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

Removed UMID parsing for now, to improve test coverage

.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

@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v2.5.0
@@ -28,7 +28,7 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         python -m pip install flake8 pytest
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+        python -m pip install -e .
     - name: Setup FFmpeg
       uses: FedericoCarboni/setup-ffmpeg@v2
     - name: Lint with flake8

.github/workflows/pythonpublish.yml

@@ -16,13 +16,13 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install setuptools wheel twine lxml
+        pip install setuptools build wheel twine lxml
     - name: Build and publish
       env:
         TWINE_USERNAME: __token__
         TWINE_PASSWORD: ${{ secrets.PYPI_APIKEY }}
       run: |
-        python setup.py sdist bdist_wheel
+        python -m build .
         twine upload dist/*
     - name: Report to Mastodon
       uses: cbrgm/mastodon-github-action@v1.0.1

.readthedocs.yaml

@@ -25,5 +25,8 @@ formats:
 
 #Optionally declare the Python requirements required to build your docs
 python:
-   install:
+  install:
-   - requirements: requirements.txt
+    - method: pip
+      path: .
+      extra_requirements:
+        - doc

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.

LICENSE

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

@@ -1,36 +1,41 @@
 [![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 metadata.
+The `wavinfo` package allows you to probe WAVE and [RF64/WAVE files][eburf64] 
+and extract extended metadata, with an emphasis on film, video and 
+professional music production.
 
 
 ## Metadata Support
 
 `wavinfo` reads:
 
-* [__Broadcast-WAVE__][ebu] metadata, including embedded program
+* [Broadcast-WAVE][bext] metadata, including embedded program
-  loudness, coding history and [__SMPTE UMID__][smpte_330m2011].
+  loudness, coding history and [SMPTE UMID][smpte_330m2011].
-* [__ADM__][adm] track metadata and schema, including channel, pack formats, object, content and programme.
+* [Audio Definition Model (ADM)][adm] track metadata and schema, including 
-* [__Dolby Digital Plus__][ebu3285s6] and Dolby Atmos `dbmd` metadata.
+  channel, pack formats, 
-* [__iXML__][ixml] production recorder metadata, including project, scene, and take tags, recorder notes
+  object, content and programme.
-  and file family information.
+* [Dolby Digital Plus][ebu3285s6] and Dolby Atmos `dbmd` metadata.
-* Most of the common [__RIFF INFO__][info-tags] metadata fields.
+* [iXML][ixml] production recorder metadata, including project, scene, and 
-* The __wav format__ is also parsed, so you can access the basic sample rate and channel count
+  take tags, recorder notes and file family information.
-  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:
+[bext]:https://wavinfo.readthedocs.io/en/latest/scopes/bext.html
-* Pro Tools __embedded regions__.
+[smpte_330m2011]:https://wavinfo.readthedocs.io/en/latest/scopes/bext.html#wavinfo.wave_bext_reader.WavBextReader.umid
-* iXML `STEINBERG` sound library attributes.
+[adm]:https://wavinfo.readthedocs.io/en/latest/scopes/adm.html
-
+[ebu3285s6]:https://wavinfo.readthedocs.io/en/latest/scopes/dolby.html
-[ebu]:https://tech.ebu.ch/docs/tech/tech3285.pdf
+[ixml]:https://wavinfo.readthedocs.io/en/latest/scopes/ixml.html
-[ebu3285s6]:https://tech.ebu.ch/docs/tech/tech3285s6.pdf
+[info-tags]:https://wavinfo.readthedocs.io/en/latest/scopes/info.html
-[adm]:https://www.itu.int/dms_pubrec/itu-r/rec/bs/R-REC-BS.2076-2-201910-I!!PDF-E.pdf
-[smpte_330m2011]:http://standards.smpte.org/content/978-1-61482-678-1/st-330-2011/SEC1.abstract
-[ixml]:http://www.ixml.info
 [eburf64]:https://tech.ebu.ch/docs/tech/tech3306v1_1.pdf
-[info-tags]:https://exiftool.org/TagNames/RIFF.html#Info
+
 
 ## How To Use
 
@@ -55,4 +60,5 @@ $ wavinfo test_files/A101_1.WAV
 
 ## Other Resources
 
-* For other file formats and ID3 decoding, look at [audio-metadata](https://github.com/thebigmunch/audio-metadata).
+* 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/requirements.txt

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

docs/source/conf.py

@@ -23,11 +23,11 @@ import wavinfo
 # -- Project information -----------------------------------------------------
 
 project = u'wavinfo'
-copyright = u'2022, Jamie Hardt'
+copyright = u'2018-2023, Jamie Hardt'
 author = u'Jamie Hardt'
 
 # The short X.Y version
-version = wavinfo.__version__
+version = wavinfo.__short_version__
 # The full version, including alpha/beta/rc tags
 release = wavinfo.__version__
 

docs/source/index.rst

@@ -19,8 +19,8 @@ music production metadata.
    quickstart
    command_line
    scopes/*
-
    classes
+   references
 
 
 Indices and tables

docs/source/quickstart.rst

@@ -15,10 +15,16 @@ instance of :class:`WaveInfoReader`.
 
