Update pythonpublish.yml

Added a Report to mastadon action

.coveragerc

@@ -1,13 +0,0 @@
-[run]
-branch = True
-source = wavinfo 
-
-[report]
-exclude_lines =
-    if self.debug:
-    pragma: no cover
-    raise NotImplementedError
-    if __name__ == .__main__.:
-ignore_errors = True
-omit =
-    tests/*

.github/workflows/python-package.yml

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

.github/workflows/pythonpublish.yml

@@ -2,7 +2,7 @@ name: Upload Python Package
 
 on:
   release:
-    types: [created]
+    types: [published]
 
 jobs:
   deploy:
@@ -19,8 +19,18 @@ jobs:
         pip install setuptools wheel twine lxml
     - name: Build and publish
       env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_USERNAME: __token__
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_APIKEY }}
       run: |
         python setup.py sdist bdist_wheel
         twine upload dist/*
+    - name: Report to Mastodon
+      uses: cbrgm/mastodon-github-action@v1.0.1
+      with:
+        message: |
+          I just released a new version of wavinfo, my library for reading WAVE file metadata!
+          
+          ${{ github.server_url }}/${{ github.repository }}
+      env:
+        MASTODON_URL: ${{ secrets.MASTODON_URL }}
+        MASTODON_ACCESS_TOKEN: ${{ secrets.MASTODON_ACCESS_TOKEN }}

.gitignore

@@ -89,6 +89,7 @@ venv/
 ENV/
 env.bak/
 venv.bak/
+docs_venv/
 
 # Spyder project settings
 .spyderproject

.idea/.gitignore

@@ -1,3 +0,0 @@
-
-# Default ignored files
-/workspace.xml

.idea/dictionaries/jamiehardt.xml

@@ -1,8 +0,0 @@
-<component name="ProjectDictionaryState">
-  <dictionary name="jamiehardt">
-    <words>
-      <w>ident</w>
-      <w>umid</w>
-    </words>
-  </dictionary>
-</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -1,6 +0,0 @@
-<component name="InspectionProjectProfileManager">
-  <settings>
-    <option name="USE_PROJECT_PROFILE" value="false" />
-    <version value="1.0" />
-  </settings>
-</component>

.idea/misc.xml

@@ -1,4 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7" project-jdk-type="Python SDK" />
-</project>

.idea/modules.xml

@@ -1,8 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectModuleManager">
-    <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/wavinfo.iml" filepath="$PROJECT_DIR$/.idea/wavinfo.iml" />
-    </modules>
-  </component>
-</project>

.idea/vcs.xml

@@ -1,6 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="VcsDirectoryMappings">
-    <mapping directory="" vcs="Git" />
-  </component>
-</project>

.idea/wavinfo.iml

@@ -1,11 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<module type="PYTHON_MODULE" version="4">
-  <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="Python 3.7" jdkType="Python SDK" />
-    <orderEntry type="sourceFolder" forTests="false" />
-  </component>
-  <component name="TestRunnerService">
-    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
-  </component>
-</module>

.readthedocs.yaml

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

.travis.yml

@@ -1,26 +0,0 @@
-dist: xenial
-language: python
-python:
-#    - "2.7"
-    - "3.6"
-    - "3.5"
-    - "3.7"
-    - "3.8"
-script:
-    - "gunzip tests/test_files/rf64/*.gz"
-    - "python setup.py test"
-#    - "python -m pytest tests/ -v --cov wavinfo --cov-report term-missing"
-before_install:
-    - "sudo apt-get update"
-    - "sudo add-apt-repository universe"
-    - "sudo apt-get install -y ffmpeg"
-    - "pip install pytest"
-    - "pip install lxml"
-#     - "pip install coverage"
-#     - "pip install codecov"
-#     - "pip install pytest-cov==2.5.0"
-#     - "pip install coverage==4.4"
-install:
-    - "pip install setuptools"
-# after_success:
-#     - "codecov"

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "esbonio.sphinx.confDir": ""
+}

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2020 Jamie Hardt
+Copyright (c) 2022 Jamie Hardt
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -1,33 +1,32 @@
-[![Build Status](https://travis-ci.com/iluvcapra/wavinfo.svg?branch=master)](https://travis-ci.com/iluvcapra/wavinfo)
 [![Documentation Status](https://readthedocs.org/projects/wavinfo/badge/?version=latest)](https://wavinfo.readthedocs.io/en/latest/?badge=latest) ![](https://img.shields.io/github/license/iluvcapra/wavinfo.svg) ![](https://img.shields.io/pypi/pyversions/wavinfo.svg) [![](https://img.shields.io/pypi/v/wavinfo.svg)](https://pypi.org/project/wavinfo/) ![](https://img.shields.io/pypi/wheel/wavinfo.svg)
-
+[![Lint and Test](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml/badge.svg)](https://github.com/iluvcapra/wavinfo/actions/workflows/python-package.yml)
 
 # wavinfo
 
-
+The `wavinfo` package allows you to probe WAVE and [RF64/WAVE files][eburf64] and extract extended metadata, with an emphasis on film, video and professional music production metadata.
-The `wavinfo` package allows you to probe WAVE and [RF64/WAVE files][eburf64] and extract extended metadata, with an emphasis on film, video and professional music production metadata. 
 
 `wavinfo` reads:
 
-* __Broadcast-WAVE__ metadata, compliant with [EBU Tech 3285v2 (2011)][ebu], including embedded program 
+* __Broadcast-WAVE__ metadata<sup>[1][ebu]</sup>, including embedded program
-  loudness and coding history, if extant. This also includes the [SMPTE 330M __UMID__][smpte_330m2011] 
+  loudness and coding history, if extant. This also includes the SMPTE UMID<sup>[2][smpte_330m2011]</sup>.
-  Unique Materials Identifier.
+* __iXML__ production recorder metadata<sup>[3][ixml]</sup>, including project, scene, and take tags, recorder notes
-* [__iXML__ production recorder metadata][ixml], including project, scene, and take tags, recorder notes 
   and file family information.
-* Most of the common __RIFF INFO__ metadata fields.
+* Most of the common __RIFF INFO__<sup>[4][info-tags]</sup> metadata fields.
-* The __wav format__ is also parsed, so you can access the basic sample rate and channel count 
+* The __wav format__ is also parsed, so you can access the basic sample rate and channel count
   information.
 
 In progress:
+* ADM metadata consilient with the output of the __Dolby RMU__, perhaps later fully complaint with [ITU BS.2076-2][adm].
 * iXML `STEINBERG` sound library attributes.
+* __NetMix__ library attributes.
 * Pro Tools __embedded regions__.
 
 [ebu]:https://tech.ebu.ch/docs/tech/tech3285.pdf
+[adm]:https://www.itu.int/dms_pubrec/itu-r/rec/bs/R-REC-BS.2076-2-201910-I!!PDF-E.pdf
 [smpte_330m2011]:http://standards.smpte.org/content/978-1-61482-678-1/st-330-2011/SEC1.abstract
 [ixml]:http://www.ixml.info
 [eburf64]:https://tech.ebu.ch/docs/tech/tech3306v1_1.pdf
-
+[info-tags]:https://exiftool.org/TagNames/RIFF.html#Info
-
 
 ## Demonstration
 
@@ -61,7 +60,3 @@ The length of the file in frames (interleaved samples) and bytes is available, a
 ## Other Resources
 
 * For other file formats and ID3 decoding, look at [audio-metadata](https://github.com/thebigmunch/audio-metadata).
-
-
-
-

docs/Makefile

@@ -4,7 +4,7 @@
 # You can set these variables from the command line.
 SPHINXOPTS    =
 SPHINXBUILD   = sphinx-build
-SOURCEDIR     = .
+SOURCEDIR     = source
 BUILDDIR      = _build
 
 # Put it first so that "make" without argument is like "make help".
@@ -16,4 +16,4 @@ help:
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/make.bat

