Update wave_info_reader.py

Added some more fields

.coveragerc

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

.travis.yml

@@ -1,13 +1,23 @@
 dist: xenial
 language: python
 python:
+#    - "2.7"
     - "3.6"
     - "3.5"
+    - "3.7"
 script:
-    - "python3 setup.py test"
+    - "gunzip tests/test_files/rf64/*.gz"
+    - "python setup.py test"
+#    - "py.test 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" 
+    - "sudo apt-get install -y ffmpeg"
+    - "pip install coverage"
+    - "pip install codecov"
+    - "pip install pytest-cov==2.5.0"
+#    - "pip install coverage==4.4"
 install:
-    - "pip3 install setuptools"
+    - "pip install setuptools"
+after_success:
+    - "codecov"

README.md

@@ -1,12 +1,12 @@
 [![Build Status](https://travis-ci.com/iluvcapra/wavinfo.svg?branch=master)](https://travis-ci.com/iluvcapra/wavinfo)
+[![codecov](https://codecov.io/gh/iluvcapra/wavinfo/branch/master/graph/badge.svg)](https://codecov.io/gh/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)
 
 
 # wavinfo
 
 
-The `wavinfo` package allows you to probe WAVE files and extract extended metadata, with an emphasis on 
+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. 
-production metadata. 
 
 `wavinfo` reads:
 
@@ -26,6 +26,7 @@ In progress:
 [ebu]:https://tech.ebu.ch/docs/tech/tech3285.pdf
 [smpte_330m2011]:http://standards.smpte.org/content/978-1-61482-678-1/st-330-2011/SEC1.abstract
 [ixml]:http://www.ixml.info
+[eburf64]:https://tech.ebu.ch/docs/tech/tech3306v1_1.pdf
 
 
 
