Merge pull request #23 from iluvcapra/maint-rm-umid

Removed UMID parsing for now, to improve test coverage

.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/coverage.yml

@@ -0,0 +1,39 @@
+name: Test Coverage
+
+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", "3.12"]
+
+    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
+          python -m pip install -e .
+      - name: Setup FFmpeg
+        uses: FedericoCarboni/setup-ffmpeg@v2
+      - name: Generate coverage report
+        run: |
+          pip install pytest
+          pip install pytest-cov
+          pytest --cov=./ --cov-report=xml
+      - name: Codecov
+        # You may pin to the exact commit or the version.
+        # uses: codecov/codecov-action@eaaf4bedf32dbdc6b720b63067d99c4d77d6047d
+        uses: codecov/codecov-action@v3.1.4
+      

.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", "3.12"]
+
+    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
+        python -m pip install -e .
+    - 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 build wheel twine lxml
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_APIKEY }}
+      run: |
+        python -m build .
+        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 +1,32 @@
+# .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:
+    - method: pip
+      path: .
+      extra_requirements:
+        - doc

.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"

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+[the GitHub Issues Tab](https://github.com/iluvcapra/wavinfo/issues).
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

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) 2018-2023 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 +1,43 @@
-[![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)
+[![codecov](https://codecov.io/gh/iluvcapra/wavinfo/branch/master/graph/badge.svg?token=9DZQfZENYv)](https://codecov.io/gh/iluvcapra/wavinfo)
 
 # 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.
 
-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 
-  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 
-  information.
+* [Broadcast-WAVE][bext] metadata, including embedded program
+  loudness, coding history and [SMPTE UMID][smpte_330m2011].
+* [Audio Definition Model (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.
+  * iXML `STEINBERG` sound library attributes.
+* Wave embedded cue markers, cue marker labels, notes and timed ranges as used
+  by Zoom, iZotope RX, etc.
+* 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__.
-
-[ebu]:https://tech.ebu.ch/docs/tech/tech3285.pdf
-[smpte_330m2011]:http://standards.smpte.org/content/978-1-61482-678-1/st-330-2011/SEC1.abstract
-[ixml]:http://www.ixml.info
+[bext]:https://wavinfo.readthedocs.io/en/latest/scopes/bext.html
+[smpte_330m2011]:https://wavinfo.readthedocs.io/en/latest/scopes/bext.html#wavinfo.wave_bext_reader.WavBextReader.umid
+[adm]:https://wavinfo.readthedocs.io/en/latest/scopes/adm.html
+[ebu3285s6]:https://wavinfo.readthedocs.io/en/latest/scopes/dolby.html
+[ixml]:https://wavinfo.readthedocs.io/en/latest/scopes/ixml.html
+[info-tags]:https://wavinfo.readthedocs.io/en/latest/scopes/info.html
+[eburf64]:https://tech.ebu.ch/docs/tech/tech3306v1_1.pdf
 
 
-
-## Demonstration
+## How To Use
 
 The entry point for wavinfo is the WavInfoReader class.
 
@@ -39,117 +47,18 @@ 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).

data/share/man/man1/wavinfo.1

@@ -0,0 +1,74 @@
+.TH wavinfo 1 "2023-11-07" "Jamie Hardt" "User Manuals"
+.SH NAME 
+wavinfo \- probe wave files for metadata
+.SH SYNOPSIS
+.SY wavinfo
+.I "[\-\-adm]"
+.I "[\-\-ixml]"
+.I FILE ...
+.SH DESCRIPTION
+.B wavinfo 
+extracts embedded metadata from WAVE and RF64/WAVE sound files, with an
+emphasis on film, video and professional music production metadata.
+.SH OPTIONS
+.IP "(no options)"
+With no options, 
+.B wavinfo 
+will emit a JSON (Javascript Object Notation) object containing all 
+detected metadata.
+.IP "\-\-adm"
+Output any Audio Definition Model (ADM) metadata in 
+.BR FILE .
+.IP "\-\-ixml"
+Output any iXML metdata in 
+.BR FILE .
+.IP "\-h, \-\-help"
+Print brief help.
+.SH DETAILED DESCRIPTION
+.B wavinfo 
+collects metadata according to different 
+.IR scopes .
+.SS METADATA SCOPES
+.IP fmt
+Basic audio properties: sample format, sample rate, channel count, etc.
+.IP data
+Size and frame count of the WAVE file's 
+.I data 
+segment.
+.IP cues
+Timed cue points, labels, notes and time ranges.
+.IP bext 
+Broadcast-WAV metadata: description, originator, date and time, UMID.
+.IP ixml 
+A selection of parsed iXML fields: track list, project, scene, take, tape,
+family name, family uid. For the full iXML document use the 
+.IR \-\-ixml 
+command option.
+.IP adm 
+EBU Audio Definition Model (ADM) metadata: Programme, channels. For the full 
+ADM 
+.I <axml>
+document use the 
+.IR \-\-adm 
+command option.
+.IP dolby
+Dolby bitstream and Atmos metadata.
+.IP info 
+INFO metadata fields: IART (artist), ICMT (comment), etc.
+.SH EXIT STATUS
+.IP 0
+On user quit.
+.SH AUTHOR
+Jamie Hardt 
+.UR https://github.com/iluvcapra
+.UE
+.SH BUGS
+Issue submissions, feature requests, pull requests and other contributions 
+are welcome and should be directed at 
+.BR wavinfo 's
+home page on GitHub:
+.RS 4
+.UR https://github.com/iluvcapra/wavinfo 
+.UE
+.\" .SH SEE ALSO
+.\" .BR "ffmpeg" "(1),"