@@ -1,35 +0,0 @@
-@ECHO OFF
-
-pushd %~dp0
-
-REM Command file for Sphinx documentation
-
-if "%SPHINXBUILD%" == "" (
-	set SPHINXBUILD=sphinx-build
-)
-set SOURCEDIR=.
-set BUILDDIR=_build
-
-if "%1" == "" goto help
-
-%SPHINXBUILD% >NUL 2>NUL
-if errorlevel 9009 (
-	echo.
-	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
-	echo.installed, then set the SPHINXBUILD environment variable to point
-	echo.to the full path of the 'sphinx-build' executable. Alternatively you
-	echo.may add the Sphinx directory to PATH.
-	echo.
-	echo.If you don't have Sphinx installed, grab it from
-	echo.http://sphinx-doc.org/
-	exit /b 1
-)
-
-%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
-goto end
-
-:help
-%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
-
-:end
-popd

docs/requirements.txt

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

docs/source/classes.rst

@@ -0,0 +1,18 @@
+Other wavinfo Classes
+===============
+
+
+.. autoclass:: wavinfo.wave_reader.WavInfoReader
+   :members:
+
+   .. automethod:: __init__
+   
+
+.. autoclass:: wavinfo.wave_reader.WavAudioFormat
+   :members:
+
+.. autoclass:: wavinfo.wave_reader.WavDataDescriptor
+   :members:
+
+
+

docs/source/conf.py

@@ -14,19 +14,21 @@
 #
 import os
 import sys
-sys.path.insert(0, os.path.abspath('..'))
+sys.path.insert(0, os.path.abspath('../..'))
+sys.path.insert(0, os.path.abspath("../../.."))
+print(sys.path)
 
 
 # -- Project information -----------------------------------------------------
 
 project = u'wavinfo'
-copyright = u'2019, Jamie Hardt'
+copyright = u'2022, Jamie Hardt'
 author = u'Jamie Hardt'
 
 # The short X.Y version
 version = u''
 # The full version, including alpha/beta/rc tags
-release = u'v1.1'
+release = u'v1.7.1'
 
 
 # -- General configuration ---------------------------------------------------
@@ -61,7 +63,7 @@ master_doc = 'index'
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = 'en'
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.

docs/source/index.rst

@@ -6,30 +6,15 @@
 Welcome to wavinfo's documentation!
 ===================================
 
-
-.. module:: wavinfo
-
-.. autoclass:: WavInfoReader
-   :members:
-
-   .. automethod:: __init__
-   
-
-.. autoclass:: wavinfo.wave_reader.WavAudioFormat
-   :members:
-
-.. autoclass:: wavinfo.wave_reader.WavDataDescriptor
-   :members:
-
-
 .. toctree::
    :maxdepth: 2
-   :caption: Notes:
+   :caption: Notes
-   
+  
    metadata_scopes/bext.rst
    metadata_scopes/ixml.rst
    metadata_scopes/info.rst
 
+   classes
 
 
 Indices and tables

docs/source/metadata_scopes/bext.rst

@@ -1,11 +1,6 @@
 Broadcast WAV Extension
 =======================
 
-.. module:: wavinfo
-
-.. autoclass:: wavinfo.wave_bext_reader.WavBextReader
-   :members:
-
 
 Notes
 -----
@@ -63,3 +58,14 @@ Result:
     Originator Time: 12:40:00
     Time Reference: 2190940753
     A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch
+
+
+Class Reference
+---------------
+
+.. module:: wavinfo
+
+.. autoclass:: wavinfo.wave_bext_reader.WavBextReader
+   :members:
+
+

docs/source/metadata_scopes/info.rst

@@ -1,14 +1,6 @@
 INFO Metadata
 =============
 
-
-.. module:: wavinfo
-
-.. autoclass:: wavinfo.wave_info_reader.WavInfoChunkReader
-   :members:
-
-
-
 Notes
 -----
 
@@ -28,5 +20,14 @@ music library software.
     print("INFO Comment:",   bullet.info.comment)
 
 
+Class Reference
+---------------
+
+.. module:: wavinfo
+
+.. autoclass:: wavinfo.wave_info_reader.WavInfoChunkReader
+   :members:
+
+
 
 

docs/source/metadata_scopes/ixml.rst

@@ -1,13 +1,6 @@
 iXML Production Recorder Metadata
 =================================
 
-
-.. module:: wavinfo
-
-.. autoclass:: wavinfo.wave_ixml_reader.WavIXMLFormat
-   :members:
-
-
 Notes
 -----
 iXML allows an XML document to be embedded in a WAV file.
@@ -41,4 +34,12 @@ Result:
     iXML File Family UID: USSDVGR1112089007124001008206300
 
 
+Class Reference
+---------------
+
+.. module:: wavinfo
+
+.. autoclass:: wavinfo.wave_ixml_reader.WavIXMLFormat
+   :members:
+
 

metadata.py

@@ -0,0 +1,6 @@
+"""
+Wavinfo
+"""
+__version__ = '1.7.2'
+__author__ = 'Jamie Hardt <jamiehardt@gmail.com>'
+__license__ = "MIT"

requirements.txt

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

setup.py

@@ -1,5 +1,5 @@
 from setuptools import setup
-from wavinfo import __author__, __license__, __version__
+from metadata import __author__, __license__, __version__
 
 with open("README.md", "r") as fh:
     long_description = fh.read()
@@ -26,10 +26,9 @@ setup(name='wavinfo',
           'License :: OSI Approved :: MIT License',
           'Topic :: Multimedia',
           'Topic :: Multimedia :: Sound/Audio',
-          "Programming Language :: Python :: 3.5",
+          "Programming Language :: Python :: 3.8",
-          "Programming Language :: Python :: 3.6",
+          "Programming Language :: Python :: 3.9",
-          "Programming Language :: Python :: 3.7",
+          "Programming Language :: Python :: 3.10"],
-          "Programming Language :: Python :: 3.8"],
       keywords='waveform metadata audio ebu smpte avi library film tv editing editorial',
       install_requires=['lxml'],
       entry_points={

tests/test_walk.py

@@ -0,0 +1,25 @@
+import unittest
+import wavinfo
+
+
+class TestWalk(unittest.TestCase):
+    def test_walk_metadata(self):
+        test_file = 'tests/test_files/protools/PT A101_4.A1.wav'
+        info = wavinfo.WavInfoReader(test_file)
+
+        tested_data , tested_format = False, False
+        for scope, key, value in info.walk():
+            if scope == 'fmt':
+                if key == 'channel_count':
+                    tested_format = True
+                    self.assertEqual(value, 2)
+            if scope == 'data':
+                if key == 'frame_count':
+                    tested_data = True
+                    self.assertEqual(value, 144140)
+
+        self.assertTrue(tested_data and tested_format)
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_wave_parsing.py

@@ -6,34 +6,35 @@ from unittest import TestCase
 from .utils import all_files, ffprobe
 
 import wavinfo
-        
+
+
 class TestWaveInfo(TestCase):
     def test_sanity(self):
         for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
-            self.assertTrue(info is not None)
+            self.assertEqual(info.__repr__(), 'WavInfoReader({}, latin_1, ascii)'.format(os.path.abspath(wav_file)))
+            self.assertIsNotNone(info)
 
     def test_fmt_against_ffprobe(self):
         for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
 