     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/bext.rst

@@ -4,32 +4,45 @@ Broadcast WAV Extension Metadata
 
 Notes
 -----
-A WAV file produced to Broadcast-WAV specifications will have the broadcast metadata extension,
+A WAV file produced to Broadcast-WAV specifications will have the broadcast
-which includes a 256-character free text descrption, creating entity identifier (usually the 
+metadata extension, which includes a 256-character free text descrption,
-recording application or equipment), the date and time of recording and a time reference for 
+creating entity identifier (usually the recording application or equipment),
-timecode synchronization.
+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
+In this example (from a Sound Devices 702T) the bext metadata contains
-information in the :py:attr:`description<wavinfo.wave_bext_reader.WavBextReader.description>`. 
+scene/take slating information in the
-Here also the :py:attr:`originator_ref<wavinfo.wave_bext_reader.WavBextReader.originator_ref>` 
+: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 
+If the bext metadata conforms to `EBU 3285 v1`_, it will contain the WAV's 32
-ST 330 UMID`_. The 32-byte version of the UMID is usually just a random number, while the 64-byte 
+or 64 byte `SMPTE ST 330 UMID`_. The 32-byte version of the UMID is usually
-UMID will also have information on the recording date and time, recording equipment and entity, 
+just a random number, while the 64-byte UMID will also have information on the
-and geolocation data.
+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
+If the bext metadata conforms to `EBU 3285 v2`_, it will hold precomputed
-as described by `EBU Rec 128`_.
+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)

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/info.rst

@@ -20,16 +20,16 @@ music library software.
     print("INFO Comment:",   bullet.info.comment)
 
 
-On Encodings
+String Encoding of INFO Metadata
-""""""""""""
+""""""""""""""""""""""""""""""""
-According to Microsoft, the original developers of the RIFF file and RIFF INFO 
-metadata, these fields are always to be interpreted as ISO Latin 1 characters, 
-and this is the default encoding used by `wavinfo` for these fields. You can
-select a different encoding (like Shift-JIS) by passing an encoding name (as 
-would be used by `string.encode()`) to `WavInfoReader.__init__()`'s
-`info_encoding=` parameter.
 
+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
 ---------------

docs/source/scopes/ixml.rst

@@ -40,4 +40,9 @@ 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",
+      "sSPEED=023.976-ND\n",
-      "sTAKE=1\r\n",
+      "sTAKE=1\n",
-      "sUBITS=$12311801\r\n",
+      "sUBITS=$12311801\n",
-      "sSWVER=2.67\r\n",
+      "sSWVER=2.67\n",
-      "sPROJECT=BMH\r\n",
+      "sPROJECT=BMH\n",
-      "sSCENE=A101\r\n",
+      "sSCENE=A101\n",
-      "sFILENAME=A101_1.WAV\r\n",
+      "sFILENAME=A101_1.WAV\n",
-      "sTAPE=18Y12M31\r\n",
+      "sTAPE=18Y12M31\n",
-      "sTRK1=MKH516 A\r\n",
+      "sTRK1=MKH516 A\n",
-      "sTRK2=Boom\r\n",
+      "sTRK2=Boom\n",
-      "sNOTE=\r\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",
+   "cell_type": "markdown",
-   "execution_count": null,
    "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
-}

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)
+]

requirements.txt

@@ -1 +0,0 @@
-lxml==4.9.1

setup.py

@@ -1,40 +0,0 @@
-from setuptools import setup
-from wavinfo import __author__, __license__, __version__
-
-with open("README.md", "r") as fh:
-    long_description = fh.read()
-
-setup(name='wavinfo',
-      version=__version__,
-      author=__author__,
-      author_email='jamiehardt@me.com',
-      description='Probe WAVE Files for iXML, Broadcast-WAVE and other metadata.',
-      long_description_content_type="text/markdown",
-      long_description=long_description,
-      license=__license__,
-      url='https://github.com/iluvcapra/wavinfo',
-      project_urls={
-          'Source':
-              'https://github.com/iluvcapra/wavinfo',
-          'Documentation':
-              'https://wavinfo.readthedocs.io/',
-          'Issues':
-              'https://github.com/iluvcapra/wavinfo/issues',
-      },
-      packages=['wavinfo'],
-      classifiers=['Development Status :: 5 - Production/Stable',
-          'License :: OSI Approved :: MIT License',
-          'Topic :: Multimedia',
-          'Topic :: Multimedia :: Sound/Audio',
-          "Programming Language :: Python :: 3.8",
-          "Programming Language :: Python :: 3.9",
-          "Programming Language :: Python :: 3.10",
-          "Programming Language :: Python :: 3.11"],
-      keywords='waveform metadata audio ebu smpte avi library film tv editing editorial',
-      install_requires=['lxml'],
-      entry_points={
-          'console_scripts': [
-              'wavinfo = wavinfo.__main__:main'
-          ]
-      }
-      )

tests/__init__.py

@@ -1,3 +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_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

