assertIn("programme_id", pdict.keys())
+        self.assertIn("programme_name", pdict.keys())
+        self.assertEqual(pdict['programme_id'], 'APR_1001')
+        self.assertEqual(pdict['programme_name'], 'Atmos_Master')
+        self.assertIn("contents", pdict.keys())
+        self.assertEqual(len(pdict["contents"]), 3)
+
+    def test_track_info(self):
+        info = wavinfo.WavInfoReader(self.protools_adm_wav)
+        adm = info.adm
+
+        t1 = adm.track_info(0)
+        self.assertTrue("channel_format_name" in t1.keys())
+        self.assertEqual("RoomCentricLeft", t1["channel_format_name"])
+
+        self.assertTrue("pack_format_name" in t1.keys())
+        self.assertEqual("AtmosCustomPackFormat1", t1["pack_format_name"])
+
+        t10 = adm.track_info(10)
+        self.assertTrue("content_name" in t10.keys())
+        self.assertEqual("Dialog", t10["content_name"])
+        

tests/test_dolby.py

@@ -0,0 +1,49 @@
+from unittest import TestCase
+
+import wavinfo
+from wavinfo.wave_dbmd_reader import SegmentType, DolbyAtmosMetadata, DolbyDigitalPlusMetadata
+
+class TestDolby(TestCase):
+    def setUp(self):
+        self.test_file = "tests/test_files/protools/Test_ADM_ProTools.wav"
+
+    def test_version(self):
+        t1 = wavinfo.WavInfoReader(self.test_file)
+        d = t1.dolby
+
+        self.assertEqual((1,0,0,6), d.version)
+
+    def test_segments(self):
+        t1 = wavinfo.WavInfoReader(self.test_file)
+        d = t1.dolby
+
+        ddp = [x for x in d.segment_list if x[0] == SegmentType.DolbyDigitalPlus]
+        atmos = [x for x in d.segment_list if x[0] == SegmentType.DolbyAtmos]
+
+        self.assertEqual(len(ddp), 1)
+        self.assertEqual(len(atmos), 1)
+
+    def test_checksums(self):
+        t1 = wavinfo.WavInfoReader(self.test_file)
+        d = t1.dolby
+
+        for seg in d.segment_list:
+            self.assertTrue(seg[1])
+
+    def test_ddp(self):
+        t1 = wavinfo.WavInfoReader(self.test_file)
+        d = t1.dolby
+
+        ddp = d.dolby_digital_plus()
+        self.assertEqual(len(ddp), 1, "Failed to find exactly one Dolby Digital Plus metadata segment")
+        self.assertTrue( ddp[0].audio_coding_mode, DolbyDigitalPlusMetadata.AudioCodingMode.CH_ORD_3_2 )
+        self.assertTrue( ddp[0].lfe_on)
+        
+    def test_atmos(self):
+        t1 = wavinfo.WavInfoReader(self.test_file)
+        d = t1.dolby
+
+        atmos = d.dolby_atmos()
+        self.assertEqual(len(atmos), 1, "Failed to find exactly one Atmos metadata segment")
+
+    

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 +1,113 @@
 import os.path
-import json
-import subprocess
-from subprocess import PIPE
 
 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({}, latin_1, ascii)'.format(os.path.abspath(wav_file)))
+            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_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_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:
+                if 'comment' in ffprobe_info['format']['tags']:
+                    self.assertEqual(info.bext.description, ffprobe_info['format']['tags']['comment'])
+                else:
+                    self.assertEqual(info.bext.description, '')
 
-            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']  )
-            else:
-                self.assertEqual( info.bext.originator_ref, '')
+                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, '')
 
-            # 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'])  )
+                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, '')
 
-            if 'coding_history' in ffprobe_info['format']['tags']:
-                self.assertEqual( info.bext.coding_history, ffprobe_info['format']['tags']['coding_history']  )
-            else:
-                self.assertEqual( info.bext.coding_history, '' )
+                # 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']))
+
+                if 'coding_history' in ffprobe_info['format']['tags']:
+                    self.assertEqual(info.bext.coding_history, ffprobe_info['format']['tags']['coding_history'])
+                else:
+                    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

@@ -1,4 +1,12 @@
-from .wave_reader import WavInfoReader
+"""
+methods to probe a WAV file for various kinds of production metadata.
 
-__version__ = 1.0
-__author__ = 'Jamie Hardt'
+See the documentation for `wavinfo.WavInfoReader` for more information.
+"""
+
+from .wave_reader import WavInfoReader
+from .riff_parser import WavInfoEOFError
+
+__version__ = '2.1.0'
+__author__ = 'Jamie Hardt <jamiehardt@gmail.com>'
+__license__ = "MIT"

wavinfo/__main__.py

@@ -0,0 +1,70 @@
+from optparse import OptionParser, OptionGroup
+import datetime
+from . import WavInfoReader
+from . import __version__
+import sys
+import json
+from enum import Enum
+
+class MyJSONEncoder(json.JSONEncoder):
+    def default(self, o):
+        if isinstance(o, Enum):
+            return o._name_
+        else:
+            return super().default(o)
+
+class MissingDataError(RuntimeError):
+    pass
+
+def main():
+    parser = OptionParser()
+
+    parser.usage = 'wavinfo (--adm | --ixml) [FILES]'
+
+    # parser.add_option('-f', dest='output_format', help='Set the output format',
+    #                   default='json',
+    #                   metavar='FORMAT')
+
+    parser.add_option('--adm', dest='adm', help='Output ADM XML', 
+        default=False, action='store_true')
+
+    parser.add_option('--ixml', dest='ixml', help='Output iXML',
+        default=False, action='store_true')
+
+    (options, args) = parser.parse_args(sys.argv)
+    for arg in args[1:]:
+        try:
+            this_file = WavInfoReader(path=arg)
+            if options.adm:
+                if this_file.adm:
+                    sys.stdout.write(this_file.adm.xml_str())
+                else:
+                    raise MissingDataError("adm")
+            elif options.ixml:
+                if this_file.ixml:
+                    sys.stdout.write(this_file.ixml.xml_bytes())
+                else:
+                    raise MissingDataError("ixml")
+            else:
+                ret_dict = {
+                    'filename': arg, 
+                    'run_date': datetime.datetime.now().isoformat() , 
+                    'application': "wavinfo " + __version__, 
+                    '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, cls=MyJSONEncoder, fp=sys.stdout, indent=2)
+        except MissingDataError as e:
+            print("MissingDataError: Missing metadata (%s) in file %s" % (e, arg), file=sys.stderr)
+            continue
+        except Exception as e:
+            raise e
+
+
+if __name__ == "__main__":
+    main()

