README update and stubbed out docs.

Change build system to Poetry

.flake8

@@ -0,0 +1,3 @@
+[flake8]
+per-file-ignores = 
+  wavinfo/__init__.py: F401

.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-flake8.yml

@@ -0,0 +1,40 @@
+# 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: Flake8
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11"]
+
+    steps:
+    - uses: actions/checkout@v2.5.0
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4.3.0
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8
+        python -m pip install -e .
+    - 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: Lint with flake8
+      run: |
+        flake8 wavinfo

.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:
@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12", "3.13"]
 
     steps:
     - uses: actions/checkout@v2.5.0
@@ -27,16 +27,10 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install flake8 pytest
+        python -m pip install pytest
         python -m pip install -e .
     - name: Setup FFmpeg
       uses: FedericoCarboni/setup-ffmpeg@v2
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
     - name: Test with pytest
       run: |
         pytest

.gitignore

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

README.md

@@ -1,34 +1,45 @@
-[![Documentation Status](https://readthedocs.org/projects/wavinfo/badge/?version=latest)](https://wavinfo.readthedocs.io/en/latest/?badge=latest) ![](https://img.shields.io/github/license/iluvcapra/wavinfo.svg) ![](https://img.shields.io/pypi/pyversions/wavinfo.svg) [![](https://img.shields.io/pypi/v/wavinfo.svg)](https://pypi.org/project/wavinfo/) ![](https://img.shields.io/pypi/wheel/wavinfo.svg)
-[![Lint and Test](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml/badge.svg)](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml)
+![](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)
+![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)
+
+[![Tests](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml/badge.svg)](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml)
+[![Flake8](https://github.com/iluvcapra/wavinfo/actions/workflows/python-flake8.yml/badge.svg)](https://github.com/iluvcapra/wavinfo/actions/workflows/python-flake8.yml)
 [![codecov](https://codecov.io/gh/iluvcapra/wavinfo/branch/master/graph/badge.svg?token=9DZQfZENYv)](https://codecov.io/gh/iluvcapra/wavinfo)
 
 # wavinfo
 
 The `wavinfo` package allows you to probe WAVE and [RF64/WAVE files][eburf64] 
-and extract extended metadata, with an emphasis on film, video and 
-professional music production.
+and extract extended metadata. `wavinfo` has an emphasis on film, video and 
+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.
-* The __wav format__ is also parsed, so you can access the basic sample rate 
+* Wave embedded [sampler][smpl] and sample loop metadata.
+* 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 +69,12 @@ 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/conf.py

@@ -12,24 +12,25 @@
 # 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
+import importlib
 
 # -- Project information -----------------------------------------------------
 
 project = u'wavinfo'
-copyright = u'2018-2023, Jamie Hardt'
+copyright = u'2018-2024, Jamie Hardt'
 author = u'Jamie Hardt'
 
 # The short X.Y version
-version = wavinfo.__short_version__
+version = "3.1"
 # The full version, including alpha/beta/rc tags
-release = wavinfo.__version__
+release = importlib.metadata.version("wavinfo")
 
 
 # -- General 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

@@ -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",
@@ -304,7 +305,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.12.5"
   }
  },
  "nbformat": 4,

pyproject.toml

@@ -1,13 +1,16 @@
-[build-system]
-requires = ["flit_core >=3.2,<4"]
-build-backend = "flit_core.buildapi"
+# https://python-poetry.org/docs/pyproject/
 
-[project]
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry]
 name = "wavinfo"
-authors = [{name = "Jamie Hardt", email = "jamiehardt@me.com"}]
+version = "3.1.0"
+description = "Probe WAVE files for all metadata"
+authors = ["Jamie Hardt <jamiehardt@me.com>"]
+license = "MIT" 
 readme = "README.md"
-dynamic = ["version", "description"]
-requires-python = "~=3.8"
 classifiers = [
     'Development Status :: 5 - Production/Stable',
     'License :: OSI Approved :: MIT License',
@@ -17,11 +20,13 @@ classifiers = [
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12"
-]
-dependencies = [
-    "lxml ~= 4.9.2"
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13"
 ]
+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', 
@@ -34,29 +39,17 @@ keywords = [
     'broadcast' 
 ]
 
-[tool.flit.module]
-name = "wavinfo"
+[tool.poetry.extras]
+doc = ['sphinx', 'sphinx_rtd_theme']
 
-[project.optional-dependencies]
-doc = [
-    'sphinx >= 5.3.0',
-    'sphinx_rtd_theme >= 1.1.1',
-]
-
-[project.urls]
-Home = "https://github.com/iluvcapra/wavinfo"
-Documentation = "https://wavinfo.readthedocs.io/"
-Source = "https://github.com/iluvcapra/wavinfo.git"
-Issues = 'https://github.com/iluvcapra/wavinfo/issues' 
-
-[project.entry_points.console_scripts]
+[tool.poetry.scripts]
 wavinfo = 'wavinfo.__main__:main'
 
-[project.scripts]
-wavinfo = "wavinfo.__main__:main"
-
-[tool.flit.external-data]
-directory = "data"
+[tool.poetry.dependencies]
+python = "^3.8"
+lxml = "~= 5.3.0"
+sphinx_rtd_theme = {version= '>= 1.1.1', optional=true}
+sphinx = {version= '>= 5.3.0', optional=true}
 
 [tool.pyright]
 typeCheckingMode = "basic"

tests/test_adm.py

@@ -15,17 +15,20 @@ 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())
@@ -37,7 +40,7 @@ class TestADMWave(TestCase):
     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())
         self.assertEqual("RoomCentricLeft", t1["channel_format_name"])

tests/test_cue.py

@@ -12,6 +12,7 @@ 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)])
 

tests/test_dolby.py

@@ -1,7 +1,7 @@
 from unittest import TestCase
 
 import wavinfo
-from wavinfo.wave_dbmd_reader import SegmentType, DolbyAtmosMetadata, DolbyDigitalPlusMetadata
+from wavinfo.wave_dbmd_reader import SegmentType, DolbyDigitalPlusMetadata
 
 class TestDolby(TestCase):
     def setUp(self):
@@ -19,8 +19,10 @@ class TestDolby(TestCase):
         d = t1.dolby
         assert d is not None
 
-        ddp = [x for x in d.segment_list if x[0] == SegmentType.DolbyDigitalPlus]
-        atmos = [x for x in d.segment_list if x[0] == SegmentType.DolbyAtmos]
+        ddp = [x for x in d.segment_list \
+                if x[0] == SegmentType.DolbyDigitalPlus]
+        atmos = [x for x in d.segment_list \
+                if x[0] == SegmentType.DolbyAtmos]
 
         self.assertEqual(len(ddp), 1)
         self.assertEqual(len(atmos), 1)
@@ -38,8 +40,13 @@ 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.assertTrue( ddp[0].audio_coding_mode, DolbyDigitalPlusMetadata.AudioCodingMode.CH_ORD_3_2 )
+        self.assertEqual(len(ddp), 1, 
+                         ("Failed to find exactly one Dolby Digital Plus " 
+                          "metadata segment")
+                         )
+
+        self.assertTrue( ddp[0].audio_coding_mode, 
+                        DolbyDigitalPlusMetadata.AudioCodingMode.CH_ORD_3_2 )
         self.assertTrue( ddp[0].lfe_on)
         
     def test_atmos(self):
@@ -47,6 +54,7 @@ class TestDolby(TestCase):
         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

@@ -26,7 +26,8 @@ class MainTest(unittest.TestCase):
 
     def test_ixml(self):
         with patch.object(sys, 'argv', 
-                          ['TEST', '--ixml', 'tests/test_files/sounddevices/A101_1.WAV']):
+                          ['TEST', '--ixml', 
+                           'tests/test_files/sounddevices/A101_1.WAV']):
             try:
                 main()
             except:

tests/test_smpl.py

@@ -0,0 +1,15 @@
+from unittest import TestCase
+from glob import glob
+
+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_wave_parsing.py