-            self.assertEqual( info.fmt.channel_count , ffprobe_info['streams'][0]['channels']  )
+            self.assertEqual(info.fmt.channel_count, ffprobe_info['streams'][0]['channels'])
-            self.assertEqual( info.fmt.sample_rate   , int(ffprobe_info['streams'][0]['sample_rate'])  )
+            self.assertEqual(info.fmt.sample_rate, int(ffprobe_info['streams'][0]['sample_rate']))
-            self.assertEqual( info.fmt.bits_per_sample, int(ffprobe_info['streams'][0]['bits_per_raw_sample']) )
+            self.assertEqual(info.fmt.bits_per_sample, int(ffprobe_info['streams'][0]['bits_per_raw_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'))
-                byte_rate = int(ffprobe_info['streams'][0]['sample_rate']) \
+                streams = ffprobe_info['streams'][0]
-                        * ffprobe_info['streams'][0]['channels'] \
+                byte_rate = int(streams['sample_rate']) * streams['channels'] * int(streams['bits_per_raw_sample']) / 8
-                        * int(ffprobe_info['streams'][0]['bits_per_raw_sample']) / 8
+                self.assertEqual(info.fmt.byte_rate, byte_rate)
-                self.assertEqual( info.fmt.byte_rate     , byte_rate  )
 
     def test_data_against_ffprobe(self):
         for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
-            self.assertEqual( info.data.frame_count, int(ffprobe_info['streams'][0]['duration_ts'] ))
+            self.assertEqual(info.data.frame_count, int(ffprobe_info['streams'][0]['duration_ts']))
 
     def test_bext_against_ffprobe(self):
         for wav_file in all_files():
@@ -41,56 +42,73 @@ class TestWaveInfo(TestCase):
             ffprobe_info = ffprobe(wav_file)
             if info.bext:
                 if 'comment' in ffprobe_info['format']['tags']:
-                    self.assertEqual( info.bext.description, ffprobe_info['format']['tags']['comment']  )
+                    self.assertEqual(info.bext.description, ffprobe_info['format']['tags']['comment'])
-                else: 
+                else:
-                    self.assertEqual( info.bext.description , '')
+                    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, '')
+                    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, '')
+                    self.assertEqual(info.bext.originator_ref, '')
 
                 # these don't always reflect the bext info
-                # self.assertEqual( info.bext.originator_date, ffprobe_info['format']['tags']['date']  )
+                # self.assertEqual(info.bext.originator_date, ffprobe_info['format']['tags']['date'])
-                # self.assertEqual( info.bext.originator_time, ffprobe_info['format']['tags']['creation_time']  )
+                # 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.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, '' )
+                    self.assertEqual(info.bext.coding_history, '')
 
     def test_ixml(self):
-        expected = {'A101_4.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '4',
+        expected = {'A101_4.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '4',
-                        'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124015008231000'},
+                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124015008231000'},
-                    'A101_3.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '3',
+                    'A101_3.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '3',
-                        'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124014008228300'},
+                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124014008228300'},
-                    'A101_2.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '2',
+                    'A101_2.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '2',
-                        'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124004008218600'},
+                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124004008218600'},
-                    'A101_1.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '1',
+                    'A101_1.WAV': {'project': 'BMH', 'scene': 'A101', 'take': '1',
-                        'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124001008206300'},
+                                   'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124001008206300'},
-                }
+                    }
 
         for wav_file in all_files():
-            basename =  os.path.basename(wav_file)
+            basename = os.path.basename(wav_file)
             if basename in expected:
                 info = wavinfo.WavInfoReader(wav_file)
                 e = expected[basename]
 
-                self.assertEqual( e['project'], info.ixml.project )
+                self.assertEqual(e['project'], info.ixml.project)
-                self.assertEqual( e['scene'], info.ixml.scene )
+                self.assertEqual(e['scene'], info.ixml.scene)
-                self.assertEqual( e['take'], info.ixml.take )
+                self.assertEqual(e['take'], info.ixml.take)
-                self.assertEqual( e['tape'], info.ixml.tape )
+                self.assertEqual(e['tape'], info.ixml.tape)
-                self.assertEqual( e['family_uid'], info.ixml.family_uid )
+                self.assertEqual(e['family_uid'], info.ixml.family_uid)
 
                 for track in info.ixml.track_list:
                     self.assertIsNotNone(track.channel_index)
                     if basename == 'A101_4.WAV' and track.channel_index == '1':
-                        self.assertTrue(track.name == 'MKH516 A')
+                        self.assertEqual(track.name, 'MKH516 A')
 
+    def test_metadata(self):
+        file_with_metadata = 'tests/test_files/sound_grinder_pro/new_camera bumb 1.wav'
+        self.assertTrue(os.path.exists(file_with_metadata))
+        info = wavinfo.WavInfoReader(file_with_metadata).info
+        self.assertEqual(info.title, 'camera bumb 1')
+        self.assertEqual(info.artist, 'Jamie Hardt')
+        self.assertEqual(info.copyright, '© 2010 Jamie Hardt')
+        self.assertEqual(info.product, 'Test Sounds')  # album
+        self.assertEqual(info.album, info.product)
+        self.assertEqual(info.comment, 'Comments')
+        self.assertEqual(info.software, 'Sound Grinder Pro')
+        self.assertEqual(info.created_date, '2010-12-28')
+        self.assertEqual(info.engineer, 'JPH')
+        self.assertEqual(info.keywords, 'Sound Effect, movement, microphone, bump')
+        self.assertEqual(info.title, 'camera bumb 1')
+        self.assertEqual(type(info.to_dict()), dict)
+        self.assertEqual(type(info.__repr__()), str)
 

tests/test_zoom_f8.py

@@ -8,5 +8,6 @@ from unittest import TestCase
 
 import wavinfo
 
+
 class TestZoomF8(TestCase):
     pass

tests/utils.py

@@ -4,10 +4,11 @@ import subprocess
 from subprocess import PIPE
 import json
 
-FFPROBE='ffprobe'
+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()
@@ -27,13 +28,9 @@ def ffprobe(path):
             return None
 
 
-        
 def all_files():
     for dirpath, _, filenames in os.walk('tests/test_files'):
         for filename in filenames:
             _, ext = os.path.splitext(filename)
-            if ext in ['.wav','.WAV']:
+            if ext in ['.wav', '.WAV']:
                 yield os.path.join(dirpath, filename)
-
-
-

wavinfo/__init__.py

@@ -7,6 +7,3 @@ Go to the documentation for wavinfo.WavInfoReader for more information.
 from .wave_reader import WavInfoReader
 from .riff_parser import WavInfoEOFError
 
-__version__ = '1.5'
-__author__ = 'Jamie Hardt <jamiehardt@gmail.com>'
-__license__ = "MIT"

wavinfo/__main__.py

@@ -4,6 +4,7 @@ from . import WavInfoReader
 import sys
 import json
 
+
 def main():
     parser = OptionParser()
 
@@ -28,5 +29,6 @@ def main():
         except Exception as e:
             print(e)
 
+
 if __name__ == "__main__":
     main()