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

@@ -1,59 +1,73 @@
 
 import struct
-
 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:
-        children.append(parse_chunk(stream))
+    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):
+
+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 +1,121 @@
+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: bytes):
+        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_adm_reader.py

@@ -0,0 +1,165 @@
+"""
+ADM Reader
+"""
+
+from struct import unpack, unpack_from, calcsize
+from io import BytesIO
+from collections import namedtuple
+from typing import Iterable, Tuple
+
+from lxml import etree as ET
+
+ChannelEntry = namedtuple('ChannelEntry', "track_index uid track_ref pack_ref")
+
+class WavADMReader:
+    """
+    Reads XML data from an EBU ADM (Audio Definiton Model) WAV File.
+
+    """
+
+    def __init__(self, axml_data: bytes, chna_data: bytes):
+        header_fmt = "<HH"
+        uid_fmt = "<H12s14s11sx"
+
+        #: An :mod:`lxml.etree` of the ADM XML document
+        self.axml = ET.parse(BytesIO(axml_data))
+
+        _, uid_count = unpack(header_fmt, chna_data[0:4])
+
+        #: A list of :class:`ChannelEntry` objects parsed from the
+        #: `chna` metadata chunk.
+        #:
+        #: .. note::
+        #:    In-file, the `chna` track indexes start at 1. However, this interface
+        #:    numbers the first track 0, in order to maintain consistency with other
+        #:    libraries.
+        self.channel_uids = []
+
+        offset = calcsize(header_fmt)
+        for _ in range(uid_count):
+
+            track_index, uid, track_ref, pack_ref = unpack_from(uid_fmt, chna_data, offset)
+
+            # these values are either ascii or all null
+
+            self.channel_uids.append(ChannelEntry(track_index - 1,
+                uid.decode('ascii') , track_ref.decode('ascii'), pack_ref.decode('ascii')))
+
+            offset += calcsize(uid_fmt)
+
+    def xml_str(self) -> str:
+        """ADM XML as a string"""
+        return ET.tostring(self.axml).decode("utf-8")
+
+    def programme(self) -> dict:
+        """
+        Extract the ADM audioProgramme data structure and some of its reference properties 
+        """
+        ret_dict = dict()
+
+        nsmap = self.axml.getroot().nsmap 
+        
+        afext = self.axml.find(".//audioFormatExtended", namespaces=nsmap)
+
+        program = afext.find("audioProgramme", namespaces=nsmap)
+        ret_dict['programme_id'] = program.get("audioProgrammeID")
+        ret_dict['programme_name'] = program.get("audioProgrammeName")
+        ret_dict['programme_start'] = program.get("start")
+        ret_dict['programme_end'] = program.get("end")
+        ret_dict['contents'] = []
+
+        for content_ref in program.findall("audioContentIDRef", namespaces=nsmap):
+            content_dict = dict()
+            content_dict['content_id'] = cid = content_ref.text
+            content = afext.find("audioContent[@audioContentID='%s']" % cid, namespaces=nsmap)
+            content_dict['content_name'] = content.get("audioContentName")
+            content_dict['objects'] = []
+
+            for object_ref in content.findall("audioObjectIDRef", namespaces=nsmap):
+                object_dict = dict()
+                object_dict['object_id'] = oid = object_ref.text
+                object = afext.find("audioObject[@audioObjectID='%s']" % oid, namespaces=nsmap)
+                pack = object.find("audioPackFormatIDRef", namespaces=nsmap)
+                object_dict['object_name'] = object.get("audioObjectName")
+                object_dict['object_start'] = object.get("start")
+                object_dict['object_duration'] = object.get("duration")
+                object_dict['pack_id'] = pack.text
+                track_uid_list = []
+                for t in object.findall("audioTrackUIDRef", namespaces=nsmap):
+                    track_uid_list.append(t.text)
+
+                object_dict['track_uids'] = track_uid_list
+                content_dict['objects'].append(object_dict)
+
+            ret_dict['contents'].append(content_dict)
+
+        return ret_dict
+
+    def track_info(self, index):
+        """
+        Information about a track in the WAV file.
+
+        :param index: index of audio track (indexed from zero) 
+        :returns: a dictionary with *content_name*, *content_id*, *object_name*, *object_id*, 
+            *pack_format_name*, *pack_type*, *channel_format_name*
+        """
+        channel_info = next((x for x in self.channel_uids if x.track_index == index), None)
+        
+        if channel_info is None:
+            return None
+
+        ret_dict = {}
+
+        nsmap = self.axml.getroot().nsmap
+
+        afext = self.axml.find(".//audioFormatExtended", namespaces=nsmap)
+
+        trackformat_elem = afext.find("audioTrackFormat[@audioTrackFormatID='%s']" % channel_info.track_ref, 
+            namespaces=nsmap)
+
+        stream_id = trackformat_elem[0].text
+
+        channelformatref_elem = afext.find("audioStreamFormat[@audioStreamFormatID='%s']/audioChannelFormatIDRef" % stream_id, 
+            namespaces=nsmap)
+        channelformat_id = channelformatref_elem.text
+
+        packformatref_elem = afext.find("audioStreamFormat[@audioStreamFormatID='%s']/audioPackFormatIDRef" % stream_id, 
+            namespaces=nsmap)
+        packformat_id = packformatref_elem.text
+
+        channelformat_elem = afext.find("audioChannelFormat[@audioChannelFormatID='%s']" % channelformat_id, 
+            namespaces=nsmap)
+        ret_dict['channel_format_name'] = channelformat_elem.get("audioChannelFormatName")
+
+        packformat_elem = afext.find("audioPackFormat[@audioPackFormatID='%s']" % packformat_id, 
+            namespaces=nsmap)
+        ret_dict['pack_type'] = packformat_elem.get("typeDefinition")
+        ret_dict['pack_format_name'] = packformat_elem.get("audioPackFormatName")
+
+        object_elem = afext.find("audioObject[audioPackFormatIDRef = '%s']" % packformat_id, 
+            namespaces=nsmap)
+
+        ret_dict['audio_object_name'] = object_elem.get("audioObjectName")
+        object_id = object_elem.get("audioObjectID")
+        ret_dict['object_id'] = object_id
+
+        content_elem = afext.find("audioContent/[audioObjectIDRef = '%s']" % object_id, 
+            namespaces=nsmap)
+
+        ret_dict['content_name'] = content_elem.get("audioContentName")
+        ret_dict['content_id'] = content_elem.get("audioContentID")
+
+        return ret_dict
+
+    def to_dict(self):
+        """
+        Get ADM metadata as a dictionary.
+        """
+
+        def make_entry(channel_uid_rec):
+            rd = channel_uid_rec._asdict()
+            rd.update(self.track_info(channel_uid_rec.track_index))
+            return rd
+
+        return dict(channel_entries=list(map(lambda z: make_entry(z), self.channel_uids)),
+            programme=self.programme())