@@ -13,7 +13,9 @@ 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__(), 
+                             'WavInfoReader({}, latin_1, ascii)'
+                             .format(os.path.abspath(wav_file)))
             self.assertIsNotNone(info)
 
     def test_fmt_against_ffprobe(self):
@@ -24,14 +26,21 @@ 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(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']))
+            self.assertEqual(info.fmt.channel_count, 
+                             ffprobe_info['streams'][0]['channels'])
+            self.assertEqual(info.fmt.sample_rate, 
+                             int(ffprobe_info['streams'][0]['sample_rate']))
+            self.assertEqual(info.fmt.bits_per_sample, 
+                             int(ffprobe_info['streams'][0]['bits_per_sample']
+                                 ))
 
             if info.fmt.audio_format == 1:
-                self.assertTrue(ffprobe_info['streams'][0]['codec_name'].startswith('pcm'))
+                self.assertTrue(ffprobe_info['streams'][0]['codec_name']\
+                        .startswith('pcm'))
                 streams = ffprobe_info['streams'][0]
-                byte_rate = int(streams['sample_rate']) * streams['channels'] * int(streams['bits_per_sample']) / 8
+                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):
@@ -40,7 +49,8 @@ class TestWaveInfo(TestCase):
             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():
@@ -50,39 +60,63 @@ class TestWaveInfo(TestCase):
 
             if info.bext:
                 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, '')
 
                 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, '')
 
                 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, '')
 
                 # these don't always reflect the bext info
-                # self.assertEqual(info.bext.originator_date, ffprobe_info['format']['tags']['date'])
-                # self.assertEqual(info.bext.originator_time, ffprobe_info['format']['tags']['creation_time'])
-                self.assertEqual(info.bext.time_reference, int(ffprobe_info['format']['tags']['time_reference']))
+                # self.assertEqual(info.bext.originator_date, 
+                # ffprobe_info['format']['tags']['date'])
+                # self.assertEqual(info.bext.originator_time, 
+                # ffprobe_info['format']['tags']['creation_time'])
+                self.assertEqual(info.bext.time_reference, 
+                                 int(ffprobe_info['format']['tags']\
+                                         ['time_reference']))
 
                 if 'coding_history' in ffprobe_info['format']['tags']:
-                    self.assertEqual(info.bext.coding_history, ffprobe_info['format']['tags']['coding_history'])
+                    self.assertEqual(info.bext.coding_history, 
+                                     ffprobe_info['format']['tags']\
+                                             ['coding_history'])
                 else:
                     self.assertEqual(info.bext.coding_history, '')
 
     def test_ixml(self):
-        expected = {'A101_4.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '4',
-                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124015008231000'},
-                    'A101_3.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '3',
-                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124014008228300'},
-                    'A101_2.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '2',
-                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124004008218600'},
-                    'A101_1.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '1',
-                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124001008206300'},
+        expected = {'A101_4.WAV': {'project': 'BMH', 
+                                   'scene': 'A101', 'take': '4',
+                                   'tape': '18Y12M31', 
+                                   'family_uid': 
+                                   'USSDVGR1112089007124015008231000'},
+                    'A101_3.WAV': {'project': 'BMH', 
+                                   'scene': 'A101', 'take': '3',
+                                   'tape': '18Y12M31', 
+                                   'family_uid': 
+                                   'USSDVGR1112089007124014008228300'},
+                    'A101_2.WAV': {'project': 'BMH', 
+                                   'scene': 'A101', 'take': '2',
+                                   'tape': '18Y12M31', 
+                                   'family_uid':        
+                                   'USSDVGR1112089007124004008218600'},
+                    'A101_1.WAV': {'project': 'BMH', 
+                                   'scene': 'A101', 'take': '1',
+                                   'tape': '18Y12M31', 
+                                   'family_uid': 
+                                   'USSDVGR1112089007124001008206300'},
                     }
 
         for wav_file in all_files():
@@ -112,7 +146,8 @@ 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)
 
@@ -124,7 +159,8 @@ 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
 
@@ -138,7 +174,8 @@ class TestWaveInfo(TestCase):
         self.assertEqual(info.software, 'Sound Grinder Pro')
         self.assertEqual(info.created_date, '2010-12-28')
         self.assertEqual(info.engineer, 'JPH')
-        self.assertEqual(info.keywords, 'Sound Effect, movement, microphone, bump')
+        self.assertEqual(info.keywords,
+                         'Sound Effect, movement, microphone, bump')
         self.assertEqual(info.title, 'camera bumb 1')
         self.assertEqual(type(info.to_dict()), dict)
         self.assertEqual(type(info.__repr__()), str)

tests/utils.py

@@ -8,7 +8,8 @@ FFPROBE = 'ffprobe'
 
 
 def ffprobe(path):
-    arguments = [FFPROBE, "-of", "json", "-show_format", "-show_streams", path]
+    arguments = [FFPROBE, "-of", "json", 
+                 "-show_format", "-show_streams", path]
     if int(sys.version[0]) <  3:
         process = subprocess.Popen(arguments, stdout=PIPE)
         process.wait()
@@ -20,7 +21,8 @@ def ffprobe(path):
         else:
             return None
     else: 
-        process = subprocess.run(arguments, stdin=None, stdout=PIPE, stderr=PIPE)
+        process = subprocess.run(arguments, stdin=None, 
+                                 stdout=PIPE, stderr=PIPE)
         if process.returncode == 0:
             output_str = process.stdout.decode('utf-8')
             return json.loads(output_str)

wavinfo/__init__.py

@@ -4,6 +4,3 @@ Probe WAVE Files for iXML, Broadcast-WAVE and other metadata.
 
 from .wave_reader import WavInfoReader
 from .riff_parser import WavInfoEOFError
-
-__version__ = '2.3.0'
-__short_version__ = '2.3.0'

wavinfo/__main__.py

@@ -1,37 +1,77 @@
-from optparse import OptionParser, OptionGroup
-import datetime
 from . import WavInfoReader
-from . import __version__
+
+import datetime
+from optparse import OptionParser
 import sys
+import os
 import json
 from enum import Enum
+import importlib.metadata
+from base64 import b64encode
+
 
 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
 
+
 def main():
+    version = importlib.metadata.version('wavinfo')
+    manpath = os.path.dirname(__file__) + "/man"
     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('--install-manpages',
+    #                   help="Install manual pages for wavinfo",
+    #                   default=False,
+    #                   action='store_true')
 
-    parser.add_option('--adm', dest='adm', help='Output ADM XML', 
-        default=False, action='store_true')
+    parser.add_option('--man',
+                      help="Read the manual and exit.",
+                      default=False,
+                      action='store_true')
 
-    parser.add_option('--ixml', dest='ixml', help='Output iXML',
-        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')
 
     (options, args) = parser.parse_args(sys.argv)
+
+    # 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)
@@ -47,11 +87,11 @@ def main():
                     raise MissingDataError("ixml")
             else:
                 ret_dict = {
-                    'filename': arg, 
-                    'run_date': datetime.datetime.now().isoformat() , 
-                    'application': "wavinfo " + __version__, 
+                    'filename': arg,
+                    'run_date': datetime.datetime.now().isoformat(),
+                    'application': f"wavinfo {version}",
                     'scopes': {}
-                    }
+                }
                 for scope, name, value in this_file.walk():
                     if scope not in ret_dict['scopes'].keys():
                         ret_dict['scopes'][scope] = {}
@@ -60,7 +100,8 @@ def main():
 
                 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)
+            print("MissingDataError: Missing metadata (%s) in file %s" %
+                  (e, arg), file=sys.stderr)
             continue
         except Exception as e:
             raise e

wavinfo/man/man1/wavinfo.1

@@ -17,7 +17,7 @@ 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 

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.

wavinfo/rf64_parser.py

@@ -1,14 +1,18 @@
 import struct
-from collections import namedtuple
+# from collections import namedtuple
+from typing import NamedTuple, Dict
 
 from . import riff_parser
 
-RF64Context = namedtuple('RF64Context','sample_count bigchunk_table')
+
+class RF64Context(NamedTuple):
+    sample_count: int
+    bigchunk_table: Dict[str, int]
 
