Merge branch 'master' of https://github.com/iluvcapra/wavinfo

Bug ruff

.github/ISSUE_TEMPLATE/add-support-for-new-metadata-type.md

@@ -0,0 +1,26 @@
+---
+name: Add Support For New Metadata Type
+about: For adding support for a new type of metadata
+title: "[METADATA]"
+labels: ''
+assignees: ''
+
+---
+
+**Describe the type of metadata you want to read:**
+???
+
+**List some applications that read and write this metadata:**
+???
+
+**List the authorities or organizations that use and standardize this metadata:**
+???
+
+**URL for example WAVE file with this metadata:**
+???
+
+**(Optional) Four-character code identifier for this metadata (if known):**
+???
+
+**(Optional) URLs for documentation of this metadata:**
+???

.github/workflows/coverage.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.11"]
 
     steps:
       - uses: actions/checkout@v2.5.0

.github/workflows/python-package.yml

@@ -1,7 +1,7 @@
 # This workflow will install Python dependencies, run tests and lint with a variety of Python versions
 # For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
 
-name: Python Lint and Test
+name: Tests
 
 on:
   push:
@@ -16,27 +16,21 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
 
     steps:
-    - uses: actions/checkout@v2.5.0
+    - uses: actions/checkout@v6.0.2
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4.3.0
+      uses: actions/setup-python@v6.2.0
       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 --group dev
-        python -m pip install -e .
+        python -m pip install .
     - name: Setup FFmpeg
-      uses: FedericoCarboni/setup-ffmpeg@v2
+      uses: federicocarboni/setup-ffmpeg@v3.1
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
     - name: Test with pytest
       run: |
         pytest

.github/workflows/python-ruff.yml

@@ -0,0 +1,33 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Lint with Ruff
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.13", "3.14"]
+
+    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 --group dev
+        python -m pip install .
+    - name: Lint with ruff 
+      run: |
+        ruff check src

.github/workflows/pythonpublish.yml

@@ -8,29 +8,33 @@ jobs:
   deploy:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4.2.2
     - name: Set up Python
-      uses: actions/setup-python@v1
+      uses: actions/setup-python@v5.3.0
       with:
         python-version: '3.x'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install setuptools build wheel twine lxml
+    - name: Setup uv and Handle Its Cache
-    - name: Build and publish
+      # You may pin to the exact commit or the version.
-      env:
+      # uses: hynek/setup-cached-uv@757bedc3f972eb7227a1aa657651f15a8527c817
-        TWINE_USERNAME: __token__
+      uses: hynek/setup-cached-uv@v2.3.0          
-        TWINE_PASSWORD: ${{ secrets.PYPI_APIKEY }}
+    - name: Build 
       run: |
-        python -m build .
+        uv build --wheel
-        twine upload dist/*
+    - name: Publish to Pypi
-    - name: Report to Mastodon
+      uses: pypa/gh-action-pypi-publish@v1.13.0
-      uses: cbrgm/mastodon-github-action@v1.0.1
       with:
-        message: |
+        password: ${{ secrets.PYPI_APIKEY }}
-          I just released a new version of wavinfo, my library for reading WAVE file metadata!
+    # - name: Send Bluesky Post
-          #sounddesign #filmmaking #audio #python
+    #   uses: myConsciousness/bluesky-post@v5
-          ${{ github.server_url }}/${{ github.repository }}
+    #   with:
-      env:
+    #     text: |
-        MASTODON_URL: ${{ secrets.MASTODON_URL }}
+    #       I've released a new version of wavinfo, my module for 
-        MASTODON_ACCESS_TOKEN: ${{ secrets.MASTODON_ACCESS_TOKEN }}
+    #       reading WAVE metadata.
+    #     link-preview-url: ${{ github.server_url }}/${{ github.repository }}
+    #     identifier: ${{ secrets.BLUESKY_APP_USER }}  
+    #     password: ${{ secrets.BLUESKY_APP_PASSWORD }}
+    #     service: bsky.social    
+    #     retry-count: 1

.gitignore

@@ -110,3 +110,5 @@ venv_docs/
 .DS_Store
 
 .vscode/
+
+poetry.lock

.readthedocs.yaml

@@ -7,13 +7,13 @@ version: 2
 
 # Set the version of Python and other tools you might need
 build:
-  os: ubuntu-20.04
+  os: ubuntu-lts-latest
   tools:
-    python: "3.10"
+    python: "3.13"
-    # You can also specify other tool versions:
+  jobs:
-    # nodejs: "16"
+    install: 
-    # rust: "1.55"
+      - pip install --upgrade pip
-    # golang: "1.17"
+      - pip install --group 'doc'
 
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
@@ -28,5 +28,3 @@ python:
   install:
     - method: pip
       path: .
-      extra_requirements:
-        - doc

CONTRIBUTING.md

@@ -13,3 +13,35 @@ If you discover a bug or would like better support for a feature, please do the
    review it as soon as I can. There's a `.devcontainer` available so you can creates commits 
    on this project in a GitHub codespace.
 
+
+## Regarding use of Agents
+
+`wavinfo` is an open-source project that is offered free for no commerical gain, and 
+is developed and maintained for educational and creative reasons.
+
+If you use an agent or LLM to produce code for it you are missing out on the benefits 
+of contributing to an open-source project, particularly community, collaboration with 
+other developers and designers, and being able to learn and experiment without the 
+burden of deadlines or worrying about business cases or profits.
+
+This project is supposed to be fun, do not let machines have fun for you.
+
+We can't prevent you from using LLMs to contribute to this project but we ask you 
+abide by the following eitiquette when doing so:
+
+* All communication with the maintainers must be written by a human in their own
+  voice. Never use an LLM to craft thread comments, discussion posts, issues, emails
+  or other correspondence with other developers or the maintainers. 
+* PRs must be submitted by a person. Do not allow an agent to submit its own PRs to
+  this project.
+* Especially if you are a new contributor to this project, please submit only one PR
+  at a time and please restrict the subject matter of the PR to a specific unit,
+  module or tool. All submissions have to be reviewed and understood by the
+  maintainers before they can be merged.
+
+Obviously we can't verify if you follow all of these rules but certain telltale 
+traits of LLM-predicted text or code will raise a flag: lack of brevity in 
+descriptions or code comments, large amounts of text describing your process or 
+steps that add little to understanding the changes you've made, use of an 
+obsequious tone or being excessively accomodating, immediately doing requests 
+without further discussion or clarifications.

README.md

@@ -1,34 +1,44 @@
-[![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)
+![](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)
+![GitHub last commit](https://img.shields.io/github/last-commit/iluvcapra/wavinfo) [![Documentation Status](https://readthedocs.org/projects/wavinfo/badge/?version=latest)](https://wavinfo.readthedocs.io/en/latest/?badge=latest) ![](https://img.shields.io/github/license/iluvcapra/wavinfo.svg)
-[![codecov](https://codecov.io/gh/iluvcapra/wavinfo/branch/master/graph/badge.svg?token=9DZQfZENYv)](https://codecov.io/gh/iluvcapra/wavinfo)
+
+[![Tests](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml/badge.svg)](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml)
+[![Ruff](https://github.com/iluvcapra/wavinfo/actions/workflows/python-ruff.yml/badge.svg)](https://github.com/iluvcapra/wavinfo/actions/workflows/python-ruff.yml)
 
 # wavinfo
 
 The `wavinfo` package allows you to probe WAVE and [RF64/WAVE files][eburf64] 
-and extract extended metadata, with an emphasis on film, video and 
+and extract extended metadata. `wavinfo` has an emphasis on film, video and 
-professional music production.
+professional music production but can read many other kinds.
+
+If you are trying to read a particular kind of metadata from a WAV file and
+it is not supported, please submit an issue!
 
 
 ## Metadata Support
 
 `wavinfo` reads:
 
-* [Broadcast-WAVE][bext] metadata, including embedded program
+* All defined [Broadcast-WAVE][bext] fields, including embedded program
   loudness, coding history and [SMPTE UMID][smpte_330m2011].
-* [Audio Definition Model (ADM)][adm] track metadata and schema, including 
-  channel, pack formats, 
-  object, content and programme.
-* [Dolby Digital Plus][ebu3285s6] and Dolby Atmos `dbmd` metadata.
 * [iXML][ixml] production recorder metadata, including project, scene, and 
   take tags, recorder notes and file family information.
   * iXML `STEINBERG` sound library attributes.
-* Wave embedded cue markers, cue marker labels, notes and timed ranges as used
+* All known [RIFF INFO][info-tags] metadata fields.
+* [Audio Definition Model (ADM)][adm] track metadata and schema, including 
+  channel, pack formats, 
+  object, content and programme, including [Dolby Digital Plus][ebu3285s6]
+  and Dolby Atmos `dbmd` metadata for re-renders and mixdowns.
+* Wave embedded [cue markers][cues], cue marker labels, notes and timed ranges as used
   by Zoom, iZotope RX, etc.
-* Most of the common [RIFF INFO][info-tags] metadata fields.
+* Wave embedded [sampler][smpl] and sample loop metadata.
-* The __wav format__ is also parsed, so you can access the basic sample rate 
+* The [wav format][format] is also parsed, so you can access the basic sample rate 
   and channel count information.
 