data/share/man/man7/wavinfo.7

@@ -0,0 +1,190 @@
+.TH waveinfo 7 "2023-11-07" "Jamie Hardt" "Miscellaneous Information Manuals"
+.SH NAME
+wavinfo \- information about wave sound file metadata
+.\" .SH DESCRIPTION
+.SH CHUNK MENAGERIE
+A list of chunks that you may find in a wave file from our experience.
+.SS Essential WAV Chunks 
+.IP fmt 
+Defines the format of the audio in the 
+.I data 
+chunk: the audio codec, the sample rate, bit depth, channel count, block 
+alignment and other data. May take an "extended" form, with additional data 
+(such as channel speaker assignments) if there are more than two channels in 
+the file or if it is a compressed format.
+.IP data 
+The audio data itself. PCM audio data is always stored as interleaved samples.
+.IP JUNK 
+A region of the file not currently in use. Clients sometimes add these before
+the 
+.I data
+chunk in order to align the beginning of the audio data with a memory page 
+boundary (this can make memory-mapped reads from a wave file a little more 
+efficient). A 
+.I JUNK 
+chunk is often placed at the beginning of a WAVE file to reserve space for 
+a 
+.I ds64 
+chunk that will be written to the file at the end of recording, in the event 
+that after the file is finalized, it exceeds the RIFF size limit. Thus a WAVE 
+file can be upgraded in-place to an RF64 without re-writing the audio data.
+.IP fact 
+Fact chunks record the number of samples in the decoded audio stream. It's only
+present in WAVE files that contain compressed audio.
+.IP "LIST or list"
+(Both have been seen) Not a chunk type itself but signals to a RIFF parser that 
+this chunk contains chunks itself. A LIST chunk's payload will begin with a 
+four-character code identifying the form of the list, and is then followed
+by chunks of the standard key-length-data form, which may themselves be 
+LISTs that themselves contain child chunks. WAVE files don't tend to have a 
+very deep heirarchy of chunks, compared to AVI files.
+.SS RIFF Metadata 
+The RIFF container format has a metadata system common to all RIFF files, WAVE
+being the most common at present, AVI being another very common format
+historically.
+.IP INFO 
+A 
+.I LIST 
+form containing a flat list of chunks, each containing text metadata. The role
+of the string, like "Artist", "Composer", "Comment", "Engineer" etc. are given
+by the four-character code: "Artist" is 
+.IR IART , 
+Composer is 
+.IR ICMP , 
+engineer is 
+.IR IENG , 
+Comment is 
+.IR ICMT ,
+etc.
+.IP cue
+A binary list of cues, which are timed points within the audio data.
+.IP adtl
+A 
+.I LIST 
+form containing text labels 
+.RI ( labl )
+for the cues in the 
+.I cue 
+chunk, "notes" 
+.RI ( note ,
+which are structurally identical to 
+.I labl 
+but hosts tend to use notes for longer text), and "length text"
+.I ltxt 
+metadata records, which can give a cue a length, making it a range, and a text 
+field that defines its own encoding.
+.IP CSET
+Defines the character set for all text fields in 
+.IR INFO ,  
+.I adtl 
+and other RIFF-defined text fields. By default, all of the text in RIFF 
+metadata fields is Windows Latin 1/ISO 8859-1, though as time passes many 
+clients have simply taken to sticking UTF-8 into these fields. The 
+.I CSET 
+cannot represent UTF-8 as a valid option for text encoding, it only speaks 
+Windows codepages, and we've never seen one in a WAVE file in any event and 
+it's vanishingly likely an audio app would recognize one if it saw it.
+.SS Broadcast-WAVE Metadata
+Broadcast-WAVE is a set of extensions to WAVE files to facilitate media 
+production maintained by the EBU.
+.IP bext
+A multi-field structure containing mostly fixed-width text data capturing
+essential production information: a 256 character free description field,
+originator name and a unique reference, recording date and time, a frame-based
+timestamp for sample-accurate recording time, and a coding history record. The
+extended form of the structure can hold a SMPTE UMID (a kind of UUID, which 
+may also contain timestamp and geolocation data) and pre-computed program 
+loudness measurements. 
+.IP peak
+A binary data structure containing the peak envelope for the audio data, for 
+use by clients to generate a waveform overview.
+.SS Audio Definition Model Metadata
+Audio Definition Model (ADM) metadata is a metadata standard for audio 
+broadcast and distribution maintained by the ITU.
+.IP chna
+A binary list that associates individual channels in the file to entities
+in the ADM XML document stored in the 
+.I axml 
+chunk. A 
+.I chna 
+chunk will always appear with an 
+.I axml
+chunk and vice versa.
+.IP axml
+Contains an XML document with Audio Definition Model metadata. ADM metadata 
+describes the program the WAVE file belongs to, role, channel assignment,
+and encoding properties of individual channels in the WAVE file, and if the 
+WAVE file contains object-based audio, it will also give all of the positioning
+and panning automation envelopes.
+.IP bxml 
+This is defined by the ITU as a gzip-compressed version of the 
+.I axml 
+chunk.
+.IP sxml 
+This is a hybrid binary/gzip-compressed-XML chunk that associates ADM 
+documents with timed ranges of a WAVE file.
+.SS Dolby Metadata
+.IP dbmd 
+Records hints for Dolby playback applications for downmixing, level 
+normalization and other things.
+.SS Proprietary Chunks 
+.IP ovwf 
+.B (Pro Tools)
+Pre-computed waveform overview data.
+.IP regn 
+.B (Pro Tools)
+Region and cue point metadata.
+.SS Chunks of Unknown Purpose
+.IP elm1 
+.IP minf 
+.IP umid
+.SH HISTORY
+The oldest document that defines the form of a Wave file is the 
+.I Multimedia Programming Interface and Data Specifications 1.0
+of August 1991.
+.\" .SH REFERENCES
+.\" .SS ESSENTIAL FILE FORMAT
+.\" .TP 
+.\" .UR https://www.aelius.com/njh/wavemetatools/doc/riffmci.pdf
+.\" Multimedia Programming Interface and Data Specifications 1.0
+.\" .UE 
+.\" The original definition of the 
+.\" .I RIFF 
+.\" container, the 
+.\" .I WAVE 
+.\" form, the original metadata facilites, and things like language, country and
+.\" dialect enumerations.
+.\" .TP 
+.\" .UR https://datatracker.ietf.org/doc/html/rfc2361
+.\" RFC 2361
+.\" .UE
+.\" A large RFC compilation of all of the known (in 1998) audio encoding formats 
+.\" in use. 104 different codecs are documented with a name, the corresponding 
+.\" magic number, and a vendor contact name, phone number and address (no 
+.\" emails, strangely). Almost all of these are of historical interest only.
+.\" .SS RF64/Extended WAVE Format 
+.\"
+.\" .TP
+.\" .UR https://www.itu.int/dms_pubrec/itu-r/rec/bs/R-REC-BS.2088-1-201910-I!!PDF-E.pdf
+.\" ITU Recommendation BS.2088-1-2019
+.\" .UE
+.\" BS.2088 gives a detailed description of the internals of an RF64 file, 
+.\" .I ds64 
+.\" structure and all formal requirements. It also defines the use of 
+.\" .IR <axml> ,
+.\" .IR <bxml> ,
+.\" .IR <sxml> ,
+.\" and
+.\" .I <chna>
+.\" metadata chunks for the carriage of Audio Definition Model metadata.
+.\" .TP 
+.\" .UR https://tech.ebu.ch/docs/tech/tech3306.pdf 
+.\" EBU Tech 3306 "RF64: An Extended File Format for Audio Data"
+.\" .UE
+.\" Version 1 of Tech 3306 laid out the 
+.\" .I RF64 
+.\" extended WAVE 
+.\" file format almost identically to 
+.\" .IR BS.2088 ,
+.\" Version 2 of the standard wholly adopted 
+.\" .IR BS.2088 .