wavinfo/wave_bext_reader.py

@@ -1,86 +1,90 @@
 import struct
+from .umid_parser import UMIDParser
+
+from typing import Optional
 
 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 []
-        if bext_data is None:
-            return None
-
-        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 : bytes) -> str:
+            # honestly can't remember why I'm stripping nulls this way
+            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 : str = sanitize_bytes(unpacked[0])
+        #: Originator. Usually the name of the encoding application, sometimes
+        #: a artist name.
+        self.originator : str = sanitize_bytes(unpacked[1])
+        #: A unique identifier for the file, a serial number.
+        self.originator_ref : str = sanitize_bytes(unpacked[2])
+        #: Date of the recording, in the format YYYY-MM-DD in the local calendar
+        self.originator_date : str = sanitize_bytes(unpacked[3])
+        #: Time of the recording, in the format HH:MM:SS on the local clock
+        self.originator_time : str = 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 : int  = unpacked[5]
+        #: A variable-length text field containing a list of processes and
+        #: and conversions performed on the file.
+        self.coding_history : str = sanitize_bytes(bext_data[rest_starts:])
+        #: BEXT version. 
+        self.version : int = unpacked[6]
+        #: SMPTE 330M UMID of this audio file, 64 bytes are allocated though the UMID
+        #: may only be 32 bytes long.
+        self.umid : Optional[bytes] = None
+        #: EBU R128 Integrated loudness, in LUFS.
+        self.loudness_value : Optional[float] = None
+        #: EBU R128 Loudness rante, in LUFS.
+        self.loudness_range : Optional[float] = None
+        #: True peak level, in dBFS TP
+        self.max_true_peak : Optional[float] = None
+        #: EBU R128 Maximum momentary loudness, in LUFS
+        self.max_momentary_loudness : Optional[float] = None
+        #: EBU R128 Maximum short-term loudness, in LUFS.
+        self.max_shortterm_loudness : Optional[float] = 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_dbmd_reader.py