@@ -11,11 +11,13 @@ class TestDolby(TestCase):
         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]
@@ -26,6 +28,7 @@ class TestDolby(TestCase):
     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])
@@ -33,7 +36,7 @@ class TestDolby(TestCase):
     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 )
@@ -42,7 +45,7 @@ class TestDolby(TestCase):
     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

@@ -1,6 +1,7 @@
 import unittest
 import wavinfo
 
+import glob
 
 class TestWalk(unittest.TestCase):
     def test_walk_metadata(self):
@@ -20,6 +21,17 @@ class TestWalk(unittest.TestCase):
 
         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

@@ -1,4 +1,6 @@
 import os.path
+from glob import glob
+from typing import Dict, Any, cast
 
 from unittest import TestCase
 
@@ -19,6 +21,9 @@ class TestWaveInfo(TestCase):
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
 
+            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']))
@@ -32,13 +37,17 @@ class TestWaveInfo(TestCase):
     def test_data_against_ffprobe(self):
         for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
-            ffprobe_info = ffprobe(wav_file)
+            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 all_files():
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
+            assert ffprobe_info is not None
+
             if info.bext:
                 if 'comment' in ffprobe_info['format']['tags']:
                     self.assertEqual(info.bext.description, ffprobe_info['format']['tags']['comment'])
@@ -81,7 +90,8 @@ class TestWaveInfo(TestCase):
             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)
@@ -93,10 +103,32 @@ class TestWaveInfo(TestCase):
                     if basename == 'A101_4.WAV' and track.channel_index == '1':
                         self.assertEqual(track.name, 'MKH516 A')
 
-    def test_metadata(self):
+    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')

wavinfo/__init__.py

@@ -1,12 +1,9 @@
 """
-methods to probe a WAV file for various kinds of production metadata.
+Probe WAVE Files for iXML, Broadcast-WAVE and other metadata.
-
-See the documentation for `wavinfo.WavInfoReader` for more information.
 """
 
 from .wave_reader import WavInfoReader
 from .riff_parser import WavInfoEOFError
 
-__version__ = '2.1.0'
+__version__ = '2.3.0'
-__author__ = 'Jamie Hardt <jamiehardt@gmail.com>'
+__short_version__ = '2.3.0'
-__license__ = "MIT"

wavinfo/__main__.py

@@ -19,7 +19,7 @@ class MissingDataError(RuntimeError):
 def main():
     parser = OptionParser()
 
-    parser.usage = 'wavinfo (--adm | --ixml) [FILES]'
+    parser.usage = 'wavinfo (--adm | --ixml) <FILE> +'
 
     # parser.add_option('-f', dest='output_format', help='Set the output format',
     #                   default='json',
@@ -42,7 +42,7 @@ def main():
                     raise MissingDataError("adm")
             elif options.ixml:
                 if this_file.ixml:
-                    sys.stdout.write(this_file.ixml.xml_bytes())
+                    sys.stdout.write(this_file.ixml.xml_str())
                 else:
                     raise MissingDataError("ixml")
             else:

wavinfo/rf64_parser.py

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

wavinfo/riff_parser.py

@@ -12,21 +12,10 @@ class WavInfoEOFError(EOFError):
 
 class ListChunkDescriptor(namedtuple('ListChunkDescriptor', 'signature children')):
     pass
-    # def find(self, chunk_path):
-    #     if len(chunk_path) > 1:
-    #         for chunk in self.children:
-    #             if type(chunk) is ListChunkDescriptor and \
-    #                     chunk.signature is chunk_path[0]:
-    #                 return chunk.find(chunk_path[1:])
-    #     else:
-    #         for chunk in self.children:
-    #             if type(chunk) is ChunkDescriptor and \
-    #                     chunk.ident is chunk_path[0]:
-    #                 return chunk
 
 
 class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length rf64_context')):
-    def read_data(self, from_stream):
+    def read_data(self, from_stream) -> bytes:
         from_stream.seek(self.start)
         return from_stream.read(self.length)
 
@@ -59,15 +48,21 @@ def parse_chunk(stream, rf64_context=None):
         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'}:
+    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)
+        return parse_list_chunk(stream=stream, length=data_size,
+                                rf64_context=rf64_context)
+
     else:
         data_start = stream.tell()
         stream.seek(displacement, 1)
-        return ChunkDescriptor(ident=ident, start=data_start, length=data_size, rf64_context=rf64_context)
+        return ChunkDescriptor(ident=ident, start=data_start, length=data_size,
+                               rf64_context=rf64_context)

wavinfo/umid_parser.py

@@ -1,18 +1,18 @@
-from functools import reduce
+# from functools import reduce
 
 
-def binary_to_string(binary_value):
+# def binary_to_string(binary_value):
-    return reduce(lambda val, el: val + "{:02x}".format(el), binary_value, '')
+#     return reduce(lambda val, el: val + "{:02x}".format(el), binary_value, '')
 