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/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'2018-2023, Jamie Hardt'
+author = u'Jamie Hardt'
+
+# The short X.Y version
+version = wavinfo.__short_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
+   references
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

docs/source/quickstart.rst

@@ -0,0 +1,30 @@
+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)
+    
+    adm_metadata = info.adm
+    ixml_metadata = info.ixml
+   
+WavInfoReader Class Documentation
+--------------------------------------
+
+.. module:: wavinfo
+    :noindex:
+
+.. autoclass:: wavinfo.wave_reader.WavInfoReader
+   :members:
+   :special-members: __init__
+

docs/source/references.rst

@@ -0,0 +1,40 @@
+References
+==========
+
+Wave File Format
+----------------
+
+* `ITU Recommendation BS.2088-1-2019 — Long-form file format for the international exchange of audio programme materials with metadata <https://www.itu.int/dms_pubrec/itu-r/rec/bs/R-REC-BS.2088-1-201910-I!!PDF-E.pdf>`_
+* `IETF Network Working Group RFC2361 — WAVE and AVI Codec Registries <https://www.rfc-editor.org/rfc/rfc2361>`_
+
+Broadcast Wave Format
+---------------------
+
+* `EBU Tech 3285 — Specification of the Broadcast Wave Format (BWF) <https://tech.ebu.ch/docs/tech/tech3285.pdf>`_
+* `EBU Tech 3306 — MBWF / RF64: An extended File Format for Audio <https://tech.ebu.ch/docs/tech/tech3306v1_1.pdf>`_
+* `SMPTE ST 330-2011 — Unique Material Identifier <https://ieeexplore.ieee.org/document/9787389>`_
+
+Audio Definition Model
+----------------------
+
+* `ITU Recommendation BS.2076-2-2019 — Audio definition model <https://www.itu.int/dms_pubrec/itu-r/rec/bs/R-REC-BS.2076-2-201910-I!!PDF-E.pdf>`_
+* `EBU Tech 3285 Supplement 5 — <axml> Chunk <https://tech.ebu.ch/docs/tech/tech3285s5.pdf>`_
+* `EBU ADM Guidelines <https://adm.ebu.io>`_
+
+Dolby
+-----
+
+* `EBU Tech 3285 Supplement 6 — Dolby Metadata <https://tech.ebu.ch/docs/tech/tech3285s6.pdf>`_
+* `Dolby Laboratories Atmos ADM Profile <https://developer.dolby.com/globalassets/documentation/technology/dolby_atmos_master_adm_profile_v1.0.pdf>`_
+
+iXML
+----
+
+* `Gallery Software iXML Specification <http://www.gallery.co.uk/ixml/>`_
+
+
+RIFF Metadata
+-------------
+* `1991. Multimedia Programming Interface and Data Specifications 1.0 <https://www.aelius.com/njh/wavemetatools/doc/riffmci.pdf>`_
+* `Exiftool Documentation <https://exiftool.org/TagNames/RIFF.html#Info_docs>`_
+

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 +1,88 @@
+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
+
+
+.. note::
+   All text fields in the Broadcast-WAV metadata structure are decoded by 
+   default as flat ASCII. To override this and use a different encoding, pass
+   an string encoding name to the ``bext_encoding`` parameter of
+   :py:meth:`WavInfoReader()<wavinfo.wave_reader.WavInfoReader.__init__>`
+
+
+Example
+-------
+..  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/cue.rst

@@ -0,0 +1,31 @@
+Cue Marker and Range Metadata
+------------------------------
+
+Notes
+=====
+
+Cue metadata stores timed markers that clients use to mark times of interest
+in a wave file, and optionally give them a name and longer comment. Markers 
+can also have an associated length, allowing ranges of times in a file to be 
+marked.
+
+String Encoding of Cue Metadata
+"""""""""""""""""""""""""""""""
+
+Cue labels and notes will be decoded using the string encoding passed to
+:py:meth:`WavInfoReader's<wavinfo.wave_reader.WaveInfoReader.__init__>`
+``info_encoding=`` parameter, which by default is ``latin_1`` (ISO 8859-1).
+
+Text associated with ``ltxt`` time ranges may specify their own encoding in 
+the form of a Windows codepage number. `wavinfo` will attempt to use the
+encoding specified.
+
+.. note::
+   ``cset`` character set/locale metadata is not supported. If it is present
+   in the file it will be ignored by `wavinfo`.
+
+Class Reference
+===============
+
+.. autoclass:: wavinfo.wave_cues_reader.WavCuesReader
+   :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)
+
+
+String Encoding of INFO Metadata
+""""""""""""""""""""""""""""""""
+
+Info metadata fields will be decoded using the string encoding passed to
+:py:meth:`WavInfoReader's<wavinfo.wave_reader.WaveInfoReader.__init__>`
+``info_encoding=`` parameter, which by default is ``latin_1`` (ISO 8859-1).
+
+.. note::
+   ``cset`` character set/locale metadata is not supported. If it is present
+   in the file it will be ignored by `wavinfo`.
+
+Class Reference
+---------------
+
+.. autoclass:: wavinfo.wave_info_reader.WavInfoChunkReader
+   :members:
+
+
+
+

docs/source/scopes/ixml.rst

@@ -0,0 +1,48 @@
+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:
+
+Steinberg-Specific iXML Metadata
+--------------------------------
+
+.. autoclass:: wavinfo.wave_ixml_reader.SteinbergMetadata
+   :members:
+