@@ -0,0 +1,661 @@
+"""
+Reading Dolby Bitstream Metadata
+
+Unless otherwise stated, all § references here are to 
+`EBU Tech 3285 Supplement 6`_.
+
+.. _EBU Tech 3285 Supplement 6: https://tech.ebu.ch/docs/tech/tech3285s6.pdf
+"""
+
+from enum import IntEnum, Enum
+from struct import unpack
+from dataclasses import dataclass, asdict
+from typing import List, Optional, Tuple, Any, Union
+
+from io import BytesIO
+
+class SegmentType(IntEnum):
+    """
+    Metadata segment type.
+    """
+    EndMarker = 0x0
+    DolbyE = 0x1
+    # Reserved2 = 0x2
+    DolbyDigital = 0x3
+    # Reserved4 = 0x4
+    # Reserved5 = 0x5
+    # Reserved6 = 0x6
+    DolbyDigitalPlus = 0x7
+    AudioInfo = 0x8
+    DolbyAtmos = 0x9
+    DolbyAtmosSupplemental = 0xa
+
+    @classmethod
+    def _missing_(cls,val):
+        return val
+
+
+@dataclass
+class DolbyDigitalPlusMetadata:
+    """
+    *Dolby Digital Plus* is Dolby's brand for multichannel surround
+    on discrete formats that aren't AC-3 (Dolby Digital) or Dolby E. This 
+    metadata segment is present in ADM wave files created with a Dolby Atmos 
+    Production Suite.
+
+    Where an AC-3 bitstream can contain multiple programs, a Dolby Digital 
+    Plus bitstream will only contain one program.
+    """
+
+    class DownMixLevelToken(Enum):
+        """
+        A gain coefficient used in several metadata fields for downmix
+        scenarios.
+        """
+
+        PLUS_3DB = 0b000
+        "+3 dB"
+
+        PLUS_1_5DB = 0b001
+        "+1.5 dB"
+
+        UNITY = 0b010
+        "0dB"
+
+        MINUS_1_5DB = 0b011
+        "-1.5 dB"
+
+        MINUS_3DB = 0b100
+        "-3 dB"
+
+        MINUS_4_5DB = 0b101
+        "-4.5 dB"
+
+        MINUS_6DB = 0b110
+        "-6 dB"
+
+        MUTE = 0b111
+        "-∞ dB"
+
+
+    class DolbySurroundEncodingMode(Enum):
+        """
+        Dolby surround endcoding mode.
+        """
+        RESERVED = 0b11
+        IN_USE = 0b10
+        NOT_IN_USE = 0b01
+        NOT_INDICATED = 0b00
+
+
+    class BitStreamMode(Enum):
+        """
+        Dolby Digital Plus `bsmod` field
+        § 4.3.2.2
+        """
+
+        COMPLETE_MAIN = 0b000
+        "main audio service: complete main"
+
+        MUSIC_AND_EFFECTS = 0b001
+        "main audio service: music and effects"
+
+        VISUALLY_IMPAIRED = 0b010
+        "associated service: visually impaired"
+
+        HEARING_IMPAIRED = 0b011
+        "associated service: hearing impaired"
+
+        DIALOGUE_ONLY = 0b100
+        "associated service: dialogue"
+
+        COMMENTARY = 0b101
+        "associated service: commentary"
+
+        EMERGENCY = 0b110
+        "associated service: emergency"
+
+        VOICEOVER_KARAOKE = 0b111
+        """
+        associated service: voice over *OR* main audio service: karaoke.
+        If `acmod` is `0b001` (mono 1/0), this is voice-over, otherwise it
+        should be interpreted as karaoke.
+        """
+
+
+    class AudioCodingMode(Enum):
+        """
+        Dolby Digital Plus `acmod` field
+        § 4.3.2.3
+        """
+        RESERVED = 0b000
+        CH_ORD_1_0 = 0b001
+        "Mono"
+        CH_ORD_2_0 = 0b010
+        "L/R stereo"
+        CH_ORD_3_0 = 0b011
+        "LCR stereo"
+        CH_ORD_2_1 = 0b100
+        "LR + mono surround"
+        CH_ORD_3_1 = 0b101
+        "LCR + mono surround"
+        CH_ORD_2_2 = 0b110
+        "LR + LR surround"
+        CH_ORD_3_2 = 0b111
+        "LCR + LR surround"
+
+
+    class CenterDownMixLevel(Enum):
+        """
+        § 4.3.3.1
+        """
+
+        DOWN_3DB = 0b00
+        "Attenuate 3 dB"
+    
+        DOWN_45DB = 0b01
+        "Attenuate 4.5 dB"
+        
+        DOWN_6DB = 0b10
+        "Attenuate 6 dB"
+
+        RESERVED = 0b11
+
+
+    class SurroundDownMixLevel(Enum):
+        """
+        Dolby Digital Plus `surmixlev` field
+        § 4.3.3.2
+        """
+        DOWN_3DB = 0b00
+        DOWN_6DB = 0b01
+        MUTE = 0b10
+        RESERVED = 0b11
+
+
+    class LanguageCode(int):
+        """
+        § 4.3.4.1
+
+        Per ATSC/A52 § 5.4.2.12, this is not in use and always 0xFF.
+        """
+        pass
+
+
+    class MixLevel(int):
+        """
+        § 4.3.6.2
+        """
+        pass
+
+
+    class DialnormLevel(int):
+        """
+        § 4.3.4.4
+        """
+        pass
+
+
+    class RoomType(Enum):
+        """
+        `roomtyp` 4.3.6.3
+        """
+        NOT_INDICATED = 0b00
+        LARGE_ROOM_X_CURVE = 0b01
+        SMALL_ROOM_FLAT_CURVE = 0b10
+        RESERVED = 0b11
+
+
+    class PreferredDownMixMode(Enum):
+        """
+        Indicates the creating engineer's preference of what the receiver should
+        downmix.
+        § 4.3.8.1
+        """
+        NOT_INDICATED = 0b00
+        PRO_LOGIC = 0b01
+        STEREO = 0b10
+        PRO_LOGIC_2 = 0b11
+
+
+    class SurroundEXMode(IntEnum):
+        """
+        Dolby Surround-EX mode.
+        `dsurexmod` § 4.3.9.1
+        """
+        NOT_INDICATED = 0b00
+        NOT_SEX = 0b01
+        SEX = 0b10
+        PRO_LOGIC_2 = 0b11
+
+
+    class HeadphoneMode(IntEnum):
+        """
+        `dheadphonmod` § 4.3.9.2
+        """
+        NOT_INDICATED = 0b00
+        NOT_DOLBY_HEADPHONE = 0b01
+        DOLBY_HEADPHONE = 0b10
+        RESERVED = 0b11
+
+
+    class ADConverterType(Enum):
+        STANDARD = 0
+        HDCD = 1
+
+
+    class StreamDependency(Enum):
+        """
+        Encodes `ddplus_info1.stream_type` field § 4.3.12.1
+        """
+
+        INDEPENDENT = 0
+        DEPENDENT = 1
+        INDEPENDENT_FROM_DOLBY_DIGITAL = 2
+        RESERVED = 3
+
+
+    class RFCompressionProfile(Enum):
+        """
+        `compr1` RF compression profile
+        § 4.3.10 (fig 42)
+        """
+        NONE = 0
+        FILM_STANDARD = 1
+        FILM_LIGHT = 2
+        MUSIC_STANDARD = 3
+        MUSIC_LIGHT = 4
+        SPEECH = 5
+
+    #: Program ID number, this identifies the program in a multi-program 
+    #: element. § 4.3.1
+    program_id: int
+
+    #: `True` if LFE is enabled. § 4.3.2.1
+    lfe_on: bool
+
+    #: The kind of service of this stream. `bsmod` § 4.3.2.2
+    bitstream_mode: BitStreamMode
+
+    #: Indicates which channels are in use. `acmod` § 4.3.2.3
+    audio_coding_mode: AudioCodingMode
+
+    #: When the front three channels are in use, gives the center
+    #: downmix level. ``
+    center_downmix_level: CenterDownMixLevel