wavinfo/dolby_parser.py

@@ -0,0 +1,188 @@
+# Dolby RMU Metadata per EBU Tech 3285 Supp 6
+#
+# https://tech.ebu.ch/docs/tech/tech3285s6.pdf
+#
+
+from struct import unpack, calcsize
+from enum import (Enum, IntEnum)
+
+CHUNK_IDENT = "dbmd"
+DOLBY_VERSION = "1.0.0.6"
+
+
+class _DPPGenericDownMixLevel(Enum):
+    PLUS_3DB = 0b000
+    PLUS_1_5DB = 0b001
+    UNITY = 0b010
+    MINUS_1_5DB = 0b011
+    MINUS_3DB = 0b100
+    MINUS_4_5DB = 0b101
+    MINUS_6DB = 0b110
+    MUTE = 0b111
+
+
+class DPPDolbySurroundEncodingMode(Enum):
+    RESERVED = 0b11
+    IN_USE = 0b10
+    NOT_IN_USE = 0b01
+    NOT_INDICATED = 0b00
+
+# DPPLoRoDownMixCenterLevel
+# DPPLtRtCenterMixLevel
+# DPPLtRtSurroundMixLevel
+
+class DolbyMetadataSegmentTypes(IntEnum):
+    END_MARKER = 0
+    DOLBY_E_METADATA = 1
+    DOLBY_DIGITAL_METADATA = 3
+    DOLBY_DIGITAL_PLUS_METADATA = 7
+    AUDIO_INFO = 8
+
+
+class DDPBitStreamMode(Enum):
+    """
+    Dolby Digital Plus `bsmod` field
+    § 4.3.2.2
+    """
+    COMPLETE_MAIN = 0b000
+    MUSIC_AND_EFFECTS = 0b001
+    VISUALLY_IMPAIRED = 0b010
+    HEARING_IMPAIRED = 0b011
+    DIALOGUE_ONLY = 0b100
+    COMMENTARY = 0b101
+    EMERGENCY = 0b110
+    VOICEOVER = 0b111 # if audioconfigmode is 1_0
+    KARAOKE = 0b1000  # if audioconfigmode is not 1_0
+
+
+class DDPAudioCodingMode(Enum):
+    """
+    Dolby Digital Plus `acmod` field
+    § 4.3.2.3
+    """
+    RESERVED = 0b000
+    CH_ORD_1_0 = 0b001
+    CH_ORD_2_0 = 0b010
+    CH_ORD_3_0 = 0b011
+    CH_ORD_2_1 = 0b100
+    CH_ORD_3_1 = 0b101
+    CH_ORD_2_2 = 0b110
+    CH_ORD_3_2 = 0b111
+
+
+class DPPCenterDownMixLevel(Enum):
+    """
+    § 4.3.3.1
+    """
+    DOWN_3DB = 0b00
+    DOWN_45DB = 0b01
+    DOWN_6DB = 0b10
+    RESERVED = 0b11
+
+
+class DPPSurroundDownMixLevel(Enum):
+    """
+    Dolby Digital Plus `surmixlev` field
+    § 4.3.3.2
+    """
+    DOWN_3DB = 0b00
+    DOWN_6DB = 0b01
+    MUTE = 0b10
+    RESERVED = 0b11
+
+
+class DPPLanguageCode(Enum):
+    """
+    § 4.3.4.1 , 4.3.5 (always 0xFF)
+    """
+    # this is removed in https://www.atsc.org/wp-content/uploads/2015/03/A52-201212-17.pdf § 5.4.2.12
+    # It should just be 0xff
+    pass
+
+
+class DPPMixLevel(int):
+    pass
+
+
+class DPPDialnormLevel(int):
+    pass
+
+
+class DPPRoomTime(Enum):
+    """
+    `roomtyp` 4.3.6.3
+    """
+    NOT_INDICATED = 0b00
+    LARGE_ROOM_X_CURVE = 0b01
+    SMALL_ROOM_FLAT_CURVE = 0b10
+    RESERVED = 0b11
+
+
+class DPPPreferredDownMixMode(Enum):
+    """
+    § 4.3.8.1
+    """
+    NOT_INDICATED = 0b00
+    PRO_LOGIC = 0b01
+    STEREO = 0b10
+    PRO_LOGIC_2 = 0b11
+
+
+# class DPPLtRtCenterMixLevel(_DPPGenericDownMixLevel):
+#     pass
+#
+#
+# class DPPLtRtSurroundMixLevel(_DPPGenericDownMixLevel):
+#     pass
+#
+#
+# class DPPSurroundEXMode(_DPPGenericInUseIndicator):
+#     pass
+#
+#
+# class DPPHeadphoneMode(_DPPGenericInUseIndicator):
+#     pass
+
+
+class DPPADConverterType(Enum):
+    STANDARD = 0
+    HDCD = 1
+
+
+class DDPStreamDependency(Enum):
+    """
+    Encodes `ddplus_info1.stream_type` field § 4.3.12.1
+    """
+    INDEPENDENT = 0
+    DEPENDENT = 1
+    INDEPENDENT_FROM_DOLBY_DIGITAL = 2
+    RESERVED = 3
+
+
+class DDPDataRate(int):
+    pass
+
+
+class DPPRFCompressionProfile(Enum):
+    NONE = 0
+    FILM_STANDARD = 1
+    FILM_LIGHT = 2
+    MUSIC_STANDARD = 3
+    MUSIC_LIGHT = 4
+    SPEECH = 5
+
+
+class DolbyDigitalPlusMetadata:
+
+    @classmethod
+    def parse(cls, binary_data):
+        binary_format = "<BBxxBBBBBBBBBBBBBxxxBxxxxxH"
+        assert len(binary_data >= calcsize(binary_format))
+        fields = unpack(binary_format, binary_data)
+
+
+class WavDolbyReader:
+    def __init__(self, dolby_data):
+        version, remainder = unpack("<U", dolby_data[0]), dolby_data[1:]
+
+        ## FIXME continues...

wavinfo/rf64_parser.py

@@ -1,40 +1,40 @@
 import struct
 from collections import namedtuple
-from . import riff_parser 
+from . import riff_parser
 
 RF64Context = namedtuple('RF64Context','sample_count bigchunk_table')
 
 
-def parse_rf64(stream):
+def parse_rf64(stream, signature = b'RF64'):
-    #print("starting parse_rf64")
+    # print("starting parse_rf64")
     start = stream.tell()
-    assert( stream.read(4) == b'WAVE' ) 
+    assert( stream.read(4) == b'WAVE' )
 
     ds64_chunk = riff_parser.parse_chunk(stream)
 
     ds64_field_spec = "<QQQI"
     ds64_fields_size = struct.calcsize(ds64_field_spec)
     assert(ds64_chunk.ident == b'ds64')
-    
+
     ds64_data = ds64_chunk.read_data(stream)
     assert(len(ds64_data) >= ds64_fields_size )
-    
+
-    #print("Read ds64 chunk: len()",len(ds64_data))
+    # print("Read ds64 chunk: len()",len(ds64_data))
     riff_size, data_size, sample_count, length_lookup_table = struct.unpack( ds64_field_spec , ds64_data[0:ds64_fields_size] )
-    
+
     bigchunk_table = {}
     chunksize64format = "<4sL"
     chunksize64size = struct.calcsize(chunksize64format)
-    #print("Found chunks64s:", length_lookup_table)
+    # print("Found chunks64s:", length_lookup_table)
 
     for n in range(length_lookup_table):
-        bigname, bigsize = struct.unpack_from( chunksize64format , ds64data, 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[b'RF64'] = riff_size
+    bigchunk_table[signature] = riff_size
- 
+
     stream.seek(start, 0)
-    #print("returning from parse_rf64, context: ",RF64Context( sample_count=sample_count, bigchunk_table=bigchunk_table ) )
+    # print("returning from parse_rf64, context: ", RF64Context(sample_count=sample_count, bigchunk_table=bigchunk_table))
     return RF64Context( sample_count=sample_count, bigchunk_table=bigchunk_table )
-    
+

wavinfo/riff_parser.py

@@ -11,17 +11,18 @@ class WavInfoEOFError(EOFError):
 
 
 class ListChunkDescriptor(namedtuple('ListChunkDescriptor', 'signature children')):
-    def find(self, chunk_path):
+    pass
-        if len(chunk_path) > 1:
+    # def find(self, chunk_path):
-            for chunk in self.children:
+    #     if len(chunk_path) > 1:
-                if type(chunk) is ListChunkDescriptor and \
+    #         for chunk in self.children:
-                        chunk.signature is chunk_path[0]:
+    #             if type(chunk) is ListChunkDescriptor and \
-                    return chunk.find(chunk_path[1:])
+    #                     chunk.signature is chunk_path[0]:
-        else:
+    #                 return chunk.find(chunk_path[1:])
-            for chunk in self.children:
+    #     else:
-                if type(chunk) is ChunkDescriptor and \
+    #         for chunk in self.children:
-                        chunk.ident is chunk_path[0]:
+    #             if type(chunk) is ChunkDescriptor and \
-                    return chunk
+    #                     chunk.ident is chunk_path[0]:
+    #                 return chunk
 
 
 class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length rf64_context')):
@@ -35,7 +36,7 @@ def parse_list_chunk(stream, length, rf64_context=None):
     signature = stream.read(4)
 
     children = []
-    while (stream.tell() - start + 8) < length:
+    while stream.tell() - start + 8 < length:
         child_chunk = parse_chunk(stream, rf64_context=rf64_context)
         children.append(child_chunk)
 