+
+[format]:https://wavinfo.readthedocs.io/en/latest/classes.html#wavinfo.wave_reader.WavAudioFormat
+[cues]:https://wavinfo.readthedocs.io/en/latest/scopes/cue.html
 [bext]:https://wavinfo.readthedocs.io/en/latest/scopes/bext.html
+[smpl]:https://wavinfo.readthedocs.io/en/latest/scopes/smpl.html
 [smpte_330m2011]:https://wavinfo.readthedocs.io/en/latest/scopes/bext.html#wavinfo.wave_bext_reader.WavBextReader.umid
 [adm]:https://wavinfo.readthedocs.io/en/latest/scopes/adm.html
 [ebu3285s6]:https://wavinfo.readthedocs.io/en/latest/scopes/dolby.html
@@ -58,6 +68,12 @@ The package also installs a shell command:
 $ wavinfo test_files/A101_1.WAV
 ```
 
+## Contributions!
+
+Any new or different kind of metadata you find, or any 
+new or different use of exising metadata you encounter, please submit
+an Issue or Pull Request!
+
 ## Other Resources
 
 * For other file formats and ID3 decoding, 

data/share/man/man7/wavinfo.7

@@ -1,190 +0,0 @@
-.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/source/command_line.rst

@@ -6,89 +6,135 @@ from the command line and output metadata to stdout.
 
 .. code-block:: shell
 
-    $ wavinfo [--ixml | --adm] INFILE +
+    $ wavinfo [[-i] | [--ixml | --adm]] INFILE +
-
-By default, `wavinfo` will output a JSON dictionary for each file argument.
 
 
 Options
 -------
 
-Two option flags will change the behavior of the command:
+By default, `wavinfo` will output a JSON dictionary for each file argument.
+
+``-i`` 
+    `wavinfo` will run in `interactive mode`_.
+
+Two option flags will change the behavior of the command in non-interactive 
+mode:
 
 ``--ixml``
-    The *\-\-ixml* flag will cause `wavinfo` to output the iXML metadata payload
+    The *\-\-ixml* flag will cause `wavinfo` to output the iXML metadata
-    of each input wave file, or will emit an error message to stderr if iXML 
+    payload of each input wave file, or will emit an error message to stderr if
-    metadata is not present.
+    iXML metadata is not present.
 
 ``--adm``
     The *\-\-adm* flag will cause `wavinfo` to output the ADM XML metadata 
     payload of each input wave file, or will emit an error message to stderr if
     ADM XML metadata is not present.
 
-These options are mutually-exclusive, with `\-\-adm` taking precedence. 
+These options are mutually-exclusive, with `\-\-adm` taking precedence. The 
+``--ixml`` and ``--adm`` flags futher take precedence over ``-i``.
+
+
+Interactive Mode 
+-----------------
+
+In interactive mode, `wavinfo` will present a command prompt which allows you
+to query the files provided on the command line and explore the metadata tree 
+interactively. Each file on the command line is scanned and presented as a 
+tree of metadata records.
+
+Commands include:
+
+``ls``
+    List the available metadata keys at the current level.
+
+``cd``
+    Traverse to a metadata key in the current level (or enter `..` to go up 
+    to the prevvious level).
+
+``bye``
+    Exit to the shell.
+
+Type `help` or `?` at the prompt to get a full list of commands.
 
 
 Example Output
 --------------
 
+.. attention::
+
+   Metadata fields containing binary data, such as the Broadcast-WAV UMID, will 
+   be included in the JSON output as a base-64 encoded string, preceded by the
+   marker "base64:".
+
 .. code-block:: javascript
 
-    {
+  {
-    "filename": "tests/test_files/sounddevices/A101_1.WAV",
+  "filename": "../tests/test_files/nuendo/wavinfo Test Project - Audio - 1OA.wav",
-    "run_date": "2022-11-26T17:56:38.342935",
+  "run_date": "2024-11-25T10:26:11.280053",
-    "application": "wavinfo 2.1.0",
+  "application": "wavinfo 3.0.0",
-    "scopes": {
+  "scopes": {
-        "fmt": {
+    "fmt": {
-        "audio_format": 1,
+      "audio_format": 65534,
-        "channel_count": 2,
+      "channel_count": 4,
-        "sample_rate": 48000,
+      "sample_rate": 48000,
-        "byte_rate": 288000,
+      "byte_rate": 576000,
-        "block_align": 6,
+      "block_align": 12,
-        "bits_per_sample": 24
+      "bits_per_sample": 24
+    },
+    "data": {
+      "byte_count": 576000,
+      "frame_count": 48000
+    },
+    "ixml": {
+      "track_list": [
+        {
+          "channel_index": "1",
+          "interleave_index": "1",
+          "name": "",
+          "function": "ACN0-FOA"
         },
-        "data": {
+        {
-        "byte_count": 1441434,
+          "channel_index": "2",
-        "frame_count": 240239
+          "interleave_index": "2",
+          "name": "",
+          "function": "ACN1-FOA"
         },
-        "ixml": {
+        {
-        "track_list": [
+          "channel_index": "3",
-            {
+          "interleave_index": "3",
-            "channel_index": "1",
+          "name": "",
-            "interleave_index": "1",
+          "function": "ACN2-FOA"
-            "name": "MKH516 A",
-            "function": ""
-            },
-            {
-            "channel_index": "2",
-            "interleave_index": "2",
-            "name": "Boom",
-            "function": ""
-            }
-        ],
-        "project": "BMH",
-        "scene": "A101",
-        "take": "1",
-        "tape": "18Y12M31",
-        "family_uid": "USSDVGR1112089007124001008206300",
-        "family_name": null
         },
-        "bext": {
+        {
-        "description": "sSPEED=023.976-ND\r\nsTAKE=1\r\nsUBITS=$12311801\r\nsSWVER=2.67\r\nsPROJECT=BMH\r\nsSCENE=A101\r\nsFILENAME=A101_1.WAV\r\nsTAPE=18Y12M31\r\nsTRK1=MKH516 A\r\nsTRK2=Boom\r\nsNOTE=\r\n",
+          "channel_index": "4",
-        "originator": "Sound Dev: 702T S#GR1112089007",
+          "interleave_index": "4",
-        "originator_ref": "USSDVGR1112089007124001008206301",
+          "name": "",
-        "originator_date": "2018-12-31",
+          "function": "ACN3-FOA"
-        "originator_time": "12:40:00",
-        "time_reference": 2190940753,
-        "version": 1,
-        "umid": "0000000000000000000000000000000000000000000000000000000000000000",
-        "coding_history": "A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch\r\n",
-        "loudness_value": null,
-        "loudness_range": null,
-        "max_true_peak": null,
-        "max_momentary_loudness": null,
-        "max_shortterm_loudness": null
         }
+      ],
+      "project": "wavinfo Test Project",
+      "scene": null,
+      "take": null,
+      "tape": null,
+      "family_uid": "E5DDE719B9484A758162FF7B652383A3",
+      "family_name": null
+    },
+    "bext": {
+      "description": "wavinfo Test Project Nuendo output",
+      "originator": "Nuendo",
+      "originator_ref": "USJPHNNNNNNNNN202829RRRRRRRRR",
+      "originator_date": "2022-12-02",
+      "originator_time": "10:21:06",
+      "time_reference": 172800000,
+      "version": 2,
+      "umid": "base64:k/zr4qE4RiaXyd/fO7GuCwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA==",
+      "coding_history": "A=PCM,F=48000,W=24,T=Nuendo\r\n",
+      "loudness_value": 327.67,
+      "loudness_range": 327.67,
+      "max_true_peak": 327.67,
+      "max_momentary_loudness": 327.67,
+      "max_shortterm_loudness": 327.67
     }
-    }
+  }
+}
 

docs/source/conf.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 #
 # Configuration file for the Sphinx documentation builder.
 #
@@ -12,24 +11,25 @@
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
+# import importlib
 import os
 import sys
-sys.path.insert(0, os.path.abspath('../..'))
-sys.path.insert(0, os.path.abspath("../../.."))
-print(sys.path)
 
-import wavinfo
+sys.path.insert(0, os.path.abspath("../../src"))
+sys.path.insert(0, os.path.abspath("../../../src"))
+print(sys.path)
 
 # -- Project information -----------------------------------------------------
 
-project = u'wavinfo'
+project = "wavinfo"
-copyright = u'2018-2023, Jamie Hardt'
+copyright = "2018-2025, Jamie Hardt"
-author = u'Jamie Hardt'
+author = "Jamie Hardt"
 
 # The short X.Y version
-version = wavinfo.__short_version__
+version = "4.0"
 # The full version, including alpha/beta/rc tags
-release = wavinfo.__version__
+release = "4.0.0"
+# release = importlib.metadata.version("wavinfo")
 
 
 # -- General configuration ---------------------------------------------------
@@ -42,34 +42,34 @@ release = wavinfo.__version__
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    'sphinx.ext.autodoc',
+    "sphinx.ext.autodoc",
-    'sphinx.ext.todo',
+    "sphinx.ext.todo",
-    'sphinx.ext.coverage',
+    "sphinx.ext.coverage",
 ]
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # The suffix(es) of source filenames.
 # You can specify multiple suffix as a list of string:
 #
 # source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
+source_suffix = ".rst"
 
 # The master toctree document.
-master_doc = 'index'
+master_doc = "index"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = 'en'
+language = "en"
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This pattern also affects html_static_path and html_extra_path.
-exclude_patterns = [u'_build', 'Thumbs.db', '.DS_Store']
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
 # The name of the Pygments (syntax highlighting) style to use.
 pygments_style = None
@@ -80,7 +80,7 @@ pygments_style = None
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'sphinx_rtd_theme'
+html_theme = "sphinx_rtd_theme"
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
@@ -91,7 +91,7 @@ html_theme = 'sphinx_rtd_theme'
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
 
 # Custom sidebar templates, must be a dictionary that maps document names
 # to template names.
@@ -107,7 +107,7 @@ html_static_path = ['_static']
 # -- Options for HTMLHelp output ---------------------------------------------
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'wavinfodoc'
+htmlhelp_basename = "wavinfodoc"
 
 
 # -- Options for LaTeX output ------------------------------------------------
@@ -116,15 +116,12 @@ latex_elements = {
     # The paper size ('letterpaper' or 'a4paper').
     #
     # 'papersize': 'letterpaper',
-
     # The font size ('10pt', '11pt' or '12pt').
     #
     # 'pointsize': '10pt',
-
     # Additional stuff for the LaTeX preamble.
     #
     # 'preamble': '',
-
     # Latex figure (float) alignment
     #
     # 'figure_align': 'htbp',
@@ -134,8 +131,7 @@ latex_elements = {
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, 'wavinfo.tex', u'wavinfo Documentation',
+    (master_doc, "wavinfo.tex", "wavinfo Documentation", "Jamie Hardt", "manual"),
-     u'Jamie Hardt', 'manual'),
 ]
 
 
@@ -143,10 +139,7 @@ latex_documents = [
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [
+man_pages = [(master_doc, "wavinfo", "wavinfo Documentation", [author], 1)]
-    (master_doc, 'wavinfo', u'wavinfo Documentation',
-     [author], 1)
-]
 
 
 # -- Options for Texinfo output ----------------------------------------------
@@ -155,9 +148,15 @@ man_pages = [
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-    (master_doc, 'wavinfo', u'wavinfo Documentation',
+    (
-     author, 'wavinfo', 'One line description of project.',
+        master_doc,
-     'Miscellaneous'),
+        "wavinfo",
+        "wavinfo Documentation",
+        author,
+        "wavinfo",
+        "One line description of project.",
+        "Miscellaneous",
+    ),
 ]
 
 
@@ -176,7 +175,7 @@ epub_title = project
 # epub_uid = ''
 
 # A list of files that should not be packed into the epub file.
-epub_exclude_files = ['search.html']
+epub_exclude_files = ["search.html"]
 
 
 # -- Extension configuration -------------------------------------------------

docs/source/references.rst

@@ -1,6 +1,9 @@
 References
 ==========
 
+A complete list of technical references and commentary is available as a man page
+and is installed as wavinfo(7) when you install `wavinfo` via pip.
+
 Wave File Format
 ----------------
 
@@ -33,6 +36,11 @@ iXML
 * `Gallery Software iXML Specification <http://www.gallery.co.uk/ixml/>`_
 
 
+Sampler Metadata
+----------------
+
+* `RecordingBlogs.com — Sample chunk (of a Wave file) <https://www.recordingblogs.com/wiki/sample-chunk-of-a-wave-file>`_
+
 RIFF Metadata
 -------------
 * `1991. Multimedia Programming Interface and Data Specifications 1.0 <https://www.aelius.com/njh/wavemetatools/doc/riffmci.pdf>`_

docs/source/scopes/cue.rst

@@ -29,3 +29,12 @@ Class Reference
 
 .. autoclass:: wavinfo.wave_cues_reader.WavCuesReader
    :members:
+
+.. autoclass:: wavinfo.wave_cues_reader.CueEntry
+   :members:
+
+.. autoclass:: wavinfo.wave_cues_reader.LabelEntry
+   :members:
+
+.. autoclass:: wavinfo.wave_cues_reader.NoteEntry
+   :members:

docs/source/scopes/smpl.rst

@@ -0,0 +1,14 @@
+
+Sampler Metadata
+=================
+
+Class Reference
+---------------
+
+.. automodule:: wavinfo.wave_smpl_reader
+
+.. autoclass:: wavinfo.wave_smpl_reader.WavSmplReader
+    :members:
+
+.. autoclass:: wavinfo.wave_smpl_reader.WaveSmplLoop
+    :members:

examples/demo.ipynb

@@ -26,7 +26,7 @@
    "source": [
     "from wavinfo import WavInfoReader\n",
     "\n",
-    "path = '../tests/test_files/sounddevices/A101_1.WAV'\n",
+    "path = \"../tests/test_files/sounddevices/A101_1.WAV\"\n",
     "\n",
     "info = WavInfoReader(path)"
    ]
@@ -46,6 +46,7 @@
     "  * `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",
+    "  * `smpl`: Sampler midi note and loop metadata\n",
     "\n",
     "Each of these is an attribute of a `WavInfoReader` object.\n",
     "\n",
@@ -112,7 +113,12 @@
     }
    ],
    "source": [
-    "(info.fmt.sample_rate, info.fmt.channel_count, info.fmt.block_align, info.fmt.bits_per_sample)"
+    "(\n",
+    "    info.fmt.sample_rate,\n",
+    "    info.fmt.channel_count,\n",
+    "    info.fmt.block_align,\n",
+    "    info.fmt.bits_per_sample,\n",
+    ")"
    ]
   },
   {
@@ -270,7 +276,9 @@
    ],
    "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",
+    "info = WavInfoReader(\n",
+    "    path, info_encoding=\"utf-8\"\n",
+    ")  # 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",
@@ -304,7 +312,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.12.5"
   }
  },
  "nbformat": 4,

pyproject.toml

@@ -1,27 +1,31 @@
 [build-system]
-requires = ["flit_core >=3.2,<4"]
+requires = ["uv_build>=0.8.18,<0.9.0"]
-build-backend = "flit_core.buildapi"
+build-backend = "uv_build"
 
 [project]
 name = "wavinfo"
-authors = [{name = "Jamie Hardt", email = "jamiehardt@me.com"}]
+version = "4.0.1"
+description = "Probe WAVE files for all metadata"
+authors = [{ name = "Jamie Hardt", email = "jamiehardt@me.com"}]
+license = "MIT" 
 readme = "README.md"
-dynamic = ["version", "description"]
+requires-python = ">=3.8"
-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"
+    "Programming Language :: Python :: 3.12",
-]
+    "Programming Language :: Python :: 3.13",
-dependencies = [
+    "Programming Language :: Python :: 3.14"
-    "lxml ~= 4.9.2"
 ]
+homepage = "https://github.com/iluvcapra/wavinfo"
+repository = "https://github.com/iluvcapra/wavinfo.git"
+documentation = "https://wavinfo.readthedocs.io/"
+urls.Tracker = 'https://github.com/iluvcapra/wavinfo/issues' 
 keywords = [
     'waveform', 
     'metadata', 
@@ -34,41 +38,34 @@ keywords = [
     'broadcast' 
 ]
 
-[tool.flit.module]
+dependencies = [
-name = "wavinfo"
+    "lxml>=6.0.2",
-
-[project.optional-dependencies]
-doc = [
-    'sphinx >= 5.3.0',
-    'sphinx_rtd_theme >= 1.1.1',
 ]
 
-[project.urls]
+[dependency-groups]
-Home = "https://github.com/iluvcapra/wavinfo"
+dev = [
-Documentation = "https://wavinfo.readthedocs.io/"
+    "pytest>=8.3.5",
-Source = "https://github.com/iluvcapra/wavinfo.git"
+    "ruff>=0.16.8",
-Issues = 'https://github.com/iluvcapra/wavinfo/issues' 
+]
-
+doc = [
-[project.entry_points.console_scripts]
+    "sphinx>=7.1.2",
-wavinfo = 'wavinfo.__main__:main'
+    "sphinx-rtd-theme>=3.0.2",
+]
 
 [project.scripts]
-wavinfo = "wavinfo.__main__:main"
+wavinfo = "wavinfo:__main__.main"
-
-[tool.flit.external-data]
-directory = "data"
 
 [tool.pyright]
 typeCheckingMode = "basic"
 
-[tool.pylint]
+[tool.ruff]
-max-line-length = 88
+line-length = 88
-disable = [
+indent-width = 4
-    "C0103", # (invalid-name)
+
-    "C0114", # (missing-module-docstring)
+[tool.ruff.lint]
-    "C0115", # (missing-class-docstring)
+fixable = ['ALL']
-    "C0116", # (missing-function-docstring)
+ignore = [
-    "R0903", # (too-few-public-methods)
+    'UP031', #Use format specifiers instead of percent format
-    "R0913", # (too-many-arguments)
-    "W0105", # (pointless-string-statement)
 ]
+
+

src/wavinfo/__init__.py

@@ -2,8 +2,7 @@
 Probe WAVE Files for iXML, Broadcast-WAVE and other metadata.
 """
 
-from .wave_reader import WavInfoReader
+__all__ = ["WavInfoEOFError", "WavInfoReader"]
-from .riff_parser import WavInfoEOFError
 
-__version__ = '2.3.0'
+from .riff_parser import WavInfoEOFError
-__short_version__ = '2.3.0'
+from .wave_reader import WavInfoReader

src/wavinfo/__main__.py

@@ -0,0 +1,216 @@
+from __future__ import annotations
+
+import datetime
+import importlib.metadata
+import json
+import os
+import sys
+from base64 import b64encode
+from cmd import Cmd
+from enum import Enum
+from optparse import OptionParser
+from shlex import split
+
+from . import WavInfoReader
+
+
+class MyJSONEncoder(json.JSONEncoder):
+    def default(self, o):
+        if isinstance(o, Enum):
+            return o._name_
+        elif isinstance(o, bytes):
+            return "base64:" + b64encode(o).decode("ascii")
+        else:
+            return super().default(o)
+
+
+class MissingDataError(RuntimeError):
+    pass
+
+
+class MetaBrowser(Cmd):
+    prompt = "(wavinfo) "
+
+    metadata: list | dict
+    path: list[str]
+
+    def preloop(self) -> None:
+        self.path = []
+        return super().preloop()
+
+    @property
+    def cwd(self):
+        root: list | dict = self.metadata
+        for key in self.path:
+            if isinstance(root, list):
+                root = root[int(key)]
+            else:
+                root = root[key]
+
+        return root
+
+    @staticmethod
+    def print_value(collection, key):
+        val = collection[key]
+        if isinstance(val, int):
+            print(f" - {key}: {val}")
+        elif isinstance(val, str):
+            print(f' - {key}: "{val}"')
+        elif isinstance(val, dict):
+            print(f" - {key}: Dict ({len(val)} keys)")
+        elif isinstance(val, list):
+            print(f" - {key}: List ({len(val)} keys)")
+        elif isinstance(val, bytes):
+            print(f" - {key}: ({len(val)} bytes)")
+        elif val is None:
+            print(f" - {key}: (NO VALUE)")
+        else:
+            print(f" - {key}: Unknown")
+
+    def do_ls(self, _):
+        "List items at the current node: LS"
+        root = self.cwd
+
+        if isinstance(root, list):
+            print("List:")
+            for i in range(len(root)):
+                self.print_value(root, i)
+
+        elif isinstance(root, dict):
+            print("Dictionary:")
+            for key in root:
+                self.print_value(root, key)
+
+        else:
+            print("Cannot print node, is not a list or dictionary.")
+
+    def do_cd(self, args):
+        'Switch to a different node: CD node-name | ".."'
+        argv = split(args)
+        if argv[0] == "..":
+            self.path = self.path[0:-1]
+        else:
+            if isinstance(self.cwd, list):
+                if int(argv[0]) < len(self.cwd):
+                    self.path = self.path + [argv[0]]
+                else:
+                    print(f"Index {argv[0]} does not exist")
+            elif isinstance(self.cwd, dict):
+                if argv[0] in self.cwd:
+                    self.path = self.path + [argv[0]]
+                else:
+                    print(f'Key "{argv[0]}" does not exist')
+
+        if len(self.path) > 0:
+            self.prompt = "(" + "/".join(self.path) + ") "
+        else:
+            self.prompt = "(wavinfo) "
+
+    def do_bye(self, _):
+        "Exit the interactive browser: BYE"
+        return True
+
+
+def main():
+    version = importlib.metadata.version("wavinfo")
+    manpath = os.path.dirname(__file__) + "/man"
+    parser = OptionParser()
+
+    parser.usage = "wavinfo (--adm | --ixml) <FILE> +"
+
+    # parser.add_option('--install-manpages',
+    #                   help="Install manual pages for wavinfo",
+    #                   default=False,
+    #                   action='store_true')
+
+    parser.add_option(
+        "--man", help="Read the manual and exit.", default=False, action="store_true"
+    )
+
+    parser.add_option(
+        "--adm", dest="adm", help="Output ADM XML", default=False, action="store_true"
+    )
+
+    parser.add_option(
+        "--ixml", dest="ixml", help="Output iXML", default=False, action="store_true"
+    )
+
+    parser.add_option(
+        "-i",
+        help="Read metadata with an interactive prompt",