 
-def parse_rf64(stream, signature = b'RF64') -> RF64Context:
+def parse_rf64(stream, signature=b'RF64') -> RF64Context:
     start = stream.tell()
-    assert( stream.read(4) == b'WAVE' )
+    assert stream.read(4) == b'WAVE'
 
     ds64_chunk = riff_parser.parse_chunk(stream)
     assert type(ds64_chunk) is riff_parser.ChunkDescriptor, \
@@ -16,27 +20,28 @@ def parse_rf64(stream, signature = b'RF64') -> RF64Context:
 
     ds64_field_spec = "<QQQI"
     ds64_fields_size = struct.calcsize(ds64_field_spec)
-    assert(ds64_chunk.ident == b'ds64')
+    assert ds64_chunk.ident == b'ds64'
 
     ds64_data = ds64_chunk.read_data(stream)
-    assert(len(ds64_data) >= ds64_fields_size)
+    assert len(ds64_data) >= ds64_fields_size
 
     riff_size, data_size, sample_count, length_lookup_table = struct.unpack(
-        ds64_field_spec, ds64_data[0:ds64_fields_size])
+        ds64_field_spec, ds64_data[0:ds64_fields_size]
+        )
 
     bigchunk_table = {}
     chunksize64format = "<4sL"
     # chunksize64size = struct.calcsize(chunksize64format)
 
     for _ in range(length_lookup_table):
-        bigname, bigsize = struct.unpack_from(chunksize64format, ds64_data,
-                                              offset= ds64_fields_size)
+        bigname, bigsize = struct.unpack_from(chunksize64format,
+                                              ds64_data,
+                                              offset=ds64_fields_size)
         bigchunk_table[bigname] = bigsize
 
     bigchunk_table[b'data'] = data_size
     bigchunk_table[signature] = riff_size
 
     stream.seek(start, 0)
-    return RF64Context( sample_count=sample_count,
+    return RF64Context(sample_count=sample_count,
                        bigchunk_table=bigchunk_table)
-

wavinfo/riff_parser.py

@@ -1,7 +1,7 @@
-
+# from optparse import Option
 import struct
-from collections import namedtuple
-from .rf64_parser import parse_rf64
+from .rf64_parser import parse_rf64, RF64Context
+from typing import NamedTuple, Union, List, Optional
 
 
 class WavInfoEOFError(EOFError):
@@ -10,11 +10,17 @@ class WavInfoEOFError(EOFError):
         self.chunk_start = chunk_start
 
 
-class ListChunkDescriptor(namedtuple('ListChunkDescriptor', 'signature children')):
-    pass
+class ListChunkDescriptor(NamedTuple):
+    signature: bytes
+    children: List[Union['ChunkDescriptor', 'ListChunkDescriptor']]
 
 
-class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length rf64_context')):
+class ChunkDescriptor(NamedTuple):
+    ident: bytes
+    start: int
+    length: int
+    rf64_context: Optional[RF64Context]
+
     def read_data(self, from_stream) -> bytes:
         from_stream.seek(self.start)
         return from_stream.read(self.length)
@@ -49,8 +55,8 @@ def parse_chunk(stream, rf64_context=None):
             rf64_context = parse_rf64(stream=stream, signature=ident)
 
         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]
 
     displacement = data_size
@@ -64,5 +70,7 @@ def parse_chunk(stream, rf64_context=None):
     else:
         data_start = stream.tell()
         stream.seek(displacement, 1)
-        return ChunkDescriptor(ident=ident, start=data_start, length=data_size,
+        return ChunkDescriptor(ident=ident,
+                               start=data_start,
+                               length=data_size,
                                rf64_context=rf64_context)

wavinfo/umid_parser.py

@@ -2,8 +2,8 @@
 
 
 # def binary_to_string(binary_value):
-#     return reduce(lambda val, el: val + "{:02x}".format(el), binary_value, '')
-
+#     return reduce(lambda val, el: val + "{:02x}".format(el),
+#                   binary_value, '')
 
 # class UMIDParser:
 #     """
@@ -13,109 +13,109 @@
 #     """
 #     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]
+#
+# @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
+# 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

@@ -5,12 +5,14 @@ ADM Reader
 from struct import unpack, unpack_from, calcsize
 from io import BytesIO
 from collections import namedtuple
-from typing import Iterable, Tuple
+from typing import Optional
 
 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.
@@ -26,24 +28,24 @@ class WavADMReader:
 
         _, 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)
+            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')))
+            self.channel_uids.append(
+                ChannelEntry(track_index - 1,
+                             uid.decode('ascii'),
+                             track_ref.decode('ascii'),
+                             pack_ref.decode('ascii')
+                             )
+            )
 
             offset += calcsize(uid_fmt)
 
@@ -53,12 +55,13 @@ class WavADMReader:
 
     def programme(self) -> dict:
         """
-        Read the ADM `audioProgramme` data structure and some of its reference properties. 
+        Read the ADM `audioProgramme` data structure and some of its reference
+        properties.
         """
         ret_dict = dict()
 
-        nsmap = self.axml.getroot().nsmap 
-        
+        nsmap = self.axml.getroot().nsmap
+
         afext = self.axml.find(".//audioFormatExtended", namespaces=nsmap)
 
         program = afext.find("audioProgramme", namespaces=nsmap)
@@ -68,17 +71,21 @@ class WavADMReader:
         ret_dict['programme_end'] = program.get("end")
         ret_dict['contents'] = []
 
-        for content_ref in program.findall("audioContentIDRef", namespaces=nsmap):
+        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 = 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):
+            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)
+                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")
@@ -95,16 +102,18 @@ class WavADMReader:
 
         return ret_dict
 
-    def track_info(self, index) -> dict:
+    def track_info(self, index) -> Optional[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*, 
+        :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)
-        
+        channel_info = next((x for x in self.channel_uids
+                             if x.track_index == index), None)
+
         if channel_info is None:
             return None
 
@@ -112,46 +121,60 @@ class WavADMReader:
 
         nsmap = self.axml.getroot().nsmap
 
-        afext = self.axml.find(".//audioFormatExtended", namespaces=nsmap)
+        afext = self.axml.find(".//audioFormatExtended",
+                               namespaces=nsmap)
 
-        trackformat_elem = afext.find("audioTrackFormat[@audioTrackFormatID='%s']" % channel_info.track_ref, 
-            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, 
+        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, 
+        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")
+        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, 
+        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")
+        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)
+        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)
+        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"
+    def to_dict(self) -> dict:  # FIXME should be "asdict"
         """
         Get ADM metadata as a dictionary.
         """
@@ -161,5 +184,6 @@ class WavADMReader:
             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())
+        return dict(channel_entries=list(map(lambda z: make_entry(z),
+                                             self.channel_uids)),
+                    programme=self.programme())

wavinfo/wave_bext_reader.py

@@ -3,71 +3,75 @@ import struct
 
 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.
+        :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"
+        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:
+        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)
+            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])
-            
+        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])
-            
+        self.originator: str = sanitize_bytes(unpacked[1])
+
         #: A unique identifier for the file, a serial number.
-        self.originator_ref : str = sanitize_bytes(unpacked[2])
-            
+        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])
-            
+        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]
-            
+        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
-            
+        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
-            
+        self.loudness_value: Optional[float] = None
+
         #: EBU R128 Loudness range, in LUFS.
-        self.loudness_range : Optional[float] = None
-            
+        self.loudness_range: Optional[float] = None
+
         #: True peak level, in dBFS TP
-        self.max_true_peak : Optional[float] = None
-            
+        self.max_true_peak: Optional[float] = None
+
         #: EBU R128 Maximum momentary loudness, in LUFS
-        self.max_momentary_loudness : Optional[float] = None
-            
+        self.max_momentary_loudness: Optional[float] = None
+
         #: EBU R128 Maximum short-term loudness, in LUFS.
-        self.max_shortterm_loudness : Optional[float] = None
+        self.max_shortterm_loudness: Optional[float] = None
 
         if self.version > 0:
             self.umid = unpacked[7]
@@ -84,7 +88,7 @@ class WavBextReader:
         #     umid_parsed = UMIDParser(self.umid)
         #     umid_str = umid_parsed.basic_umid_to_str()
         # else:
-            
+
         umid_str = None
 
         return {'description': self.description,

wavinfo/wave_cues_reader.py

@@ -1,26 +1,25 @@
 """
 Cues metadata
 
-For reference on implementation of cues and related metadata see: 
+For reference on implementation of cues and related metadata see:
 August 1991, "Multimedia Programming Interface and Data Specifications 1.0",
 IBM Corporation and Microsoft Corporation
 
 https://www.aelius.com/njh/wavemetatools/doc/riffmci.pdf
 """
 from dataclasses import dataclass
-import encodings
 from .riff_parser import ChunkDescriptor
 
 from struct import unpack, calcsize
 from typing import Optional, Tuple,  NamedTuple, List, Dict, Any, Generator
 