+
+    #: When the surround channels are in use, gives the surround
+    #: downmix level.
+    surround_downmix_level: SurroundDownMixLevel
+
+    #: If the `acmod` is LR, this indicates if the channels
+    #: are encoded in Dolby Surround.
+    dolby_surround_encoded: DolbySurroundEncodingMode
+
+    #: `True` if there is a langcode present in the metadata.
+    langcode_present: bool
+
+    #: `True` if this bitstream is copyrighted.
+    copyright_bitstream: bool
+
+    #: `True` if this bitstream is original.
+    original_bitstream: bool
+
+    dialnorm: DialnormLevel
+
+    #: Language code
+    langcode: int
+
+    #: `True` if `mixlevel` and `roomtype` are valid
+    prod_info_exists: bool
+
+    #: Mix level
+    mixlevel: MixLevel
+
+    #: Room Type
+    roomtype: RoomType
+
+    #: LoRo preferred center downmix level
+    loro_center_downmix_level: DownMixLevelToken
+    
+    #: LoRo preferred surround downmix level
+    loro_surround_downmix_level: DownMixLevelToken
+
+    #: Preferred downmix mode
+    downmix_mode: PreferredDownMixMode
+    
+    #: LtRt preferred center downmix level
+    ltrt_center_downmix_level: DownMixLevelToken
+
+    #: LtRt preferred surround downmix level
+    ltrt_surround_downmix_level: DownMixLevelToken
+
+    #: Surround-EX mode
+    surround_ex_mode: SurroundEXMode
+    
+    #: Dolby Headphone mode
+    dolby_headphone_encoded: HeadphoneMode
+
+    ad_converter_type: ADConverterType
+    compression_profile: RFCompressionProfile
+    dynamic_range: RFCompressionProfile
+    
+    #: Indicates if this stream can be decoded independently or not
+    stream_dependency: StreamDependency
+
+    #: Data rate of this bitstream in kilobits per second
+    datarate_kbps: int
+    
+    @staticmethod
+    def load(buffer: bytes):
+        assert len(buffer) == 96, "Dolby Digital Plus segment incorrect size, "
+        "expected 96 got %i" % len(buffer)
+
+        def program_id(b) -> int:
+            return b
+
+        def program_info(b):
+            return (b & 0x40) > 0, \
+                DolbyDigitalPlusMetadata.BitStreamMode(b & 0x38 >> 3), \
+                DolbyDigitalPlusMetadata.AudioCodingMode(b & 0x7)
+
+        def ddplus_reserved1(_):
+            pass
+
+        def surround_config(b):
+            return DolbyDigitalPlusMetadata.CenterDownMixLevel(b & 0x30 >> 4), \
+                DolbyDigitalPlusMetadata.SurroundDownMixLevel(b & 0xc >> 2), \
+                DolbyDigitalPlusMetadata.DolbySurroundEncodingMode(b & 0x3)
+
+        def dialnorm_info(b):
+            return (b & 0x80) > 0 , b & 0x40 > 0, b & 0x20 > 0, \
+                DolbyDigitalPlusMetadata.DialnormLevel(b & 0x1f)
+
+        def langcod(b) -> int:
+            return b
+
+        def audio_prod_info(b):
+            return (b & 0x80) > 0, \
+                DolbyDigitalPlusMetadata.MixLevel(b & 0x7c >> 2), \
+                DolbyDigitalPlusMetadata.RoomType(b & 0x3)
+
+        # loro_center_downmix_level, loro_surround_downmix_level 
+        def ext_bsi1_word1(b):
+            return DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x38 >> 3), \
+                DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x7)
+
+        # downmix_mode, ltrt_center_downmix_level, ltrt_surround_downmix_level
+        def ext_bsi1_word2(b):
+            return DolbyDigitalPlusMetadata.PreferredDownMixMode(b & 0xC0 >> 6), \
+                DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x38 >> 3), \
+                DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x7)
+
+        #surround_ex_mode, dolby_headphone_encoded, ad_converter_type 
+        def ext_bsi2_word1(b):
+            return DolbyDigitalPlusMetadata.SurroundEXMode(b & 0x60 >> 5), \
+                DolbyDigitalPlusMetadata.HeadphoneMode(b & 0x18 >> 3), \
+                DolbyDigitalPlusMetadata.ADConverterType( b & 0x4 >> 2)
+
+        def ddplus_reserved2(_):
+            pass
+
+        def compr1(b):
+            return DolbyDigitalPlusMetadata.RFCompressionProfile(b)
+
+        def dynrng1(b):
+            DolbyDigitalPlusMetadata.RFCompressionProfile(b) 
+
+        def ddplus_reserved3(_):
+            pass
+
+        def ddplus_info1(b):
+            return DolbyDigitalPlusMetadata.StreamDependency(b & 0xc >> 2)
+
+        def ddplus_reserved4(_):
+            pass
+
+        def datarate(b) -> int:
+            return unpack("<H", b)[0]
+
+        def reserved(_):
+            pass
+
+        pid = program_id(buffer[0])
+        lfe_on, bitstream_mode, audio_coding_mode = program_info(buffer[1])
+        ddplus_reserved1(buffer[2:2])
+        center_downmix_level, surround_downmix_level, dolby_surround_encoded = surround_config(buffer[4])
+        langcode_present, copyright_bitstream, original_bitstream, dialnorm = dialnorm_info(buffer[5])
+        langcode = langcod(buffer[6])
+        prod_info_exists, mixlevel, roomtype = audio_prod_info(buffer[7])
+
+        loro_center_downmix_level, loro_surround_downmix_level = ext_bsi1_word1(buffer[8])
+        downmix_mode, ltrt_center_downmix_level, ltrt_surround_downmix_level = ext_bsi1_word2(buffer[9])
+        surround_ex_mode, dolby_headphone_encoded, ad_converter_type = ext_bsi2_word1(buffer[10])
+
+        ddplus_reserved2(buffer[11:14])
+        compression = compr1(buffer[14])
+        dynamic_range = dynrng1(buffer[15])
+        ddplus_reserved3(buffer[16:19])
+        stream_info = ddplus_info1(buffer[19])
+        ddplus_reserved4(buffer[20:25])
+        data_rate = datarate(buffer[25:27])
+        reserved(buffer[27:69])
+
+        return DolbyDigitalPlusMetadata(program_id=pid,
+            lfe_on=lfe_on, 
+            bitstream_mode=bitstream_mode,
+            audio_coding_mode=audio_coding_mode,
+            center_downmix_level=center_downmix_level,
+            surround_downmix_level=surround_downmix_level,
+            dolby_surround_encoded=dolby_surround_encoded, 
+            langcode_present=langcode_present, 
+            copyright_bitstream=copyright_bitstream, 
+            original_bitstream=original_bitstream,
+            dialnorm=dialnorm, 
+            langcode=langcode,
+            prod_info_exists=prod_info_exists,
+            mixlevel=mixlevel,
+            roomtype=roomtype,
+            loro_center_downmix_level=loro_center_downmix_level,
+            loro_surround_downmix_level=loro_surround_downmix_level,