@@ -52,104 +53,6 @@ The length of the file in frames (interleaved samples) and bytes is available, a
 >>> (48000, 2, 6, 24)
 ```
 
-### Broadcast WAV Extension
-
-A WAV file produced to Broadcast-WAV specifications will have the broadcast metadata extension,
-which includes a 256-character free text descrption, creating entity identifier (usually the 
-recording application or equipment), the date and time of recording and a time reference for 
-timecode synchronization.
-
-The `coding_history` is designed to contain a record of every conversion performed on the audio
-file.
-
-In this example (from a Sound Devices 702T) the bext metadata contains scene/take slating
-information in the `description`. Here also the `originator_ref` is a serial number conforming
-to EBU Rec 99.
-
-If the bext metadata conforms to EBU 3285 v1, it will contain the WAV's 32 or 64 byte SMPTE 
-330M UMID. The 32-byte version of the UMID is usually just a random number, while the 64-byte 
-UMID will also have information on the recording date and time, recording equipment and entity, 
-and geolocation data.
-
-If the bext metadata conforms to EBU 3285 v2, it will hold precomputed program loudness values
-as described by EBU Rec 128.
-
-```python
-print(info.bext.description)
-print("----------")
-print("Originator:", info.bext.originator)
-print("Originator Ref:", info.bext.originator_ref)
-print("Originator Date:", info.bext.originator_date)
-print("Originator Time:", info.bext.originator_time)
-print("Time Reference:", info.bext.time_reference)
-print(info.bext.coding_history)
-```
-
-    sSPEED=023.976-ND
-    sTAKE=1
-    sUBITS=$12311801
-    sSWVER=2.67
-    sPROJECT=BMH
-    sSCENE=A101
-    sFILENAME=A101_1.WAV
-    sTAPE=18Y12M31
-    sTRK1=MKH516 A
-    sTRK2=Boom
-    sNOTE=
-    
-    ----------
-    Originator: Sound Dev: 702T S#GR1112089007
-    Originator Ref: USSDVGR1112089007124001008206301
-    Originator Date: 2018-12-31
-    Originator Time: 12:40:00
-    Time Reference: 2190940753
-    A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch
 
 
 
-### iXML Production Recorder Metadata
-
-iXML allows an XML document to be embedded in a WAV file.
-
-The iXML website recommends a schema for recorder information but 
-there is no official DTD and vendors mostly do their own thing, apart from 
-hitting a few key xpaths. iXML is used by most location/production recorders 
-to save slating information, timecode and sync points in a reliable way.
-
-iXML is also used to link "families" of WAV files together, so WAV files
-recorded simultaneously or contiguously can be related by a receiving client.
-
-```python
-print("iXML Project:", info.ixml.project)
-print("iXML Scene:", info.ixml.scene)
-print("iXML Take:", info.ixml.take)
-print("iXML Tape:", info.ixml.tape)
-print("iXML File Family Name:", info.ixml.family_name)
-print("iXML File Family UID:", info.ixml.family_uid)
-```
-
-    iXML Project: BMH
-    iXML Scene: A101
-    iXML Take: 1
-    iXML Tape: 18Y12M31
-    iXML File Family Name: None
-    iXML File Family UID: USSDVGR1112089007124001008206300
-
-
-### INFO Metadata
-
-INFO Metadata is a standard method for saving tagged text data in a WAV or AVI
-file. INFO fields are often read by the file explorer and host OS, and used in 
-music library software.
-
-```python
-bullet_path = '../tests/test_files/BULLET Impact Plastic LCD TV Screen Shatter Debris 2x.wav'
-
-bullet = WavInfoReader(bullet_path)
-```
-
-    print("INFO Artist:",    bullet.info.artist)
-    print("INFO Copyright:", bullet.info.copyright)
-    print("INFO Comment:",   bullet.info.comment)
-
-

docs/Makefile

@@ -0,0 +1,19 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/conf.py

@@ -0,0 +1,184 @@
+# -*- coding: utf-8 -*-
+#
+# Configuration file for the Sphinx documentation builder.
+#
+# This file does only contain a selection of the most common options. For a
+# full list see the documentation:
+# http://www.sphinx-doc.org/en/master/config
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+sys.path.insert(0, os.path.abspath('..'))
+
+
+# -- Project information -----------------------------------------------------
+
+project = u'wavinfo'
+copyright = u'2019, 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'
+
+
+# -- General configuration ---------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.autodoc',
+    'sphinx.ext.todo',
+    'sphinx.ext.coverage',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = [u'_build', 'Thumbs.db', '.DS_Store']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = None
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_rtd_theme'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# Custom sidebar templates, must be a dictionary that maps document names
+# to template names.
+#
+# The default sidebars (for documents that don't match any pattern) are
+# defined by theme itself.  Builtin themes are using these templates by
+# default: ``['localtoc.html', 'relations.html', 'sourcelink.html',
+# 'searchbox.html']``.
+#
+# html_sidebars = {}
+
+
+# -- Options for HTMLHelp output ---------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'wavinfodoc'
+
+
+# -- Options for LaTeX output ------------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'wavinfo.tex', u'wavinfo Documentation',