-#: Country Codes used in the RIFF standard to resolve locale. These codes 
+#: Country Codes used in the RIFF standard to resolve locale. These codes
 #: appear in CSET and LTXT metadata.
 CountryCodes = """000 None Indicated
 001,USA
 002,Canada
 003,Latin America
-030,Greece 
+030,Greece
 031,Netherlands
 032,Belgium
 033,France
@@ -44,50 +43,50 @@ CountryCodes = """000 None Indicated
 090,Turkey
 351,Portugal
 352,Luxembourg
-354,Iceland 
+354,Iceland
 358,Finland"""
 
-#: Language and Dialect codes used in the RIFF standard to resolve native 
+#: Language and Dialect codes used in the RIFF standard to resolve native
 #: language of text fields. These codes appear in CSET and LTXT metadata.
 LanguageDialectCodes = """0 0 None Indicated
 1,1,Arabic
 2,1,Bulgarian
 3,1,Catalan
-4,1,Traditional Chinese 
-4,2,Simplified Chinese 
+4,1,Traditional Chinese
+4,2,Simplified Chinese
 5,1,Czech
 6,1,Danish
 7,1,German
-7,2,Swiss German 
+7,2,Swiss German
 8,1,Greek
 9,1,US English
-9,2,UK English 
+9,2,UK English
 10,1,Spanish
-10,2,Spanish Mexican 
+10,2,Spanish Mexican
 11,1,Finnish
 12,1,French
-12,2,Belgian French 
-12,3,Canadian French 
-12,4,Swiss French 
-13,1,Hebrew 
+12,2,Belgian French
+12,3,Canadian French
+12,4,Swiss French
+13,1,Hebrew
 14,1,Hungarian
 15,1,Icelandic
 16,1,Italian
-16,2,Swiss Italian 
+16,2,Swiss Italian
 17,1,Japanese
 18,1,Korean
 19,1,Dutch
-19,2,Belgian Dutch 
-20,1,Norwegian - Bokmal 
-20,2,Norwegian - Nynorsk 
+19,2,Belgian Dutch
+20,1,Norwegian - Bokmal
+20,2,Norwegian - Nynorsk
 21,1,Polish
-22,1,Brazilian Portuguese 
-22,2,Portuguese 
-23,1,Rhaeto-Romanic 
+22,1,Brazilian Portuguese
+22,2,Portuguese
+23,1,Rhaeto-Romanic
 24,1,Romanian
 25,1,Russian
-26,1,Serbo-Croatian (Latin) 
-26,2,Serbo-Croatian (Cyrillic) 
+26,1,Serbo-Croatian (Latin)
+26,2,Serbo-Croatian (Cyrillic)
 27,1,Slovak
 28,1,Albanian
 29,1,Swedish
@@ -98,7 +97,14 @@ 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
@@ -106,7 +112,7 @@ class CueEntry(NamedTuple):
     sample_offset: int
 
     Format = "<II4sIII"
-    
+
     @classmethod
     def format_size(cls) -> int:
         return calcsize(cls.Format)
@@ -114,16 +120,20 @@ class CueEntry(NamedTuple):
     @classmethod
     def read(cls, data: bytes) -> 'CueEntry':
         assert len(data) == cls.format_size(), \
-            f"cue data size incorrect, expected {calcsize(cls.Format)} found {len(data)}"
+            (f"cue data size incorrect, expected {calcsize(cls.Format)} "
+             "found {len(data)}")
 
         parsed = unpack(cls.Format, data)
 
         return cls(name=parsed[0], position=parsed[1], chunk_id=parsed[2],
-                   chunk_start=parsed[3], block_start=parsed[4], 
+                   chunk_start=parsed[3], block_start=parsed[4],
                    sample_offset=parsed[5])
 
 
 class LabelEntry(NamedTuple):
+    """
+    A ``labl`` structure.
+    """
     name: int
     text: str
 
@@ -137,6 +147,9 @@ NoteEntry = LabelEntry
 
 
 class RangeLabel(NamedTuple):
+    """
+    A ``ltxt`` structure.
+    """
     name: int
     length: int
     purpose: str
@@ -156,33 +169,41 @@ class RangeLabel(NamedTuple):
             fallback_encoding = f"cp{data[6]}"
 
         return cls(name=parsed[0], length=parsed[1], purpose=parsed[2],
-                   country=parsed[3], language=parsed[4], 
-                   dialect=parsed[5], codepage=parsed[6], 
+                   country=parsed[3], language=parsed[4],
+                   dialect=parsed[5], codepage=parsed[6],
                    text=text_data.decode(fallback_encoding))
 
 
 @dataclass
 class WavCuesReader:
+
+    #: Every ``cue`` entry in the file
     cues: List[CueEntry]
+
+    #: 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,
-              cues: Optional[ChunkDescriptor], 
-              labls: List[ChunkDescriptor],
-              ltxts: List[ChunkDescriptor], 
-              notes: List[ChunkDescriptor],
-              fallback_encoding: str) -> 'WavCuesReader':
-        
+                 cues: Optional[ChunkDescriptor],
+                 labls: List[ChunkDescriptor],
+                 ltxts: List[ChunkDescriptor],
+                 notes: List[ChunkDescriptor],
+                 fallback_encoding: str) -> 'WavCuesReader':
+
         cue_list = []
         if cues is not None:
             cues_data = cues.read_data(f)
             assert len(cues_data) >= 4, "cue metadata too short"
             offset = calcsize("<I")
             cues_count = unpack("<I", cues_data[0:offset])
-            
+
             for _ in range(cues_count[0]):
                 cue_bytes = cues_data[offset: offset + CueEntry.format_size()]
                 cue_list.append(CueEntry.read(cue_bytes))
@@ -191,14 +212,14 @@ class WavCuesReader:
         label_list = []
         for labl in labls:
             label_list.append(
-                LabelEntry.read(labl.read_data(f), 
+                LabelEntry.read(labl.read_data(f),
                                 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)
             )
 
@@ -214,7 +235,7 @@ class WavCuesReader:
 
     def each_cue(self) -> Generator[Tuple[int, int], None, None]:
         """
-        Iterate through each cue. 
+        Iterate through each cue.
 
         :yields: the cue's ``name`` and ``sample_offset``
         """
@@ -222,17 +243,17 @@ class WavCuesReader:
             yield (cue.name, cue.sample_offset)
 
     def label_and_note(self, cue_ident: int) -> Tuple[Optional[str],
-                                                      Optional[str]]: 
+                                                      Optional[str]]:
         """
         Get the label and note (extended comment) for a cue.
 
         :param cue_ident: the cue's name, its unique identifying number
         :returns: a tuple of the the cue's label (if present) and note (if
-            present) 
+            present)
         """
-        label = next((l.text for l in self.labels 
-                      if l.name == cue_ident), None)
-        note = next((n.text for n in self.notes 
+        label = next((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)
         return (label, note)
 
@@ -243,7 +264,7 @@ class WavCuesReader:
         :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)
 
     def to_dict(self) -> Dict[str, Any]:
@@ -258,15 +279,8 @@ class WavCuesReader:
             if label is not None:
                 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 
-        
-        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])
-
-
+                retval[n]['length'] = r
 
+        return retval

wavinfo/wave_dbmd_reader.py

@@ -1,7 +1,7 @@
 """
 Reading Dolby Bitstream Metadata
 
-Unless otherwise stated, all § references here are to 
+Unless otherwise stated, all § references here are to
 `EBU Tech 3285 Supplement 6`_.
 
 .. _EBU Tech 3285 Supplement 6: https://tech.ebu.ch/docs/tech/tech3285s6.pdf
@@ -10,10 +10,11 @@ Unless otherwise stated, all § references here are to
 from enum import IntEnum, Enum
 from struct import unpack
 from dataclasses import dataclass, asdict
-from typing import List, Optional, Tuple, Any, Union
+from typing import List, Tuple, Any, Union
 
 from io import BytesIO
 
+
 class SegmentType(IntEnum):
     """
     Metadata segment type.
@@ -31,7 +32,7 @@ class SegmentType(IntEnum):
     DolbyAtmosSupplemental = 0xa
 
     @classmethod
-    def _missing_(cls,val):
+    def _missing_(cls, val):
         return val
 
 
@@ -39,11 +40,11 @@ class SegmentType(IntEnum):
 class DolbyDigitalPlusMetadata:
     """
     *Dolby Digital Plus* is Dolby's brand for multichannel surround
-    on discrete formats that aren't AC-3 (Dolby Digital) or Dolby E. This 
-    metadata segment is present in ADM wave files created with a Dolby Atmos 
+    on discrete formats that aren't AC-3 (Dolby Digital) or Dolby E. This
+    metadata segment is present in ADM wave files created with a Dolby Atmos
     Production Suite.
 