+            downmix_mode=downmix_mode,
+            ltrt_center_downmix_level=ltrt_center_downmix_level, 
+            ltrt_surround_downmix_level=ltrt_surround_downmix_level,
+            surround_ex_mode=surround_ex_mode,
+            dolby_headphone_encoded=dolby_headphone_encoded,
+            ad_converter_type=ad_converter_type,
+            compression_profile=compression,
+            dynamic_range=dynamic_range,
+            stream_dependency=stream_info,
+            datarate_kbps=data_rate)
+
+
+@dataclass
+class DolbyAtmosMetadata:
+    """
+    Dolby Atmos Metadata Segment
+
+    https://github.com/DolbyLaboratories/dbmd-atmos-parser/
+    """
+
+    class WarpMode(Enum):
+        NORMAL = 0x00
+        WARPING = 0x01
+        DOWNMIX_PLIIX = 0x02
+        DOWNMIX_LORO = 0x03
+        NOT_INDICATED = 0x04
+
+    tool_name: str
+    tool_version: Tuple[int,int,int]
+    warp_mode: WarpMode
+
+    SEGMENT_LENGTH = 248
+    TOOL_NAME_LENGTH = 64
+
+    @classmethod
+    def load(cls, data: bytes):
+        assert len(data) == cls.SEGMENT_LENGTH, "DolbyAtmosMetadata segment "\
+            "is incorrect length, expected %i actual was %i" % (cls.SEGMENT_LENGTH, len(data)) 
+
+        h = BytesIO(data)
+
+        h.seek(32, 1)
+        toolname = h.read(cls.TOOL_NAME_LENGTH)
+        toolname = unpack("%is" % cls.TOOL_NAME_LENGTH, toolname)[0]
+        toolname = toolname.decode('utf-8').strip('\0')
+
+        vers = h.read(3)
+        major, minor, fix = unpack("BBB", vers)
+
+        h.seek(53, 1)
+
+        a_val = unpack("B", h.read(1))[0]
+        warp_mode = a_val & 0x7
+
+        return DolbyAtmosMetadata(tool_name=toolname, 
+            tool_version=(major, minor, fix), warp_mode=DolbyAtmosMetadata.WarpMode(warp_mode))
+
+        
+@dataclass
+class DolbyAtmosSupplementalMetadata:
+    """
+    Dolby Atmos supplemental metadata segment.
+
+    https://github.com/DolbyLaboratories/dbmd-atmos-parser/blob/master/dbmd_atmos_parse/src/dbmd_atmos_parse.c
+    """ 
+
+    class BinauralRenderMode(Enum):
+        BYPASS = 0x00
+        NEAR = 0x01
+        FAR = 0x02
+        MID = 0x03
+        NOT_INDICATED = 0x04
+
+
+    object_count: int
+    render_modes: List['DolbyAtmosSupplementalMetadata.BinauralRenderMode']
+    trim_modes: List[int]
+
+
+    MAGIC = 0xf8726fbd
+    TRIM_CONFIG_COUNT = 9
+
+    @classmethod
+    def load(cls, data: bytes):
+
+        trim_modes = []
+        render_modes = []
+
+        h = BytesIO(data)
+        magic = unpack("<I", h.read(4))
+        assert magic == cls.MAGIC, "Magic value was not found"
+
+        object_count = unpack("<H", h.read(2))
+
+        h.read(1) #skip 1
+
+        for _ in range(cls.TRIM_CONFIG_COUNT):
+            auto_trim = unpack("B", h.read(1))
+            trim_modes.append(auto_trim)
+
+            h.read(14) #skip 14
+        
+        h.read(object_count) # skip object_count bytes
+
+        for _ in range(object_count):
+            binaural_mode = unpack("B", h.read(1))
+            binaural_mode &= 0x7
+            render_modes.append(binaural_mode)
+
+        return DolbyAtmosSupplementalMetadata(object_count=object_count,
+            render_modes=render_modes,trim_modes=trim_modes)
+
+
+class WavDolbyMetadataReader:
+    """
+    Reads Dolby bitstream metadata.
+    """
+
+    #: List of the Dolby Metadata Segments.
+    #:
+    #: Each list entry is a tuple of `SegmentType`, a `bool`
+    #: indicating if the segment's checksum was valid, and the
+    #: segment's parsed dataclass (or a `bytes` array if it was 
+    #: not recognized).
+    segment_list: Tuple[Union[SegmentType, int], bool, Any] 
+
+    version: Tuple[int,int,int,int]
+
+    @staticmethod
+    def segment_checksum(bs: bytes, size: int):
+        retval = size
+        for b in bs:
+            retval += int(b)
+            retval &= 0xff
+
+        retval = ((~retval) + 1) & 0xff
+
+        return retval
+
+
+    def __init__(self, dbmd_data) -> None:
+        self.segment_list = []
+
+        h = BytesIO(dbmd_data)
+
+        v_vec = []
+        for _ in range(4):
+            b = h.read(1)
+            v_vec.insert(0, unpack("B",b)[0])
+        
+        self.version = tuple(v_vec)
+
+        while True:
+            stype= SegmentType(unpack("B", h.read(1))[0])
+            if stype == SegmentType.EndMarker:
+                break
+            else:
+                seg_size = unpack("<H", h.read(2))[0]
+                seg_payload = h.read(seg_size)
+                expected_checksum = WavDolbyMetadataReader.segment_checksum(seg_payload, seg_size)
+                checksum = unpack("B", h.read(1))[0]
+
+                segment = seg_payload
+                if stype == SegmentType.DolbyDigitalPlus:
+                    segment = DolbyDigitalPlusMetadata.load(segment)
+                elif stype == SegmentType.DolbyAtmos:
+                    segment = DolbyAtmosMetadata.load(segment)
+                # elif stype == SegmentType.DolbyAtmosSupplemental:
+                #     segment = DolbyAtmosSupplementalMetadata.load(segment)
+                
+                self.segment_list.append( (stype, checksum == expected_checksum, segment) )
+    
+    def dolby_digital_plus(self) -> List[DolbyDigitalPlusMetadata]:
+        """
+        Every valid Dolby Digital Plus metadata segment in the file.
+        """
+        return [x[2] for x in self.segment_list \
+            if x[0] == SegmentType.DolbyDigitalPlus and x[1]]
+
+    def dolby_atmos(self) -> List[DolbyAtmosMetadata]:
+        """
+        Every valid Dolby Atmos metadata segment in the file.
+        """
+        return [x[2] for x in self.segment_list \
+            if x[0] == SegmentType.DolbyAtmos and x[1]]
+
+    # def dolby_atmos_supplemental(self) -> List[DolbyAtmosSupplementalMetadata]:
+    #     """
+    #     Every valid Dolby Atmos Supplemental metadata segment in the file.
+    #     """
+    #     return [x[2] for x in self.segment_list \
+    #         if x[0] == SegmentType.DolbyAtmosSupplemental and x[1]]
+
+    def to_dict(self) -> dict:
+
+        ddp = map(lambda x: asdict(x), self.dolby_digital_plus())
+        atmos = map(lambda x: asdict(x), self.dolby_atmos())
+        #atmos_sup = map(lambda x: asdict(x), self.dolby_atmos_supplemental())
+        
+        return dict(dolby_digital_plus=list(ddp),
+             dolby_atmos=list(atmos))