+        default=False,
+        action="store_true",
+    )
+
+    (options, args) = parser.parse_args(sys.argv)
+
+    interactive_dict = []
+
+    # if options.install_manpages:
+    #     print("Installing manpages...")
+    #     print(f"Docfiles at {__file__}")
+    #     return
+
+    if options.man:
+        import shlex
+
+        print("Which man page?")
+        print("1) wavinfo usage")
+        print("7) General info on Wave file metadata")
+        m = input("?> ")
+
+        args = ["man", "-M", manpath, "1", "wavinfo"]
+        if m.startswith("7"):
+            args[3] = "7"
+
+        os.system(shlex.join(args))
+        return
+
+    for arg in args[1:]:
+        try:
+            this_file = WavInfoReader(path=arg)
+            if options.adm:
+                if this_file.adm:
+                    sys.stdout.write(this_file.adm.xml_str())
+                else:
+                    raise MissingDataError("adm")
+            elif options.ixml:
+                if this_file.ixml:
+                    sys.stdout.write(this_file.ixml.xml_str())
+                else:
+                    raise MissingDataError("ixml")
+            else:
+                ret_dict = {
+                    "filename": arg,
+                    "run_date": datetime.datetime.now(
+                        tz=datetime.timezone.utc
+                    ).isoformat(),
+                    "application": f"wavinfo {version}",
+                    "scopes": {},
+                }
+                for scope, name, value in this_file.walk():
+                    if scope not in ret_dict["scopes"]:
+                        ret_dict["scopes"][scope] = {}
+
+                    ret_dict["scopes"][scope][name] = value
+
+                if options.i:
+                    interactive_dict.append(ret_dict)
+                else:
+                    json.dump(ret_dict, cls=MyJSONEncoder, fp=sys.stdout, indent=2)
+
+        except MissingDataError as e:
+            print(
+                "MissingDataError: Missing metadata (%s) in file %s" % (e, arg),
+                file=sys.stderr,
+            )
+            continue
+
+        if len(interactive_dict) > 0:
+            cli = MetaBrowser()
+            cli.metadata = interactive_dict
+            cli.cmdloop()
+
+
+if __name__ == "__main__":
+    main()

src/wavinfo/man/man1/wavinfo.1

@@ -3,6 +3,7 @@
 wavinfo \- probe wave files for metadata
 .SH SYNOPSIS
 .SY wavinfo
+.I "[\-i]"
 .I "[\-\-adm]"
 .I "[\-\-ixml]"
 .I FILE ...
@@ -17,13 +18,17 @@ With no options,
 will emit a JSON (Javascript Object Notation) object containing all 
 detected metadata.
 .IP "\-\-adm"
-Output any Audio Definition Model (ADM) metadata in 
+Output Audio Definition Model (ADM) XML metadata in 
 .BR FILE .
 .IP "\-\-ixml"
 Output any iXML metdata in 
 .BR FILE .
 .IP "\-h, \-\-help"
 Print brief help.
+.IP "\-i"
+Enter 
+.I "interactive mode"
+and browse metadata in FILE with an interactive command prompt.
 .SH DETAILED DESCRIPTION
 .B wavinfo 
 collects metadata according to different 

src/wavinfo/man/man7/wavinfo.7

@@ -0,0 +1,380 @@
+.TH waveinfo 7 "2024-07-10" "Jamie Hardt" "Miscellaneous Information Manuals"
+.SH NAME 
+wavinfo \- WAVE file metadata
+.SH SYNOPSIS
+Everything you ever wanted to know about WAVE metadata but were afraid to ask. 
+.SH DESCRIPTION 
+.PP
+The WAVE file format is forwards-compatible. Apart from audio data, it can 
+hold arbitrary blocks of bytes which clients will automatically ignore 
+unless they recognize them and know how to read them.
+.PP
+Without saying too much about the structure and parsing of WAVE files 
+themselves \- a subject beyond the scope of this document \- WAVE files are 
+divided into segments or 
+.BR chunks ,
+which a client parser can either read or skip without reading. Chunks have 
+an identifier, or signature: a four-character-code that tells a client what
+kind of chunk it is, and a length. Based on this information, a client can look
+at the identifier and decide if it knows how to read a chunk and if it wants
+to. If it doesn't, it can simply read the length and skip past it.
+.PP
+Some chunks are mandated by the Microsoft standard, specifically
+.I fmt 
+and
+.I data
+in the case of PCM-encoded WAVE files. Other chunks, like 
+.I cue
+or
+.IR bext ,
+are optional, and optional chunks usually hold metadata. 
+.PP
+Chunks can also nest inside other chunks, a special identifier 
+.I LIST 
+is used to indicate these. A WAVE file is a recursive list: a top level 
+list of chunks, where chunks may contain a list of chunks themselves.
+.SS Order and Arrangement of Metadata Chunks in a WAVE File
+.PP
+Chunks in a WAVE file can appear in any order, and a capable parser can accept
+them appearing in any order. However, authorities give guidance on where chunks
+should be placed when creating a new WAVE file.
+.PP
+.IP 1)
+For all new WAVE files, clients should always place an empty chunk, a
+so-called
+.I JUNK
+chunk, in the first position in the top-level list of a WAVE file, and
+it should be sized large enough to hold a 
+.I ds64
+chunk record. This will allow clients to upgrade the file to a RF64
+WAVE file 
+.BR in-place ,
+without having to re-write the file or audio data.
+.IP 2)
+Older authorites recommend placing metadata before the audio data, so clients
+reading the file sequentially will hit it before having to seek through the
+audio. This may improve metadata read performance on certain architectures.
+.IP 3)
+Older authorities also recommend inserting 
+.I JUNK
+before the 
+.I data 
+chunk, sized so that the first byte of the
+.I data
+payload lands immediately at 0x1000 (4096), because this was a common factor of
+the page boundaries of many operating systems and architectures. This may
+optimize the audio I/O performance in certain situations. 
+.IP 4)
+Modern implementations (we're looking at 
+.B Pro Tools
+here) tend to place the Broadcast-WAVE
+.I bext
+metadata before the data, followed by the data itself, and then other data
+after that.
+.\" .PP
+.\" Clients reading WAVE files should be tolerant and accept any configuration of
+.\" chunks, and should accept any file as long as the obligatory
+.\" .I fmt
+.\" and 
+.\" .I data
+.\" chunks
+.\" are present. 
+.PP
+It's not unheard-of to see a naive implementor expect 
+.B only
+.I fmt 
+and 
+.I data 
+chunks, in this order, and to hard-code the offsets of the short
+.I fmt
+chunk and 
+.I data
+chunk into their program, and this is something that should always be checked
+when evaluating a new tool, just to make sure the developer didn't do this.
+Many coding examples and WAVE file explainers from the 90s and early aughts
+give the basic layout of a WAVE file, and naive devs go along with it.
+.SS Encoding and Decoding Text Metadata
+.\" .PP
+.\" Modern metadata systems, anything developed since the late aughts, will defer
+.\" encoding to an XML parser, so when dealing with
+.\" .I ixml 
+.\" or
+.\" .I axml
+.\" so a client can mostly ignore this problem.
+.\" .PP
+.\" The most established metadata systems are older than this though, and so the
+.\" entire weight of text encoding history falls upon the client.
+.\" .PP
+.\" The original WAVE specification, a part of the Microsoft/IBM Multimedia
+.\" interface of 1991, was written at a time when Windows was an ascendant and
+.\" soon-to-be dominant desktop environment. Audio files were almost 
+.\" never shared via LANs or the Internet or any other way. When audio files were
+.\" shared, among the miniscule number of people who did this, it was via BBS or
+.\" Usenet. Users at this time may have ripped them from CDs, but the cost of hard
+.\" drives and low quality of compressed formats at the time made this little more
+.\" than a curiosity. There was no CDBaby or CDDB to download and populate metadata
+.\" from at this time.
+.\" .PP
+.\" So, the 
+.\" .I INFO
+.\" and 
+.\" .I cue
+.\" metadata systems, which are by far the most prevalent and supported, were
+.\" published two years before the so-called "Endless September" of 1993 when the
+.\" Internet became mainstream, when Unicode was still a twinkle in the eye, and
+.\" two years before Ariana Grande was born.   
+.PP
+The safest assumption, and the mandate of the Microsoft, is that all text
+metadata, by default, be encoded in Windows codepage 819, a.k.a. ISO Latin
+alphabet 1, or ISO 8859-1. This covers most Western European scripts but
+excludes all of Asia, Russia, most of the European Near East, the Middle
+East.
+.PP 
+To account for this, Microsoft proposed a few conventions, none of which have 
+been adopted with any consistency among clients of the WAVE file standard.
+.IP 1)
+The RIFF standard defines a 
+.I cset 
+chunk which declares a Windows codepage for character encoding, along with a 
+native country code, language and dialect, which clients should use for
+determining text information. We have never seen a WAVE
+file with a 
+.I cest 
+chunk.
+.IP 2)
+Certain RIFF chunks allow the writing client to override the default encoding.
+Relevant to audio files are the 
+.I ltxt 
+chunk, which encodes a country, language, dialect and codepage along with a
+time range text note. We have never seen the text field on one of these 
+filled-out either.
+.PP 
+Some clients, in our experience, simply write UTF-8 into 
+.IR cue ,
+.IR labl ,
+and
+.I note 
+fields without any kind of framing.
+.PP 
+A practical solution is to assume either ISO Latin 1, Windows CP 859 or Windows
+CP 1252, and allow the client or user to override this based on its own
+inferences. The 
+.I chardet 
+python package may provide useable guesses for text encoding, YMMV.
+.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.
+.SS Optional WAVE Chunks
+.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 "LIST form INFO"
+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 "LIST form adtl"
+Contains 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 unlikely 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
+Dolby metadata is present in Dolby Atmos master ADM WAVE files.
+.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 REFERENCES
+(Note: We're not including URLs in this list, the title and standard number 
+should be sufficient to find almost all of these documents. The ITU, EBU and 
+IETF standards documents are freely-available.)
+.SS Essential File Format
+.TP  
+.B Multimedia Programming Interface and Data Specifications 1.0. Microsoft Corporation, 1991.
+The original definition of the 
+.I RIFF 
+container, the 
+.I WAVE 
+form, the original metadata facilites (like 
+.IR INFO " and " cue ),
+and things like language, country and
+dialect enumerations. This document also contains descriptions of certain
+variations on the WAVE, such as 
+.I LIST wavl
+and compressed WAVE files that are so rare in practice as to be virtually
+non-existent.
+.TP 
+.B ITU Recommendation BS.2088-1-2019 \- Long-form file format for the international exchange of audio programme mterials with metadata. ITU 2019.
+Formalized the RF64 file format, ADM carrier chunks like 
+.IR axml 
+and 
+.IR chna .
+Formally supercedes the previous standard for RF64, 
+.BR "EBU 3306 v1" .
+One oddity with this standard is it defines the file header for an extended 
+WAVE file to be 
+.IR BW64 ,
+but this is never seen in practice.
+.TP 
+.B RFC 2361 \- WAVE and AVI Codec Registries. IETF Network Working Group, 1998.
+Gives an exhaustive list of all of the codecs that Microsoft had assigned to
+vendor WAVE files as of 1998. At the time, numerous hardware vendors, sound
+card and chip manufacturers, sound software developers and others all provided
+their own slightly-different adaptive PCM codecs, linear predictive compression
+codes, DCTs and other things, and Microsoft would issue these vendors WAVE
+codec magic numbers. Almost all of these are no longer in use, the only ones
+one ever encounters in the modern era are integer PCM (0x01), floating-point
+PCM (0x03) and the extended format marker (0xFFFFFFFF). There are over a
+hundred codecs assigned, however, a roll-call of failed software and hardware
+brands.
+.SS Broadcast WAVE Format
+.TP 
+.B EBU Tech 3285 \- Specification of the Broadcast Wave Format (BWF). EBU, 2011.
+Defines the elements of a Broadcast WAVE file, the 
+.I bext 
+metadata chunk structure, allowed sample formats and other things. Over the 
+years the EBU has published numerous supplements covering extensions to the 
+format, such as embedding SMPTE UMIDs, pre-calculated loudness data (EBU Tech 
+3285 v2), 
+.I peak 
+waveform overview data (Suppl. 3), ADM metadata (Suppl. 5 and 7), Dolby master 
+metadata (Suppl. 6), and other things.
+.TP 
+.B SMPTE 330M-2011 \- Unique Material Identifier. SMPTE, 2011.
+Describes the format of the SMPTE UMID field, a 32- or 64-byte UUID used to 
+identify media files. UMIDs are usually a dumb number in their 32-byte form, 
+but the extended form can encode a high-precision timestamp (with options for 
+epoch and timescale) and geolocation information. Broadcast-WAVE files 
+conforming to 
+.B "EBU 3285 v2"
+have a SMPTE UMID embedded in the 
+.I bext 
+chunk.
+.SS Audio Definition Model 
+.TP 
+.B ITU Recommendation BS.2076-2-2019 \- Audio definition model. ITU, 2019.
+Defines the Audio Definition Model, entities, relationships and properties. If
+you ever had any questions about how ADM works, this is where you would start.
+.SS iXML Metadata 
+.TP 
+.B iXML Specification v3.01. Gallery Software, 2021.
+iXML is a standard for embedding mostly human-created metadata into WAVE files,
+and mostly with an emphasis on location sound recorders used on film and 
+television productions. Frustratingly the developer has never published a DTD 
+or schema validation or strict formal standard, and encourages vendors to just
+do whatever, but most of the heavily-traveled metadata fields are standardized,
+for recording information like a recording's scene, take, recording notes,
+circled or alt status. iXML also has a system of 
+.B "families"
+for associating several WAVE files together into one recording.

src/wavinfo/rf64_parser.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+import struct
+from typing import NamedTuple
+
+from . import riff_parser
+
+
+class RF64Context(NamedTuple):
+    sample_count: int
+    bigchunk_table: dict[str, int]
+
+
+def parse_rf64(stream, signature=b"RF64") -> RF64Context:
+    start = stream.tell()
+    assert stream.read(4) == b"WAVE"
+
+    ds64_chunk = riff_parser.parse_chunk(stream)
+    assert type(ds64_chunk) is riff_parser.ChunkDescriptor, (
+        f"Expected ds64 chunk here, found {type(ds64_chunk)}"
+    )
+
+    ds64_field_spec = "<QQQI"
+    ds64_fields_size = struct.calcsize(ds64_field_spec)
+    assert ds64_chunk.ident == b"ds64"
+
+    ds64_data = ds64_chunk.read_data(stream)
+    assert len(ds64_data) >= ds64_fields_size
+
+    riff_size, data_size, sample_count, length_lookup_table = struct.unpack(
+        ds64_field_spec, ds64_data[0:ds64_fields_size]
+    )
+
+    bigchunk_table = {}
+    chunksize64format = "<4sL"
+    # chunksize64size = struct.calcsize(chunksize64format)
+
+    for _ in range(length_lookup_table):
+        bigname, bigsize = struct.unpack_from(
+            chunksize64format, ds64_data, offset=ds64_fields_size
+        )
+        bigchunk_table[bigname] = bigsize
+
+    bigchunk_table[b"data"] = data_size
+    bigchunk_table[signature] = riff_size
+
+    stream.seek(start, 0)
+    return RF64Context(sample_count=sample_count, bigchunk_table=bigchunk_table)

src/wavinfo/riff_parser.py

@@ -1,7 +1,9 @@
+from __future__ import annotations
 
 import struct
-from collections import namedtuple
+from typing import NamedTuple
-from .rf64_parser import parse_rf64
+
+from .rf64_parser import RF64Context, parse_rf64
 
 
 class WavInfoEOFError(EOFError):
@@ -10,11 +12,17 @@ class WavInfoEOFError(EOFError):
         self.chunk_start = chunk_start
 
 
-class ListChunkDescriptor(namedtuple('ListChunkDescriptor', 'signature children')):
+class ListChunkDescriptor(NamedTuple):
-    pass
+    signature: bytes
+    children: list[ChunkDescriptor | ListChunkDescriptor]
 
 
-class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length rf64_context')):
+class ChunkDescriptor(NamedTuple):
+    ident: bytes
+    start: int
+    length: int
+    rf64_context: RF64Context | None
+
     def read_data(self, from_stream) -> bytes:
         from_stream.seek(self.start)
         return from_stream.read(self.length)
@@ -42,14 +50,15 @@ def parse_chunk(stream, rf64_context=None):
     if len(ident) != 4 or len(size_bytes) != 4:
         raise WavInfoEOFError(identifier=ident, chunk_start=header_start)
 
-    data_size = struct.unpack('<I', size_bytes)[0]
+    data_size = struct.unpack("<I", size_bytes)[0]
 
     if data_size == 0xFFFFFFFF:
-        if rf64_context is None and ident in {b'RF64', b'BW64'}:
+        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, \
+        assert rf64_context is not None, (
-            f"Sentinel data size 0xFFFFFFFF found outside of RF64 context"
+            "Sentinel data size 0xFFFFFFFF found outside of RF64 context"
+        )
 
         data_size = rf64_context.bigchunk_table[ident]
 
@@ -57,12 +66,14 @@ def parse_chunk(stream, rf64_context=None):
     if displacement % 2:
         displacement += 1
 
-    if ident in {b'RIFF', b'LIST', b'RF64', b'BW64', b'list'}:
+    if ident in {b"RIFF", b"LIST", b"RF64", b"BW64", b"list"}:
-        return parse_list_chunk(stream=stream, length=data_size,
+        return parse_list_chunk(
-                                rf64_context=rf64_context)
+            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,
+        return ChunkDescriptor(
-                               rf64_context=rf64_context)
+            ident=ident, start=data_start, length=data_size, rf64_context=rf64_context
+        )

src/wavinfo/umid_parser.py

@@ -0,0 +1,121 @@
+# from functools import reduce
+
+
+# def binary_to_string(binary_value):
+#     return reduce(lambda val, el: val + "{:02x}".format(el),
+#                   binary_value, '')
+
+# class UMIDParser:
+#     """
+#     Parse a raw binary SMPTE 330M Universal Materials Identifier
+#
+#     This implementation is based on SMPTE ST 330:2011
+#     """
+#     def __init__(self, raw_umid: bytes):
+#         self.raw_umid = raw_umid
+#
+# @property
+# def universal_label(self) -> bytearray:
+#     return self.raw_umid[0:12]
+#
+# @property
+# def basic_umid(self):
+#     return self.raw_umid[0:32]
+
+# def basic_umid_to_str(self):
+#     return binary_to_string(self.raw_umid[0:32])
+#
+# @property
+# def universal_label_is_valid(self) -> bool:
+#     valid_preamble = b'\x06\x0a\x2b\x34\x01\x01\x01\x05\x01\x01'
+#     return self.universal_label[0:len(valid_preamble)] == valid_preamble
+#
+# @property
+# def material_type(self) -> str:
+#     material_byte = self.raw_umid[10]
+#     if material_byte == 0x1:
+#         return 'picture'
+#     elif material_byte == 0x2:
+#         return 'audio'
+#     elif material_byte == 0x3:
+#         return 'data'
+#     elif material_byte == 0x4:
+#         return 'other'
+#     elif material_byte == 0x5:
+#         return 'picture_single_component'
+#     elif material_byte == 0x6:
+#         return 'picture_multiple_component'
+#     elif material_byte == 0x7:
+#         return 'audio_single_component'
+#     elif material_byte == 0x9:
+#         return 'audio_multiple_component'
+#     elif material_byte == 0xb:
+#         return 'auxiliary_single_component'
+#     elif material_byte == 0xc:
+#         return 'auxiliary_multiple_component'
+#     elif material_byte == 0xd:
+#         return 'mixed_components'
+#     elif material_byte == 0xf:
+#         return 'not_identified'
+#     else:
+#         return 'not_recognized'
+#
+# @property
+# def material_number_creation_method(self) -> str:
+#     method_byte = self.raw_umid[11]
+#     method_byte = (method_byte << 4) & 0xf
+#     if method_byte == 0x0:
+#         return 'undefined'
+#     elif method_byte == 0x1:
+#         return 'smpte'
+#     elif method_byte == 0x2:
+#         return 'uuid'
+#     elif method_byte == 0x3:
+#         return 'masked'
+#     elif method_byte == 0x4:
+#         return 'ieee1394'
+#     elif 0x5 <= method_byte <= 0x7:
+#         return 'reserved_undefined'
+#     else:
+#         return 'unrecognized'
+#
+# @property
+# def instance_number_creation_method(self) -> str:
+#     method_byte = self.raw_umid[11]
+#     method_byte = method_byte & 0xf
+#     if method_byte == 0x0:
+#         return 'undefined'
+#     elif method_byte == 0x01:
+#         return 'local_registration'
+#     elif method_byte == 0x02:
+#         return '24_bit_prs'
+#     elif method_byte == 0x03:
+#         return 'copy_number_and_16_bit_prs'
+#     elif 0x04 <= method_byte <= 0x0e:
+#         return 'reserved_undefined'