-    Where an AC-3 bitstream can contain multiple programs, a Dolby Digital 
+    Where an AC-3 bitstream can contain multiple programs, a Dolby Digital
     Plus bitstream will only contain one program.
     """
 
@@ -77,7 +78,6 @@ class DolbyDigitalPlusMetadata:
         MUTE = 0b111
         "-∞ dB"
 
-
     class DolbySurroundEncodingMode(Enum):
         """
         Dolby surround endcoding mode.
@@ -87,7 +87,6 @@ class DolbyDigitalPlusMetadata:
         NOT_IN_USE = 0b01
         NOT_INDICATED = 0b00
 
-
     class BitStreamMode(Enum):
         """
         Dolby Digital Plus `bsmod` field
@@ -122,7 +121,6 @@ class DolbyDigitalPlusMetadata:
         should be interpreted as karaoke.
         """
 
-
     class AudioCodingMode(Enum):
         """
         Dolby Digital Plus `acmod` field
@@ -144,7 +142,6 @@ class DolbyDigitalPlusMetadata:
         CH_ORD_3_2 = 0b111
         "LCR + LR surround"
 
-
     class CenterDownMixLevel(Enum):
         """
         § 4.3.3.1
@@ -152,16 +149,15 @@ class DolbyDigitalPlusMetadata:
 
         DOWN_3DB = 0b00
         "Attenuate 3 dB"
-    
+
         DOWN_45DB = 0b01
         "Attenuate 4.5 dB"
-        
+
         DOWN_6DB = 0b10
         "Attenuate 6 dB"
 
         RESERVED = 0b11
 
-
     class SurroundDownMixLevel(Enum):
         """
         Dolby Digital Plus `surmixlev` field
@@ -172,7 +168,6 @@ class DolbyDigitalPlusMetadata:
         MUTE = 0b10
         RESERVED = 0b11
 
-
     class LanguageCode(int):
         """
         § 4.3.4.1
@@ -181,21 +176,18 @@ class DolbyDigitalPlusMetadata:
         """
         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
@@ -205,11 +197,10 @@ class DolbyDigitalPlusMetadata:
         SMALL_ROOM_FLAT_CURVE = 0b10
         RESERVED = 0b11
 
-
     class PreferredDownMixMode(Enum):
         """
-        Indicates the creating engineer's preference of what the receiver should
-        downmix.
+        Indicates the creating engineer's preference of what the receiver
+        should downmix.
         § 4.3.8.1
         """
         NOT_INDICATED = 0b00
@@ -217,7 +208,6 @@ class DolbyDigitalPlusMetadata:
         STEREO = 0b10
         PRO_LOGIC_2 = 0b11
 
-
     class SurroundEXMode(IntEnum):
         """
         Dolby Surround-EX mode.
@@ -228,7 +218,6 @@ class DolbyDigitalPlusMetadata:
         SEX = 0b10
         PRO_LOGIC_2 = 0b11
 
-
     class HeadphoneMode(IntEnum):
         """
         `dheadphonmod` § 4.3.9.2
@@ -238,12 +227,10 @@ class DolbyDigitalPlusMetadata:
         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
@@ -254,7 +241,6 @@ class DolbyDigitalPlusMetadata:
         INDEPENDENT_FROM_DOLBY_DIGITAL = 2
         RESERVED = 3
 
-
     class RFCompressionProfile(Enum):
         """
         `compr1` RF compression profile
@@ -267,7 +253,7 @@ class DolbyDigitalPlusMetadata:
         MUSIC_LIGHT = 4
         SPEECH = 5
 
-    #: Program ID number, this identifies the program in a multi-program 
+    #: Program ID number, this identifies the program in a multi-program
     #: element. § 4.3.1
     program_id: int
 
@@ -317,13 +303,13 @@ class DolbyDigitalPlusMetadata:
 
     #: LoRo preferred center downmix level
     loro_center_downmix_level: DownMixLevelToken
-    
+
     #: LoRo preferred surround downmix level
     loro_surround_downmix_level: DownMixLevelToken
 
     #: Preferred downmix mode
     downmix_mode: PreferredDownMixMode
-    
+
     #: LtRt preferred center downmix level
     ltrt_center_downmix_level: DownMixLevelToken
 
@@ -332,20 +318,20 @@ class DolbyDigitalPlusMetadata:
 
     #: Surround-EX mode
     surround_ex_mode: SurroundEXMode
-    
+
     #: Dolby Headphone mode
     dolby_headphone_encoded: HeadphoneMode
 
     ad_converter_type: ADConverterType
     compression_profile: RFCompressionProfile
     dynamic_range: RFCompressionProfile
-    
+
     #: Indicates if this stream can be decoded independently or not
     stream_dependency: StreamDependency
 
     #: Data rate of this bitstream in kilobits per second
     datarate_kbps: int
-    
+
     @staticmethod
     def load(buffer: bytes):
         assert len(buffer) == 96, "Dolby Digital Plus segment incorrect size, "
@@ -363,12 +349,14 @@ class DolbyDigitalPlusMetadata:
             pass
 
         def surround_config(b):
-            return DolbyDigitalPlusMetadata.CenterDownMixLevel(b & 0x30 >> 4), \
-                DolbyDigitalPlusMetadata.SurroundDownMixLevel(b & 0xc >> 2), \
+            return (
+                DolbyDigitalPlusMetadata.CenterDownMixLevel(b & 0x30 >> 4),
+                DolbyDigitalPlusMetadata.SurroundDownMixLevel(b & 0xc >> 2),
                 DolbyDigitalPlusMetadata.DolbySurroundEncodingMode(b & 0x3)
+                )
 
         def dialnorm_info(b):
-            return (b & 0x80) > 0 , b & 0x40 > 0, b & 0x20 > 0, \
+            return (b & 0x80) > 0, b & 0x40 > 0, b & 0x20 > 0, \
                 DolbyDigitalPlusMetadata.DialnormLevel(b & 0x1f)
 
         def langcod(b) -> int:
@@ -379,22 +367,23 @@ class DolbyDigitalPlusMetadata:
                 DolbyDigitalPlusMetadata.MixLevel(b & 0x7c >> 2), \
                 DolbyDigitalPlusMetadata.RoomType(b & 0x3)
 
-        # loro_center_downmix_level, loro_surround_downmix_level 
+        # loro_center_downmix_level, loro_surround_downmix_level
         def ext_bsi1_word1(b):
             return DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x38 >> 3), \
                 DolbyDigitalPlusMetadata.DownMixLevelToken(b & 0x7)
 
         # downmix_mode, ltrt_center_downmix_level, ltrt_surround_downmix_level
         def ext_bsi1_word2(b):
-            return DolbyDigitalPlusMetadata.PreferredDownMixMode(b & 0xC0 >> 6), \
+            return DolbyDigitalPlusMetadata\
+                .PreferredDownMixMode(b & 0xC0 >> 6), \
                 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), \
                 DolbyDigitalPlusMetadata.HeadphoneMode(b & 0x18 >> 3), \
-                DolbyDigitalPlusMetadata.ADConverterType( b & 0x4 >> 2)
+                DolbyDigitalPlusMetadata.ADConverterType(b & 0x4 >> 2)
 
         def ddplus_reserved2(_):
             pass
@@ -403,7 +392,7 @@ class DolbyDigitalPlusMetadata:
             return DolbyDigitalPlusMetadata.RFCompressionProfile(b)
 
         def dynrng1(b):
-            DolbyDigitalPlusMetadata.RFCompressionProfile(b) 
+            DolbyDigitalPlusMetadata.RFCompressionProfile(b)
 
         def ddplus_reserved3(_):
             pass
@@ -423,14 +412,19 @@ 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])
-        langcode_present, copyright_bitstream, original_bitstream, dialnorm = dialnorm_info(buffer[5])
+        center_downmix_level, surround_downmix_level, \
+            dolby_surround_encoded = surround_config(buffer[4])
+        langcode_present, copyright_bitstream, original_bitstream, \
+            dialnorm = dialnorm_info(buffer[5])
         langcode = langcod(buffer[6])
         prod_info_exists, mixlevel, roomtype = audio_prod_info(buffer[7])
 