@@ -55,16 +56,16 @@ def parse_chunk(stream, rf64_context=None):
     data_size = struct.unpack('<I', size_bytes)[0]
 
     if data_size == 0xFFFFFFFF:
-        if rf64_context is None and ident == b'RF64':
+        if rf64_context is None and ident in {b'RF64', b'BW64'}:
-            rf64_context = parse_rf64(stream=stream)
+            rf64_context = parse_rf64(stream=stream, signature=ident)
-        
-        data_size = rf64_context.bigchunk_table[ident]
-            
-    displacement = data_size
-    if displacement % 2 is not 0:
-        displacement = displacement + 1
 
-    if ident in [b'RIFF', b'LIST', b'RF64']:
+        data_size = rf64_context.bigchunk_table[ident]
+
+    displacement = data_size
+    if displacement % 2:
+        displacement += 1
+
+    if ident in {b'RIFF', b'LIST', b'RF64', b'BW64'}:
         return parse_list_chunk(stream=stream, length=data_size, rf64_context=rf64_context)
     else:
         data_start = stream.tell()

wavinfo/umid_parser.py

@@ -1,5 +1,9 @@
-import struct
+from functools import reduce
-from typing import Union
+
+
+def binary_to_string(binary_value):
+    return reduce(lambda val, el: val + "{:02x}".format(el), binary_value, '')
+
 
 class UMIDParser:
     """
@@ -7,123 +11,111 @@ class UMIDParser:
 
     This implementation is based on SMPTE ST 330:2011
     """
-    def __init__(self, raw_umid: bytearray):
+    def __init__(self, raw_umid: bytes):
         self.raw_umid = raw_umid
-
+    #
-    @classmethod
+    # @property
-    def binary_to_string(cls, binary_value):
+    # def universal_label(self) -> bytearray:
-        result_str = ''
+    #     return self.raw_umid[0:12]
-        for n in range(len(binary_value)):
+    #
-            result_str = f'{binary_value[n]:x}' + result_str
+    # @property
-
+    # def basic_umid(self):
-        return result_str
+    #     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 "%024x-%06x-%032x" % (self.binary_to_string(self.universal_label),
+        return binary_to_string(self.raw_umid[0:32])
-                                     self.binary_to_string(self.instance_number),
+    #
-                                     self.binary_to_string(self.material_number))
+    # @property
-
+    # def universal_label_is_valid(self) -> bool:
-    @property
+    #     valid_preamble = b'\x06\x0a\x2b\x34\x01\x01\x01\x05\x01\x01'
-    def universal_label_is_valid(self) -> bool:
+    #     return self.universal_label[0:len(valid_preamble)] == valid_preamble
-        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:
-    @property
+    #     material_byte = self.raw_umid[10]
-    def material_type(self) -> str:
+    #     if material_byte == 0x1:
-        material_byte = self.raw_umid[10]
+    #         return 'picture'
-        if material_byte == 0x1:
+    #     elif material_byte == 0x2:
-            return 'picture'
+    #         return 'audio'
-        elif material_byte == 0x2:
+    #     elif material_byte == 0x3:
-            return 'audio'
+    #         return 'data'
-        elif material_byte == 0x3:
+    #     elif material_byte == 0x4:
-            return 'data'
+    #         return 'other'
-        elif material_byte == 0x4:
+    #     elif material_byte == 0x5:
-            return 'other'
+    #         return 'picture_single_component'
-        elif material_byte == 0x5:
+    #     elif material_byte == 0x6:
-            return 'picture_single_component'
+    #         return 'picture_multiple_component'
-        elif material_byte == 0x6:
+    #     elif material_byte == 0x7:
-            return 'picture_multiple_component'
+    #         return 'audio_single_component'
-        elif material_byte == 0x7:
+    #     elif material_byte == 0x9:
-            return 'audio_single_component'
+    #         return 'audio_multiple_component'
-        elif material_byte == 0x9:
+    #     elif material_byte == 0xb:
-            return 'audio_multiple_component'
+    #         return 'auxiliary_single_component'
-        elif material_byte == 0xb:
+    #     elif material_byte == 0xc:
-            return 'auxiliary_single_component'
+    #         return 'auxiliary_multiple_component'
-        elif material_byte == 0xc:
+    #     elif material_byte == 0xd:
-            return 'auxiliary_multiple_component'
+    #         return 'mixed_components'
-        elif material_byte == 0xd:
+    #     elif material_byte == 0xf:
-            return 'mixed_components'
+    #         return 'not_identified'
-        elif material_byte == 0xf:
+    #     else:
-            return 'not_identified'
+    #         return 'not_recognized'
-        else:
+    #
-            return 'not_recognized'
+    # @property
-
+    # def material_number_creation_method(self) -> str:
-    @property
+    #     method_byte = self.raw_umid[11]
-    def material_number_creation_method(self) -> str:
+    #     method_byte = (method_byte << 4) & 0xf
-        method_byte = self.raw_umid[11]
+    #     if method_byte == 0x0:
-        method_byte = (method_byte << 4) & 0xf
+    #         return 'undefined'
-        if method_byte == 0x0:
+    #     elif method_byte == 0x1:
-            return 'undefined'
+    #         return 'smpte'
-        elif method_byte == 0x1:
+    #     elif method_byte == 0x2:
-            return 'smpte'
+    #         return 'uuid'
-        elif method_byte == 0x2:
+    #     elif method_byte == 0x3:
-            return 'uuid'
+    #         return 'masked'
-        elif method_byte == 0x3:
+    #     elif method_byte == 0x4:
-            return 'masked'
+    #         return 'ieee1394'
-        elif method_byte == 0x4:
+    #     elif 0x5 <= method_byte <= 0x7:
-            return 'ieee1394'
+    #         return 'reserved_undefined'
-        elif 0x5 <= method_byte <= 0x7:
+    #     else:
-            return 'reserved_undefined'
+    #         return 'unrecognized'
-        else:
+    #
-            return 'unrecognized'
+    # @property
-
+    # def instance_number_creation_method(self) -> str:
-    @property
+    #     method_byte = self.raw_umid[11]
-    def instance_number_creation_method(self) -> str:
+    #     method_byte = method_byte & 0xf
-        method_byte = self.raw_umid[11]
+    #     if method_byte == 0x0:
-        method_byte = method_byte & 0xf
+    #         return 'undefined'
-        if method_byte == 0x0:
+    #     elif method_byte == 0x01:
-            return 'undefined'
+    #         return 'local_registration'
-        elif method_byte == 0x01:
+    #     elif method_byte == 0x02:
-            return 'local_registration'
+    #         return '24_bit_prs'
-        elif method_byte == 0x02:
+    #     elif method_byte == 0x03:
-            return '24_bit_prs'
+    #         return 'copy_number_and_16_bit_prs'
-        elif method_byte == 0x03:
+    #     elif 0x04 <= method_byte <= 0x0e:
-            return 'copy_number_and_16_bit_prs'
+    #         return 'reserved_undefined'
-        elif 0x04 <= method_byte <= 0x0e:
+    #     elif method_byte == 0x0f:
-            return 'reserved_undefined'
+    #         return 'live_stream'
-        elif method_byte == 0x0f:
+    #     else:
-            return 'live_stream'
+    #         return 'unrecognized'
-        else:
+    #
-            return 'unrecognized'
+    # @property
-
+    # def indicated_length(self) -> str:
-    @property
+    #     if self.raw_umid[12] == 0x13:
-    def indicated_length(self) -> str:
+    #         return 'basic'
-        if self.raw_umid[12] == 0x13:
+    #     elif self.raw_umid[12] == 0x33:
-            return 'basic'
+    #         return 'extended'
-        elif self.raw_umid[12] == 0x33:
+    #
-            return 'extended'
+    # @property
-
+    # def instance_number(self) -> bytearray:
-    @property
+    #     return self.raw_umid[13:3]
-    def instance_number(self) -> bytearray:
+    #
-        return self.raw_umid[13:3]
+    # @property
-
+    # def material_number(self) -> bytearray:
-    @property
+    #     return self.raw_umid[16:16]
-    def material_number(self) -> bytearray:
+    #
-        return self.raw_umid[16:16]
+    # @property
-
+    # def source_pack(self) -> Union[bytearray, None]:
-    @property
+    #     if self.indicated_length == 'extended':
-    def source_pack(self) -> Union[bytearray, None]:
+    #         return self.raw_umid[32:32]
-        if self.indicated_length == 'extended':
+    #     else:
-            return self.raw_umid[32:32]
+    #         return None
-        else:
-            return None
-
-