examples/demo.ipynb

@@ -6,7 +6,16 @@
    "source": [
     "# `wavinfo` Demonstration\n",
     "\n",
-    "The entry point for wavinfo is the WavInfoReader class."
+    "The `wavinfo` module allows you to read most of the metadata formats that are available for WAV files."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Opening a WAV file for reading metadata\n",
+    "\n",
+    "The entry point for wavinfo is the `WavInfoReader` class:"
    ]
   },
   {
@@ -26,7 +35,35 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Basic WAV Data\n",
+    "Once you have a `WavInfoReader`, you can access different metadata systems or \"scopes.\"\n",
+    "\n",
+    "The scopes that are presently supported are: \n",
+    "  * `fmt`: sample format, sample rate, bit depth, block alignment, etc.\n",
+    "  * `data`: data chunk description, bytes length and frames length.\n",
+    "  * `ixml`: Gallery Software's iXML metadata, used by production sound recorder equipment and DAWs.\n",
+    "  * `bext`: Broacast-WAV metadata as used by DAWs.\n",
+    "  * `info`: title, artist and description metadata tags, among other items.\n",
+    "  * `adm`: EBU Audio Defintion Model metadata, as used by Dolby Atmos.\n",
+    "  * `cues`: Cue marker metadata, including labels and notes \n",
+    "  * `dolby`: Dolby recorder and playback metadata\n",
+    "\n",
+    "Each of these is an attribute of a `WavInfoReader` object.\n",
+    "\n",
+    "Each scope corresponds to a vendor-defined metadata system. Many scopes directly represent a specific file *chunk*, like `fmt` or `ixml`, and some may involve data read from many chunks. Examples of this would include `cues` or `adm`.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Metadata Scopes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### `data` and `fmt`: Basic WAV Data\n",
     "\n",
     "The length of the file in frames (interleaved samples) and bytes is available, as is the contents of the format chunk."
    ]
@@ -51,6 +88,13 @@
     "(info.data.frame_count, info.data.byte_count)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The `fmt` scope allows the client to read metadata from the WAVE format description."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 3,
@@ -75,7 +119,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Broadcast WAV Extension"
+    "### `bext`: Broadcast WAV Extension\n",
+    "\n",
+    "The `bext` scope allows the client to access Broadcast-WAV metadata. "
    ]
   },
   {
@@ -87,17 +133,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "sSPEED=023.976-ND\r\n",
-      "sTAKE=1\r\n",
-      "sUBITS=$12311801\r\n",
-      "sSWVER=2.67\r\n",
-      "sPROJECT=BMH\r\n",
-      "sSCENE=A101\r\n",
-      "sFILENAME=A101_1.WAV\r\n",
-      "sTAPE=18Y12M31\r\n",
-      "sTRK1=MKH516 A\r\n",
-      "sTRK2=Boom\r\n",
-      "sNOTE=\r\n",
+      "sSPEED=023.976-ND\n",
+      "sTAKE=1\n",
+      "sUBITS=$12311801\n",
+      "sSWVER=2.67\n",
+      "sPROJECT=BMH\n",
+      "sSCENE=A101\n",
+      "sFILENAME=A101_1.WAV\n",
+      "sTAPE=18Y12M31\n",
+      "sTRK1=MKH516 A\n",
+      "sTRK2=Boom\n",
+      "sNOTE=\n",
       "\n",
       "----------\n",
       "Originator: Sound Dev: 702T S#GR1112089007\n",
@@ -105,7 +151,7 @@
       "Originator Date: 2018-12-31\n",
       "Originator Time: 12:40:00\n",
       "Time Reference: 2190940753\n",
-      "A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch\r\n",
+      "A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch\n",
       "\n"
      ]
     }
@@ -125,7 +171,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## iXML Production Recorder Metadata"
+    "### `ixml`: iXML Production Recorder Metadata"
    ]
   },
   {
@@ -156,11 +202,83 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "### `cues`: Cues Metadata\n",
+    "\n",
+    "Cue time markers are accessible through the `cues` scope. The `each_cue` method returns an iterator that yields a tuple of each cue \"name\" or integer UID, and sample location. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Cue ID: 1\n",
+      "Cue Offset: 29616\n",
+      "Cue ID: 2\n",
+      "Cue Offset: 74592\n",
+      "Cue ID: 3\n",
+      "Cue Offset: 121200\n"
+     ]
+    }
+   ],
+   "source": [
+    "path = \"../tests/test_files/cue_chunks/STE-000.wav\"\n",
+    "info = WavInfoReader(path)\n",
+    "\n",
+    "for cue in info.cues.each_cue():\n",
+    "    print(f\"Cue ID: {cue[0]}\")\n",
+    "    print(f\"Cue Offset: {cue[1]}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "There is also a convenience method to get the appropriate label and note for a given marker. (Note here also `WavInfoReader`'s facility for overriding default text encodings.)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Cue ID: 1\n",
+      "    Label: Marker 1\n",
+      "    At: 1000\n",
+      "    Note: <NO NOTE>\n",
+      "Cue ID: 2\n",
+      "    Label: Marker 2\n",
+      "    At: 5000\n",
+      "    Note: Marker Comment 1\n",
+      "Cue ID: 3\n",
+      "    Label: Marker 3\n",
+      "    At: 10000\n",
+      "    Note: Лорем ипсум долор сит амет, тимеам вивендум хас ет, цу адолесценс дефинитионес еам.\n"
+     ]
+    }
+   ],
+   "source": [
+    "path = \"../tests/test_files/cue_chunks/izotoperx_cues_test.wav\"\n",
+    "info = WavInfoReader(path, info_encoding=\"utf-8\") # iZotope RX seems to encode marker text as UTF-8\n",
+    "\n",
+    "for cue in info.cues.each_cue():\n",
+    "    print(f\"Cue ID: {cue[0]}\")\n",
+    "    label, note = info.cues.label_and_note(cue[0])\n",
+    "    print(f\"    Label: {label}\")\n",
+    "    print(f\"    At: {cue[1]}\")\n",
+    "    print(f\"    Note: {note or '<NO NOTE>'}\")"
+   ]
   },
   {
    "cell_type": "code",
@@ -172,7 +290,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -186,9 +304,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.2"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