-        loro_center_downmix_level, loro_surround_downmix_level = ext_bsi1_word1(buffer[8])
-        downmix_mode, ltrt_center_downmix_level, ltrt_surround_downmix_level = ext_bsi1_word2(buffer[9])
-        surround_ex_mode, dolby_headphone_encoded, ad_converter_type = ext_bsi2_word1(buffer[10])
+        loro_center_downmix_level, \
+            loro_surround_downmix_level = ext_bsi1_word1(buffer[8])
+        downmix_mode, ltrt_center_downmix_level, \
+            ltrt_surround_downmix_level = ext_bsi1_word2(buffer[9])
+        surround_ex_mode, dolby_headphone_encoded, \
+            ad_converter_type = ext_bsi2_word1(buffer[10])
 
         ddplus_reserved2(buffer[11:14])
         compression = compr1(buffer[14])
@@ -441,33 +435,33 @@ class DolbyDigitalPlusMetadata:
         data_rate = datarate(buffer[25:27])
         reserved(buffer[27:69])
 
-        return DolbyDigitalPlusMetadata(program_id=pid,
-            lfe_on=lfe_on, 
-            bitstream_mode=bitstream_mode,
-            audio_coding_mode=audio_coding_mode,
-            center_downmix_level=center_downmix_level,
-            surround_downmix_level=surround_downmix_level,
-            dolby_surround_encoded=dolby_surround_encoded, 
-            langcode_present=langcode_present, 
-            copyright_bitstream=copyright_bitstream, 
-            original_bitstream=original_bitstream,
-            dialnorm=dialnorm, 
-            langcode=langcode,
-            prod_info_exists=prod_info_exists,
-            mixlevel=mixlevel,
-            roomtype=roomtype,
-            loro_center_downmix_level=loro_center_downmix_level,
-            loro_surround_downmix_level=loro_surround_downmix_level,
-            downmix_mode=downmix_mode,
-            ltrt_center_downmix_level=ltrt_center_downmix_level, 
-            ltrt_surround_downmix_level=ltrt_surround_downmix_level,
-            surround_ex_mode=surround_ex_mode,
-            dolby_headphone_encoded=dolby_headphone_encoded,
-            ad_converter_type=ad_converter_type,
-            compression_profile=compression,
-            dynamic_range=dynamic_range,
-            stream_dependency=stream_info,
-            datarate_kbps=data_rate)
+        return DolbyDigitalPlusMetadata(
+                 program_id=pid, lfe_on=lfe_on,
+                 bitstream_mode=bitstream_mode,
+                 audio_coding_mode=audio_coding_mode,
+                 center_downmix_level=center_downmix_level,
+                 surround_downmix_level=surround_downmix_level,
+                 dolby_surround_encoded=dolby_surround_encoded,
+                 langcode_present=langcode_present,
+                 copyright_bitstream=copyright_bitstream,
+                 original_bitstream=original_bitstream,
+                 dialnorm=dialnorm,
+                 langcode=langcode,
+                 prod_info_exists=prod_info_exists,
+                 mixlevel=mixlevel,
+                 roomtype=roomtype,
+                 loro_center_downmix_level=loro_center_downmix_level,
+                 loro_surround_downmix_level=loro_surround_downmix_level,
+                 downmix_mode=downmix_mode,
+                 ltrt_center_downmix_level=ltrt_center_downmix_level,
+                 ltrt_surround_downmix_level=ltrt_surround_downmix_level,
+                 surround_ex_mode=surround_ex_mode,
+                 dolby_headphone_encoded=dolby_headphone_encoded,
+                 ad_converter_type=ad_converter_type,
+                 compression_profile=compression,
+                 dynamic_range=dynamic_range,
+                 stream_dependency=stream_info,
+                 datarate_kbps=data_rate)
 
 
 @dataclass
@@ -486,7 +480,7 @@ 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
@@ -494,8 +488,10 @@ class DolbyAtmosMetadata:
 
     @classmethod
     def load(cls, data: bytes):
-        assert len(data) == cls.SEGMENT_LENGTH, "DolbyAtmosMetadata segment "\
-            "is incorrect length, expected %i actual was %i" % (cls.SEGMENT_LENGTH, len(data)) 
+
+        assert len(data) == cls.SEGMENT_LENGTH
+        # (f"DolbyAtmosMetadata segment is incorrect length, "
+        #  f"expected {cls.SEGMENT_LENGTH} actual was {len(data)}")
 
         h = BytesIO(data)
 
@@ -512,17 +508,20 @@ class DolbyAtmosMetadata:
         a_val = unpack("B", h.read(1))[0]
         warp_mode = a_val & 0x7
 
-        return DolbyAtmosMetadata(tool_name=toolname, 
-            tool_version=(major, minor, fix), warp_mode=DolbyAtmosMetadata.WarpMode(warp_mode))
+        return DolbyAtmosMetadata(tool_name=toolname,
+                                  tool_version=(major, minor, fix),
+                                  warp_mode=DolbyAtmosMetadata
+                                  .WarpMode(warp_mode))
+
 
-        
 @dataclass
 class DolbyAtmosSupplementalMetadata:
     """
     Dolby Atmos supplemental metadata segment.
 
-    https://github.com/DolbyLaboratories/dbmd-atmos-parser/blob/master/dbmd_atmos_parse/src/dbmd_atmos_parse.c
-    """ 
+    https://github.com/DolbyLaboratories/dbmd-atmos-parser/blob/
+    master/dbmd_atmos_parse/src/dbmd_atmos_parse.c
+    """
 
     class BinauralRenderMode(Enum):
         BYPASS = 0x00
@@ -531,12 +530,10 @@ class DolbyAtmosSupplementalMetadata:
         MID = 0x03
         NOT_INDICATED = 0x04
 
-
     object_count: int
     render_modes: List['DolbyAtmosSupplementalMetadata.BinauralRenderMode']
     trim_modes: List[int]
 
-
     MAGIC = 0xf8726fbd
     TRIM_CONFIG_COUNT = 9
 
@@ -552,15 +549,15 @@ 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(object_count) # skip object_count bytes
+            h.read(14)  # skip 14
+
+        h.read(object_count)  # skip object_count bytes
 
         for _ in range(object_count):
             binaural_mode = unpack("B", h.read(1))[0]
@@ -568,7 +565,8 @@ class DolbyAtmosSupplementalMetadata:
             render_modes.append(binaural_mode)
 
         return DolbyAtmosSupplementalMetadata(object_count=object_count,
-            render_modes=render_modes,trim_modes=trim_modes)
+                                              render_modes=render_modes,
+                                              trim_modes=trim_modes)
 
 
 class WavDolbyMetadataReader:
@@ -580,11 +578,11 @@ class WavDolbyMetadataReader:
     #:
     #: Each list entry is a tuple of `SegmentType`, a `bool`
     #: indicating if the segment's checksum was valid, and the
-    #: segment's parsed dataclass (or a `bytes` array if it was 
+    #: segment's parsed dataclass (or a `bytes` array if it was
     #: not recognized).
     segment_list: List[Tuple[Union[SegmentType, int], bool, Any]]
 
-    version: Tuple[int,int,int,int]
+    version: Tuple[int, int, int, int]
 
     @staticmethod
     def segment_checksum(bs: bytes, size: int):
@@ -597,7 +595,6 @@ class WavDolbyMetadataReader:
 
         return retval
 
-
     def __init__(self, dbmd_data):
         self.segment_list = []
 