 
-class UMIDParser:
+# class UMIDParser:
-    """
+#     """
-    Parse a raw binary SMPTE 330M Universal Materials Identifier
+#     Parse a raw binary SMPTE 330M Universal Materials Identifier
-
+#
-    This implementation is based on SMPTE ST 330:2011
+#     This implementation is based on SMPTE ST 330:2011
-    """
+#     """
-    def __init__(self, raw_umid: bytes):
+#     def __init__(self, raw_umid: bytes):
-        self.raw_umid = raw_umid
+#         self.raw_umid = raw_umid
     #
     # @property
     # def universal_label(self) -> bytearray:
@@ -22,8 +22,8 @@ class UMIDParser:
     # def basic_umid(self):
     #     return self.raw_umid[0:32]
 
-    def basic_umid_to_str(self):
+    # def basic_umid_to_str(self):
-        return binary_to_string(self.raw_umid[0:32])
+    #     return binary_to_string(self.raw_umid[0:32])
     #
     # @property
     # def universal_label_is_valid(self) -> bool:

wavinfo/wave_adm_reader.py

@@ -53,7 +53,7 @@ class WavADMReader:
 
     def programme(self) -> dict:
         """
-        Extract the ADM audioProgramme data structure and some of its reference properties 
+        Read the ADM `audioProgramme` data structure and some of its reference properties. 
         """
         ret_dict = dict()
 
@@ -95,7 +95,7 @@ class WavADMReader:
 
         return ret_dict
 
-    def track_info(self, index):
+    def track_info(self, index) -> dict:
         """
         Information about a track in the WAV file.
 
@@ -151,7 +151,7 @@ class WavADMReader:
 
         return ret_dict
 
-    def to_dict(self):
+    def to_dict(self) -> dict: #FIXME should be "asdict"
         """
         Get ADM metadata as a dictionary.
         """

wavinfo/wave_bext_reader.py

@@ -1,5 +1,5 @@
 import struct
-from .umid_parser import UMIDParser
+# from .umid_parser import UMIDParser
 
 from typing import Optional
 
@@ -25,34 +25,47 @@ class WavBextReader:
 
         #: Description. A free-text field up to 256 characters long.
         self.description : str = sanitize_bytes(unpacked[0])
+            
         #: Originator. Usually the name of the encoding application, sometimes
-        #: a artist name.
+        #: 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 in the local calendar
+            
+        #: 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 on the local clock
+            
+        #: Time of the recording, in the format HH:MM:SS.
         self.originator_time : str = sanitize_bytes(unpacked[4])
-        #: The sample offset of the start of the file relative to an
+            
-        #: epoch, usually midnight the day of the recording. 
+        #: 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 rante, in LUFS.
+            
+        #: 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
 
@@ -67,11 +80,12 @@ class WavBextReader:
             self.max_shortterm_loudness = unpacked[12] / 100.0
 
     def to_dict(self):
-        if self.umid is not None:
+        # if self.umid is not None:
-            umid_parsed = UMIDParser(self.umid)
+        #     umid_parsed = UMIDParser(self.umid)
-            umid_str = umid_parsed.basic_umid_to_str()
+        #     umid_str = umid_parsed.basic_umid_to_str()
-        else:
+        # else:
-            umid_str = None
+            
+        umid_str = None
 
         return {'description': self.description,
                 'originator': self.originator,

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])
+
+
+

wavinfo/wave_dbmd_reader.py

@@ -547,10 +547,10 @@ class DolbyAtmosSupplementalMetadata:
         render_modes = []
 
         h = BytesIO(data)
-        magic = unpack("<I", h.read(4))
+        magic = unpack("<I", h.read(4))[0]
         assert magic == cls.MAGIC, "Magic value was not found"
 
-        object_count = unpack("<H", h.read(2))
+        object_count = unpack("<H", h.read(2))[0]
 
         h.read(1) #skip 1
 
@@ -563,7 +563,7 @@ class DolbyAtmosSupplementalMetadata:
         h.read(object_count) # skip object_count bytes
 
         for _ in range(object_count):
-            binaural_mode = unpack("B", h.read(1))
+            binaural_mode = unpack("B", h.read(1))[0]
             binaural_mode &= 0x7
             render_modes.append(binaural_mode)
 
@@ -582,7 +582,7 @@ class WavDolbyMetadataReader:
     #: indicating if the segment's checksum was valid, and the
     #: segment's parsed dataclass (or a `bytes` array if it was 
     #: not recognized).
-    segment_list: Tuple[Union[SegmentType, int], bool, Any] 
+    segment_list: List[Tuple[Union[SegmentType, int], bool, Any]]
 
     version: Tuple[int,int,int,int]
 