examples/wavinfo.ipynb

@@ -1,215 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import wavinfo\n",
-    "import pprint"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pp = pprint.PrettyPrinter(indent=4)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "path = '../tests/test_files/protools/PT A101_4.A1.wav'\n",
-    "\n",
-    "info = wavinfo.WavInfoReader(path)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[   ChunkDescriptor(ident=b'bext', start=20, length=858),\n",
-      "    ChunkDescriptor(ident=b'iXML', start=886, length=5226),\n",
-      "    ChunkDescriptor(ident=b'fmt ', start=6120, length=16),\n",
-      "    ChunkDescriptor(ident=b'data', start=6144, length=864840),\n",
-      "    ChunkDescriptor(ident=b'umid', start=870992, length=24),\n",
-      "    ChunkDescriptor(ident=b'minf', start=871024, length=16),\n",
-      "    ChunkDescriptor(ident=b'regn', start=871048, length=92)]\n"
-     ]
-    }
-   ],
-   "source": [
-    "import wavinfo.wave_parser\n",
-    "\n",
-    "with open(path,'rb') as f:\n",
-    "    chunk_tree = wavinfo.wave_parser.parse_chunk(f)\n",
-    "\n",
-    "pp.pprint(chunk_tree.children)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "b'\\x00\\x00\\x00\\x00\\x00\\x00\\x00*\\xfd\\xf5\\x0c$\\xe4s\\x80\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\n",
-      "000000000000002afdf50c24e47380000000000000000000\n",
-      "24\n"
-     ]
-    }
-   ],
-   "source": [
-    "with open(path,'rb') as f:\n",
-    "    f.seek( chunk_tree.children[4].start )\n",
-    "    umid_bin = f.read(chunk_tree.children[4].length)\n",
-    "    f.seek( chunk_tree.children[6].start )\n",
-    "    regn_bin = f.read(chunk_tree.children[6].length)\n",
-    "    \n",
-    "print(umid_bin)\n",
-    "print(umid_bin.hex())\n",
-    "print(len(umid_bin))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<wavinfo.wave_bext_reader.WavBextReader object at 0x10d5f8ac8>\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(info.bext)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "b'\\x01\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00*\\xfd\\xf5\\x0c$\\xe4s\\x80\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x0c3\\x02\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00T\\xd5\\xa2\\x82\\x00\\x00\\x00\\x00\\x10PT A101_4.A1.wavGK\\xaa\\xaf\\x7f\\x00\\x00@ }\\x06\\x00`\\x00\\x00'\n",
-      "01000000000000000000002afdf50c24e473800000000000000000000c330200000000000000000000000000000000000000000054d5a2820000000010505420413130315f342e41312e776176474baaaf7f000040207d0600600000\n",
-      "92\n"
-     ]
-    }
-   ],
-   "source": [
-    "\n",
-    "print(regn_bin)\n",
-    "print(regn_bin.hex())\n",
-    "print(len(regn_bin))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{   'artist': 'Frank Bry',\n",
-      "    'comment': 'BULLET Impact Plastic LCD TV Screen Shatter Debris 2x',\n",
-      "    'copyright': '2018 Creative Sound Design, LLC (The Recordist Christmas '\n",
-      "                 '2018) www.therecordist.com',\n",
-      "    'created_date': '2018-11-15',\n",
-      "    'engineer': None,\n",
-      "    'genre': 'Bullets',\n",
-      "    'keywords': None,\n",
-      "    'product': 'The Recordist Christmas 2018',\n",
-      "    'software': 'Soundminer',\n",
-      "    'source': None,\n",
-      "    'tape': None,\n",
-      "    'title': None}\n",
-      "{   'coding_history': '',\n",
-      "    'description': 'BULLET Impact Plastic LCD TV Screen Shatter Debris 2x',\n",
-      "    'loudness_range': None,\n",
-      "    'loudness_value': None,\n",
-      "    'max_momentary_loudness': None,\n",
-      "    'max_shortterm_loudness': None,\n",
-      "    'max_true_peak': None,\n",
-      "    'originator': 'TheRecordist',\n",
-      "    'originator_date': '2018-12-20',\n",
-      "    'originator_ref': 'aaiAKt3fCGTk',\n",
-      "    'originator_time': '12:15:37',\n",
-      "    'time_reference': 57882,\n",
-      "    'version': 0}\n"
-     ]
-    }
-   ],
-   "source": [
-    "path = '../tests/test_files/BULLET Impact Plastic LCD TV Screen Shatter Debris 2x.wav'\n",
-    "\n",
-    "info = wavinfo.WavInfoReader(path)\n",
-    "\n",
-    "with open(path,'rb') as f:\n",
-    "    chunk_tree = wavinfo.wave_parser.parse_chunk(f)\n",
-    "    \n",
-    "pp.pprint(info.info.to_dict())\n",
-    "pp.pprint(info.bext.to_dict())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

pypi_upload.sh

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

pyproject.toml

@@ -0,0 +1,74 @@
+[build-system]
+requires = ["flit_core >=3.2,<4"]
+build-backend = "flit_core.buildapi"
+
+[project]
+name = "wavinfo"
+authors = [{name = "Jamie Hardt", email = "jamiehardt@me.com"}]
+readme = "README.md"
+dynamic = ["version", "description"]
+requires-python = "~=3.8"
+classifiers = [
+    'Development Status :: 5 - Production/Stable',
+    'License :: OSI Approved :: MIT License',
+    'Topic :: Multimedia',
+    'Topic :: Multimedia :: Sound/Audio',
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12"
+]
+dependencies = [
+    "lxml ~= 4.9.2"
+]
+keywords = [
+    'waveform', 
+    'metadata', 
+    'audio', 
+    'ebu', 
+    'smpte', 
+    'avi', 
+    'library', 
+    'film', 
+    'broadcast' 
+]
+
+[tool.flit.module]
+name = "wavinfo"
+
+[project.optional-dependencies]
+doc = [
+    'sphinx >= 5.3.0',
+    'sphinx_rtd_theme >= 1.1.1',
+]
+
+[project.urls]
+Home = "https://github.com/iluvcapra/wavinfo"
+Documentation = "https://wavinfo.readthedocs.io/"
+Source = "https://github.com/iluvcapra/wavinfo.git"
+Issues = 'https://github.com/iluvcapra/wavinfo/issues' 
+
+[project.entry_points.console_scripts]
+wavinfo = 'wavinfo.__main__:main'
+
+[project.scripts]
+wavinfo = "wavinfo.__main__:main"
+
+[tool.flit.external-data]
+directory = "data"
+
+[tool.pyright]
+typeCheckingMode = "basic"
+
+[tool.pylint]
+max-line-length = 88
+disable = [
+    "C0103", # (invalid-name)
+    "C0114", # (missing-module-docstring)
+    "C0115", # (missing-class-docstring)
+    "C0116", # (missing-function-docstring)
+    "R0903", # (too-few-public-methods)
+    "R0913", # (too-many-arguments)
+    "W0105", # (pointless-string-statement)
+]

setup.py

@@ -1,20 +0,0 @@
-from setuptools import setup
-
-with open("README.md", "r") as fh:
-    long_description = fh.read()
-
-setup(name='wavinfo',
-      version='1.0',
-      author='Jamie Hardt',
-      author_email='jamiehardt@me.com',
-      description='WAVE sound file metadata parser.',
-      long_description_content_type="text/markdown",
-      long_description=long_description,
-      url='https://github.com/iluvcapra/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'])

tests/__init__.py

@@ -1,2 +1,44 @@
 from . import test_wave_parsing
 
+from io import BytesIO
+from typing import Generator
+import zipfile as zf
+import os.path
+import os
+from contextlib import contextmanager
+
+# class TestFileLoader:
+#     """
+#     This guy manages the test_files archive.
+#     """
+
+#     def __init__(self, test_file_arch_name = 'archive.zip') -> None:
+#         self.base_path = os.path.join(os.path.dirname(__file__), "test_files")
+#         self.test_file_arch_name = test_file_arch_name
+#         self._gather_test_files_into_archive()
+
+#     @property
+#     def arch_path(self):
+#         return os.path.join(self.base_path, self.test_file_arch_name)        
+
+#     @contextmanager
+#     def open(self, name) -> Generator[BytesIO]:
+#         z = zf.ZipFile(self.arch_path, 'r')
+#         member = z.open(name, 'r')
+#         try:
+#             yield member
+#         finally:
+#             zf.close()
+
+#     def _gather_test_files_into_archive(self):
+#         with zf.ZipFile(self.arch_path, 'a') as zip:
+#             for root, _, files in os.walk(self.base_path):
+#                 for name in files:
+#                     if root == self.base_path and name == self.test_file_arch_name:
+#                         continue
+#                     else:
+#                         p = os.path.join(root, name)
+#                         zip.write(p)
+#                         os.unlink(p)
+
+