@@ -606,18 +603,19 @@ 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
@@ -627,35 +625,36 @@ class WavDolbyMetadataReader:
                     segment = DolbyAtmosMetadata.load(segment)
                 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]:
         """
         Every valid Dolby Digital Plus metadata segment in the file.
         """
-        return [x[2] for x in self.segment_list \
-            if x[0] == SegmentType.DolbyDigitalPlus and x[1]]
+        return [x[2] for x in self.segment_list
+                if x[0] == SegmentType.DolbyDigitalPlus and x[1]]
 
     def dolby_atmos(self) -> List[DolbyAtmosMetadata]:
         """
         Every valid Dolby Atmos metadata segment in the file.
         """
-        return [x[2] for x in self.segment_list \
-            if x[0] == SegmentType.DolbyAtmos and x[1]]
+        return [x[2] for x in self.segment_list
+                if x[0] == SegmentType.DolbyAtmos and x[1]]
 
     def dolby_atmos_supplemental(self) -> List[DolbyAtmosSupplementalMetadata]:
         """
         Every valid Dolby Atmos Supplemental metadata segment in the file.
         """
-        return [x[2] for x in self.segment_list \
-            if x[0] == SegmentType.DolbyAtmosSupplemental and x[1]]
+        return [x[2] for x in self.segment_list
+                if x[0] == SegmentType.DolbyAtmosSupplemental and x[1]]
 
     def to_dict(self) -> dict:
 
         ddp = map(lambda x: asdict(x), self.dolby_digital_plus())
         atmos = map(lambda x: asdict(x), self.dolby_atmos())
-        #atmos_sup = map(lambda x: asdict(x), self.dolby_atmos_supplemental())
-        
+        # atmos_sup = map(lambda x: asdict(x), self.dolby_atmos_supplemental())
+
         return dict(dolby_digital_plus=list(ddp),
-             dolby_atmos=list(atmos))
+                    dolby_atmos=list(atmos))

wavinfo/wave_info_reader.py

@@ -2,6 +2,7 @@ from .riff_parser import parse_chunk, ListChunkDescriptor
 
 from typing import Optional
 
+
 class WavInfoChunkReader:
 
     def __init__(self, f, encoding):
@@ -9,47 +10,52 @@ class WavInfoChunkReader:
 
         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]
+        list_chunks = [chunk for chunk in parsed_chunks.children
+                       if type(chunk) is ListChunkDescriptor]
 
-        self.info_chunk = next((chunk for chunk in list_chunks if chunk.signature == b'INFO'), None)
+        self.info_chunk = next((chunk for chunk in list_chunks
+                                if chunk.signature == b'INFO'), None)
 
         #: 'ICOP' Copyright
-        self.copyright : Optional[str] = self._get_field(f, b'ICOP')
+        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
+        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')
+        self.genre: Optional[str] = self._get_field(f, b'IGNR')
         #: 'ISBJ' Subject
-        self.subject : Optional[str] = self._get_field(f, b'ISBJ')
+        self.subject: Optional[str] = self._get_field(f, b'ISBJ')
         #: 'IART' Artist, composer, author
-        self.artist : Optional[str] = self._get_field(f, b'IART')
+        self.artist: Optional[str] = self._get_field(f, b'IART')
         #: 'ICMT' Comment
-        self.comment : Optional[str] = self._get_field(f, b'ICMT')
+        self.comment: Optional[str] = self._get_field(f, b'ICMT')
         #: 'ISFT' Software, encoding application
-        self.software : Optional[str] = self._get_field(f, b'ISFT')
+        self.software: Optional[str] = self._get_field(f, b'ISFT')
         #: 'ICRD' Created date
-        self.created_date : Optional[str] = self._get_field(f, b'ICRD')
+        self.created_date: Optional[str] = self._get_field(f, b'ICRD')
         #: 'IENG' Engineer
-        self.engineer : Optional[str] = self._get_field(f, b'IENG')
+        self.engineer: Optional[str] = self._get_field(f, b'IENG')
         #: 'ITCH' Technician
-        self.technician : Optional[str] = self._get_field(f, b'ITCH')
+        self.technician: Optional[str] = self._get_field(f, b'ITCH')
         #: 'IKEY' Keywords, keyword list
-        self.keywords : Optional[str] = self._get_field(f, b'IKEY')
+        self.keywords: Optional[str] = self._get_field(f, b'IKEY')
         #: 'INAM' Name, title
-        self.title : Optional[str] = self._get_field(f, b'INAM')
+        self.title: Optional[str] = self._get_field(f, b'INAM')
         #: 'ISRC' Source
-        self.source : Optional[str] = self._get_field(f, b'ISRC')
+        self.source: Optional[str] = self._get_field(f, b'ISRC')
         #: 'TAPE' Tape
-        self.tape : Optional[str] = self._get_field(f, b'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')
+        self.archival_location: Optional[str] = self._get_field(f, b'IARL')
         #: 'ICSM' Commissioned
-        self.commissioned : Optional[str] = self._get_field(f, b'ICMS')
+        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),
+        search = next(((chunk.start, chunk.length)
+                       for chunk in self.info_chunk.children
+                       if chunk.ident == field_ident),
                       None)
 
         if search is not None:
@@ -59,7 +65,7 @@ class WavInfoChunkReader:
         else:
             return None
 
-    def to_dict(self) -> dict: #FIXME should be asdict 
+    def to_dict(self) -> dict:  # FIXME should be asdict
         """
         A dictionary with all of the key/values read from the INFO scope.
         """

wavinfo/wave_ixml_reader.py

@@ -1,10 +1,16 @@
 from lxml import etree as ET
 import io
-from collections import namedtuple
+# from collections import namedtuple
 from typing import Optional
 from enum import IntEnum
+from typing import NamedTuple
 
-IXMLTrack = namedtuple('IXMLTrack', ['channel_index', 'interleave_index', 'name', 'function'])
+
+class IXMLTrack(NamedTuple):
+    channel_index: int
+    interleave_index: int
+    name: str
+    function: str
 
 
 class SteinbergMetadata:
@@ -29,7 +35,7 @@ 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
@@ -72,7 +78,8 @@ class SteinbergMetadata:
         """
         `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))
 
@@ -81,7 +88,8 @@ class SteinbergMetadata:
         """
         AudioSampleFormatSize
         """
-        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'AudioSampleFormatSize']/VALUE")
+        val = self.parsed.find(
+            "./ATTR_LIST/ATTR[NAME = 'AudioSampleFormatSize']/VALUE")
         if val is not None:
             return int(val.text)
 
@@ -90,7 +98,8 @@ class SteinbergMetadata:
         """
         MediaCompany
         """
-        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'MediaCompany']/VALUE")
+        val = self.parsed.find(
+            "./ATTR_LIST/ATTR[NAME = 'MediaCompany']/VALUE")
         if val is not None:
             return val.text
 
@@ -99,7 +108,8 @@ class SteinbergMetadata:
         """
         MediaDropFrames
         """
-        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'MediaDropFrames']/VALUE")
+        val = self.parsed.find(
+            "./ATTR_LIST/ATTR[NAME = 'MediaDropFrames']/VALUE")
         if val is not None:
             return val.text == "1"
 
@@ -108,7 +118,8 @@ class SteinbergMetadata:
         """
         MediaDuration
         """
-        val = self.parsed.find("./ATTR_LIST/ATTR[NAME = 'MediaDuration']/VALUE")
+        val = self.parsed.find(
+            "./ATTR_LIST/ATTR[NAME = 'MediaDuration']/VALUE")
         if val is not None:
             return float(val.text)
 
@@ -145,6 +156,7 @@ class WavIXMLFormat:
     """
     iXML recorder metadata.
     """
+
     def __init__(self, xml):
         """
         Parse iXML.
@@ -153,13 +165,13 @@ 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]:
         e = self.parsed.find("./" + xpath)
         if e is not None:
             return e.text
-        else: 
+        else:
             return None
 
     def xml_str(self) -> str:
@@ -181,10 +193,13 @@ class WavIXMLFormat:
         """
         for track in self.parsed.find("./TRACK_LIST").iter():
             if track.tag == 'TRACK':
-                yield IXMLTrack(channel_index=track.xpath('string(CHANNEL_INDEX/text())'),
-                                interleave_index=track.xpath('string(INTERLEAVE_INDEX/text())'),
-                                name=track.xpath('string(NAME/text())'),
-                                function=track.xpath('string(FUNCTION/text())'))
+                yield IXMLTrack(
+                    channel_index=track.xpath('string(CHANNEL_INDEX/text())'),
+                    interleave_index=track.xpath(
+                        'string(INTERLEAVE_INDEX/text())'),
+                    name=track.xpath('string(NAME/text())'),
+                    function=track.xpath('string(FUNCTION/text())')
+                )
 
     @property
     def project(self) -> Optional[str]:
@@ -201,7 +216,7 @@ class WavIXMLFormat:
         return self._get_text_value("SCENE")
 