+     u'Jamie Hardt', 'manual'),
+]
+
+
+# -- Options for manual page output ------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'wavinfo', u'wavinfo Documentation',
+     [author], 1)
+]
+
+
+# -- Options for Texinfo output ----------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'wavinfo', u'wavinfo Documentation',
+     author, 'wavinfo', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+# -- Options for Epub output -------------------------------------------------
+
+# Bibliographic Dublin Core info.
+epub_title = project
+
+# The unique identifier of the text. This can be a ISBN number
+# or the project homepage.
+#
+# epub_identifier = ''
+
+# A unique identification for the text.
+#
+# epub_uid = ''
+
+# A list of files that should not be packed into the epub file.
+epub_exclude_files = ['search.html']
+
+
+# -- Extension configuration -------------------------------------------------
+
+# -- Options for todo extension ----------------------------------------------
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = True

docs/index.rst

@@ -0,0 +1,40 @@
+.. wavinfo documentation master file, created by
+   sphinx-quickstart on Thu Jan  3 17:09:28 2019.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to wavinfo's documentation!
+===================================
+
+
+.. module:: wavinfo
+
+.. autoclass:: WavInfoReader
+   :members:
+
+   .. automethod:: __init__
+   
+
+.. autoclass:: wavinfo.wave_reader.WavAudioFormat
+   :members:
+
+.. autoclass:: wavinfo.wave_reader.WavDataDescriptor
+   :members:
+
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Notes:
+   
+   metadata_scopes/bext.rst
+   metadata_scopes/ixml.rst
+   metadata_scopes/info.rst
+
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

docs/make.bat

@@ -0,0 +1,35 @@
+@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/metadata_scopes/bext.rst

@@ -0,0 +1,65 @@
+Broadcast WAV Extension
+=======================
+
+.. module:: wavinfo
+
+.. autoclass:: wavinfo.wave_bext_reader.WavBextReader
+   :members:
+
+
+Notes
+-----
+A WAV file produced to Broadcast-WAV specifications will have the broadcast metadata extension,
+which includes a 256-character free text descrption, creating entity identifier (usually the 
+recording application or equipment), the date and time of recording and a time reference for 
+timecode synchronization.
+
+The `coding_history` is designed to contain a record of every conversion performed on the audio
+file.
+
+In this example (from a Sound Devices 702T) the bext metadata contains scene/take slating
+information in the `description`. Here also the `originator_ref` is a serial number conforming
+to EBU Rec 99.
+
+If the bext metadata conforms to EBU 3285 v1, it will contain the WAV's 32 or 64 byte SMPTE 
+330M UMID. The 32-byte version of the UMID is usually just a random number, while the 64-byte 
+UMID will also have information on the recording date and time, recording equipment and entity, 
+and geolocation data.
+
+If the bext metadata conforms to EBU 3285 v2, it will hold precomputed program loudness values
+as described by EBU Rec 128.
+
+..  code:: python
+
+    print(info.bext.description)
+    print("----------")
+    print("Originator:", info.bext.originator)
+    print("Originator Ref:", info.bext.originator_ref)
+    print("Originator Date:", info.bext.originator_date)
+    print("Originator Time:", info.bext.originator_time)
+    print("Time Reference:", info.bext.time_reference)
+    print(info.bext.coding_history)
+
+Result: 
+
+::
+
+    sSPEED=023.976-ND
+    sTAKE=1
+    sUBITS=$12311801
+    sSWVER=2.67
+    sPROJECT=BMH
+    sSCENE=A101
+    sFILENAME=A101_1.WAV
+    sTAPE=18Y12M31
+    sTRK1=MKH516 A
+    sTRK2=Boom
+    sNOTE=
+    
+    ----------
+    Originator: Sound Dev: 702T S#GR1112089007
+    Originator Ref: USSDVGR1112089007124001008206301
+    Originator Date: 2018-12-31
+    Originator Time: 12:40:00
+    Time Reference: 2190940753
+    A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch

docs/metadata_scopes/info.rst

@@ -0,0 +1,32 @@
+INFO Metadata
+=============
+
+
+.. module:: wavinfo
+
+.. autoclass:: wavinfo.wave_info_reader.WavInfoChunkReader
+   :members:
+
+
+
+Notes
+-----
+
+INFO Metadata is a standard method for saving tagged text data in a WAV or AVI
+file. INFO fields are often read by the file explorer and host OS, and used in 
+music library software.
+
+
+..  code:: python
+
+    bullet_path = '../tests/test_files/BULLET Impact Plastic LCD TV Screen Shatter Debris 2x.wav'
+
+    bullet = WavInfoReader(bullet_path)
+
+    print("INFO Artist:",    bullet.info.artist)
+    print("INFO Copyright:", bullet.info.copyright)
+    print("INFO Comment:",   bullet.info.comment)
+
+
+
+

docs/metadata_scopes/ixml.rst

@@ -0,0 +1,44 @@
+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.
+
+The iXML website recommends a schema for recorder information but 
+there is no official DTD and vendors mostly do their own thing, apart from 
+hitting a few key xpaths. iXML is used by most location/production recorders 
+to save slating information, timecode and sync points in a reliable way.
+