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_cue.py

@@ -0,0 +1,74 @@
+from unittest import TestCase
+from glob import glob
+
+import wavinfo
+
+class TestCue(TestCase):
+    def setUp(self) -> None:
+        self.test_files = glob("tests/test_files/cue_chunks/*.wav") 
+        return super().setUp()
+
+    def test_enumerate(self):
+        file1 = "tests/test_files/cue_chunks/STE-000.wav"
+        w1 = wavinfo.WavInfoReader(file1)
+        self.assertIsNotNone(w1.cues)
+        vals = list(w1.cues.each_cue())
+        self.assertEqual(vals, [(1,29616),(2,74592),(3,121200)])
+
+    def test_labels_notes(self):
+        file = "tests/test_files/cue_chunks/izotoperx_cues_test.wav"
+        w1 = wavinfo.WavInfoReader(file)
+        self.assertIsNotNone(w1.cues)
+        assert w1.cues is not None
+
+        for name, _ in w1.cues.each_cue():
+            self.assertIn(name,[1,2,3])
+            label, note = w1.cues.label_and_note(name)
+            if name == 1:
+                self.assertEqual("Marker 1", label)
+                self.assertIsNone(note)
+
+    def test_range(self):
+        file = "tests/test_files/cue_chunks/izotoperx_cues_test.wav"
+        w1 = wavinfo.WavInfoReader(file)
+        self.assertIsNotNone(w1.cues)
+        assert w1.cues is not None
+
+        self.assertEqual(w1.cues.range(3), 10000) 
+
+    def test_encoding_fallback(self):
+        """
+        Added this after I noticed that iZotope RX seems to just encode "notes"
+        as utf-8 without bothering to dump this info into the ltxt or 
+        specifying an encoding by some other means.
+        """
+        file = "tests/test_files/cue_chunks/izotoperx_cues_test.wav"
+        w = wavinfo.WavInfoReader(file, info_encoding='utf-8')
+        expected = ("Лорем ипсум долор сит амет, тимеам вивендум хас ет, "  
+            "цу адолесценс дефинитионес еам.")
+
+        assert w.cues is not None
+        note = [n for n in w.cues.notes if n.name == 3]
+        self.assertEqual(len(note), 1)
+        self.assertEqual(note[0].text, expected)
+
+    def test_label(self):
+        file = "tests/test_files/cue_chunks/izotoperx_cues_test.wav"
+        w = wavinfo.WavInfoReader(file)
+        
+        self.assertIsNotNone(w.cues)
+        assert w.cues is not None  
+
+        self.assertEqual(len(w.cues.labels), 3)
+        for label in w.cues.labels:
+            self.assertIn(label.name, [1,2,3])
+            if label.name == 1:
+                self.assertEqual(label.text, "Marker 1")
+            elif label.name == 2:
+                self.assertEqual(label.text, "Marker 2")
+            elif label.name == 3:
+                self.assertEqual(label.text, "Marker 3")
+
+
+
+

tests/test_dolby.py

@@ -0,0 +1,52 @@
+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
+        
+        assert d is not None
+        self.assertEqual((1,0,0,6), d.version)
+
+    def test_segments(self):
+        t1 = wavinfo.WavInfoReader(self.test_file)
+        d = t1.dolby
+        assert d is not None
+
+        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
+        assert d is not None
+
+        for seg in d.segment_list:
+            self.assertTrue(seg[1])
+
+    def test_ddp(self):
+        t1 = wavinfo.WavInfoReader(self.test_file)
+        d = t1.dolby
+        assert d is not None
+        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
+        assert d is not None
+        atmos = d.dolby_atmos()
+        self.assertEqual(len(atmos), 1, "Failed to find exactly one Atmos metadata segment")
+
+    

tests/test_main.py

@@ -0,0 +1,33 @@
+import unittest
+
+from unittest.mock import patch
+
+from wavinfo.__main__ import main
+
+import sys
+import glob
+
+class MainTest(unittest.TestCase):
+    
+    def test_empty_argv(self): 
+        with patch.object(sys, 'argv', []):
+            try:
+                main()
+            except:
+                self.fail("main() throwing an exception")
+
+    def test_a_file(self):
+        for path in glob.glob("tests/test_files/**/*.wav"):
+            with patch.object(sys, 'argv', ["TEST", path]):
+                try:
+                    main()
+                except:
+                    self.fail("main() throwing an exception") 
+
+    def test_ixml(self):
+        with patch.object(sys, 'argv', 
+                          ['TEST', '--ixml', 'tests/test_files/sounddevices/A101_1.WAV']):
+            try:
+                main()
+            except:
+                self.fail("main() throwing an exception") 

tests/test_rf64.py

@@ -0,0 +1,25 @@
+# import os.path
+import gzip
+from glob import glob
+# from typing import Dict, Any, cast
+
+from unittest import TestCase
+
+# from .utils import all_files, ffprobe
+
+import wavinfo
+
+class TestRf64(TestCase):
+
+    def setUp(self) -> None:
+        return super().setUp()
+
+    def test_open(self):
+
+        for path in glob("tests/test_files/rf64/*.wav.gz"):
+            gz = gzip.open(path)
+            wav_info = wavinfo.WavInfoReader(gz)
+
+            self.assertIsNotNone(wav_info)
+            # self.assertIsNotNone(wav_info.bext)
+

tests/test_walk.py

@@ -0,0 +1,37 @@
+import unittest
+import wavinfo
+
+import glob
+
+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)
+
+    def test_walk_all(self):
+        for file in glob.glob('tests/test_files/**/*.wav'):
+            info = wavinfo.WavInfoReader(file)
+            
+            try:
+                for _, _, _ in info.walk():
+                    pass 
+            except:
+                self.fail(f"Failed to walk metadata in file {file}")
+
+        
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_wave_parsing.py

@@ -1,108 +1,145 @@
 import os.path
-import json
-import subprocess
-from subprocess import PIPE
+from glob import glob
+from typing import Dict, Any, cast
 
 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']) )
+            assert info.fmt is not None
+            assert ffprobe_info is not None
+
+            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'] ))
+            ffprobe_info = cast(Dict[str,Any], ffprobe(wav_file))
+            assert ffprobe_info is not None
+            assert info.data is not None
+            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)
+            assert ffprobe_info is not None
 