wavinfo/wave_axml_reader.py

@@ -0,0 +1,9 @@
+from lxml import etree as ET
+from collections import namedtuple
+
+from ear.fileio.bw64 import Bw64Reader
+
+
+
+
+

wavinfo/wave_bext_reader.py

@@ -1,85 +1,89 @@
 import struct
+from .umid_parser import UMIDParser
+
+from typing import Optional
 
 class WavBextReader:
-    def __init__(self,bext_data,encoding):
+    def __init__(self, bext_data, encoding):
         """
         Read Broadcast-WAV extended metadata.
-        :param best_data: The bytes-like data.
+        :param bext_data: The bytes-like data.
-        "param encoding: The encoding to use when decoding the text fields of the
+        :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 sanatize_bytes(bytes):
+        def sanitize_bytes(b : bytes) -> str:
-            first_null = next( (index for index, byte in enumerate(bytes) if byte == 0 ), None )
+            first_null = next((index for index, byte in enumerate(b) if byte == 0), None)
-            if first_null is not None:
+            trimmed = b if first_null is None else b[:first_null]
-                trimmed = bytes[:first_null]
-            else:
-                trimmed = bytes
-
             decoded = trimmed.decode(encoding)
             return decoded
 
         #: Description. A free-text field up to 256 characters long.
-        self.description     = sanatize_bytes(unpacked[0])
+        self.description : str = sanitize_bytes(unpacked[0])
         #: Originator. Usually the name of the encoding application, sometimes
         #: a artist name.
-        self.originator      = sanatize_bytes(unpacked[1])
+        self.originator : str = sanitize_bytes(unpacked[1])
-        #: A unique identifer for the file, a serial number.
+        #: A unique identifier for the file, a serial number.
-        self.originator_ref  = sanatize_bytes(unpacked[2])
+        self.originator_ref : str = sanitize_bytes(unpacked[2])
         #: Date of the recording, in the format YYY-MM-DD
-        self.originator_date = sanatize_bytes(unpacked[3])
+        self.originator_date : str = sanitize_bytes(unpacked[3])
         #: Time of the recording, in the format HH:MM:SS.
-        self.originator_time = sanatize_bytes(unpacked[4])
+        self.originator_time : str = sanitize_bytes(unpacked[4])
         #: The sample offset of the start of the file relative to an
         #: epoch, usually midnight the day of the recording. 
-        self.time_reference  = unpacked[5]
+        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  = sanatize_bytes(bext_data[rest_starts:])
+        self.coding_history : str = sanitize_bytes(bext_data[rest_starts:])
         #: BEXT version. 
-        self.version         = unpacked[6]
+        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            = None
+        self.umid : Optional[bytes] = None
         #: EBU R128 Integrated loudness, in LUFS.
-        self.loudness_value          = None
+        self.loudness_value : Optional[float] = None
         #: EBU R128 Loudness rante, in LUFS.
-        self.loudness_range          = None
+        self.loudness_range : Optional[float] = None
         #: True peak level, in dBFS TP
-        self.max_true_peak           = None
+        self.max_true_peak : Optional[float] = None
         #: EBU R128 Maximum momentary loudness, in LUFS
-        self.max_momentary_loudness  = None
+        self.max_momentary_loudness : Optional[float] = None
         #: EBU R128 Maximum short-term loudness, in LUFS.
-        self.max_shortterm_loudness  = None
+        self.max_shortterm_loudness : Optional[float] = None
 
         if self.version > 0:
             self.umid = unpacked[7]
 
         if self.version > 1:
-            self.loudness_value          = unpacked[8] / 100.0
+            self.loudness_value = unpacked[8] / 100.0
-            self.loudness_range          = unpacked[9] / 100.0
+            self.loudness_range = unpacked[9] / 100.0
-            self.max_true_peak           = unpacked[10] / 100.0
+            self.max_true_peak = unpacked[10] / 100.0
-            self.max_momentary_loudness  = unpacked[11] / 100.0
+            self.max_momentary_loudness = unpacked[11] / 100.0
-            self.max_shortterm_loudness  = unpacked[12] / 100.0
+            self.max_shortterm_loudness = unpacked[12] / 100.0
-
 
     def to_dict(self):
-        return {'description':      self.description,
+        if self.umid is not None:
-                'originator':       self.originator,
+            umid_parsed = UMIDParser(self.umid)
-                'originator_ref':   self.originator_ref,
+            umid_str = umid_parsed.basic_umid_to_str()
-                'originator_date':  self.originator_date,
+        else:
-                'originator_time':  self.originator_time,
+            umid_str = None
-                'time_reference':   self.time_reference,
-                'version':          self.version,
-                'coding_history':   self.coding_history,
-                'loudness_value':   self.loudness_value,
-                'loudness_range':   self.loudness_range,
-                'max_true_peak':    self.max_true_peak,
-                'max_momentary_loudness':   self.max_momentary_loudness,
-                'max_shortterm_loudness':   self.max_shortterm_loudness
-                }
 
+        return {'description': self.description,
+                'originator': self.originator,
+                'originator_ref': self.originator_ref,
+                'originator_date': self.originator_date,
+                'originator_time': self.originator_time,
+                'time_reference': self.time_reference,
+                'version': self.version,
+                'umid': umid_str,
+                'coding_history': self.coding_history,
+                'loudness_value': self.loudness_value,
+                'loudness_range': self.loudness_range,
+                'max_true_peak': self.max_true_peak,
+                'max_momentary_loudness': self.max_momentary_loudness,
+                'max_shortterm_loudness': self.max_shortterm_loudness
+                }

wavinfo/wave_info_reader.py

@@ -1,6 +1,7 @@
-
 from .riff_parser import parse_chunk, ListChunkDescriptor
 
+from typing import Optional
+
 class WavInfoChunkReader:
 
     def __init__(self, f, encoding):
@@ -9,53 +10,47 @@ class WavInfoChunkReader:
         f.seek(0)
         parsed_chunks = parse_chunk(f)
 
-        list_chunks = [chunk for chunk in parsed_chunks.children \
+        list_chunks = [chunk for chunk in parsed_chunks.children if type(chunk) is ListChunkDescriptor]
-                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      = self._get_field(f,b'ICOP')
+        self.copyright : Optional[str] = self._get_field(f, b'ICOP')
         #: 'IPRD' Product
-        self.product        = self._get_field(f,b'IPRD')
+        self.product : Optional[str]= self._get_field(f, b'IPRD')
+        self.album : Optional[str] = self.product
         #: 'IGNR' Genre
-        self.genre          = self._get_field(f,b'IGNR')
+        self.genre : Optional[str] = self._get_field(f, b'IGNR')
         #: 'ISBJ' Supject
-        self.subject        = self._get_field(f,b'ISBJ')
+        self.subject : Optional[str] = self._get_field(f, b'ISBJ')
         #: 'IART' Artist, composer, author
-        self.artist         = self._get_field(f,b'IART')
+        self.artist : Optional[str] = self._get_field(f, b'IART')
         #: 'ICMT' Comment
-        self.comment        = self._get_field(f,b'ICMT')
+        self.comment : Optional[str] = self._get_field(f, b'ICMT')
         #: 'ISFT' Software, encoding application
-        self.software       = self._get_field(f,b'ISFT')
+        self.software : Optional[str] = self._get_field(f, b'ISFT')
         #: 'ICRD' Created date
-        self.created_date   = self._get_field(f,b'ICRD')
+        self.created_date : Optional[str] = self._get_field(f, b'ICRD')
         #: 'IENG' Engineer
-        self.engineer       = self._get_field(f,b'IENG')
+        self.engineer : Optional[str] = self._get_field(f, b'IENG')
         #: 'ITCH' Technician
-        self.technician     = self._get_field(f,b'ITCH')
+        self.technician : Optional[str] = self._get_field(f, b'ITCH')
         #: 'IKEY' Keywords, keyword list
-        self.keywords       = self._get_field(f,b'IKEY')
+        self.keywords : Optional[str] = self._get_field(f, b'IKEY')
         #: 'INAM' Name, title
-        self.title          = self._get_field(f,b'INAM')
+        self.title : Optional[str] = self._get_field(f, b'INAM')
         #: 'ISRC' Source
-        self.source         = self._get_field(f,b'ISRC')
+        self.source : Optional[str] = self._get_field(f, b'ISRC')
         #: 'TAPE' Tape
-        self.tape           = self._get_field(f,b'TAPE')
+        self.tape : Optional[str] = self._get_field(f, b'TAPE')
         #: 'IARL' Archival Location
-        self.archival_location = self._get_field(f,b'IARL')
+        self.archival_location : Optional[str] = self._get_field(f, b'IARL')
-        #: 'ISFT' Software
-        self.software       = self._get_field(f,b'ISFT')
         #: 'ICSM' Commissioned
-        self.commissioned   = 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]:
-    def _get_field(self, f, field_ident):
+        search = next(((chunk.start, chunk.length) for chunk in self.info_chunk.children if chunk.ident == field_ident),
-
+                      None)
-        search = next( ( (chunk.start, chunk.length) for chunk in self.info_chunk.children \
-                if chunk.ident == field_ident ), None)
 