+#     elif method_byte == 0x0f:
+#         return 'live_stream'
+#     else:
+#         return 'unrecognized'
+#
+# @property
+# def indicated_length(self) -> str:
+#     if self.raw_umid[12] == 0x13:
+#         return 'basic'
+#     elif self.raw_umid[12] == 0x33:
+#         return 'extended'
+#
+# @property
+# def instance_number(self) -> bytearray:
+#     return self.raw_umid[13:3]
+#
+# @property
+# def material_number(self) -> bytearray:
+#     return self.raw_umid[16:16]
+#
+# @property
+# def source_pack(self) -> Union[bytearray, None]:
+#     if self.indicated_length == 'extended':
+#         return self.raw_umid[32:32]
+#     else:
+#         return None

src/wavinfo/wave_adm_reader.py

@@ -0,0 +1,212 @@
+"""
+ADM Reader
+"""
+from __future__ import annotations
+
+from collections import namedtuple
+from io import BytesIO
+from struct import calcsize, unpack, unpack_from
+
+from lxml import etree as ET
+
+ChannelEntry = namedtuple("ChannelEntry", "track_index uid track_ref pack_ref")
+
+
+class WavADMReader:
+    """
+    Reads XML data from an EBU ADM (Audio Definiton Model) WAV File.
+
+    """
+
+    def __init__(self, axml_data: bytes, chna_data: bytes):
+        header_fmt = "<HH"
+        uid_fmt = "<H12s14s11sx"
+
+        #: An :mod:`lxml.etree` of the ADM XML document
+        self.axml = ET.parse(BytesIO(axml_data))
+
+        _, uid_count = unpack(header_fmt, chna_data[0:4])
+
+        self.channel_uids = []
+
+        offset = calcsize(header_fmt)
+        for _ in range(uid_count):
+            track_index, uid, track_ref, pack_ref = unpack_from(
+                uid_fmt, chna_data, offset
+            )
+
+            # these values are either ascii or all null
+
+            self.channel_uids.append(
+                ChannelEntry(
+                    track_index - 1,
+                    uid.decode("ascii"),
+                    track_ref.decode("ascii"),
+                    pack_ref.decode("ascii"),
+                )
+            )
+
+            offset += calcsize(uid_fmt)
+
+    def xml_str(self) -> str:
+        """ADM XML as a string"""
+        return ET.tostring(self.axml).decode("utf-8")
+
+    def programme(self) -> dict:
+        """
+        Read the ADM `audioProgramme` data structure and some of its reference
+        properties.
+        """
+        ret_dict = {}
+
+        nsmap = self.axml.getroot().nsmap
+
+        afext = self.axml.find(".//audioFormatExtended", namespaces=nsmap)
+
+        program = afext.find("audioProgramme", namespaces=nsmap)
+        ret_dict["programme_id"] = program.get("audioProgrammeID")
+        ret_dict["programme_name"] = program.get("audioProgrammeName")
+        ret_dict["programme_start"] = program.get("start")
+        ret_dict["programme_end"] = program.get("end")
+        ret_dict["contents"] = []
+
+        for content_ref in program.findall("audioContentIDRef", namespaces=nsmap):
+            content_dict = {}
+            content_dict["content_id"] = cid = content_ref.text
+            content = afext.find(
+                "audioContent[@audioContentID='%s']" % cid, namespaces=nsmap
+            )
+            content_dict["content_name"] = content.get("audioContentName")
+            content_dict["objects"] = []
+
+            for object_ref in content.findall("audioObjectIDRef", namespaces=nsmap):
+                object_dict = {}
+                object_dict["object_id"] = oid = object_ref.text
+                object = afext.find(
+                    "audioObject[@audioObjectID='%s']" % oid, namespaces=nsmap
+                )
+                pack = object.find("audioPackFormatIDRef", namespaces=nsmap)
+                object_dict["object_name"] = object.get("audioObjectName")
+                object_dict["object_start"] = object.get("start")
+                object_dict["object_duration"] = object.get("duration")
+                object_dict["pack_id"] = pack.text
+                track_uid_list = []
+                for t in object.findall("audioTrackUIDRef", namespaces=nsmap):
+                    track_uid_list.append(t.text)
+
+                object_dict["track_uids"] = track_uid_list
+                content_dict["objects"].append(object_dict)
+
+            ret_dict["contents"].append(content_dict)
+
+        return ret_dict
+
+    def track_info(self, index) -> dict | None:
+        """
+        Information about a track in the WAV file.
+
+        :param index: index of audio track (indexed from zero)
+        :returns: a dictionary with *content_name*, *content_id*,
+            *object_name*, *object_id*,
+            *pack_format_name*, *pack_type*, *channel_format_name*
+        """
+        channel_info = next(
+            (x for x in self.channel_uids if x.track_index == index), None
+        )
+
+        if channel_info is None:
+            return None
+
+        ret_dict = {}
+
+        nsmap = self.axml.getroot().nsmap
+
+        afext = self.axml.find(".//audioFormatExtended", namespaces=nsmap)
+
+        trackformat_elem = afext.find(
+            "audioTrackFormat[@audioTrackFormatID='%s']" % channel_info.track_ref,
+            namespaces=nsmap,
+        )
+
+        stream_id = trackformat_elem[0].text
+
+        channelformatref_elem = afext.find(
+            ("audioStreamFormat[@audioStreamFormatID='%s']/audioChannelFormatIDRef")
+            % stream_id,
+            namespaces=nsmap,
+        )
+        if channelformatref_elem is not None:
+            channelformat_id = channelformatref_elem.text
+        else:
+            channelformat_id = None
+
+        packformatref_elem = afext.find(
+            ("audioStreamFormat[@audioStreamFormatID='%s']/audioPackFormatIDRef")
+            % stream_id,
+            namespaces=nsmap,
+        )
+
+        if packformatref_elem is not None:
+            packformat_id = packformatref_elem.text
+        else:
+            packformat_id = None
+
+        if channelformat_id:
+            channelformat_elem = afext.find(
+                "audioChannelFormat[@audioChannelFormatID='%s']" % channelformat_id,
+                namespaces=nsmap,
+            )
+            ret_dict["channel_format_name"] = channelformat_elem.get(
+                "audioChannelFormatName"
+            )
+        else:
+            ret_dict["channel_format_name"] = None
+
+        packformat_elem = afext.find(
+            "audioPackFormat[@audioPackFormatID='%s']" % packformat_id, namespaces=nsmap
+        )
+        if packformat_elem is not None:
+            ret_dict["pack_type"] = packformat_elem.get("typeDefinition")
+            ret_dict["pack_format_name"] = packformat_elem.get("audioPackFormatName")
+        else:
+            ret_dict["pack_type"] = None
+            ret_dict["pack_format_name"] = None
+
+        object_elem = afext.find(
+            "audioObject[audioPackFormatIDRef = '%s']" % packformat_id, namespaces=nsmap
+        )
+
+        if object_elem is not None:
+            ret_dict["audio_object_name"] = object_elem.get("audioObjectName")
+            object_id = object_elem.get("audioObjectID")
+            ret_dict["object_id"] = object_id
+
+            content_elem = afext.find(
+                "audioContent/[audioObjectIDRef = '%s']" % object_id, namespaces=nsmap
+            )
+
+            ret_dict["content_name"] = content_elem.get("audioContentName")
+            ret_dict["content_id"] = content_elem.get("audioContentID")
+
+        else:
+            ret_dict["audio_object_name"] = None
+            ret_dict["object_id"] = None
+            ret_dict["content_name"] = None
+            ret_dict["content_id"] = None
+
+        return ret_dict
+
+    def to_dict(self) -> dict:  # FIXME should be "asdict"
+        """
+        Get ADM metadata as a dictionary.
+        """
+
+        def make_entry(channel_uid_rec):
+            rd = channel_uid_rec._asdict()
+            rd.update(self.track_info(channel_uid_rec.track_index))
+            return rd
+
+        return {
+            'channel_entries': [make_entry(z) for z in self.channel_uids],
+            'programme': self.programme(),
+        }

src/wavinfo/wave_bext_reader.py

@@ -0,0 +1,112 @@
+from __future__ import annotations
+
+import struct
+
+# from .umid_parser import UMIDParser
+
+
+class WavBextReader:
+    def __init__(self, bext_data, encoding):
+        """
+        Read Broadcast-WAV extended metadata.
+        :param bext_data: The bytes-like data.
+        :param encoding: The encoding to use when decoding the text fields of
+            the BEXT metadata scope. According to EBU Rec 3285 this shall be
+            ASCII.
+        """
+        packstring = (
+            "<256s" + "32s" + "32s" + "10s" + "8s" + "QH" + "64s" + "hhhhh" + "180s"
+        )
+
+        rest_starts = struct.calcsize(packstring)
+        unpacked = struct.unpack(packstring, bext_data[:rest_starts])
+
+        def sanitize_bytes(b: bytes) -> str:
+            # honestly can't remember why I'm stripping nulls this way
+            first_null = next(
+                (index for index, byte in enumerate(b) if byte == 0), None
+            )
+            trimmed = b if first_null is None else b[:first_null]
+            decoded = trimmed.decode(encoding)
+            return decoded
+
+        #: Description. A free-text field up to 256 characters long.
+        self.description: str = sanitize_bytes(unpacked[0])
+
+        #: Originator. Usually the name of the encoding application, sometimes
+        #: an artist name.
+        self.originator: str = sanitize_bytes(unpacked[1])
+
+        #: A unique identifier for the file, a serial number.
+        self.originator_ref: str = sanitize_bytes(unpacked[2])
+
+        #: Date of the recording, in the format YYYY-MM-DD.
+        self.originator_date: str = sanitize_bytes(unpacked[3])
+
+        #: Time of the recording, in the format HH:MM:SS.
+        self.originator_time: str = sanitize_bytes(unpacked[4])
+
+        #: The sample offset of the start, usually relative
+        #: to midnight.
+        self.time_reference: int = unpacked[5]
+
+        #: A variable-length text field containing a list of processes and
+        #: and conversions performed on the file.
+        self.coding_history: str = sanitize_bytes(bext_data[rest_starts:])
+
+        #: BEXT version.
+        self.version: int = unpacked[6]
+
+        #: SMPTE 330M UMID of this audio file, 64 bytes are allocated though
+        #: the UMID may only be 32 bytes long.
+        self.umid: bytes | None = None
+
+        #: EBU R128 Integrated loudness, in LUFS.
+        self.loudness_value: float | None = None
+
+        #: EBU R128 Loudness range, in LUFS.
+        self.loudness_range: float | None = None
+
+        #: True peak level, in dBFS TP
+        self.max_true_peak: float | None = None
+
+        #: EBU R128 Maximum momentary loudness, in LUFS
+        self.max_momentary_loudness: float | None = None
+
+        #: EBU R128 Maximum short-term loudness, in LUFS.
+        self.max_shortterm_loudness: float | None = None
+
+        if self.version > 0:
+            self.umid = unpacked[7]
+
+        if self.version > 1:
+            self.loudness_value = unpacked[8] / 100.0
+            self.loudness_range = unpacked[9] / 100.0
+            self.max_true_peak = unpacked[10] / 100.0
+            self.max_momentary_loudness = unpacked[11] / 100.0
+            self.max_shortterm_loudness = unpacked[12] / 100.0
+
+    def to_dict(self):
+        # if self.umid is not None:
+        #     umid_parsed = UMIDParser(self.umid)
+        #     umid_str = umid_parsed.basic_umid_to_str()
+        # else:
+
+        # umid_str = None
+
+        return {
+            "description": self.description,
+            "originator": self.originator,
+            "originator_ref": self.originator_ref,
+            "originator_date": self.originator_date,
+            "originator_time": self.originator_time,
+            "time_reference": self.time_reference,
+            "version": self.version,
+            "umid": self.umid,
+            "coding_history": self.coding_history,
+            "loudness_value": self.loudness_value,
+            "loudness_range": self.loudness_range,
+            "max_true_peak": self.max_true_peak,
+            "max_momentary_loudness": self.max_momentary_loudness,
+            "max_shortterm_loudness": self.max_shortterm_loudness,
+        }

src/wavinfo/wave_cues_reader.py

@@ -7,12 +7,14 @@ 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 __future__ import annotations
-from typing import Optional, Tuple,  NamedTuple, List, Dict, Any, Generator
+
+from dataclasses import dataclass
+from struct import calcsize, unpack
+from typing import Any, Generator, NamedTuple
+
+from .riff_parser import ChunkDescriptor
 
 #: Country Codes used in the RIFF standard to resolve locale. These codes
 #: appear in CSET and LTXT metadata.
@@ -98,7 +100,15 @@ LanguageDialectCodes = """0 0 None Indicated
 
 
 class CueEntry(NamedTuple):
+    """
+    A ``cue`` element structure.
+    """
+
+    #: Cue "name" or id number
     name: int
+    #: Cue position, as a frame count in the play order of the WAVE file. In
+    #: principle this can be affected by playlists and ``wavl`` chunk
+    #: placement.
     position: int
     chunk_id: bytes
     chunk_start: int
@@ -112,31 +122,47 @@ class CueEntry(NamedTuple):
         return calcsize(cls.Format)
 
     @classmethod
-    def read(cls, data: bytes) -> 'CueEntry':
+    def read(cls, data: bytes) -> CueEntry:
-        assert len(data) == cls.format_size(), \
+        assert len(data) == cls.format_size(), (
-            f"cue data size incorrect, expected {calcsize(cls.Format)} found {len(data)}"
+            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],
+        return cls(
-                   chunk_start=parsed[3], block_start=parsed[4], 
+            name=parsed[0],
-                   sample_offset=parsed[5])
+            position=parsed[1],
+            chunk_id=parsed[2],
+            chunk_start=parsed[3],
+            block_start=parsed[4],
+            sample_offset=parsed[5],
+        )
 
 
 class LabelEntry(NamedTuple):
+    """
+    A ``labl`` structure.
+    """
+
     name: int
     text: str
 
     @classmethod
     def read(cls, data: bytes, encoding: str):
-        return cls(name=unpack("<I", data[0:4])[0],
+        return cls(
-                   text=data[4:].decode(encoding).rstrip("\0"))
+            name=unpack("<I", data[0:4])[0], text=data[4:].decode(encoding).rstrip("\0")
+        )
 
 
 NoteEntry = LabelEntry
 
 
 class RangeLabel(NamedTuple):
+    """
+    A ``ltxt`` structure.
+    """
+
     name: int
     length: int
     purpose: str
@@ -149,33 +175,50 @@ class RangeLabel(NamedTuple):
     @classmethod
     def read(cls, data: bytes, fallback_encoding: str):
         leader_struct_fmt = "<II4sHHHH"
-        parsed = unpack(leader_struct_fmt, data[0:calcsize(leader_struct_fmt)])
+        parsed = unpack(leader_struct_fmt, data[0 : calcsize(leader_struct_fmt)])
-        text_data = data[calcsize(leader_struct_fmt):]
+        text_data = data[calcsize(leader_struct_fmt) :]
+
+        purpose_str = parsed[2].decode('ascii')
 
         if data[6] != 0:
             fallback_encoding = f"cp{data[6]}"
 
-        return cls(name=parsed[0], length=parsed[1], purpose=parsed[2],
+        return cls(
-                   country=parsed[3], language=parsed[4], 
+            name=parsed[0],
-                   dialect=parsed[5], codepage=parsed[6], 
+            length=parsed[1],
-                   text=text_data.decode(fallback_encoding))
+            purpose=purpose_str,
+            country=parsed[3],
+            language=parsed[4],
+            dialect=parsed[5],
+            codepage=parsed[6],
+            text=text_data.decode(fallback_encoding),
+        )
 
 
 @dataclass
 class WavCuesReader:
-    cues: List[CueEntry]
+    #: Every ``cue`` entry in the file
-    labels: List[LabelEntry]
+    cues: list[CueEntry]
-    ranges: List[RangeLabel]
+
-    notes: List[NoteEntry]
+    #: Every ``labl`` in the file
+    labels: list[LabelEntry]
+
+    #: Every ``ltxt`` in the file
+    ranges: list[RangeLabel]
+
+    #: Every ``note`` in the file
+    notes: list[NoteEntry]
 
     @classmethod
-    def read_all(cls, f,
+    def read_all(
-              cues: Optional[ChunkDescriptor], 
+        cls,
-              labls: List[ChunkDescriptor],
+        f,
-              ltxts: List[ChunkDescriptor], 
+        cues: ChunkDescriptor | None,
-              notes: List[ChunkDescriptor],
+        labls: list[ChunkDescriptor],
-              fallback_encoding: str) -> 'WavCuesReader':
+        ltxts: list[ChunkDescriptor],
-        
+        notes: list[ChunkDescriptor],
+        fallback_encoding: str,
+    ) -> WavCuesReader:
         cue_list = []
         if cues is not None:
             cues_data = cues.read_data(f)
@@ -184,35 +227,33 @@ class WavCuesReader:
             cues_count = unpack("<I", cues_data[0:offset])
 
             for _ in range(cues_count[0]):
-                cue_bytes = cues_data[offset: offset + CueEntry.format_size()]
+                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), 
+                LabelEntry.read(labl.read_data(f), encoding=fallback_encoding)
-                                encoding=fallback_encoding)
             )
 
         range_list = []
         for r in ltxts:
             range_list.append(
-                RangeLabel.read(r.read_data(f), 
+                RangeLabel.read(r.read_data(f), fallback_encoding=fallback_encoding)
-                                fallback_encoding=fallback_encoding)
             )
 
         note_list = []
         for note in notes:
             note_list.append(
-                NoteEntry.read(note.read_data(f),
+                NoteEntry.read(note.read_data(f), encoding=fallback_encoding)
-                               encoding=fallback_encoding)
             )
 
-        return WavCuesReader(cues=cue_list, labels=label_list,
+        return WavCuesReader(
-                             ranges=range_list, notes=note_list)
+            cues=cue_list, labels=label_list, ranges=range_list, notes=note_list
+        )
 
-    def each_cue(self) -> Generator[Tuple[int, int], None, None]:
+    def each_cue(self) -> Generator[tuple[int, int], None, None]:
         """
         Iterate through each cue.
 
@@ -221,8 +262,7 @@ class WavCuesReader:
         for cue in self.cues:
             yield (cue.name, cue.sample_offset)
 
-    def label_and_note(self, cue_ident: int) -> Tuple[Optional[str],
+    def label_and_note(self, cue_ident: int) -> tuple[str | None, str | None]:
-                                                      Optional[str]]: 
         """
         Get the label and note (extended comment) for a cue.
 
@@ -230,43 +270,35 @@ class WavCuesReader:
         :returns: a tuple of the the cue's label (if present) and note (if
             present)
         """
-        label = next((l.text for l in self.labels 
+        label = next(
-                      if l.name == cue_ident), None)
+            (label.text for label in self.labels if label.name == cue_ident), None
-        note = next((n.text for n in self.notes 
+        )
-                     if n.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]:
+    def range(self, cue_ident: int) -> int | None:
         """
         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 
+        return next((r.length for r in self.ranges if r.name == cue_ident), None)
-                     if r.name == cue_ident), None)
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
-        retval = dict()
+        retval = {}
 
         for n, t in self.each_cue():
-            retval[n] = dict()
+            retval[n] = {}
-            retval[n]['frame'] = t
+            retval[n]["frame"] = t
             label, note = self.label_and_note(n)
             r = self.range(n)
 
             if label is not None:
-                retval[n]['label'] = label
+                retval[n]["label"] = label
             if note is not None:
-                retval[n]['note'] = note  
+                retval[n]["note"] = note
             if r is not None:
-                retval[n]['length'] = r 
+                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])
-
-
-

src/wavinfo/wave_dbmd_reader.py

@@ -7,17 +7,20 @@ Unless otherwise stated, all § references here are to
 .. _EBU Tech 3285 Supplement 6: https://tech.ebu.ch/docs/tech/tech3285s6.pdf
 """
 
-from enum import IntEnum, Enum
+from __future__ import annotations
-from struct import unpack
-from dataclasses import dataclass, asdict
-from typing import List, Optional, Tuple, Any, Union
 
+from dataclasses import asdict, dataclass
+from enum import Enum, IntEnum
 from io import BytesIO
+from struct import unpack
+from typing import Any
+
 
 class SegmentType(IntEnum):