-            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 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, '')
 
-            # 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 'encoded_by' in ffprobe_info['format']['tags']:
+                    self.assertEqual(info.bext.originator, ffprobe_info['format']['tags']['encoded_by'])
+                else:
+                    self.assertEqual(info.bext.originator, '')
 
-            if '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, '' )
+                if 'originator_reference' in ffprobe_info['format']['tags']:
+                    self.assertEqual(info.bext.originator_ref, ffprobe_info['format']['tags']['originator_reference'])
+                else:
+                    self.assertEqual(info.bext.originator_ref, '')
+
+                # these don't always reflect the bext info
+                # self.assertEqual(info.bext.originator_date, ffprobe_info['format']['tags']['date'])
+                # self.assertEqual(info.bext.originator_time, ffprobe_info['format']['tags']['creation_time'])
+                self.assertEqual(info.bext.time_reference, int(ffprobe_info['format']['tags']['time_reference']))
+
+                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.assertIsNotNone(info.ixml)
+                assert info.ixml is not None 
+                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_steinberg_ixml(self):
+        nuendo_files = 'tests/test_files/nuendo/*.wav'
+        for file in glob(nuendo_files):
+            info = wavinfo.WavInfoReader(file)
+            assert info.ixml is not None 
+            self.assertIsNotNone(info.ixml.steinberg)
+            assert info.ixml.steinberg is not None
+            self.assertIsNotNone(info.ixml.steinberg.audio_speaker_arrangement)
+            self.assertEqual(info.ixml.steinberg.sample_format_size, 3) 
+            self.assertEqual(info.ixml.steinberg.media_company, "https://github.com/iluvcapra/wavinfo")
+            self.assertFalse(info.ixml.steinberg.media_drop_frames)
+            self.assertEqual(info.ixml.steinberg.media_duration, 1200.0)
+
+    def test_steinberg_missing(self):
+        file_with_no_nuendo = "tests/test_files/sounddevices/A101_1.WAV"
+
+        info = wavinfo.WavInfoReader(file_with_no_nuendo)
+        assert info.ixml is not None
+        self.assertIsNone(info.ixml.steinberg)
+
+    def test_info_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
+
+        assert info is not None
+        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)
 
-                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 )

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 +1,9 @@
-from .wave_reader import WavInfoReader
+"""
+Probe WAVE Files for iXML, Broadcast-WAVE and other metadata.
+"""
 
-__version__ = 1.0
-__author__ = 'Jamie Hardt'
+from .wave_reader import WavInfoReader
+from .riff_parser import WavInfoEOFError
+
+__version__ = '2.3.0'
+__short_version__ = '2.3.0'

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) <FILE> +'
+
+    # 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_str())
+                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 +1,42 @@
+import struct
+from collections import namedtuple
+
+from . import riff_parser
+
+RF64Context = namedtuple('RF64Context','sample_count bigchunk_table')
+
+
+def parse_rf64(stream, signature = b'RF64') -> RF64Context:
+    start = stream.tell()
+    assert( stream.read(4) == b'WAVE' )
+
+    ds64_chunk = riff_parser.parse_chunk(stream)
+    assert type(ds64_chunk) is riff_parser.ChunkDescriptor, \
+        f"Expected ds64 chunk here, found {type(ds64_chunk)}"
+
+    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)
+
+    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)
+
+    for _ 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)
+    return RF64Context( sample_count=sample_count,
+                       bigchunk_table=bigchunk_table)
+

wavinfo/riff_parser.py

@@ -1,59 +1,68 @@
 
 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') ):
-    def read_data(self, from_stream):
+class WavInfoEOFError(EOFError):
+    def __init__(self, identifier, chunk_start):
+        self.identifier = identifier
+        self.chunk_start = chunk_start
+
+
+class ListChunkDescriptor(namedtuple('ListChunkDescriptor', 'signature children')):
+    pass
+
+
+class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length rf64_context')):
+    def read_data(self, from_stream) -> bytes:
         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 data_size == 0xFFFFFFFF:
+        if rf64_context is None and ident in {b'RF64', b'BW64'}:
+            rf64_context = parse_rf64(stream=stream, signature=ident)
+
+        assert rf64_context is not None, \
+            f"Sentinel data size 0xFFFFFFFF found outside of RF64 context"
+        
+        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', b'list'}:
+        return parse_list_chunk(stream=stream, length=data_size,
+                                rf64_context=rf64_context)
 
-    if ident in [b'RIFF',b'LIST']:
-        return parse_list_chunk(stream=stream, length=size)
     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:
+        """
+        Read 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) -> dict:
+        """
+        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) -> dict: #FIXME should be "asdict"
+        """
+        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 +1,104 @@
 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
+        #: an 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.
+        self.originator_date : str = sanitize_bytes(unpacked[3])
+            
+        #: Time of the recording, in the format HH:MM:SS.
+        self.originator_time : str = sanitize_bytes(unpacked[4])
+            
+        #: The sample offset of the start, usually relative 
+        #: to midnight. 
+        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 range, 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_cues_reader.py