         if search is not None:
             f.seek(search[0])
@@ -64,32 +59,30 @@ class WavInfoChunkReader:
         else:
             return None
 
-
     def to_dict(self):
         """
         A dictionary with all of the key/values read from the INFO scope.
         """
-        return {'copyright':    self.copyright,
+        return {'copyright': self.copyright,
-                'product':  self.product,
+                'product': self.product,
-                'genre':    self.genre,
+                'album': self.album,
-                'artist':   self.artist,
+                'genre': self.genre,
-                'comment':  self.comment,
+                'artist': self.artist,
+                'comment': self.comment,
                 'software': self.software,
                 'created_date': self.created_date,
                 'engineer': self.engineer,
                 'keywords': self.keywords,
-                'title':    self.title,
+                'title': self.title,
-                'source':   self.source,
+                'source': self.source,
-                'tape':     self.tape,
+                'tape': self.tape,
                 'commissioned': self.commissioned,
-                'software': self.software,
+                'archival_location': self.archival_location,
-                'archival_location':self.archival_location,
+                'subject': self.subject,
-                'subject':  self.subject,
+                'technician': self.technician
-                'technician':self.technician
                 }
 
-
+    def __repr__(self):
-
+        return_val = self.to_dict()
-
+        return_val.update({'encoding': self.encoding})
-
+        return str(return_val)
-

wavinfo/wave_ixml_reader.py

@@ -1,11 +1,11 @@
-#import xml.etree.ElementTree as ET
 from lxml import etree as ET
 import io
 from collections import namedtuple
-
+from typing import Optional
 
 IXMLTrack = namedtuple('IXMLTrack', ['channel_index', 'interleave_index', 'name', 'function'])
 
+
 class WavIXMLFormat:
     """
     iXML recorder metadata.
@@ -16,20 +16,16 @@ class WavIXMLFormat:
         :param xml: A bytes-like object containing the iXML payload.
         """
         self.source = xml
-        xmlBytes = io.BytesIO(xml)
+        xml_bytes = io.BytesIO(xml)
-        try:
+        parser = ET.XMLParser(recover=True)
-            parser = ET.XMLParser(recover=True)
+        self.parsed = ET.parse(xml_bytes, parser=parser)
-            self.parsed = ET.parse(xmlBytes, parser=parser)
-        except ET.ParseError as err:
-            print("Error parsing iXML: " + str(err))
-            decoded = xml.decode(encoding='utf_8_sig')
-            print(decoded)
-            self.parsed = ET.parse(io.StringIO(decoded))
 
-    def _get_text_value(self, xpath):
+    def _get_text_value(self, xpath) -> Optional[str]:
         e = self.parsed.find("./" + xpath)
         if e is not None:
             return e.text
+        else: 
+            return None
 
     @property
     def raw_xml(self):
@@ -52,35 +48,35 @@ class WavIXMLFormat:
                                 function=track.xpath('string(FUNCTION/text())'))
 
     @property
-    def project(self):
+    def project(self) -> Optional[str]:
         """
         The project/film name entered for the recording.
         """
         return self._get_text_value("PROJECT")
 
     @property
-    def scene(self):
+    def scene(self) -> Optional[str]:
         """
         Scene/slate.
         """
         return self._get_text_value("SCENE")
 
     @property
-    def take(self):
+    def take(self) ->  Optional[str]:
         """
         Take number.
         """
         return self._get_text_value("TAKE")
 
     @property
-    def tape(self):
+    def tape(self) -> Optional[str]:
         """
         Tape name.
         """
         return self._get_text_value("TAPE")
 
     @property
-    def family_uid(self):
+    def family_uid(self) -> Optional[str]:
         """
         The globally-unique ID for this file family. This may be in the format
         of a GUID, or an EBU Rec 9 source identifier, or some other dumb number.
@@ -88,10 +84,8 @@ class WavIXMLFormat:
         return self._get_text_value("FILE_SET/FAMILY_UID")
 
     @property
-    def family_name(self):
+    def family_name(self) -> Optional[str]:
         """
         The name of this file's file family.
         """
         return self._get_text_value("FILE_SET/FAMILY_NAME")
-
-

wavinfo/wave_reader.py

@@ -1,13 +1,9 @@
 #-*- coding: utf-8 -*-
 import struct
 import os
-import sys
 from collections import namedtuple
 
-if sys.version[0] == '3':
+import pathlib
-    import pathlib
-else:
-    import urlparse, urllib
 
 from .riff_parser import parse_chunk, ChunkDescriptor, ListChunkDescriptor
 from .wave_ixml_reader import WavIXMLFormat
@@ -15,12 +11,14 @@ from .wave_bext_reader import WavBextReader
 from .wave_info_reader import WavInfoChunkReader
 
 #: Calculated statistics about the audio data.
-WavDataDescriptor = namedtuple('WavDataDescriptor','byte_count frame_count')
+WavDataDescriptor = namedtuple('WavDataDescriptor', 'byte_count frame_count')
 
 #: The format of the audio samples.
-WavAudioFormat = namedtuple('WavAudioFormat','audio_format channel_count sample_rate byte_rate block_align bits_per_sample')
+WavAudioFormat = namedtuple('WavAudioFormat',
+                            'audio_format channel_count sample_rate byte_rate block_align bits_per_sample')
 
-class WavInfoReader():
+
+class WavInfoReader:
     """
     Parse a WAV audio file for metadata.
     """
@@ -29,66 +27,71 @@ class WavInfoReader():
         """
         Create a new reader object.
 
-        :param path: A filesystem path to the wav file you wish to probe.
+        :param path: 
+            A filesystem path to the wav file you wish to probe or a 
+            file handle to an open file.
 
-        :param info_encoding: The text encoding of the INFO metadata fields.
+        :param info_encoding: 
-          latin_1/Win CP1252 has always been a pretty good guess for this.
+            The text encoding of the INFO metadata fields.
+            latin_1/Win CP1252 has always been a pretty good guess for this.
 