@@ -598,7 +598,7 @@ class WavDolbyMetadataReader:
         return retval
 
 
-    def __init__(self, dbmd_data) -> None:
+    def __init__(self, dbmd_data):
         self.segment_list = []
 
         h = BytesIO(dbmd_data)
@@ -625,8 +625,8 @@ class WavDolbyMetadataReader:
                     segment = DolbyDigitalPlusMetadata.load(segment)
                 elif stype == SegmentType.DolbyAtmos:
                     segment = DolbyAtmosMetadata.load(segment)
-                # elif stype == SegmentType.DolbyAtmosSupplemental:
+                elif stype == SegmentType.DolbyAtmosSupplemental:
-                #     segment = DolbyAtmosSupplementalMetadata.load(segment)
+                    segment = DolbyAtmosSupplementalMetadata.load(segment)
                 
                 self.segment_list.append( (stype, checksum == expected_checksum, segment) )
     
@@ -644,12 +644,12 @@ class WavDolbyMetadataReader:
         return [x[2] for x in self.segment_list \
             if x[0] == SegmentType.DolbyAtmos and x[1]]
 
-    # def dolby_atmos_supplemental(self) -> List[DolbyAtmosSupplementalMetadata]:
+    def dolby_atmos_supplemental(self) -> List[DolbyAtmosSupplementalMetadata]:
-    #     """
+        """
-    #     Every valid Dolby Atmos Supplemental metadata segment in the file.
+        Every valid Dolby Atmos Supplemental metadata segment in the file.
-    #     """
+        """
-    #     return [x[2] for x in self.segment_list \
+        return [x[2] for x in self.segment_list \
-    #         if x[0] == SegmentType.DolbyAtmosSupplemental and x[1]]
+            if x[0] == SegmentType.DolbyAtmosSupplemental and x[1]]
 
     def to_dict(self) -> dict:
 

wavinfo/wave_info_reader.py

@@ -21,7 +21,7 @@ class WavInfoChunkReader:
         self.album : Optional[str] = self.product
         #: 'IGNR' Genre
         self.genre : Optional[str] = self._get_field(f, b'IGNR')
-        #: 'ISBJ' Supject
+        #: 'ISBJ' Subject
         self.subject : Optional[str] = self._get_field(f, b'ISBJ')
         #: 'IART' Artist, composer, author
         self.artist : Optional[str] = self._get_field(f, b'IART')
@@ -59,7 +59,7 @@ class WavInfoChunkReader:
         else:
             return None
 
-    def to_dict(self):
+    def to_dict(self) -> dict: #FIXME should be asdict 
         """
         A dictionary with all of the key/values read from the INFO scope.
         """

wavinfo/wave_ixml_reader.py

@@ -2,10 +2,145 @@ from lxml import etree as ET
 import io
 from collections import namedtuple
 from typing import Optional
+from enum import IntEnum
 
 IXMLTrack = namedtuple('IXMLTrack', ['channel_index', 'interleave_index', 'name', 'function'])
 