     """
     Metadata segment type.
     """
+
     EndMarker = 0x0
     DolbyE = 0x1
     # Reserved2 = 0x2
@@ -28,10 +31,10 @@ class SegmentType(IntEnum):
     DolbyDigitalPlus = 0x7
     AudioInfo = 0x8
     DolbyAtmos = 0x9
-    DolbyAtmosSupplemental = 0xa
+    DolbyAtmosSupplemental = 0xA
 
     @classmethod
-    def _missing_(cls,val):
+    def _missing_(cls, val):
         return val
 
 
@@ -77,17 +80,16 @@ class DolbyDigitalPlusMetadata:
         MUTE = 0b111
         "-∞ dB"
 
-
     class DolbySurroundEncodingMode(Enum):
         """
         Dolby surround endcoding mode.
         """
+
         RESERVED = 0b11
         IN_USE = 0b10
         NOT_IN_USE = 0b01
         NOT_INDICATED = 0b00
 
-
     class BitStreamMode(Enum):
         """
         Dolby Digital Plus `bsmod` field
@@ -122,12 +124,12 @@ class DolbyDigitalPlusMetadata:
         should be interpreted as karaoke.
         """
 
-
     class AudioCodingMode(Enum):
         """
         Dolby Digital Plus `acmod` field
         § 4.3.2.3
         """
+
         RESERVED = 0b000
         CH_ORD_1_0 = 0b001
         "Mono"
@@ -144,7 +146,6 @@ class DolbyDigitalPlusMetadata:
         CH_ORD_3_2 = 0b111
         "LCR + LR surround"
 
-
     class CenterDownMixLevel(Enum):
         """
         § 4.3.3.1
@@ -161,89 +162,81 @@ class DolbyDigitalPlusMetadata:
 
         RESERVED = 0b11
 
-
     class SurroundDownMixLevel(Enum):
         """
         Dolby Digital Plus `surmixlev` field
         § 4.3.3.2
         """
+
         DOWN_3DB = 0b00
         DOWN_6DB = 0b01
         MUTE = 0b10
         RESERVED = 0b11
 
-
     class LanguageCode(int):
         """
         § 4.3.4.1
 
         Per ATSC/A52 § 5.4.2.12, this is not in use and always 0xFF.
         """
-        pass
-
 
     class MixLevel(int):
         """
         § 4.3.6.2
         """
-        pass
-
 
     class DialnormLevel(int):
         """
         § 4.3.4.4
         """
-        pass
-
 
     class RoomType(Enum):
         """
         `roomtyp` 4.3.6.3
         """
+
         NOT_INDICATED = 0b00
         LARGE_ROOM_X_CURVE = 0b01
         SMALL_ROOM_FLAT_CURVE = 0b10
         RESERVED = 0b11
 
-
     class PreferredDownMixMode(Enum):
         """
-        Indicates the creating engineer's preference of what the receiver should
+        Indicates the creating engineer's preference of what the receiver
-        downmix.
+        should downmix.
         § 4.3.8.1
         """
+
         NOT_INDICATED = 0b00
         PRO_LOGIC = 0b01
         STEREO = 0b10
         PRO_LOGIC_2 = 0b11
 
-
     class SurroundEXMode(IntEnum):
         """
         Dolby Surround-EX mode.
         `dsurexmod` § 4.3.9.1
         """
+
         NOT_INDICATED = 0b00
         NOT_SEX = 0b01
         SEX = 0b10
         PRO_LOGIC_2 = 0b11
 
-
     class HeadphoneMode(IntEnum):
         """
         `dheadphonmod` § 4.3.9.2
         """
+
         NOT_INDICATED = 0b00
         NOT_DOLBY_HEADPHONE = 0b01
         DOLBY_HEADPHONE = 0b10
         RESERVED = 0b11
 
-
     class ADConverterType(Enum):
         STANDARD = 0
         HDCD = 1
 
-
     class StreamDependency(Enum):
         """
         Encodes `ddplus_info1.stream_type` field § 4.3.12.1
@@ -254,12 +247,12 @@ class DolbyDigitalPlusMetadata:
         INDEPENDENT_FROM_DOLBY_DIGITAL = 2
         RESERVED = 3
 
-
     class RFCompressionProfile(Enum):
         """
         `compr1` RF compression profile
         § 4.3.10 (fig 42)
         """
+
         NONE = 0
         FILM_STANDARD = 1
         FILM_LIGHT = 2
@@ -348,53 +341,70 @@ class DolbyDigitalPlusMetadata:
 
     @staticmethod
     def load(buffer: bytes):
-        assert len(buffer) == 96, "Dolby Digital Plus segment incorrect size, "
+        assert len(buffer) == 96, (
-        "expected 96 got %i" % len(buffer)
+            "Dolby Digital Plus segment incorrect size, "
+            "expected 96 got %i" % len(buffer)
+        )
 
         def program_id(b) -> int:
             return b
 
         def program_info(b):
-            return (b & 0x40) > 0, \
+            return (
-                DolbyDigitalPlusMetadata.BitStreamMode(b & 0x38 >> 3), \
+                (b & 0x40) > 0,
-                DolbyDigitalPlusMetadata.AudioCodingMode(b & 0x7)
+                DolbyDigitalPlusMetadata.BitStreamMode(b & 0x38 >> 3),
+                DolbyDigitalPlusMetadata.AudioCodingMode(b & 0x7),
+            )
 
         def ddplus_reserved1(_):
             pass
 
         def surround_config(b):
-            return DolbyDigitalPlusMetadata.CenterDownMixLevel(b & 0x30 >> 4), \
+            return (
-                DolbyDigitalPlusMetadata.SurroundDownMixLevel(b & 0xc >> 2), \
+                DolbyDigitalPlusMetadata.CenterDownMixLevel(b & 0x30 >> 4),
-                DolbyDigitalPlusMetadata.DolbySurroundEncodingMode(b & 0x3)
+                DolbyDigitalPlusMetadata.SurroundDownMixLevel(b & 0xC >> 2),
+                DolbyDigitalPlusMetadata.DolbySurroundEncodingMode(b & 0x3),
+            )
 
         def dialnorm_info(b):
-            return (b & 0x80) > 0 , b & 0x40 > 0, b & 0x20 > 0, \
+            return (
-                DolbyDigitalPlusMetadata.DialnormLevel(b & 0x1f)
+                (b & 0x80) > 0,
+                b & 0x40 > 0,
+                b & 0x20 > 0,
+                DolbyDigitalPlusMetadata.DialnormLevel(b & 0x1F),
+            )
 
         def langcod(b) -> int:
             return b
 
         def audio_prod_info(b):
-            return (b & 0x80) > 0, \
+            return (
-                DolbyDigitalPlusMetadata.MixLevel(b & 0x7c >> 2), \
+                (b & 0x80) > 0,
-                DolbyDigitalPlusMetadata.RoomType(b & 0x3)
+                DolbyDigitalPlusMetadata.MixLevel(b & 0x7C >> 2),
+                DolbyDigitalPlusMetadata.RoomType(b & 0x3),
+            )
 
         # loro_center_downmix_level, loro_surround_downmix_level
         def ext_bsi1_word1(b):
-            return DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x38 >> 3), \
+            return DolbyDigitalPlusMetadata.DownMixLevelToken(
-                DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x7)
+                b & 0x38 >> 3
+            ), DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x7)
 
         # downmix_mode, ltrt_center_downmix_level, ltrt_surround_downmix_level
         def ext_bsi1_word2(b):
-            return DolbyDigitalPlusMetadata.PreferredDownMixMode(b & 0xC0 >> 6), \
+            return (
-                DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x38 >> 3), \
+                DolbyDigitalPlusMetadata.PreferredDownMixMode(b & 0xC0 >> 6),
-                DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x7)
+                DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x38 >> 3),
+                DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x7),
+            )
 
-        #surround_ex_mode, dolby_headphone_encoded, ad_converter_type 
+        # surround_ex_mode, dolby_headphone_encoded, ad_converter_type
         def ext_bsi2_word1(b):
-            return DolbyDigitalPlusMetadata.SurroundEXMode(b & 0x60 >> 5), \
+            return (
-                DolbyDigitalPlusMetadata.HeadphoneMode(b & 0x18 >> 3), \
+                DolbyDigitalPlusMetadata.SurroundEXMode(b & 0x60 >> 5),
-                DolbyDigitalPlusMetadata.ADConverterType( b & 0x4 >> 2)
+                DolbyDigitalPlusMetadata.HeadphoneMode(b & 0x18 >> 3),
+                DolbyDigitalPlusMetadata.ADConverterType(b & 0x4 >> 2),
+            )
 
         def ddplus_reserved2(_):
             pass
@@ -403,13 +413,13 @@ class DolbyDigitalPlusMetadata:
             return DolbyDigitalPlusMetadata.RFCompressionProfile(b)
 
         def dynrng1(b):
-            DolbyDigitalPlusMetadata.RFCompressionProfile(b) 
+            return DolbyDigitalPlusMetadata.RFCompressionProfile(b)
 
         def ddplus_reserved3(_):
             pass
 
         def ddplus_info1(b):
-            return DolbyDigitalPlusMetadata.StreamDependency(b & 0xc >> 2)
+            return DolbyDigitalPlusMetadata.StreamDependency(b & 0xC >> 2)
 
         def ddplus_reserved4(_):
             pass
@@ -423,14 +433,24 @@ class DolbyDigitalPlusMetadata:
         pid = program_id(buffer[0])
         lfe_on, bitstream_mode, audio_coding_mode = program_info(buffer[1])
         ddplus_reserved1(buffer[2:2])
-        center_downmix_level, surround_downmix_level, dolby_surround_encoded = surround_config(buffer[4])
+        center_downmix_level, surround_downmix_level, dolby_surround_encoded = (
-        langcode_present, copyright_bitstream, original_bitstream, dialnorm = dialnorm_info(buffer[5])
+            surround_config(buffer[4])
+        )
+        langcode_present, copyright_bitstream, original_bitstream, dialnorm = (
+            dialnorm_info(buffer[5])
+        )
         langcode = langcod(buffer[6])
         prod_info_exists, mixlevel, roomtype = audio_prod_info(buffer[7])
 
-        loro_center_downmix_level, loro_surround_downmix_level = ext_bsi1_word1(buffer[8])
+        loro_center_downmix_level, loro_surround_downmix_level = ext_bsi1_word1(
-        downmix_mode, ltrt_center_downmix_level, ltrt_surround_downmix_level = ext_bsi1_word2(buffer[9])
+            buffer[8]
-        surround_ex_mode, dolby_headphone_encoded, ad_converter_type = ext_bsi2_word1(buffer[10])
+        )
+        downmix_mode, ltrt_center_downmix_level, ltrt_surround_downmix_level = (
+            ext_bsi1_word2(buffer[9])
+        )
+        surround_ex_mode, dolby_headphone_encoded, ad_converter_type = ext_bsi2_word1(
+            buffer[10]
+        )
 
         ddplus_reserved2(buffer[11:14])
         compression = compr1(buffer[14])
@@ -441,7 +461,8 @@ class DolbyDigitalPlusMetadata:
         data_rate = datarate(buffer[25:27])
         reserved(buffer[27:69])
 
-        return DolbyDigitalPlusMetadata(program_id=pid,
+        return DolbyDigitalPlusMetadata(
+            program_id=pid,
             lfe_on=lfe_on,
             bitstream_mode=bitstream_mode,
             audio_coding_mode=audio_coding_mode,
@@ -467,7 +488,8 @@ class DolbyDigitalPlusMetadata:
             compression_profile=compression,
             dynamic_range=dynamic_range,
             stream_dependency=stream_info,
-            datarate_kbps=data_rate)
+            datarate_kbps=data_rate,
+        )
 
 
 @dataclass
@@ -486,7 +508,7 @@ class DolbyAtmosMetadata:
         NOT_INDICATED = 0x04
 
     tool_name: str
-    tool_version: Tuple[int,int,int]
+    tool_version: tuple[int, int, int]
     warp_mode: WarpMode
 
     SEGMENT_LENGTH = 248
@@ -494,15 +516,16 @@ class DolbyAtmosMetadata:
 
     @classmethod
     def load(cls, data: bytes):
-        assert len(data) == cls.SEGMENT_LENGTH, "DolbyAtmosMetadata segment "\
+        assert len(data) == cls.SEGMENT_LENGTH
-            "is incorrect length, expected %i actual was %i" % (cls.SEGMENT_LENGTH, len(data)) 
+        # (f"DolbyAtmosMetadata segment is incorrect length, "
+        #  f"expected {cls.SEGMENT_LENGTH} actual was {len(data)}")
 
         h = BytesIO(data)
 
         h.seek(32, 1)
         toolname = h.read(cls.TOOL_NAME_LENGTH)
         toolname = unpack("%is" % cls.TOOL_NAME_LENGTH, toolname)[0]
-        toolname = toolname.decode('utf-8').strip('\0')
+        toolname = toolname.decode("utf-8").strip("\0")
 
         vers = h.read(3)
         major, minor, fix = unpack("BBB", vers)
@@ -512,8 +535,11 @@ class DolbyAtmosMetadata:
         a_val = unpack("B", h.read(1))[0]
         warp_mode = a_val & 0x7
 
-        return DolbyAtmosMetadata(tool_name=toolname, 
+        return DolbyAtmosMetadata(
-            tool_version=(major, minor, fix), warp_mode=DolbyAtmosMetadata.WarpMode(warp_mode))
+            tool_name=toolname,
+            tool_version=(major, minor, fix),
+            warp_mode=DolbyAtmosMetadata.WarpMode(warp_mode),
+        )
 
 
 @dataclass
@@ -521,7 +547,8 @@ class DolbyAtmosSupplementalMetadata:
     """
     Dolby Atmos supplemental metadata segment.
 
-    https://github.com/DolbyLaboratories/dbmd-atmos-parser/blob/master/dbmd_atmos_parse/src/dbmd_atmos_parse.c
+    https://github.com/DolbyLaboratories/dbmd-atmos-parser/blob/
+    master/dbmd_atmos_parse/src/dbmd_atmos_parse.c
     """
 
     class BinauralRenderMode(Enum):
@@ -531,18 +558,15 @@ class DolbyAtmosSupplementalMetadata:
         MID = 0x03
         NOT_INDICATED = 0x04
 
-
     object_count: int
-    render_modes: List['DolbyAtmosSupplementalMetadata.BinauralRenderMode']
+    render_modes: list[DolbyAtmosSupplementalMetadata.BinauralRenderMode]
-    trim_modes: List[int]
+    trim_modes: list[int]
 
-
+    MAGIC = 0xF8726FBD
-    MAGIC = 0xf8726fbd
     TRIM_CONFIG_COUNT = 9
 
     @classmethod
     def load(cls, data: bytes):
-
         trim_modes = []
         render_modes = []
 
@@ -552,23 +576,24 @@ class DolbyAtmosSupplementalMetadata:
 
         object_count = unpack("<H", h.read(2))[0]
 
-        h.read(1) #skip 1
+        h.read(1)  # skip 1
 
         for _ in range(cls.TRIM_CONFIG_COUNT):
             auto_trim = unpack("B", h.read(1))
             trim_modes.append(auto_trim)
 
-            h.read(14) #skip 14
+            h.read(14)  # skip 14
 
-        h.read(object_count) # skip object_count bytes
+        h.read(object_count)  # skip object_count bytes
 
         for _ in range(object_count):
             binaural_mode = unpack("B", h.read(1))[0]
             binaural_mode &= 0x7
             render_modes.append(binaural_mode)
 
-        return DolbyAtmosSupplementalMetadata(object_count=object_count,
+        return DolbyAtmosSupplementalMetadata(
-            render_modes=render_modes,trim_modes=trim_modes)
+            object_count=object_count, render_modes=render_modes, trim_modes=trim_modes
+        )
 
 
 class WavDolbyMetadataReader:
@@ -582,22 +607,21 @@ 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: List[Tuple[Union[SegmentType, int], bool, Any]]
+    segment_list: list[tuple[SegmentType | int, bool, Any]]
 
-    version: Tuple[int,int,int,int]
+    version: tuple[int, int, int, int]
 
     @staticmethod
     def segment_checksum(bs: bytes, size: int):
         retval = size
         for b in bs:
             retval += int(b)
-            retval &= 0xff
+            retval &= 0xFF
 
-        retval = ((~retval) + 1) & 0xff
+        retval = ((~retval) + 1) & 0xFF
 
         return retval
 
-
     def __init__(self, dbmd_data):
         self.segment_list = []
 
@@ -606,18 +630,20 @@ class WavDolbyMetadataReader:
         v_vec = []
         for _ in range(4):
             b = h.read(1)
-            v_vec.insert(0, unpack("B",b)[0])
+            v_vec.insert(0, unpack("B", b)[0])
 
         self.version = tuple(v_vec)
 
         while True:
-            stype= SegmentType(unpack("B", h.read(1))[0])
+            stype = SegmentType(unpack("B", h.read(1))[0])
             if stype == SegmentType.EndMarker:
                 break
             else:
                 seg_size = unpack("<H", h.read(2))[0]
                 seg_payload = h.read(seg_size)
-                expected_checksum = WavDolbyMetadataReader.segment_checksum(seg_payload, seg_size)
+                expected_checksum = WavDolbyMetadataReader.segment_checksum(
+                    seg_payload, seg_size
+                )
                 checksum = unpack("B", h.read(1))[0]
 
                 segment = seg_payload
@@ -628,34 +654,41 @@ class WavDolbyMetadataReader:
                 elif stype == SegmentType.DolbyAtmosSupplemental:
                     segment = DolbyAtmosSupplementalMetadata.load(segment)
 
-                self.segment_list.append( (stype, checksum == expected_checksum, segment) )
+                self.segment_list.append(
+                    (stype, checksum == expected_checksum, segment)
+                )
 
-    def dolby_digital_plus(self) -> List[DolbyDigitalPlusMetadata]:
+    def dolby_digital_plus(self) -> list[DolbyDigitalPlusMetadata]:
         """
         Every valid Dolby Digital Plus metadata segment in the file.
         """
-        return [x[2] for x in self.segment_list \
+        return [
-            if x[0] == SegmentType.DolbyDigitalPlus and x[1]]
+            x[2]
+            for x in self.segment_list
+            if x[0] == SegmentType.DolbyDigitalPlus and x[1]
+        ]
 
-    def dolby_atmos(self) -> List[DolbyAtmosMetadata]:
+    def dolby_atmos(self) -> list[DolbyAtmosMetadata]:
         """
         Every valid Dolby Atmos metadata segment in the file.
         """
-        return [x[2] for x in self.segment_list \
+        return [
-            if x[0] == SegmentType.DolbyAtmos and x[1]]
+            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.
         """
-        return [x[2] for x in self.segment_list \
+        return [
-            if x[0] == SegmentType.DolbyAtmosSupplemental and x[1]]
+            x[2]
+            for x in self.segment_list
+            if x[0] == SegmentType.DolbyAtmosSupplemental and x[1]
+        ]
 
     def to_dict(self) -> dict:
+        ddp = [asdict(x) for x in self.dolby_digital_plus()]
+        atmos = [asdict(x) for x in self.dolby_atmos()]
+        # atmos_sup = map(lambda x: asdict(x), self.dolby_atmos_supplemental())
 
-        ddp = map(lambda x: asdict(x), self.dolby_digital_plus())
+        return {"dolby_digital_plus": ddp, "dolby_atmos": atmos}
-        atmos = map(lambda x: asdict(x), self.dolby_atmos())
-        #atmos_sup = map(lambda x: asdict(x), self.dolby_atmos_supplemental())
-        
-        return dict(dolby_digital_plus=list(ddp),
-             dolby_atmos=list(atmos))

src/wavinfo/wave_info_reader.py

@@ -0,0 +1,102 @@
+from __future__ import annotations
+
+from .riff_parser import ListChunkDescriptor, parse_chunk
+
+
+class WavInfoChunkReader:
+    def __init__(self, f, encoding):
+        self.encoding = encoding
+
+        f.seek(0)
+        parsed_chunks = parse_chunk(f)
+        assert type(parsed_chunks) is ListChunkDescriptor
+
+        list_chunks = [
+            chunk
+            for chunk in parsed_chunks.children
+            if type(chunk) is ListChunkDescriptor
+        ]
+
+        self.info_chunk = next(
+            (chunk for chunk in list_chunks if chunk.signature == b"INFO"), None
+        )
+
+        #: 'ICOP' Copyright
+        self.copyright: str | None = self._get_field(f, b"ICOP")
+        #: 'IPRD' Product
+        self.product: str | None = self._get_field(f, b"IPRD")
+        self.album: str | None = self.product
+        #: 'IGNR' Genre
+        self.genre: str | None = self._get_field(f, b"IGNR")
+        #: 'ISBJ' Subject
+        self.subject: str | None = self._get_field(f, b"ISBJ")
+        #: 'IART' Artist, composer, author
+        self.artist: str | None = self._get_field(f, b"IART")
+        #: 'ICMT' Comment
+        self.comment: str | None = self._get_field(f, b"ICMT")
+        #: 'ISFT' Software, encoding application
+        self.software: str | None = self._get_field(f, b"ISFT")
+        #: 'ICRD' Created date
+        self.created_date: str | None = self._get_field(f, b"ICRD")
+        #: 'IENG' Engineer
+        self.engineer: str | None = self._get_field(f, b"IENG")
+        #: 'ITCH' Technician
+        self.technician: str | None = self._get_field(f, b"ITCH")
+        #: 'IKEY' Keywords, keyword list
+        self.keywords: str | None = self._get_field(f, b"IKEY")
+        #: 'INAM' Name, title
+        self.title: str | None = self._get_field(f, b"INAM")
+        #: 'ISRC' Source
+        self.source: str | None = self._get_field(f, b"ISRC")
+        #: 'TAPE' Tape
+        self.tape: str | None = self._get_field(f, b"TAPE")
+        #: 'IARL' Archival Location
+        self.archival_location: str | None = self._get_field(f, b"IARL")
+        #: 'ICSM' Commissioned
+        self.commissioned: str | None = self._get_field(f, b"ICMS")
+
+    def _get_field(self, f, field_ident) -> str | None:
+        search = next(
+            (
+                (chunk.start, chunk.length)
+                for chunk in self.info_chunk.children
+                if chunk.ident == field_ident
+            ),
+            None,
+        )
+
+        if search is not None:
+            f.seek(search[0])
+            data = f.read(search[1])
+            return data.decode(self.encoding).rstrip("\0")
+        else:
+            return None
+
+    def to_dict(self) -> dict:  # FIXME should be asdict
+        """
+        A dictionary with all of the key/values read from the INFO scope.
+        """
+        return {
+            "copyright": self.copyright,
+            "product": self.product,
+            "album": self.album,
+            "genre": self.genre,
+            "artist": self.artist,
+            "comment": self.comment,
+            "software": self.software,
+            "created_date": self.created_date,
+            "engineer": self.engineer,