wavinfo/wave_info_reader.py

@@ -1,6 +1,7 @@
-
 from .riff_parser import parse_chunk, ListChunkDescriptor
 
+from typing import Optional
+
 class WavInfoChunkReader:
 
     def __init__(self, f, encoding):
@@ -9,30 +10,47 @@ 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.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')
+        #: 'ICOP' Copyright
+        self.copyright : Optional[str] = self._get_field(f, b'ICOP')
+        #: 'IPRD' Product
+        self.product : Optional[str]= self._get_field(f, b'IPRD')
+        self.album : Optional[str] = self.product
+        #: 'IGNR' Genre
+        self.genre : Optional[str] = self._get_field(f, b'IGNR')
+        #: 'ISBJ' Supject
+        self.subject : Optional[str] = self._get_field(f, b'ISBJ')
+        #: 'IART' Artist, composer, author
+        self.artist : Optional[str] = self._get_field(f, b'IART')
+        #: 'ICMT' Comment
+        self.comment : Optional[str] = self._get_field(f, b'ICMT')
+        #: 'ISFT' Software, encoding application
+        self.software : Optional[str] = self._get_field(f, b'ISFT')
+        #: 'ICRD' Created date
+        self.created_date : Optional[str] = self._get_field(f, b'ICRD')
+        #: 'IENG' Engineer
+        self.engineer : Optional[str] = self._get_field(f, b'IENG')
+        #: 'ITCH' Technician
+        self.technician : Optional[str] = self._get_field(f, b'ITCH')
+        #: 'IKEY' Keywords, keyword list
+        self.keywords : Optional[str] = self._get_field(f, b'IKEY')
+        #: 'INAM' Name, title
+        self.title : Optional[str] = self._get_field(f, b'INAM')
+        #: 'ISRC' Source
+        self.source : Optional[str] = self._get_field(f, b'ISRC')
+        #: 'TAPE' Tape
+        self.tape : Optional[str] = self._get_field(f, b'TAPE')
+        #: 'IARL' Archival Location
+        self.archival_location : Optional[str] = self._get_field(f, b'IARL')
+        #: 'ICSM' Commissioned
+        self.commissioned : Optional[str] = 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)
+    def _get_field(self, f, field_ident) -> Optional[str]:
+        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 +59,30 @@ 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 +1,104 @@
-import xml.etree.ElementTree as ET
+from lxml import etree as ET
 import io
+from collections import namedtuple
+from typing import Optional
+
+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):
+    def _get_text_value(self, xpath) -> Optional[str]:
         e = self.parsed.find("./" + xpath)
         if e is not None:
             return e.text
+        else: 
+            return None
+
+    def xml_bytes(self):
+        return ET.tostring(self.parsed).decode("utf-8")
 
     @property
-    def project(self):
+    def raw_xml(self):
+        """
+        The root entity of the iXML document.
+        """
+        return self.parsed
+
+    @property
+    def track_list(self):
+        """
+        A description of each track.
+        :returns: 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) -> Optional[str]:
+        """
+        The project/film name entered for the recording.
+        """
         return self._get_text_value("PROJECT")
 
     @property
-    def scene(self):
+    def scene(self) -> Optional[str]:
+        """
+        Scene/slate.
+        """
         return self._get_text_value("SCENE")
 
     @property
-    def take(self):
+    def take(self) ->  Optional[str]:
+        """
+        Take number.
+        """
         return self._get_text_value("TAKE")
 
     @property
-    def tape(self):
+    def tape(self) -> Optional[str]:
+        """
+        Tape name.
+        """
         return self._get_text_value("TAPE")
 
     @property
-    def family_uid(self):
+    def family_uid(self) -> Optional[str]:
+        """
+        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):
+    def family_name(self) -> Optional[str]:
+        """
+        The name of this file's file family.
+        """
         return self._get_text_value("FILE_SET/FAMILY_NAME")
 
-
+    def to_dict(self):
+        return dict(track_list=list(map(lambda x: x._asdict(), self.track_list)), 
+            project=self.project,
+            scene=self.scene,
+            take=self.take,
+            tape=self.tape,
+            family_uid=self.family_uid,
+            family_name=self.family_name 
+            )

wavinfo/wave_reader.py

@@ -1,79 +1,120 @@
+#-*- coding: utf-8 -*-
 import struct
-
+import os
 from collections import namedtuple
 
+from typing import Optional, Generator, Any
+
+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
+from .wave_adm_reader import WavADMReader
+from .wave_dbmd_reader import WavDolbyMetadataReader
 
-WavDataDescriptor = namedtuple('WavDataDescriptor','byte_count frame_count')
+#: Calculated statistics about the audio data.
+WavDataDescriptor = namedtuple('WavDataDescriptor', 'byte_count frame_count')
 
-WavInfoFormat = namedtuple("WavInfoFormat",'audio_format channel_count sample_rate byte_rate block_align bits_per_sample')
-
-WavBextFormat = namedtuple("WavBextFormat",'description originator originator_ref ' +
-    'originator_date originator_time time_reference version umid ' +
-    'loudness_value loudness_range max_true_peak max_momentary_loudness max_shortterm_loudness ' +
-    'coding_history')
+#: The format of the audio samples.
+WavAudioFormat = namedtuple('WavAudioFormat',
+                            'audio_format channel_count sample_rate byte_rate block_align bits_per_sample')
 
 
-class WavInfoReader():
+class WavInfoReader:
     """
-    format : WAV format
-    bext   : The Broadcast-WAV extension as definied by EBU Tech 3285 v2 (2011)
+    Parse a WAV audio file for metadata.
 