 
+class SteinbergMetadata:
+    """
+    Vendor-specific Steinberg metadata.
+    """
+
+    class AudioSpeakerArrangement(IntEnum):
+        """
+        Steinberg speaker format enumeration.
+        """
+        MONO = 0
+        STEREO = 1
+        LRC = 10
+        LRCS = 14
+        QUAD = 15
+        CINE_50 = 18
+        CINE_51 = 19
+        CINE_60 = 20
+        CINE_61 = 22
+        CINE_70 = 25
+        CINE_71 = 27
+        SDDS_70 = 24
+        SDDS_71 = 26
+        MUSIC_60 = 21 #??
+        MUSIC_61 = 23
+        ATMOS_712 = 33
+        ATMOS_504 = 35
+        ATMOS_514 = 36
+        ATMOS_714 = 44
+        ATMOS_702 = 48
+        ATMOS_716 = 51
+        ATMOS_914 = 53
+        ATMOS_916 = 55
+        AMB_1ORDER = 45
+        AMB_2ORDER = 46
+        AMB_3ORDER = 47
+        AURO_10_0 = 37
+        AURO_10_1 = 38
+        AURO_11_0 = 39
+        AURO_11_1 = 40
+        AURO_13_0 = 41
+        AURO_13_1 = 42
+
+    Steinberg_xpath = "./STEINBERG"
+
+    @classmethod
+    def present(cls, xml: ET.ElementTree) -> bool:
+        """
+        Test if `xml` has Steinberg metadata.
+        :param xml: an iXML ElementTree
+        """
+        x = xml.find(cls.Steinberg_xpath)
+        return x is not None
+
+    def __init__(self, xml: ET.ElementTree) -> None:
+        """
+        Parse Steinberg iXML data.
+        :param xml: The entire iXML Tree
+        """
+        self.parsed = xml.find(self.Steinberg_xpath)
+
+    @property
+    def audio_speaker_arrangement(self) -> Optional[AudioSpeakerArrangement]:
+        """
+        `AudioSpeakerArrangement` property
+        """
+        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'AudioSpeakerArrangement']/VALUE")
+        if val is not None:
+            return type(self).AudioSpeakerArrangement(int(val.text))
+
+    @property
+    def sample_format_size(self) -> Optional[int]:
+        """
+        AudioSampleFormatSize
+        """
+        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'AudioSampleFormatSize']/VALUE")
+        if val is not None:
+            return int(val.text)
+
+    @property
+    def media_company(self) -> Optional[str]:
+        """
+        MediaCompany
+        """
+        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'MediaCompany']/VALUE")
+        if val is not None:
+            return val.text
+
+    @property
+    def media_drop_frames(self) -> Optional[bool]:
+        """
+        MediaDropFrames
+        """
+        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'MediaDropFrames']/VALUE")
+        if val is not None:
+            return val.text == "1"
+
+    @property
+    def media_duration(self) -> Optional[float]:
+        """
+        MediaDuration
+        """
+        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'MediaDuration']/VALUE")
+        if val is not None:
+            return float(val.text)
+
+    @property
+    def media_start_time(self) -> Optional[float]:
+        """
+        MediaStartTime
+        """
+        pass
+
+    @property
+    def media_track_title(self) -> Optional[str]:
+        """
+        MediaTrackTitle
+        """
+        pass
+
+    @property
+    def program_name(self) -> Optional[str]:
+        """
+        ProgramName
+        """
+        pass
+
+    @property
+    def program_version(self) -> Optional[str]:
+        """
+        ProgramVersion
+        """
+        pass
+
+
 class WavIXMLFormat:
     """
     iXML recorder metadata.
@@ -18,7 +153,7 @@ class WavIXMLFormat:
         self.source = xml
         xml_bytes = io.BytesIO(xml)
         parser = ET.XMLParser(recover=True)
-        self.parsed = ET.parse(xml_bytes, parser=parser)
+        self.parsed : ET.ElementTree = ET.parse(xml_bytes, parser=parser)
 
     def _get_text_value(self, xpath) -> Optional[str]:
         e = self.parsed.find("./" + xpath)
@@ -27,11 +162,11 @@ class WavIXMLFormat:
         else: 
             return None
 
-    def xml_bytes(self):
+    def xml_str(self) -> str:
         return ET.tostring(self.parsed).decode("utf-8")
 
     @property
-    def raw_xml(self):
+    def raw_xml(self) -> ET.ElementTree:
         """
         The root entity of the iXML document.
         """
@@ -41,7 +176,8 @@ class WavIXMLFormat:
     def track_list(self):
         """
         A description of each track.
-        :returns: An Iterator
+
+        :yields: `IXMLTrack` for each track.
         """
         for track in self.parsed.find("./TRACK_LIST").iter():
             if track.tag == 'TRACK':
@@ -93,6 +229,16 @@ class WavIXMLFormat:
         """
         return self._get_text_value("FILE_SET/FAMILY_NAME")
 
+    @property
+    def steinberg(self) -> Optional[SteinbergMetadata]:
+        """
+        Steinberg vendor iXML metadata if present.
+        """
+        if SteinbergMetadata.present(self.raw_xml):
+            return SteinbergMetadata(self.raw_xml)
+        else:
+            return None
+
     def to_dict(self):
         return dict(track_list=list(map(lambda x: x._asdict(), self.track_list)), 
             project=self.project,

wavinfo/wave_reader.py

@@ -13,20 +13,20 @@ from .wave_bext_reader import WavBextReader
 from .wave_info_reader import WavInfoChunkReader
 from .wave_adm_reader import WavADMReader
 from .wave_dbmd_reader import WavDolbyMetadataReader
+from .wave_cues_reader import WavCuesReader
 
 #: Calculated statistics about the audio data.
 WavDataDescriptor = namedtuple('WavDataDescriptor', 'byte_count frame_count')
 
 #: The format of the audio samples.
 WavAudioFormat = namedtuple('WavAudioFormat',
-                            'audio_format channel_count sample_rate byte_rate block_align bits_per_sample')
+                            ['audio_format', 'channel_count', 'sample_rate',
+                             'byte_rate',  'block_align',  'bits_per_sample'])
 
 
 class WavInfoReader:
     """
     Parse a WAV audio file for metadata.
-
-    
     """
 
     def __init__(self, path, info_encoding='latin_1', bext_encoding='ascii'):
@@ -34,62 +34,65 @@ class WavInfoReader:
         Create a new reader object.
 
         :param path: 
-            A filesystem path to the wav file you wish to probe or a 
+            A pathlike object or IO to the wav file you wish to probe or a 
             file handle to an open file.
 
         :param info_encoding: 
-            The text encoding of the INFO metadata fields.
+            The text encoding of the ``INFO``, ``LABL`` and other RIFF-defined
-            latin_1/Win CP1252 has always been a pretty good guess for this.
+            metadata fields. 
 