     @property
-    def take(self) ->  Optional[str]:
+    def take(self) -> Optional[str]:
         """
         Take number.
         """
@@ -218,7 +233,8 @@ class WavIXMLFormat:
     def family_uid(self) -> Optional[str]:
         """
         The globally-unique ID for this file family. This may be in the format
-        of a GUID, or an EBU Rec 9 source identifier, or some other dumb number.
+        of a GUID, or an EBU Rec 9 source identifier, or some other dumb
+        number.
         """
         return self._get_text_value("FILE_SET/FAMILY_UID")
 
@@ -240,11 +256,8 @@ class WavIXMLFormat:
             return None
 
     def to_dict(self):
-        return dict(track_list=list(map(lambda x: x._asdict(), self.track_list)), 
-            project=self.project,
-            scene=self.scene,
-            take=self.take,
-            tape=self.tape,
-            family_uid=self.family_uid,
-            family_name=self.family_name 
-            )
+        return dict(
+            track_list=list(map(lambda x: x._asdict(), self.track_list)),
+            project=self.project, scene=self.scene, take=self.take,
+            tape=self.tape, family_uid=self.family_uid,
+            family_name=self.family_name)

wavinfo/wave_reader.py

@@ -1,12 +1,11 @@
-#-*- coding: utf-8 -*-
+# -*- coding: utf-8 -*-
 import struct
 import os
-from collections import namedtuple
-
-from typing import Optional, Generator, Any
+from typing import Optional, Generator, Any, NamedTuple
 
 import pathlib
 
+
 from .riff_parser import parse_chunk, ChunkDescriptor, ListChunkDescriptor
 from .wave_ixml_reader import WavIXMLFormat
 from .wave_bext_reader import WavBextReader
@@ -14,14 +13,24 @@ from .wave_info_reader import WavInfoChunkReader
 from .wave_adm_reader import WavADMReader
 from .wave_dbmd_reader import WavDolbyMetadataReader
 from .wave_cues_reader import WavCuesReader
+from .wave_smpl_reader import WavSmplReader
 
 #: Calculated statistics about the audio data.
-WavDataDescriptor = namedtuple('WavDataDescriptor', 'byte_count frame_count')
+
+
+class WavDataDescriptor(NamedTuple):
+    byte_count: int
+    frame_count: int
+
 
 #: The format of the audio samples.
-WavAudioFormat = namedtuple('WavAudioFormat',
-                            ['audio_format', 'channel_count', 'sample_rate',
-                             'byte_rate',  'block_align',  'bits_per_sample'])
+class WavAudioFormat(NamedTuple):
+    audio_format: int
+    channel_count: int
+    sample_rate: int
+    byte_rate: int
+    block_align: int
+    bits_per_sample: int
 
 
 class WavInfoReader:
@@ -33,52 +42,55 @@ class WavInfoReader:
         """
         Create a new reader object.
 
-        :param path: 
-            A pathlike object or IO to the wav file you wish to probe or a 
+        :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: 
+        :param info_encoding:
             The text encoding of the ``INFO``, ``LABL`` and other RIFF-defined
-            metadata fields. 
+            metadata fields.
 
-        :param bext_encoding: 
+        :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
+        self.fmt: Optional[WavAudioFormat] = None
 
         #: Statistics of the `data` section.
-        self.data :Optional[WavDataDescriptor] = None
+        self.data: Optional[WavDataDescriptor] = None
 
         #: Broadcast-Wave metadata.
-        self.bext :Optional[WavBextReader] = None
+        self.bext: Optional[WavBextReader] = None
 
         #: iXML metadata.
-        self.ixml :Optional[WavIXMLFormat] = None
+        self.ixml: Optional[WavIXMLFormat] = None
 
         #: ADM Audio Definiton Model metadata.
-        self.adm :Optional[WavADMReader]= None
+        self.adm: Optional[WavADMReader] = None
 
         #: Dolby bitstream metadata.
-        self.dolby :Optional[WavDolbyMetadataReader] = None
+        self.dolby: Optional[WavDolbyMetadataReader] = None
 
         #: RIFF INFO metadata.
-        self.info :Optional[WavInfoChunkReader]= None
+        self.info: Optional[WavInfoChunkReader] = None
 
         #: RIFF cues markers, labels, and notes.
-        self.cues :Optional[WavCuesReader] = None
+        self.cues: Optional[WavCuesReader] = None
+
+        #: Sampler `smpl` metadata
+        self.smpl: Optional[WavSmplReader] = 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)
 
@@ -86,13 +98,13 @@ class WavInfoReader:
             self.url: str = pathlib.Path(absolute_path).as_uri()
 
             self.path = absolute_path
-        
-            with open(path, 'rb') as f:
-                self.get_wav_info(f)
-            
+
+            with open(path, 'rb') as path:
+                self.get_wav_info(path)
+
     def get_wav_info(self, wavfile):
         chunks = parse_chunk(wavfile)
-        assert type(chunks) is ListChunkDescriptor  
+        assert type(chunks) is ListChunkDescriptor
 
         self.main_list = chunks.children
         wavfile.seek(0)
@@ -100,15 +112,18 @@ class WavInfoReader:
         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.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) -> Optional[bytes]:
-        top_chunks = (chunk for chunk in self.main_list \
-            if type(chunk) is ChunkDescriptor and chunk.ident == ident)
+    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)
@@ -117,19 +132,19 @@ class WavInfoReader:
             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)
+        top_chunks = (chunk for chunk in self.main_list
+                      if type(chunk) is ListChunkDescriptor and
+                      chunk.signature == signature)
 
         return next(top_chunks, None)
 
     def _describe_data(self):
-        data_chunk = next(c for c in self.main_list \
-            if type(c) is ChunkDescriptor and c.ident == b'data')
+        data_chunk = next(c for c in self.main_list
+                          if type(c) is ChunkDescriptor and c.ident == b'data')
 
         assert isinstance(self.fmt, WavAudioFormat)
         return WavDataDescriptor(
-            byte_count=data_chunk.length, 
+            byte_count=data_chunk.length,
             frame_count=int(data_chunk.length / self.fmt.block_align))
 
     def _get_format(self, f):
@@ -150,8 +165,8 @@ class WavInfoReader:
                               )
 
     def _get_info(self, f, encoding):
-        finder = (chunk.signature for chunk in self.main_list \
-            if type(chunk) is ListChunkDescriptor)
+        finder = (chunk.signature for chunk in self.main_list
+                  if type(chunk) is ListChunkDescriptor)
 
         if b'INFO' in finder:
             return WavInfoChunkReader(f, encoding)
@@ -176,33 +191,42 @@ class WavInfoReader:
         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)
+        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']
+            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)
+        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()"
+    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" or "adm".
+            "fmt", "data", "ixml", "bext", "info", "dolby", "cues", "adm" or
+            "smpl".
         """
 
-        scopes = ('fmt', 'data', 'ixml', 'bext', 'info', 'adm', 'cues', 
-                 'dolby')
+        scopes = ('fmt', 'data', 'ixml', 'bext', 'info', 'adm', 'cues',
+                  'dolby', 'smpl')
 
         for scope in scopes:
             if scope in ['fmt', 'data']:
@@ -211,9 +235,12 @@ class WavInfoReader:
                     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]
-        
+                mdict = self.__getattribute__(scope).to_dict(
+                ) if self.__getattribute__(scope) else {}
+                for key in mdict.keys():
+                    yield scope, key, mdict[key]
+
     def __repr__(self):
-        return 'WavInfoReader({}, {}, {})'.format(self.path, self.info_encoding, self.bext_encoding)
+        return 'WavInfoReader({}, {}, {})'.format(self.path,
+                                                  self.info_encoding,
+                                                  self.bext_encoding)

wavinfo/wave_smpl_reader.py

@@ -0,0 +1,114 @@
+import struct
+
+from typing import Tuple, NamedTuple, List
+
+
+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,
+        }

wavinfo/wavfind.py

@@ -9,23 +9,24 @@ import sys
 def main():
     parser = OptionParser()
 
-    parser.usage = "wavfind [--scene=SCENE] [--take=TAKE] [--desc=DESC] <PATH> +"
+    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.")
+                            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("--scene", 
-        help='Search for this scene', 
-        metavar='SCENE')
-    
     primaries.add_option("--take",
-        help='Search for this take',
-        metavar='TAKE')
+                         help='Search for this take',
+                         metavar='TAKE')
 
     primaries.add_option("--desc",
-        help='Search descriptions',
-        metavar='DESC')
-        
+                         help='Search descriptions',
+                         metavar='DESC')
 
     (options, args) = parser.parse_args(sys.argv)