+            "keywords": self.keywords,
+            "title": self.title,
+            "source": self.source,
+            "tape": self.tape,
+            "commissioned": self.commissioned,
+            "archival_location": self.archival_location,
+            "subject": self.subject,
+            "technician": self.technician,
+        }
+
+    def __repr__(self):
+        return_val = self.to_dict()
+        return_val.update({"encoding": self.encoding})
+        return str(return_val)

src/wavinfo/wave_ixml_reader.py

@@ -1,10 +1,19 @@
-from lxml import etree as ET
+from __future__ import annotations
+
 import io
-from collections import namedtuple
-from typing import Optional
 from enum import IntEnum
 
-IXMLTrack = namedtuple('IXMLTrack', ['channel_index', 'interleave_index', 'name', 'function'])
+# from collections import namedtuple
+from typing import NamedTuple
+
+from lxml import etree as ET
+
+
+class IXMLTrack(NamedTuple):
+    channel_index: int
+    interleave_index: int
+    name: str
+    function: str
 
 
 class SteinbergMetadata:
@@ -16,6 +25,7 @@ class SteinbergMetadata:
         """
         Steinberg speaker format enumeration.
         """
+
         MONO = 0
         STEREO = 1
         LRC = 10
@@ -29,7 +39,7 @@ class SteinbergMetadata:
         CINE_71 = 27
         SDDS_70 = 24
         SDDS_71 = 26
-        MUSIC_60 = 21 #??
+        MUSIC_60 = 21  # ??
         MUSIC_61 = 23
         ATMOS_712 = 33
         ATMOS_504 = 35
@@ -68,16 +78,18 @@ class SteinbergMetadata:
         self.parsed = xml.find(self.Steinberg_xpath)
 
     @property
-    def audio_speaker_arrangement(self) -> Optional[AudioSpeakerArrangement]:
+    def audio_speaker_arrangement(self) -> AudioSpeakerArrangement | None:
         """
         `AudioSpeakerArrangement` property
         """
-        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'AudioSpeakerArrangement']/VALUE")
+        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]:
+    def sample_format_size(self) -> int | None:
         """
         AudioSampleFormatSize
         """
@@ -86,7 +98,7 @@ class SteinbergMetadata:
             return int(val.text)
 
     @property
-    def media_company(self) -> Optional[str]:
+    def media_company(self) -> str | None:
         """
         MediaCompany
         """
@@ -95,7 +107,7 @@ class SteinbergMetadata:
             return val.text
 
     @property
-    def media_drop_frames(self) -> Optional[bool]:
+    def media_drop_frames(self) -> bool | None:
         """
         MediaDropFrames
         """
@@ -104,7 +116,7 @@ class SteinbergMetadata:
             return val.text == "1"
 
     @property
-    def media_duration(self) -> Optional[float]:
+    def media_duration(self) -> float | None:
         """
         MediaDuration
         """
@@ -112,39 +124,36 @@ class SteinbergMetadata:
         if val is not None:
             return float(val.text)
 
-    @property
+    # @property
-    def media_start_time(self) -> Optional[float]:
+    # def media_start_time(self) -> float | None:
-        """
+    #     """
-        MediaStartTime
+    #     MediaStartTime
-        """
+    #     """
-        pass
 
-    @property
+    # @property
-    def media_track_title(self) -> Optional[str]:
+    # def media_track_title(self) -> str | None:
-        """
+    #     """
-        MediaTrackTitle
+    #     MediaTrackTitle
-        """
+    #     """
-        pass
 
-    @property
+    # @property
-    def program_name(self) -> Optional[str]:
+    # def program_name(self) -> str | None:
-        """
+    #     """
-        ProgramName
+    #     ProgramName
-        """
+    #     """
-        pass
 
-    @property
+    # @property
-    def program_version(self) -> Optional[str]:
+    # def program_version(self) -> str | None:
-        """
+    #     """
-        ProgramVersion
+    #     ProgramVersion
-        """
+    #     """
-        pass
 
 
 class WavIXMLFormat:
     """
     iXML recorder metadata.
     """
+
     def __init__(self, xml):
         """
         Parse iXML.
@@ -153,9 +162,9 @@ class WavIXMLFormat:
         self.source = xml
         xml_bytes = io.BytesIO(xml)
         parser = ET.XMLParser(recover=True)
-        self.parsed : ET.ElementTree = ET.parse(xml_bytes, parser=parser)
+        self.parsed: ET.ElementTree = ET.parse(xml_bytes, parser=parser)
 
-    def _get_text_value(self, xpath) -> Optional[str]:
+    def _get_text_value(self, xpath) -> str | None:
         e = self.parsed.find("./" + xpath)
         if e is not None:
             return e.text
@@ -180,57 +189,60 @@ class WavIXMLFormat:
         :yields: `IXMLTrack` for each track.
         """
         for track in self.parsed.find("./TRACK_LIST").iter():
-            if track.tag == 'TRACK':
+            if track.tag == "TRACK":
-                yield IXMLTrack(channel_index=track.xpath('string(CHANNEL_INDEX/text())'),
+                yield IXMLTrack(
-                                interleave_index=track.xpath('string(INTERLEAVE_INDEX/text())'),
+                    channel_index=track.xpath("string(CHANNEL_INDEX/text())"),
-                                name=track.xpath('string(NAME/text())'),
+                    interleave_index=track.xpath("string(INTERLEAVE_INDEX/text())"),
-                                function=track.xpath('string(FUNCTION/text())'))
+                    name=track.xpath("string(NAME/text())"),
+                    function=track.xpath("string(FUNCTION/text())"),
+                )
 
     @property
-    def project(self) -> Optional[str]:
+    def project(self) -> str | None:
         """
         The project/film name entered for the recording.
         """
         return self._get_text_value("PROJECT")
 
     @property
-    def scene(self) -> Optional[str]:
+    def scene(self) -> str | None:
         """
         Scene/slate.
         """
         return self._get_text_value("SCENE")
 
     @property
-    def take(self) ->  Optional[str]:
+    def take(self) -> str | None:
         """
         Take number.
         """
         return self._get_text_value("TAKE")
 
     @property
-    def tape(self) -> Optional[str]:
+    def tape(self) -> str | None:
         """
         Tape name.
         """
         return self._get_text_value("TAPE")
 
     @property
-    def family_uid(self) -> Optional[str]:
+    def family_uid(self) -> str | None:
         """
         The globally-unique ID for this file family. This may be in the format
-        of a GUID, or an EBU Rec 9 source identifier, or some other dumb number.
+        of a GUID, or an EBU Rec 9 source identifier, or some other dumb
+        number.
         """
         return self._get_text_value("FILE_SET/FAMILY_UID")
 
     @property
-    def family_name(self) -> Optional[str]:
+    def family_name(self) -> str | None:
         """
         The name of this file's file family.
         """
         return self._get_text_value("FILE_SET/FAMILY_NAME")
 
     @property
-    def steinberg(self) -> Optional[SteinbergMetadata]:
+    def steinberg(self) -> SteinbergMetadata | None:
         """
         Steinberg vendor iXML metadata if present.
         """
@@ -240,11 +252,12 @@ class WavIXMLFormat:
             return None
 
     def to_dict(self):
-        return dict(track_list=list(map(lambda x: x._asdict(), self.track_list)), 
+        return {
-            project=self.project,
+            "track_list": [x._asdict() for x in self.track_list],
-            scene=self.scene,
+            "project": self.project,
-            take=self.take,
+            "scene": self.scene,
-            tape=self.tape,
+            "take": self.take,
-            family_uid=self.family_uid,
+            "tape": self.tape,
-            family_name=self.family_name 
+            "family_uid": self.family_uid,
-            )
+            "family_name": self.family_name,
+        }

src/wavinfo/wave_reader.py

@@ -0,0 +1,267 @@
+from __future__ import annotations
+
+import os
+import pathlib
+import struct
+from typing import Any, Generator, NamedTuple
+
+from .riff_parser import ChunkDescriptor, ListChunkDescriptor, parse_chunk
+from .wave_adm_reader import WavADMReader
+from .wave_bext_reader import WavBextReader
+from .wave_cues_reader import WavCuesReader
+from .wave_dbmd_reader import WavDolbyMetadataReader
+from .wave_info_reader import WavInfoChunkReader
+from .wave_ixml_reader import WavIXMLFormat
+from .wave_smpl_reader import WavSmplReader
+
+#: Calculated statistics about the audio data.
+
+
+class WavDataDescriptor(NamedTuple):
+    byte_count: int
+    frame_count: int
+
+
+#: The format of the audio samples.
+class WavAudioFormat(NamedTuple):
+    audio_format: int
+    channel_count: int
+    sample_rate: int
+    byte_rate: int
+    block_align: int
+    bits_per_sample: int
+
+
+class WavInfoReader:
+    """
+    Parse a WAV audio file for metadata.
+    """
+
+    def __init__(self, path, info_encoding="latin_1", bext_encoding="ascii"):
+        """
+        Create a new reader object.
+
+        :param path:
+            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``, ``LABL`` and other RIFF-defined
+            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: WavAudioFormat | None = None
+
+        #: Statistics of the `data` section.
+        self.data: WavDataDescriptor | None = None
+
+        #: Broadcast-Wave metadata.
+        self.bext: WavBextReader | None = None
+
+        #: iXML metadata.
+        self.ixml: WavIXMLFormat | None = None
+
+        #: ADM Audio Definiton Model metadata.
+        self.adm: WavADMReader | None = None
+
+        #: Dolby bitstream metadata.
+        self.dolby: WavDolbyMetadataReader | None = None
+
+        #: RIFF INFO metadata.
+        self.info: WavInfoChunkReader | None = None
+
+        #: RIFF cues markers, labels, and notes.
+        self.cues: WavCuesReader | None = None
+
+        #: Sampler `smpl` metadata
+        self.smpl: WavSmplReader | None = 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: str = pathlib.Path(absolute_path).as_uri()
+
+            self.path = absolute_path
+
+            with open(path, "rb") as file:
+                self.get_wav_info(file)
+
+    def get_wav_info(self, wavfile):
+        chunks = parse_chunk(wavfile)
+        assert type(chunks) is ListChunkDescriptor
+
+        self.main_list = chunks.children
+        wavfile.seek(0)
+
+        self.fmt = self._get_format(wavfile)
+        self.bext = self._get_bext(wavfile, encoding=self.bext_encoding)
+        self.ixml = self._get_ixml(wavfile)
+        self.adm = self._get_adm(wavfile)
+        self.info = self._get_info(wavfile, encoding=self.info_encoding)
+        self.dolby = self._get_dbmd(wavfile)
+        self.cues = self._get_cue(wavfile)
+        self.smpl = self._get_sampler_loops(wavfile)
+        self.data = self._describe_data()
+
+    def _find_chunk_data(self, ident, from_stream, default_none=False) -> bytes | None:
+        top_chunks = (
+            chunk
+            for chunk in self.main_list
+            if type(chunk) is ChunkDescriptor and chunk.ident == ident
+        )
+
+        chunk_descriptor = next(top_chunks, None) if default_none else next(top_chunks)
+
+        return chunk_descriptor.read_data(from_stream) if chunk_descriptor else None
+
+    def _find_list_chunk(self, signature) -> ListChunkDescriptor | None:
+        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"
+        )
+
+        assert isinstance(self.fmt, WavAudioFormat)
+        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"
+
+        packstring = "<HHIIHH"
+        rest_starts = struct.calcsize(packstring)
+
+        unpacked = struct.unpack(packstring, fmt_data[:rest_starts])
+
+        return WavAudioFormat(
+            audio_format=unpacked[0],
+            channel_count=unpacked[1],
+            sample_rate=unpacked[2],
+            byte_rate=unpacked[3],
+            block_align=unpacked[4],
+            bits_per_sample=unpacked[5],
+        )
+
+    def _get_info(self, f, encoding):
+        finder = (
+            chunk.signature
+            for chunk in self.main_list
+            if type(chunk) is ListChunkDescriptor
+        )
+
+        if b"INFO" in finder:
+            return WavInfoChunkReader(f, encoding)
+
+    def _get_bext(self, f, encoding):
+        bext_data = self._find_chunk_data(b"bext", f, default_none=True)
+        return WavBextReader(bext_data, encoding) if bext_data else None
+
+    def _get_adm(self, f):
+        axml = self._find_chunk_data(b"axml", f, default_none=True)
+        chna = self._find_chunk_data(b"chna", f, default_none=True)
+        return WavADMReader(axml_data=axml, chna_data=chna) if axml and chna else None
+
+    def _get_dbmd(self, f):
+        dbmd_data = self._find_chunk_data(b"dbmd", f, default_none=True)
+        return WavDolbyMetadataReader(dbmd_data=dbmd_data) if dbmd_data else None
+
+    def _get_ixml(self, f):
+        ixml_data = self._find_chunk_data(b"iXML", f, default_none=True)
+        return WavIXMLFormat(ixml_data.rstrip(b"\0")) if ixml_data else None
+
+    def _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 type(c) is ChunkDescriptor and c.ident == b"labl"
+            ]
+            ltxts = [
+                c
+                for c in adtl.children
+                if type(c) is ChunkDescriptor and c.ident == b"ltxt"
+            ]
+            notes = [
+                c
+                for c in adtl.children
+                if type(c) is ChunkDescriptor and c.ident == b"note"
+            ]
+
+        return WavCuesReader.read_all(
+            f, cue, labls, ltxts, notes, fallback_encoding=self.info_encoding
+        )
+
+    def _get_sampler_loops(self, f):
+        sampler_data = self._find_chunk_data(b"smpl", f, default_none=True)
+        return WavSmplReader(sampler_data) if sampler_data else None
+
+    # FIXME: this should probably be named "iter()"
+    def walk(self) -> Generator[str, str, Any]:
+        """
+        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", "cues", "adm" or
+            "smpl".
+        """
+
+        scopes = ("fmt", "data", "ixml", "bext", "info", "adm", "cues", "dolby", "smpl")
+
+        for scope in scopes:
+            if scope in ["fmt", "data"]:
+                attr = self.__getattribute__(scope)
+                for field in attr._fields:
+                    yield scope, field, attr.__getattribute__(field)
+
+            else:
+                mdict = (
+                    self.__getattribute__(scope).to_dict()
+                    if self.__getattribute__(scope)
+                    else {}
+                )
+                for key in mdict:
+                    yield scope, key, mdict[key]
+
+    def __repr__(self):
+        return f"WavInfoReader({self.path}, {self.info_encoding}, {self.bext_encoding})"

src/wavinfo/wave_smpl_reader.py

@@ -0,0 +1,117 @@
+from __future__ import annotations
+
+import struct
+from typing import NamedTuple
+
+
+class WaveSmplLoop(NamedTuple):
+    ident: int
+    loop_type: int
+    start: int
+    end: int
+    detune_cents: int
+    repetition_count: int
+
+    def loop_type_desc(self):
+        if self.loop_type == 0:
+            return "FORWARD"
+        elif self.loop_type == 1:
+            return "FORWARD_BACKWARD"
+        elif self.loop_type == 2:
+            return "BACKWARD"
+        elif 3 <= self.loop_type <= 31:
+            return "RESERVED"
+        else:
+            return "VENDOR"
+
+    def to_dict(self):
+        return {
+            "ident": self.ident,
+            "loop_type": self.loop_type,
+            "loop_type_description": self.loop_type_desc(),
+            "start_samples": self.start,
+            "end_samples": self.end,
+            "detune_cents": self.detune_cents,
+            "repetition_count": self.repetition_count,
+        }
+
+
+class WavSmplReader:
+    def __init__(self, smpl_data: bytes):
+        """
+        Read sampler metadata from smpl chunk.
+        """
+
+        header_field_fmt = "<IIIIiIbbbbII"
+        loop_field_fmt = "<IIIIiI"
+        header_size = struct.calcsize(header_field_fmt)
+        loop_size = struct.calcsize(loop_field_fmt)
+
+        unpacked_data = struct.unpack(header_field_fmt, smpl_data[0:header_size])
+
+        #: The MIDI Manufacturer's Association code for the sampler
+        #: manufactuer, or 0 if not specific.
+        self.manufacturer: int = unpacked_data[0]
+
+        #: The manufacturer-assigned code for their specific sampler model, or
+        #: 0 if not specific.
+        self.product: int = unpacked_data[1]
+
+        #: The number of nanoseconds in one audio frame.
+        self.sample_period_ns: int = unpacked_data[2]
+
+        #: The MIDI note number for the loops in this sample
+        self.midi_note: int = unpacked_data[3]
+
+        #: The number of semitones above the MIDI note the loops tune for.
+        self.midi_pitch_detune_cents: int = unpacked_data[4]
+
+        #: SMPTE timecode format, one of (0, 24, 25, 29, 30)
+        self.smpte_format: int = unpacked_data[5]
+
+        #: The SMPTE offset to apply, as a tuple of four ints representing
+        #: hh, mm, ss, ff
+        self.smpte_offset: tuple[int, int, int, int] = unpacked_data[6:10]
+
+        loop_count = unpacked_data[10]
+        sampler_udata_length = unpacked_data[11]
+
+        #: List of loops in the file.
+        self.sample_loops: list[WaveSmplLoop] = []
+
+        loop_buffer = smpl_data[header_size : header_size + loop_size * loop_count]
+
+        for unpacked_loop in struct.iter_unpack(loop_field_fmt, loop_buffer):
+            self.sample_loops.append(
+                WaveSmplLoop(
+                    ident=unpacked_loop[0],
+                    loop_type=unpacked_loop[1],
+                    start=unpacked_loop[2],
+                    end=unpacked_loop[3],
+                    detune_cents=unpacked_loop[4],
+                    repetition_count=unpacked_loop[5],
+                )
+            )
+
+        #: Sampler-specific user data.
+        self.sampler_udata: bytes | None = None
+
+        if sampler_udata_length > 0:
+            self.sampler_udata = smpl_data[
+                header_size + loop_size * loop_count : header_size
+                + loop_size * loop_count
+                + sampler_udata_length
+            ]
+
+    def to_dict(self):
+        return {
+            "manufactuer": self.manufacturer,
+            "product": self.product,
+            "sample_period_ns": self.sample_period_ns,
+            "midi_note": self.midi_note,
+            "midi_pitch_detune_cents": self.midi_pitch_detune_cents,
+            "smpte_format": self.smpte_format,
+            "smpte_offset": "%02i:%02i:%02i:%02i" % self.smpte_offset,
+            "loops": [x.to_dict() for x in self.sample_loops],
+            "sampler_user_data": self.sampler_udata,
+        }

src/wavinfo/wavfind.py

@@ -0,0 +1,31 @@
+"""
+wavfind.py
+
+Under construction! Do Not Use!
+"""
+import sys
+from optparse import OptionGroup, OptionParser
+
+
+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()

tests/__init__.py

@@ -1,44 +0,0 @@
-from . import test_wave_parsing
-
-from io import BytesIO
-from typing import Generator
-import zipfile as zf
-import os.path
-import os
-from contextlib import contextmanager
-
-# class TestFileLoader:
-#     """
-#     This guy manages the test_files archive.
-#     """
-
-#     def __init__(self, test_file_arch_name = 'archive.zip') -> None:
-#         self.base_path = os.path.join(os.path.dirname(__file__), "test_files")
-#         self.test_file_arch_name = test_file_arch_name
-#         self._gather_test_files_into_archive()
-
-#     @property
-#     def arch_path(self):
-#         return os.path.join(self.base_path, self.test_file_arch_name)        
-
-#     @contextmanager
-#     def open(self, name) -> Generator[BytesIO]:
-#         z = zf.ZipFile(self.arch_path, 'r')
-#         member = z.open(name, 'r')
-#         try:
-#             yield member
-#         finally:
-#             zf.close()
-
-#     def _gather_test_files_into_archive(self):
-#         with zf.ZipFile(self.arch_path, 'a') as zip:
-#             for root, _, files in os.walk(self.base_path):
-#                 for name in files:
-#                     if root == self.base_path and name == self.test_file_arch_name:
-#                         continue
-#                     else:
-#                         p = os.path.join(root, name)
-#                         zip.write(p)
-#                         os.unlink(p)
-
-

tests/test_adm.py

@@ -2,8 +2,8 @@ from unittest import TestCase
 
 import wavinfo
 
-class TestADMWave(TestCase):
 
+class TestADMWave(TestCase):
     def setUp(self) -> None:
         self.protools_adm_wav = "tests/test_files/protools/Test_ADM_ProTools.wav"
         return super().setUp()
@@ -15,37 +15,41 @@ class TestADMWave(TestCase):
         adm = info.adm