         :param bext_encoding: 
             The text encoding to use when decoding the string
             fields of the Broadcast-WAV extension. Per EBU 3285 this is ASCII
             but this parameter is available to you if you encounter a weirdo.
-
-
         """
         
         self.info_encoding = info_encoding
         self.bext_encoding = bext_encoding
         
+        #: Wave audio data format.
+        self.fmt :Optional[WavAudioFormat] = None
+
+        #: Statistics of the `data` section.
+        self.data :Optional[WavDataDescriptor] = None
+
+        #: Broadcast-Wave metadata.
+        self.bext :Optional[WavBextReader] = None
+
+        #: iXML metadata.
+        self.ixml :Optional[WavIXMLFormat] = None
+
+        #: ADM Audio Definiton Model metadata.
+        self.adm :Optional[WavADMReader]= None
+
+        #: Dolby bitstream metadata.
+        self.dolby :Optional[WavDolbyMetadataReader] = None
+
+        #: RIFF INFO metadata.
+        self.info :Optional[WavInfoChunkReader]= None
+
+        #: RIFF cues markers, labels, and notes.
+        self.cues :Optional[WavCuesReader] = None
+
         if hasattr(path, 'read'):
             self.get_wav_info(path)
             self.url = 'about:blank'
             self.path = repr(path)
+            
         else:
             absolute_path = os.path.abspath(path)
 
             #: `file://` url for the file.
-            self.url: pathlib.Path = pathlib.Path(absolute_path).as_uri()
+            self.url: str = pathlib.Path(absolute_path).as_uri()
 
             self.path = absolute_path
         
-            #: Wave audio data format.
-            self.fmt :Optional[WavAudioFormat] = None
-
-            #: Statistics of the `data` section.
-            self.data :Optional[WavDataDescriptor] = None
-
-            #: Broadcast-Wave metadata.
-            self.bext :Optional[WavBextReader] = None
-
-            #: iXML metadata.
-            self.ixml :Optional[WavIXMLFormat] = None
-
-            #: ADM Audio Definiton Model metadata.
-            self.adm :Optional[WavADMReader]= None
-
-            #: Dolby bitstream metadata.
-            self.dolby :Optional[WavDolbyMetadataReader] = None
-
-            #: RIFF INFO metadata.
-            self.info :Optional[WavInfoChunkReader]= None
-            
             with open(path, 'rb') as f:
                 self.get_wav_info(f)
             
     def get_wav_info(self, wavfile):
         chunks = parse_chunk(wavfile)
+        assert type(chunks) is ListChunkDescriptor  
 
         self.main_list = chunks.children
         wavfile.seek(0)
@@ -100,41 +103,44 @@ class WavInfoReader:
         self.adm  = self._get_adm(wavfile)
         self.info = self._get_info(wavfile, encoding=self.info_encoding)
         self.dolby = self._get_dbmd(wavfile)
+        self.cues = self._get_cue(wavfile)
         self.data = self._describe_data()
 
-    def _find_chunk_data(self, ident, from_stream, default_none=False):
+    def _find_chunk_data(self, ident, from_stream, default_none=False) -> Optional[bytes]:
-        top_chunks = (chunk for chunk in self.main_list if type(chunk) is ChunkDescriptor and chunk.ident == ident)
+        top_chunks = (chunk for chunk in self.main_list \
-        chunk_descriptor = next(top_chunks, None) if default_none else next(top_chunks)
+            if type(chunk) is ChunkDescriptor and chunk.ident == ident)
-        return chunk_descriptor.read_data(from_stream) if chunk_descriptor else None
+
+        chunk_descriptor = next(top_chunks, None) \
+            if default_none else next(top_chunks)
+
+        return chunk_descriptor.read_data(from_stream) \
+            if chunk_descriptor else None
+
+    def _find_list_chunk(self, signature) -> Optional[ListChunkDescriptor]:
+        top_chunks = (chunk for chunk in self.main_list \
+            if type(chunk) is ListChunkDescriptor and \
+                chunk.signature == signature)
+
+        return next(top_chunks, None)
 
     def _describe_data(self):
-        data_chunk = next(c for c in self.main_list if type(c) is ChunkDescriptor and c.ident == b'data')
+        data_chunk = next(c for c in self.main_list \
+            if type(c) is ChunkDescriptor and c.ident == b'data')
 
-        return WavDataDescriptor(byte_count=data_chunk.length,
+        assert isinstance(self.fmt, WavAudioFormat)
-                                 frame_count=int(data_chunk.length / self.fmt.block_align))
+        return WavDataDescriptor(
+            byte_count=data_chunk.length, 
+            frame_count=int(data_chunk.length / self.fmt.block_align))
 
     def _get_format(self, f):
         fmt_data = self._find_chunk_data(b'fmt ', f)
+        assert fmt_data is not None, "Fmt data not found, not a valid wav file"
 