+    
     """
 
     def __init__(self, path, info_encoding='latin_1', bext_encoding='ascii'):
         """
-        Parse a WAV audio file for metadata.
+        Create a new reader object.
 
-        * `path`: A filesystem path to the wav file you wish to probe.
+        :param path: 
+            A filesystem path to the wav file you wish to probe or a 
+            file handle to an open file.
 
-        * `info_encoding`: The text encoding of the INFO metadata fields.
-          `latin_1`/Win CP1252 has always been a pretty good guess for this.
+        :param info_encoding: 
+            The text encoding of the INFO metadata fields.
+            latin_1/Win CP1252 has always been a pretty good guess for this.
+
+        :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 weirdo.
 
-        * `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.
 
         """
-        with open(path, 'rb') as f:
-            chunks = parse_chunk(f)
+        
+        self.info_encoding = info_encoding
+        self.bext_encoding = bext_encoding
+        
+        if hasattr(path, 'read'):
+            self.get_wav_info(path)
+            self.url = 'about:blank'
+            self.path = repr(path)
+        else:
+            absolute_path = os.path.abspath(path)
 
-            self.main_list = chunks.children
-            f.seek(0)
+            #: `file://` url for the file.
+            self.url: pathlib.Path = pathlib.Path(absolute_path).as_uri()
 
-            self.fmt    = self._get_format(f)
-            self.bext   = self._get_bext(f, encoding=bext_encoding)
-            self.ixml   = self._get_ixml(f)
-            self.info   = self._get_info(f, encoding=info_encoding)
-            self.data   = self._describe_data(f)
+            self.path = absolute_path
+
+            #: Wave audio data format.
+            self.fmt :Optional[WavAudioFormat] = None
+
+            #: Statistics of the `data` section.
+            self.data :Optional[WavDataDescriptor] = None
+
+            #: Broadcast-Wave metadata.
+            self.bext :Optional[WavBextReader] = None
+
+            #: iXML metadata.
+            self.ixml :Optional[WavIXMLFormat] = None
+
+            #: ADM Audio Definiton Model metadata.
+            self.adm :Optional[WavADMReader]= None
+
+            #: Dolby bitstream metadata.
+            self.dolby :Optional[WavDolbyMetadataReader] = None
+
+            #: RIFF INFO metadata.
+            self.info :Optional[WavInfoChunkReader]= None
+            
+            with open(path, 'rb') as f:
+                self.get_wav_info(f)
+            
+    def get_wav_info(self, wavfile):
+        chunks = parse_chunk(wavfile)
+
+        self.main_list = chunks.children
+        wavfile.seek(0)
+
+        self.fmt = self._get_format(wavfile)
+        self.bext = self._get_bext(wavfile, encoding=self.bext_encoding)
+        self.ixml = self._get_ixml(wavfile)
+        self.adm  = self._get_adm(wavfile)
+        self.info = self._get_info(wavfile, encoding=self.info_encoding)
+        self.dolby = self._get_dbmd(wavfile)
+        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))
+    def _describe_data(self):
+        data_chunk = next(c for c in self.main_list if type(c) is ChunkDescriptor and c.ident == b'data')
 
-        if chunk_descriptor:
-            return chunk_descriptor.read_data(from_stream)
-        else:
-            return None
+        return WavDataDescriptor(byte_count=data_chunk.length,
+                                 frame_count=int(data_chunk.length / self.fmt.block_align))
 
-
-    def _describe_data(self,f):
-        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))
-
-
-    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
@@ -87,41 +128,65 @@ 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 WavInfoFormat(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)
-        return WavBextReader(bext_data, encoding)
+        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
+    def _get_adm(self, f):
+        axml = self._find_chunk_data(b'axml', f, default_none=True)
+        chna = self._find_chunk_data(b'chna', f, default_none=True)
+        return WavADMReader(axml_data=axml, chna_data=chna) if axml and chna else None
 
-        ixml_string = ixml_data
-        return WavIXMLFormat(ixml_string)
+    def _get_dbmd(self, f):
+        dbmd_data = self._find_chunk_data(b'dbmd', f, default_none=True)
+        return WavDolbyMetadataReader(dbmd_data=dbmd_data) if dbmd_data else None
 
+    def _get_ixml(self, f):
+        ixml_data = self._find_chunk_data(b'iXML', f, default_none=True)
+        return WavIXMLFormat(ixml_data.rstrip(b'\0')) if ixml_data else None
 
+    def walk(self) -> Generator[str,str,Any]: #FIXME: this should probably be named "iter()"
+        """
+        Walk all of the available metadata fields.
+        
+        :yields: tuples of the *scope*, *key*, and *value* of
+            each metadatum. The *scope* value will be one of
+            "fmt", "data", "ixml", "bext", "info", "dolby", or "adm".
+        """
 
+        scopes = ('fmt', 'data', 'ixml', 'bext', 'info', 'adm', 'dolby')
 
+        for scope in scopes:
+            if scope in ['fmt', 'data']:
+                attr = self.__getattribute__(scope)
+                for field in attr._fields:
+                    yield scope, field, attr.__getattribute__(field)
 
+            else:
+                dict = self.__getattribute__(scope).to_dict() if self.__getattribute__(scope) else {}
+                for key in dict.keys():
+                    yield scope, key, dict[key]
+        
+    def __repr__(self):
+        return 'WavInfoReader({}, {}, {})'.format(self.path, self.info_encoding, self.bext_encoding)