         self.assertIsNotNone(adm)
 
+        assert adm is not None
         self.assertEqual(len(adm.channel_uids), 14)
 
     def test_to_dict(self):
         info = wavinfo.WavInfoReader(self.protools_adm_wav)
         adm = info.adm
+        assert adm is not None
         dict = adm.to_dict()
         self.assertIsNotNone(dict)
 
     def test_programme(self):
         info = wavinfo.WavInfoReader(self.protools_adm_wav)
         adm = info.adm
+        assert adm is not None
         pdict = adm.programme()
         self.assertIn("programme_id", pdict.keys())
         self.assertIn("programme_name", pdict.keys())
-        self.assertEqual(pdict['programme_id'], 'APR_1001')
+        self.assertEqual(pdict["programme_id"], "APR_1001")
-        self.assertEqual(pdict['programme_name'], 'Atmos_Master')
+        self.assertEqual(pdict["programme_name"], "Atmos_Master")
         self.assertIn("contents", pdict.keys())
         self.assertEqual(len(pdict["contents"]), 3)
 
     def test_track_info(self):
         info = wavinfo.WavInfoReader(self.protools_adm_wav)
         adm = info.adm
-
+        assert adm is not None
         t1 = adm.track_info(0)
-        self.assertTrue("channel_format_name" in t1.keys())
+        assert t1 is not None
+        self.assertTrue("channel_format_name" in t1)
         self.assertEqual("RoomCentricLeft", t1["channel_format_name"])
 
-        self.assertTrue("pack_format_name" in t1.keys())
+        self.assertTrue("pack_format_name" in t1)
         self.assertEqual("AtmosCustomPackFormat1", t1["pack_format_name"])
 
         t10 = adm.track_info(10)
-        self.assertTrue("content_name" in t10.keys())
+        assert t10 is not None
+        self.assertTrue("content_name" in t10)
         self.assertEqual("Dialog", t10["content_name"])
-        

tests/test_cue.py

@@ -1,8 +1,9 @@
-from unittest import TestCase
 from glob import glob
+from unittest import TestCase
 
 import wavinfo
 
+
 class TestCue(TestCase):
     def setUp(self) -> None:
         self.test_files = glob("tests/test_files/cue_chunks/*.wav")
@@ -12,8 +13,9 @@ class TestCue(TestCase):
         file1 = "tests/test_files/cue_chunks/STE-000.wav"
         w1 = wavinfo.WavInfoReader(file1)
         self.assertIsNotNone(w1.cues)
+        assert w1.cues is not None
         vals = list(w1.cues.each_cue())
-        self.assertEqual(vals, [(1,29616),(2,74592),(3,121200)])
+        self.assertEqual(vals, [(1, 29616), (2, 74592), (3, 121200)])
 
     def test_labels_notes(self):
         file = "tests/test_files/cue_chunks/izotoperx_cues_test.wav"
@@ -22,7 +24,7 @@ class TestCue(TestCase):
         assert w1.cues is not None
 
         for name, _ in w1.cues.each_cue():
-            self.assertIn(name,[1,2,3])
+            self.assertIn(name, [1, 2, 3])
             label, note = w1.cues.label_and_note(name)
             if name == 1:
                 self.assertEqual("Marker 1", label)
@@ -43,9 +45,11 @@ class TestCue(TestCase):
         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')
+        w = wavinfo.WavInfoReader(file, info_encoding="utf-8")
-        expected = ("Лорем ипсум долор сит амет, тимеам вивендум хас ет, "  
+        expected = (
-            "цу адолесценс дефинитионес еам.")
+            "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]
@@ -61,14 +65,10 @@ class TestCue(TestCase):
 
         self.assertEqual(len(w.cues.labels), 3)
         for label in w.cues.labels:
-            self.assertIn(label.name, [1,2,3])
+            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

@@ -1,7 +1,8 @@
 from unittest import TestCase
 
 import wavinfo
-from wavinfo.wave_dbmd_reader import SegmentType, DolbyAtmosMetadata, DolbyDigitalPlusMetadata
+from wavinfo.wave_dbmd_reader import DolbyDigitalPlusMetadata, SegmentType
+
 
 class TestDolby(TestCase):
     def setUp(self):
@@ -12,7 +13,7 @@ class TestDolby(TestCase):
         d = t1.dolby
 
         assert d is not None
-        self.assertEqual((1,0,0,6), d.version)
+        self.assertEqual((1, 0, 0, 6), d.version)
 
     def test_segments(self):
         t1 = wavinfo.WavInfoReader(self.test_file)
@@ -38,15 +39,23 @@ class TestDolby(TestCase):
         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.assertEqual(
-        self.assertTrue( ddp[0].audio_coding_mode, DolbyDigitalPlusMetadata.AudioCodingMode.CH_ORD_3_2 )
+            len(ddp),
-        self.assertTrue( ddp[0].lfe_on)
+            1,
+            ("Failed to find exactly one Dolby Digital Plus metadata segment"),
+        )
+
+        self.assertTrue(
+            ddp[0].audio_coding_mode,
+            DolbyDigitalPlusMetadata.AudioCodingMode.CH_ORD_3_2,
+        )
+        self.assertTrue(ddp[0].lfe_on)
 
     def test_atmos(self):
         t1 = wavinfo.WavInfoReader(self.test_file)
         d = t1.dolby
         assert d is not None
         atmos = d.dolby_atmos()
-        self.assertEqual(len(atmos), 1, "Failed to find exactly one Atmos metadata segment")
+        self.assertEqual(
-
+            len(atmos), 1, "Failed to find exactly one Atmos metadata segment"
-    
+        )

tests/test_main.py

@@ -1,33 +1,23 @@
+import glob
+import sys
 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', []):
+        with patch.object(sys, "argv", []):
-            try:
+            main()
-                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]):
+            with patch.object(sys, "argv", ["TEST", path]):
-                try:
+                 main()
-                    main()
-                except:
-                    self.fail("main() throwing an exception") 
 
     def test_ixml(self):
-        with patch.object(sys, 'argv', 
+        with patch.object(
-                          ['TEST', '--ixml', 'tests/test_files/sounddevices/A101_1.WAV']):
+            sys, "argv", ["TEST", "--ixml", "tests/test_files/sounddevices/A101_1.WAV"]
-            try:
+        ):
-                main()
+            main()
-            except:
-                self.fail("main() throwing an exception") 

tests/test_rf64.py

@@ -1,25 +1,20 @@
 # import os.path
 import gzip
 from glob import glob
-# from typing import Dict, Any, cast
 
+# from typing import Dict, Any, cast
 from unittest import TestCase
 
 # from .utils import all_files, ffprobe
-
 import wavinfo
 
-class TestRf64(TestCase):
 
+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)
+            with gzip.open(path) as gz:
-            wav_info = wavinfo.WavInfoReader(gz)
+                wav_info = wavinfo.WavInfoReader(gz)
-
+                self.assertIsNotNone(wav_info)
-            self.assertIsNotNone(wav_info)
-            # self.assertIsNotNone(wav_info.bext)
-

tests/test_smpl.py

@@ -0,0 +1,16 @@
+from glob import glob
+from unittest import TestCase
+
+import wavinfo
+
+
+class TestSmpl(TestCase):
+    def setUp(self) -> None:
+        self.test_files = glob("tests/test_files/smpl/*.wav")
+        return super().setUp()
+
+    def test_each(self):
+        for file in self.test_files:
+            w = wavinfo.WavInfoReader(file)
+            d = w.walk()
+            self.assertIsNotNone(d)

tests/test_walk.py

@@ -1,37 +1,35 @@
+import glob
 import unittest
+
 import wavinfo
 
-import glob
 
 class TestWalk(unittest.TestCase):
     def test_walk_metadata(self):
-        test_file = 'tests/test_files/protools/PT A101_4.A1.wav'
+        test_file = "tests/test_files/protools/PT A101_4.A1.wav"
         info = wavinfo.WavInfoReader(test_file)
 
-        tested_data , tested_format = False, False
+        tested_data, tested_format = False, False
         for scope, key, value in info.walk():
-            if scope == 'fmt':
+            if scope == "fmt" and key == "channel_count":
-                if key == 'channel_count':
                     tested_format = True
                     self.assertEqual(value, 2)
-            if scope == 'data':
+            if scope == "data" and key == "frame_count":
-                if key == 'frame_count':
                     tested_data = True
                     self.assertEqual(value, 144140)
 
         self.assertTrue(tested_data and tested_format)
 
     def test_walk_all(self):
-        for file in glob.glob('tests/test_files/**/*.wav'):
+        for file in glob.glob("tests/test_files/**/*.wav"):
             info = wavinfo.WavInfoReader(file)
 
-            try:
+            # try:
-                for _, _, _ in info.walk():
+            for _, _, _ in info.walk():
-                    pass 
+                pass
-            except:
+            # except Exception as e:
-                self.fail(f"Failed to walk metadata in file {file}")
+                # self.fail(f"Failed to walk metadata in file {file}: {e}")
 
 
-
+if __name__ == "__main__":
-if __name__ == '__main__':
     unittest.main()

tests/test_wave_parsing.py

@@ -1,19 +1,21 @@
 import os.path
 from glob import glob
-from typing import Dict, Any, cast
+from typing import Any, Dict, cast
-
 from unittest import TestCase
 
-from .utils import all_files, ffprobe
-
 import wavinfo
 
+from .utils import all_files, ffprobe
+
 
 class TestWaveInfo(TestCase):
     def test_sanity(self):
         for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
-            self.assertEqual(info.__repr__(), 'WavInfoReader({}, latin_1, ascii)'.format(os.path.abspath(wav_file)))
+            self.assertEqual(
+                info.__repr__(),
+                f"WavInfoReader({os.path.abspath(wav_file)}, latin_1, ascii)",
+            )
             self.assertIsNotNone(info)
 
     def test_fmt_against_ffprobe(self):
@@ -24,23 +26,39 @@ class TestWaveInfo(TestCase):
             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(
-            self.assertEqual(info.fmt.sample_rate, int(ffprobe_info['streams'][0]['sample_rate']))
+                info.fmt.channel_count, ffprobe_info["streams"][0]["channels"]
-            self.assertEqual(info.fmt.bits_per_sample, int(ffprobe_info['streams'][0]['bits_per_sample']))
+            )
+            self.assertEqual(
+                info.fmt.sample_rate, int(ffprobe_info["streams"][0]["sample_rate"])
+            )
+            self.assertEqual(
+                info.fmt.bits_per_sample,
+                int(ffprobe_info["streams"][0]["bits_per_sample"]),
+            )
 
             if info.fmt.audio_format == 1:
-                self.assertTrue(ffprobe_info['streams'][0]['codec_name'].startswith('pcm'))
+                self.assertTrue(
-                streams = ffprobe_info['streams'][0]
+                    ffprobe_info["streams"][0]["codec_name"].startswith("pcm")
-                byte_rate = int(streams['sample_rate']) * streams['channels'] * int(streams['bits_per_sample']) / 8
+                )
+                streams = ffprobe_info["streams"][0]
+                byte_rate = (
+                    int(streams["sample_rate"])
+                    * streams["channels"]
+                    * int(streams["bits_per_sample"])
+                    / 8
+                )
                 self.assertEqual(info.fmt.byte_rate, byte_rate)
 
     def test_data_against_ffprobe(self):
         for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
-            ffprobe_info = cast(Dict[str,Any], 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']))
+            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():
@@ -49,41 +67,78 @@ class TestWaveInfo(TestCase):
             assert ffprobe_info is not None
 
             if info.bext:
-                if 'comment' in ffprobe_info['format']['tags']:
+                if "comment" in ffprobe_info["format"]["tags"]:
-                    self.assertEqual(info.bext.description, ffprobe_info['format']['tags']['comment'])
+                    self.assertEqual(
+                        info.bext.description, ffprobe_info["format"]["tags"]["comment"]
+                    )
                 else:
-                    self.assertEqual(info.bext.description, '')
+                    self.assertEqual(info.bext.description, "")
 
-                if 'encoded_by' in ffprobe_info['format']['tags']:
+                if "encoded_by" in ffprobe_info["format"]["tags"]:
-                    self.assertEqual(info.bext.originator, ffprobe_info['format']['tags']['encoded_by'])
+                    self.assertEqual(
+                        info.bext.originator,
+                        ffprobe_info["format"]["tags"]["encoded_by"],
+                    )
                 else:
-                    self.assertEqual(info.bext.originator, '')
+                    self.assertEqual(info.bext.originator, "")
 
-                if 'originator_reference' in ffprobe_info['format']['tags']:
+                if "originator_reference" in ffprobe_info["format"]["tags"]:
-                    self.assertEqual(info.bext.originator_ref, ffprobe_info['format']['tags']['originator_reference'])
+                    self.assertEqual(
+                        info.bext.originator_ref,
+                        ffprobe_info["format"]["tags"]["originator_reference"],
+                    )
                 else:
-                    self.assertEqual(info.bext.originator_ref, '')
+                    self.assertEqual(info.bext.originator_ref, "")
 
                 # these don't always reflect the bext info
-                # self.assertEqual(info.bext.originator_date, ffprobe_info['format']['tags']['date'])
+                # self.assertEqual(info.bext.originator_date,
-                # self.assertEqual(info.bext.originator_time, ffprobe_info['format']['tags']['creation_time'])
+                # ffprobe_info['format']['tags']['date'])
-                self.assertEqual(info.bext.time_reference, int(ffprobe_info['format']['tags']['time_reference']))
+                # self.assertEqual(info.bext.originator_time,
+                # ffprobe_info['format']['tags']['creation_time'])
+                self.assertEqual(
+                    info.bext.time_reference,
+                    int(ffprobe_info["format"]["tags"]["time_reference"]),
+                )
 
-                if 'coding_history' in ffprobe_info['format']['tags']:
+                if "coding_history" in ffprobe_info["format"]["tags"]:
-                    self.assertEqual(info.bext.coding_history, ffprobe_info['format']['tags']['coding_history'])
+                    self.assertEqual(
+                        info.bext.coding_history,
+                        ffprobe_info["format"]["tags"]["coding_history"],
+                    )
                 else:
-                    self.assertEqual(info.bext.coding_history, '')
+                    self.assertEqual(info.bext.coding_history, "")
 
     def test_ixml(self):
-        expected = {'A101_4.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '4',
+        expected = {
-                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124015008231000'},
+            "A101_4.WAV": {
-                    'A101_3.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '3',
+                "project": "BMH",
-                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124014008228300'},
+                "scene": "A101",
-                    'A101_2.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '2',
+                "take": "4",
-                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124004008218600'},
+                "tape": "18Y12M31",
-                    'A101_1.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '1',
+                "family_uid": "USSDVGR1112089007124015008231000",
-                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124001008206300'},
+            },
-                    }
+            "A101_3.WAV": {
+                "project": "BMH",
+                "scene": "A101",
+                "take": "3",
+                "tape": "18Y12M31",
+                "family_uid": "USSDVGR1112089007124014008228300",
+            },
+            "A101_2.WAV": {
+                "project": "BMH",
+                "scene": "A101",
+                "take": "2",
+                "tape": "18Y12M31",
+                "family_uid": "USSDVGR1112089007124004008218600",
+            },
+            "A101_1.WAV": {
+                "project": "BMH",
+                "scene": "A101",
+                "take": "1",
+                "tape": "18Y12M31",
+                "family_uid": "USSDVGR1112089007124001008206300",
+            },
+        }
 
         for wav_file in all_files():
             basename = os.path.basename(wav_file)
@@ -92,19 +147,19 @@ class TestWaveInfo(TestCase):
                 e = expected[basename]
                 self.assertIsNotNone(info.ixml)
                 assert info.ixml is not None
-                self.assertEqual(e['project'], info.ixml.project)
+                self.assertEqual(e["project"], info.ixml.project)
-                self.assertEqual(e['scene'], info.ixml.scene)
+                self.assertEqual(e["scene"], info.ixml.scene)
-                self.assertEqual(e['take'], info.ixml.take)
+                self.assertEqual(e["take"], info.ixml.take)
-                self.assertEqual(e['tape'], info.ixml.tape)
+                self.assertEqual(e["tape"], info.ixml.tape)
-                self.assertEqual(e['family_uid'], info.ixml.family_uid)
+                self.assertEqual(e["family_uid"], info.ixml.family_uid)
 
                 for track in info.ixml.track_list:
                     self.assertIsNotNone(track.channel_index)
-                    if basename == 'A101_4.WAV' and track.channel_index == '1':
+                    if basename == "A101_4.WAV" and track.channel_index == "1":
-                        self.assertEqual(track.name, 'MKH516 A')
+                        self.assertEqual(track.name, "MKH516 A")
 
     def test_steinberg_ixml(self):
-        nuendo_files = 'tests/test_files/nuendo/*.wav'
+        nuendo_files = "tests/test_files/nuendo/*.wav"
         for file in glob(nuendo_files):
             info = wavinfo.WavInfoReader(file)
             assert info.ixml is not None
@@ -112,7 +167,10 @@ class TestWaveInfo(TestCase):
             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.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)
 
@@ -124,22 +182,21 @@ class TestWaveInfo(TestCase):
         self.assertIsNone(info.ixml.steinberg)
 
     def test_info_metadata(self):
-        file_with_metadata = 'tests/test_files/sound_grinder_pro/new_camera bumb 1.wav'
+        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.title, "camera bumb 1")
-        self.assertEqual(info.artist, 'Jamie Hardt')
+        self.assertEqual(info.artist, "Jamie Hardt")
-        self.assertEqual(info.copyright, '© 2010 Jamie Hardt')
+        self.assertEqual(info.copyright, "© 2010 Jamie Hardt")
-        self.assertEqual(info.product, 'Test Sounds')  # album
+        self.assertEqual(info.product, "Test Sounds")  # album
         self.assertEqual(info.album, info.product)
-        self.assertEqual(info.comment, 'Comments')
+        self.assertEqual(info.comment, "Comments")
-        self.assertEqual(info.software, 'Sound Grinder Pro')
+        self.assertEqual(info.software, "Sound Grinder Pro")
-        self.assertEqual(info.created_date, '2010-12-28')
+        self.assertEqual(info.created_date, "2010-12-28")
-        self.assertEqual(info.engineer, 'JPH')
+        self.assertEqual(info.engineer, "JPH")
-        self.assertEqual(info.keywords, 'Sound Effect, movement, microphone, bump')
+        self.assertEqual(info.keywords, "Sound Effect, movement, microphone, bump")
-        self.assertEqual(info.title, 'camera bumb 1')
+        self.assertEqual(info.title, "camera bumb 1")
         self.assertEqual(type(info.to_dict()), dict)
         self.assertEqual(type(info.__repr__()), str)
-

tests/test_zoom_f8.py

@@ -1,12 +1,6 @@
-import os.path
-import sys
-import json
-import subprocess
-from subprocess import PIPE
-
 from unittest import TestCase
 
-import wavinfo
+# import wavinfo
 
 
 class TestZoomF8(TestCase):

tests/utils.py

@@ -1,36 +1,23 @@
-import os.path
-import sys
-import subprocess
-from subprocess import PIPE
 import json
+import os.path
+import subprocess
 
-FFPROBE = 'ffprobe'
+FFPROBE = "ffprobe"
 
 
 def ffprobe(path):
     arguments = [FFPROBE, "-of", "json", "-show_format", "-show_streams", path]
-    if int(sys.version[0]) <  3:
+    process = subprocess.run(arguments, check=True, capture_output=True)
-        process = subprocess.Popen(arguments, stdout=PIPE)
+    if process.returncode == 0:
-        process.wait()
+        output_str = process.stdout.decode("utf-8")
-        if process.returncode == 0:
+        return json.loads(output_str)
-            output = process.communicate()[0]
-            if output:
-                output_str = output.decode('utf-8')
-                return json.loads(output_str)
-        else:
-            return None
     else:
-        process = subprocess.run(arguments, stdin=None, stdout=PIPE, stderr=PIPE)
+        return None
-        if process.returncode == 0:
-            output_str = process.stdout.decode('utf-8')
-            return json.loads(output_str)
-        else:
-            return None
 
 
 def all_files():
-    for dirpath, _, filenames in os.walk('tests/test_files'):
+    for dirpath, _, filenames in os.walk("tests/test_files"):
         for filename in filenames:
             _, ext = os.path.splitext(filename)
-            if ext in ['.wav', '.WAV']:
+            if ext in [".wav", ".WAV"]:
                 yield os.path.join(dirpath, filename)

wavinfo/__main__.py

@@ -1,70 +0,0 @@
-from optparse import OptionParser, OptionGroup
-import datetime
-from . import WavInfoReader
-from . import __version__
-import sys
-import json
-from enum import Enum
-
-class MyJSONEncoder(json.JSONEncoder):
-    def default(self, o):
-        if isinstance(o, Enum):
-            return o._name_
-        else:
-            return super().default(o)
-
-class MissingDataError(RuntimeError):
-    pass
-
-def main():
-    parser = OptionParser()
-
-    parser.usage = 'wavinfo (--adm | --ixml) <FILE> +'
-
-    # parser.add_option('-f', dest='output_format', help='Set the output format',
-    #                   default='json',
-    #                   metavar='FORMAT')
-
-    parser.add_option('--adm', dest='adm', help='Output ADM XML', 
-        default=False, action='store_true')
-
-    parser.add_option('--ixml', dest='ixml', help='Output iXML',
-        default=False, action='store_true')
-
-    (options, args) = parser.parse_args(sys.argv)
-    for arg in args[1:]:
-        try:
-            this_file = WavInfoReader(path=arg)
-            if options.adm:
-                if this_file.adm:
-                    sys.stdout.write(this_file.adm.xml_str())
-                else:
-                    raise MissingDataError("adm")
-            elif options.ixml:
-                if this_file.ixml:
-                    sys.stdout.write(this_file.ixml.xml_str())
-                else:
-                    raise MissingDataError("ixml")
-            else:
-                ret_dict = {
-                    'filename': arg, 
-                    'run_date': datetime.datetime.now().isoformat() , 
-                    'application': "wavinfo " + __version__, 
-                    'scopes': {}
-                    }
-                for scope, name, value in this_file.walk():
-                    if scope not in ret_dict['scopes'].keys():
-                        ret_dict['scopes'][scope] = {}
-
-                    ret_dict['scopes'][scope][name] = value
-
-                json.dump(ret_dict, cls=MyJSONEncoder, fp=sys.stdout, indent=2)
-        except MissingDataError as e:
-            print("MissingDataError: Missing metadata (%s) in file %s" % (e, arg), file=sys.stderr)
-            continue
-        except Exception as e:
-            raise e
-
-
-if __name__ == "__main__":
-    main()

wavinfo/rf64_parser.py

@@ -1,42 +0,0 @@
-import struct
-from collections import namedtuple
-
-from . import riff_parser
-
-RF64Context = namedtuple('RF64Context','sample_count bigchunk_table')
-
-
-def parse_rf64(stream, signature = b'RF64') -> RF64Context:
-    start = stream.tell()
-    assert( stream.read(4) == b'WAVE' )
-
-    ds64_chunk = riff_parser.parse_chunk(stream)
-    assert type(ds64_chunk) is riff_parser.ChunkDescriptor, \
-        f"Expected ds64 chunk here, found {type(ds64_chunk)}"
-
-    ds64_field_spec = "<QQQI"
-    ds64_fields_size = struct.calcsize(ds64_field_spec)
-    assert(ds64_chunk.ident == b'ds64')
-
-    ds64_data = ds64_chunk.read_data(stream)
-    assert(len(ds64_data) >= ds64_fields_size)
-
-    riff_size, data_size, sample_count, length_lookup_table = struct.unpack(
-        ds64_field_spec, ds64_data[0:ds64_fields_size])
-
-    bigchunk_table = {}
-    chunksize64format = "<4sL"
-    # chunksize64size = struct.calcsize(chunksize64format)
-
-    for _ in range(length_lookup_table):
-        bigname, bigsize = struct.unpack_from(chunksize64format, ds64_data,
-                                              offset= ds64_fields_size)
-        bigchunk_table[bigname] = bigsize
-
-    bigchunk_table[b'data'] = data_size
-    bigchunk_table[signature] = riff_size
-
-    stream.seek(start, 0)
-    return RF64Context( sample_count=sample_count,
-                       bigchunk_table=bigchunk_table)
-

wavinfo/umid_parser.py

@@ -1,121 +0,0 @@
-# from functools import reduce
-
-
-# def binary_to_string(binary_value):
-#     return reduce(lambda val, el: val + "{:02x}".format(el), binary_value, '')
-
-
-# class UMIDParser:
-#     """
-#     Parse a raw binary SMPTE 330M Universal Materials Identifier
-#
-#     This implementation is based on SMPTE ST 330:2011
-#     """
-#     def __init__(self, raw_umid: bytes):
-#         self.raw_umid = raw_umid
-    #
-    # @property
-    # def universal_label(self) -> bytearray:
-    #     return self.raw_umid[0:12]
-    #
-    # @property
-    # def basic_umid(self):
-    #     return self.raw_umid[0:32]
-
-    # def basic_umid_to_str(self):
-    #     return binary_to_string(self.raw_umid[0:32])
-    #
-    # @property
-    # def universal_label_is_valid(self) -> bool:
-    #     valid_preamble = b'\x06\x0a\x2b\x34\x01\x01\x01\x05\x01\x01'
-    #     return self.universal_label[0:len(valid_preamble)] == valid_preamble
-    #
-    # @property
-    # def material_type(self) -> str:
-    #     material_byte = self.raw_umid[10]
-    #     if material_byte == 0x1:
-    #         return 'picture'
-    #     elif material_byte == 0x2:
-    #         return 'audio'
-    #     elif material_byte == 0x3:
-    #         return 'data'
-    #     elif material_byte == 0x4:
-    #         return 'other'
-    #     elif material_byte == 0x5:
-    #         return 'picture_single_component'
-    #     elif material_byte == 0x6:
-    #         return 'picture_multiple_component'
-    #     elif material_byte == 0x7:
-    #         return 'audio_single_component'
-    #     elif material_byte == 0x9:
-    #         return 'audio_multiple_component'
-    #     elif material_byte == 0xb:
-    #         return 'auxiliary_single_component'
-    #     elif material_byte == 0xc:
-    #         return 'auxiliary_multiple_component'
-    #     elif material_byte == 0xd:
-    #         return 'mixed_components'
-    #     elif material_byte == 0xf:
-    #         return 'not_identified'
-    #     else:
-    #         return 'not_recognized'
-    #
-    # @property
-    # def material_number_creation_method(self) -> str:
-    #     method_byte = self.raw_umid[11]
-    #     method_byte = (method_byte << 4) & 0xf
-    #     if method_byte == 0x0:
-    #         return 'undefined'
-    #     elif method_byte == 0x1:
-    #         return 'smpte'
-    #     elif method_byte == 0x2:
-    #         return 'uuid'
-    #     elif method_byte == 0x3:
-    #         return 'masked'
-    #     elif method_byte == 0x4:
-    #         return 'ieee1394'
-    #     elif 0x5 <= method_byte <= 0x7:
-    #         return 'reserved_undefined'
-    #     else:
-    #         return 'unrecognized'
-    #
-    # @property
-    # def instance_number_creation_method(self) -> str:
-    #     method_byte = self.raw_umid[11]
-    #     method_byte = method_byte & 0xf
-    #     if method_byte == 0x0:
-    #         return 'undefined'
-    #     elif method_byte == 0x01:
-    #         return 'local_registration'
-    #     elif method_byte == 0x02:
-    #         return '24_bit_prs'
-    #     elif method_byte == 0x03:
-    #         return 'copy_number_and_16_bit_prs'
-    #     elif 0x04 <= method_byte <= 0x0e:
-    #         return 'reserved_undefined'
-    #     elif method_byte == 0x0f:
-    #         return 'live_stream'
-    #     else:
-    #         return 'unrecognized'
-    #
-    # @property
-    # def indicated_length(self) -> str:
-    #     if self.raw_umid[12] == 0x13:
-    #         return 'basic'
-    #     elif self.raw_umid[12] == 0x33:
-    #         return 'extended'
-    #
-    # @property
-    # def instance_number(self) -> bytearray:
-    #     return self.raw_umid[13:3]
-    #
-    # @property
-    # def material_number(self) -> bytearray:
-    #     return self.raw_umid[16:16]
-    #
-    # @property
-    # def source_pack(self) -> Union[bytearray, None]:
-    #     if self.indicated_length == 'extended':
-    #         return self.raw_umid[32:32]
-    #     else:
-    #         return None

wavinfo/wave_adm_reader.py

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

wavinfo/wave_bext_reader.py

@@ -1,104 +0,0 @@
-import struct
-# from .umid_parser import UMIDParser
-
-from typing import Optional
-
-class WavBextReader:
-    def __init__(self, bext_data, encoding):
-        """
-        Read Broadcast-WAV extended metadata.
-        :param bext_data: The bytes-like data.
-        :param encoding: The encoding to use when decoding the text fields of the
-                 BEXT metadata scope. According to EBU Rec 3285 this shall be ASCII.
-        """
-        packstring = "<256s" + "32s" + "32s" + "10s" + "8s" + "QH" + "64s" + "hhhhh" + "180s"
-
-        rest_starts = struct.calcsize(packstring)
-        unpacked = struct.unpack(packstring, bext_data[:rest_starts])
-
-        def sanitize_bytes(b : bytes) -> str:
-            # honestly can't remember why I'm stripping nulls this way
-            first_null = next((index for index, byte in enumerate(b) if byte == 0), None)
-            trimmed = b if first_null is None else b[:first_null]
-            decoded = trimmed.decode(encoding)
-            return decoded
-
-        #: Description. A free-text field up to 256 characters long.
-        self.description : str = sanitize_bytes(unpacked[0])
-            
-        #: Originator. Usually the name of the encoding application, sometimes
-        #: an artist name.
-        self.originator : str = sanitize_bytes(unpacked[1])
-            
-        #: A unique identifier for the file, a serial number.
-        self.originator_ref : str = sanitize_bytes(unpacked[2])
-            
-        #: Date of the recording, in the format YYYY-MM-DD.
-        self.originator_date : str = sanitize_bytes(unpacked[3])
-            
-        #: Time of the recording, in the format HH:MM:SS.
-        self.originator_time : str = sanitize_bytes(unpacked[4])
-            
-        #: The sample offset of the start, usually relative 
-        #: to midnight. 
-        self.time_reference : int  = unpacked[5]
-            
-        #: A variable-length text field containing a list of processes and
-        #: and conversions performed on the file.
-        self.coding_history : str = sanitize_bytes(bext_data[rest_starts:])
-            
-        #: BEXT version. 
-        self.version : int = unpacked[6]
-            
-        #: SMPTE 330M UMID of this audio file, 64 bytes are allocated though the UMID
-        #: may only be 32 bytes long.
-        self.umid : Optional[bytes] = None
-            
-        #: EBU R128 Integrated loudness, in LUFS.
-        self.loudness_value : Optional[float] = None
-            
-        #: EBU R128 Loudness range, in LUFS.
-        self.loudness_range : Optional[float] = None
-            
-        #: True peak level, in dBFS TP
-        self.max_true_peak : Optional[float] = None
-            
-        #: EBU R128 Maximum momentary loudness, in LUFS
-        self.max_momentary_loudness : Optional[float] = None
-            
-        #: EBU R128 Maximum short-term loudness, in LUFS.
-        self.max_shortterm_loudness : Optional[float] = None
-
-        if self.version > 0:
-            self.umid = unpacked[7]
-
-        if self.version > 1:
-            self.loudness_value = unpacked[8] / 100.0
-            self.loudness_range = unpacked[9] / 100.0
-            self.max_true_peak = unpacked[10] / 100.0
-            self.max_momentary_loudness = unpacked[11] / 100.0
-            self.max_shortterm_loudness = unpacked[12] / 100.0
-
-    def to_dict(self):
-        # if self.umid is not None:
-        #     umid_parsed = UMIDParser(self.umid)
-        #     umid_str = umid_parsed.basic_umid_to_str()
-        # else:
-            
-        umid_str = None
-
-        return {'description': self.description,
-                'originator': self.originator,
-                'originator_ref': self.originator_ref,
-                'originator_date': self.originator_date,
-                'originator_time': self.originator_time,
-                'time_reference': self.time_reference,
-                'version': self.version,
-                'umid': umid_str,
-                'coding_history': self.coding_history,
-                'loudness_value': self.loudness_value,
-                'loudness_range': self.loudness_range,
-                'max_true_peak': self.max_true_peak,
-                'max_momentary_loudness': self.max_momentary_loudness,
-                'max_shortterm_loudness': self.max_shortterm_loudness
-                }

wavinfo/wave_info_reader.py

@@ -1,88 +0,0 @@
-from .riff_parser import parse_chunk, ListChunkDescriptor
-
-from typing import Optional
-
-class WavInfoChunkReader:
-
-    def __init__(self, f, encoding):
-        self.encoding = encoding
-
-        f.seek(0)
-        parsed_chunks = parse_chunk(f)
-
-        list_chunks = [chunk for chunk in parsed_chunks.children if type(chunk) is ListChunkDescriptor]
-
-        self.info_chunk = next((chunk for chunk in list_chunks if chunk.signature == b'INFO'), None)
-
-        #: 'ICOP' Copyright
-        self.copyright : Optional[str] = self._get_field(f, b'ICOP')
-        #: 'IPRD' Product
-        self.product : Optional[str]= self._get_field(f, b'IPRD')
-        self.album : Optional[str] = self.product
-        #: 'IGNR' Genre
-        self.genre : Optional[str] = self._get_field(f, b'IGNR')
-        #: 'ISBJ' 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')
-        #: 'ICMT' Comment
-        self.comment : Optional[str] = self._get_field(f, b'ICMT')
-        #: 'ISFT' Software, encoding application
-        self.software : Optional[str] = self._get_field(f, b'ISFT')
-        #: 'ICRD' Created date
-        self.created_date : Optional[str] = self._get_field(f, b'ICRD')
-        #: 'IENG' Engineer
-        self.engineer : Optional[str] = self._get_field(f, b'IENG')
-        #: 'ITCH' Technician
-        self.technician : Optional[str] = self._get_field(f, b'ITCH')
-        #: 'IKEY' Keywords, keyword list
-        self.keywords : Optional[str] = self._get_field(f, b'IKEY')
-        #: 'INAM' Name, title
-        self.title : Optional[str] = self._get_field(f, b'INAM')
-        #: 'ISRC' Source
-        self.source : Optional[str] = self._get_field(f, b'ISRC')
-        #: 'TAPE' Tape
-        self.tape : Optional[str] = self._get_field(f, b'TAPE')
-        #: 'IARL' Archival Location
-        self.archival_location : Optional[str] = self._get_field(f, b'IARL')
-        #: 'ICSM' Commissioned
-        self.commissioned : Optional[str] = self._get_field(f, b'ICMS')
-
-    def _get_field(self, f, field_ident) -> Optional[str]:
-        search = next(((chunk.start, chunk.length) for chunk in self.info_chunk.children if chunk.ident == field_ident),
-                      None)
-
-        if search is not None:
-            f.seek(search[0])
-            data = f.read(search[1])
-            return data.decode(self.encoding).rstrip('\0')
-        else:
-            return None
-
-    def to_dict(self) -> dict: #FIXME should be asdict 
-        """
-        A dictionary with all of the key/values read from the INFO scope.
-        """
-        return {'copyright': self.copyright,
-                'product': self.product,
-                'album': self.album,
-                'genre': self.genre,
-                'artist': self.artist,
-                'comment': self.comment,
-                'software': self.software,
-                'created_date': self.created_date,
-                'engineer': self.engineer,
-                'keywords': self.keywords,
-                'title': self.title,
-                'source': self.source,
-                'tape': self.tape,
-                'commissioned': self.commissioned,
-                'archival_location': self.archival_location,
-                'subject': self.subject,
-                'technician': self.technician
-                }
-
-    def __repr__(self):
-        return_val = self.to_dict()
-        return_val.update({'encoding': self.encoding})
-        return str(return_val)

wavinfo/wave_reader.py

@@ -1,219 +0,0 @@
-#-*- coding: utf-8 -*-
-import struct
-import os
-from collections import namedtuple
-
-from typing import Optional, Generator, Any
-
-import pathlib
-
-from .riff_parser import parse_chunk, ChunkDescriptor, ListChunkDescriptor
-from .wave_ixml_reader import WavIXMLFormat
-from .wave_bext_reader import WavBextReader
-from .wave_info_reader import WavInfoChunkReader
-from .wave_adm_reader import WavADMReader
-from .wave_dbmd_reader import WavDolbyMetadataReader
-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'])
-
-
-class WavInfoReader:
-    """
-    Parse a WAV audio file for metadata.
-    """
-
-    def __init__(self, path, info_encoding='latin_1', bext_encoding='ascii'):
-        """
-        Create a new reader object.
-
-        :param path: 
-            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``, ``LABL`` and other RIFF-defined
-            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: str = pathlib.Path(absolute_path).as_uri()
-
-            self.path = absolute_path
-        
-            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)
-
-        self.fmt = self._get_format(wavfile)
-        self.bext = self._get_bext(wavfile, encoding=self.bext_encoding)
-        self.ixml = self._get_ixml(wavfile)
-        self.adm  = self._get_adm(wavfile)
-        self.info = self._get_info(wavfile, encoding=self.info_encoding)
-        self.dolby = self._get_dbmd(wavfile)
-        self.cues = self._get_cue(wavfile)
-        self.data = self._describe_data()
-
-    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)
-
-        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')
-
-        assert isinstance(self.fmt, WavAudioFormat)
-        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"
-
-        packstring = "<HHIIHH"
-        rest_starts = struct.calcsize(packstring)
-
-        unpacked = struct.unpack(packstring, fmt_data[:rest_starts])
-
-        return WavAudioFormat(audio_format=unpacked[0],
-                              channel_count=unpacked[1],
-                              sample_rate=unpacked[2],
-                              byte_rate=unpacked[3],
-                              block_align=unpacked[4],
-                              bits_per_sample=unpacked[5]
-                              )
-
-    def _get_info(self, f, encoding):
-        finder = (chunk.signature for chunk in self.main_list \
-            if type(chunk) is ListChunkDescriptor)
-
-        if b'INFO' in finder:
-            return WavInfoChunkReader(f, encoding)
-
-    def _get_bext(self, f, encoding):
-        bext_data = self._find_chunk_data(b'bext', f, default_none=True)
-        return WavBextReader(bext_data, encoding) if bext_data else None
-
-    def _get_adm(self, f):
-        axml = self._find_chunk_data(b'axml', f, default_none=True)
-        chna = self._find_chunk_data(b'chna', f, default_none=True)
-        return WavADMReader(axml_data=axml, chna_data=chna) \
-            if axml and chna else None
-
-    def _get_dbmd(self, f):
-        dbmd_data = self._find_chunk_data(b'dbmd', f, default_none=True)
-        return WavDolbyMetadataReader(dbmd_data=dbmd_data) \
-            if dbmd_data else None
-
-    def _get_ixml(self, f):
-        ixml_data = self._find_chunk_data(b'iXML', f, default_none=True)
-        return WavIXMLFormat(ixml_data.rstrip(b'\0')) if ixml_data else None
-
-    def _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", "cues" or "adm".
-        """
-
-        scopes = ('fmt', 'data', 'ixml', 'bext', 'info', 'adm', 'cues', 
-                 'dolby')
-
-        for scope in scopes:
-            if scope in ['fmt', 'data']:
-                attr = self.__getattribute__(scope)
-                for field in attr._fields:
-                    yield scope, field, attr.__getattribute__(field)
-
-            else:
-                dict = self.__getattribute__(scope).to_dict() if self.__getattribute__(scope) else {}
-                for key in dict.keys():
-                    yield scope, key, dict[key]
-        
-    def __repr__(self):
-        return 'WavInfoReader({}, {}, {})'.format(self.path, self.info_encoding, self.bext_encoding)

wavinfo/wavfind.py

@@ -1,34 +0,0 @@
-"""
-
-"""
-
-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()