@@ -0,0 +1,272 @@
+"""
+Cues metadata
+
+For reference on implementation of cues and related metadata see: 
+August 1991, "Multimedia Programming Interface and Data Specifications 1.0",
+IBM Corporation and Microsoft Corporation
+
+https://www.aelius.com/njh/wavemetatools/doc/riffmci.pdf
+"""
+from dataclasses import dataclass
+import encodings
+from .riff_parser import ChunkDescriptor
+
+from struct import unpack, calcsize
+from typing import Optional, Tuple,  NamedTuple, List, Dict, Any, Generator
+
+#: Country Codes used in the RIFF standard to resolve locale. These codes 
+#: appear in CSET and LTXT metadata.
+CountryCodes = """000 None Indicated
+001,USA
+002,Canada
+003,Latin America
+030,Greece 
+031,Netherlands
+032,Belgium
+033,France
+034,Spain
+039,Italy
+041,Switzerland
+043,Austria
+044,United Kingdom
+045,Denmark
+046,Sweden
+047,Norway
+049,West Germany
+052,Mexico
+055,Brazil
+061,Australia
+064,New Zealand
+081,Japan
+082,Korea
+086,People’s Republic of China
+088,Taiwan
+090,Turkey
+351,Portugal
+352,Luxembourg
+354,Iceland 
+358,Finland"""
+
+#: Language and Dialect codes used in the RIFF standard to resolve native 
+#: language of text fields. These codes appear in CSET and LTXT metadata.
+LanguageDialectCodes = """0 0 None Indicated
+1,1,Arabic
+2,1,Bulgarian
+3,1,Catalan
+4,1,Traditional Chinese 
+4,2,Simplified Chinese 
+5,1,Czech
+6,1,Danish
+7,1,German
+7,2,Swiss German 
+8,1,Greek
+9,1,US English
+9,2,UK English 
+10,1,Spanish
+10,2,Spanish Mexican 
+11,1,Finnish
+12,1,French
+12,2,Belgian French 
+12,3,Canadian French 
+12,4,Swiss French 
+13,1,Hebrew 
+14,1,Hungarian
+15,1,Icelandic
+16,1,Italian
+16,2,Swiss Italian 
+17,1,Japanese
+18,1,Korean
+19,1,Dutch
+19,2,Belgian Dutch 
+20,1,Norwegian - Bokmal 
+20,2,Norwegian - Nynorsk 
+21,1,Polish
+22,1,Brazilian Portuguese 
+22,2,Portuguese 
+23,1,Rhaeto-Romanic 
+24,1,Romanian
+25,1,Russian
+26,1,Serbo-Croatian (Latin) 
+26,2,Serbo-Croatian (Cyrillic) 
+27,1,Slovak
+28,1,Albanian
+29,1,Swedish
+30,1,Thai
+31,1,Turkish
+32,1,Urdu
+33,1,Bahasa"""
+
+
+class CueEntry(NamedTuple):
+    name: int
+    position: int
+    chunk_id: bytes
+    chunk_start: int
+    block_start: int
+    sample_offset: int
+
+    Format = "<II4sIII"
+    
+    @classmethod
+    def format_size(cls) -> int:
+        return calcsize(cls.Format)
+
+    @classmethod
+    def read(cls, data: bytes) -> 'CueEntry':
+        assert len(data) == cls.format_size(), \
+            f"cue data size incorrect, expected {calcsize(cls.Format)} found {len(data)}"
+
+        parsed = unpack(cls.Format, data)
+
+        return cls(name=parsed[0], position=parsed[1], chunk_id=parsed[2],
+                   chunk_start=parsed[3], block_start=parsed[4], 
+                   sample_offset=parsed[5])
+
+
+class LabelEntry(NamedTuple):
+    name: int
+    text: str
+
+    @classmethod
+    def read(cls, data: bytes, encoding: str):
+        return cls(name=unpack("<I", data[0:4])[0],
+                   text=data[4:].decode(encoding).rstrip("\0"))
+
+
+NoteEntry = LabelEntry
+
+
+class RangeLabel(NamedTuple):
+    name: int
+    length: int
+    purpose: str
+    country: int
+    language: int
+    dialect: int
+    codepage: int
+    text: str
+
+    @classmethod
+    def read(cls, data: bytes, fallback_encoding: str):
+        leader_struct_fmt = "<II4sHHHH"
+        parsed = unpack(leader_struct_fmt, data[0:calcsize(leader_struct_fmt)])
+        text_data = data[calcsize(leader_struct_fmt):]
+
+        if data[6] != 0:
+            fallback_encoding = f"cp{data[6]}"
+
+        return cls(name=parsed[0], length=parsed[1], purpose=parsed[2],
+                   country=parsed[3], language=parsed[4], 
+                   dialect=parsed[5], codepage=parsed[6], 
+                   text=text_data.decode(fallback_encoding))
+
+
+@dataclass
+class WavCuesReader:
+    cues: List[CueEntry]
+    labels: List[LabelEntry]
+    ranges: List[RangeLabel]
+    notes: List[NoteEntry]
+
+    @classmethod
+    def read_all(cls, f,
+              cues: Optional[ChunkDescriptor], 
+              labls: List[ChunkDescriptor],
+              ltxts: List[ChunkDescriptor], 
+              notes: List[ChunkDescriptor],
+              fallback_encoding: str) -> 'WavCuesReader':
+        
+        cue_list = []
+        if cues is not None:
+            cues_data = cues.read_data(f)
+            assert len(cues_data) >= 4, "cue metadata too short"
+            offset = calcsize("<I")
+            cues_count = unpack("<I", cues_data[0:offset])
+            
+            for _ in range(cues_count[0]):
+                cue_bytes = cues_data[offset: offset + CueEntry.format_size()]
+                cue_list.append(CueEntry.read(cue_bytes))
+                offset += CueEntry.format_size()
+
+        label_list = []
+        for labl in labls:
+            label_list.append(
+                LabelEntry.read(labl.read_data(f), 
+                                encoding=fallback_encoding)
+            )
+
+        range_list = []
+        for r in ltxts:
+            range_list.append(
+                RangeLabel.read(r.read_data(f), 
+                                fallback_encoding=fallback_encoding)
+            )
+
+        note_list = []
+        for note in notes:
+            note_list.append(
+                NoteEntry.read(note.read_data(f),
+                               encoding=fallback_encoding)
+            )
+
+        return WavCuesReader(cues=cue_list, labels=label_list,
+                             ranges=range_list, notes=note_list)
+
+    def each_cue(self) -> Generator[Tuple[int, int], None, None]:
+        """
+        Iterate through each cue. 
+
+        :yields: the cue's ``name`` and ``sample_offset``
+        """
+        for cue in self.cues:
+            yield (cue.name, cue.sample_offset)
+
+    def label_and_note(self, cue_ident: int) -> Tuple[Optional[str],
+                                                      Optional[str]]: 
+        """
+        Get the label and note (extended comment) for a cue.
+
+        :param cue_ident: the cue's name, its unique identifying number
+        :returns: a tuple of the the cue's label (if present) and note (if
+            present) 
+        """
+        label = next((l.text for l in self.labels 
+                      if l.name == cue_ident), None)
+        note = next((n.text for n in self.notes 
+                     if n.name == cue_ident), None)
+        return (label, note)
+
+    def range(self, cue_ident: int) -> Optional[int]:
+        """
+        Get the length of the time range for a cue, if it has one.
+
+        :param cue_ident: the cue's name, its unique identifying number
+        :returns: the length of the marker's range, or `None`
+        """
+        return next((r.length for r in self.ranges 
+                     if r.name == cue_ident), None)
+
+    def to_dict(self) -> Dict[str, Any]:
+        retval = dict()
+
+        for n, t in self.each_cue():
+            retval[n] = dict()
+            retval[n]['frame'] = t
+            label, note = self.label_and_note(n)
+            r = self.range(n)
+
+            if label is not None:
+                retval[n]['label'] = label
+            if note is not None:
+                retval[n]['note'] = note  
+            if r is not None:
+                retval[n]['length'] = r 
+        
+        return retval 
+        # return dict(cues=[c._asdict() for c in self.cues],
+        #             labels=[l._asdict() for l in self.labels],
+        #             ranges=[r._asdict() for r in self.ranges],
+        #             notes=[n._asdict() for n in self.notes])
+
+
+