-        # The format chunk is
-        # audio_format    U16
-        # channel_count   U16
-        # sample_rate     U32   Note an integer
-        # byte_rate       U32   == SampleRate * NumChannels * BitsPerSample/8
-        # block_align     U16   == NumChannels * BitsPerSample/8
-        # bits_per_sampl  U16
         packstring = "<HHIIHH"
         rest_starts = struct.calcsize(packstring)
 
         unpacked = struct.unpack(packstring, fmt_data[:rest_starts])
 
-        # 0x0001	WAVE_FORMAT_PCM	PCM
-        # 0x0003	WAVE_FORMAT_IEEE_FLOAT	IEEE float
-        # 0x0006	WAVE_FORMAT_ALAW	8-bit ITU-T G.711 A-law
-        # 0x0007	WAVE_FORMAT_MULAW	8-bit ITU-T G.711 µ-law
-        # 0xFFFE	WAVE_FORMAT_EXTENSIBLE	Determined by SubFormat
-
-        # https://sno.phy.queensu.ca/~phil/exiftool/TagNames/RIFF.html
         return WavAudioFormat(audio_format=unpacked[0],
                               channel_count=unpacked[1],
                               sample_rate=unpacked[2],
@@ -144,7 +150,8 @@ class WavInfoReader:
                               )
 
     def _get_info(self, f, encoding):
-        finder = (chunk.signature for chunk in self.main_list if type(chunk) is ListChunkDescriptor)
+        finder = (chunk.signature for chunk in self.main_list \
+            if type(chunk) is ListChunkDescriptor)
 
         if b'INFO' in finder:
             return WavInfoChunkReader(f, encoding)
@@ -156,26 +163,46 @@ class WavInfoReader:
     def _get_adm(self, f):
         axml = self._find_chunk_data(b'axml', f, default_none=True)
         chna = self._find_chunk_data(b'chna', f, default_none=True)
-        return WavADMReader(axml_data=axml, chna_data=chna) if axml and chna else None
+        return WavADMReader(axml_data=axml, chna_data=chna) \
+            if axml and chna else None
 
     def _get_dbmd(self, f):
         dbmd_data = self._find_chunk_data(b'dbmd', f, default_none=True)
-        return WavDolbyMetadataReader(dbmd_data=dbmd_data) if dbmd_data else None
+        return WavDolbyMetadataReader(dbmd_data=dbmd_data) \
+            if dbmd_data else None
 
     def _get_ixml(self, f):
         ixml_data = self._find_chunk_data(b'iXML', f, default_none=True)
         return WavIXMLFormat(ixml_data.rstrip(b'\0')) if ixml_data else None
 
+    def _get_cue(self, f):
+        cue = next((cue_chunk for cue_chunk in self.main_list if \
+            type(cue_chunk) is ChunkDescriptor and \
+            cue_chunk.ident == b'cue '), None)
+
+        adtl = self._find_list_chunk(b'adtl')
+        labls = []
+        ltxts = []
+        notes = []
+        if adtl is not None:
+            labls = [c for c in adtl.children if c.ident == b'labl']
+            ltxts = [c for c in adtl.children if c.ident == b'ltxt']
+            notes = [c for c in adtl.children if c.ident == b'note']
+
+        return WavCuesReader.read_all(f, cue, labls, ltxts, notes, 
+                                   fallback_encoding=self.info_encoding)
+
     def walk(self) -> Generator[str,str,Any]: #FIXME: this should probably be named "iter()"
         """
         Walk all of the available metadata fields.
         
         :yields: tuples of the *scope*, *key*, and *value* of
             each metadatum. The *scope* value will be one of
-            "fmt", "data", "ixml", "bext", "info", "dolby", or "adm".
+            "fmt", "data", "ixml", "bext", "info", "dolby", "cues" or "adm".
         """
 
-        scopes = ('fmt', 'data', 'ixml', 'bext', 'info', 'adm', 'dolby')
+        scopes = ('fmt', 'data', 'ixml', 'bext', 'info', 'adm', 'cues', 
+                 'dolby')
 
         for scope in scopes:
             if scope in ['fmt', 'data']:

wavinfo/wavfind.py

@@ -0,0 +1,34 @@
+"""
+
+"""
+
+from optparse import OptionParser, OptionGroup
+import sys
+
+
+def main():
+    parser = OptionParser()
+
+    parser.usage = "wavfind [--scene=SCENE] [--take=TAKE] [--desc=DESC] <PATH> +"
+
+    primaries = OptionGroup(parser, title="Search Predicates",
+        description="Argument values can be globs, and are logically-AND'ed.")
+
+    primaries.add_option("--scene", 
+        help='Search for this scene', 
+        metavar='SCENE')
+    
+    primaries.add_option("--take",
+        help='Search for this take',
+        metavar='TAKE')
+
+    primaries.add_option("--desc",
+        help='Search descriptions',
+        metavar='DESC')
+        
+
+    (options, args) = parser.parse_args(sys.argv)
+
+
+if __name__ == "__main__":
+    main()