-        :param bext_encoding: The text encoding to use when decoding the string
+        :param bext_encoding: 
-          fields of the Broadcast-WAV extension. Per EBU 3285 this is ASCII
+            The text encoding to use when decoding the string
-          but this parameter is available to you if you encounter a werido.
+            fields of the Broadcast-WAV extension. Per EBU 3285 this is ASCII
+            but this parameter is available to you if you encounter a weirdo.
         """
-        absolute_path = os.path.abspath(path)
+        
+        self.info_encoding = info_encoding
+        self.bext_encoding = bext_encoding
+        
+        if hasattr(path, 'read'):
+            self.get_wav_info(path)
+            self.url = 'about:blank'
+            self.path = repr(path)
+        else:
+            absolute_path = os.path.abspath(path)
 
-        if sys.version[0] == '3':
             #: `file://` url for the file.
             self.url = pathlib.Path(absolute_path).as_uri()
-        else:
-            self.url = urlparse.urljoin('file:', urllib.pathname2url(absolute_path))
 
-        with open(path, 'rb') as f:
+            # for __repr__()
-            chunks = parse_chunk(f)
+            self.path = absolute_path
+            
+            with open(path, 'rb') as f:
+                self.get_wav_info(f)
+            
+    def get_wav_info(self, wavfile):
+        chunks = parse_chunk(wavfile)
 
-            self.main_list = chunks.children
+        self.main_list = chunks.children
-            f.seek(0)
+        wavfile.seek(0)
 
-            #: :class:`wavinfo.wave_reader.WavAudioFormat`
+        #: :class:`wavinfo.wave_reader.WavAudioFormat`
-            self.fmt    = self._get_format(f)
+        self.fmt = self._get_format(wavfile)
 
-            #: :class:`wavinfo.wave_bext_reader.WavBextReader` with Broadcast-WAV metadata
+        #: :class:`wavinfo.wave_bext_reader.WavBextReader` with Broadcast-WAV metadata
-            self.bext   = self._get_bext(f, encoding=bext_encoding)
+        self.bext = self._get_bext(wavfile, encoding=self.bext_encoding)
 
-            #: :class:`wavinfo.wave_ixml_reader.WavIXMLFormat` with iXML metadata
+        #: :class:`wavinfo.wave_ixml_reader.WavIXMLFormat` with iXML metadata
-            self.ixml   = self._get_ixml(f)
+        self.ixml = self._get_ixml(wavfile)
 
-            #: :class:`wavinfo.wave_info_reader.WavInfoChunkReader` with RIFF INFO metadata
+        #: :class:`wavinfo.wave_info_reader.WavInfoChunkReader` with RIFF INFO metadata
-            self.info   = self._get_info(f, encoding=info_encoding)
+        self.info = self._get_info(wavfile, encoding=self.info_encoding)
-            self.data   = self._describe_data(f)
+        self.data = self._describe_data()
 
     def _find_chunk_data(self, ident, from_stream, default_none=False):
-        chunk_descriptor = None
+        top_chunks = (chunk for chunk in self.main_list if type(chunk) is ChunkDescriptor and chunk.ident == ident)
-        top_chunks = (chunk for chunk in self.main_list if type(chunk) is ChunkDescriptor)
+        chunk_descriptor = next(top_chunks, None) if default_none else next(top_chunks)
+        return chunk_descriptor.read_data(from_stream) if chunk_descriptor else None
 
-        if default_none:
+    def _describe_data(self):
-            chunk_descriptor = next((chunk for chunk in top_chunks if chunk.ident == ident),None)
-        else:
-            chunk_descriptor = next((chunk for chunk in top_chunks if chunk.ident == ident))
-
-        if chunk_descriptor:
-            return chunk_descriptor.read_data(from_stream)
-        else:
-            return None
-
-
-    def _describe_data(self,f):
         data_chunk = next(c for c in self.main_list if c.ident == b'data')
 
-        return WavDataDescriptor(byte_count= data_chunk.length,
+        return WavDataDescriptor(byte_count=data_chunk.length,
-                frame_count= int(data_chunk.length / self.fmt.block_align))
+                                 frame_count=int(data_chunk.length / self.fmt.block_align))
 
-
+    def _get_format(self, f):
-    def _get_format(self,f):
+        fmt_data = self._find_chunk_data(b'fmt ', f)
-        fmt_data = self._find_chunk_data(b'fmt ',f)
 
         # The format chunk is
         # audio_format    U16
@@ -102,42 +105,34 @@ class WavInfoReader():
 
         unpacked = struct.unpack(packstring, fmt_data[:rest_starts])
 
-        #0x0001	WAVE_FORMAT_PCM	PCM
+        # 0x0001	WAVE_FORMAT_PCM	PCM
-        #0x0003	WAVE_FORMAT_IEEE_FLOAT	IEEE float
+        # 0x0003	WAVE_FORMAT_IEEE_FLOAT	IEEE float
-        #0x0006	WAVE_FORMAT_ALAW	8-bit ITU-T G.711 A-law
+        # 0x0006	WAVE_FORMAT_ALAW	8-bit ITU-T G.711 A-law
-        #0x0007	WAVE_FORMAT_MULAW	8-bit ITU-T G.711 µ-law
+        # 0x0007	WAVE_FORMAT_MULAW	8-bit ITU-T G.711 µ-law
-        #0xFFFE	WAVE_FORMAT_EXTENSIBLE	Determined by SubFormat
+        # 0xFFFE	WAVE_FORMAT_EXTENSIBLE	Determined by SubFormat
 
-        #https://sno.phy.queensu.ca/~phil/exiftool/TagNames/RIFF.html
+        # https://sno.phy.queensu.ca/~phil/exiftool/TagNames/RIFF.html
-        return WavAudioFormat(audio_format = unpacked[0],
+        return WavAudioFormat(audio_format=unpacked[0],
-                    channel_count   = unpacked[1],
+                              channel_count=unpacked[1],
-                    sample_rate     = unpacked[2],
+                              sample_rate=unpacked[2],
-                    byte_rate       = unpacked[3],
+                              byte_rate=unpacked[3],
-                    block_align     = unpacked[4],
+                              block_align=unpacked[4],
-                    bits_per_sample = unpacked[5]
+                              bits_per_sample=unpacked[5]
-                    )
+                              )
 
     def _get_info(self, f, encoding):
-        finder = (chunk.signature for chunk in self.main_list \
+        finder = (chunk.signature for chunk in self.main_list if type(chunk) is ListChunkDescriptor)
-                if type(chunk) is ListChunkDescriptor)
 
         if b'INFO' in finder:
             return WavInfoChunkReader(f, encoding)
 
     def _get_bext(self, f, encoding):
-        bext_data = self._find_chunk_data(b'bext',f,default_none=True)
+        bext_data = self._find_chunk_data(b'bext', f, default_none=True)
-        if bext_data:
+        return WavBextReader(bext_data, encoding) if bext_data else None
-            return WavBextReader(bext_data, encoding)
-        else:
-            return None
 
-    def _get_ixml(self,f):
+    def _get_ixml(self, f):
-        ixml_data = self._find_chunk_data(b'iXML',f,default_none=True)
+        ixml_data = self._find_chunk_data(b'iXML', f, default_none=True)
-        if ixml_data is None:
+        return None if ixml_data is None else WavIXMLFormat(ixml_data.rstrip(b'\0'))
-            return None
-
-        ixml_string = ixml_data.rstrip(b'\0')
-        return WavIXMLFormat(ixml_string)
 
     def walk(self):
         """
@@ -147,13 +142,22 @@ class WavInfoReader():
         metadata field, and the value.
         """
 
-        scopes = ('fmt', 'data') #'bext', 'ixml', 'info')
+        scopes = ('fmt', 'data')  # 'bext', 'ixml', 'info')
 
         for scope in scopes:
             attr = self.__getattribute__(scope)
             for field in attr._fields:
                 yield scope, field, attr.__getattribute__(field)
 
-            bext_dict = self.bext.to_dict()
+            if self.bext is not None:
-            for key in bext_dict.keys():
+                bext_dict = (self.bext or {}).to_dict()
-                yield 'bext', key, bext_dict[key]
+                for key in bext_dict.keys():
+                    yield 'bext', key, bext_dict[key]
+
+            if self.info is not None:
+                info_dict = self.info.to_dict()
+                for key in info_dict.keys():
+                    yield 'info', key, info_dict[key]
+
+    def __repr__(self):
+        return 'WavInfoReader({}, {}, {})'.format(self.path, self.info_encoding, self.bext_encoding)