+iXML is also used to link "families" of WAV files together, so WAV files
+recorded simultaneously or contiguously can be related by a receiving client.
+
+..  code:: python
+
+    print("iXML Project:", info.ixml.project)
+    print("iXML Scene:", info.ixml.scene)
+    print("iXML Take:", info.ixml.take)
+    print("iXML Tape:", info.ixml.tape)
+    print("iXML File Family Name:", info.ixml.family_name)
+    print("iXML File Family UID:", info.ixml.family_uid)
+
+Result:
+
+::
+
+    iXML Project: BMH
+    iXML Scene: A101
+    iXML Take: 1
+    iXML Tape: 18Y12M31
+    iXML File Family Name: None
+    iXML File Family UID: USSDVGR1112089007124001008206300
+
+
+

setup.py

@@ -4,10 +4,10 @@ with open("README.md", "r") as fh:
     long_description = fh.read()
 
 setup(name='wavinfo',
-      version='1.0',
+      version='1.2',
       author='Jamie Hardt',
       author_email='jamiehardt@me.com',
-      description='WAVE sound file metadata parser.',
+      description='Probe WAVE Files for iXML, Broadcast-WAVE and other metadata.',
       long_description_content_type="text/markdown",
       long_description=long_description,
       url='https://github.com/iluvcapra/wavinfo',
@@ -16,5 +16,8 @@ setup(name='wavinfo',
           'Topic :: Multimedia',
 	  'Topic :: Multimedia :: Sound/Audio',
           "Programming Language :: Python :: 3.5",
-          "Programming Language :: Python :: 3.6"],
+          "Programming Language :: Python :: 3.6",
-      packages=['wavinfo'])
+          "Programming Language :: Python :: 3.7"],
+      packages=['wavinfo'],
+      install_requires=['lxml']
+      )

tests/__init__.py

@@ -1,2 +1,3 @@
 from . import test_wave_parsing
 
+

tests/test_wave_parsing.py

@@ -1,46 +1,20 @@
 import os.path
-import json
+import sys
-import subprocess
-from subprocess import PIPE
 
 from unittest import TestCase
 
+from .utils import all_files, ffprobe
+
 import wavinfo
-
+        
-FFPROBE='ffprobe'
-
-
-def ffprobe(path):
-
-    arguments = [ FFPROBE , "-of", "json" , "-show_format", "-show_streams", path ]
-
-    process = subprocess.run(arguments, stdin=None, stdout=PIPE, stderr=PIPE)
-
-    if process.returncode == 0:
-        output_str = process.stdout.decode('utf-8')
-        return json.loads(output_str)
-    else:
-        return None
-
-
 class TestWaveInfo(TestCase):
-
-
-    def all_files(self):
-        for dirpath, dirnames, filenames in os.walk('tests/test_files'):
-            for filename in filenames:
-                name, ext = os.path.splitext(filename)
-                if ext in ['.wav','.WAV']:
-                    yield os.path.join(dirpath, filename)
-
-
     def test_sanity(self):
-        for wav_file in self.all_files():
+        for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
             self.assertTrue(info is not None)
 
     def test_fmt_against_ffprobe(self):
-        for wav_file in self.all_files():
+        for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
 
@@ -56,33 +30,40 @@ class TestWaveInfo(TestCase):
                 self.assertEqual( info.fmt.byte_rate     , byte_rate  )
 
     def test_data_against_ffprobe(self):
-        for wav_file in self.all_files():
+        for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
-
             self.assertEqual( info.data.frame_count, int(ffprobe_info['streams'][0]['duration_ts'] ))
 
     def test_bext_against_ffprobe(self):
-        for wav_file in self.all_files():
+        for wav_file in all_files():
             info = wavinfo.WavInfoReader(wav_file)
             ffprobe_info = ffprobe(wav_file)
+            if info.bext:
+                if 'comment' in ffprobe_info['format']['tags']:
+                    self.assertEqual( info.bext.description, ffprobe_info['format']['tags']['comment']  )
+                else: 
+                    self.assertEqual( info.bext.description , '')
+                
+                if 'encoded_by' in ffprobe_info['format']['tags']:
+                    self.assertEqual( info.bext.originator, ffprobe_info['format']['tags']['encoded_by']  )
+                else:
+                    self.assertEqual( info.bext.originator, '')
+                    
+                if 'originator_reference' in ffprobe_info['format']['tags']:
+                    self.assertEqual( info.bext.originator_ref, ffprobe_info['format']['tags']['originator_reference']  )
+                else:
+                    self.assertEqual( info.bext.originator_ref, '')
 
-            self.assertEqual( info.bext.description, ffprobe_info['format']['tags']['comment']  )
+                # these don't always reflect the bext info
-            self.assertEqual( info.bext.originator, ffprobe_info['format']['tags']['encoded_by']  )
+                # self.assertEqual( info.bext.originator_date, ffprobe_info['format']['tags']['date']  )
-            if 'originator_reference' in ffprobe_info['format']['tags']:
+                # self.assertEqual( info.bext.originator_time, ffprobe_info['format']['tags']['creation_time']  )
-                self.assertEqual( info.bext.originator_ref, ffprobe_info['format']['tags']['originator_reference']  )
+                self.assertEqual( info.bext.time_reference, int(ffprobe_info['format']['tags']['time_reference'])  )
-            else:
-                self.assertEqual( info.bext.originator_ref, '')
 
-            # these don't always reflect the bext info
+                if 'coding_history' in ffprobe_info['format']['tags']:
-            # self.assertEqual( info.bext.originator_date, ffprobe_info['format']['tags']['date']  )
+                    self.assertEqual( info.bext.coding_history, ffprobe_info['format']['tags']['coding_history']  )
-            # self.assertEqual( info.bext.originator_time, ffprobe_info['format']['tags']['creation_time']  )
+                else:
-            self.assertEqual( info.bext.time_reference, int(ffprobe_info['format']['tags']['time_reference'])  )
+                    self.assertEqual( info.bext.coding_history, '' )
-
-            if 'coding_history' in ffprobe_info['format']['tags']:
-                self.assertEqual( info.bext.coding_history, ffprobe_info['format']['tags']['coding_history']  )
-            else:
-                self.assertEqual( info.bext.coding_history, '' )
 
     def test_ixml(self):
         expected = {'A101_4.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '4',
@@ -95,7 +76,7 @@ class TestWaveInfo(TestCase):
                         'tape': '18Y12M31', 'family_uid': 'USSDVGR1112089007124001008206300'},
                 }
 
-        for wav_file in self.all_files():
+        for wav_file in all_files():
             basename =  os.path.basename(wav_file)
             if basename in expected:
                 info = wavinfo.WavInfoReader(wav_file)

tests/test_zoom_f8.py

@@ -0,0 +1,12 @@
+import os.path
+import sys
+import json
+import subprocess
+from subprocess import PIPE
+
+from unittest import TestCase
+
+import wavinfo
+
+class TestZoomF8(TestCase):
+    pass

tests/utils.py

@@ -0,0 +1,39 @@
+import os.path
+import sys
+import subprocess
+from subprocess import PIPE
+import json
+
+FFPROBE='ffprobe'
+
+def ffprobe(path):
+    arguments = [ FFPROBE , "-of", "json" , "-show_format", "-show_streams", path ]
+    if int(sys.version[0]) <  3:
+        process = subprocess.Popen(arguments, stdout=PIPE)
+        process.wait()
+        if process.returncode == 0:
+            output = process.communicate()[0]
+            if output:
+                output_str = output.decode('utf-8')
+                return json.loads(output_str)
+        else:
+            return None
+    else: 
+        process = subprocess.run(arguments, stdin=None, stdout=PIPE, stderr=PIPE)
+        if process.returncode == 0:
+            output_str = process.stdout.decode('utf-8')
+            return json.loads(output_str)
+        else:
+            return None
+
+
+        
+def all_files():
+    for dirpath, _, filenames in os.walk('tests/test_files'):
+        for filename in filenames:
+            _, ext = os.path.splitext(filename)
+            if ext in ['.wav','.WAV']:
+                yield os.path.join(dirpath, filename)
+
+
+

wavinfo/__init__.py

@@ -1,4 +1,14 @@
+# -*- coding: utf-8 -*-
+
+# :module:`wavinfo` provides methods to probe a WAV file for
+# various kinds of production metadata.
+#
+#
+#
+#
+
+
 from .wave_reader import WavInfoReader
 
-__version__ = 1.0
+__version__ = '1.1'
 __author__ = 'Jamie Hardt'

wavinfo/rf64_parser.py

@@ -0,0 +1,40 @@
+import struct
+from collections import namedtuple
+from . import riff_parser 
+
+RF64Context = namedtuple('RF64Context','sample_count bigchunk_table')
+
+
+def parse_rf64(stream):
+    #print("starting parse_rf64")
+    start = stream.tell()
+    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))
+    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)
+
+    for n in range(length_lookup_table):
+        bigname, bigsize = struct.unpack_from( chunksize64format , ds64data, offset= ds64_fields_size ) 
+        bigchunk_table[bigname] = bigsize
+
+    bigchunk_table[b'data'] = data_size
+    bigchunk_table[b'RF64'] = riff_size
+ 
+    stream.seek(start, 0)
+    #print("returning from parse_rf64, context: ",RF64Context( sample_count=sample_count, bigchunk_table=bigchunk_table ) )
+    return RF64Context( sample_count=sample_count, bigchunk_table=bigchunk_table )
+    

wavinfo/riff_parser.py

@@ -1,7 +1,8 @@
 
 import struct
-
+import pdb
 from collections import namedtuple
+from .rf64_parser import parse_rf64
 
 class ListChunkDescriptor(namedtuple('ListChunkDescriptor' , 'signature children')):
 
@@ -18,42 +19,52 @@ class ListChunkDescriptor(namedtuple('ListChunkDescriptor' , 'signature children
                             return chunk
 
 
-class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length') ):
+class ChunkDescriptor(namedtuple('ChunkDescriptor', 'ident start length rf64_context') ):
     def read_data(self, from_stream):
         from_stream.seek(self.start)
         return from_stream.read(self.length)
 
-def parse_list_chunk(stream, length):
+def parse_list_chunk(stream, length, rf64_context =None):
     start = stream.tell()
 
     signature = stream.read(4)
 
+    #print("Parsing list chunk with siganture: ", signature)
     children = []
     while (stream.tell() - start) < length:
-        children.append(parse_chunk(stream))
+        child_chunk = parse_chunk(stream, rf64_context= rf64_context)
+        if child_chunk:
+             children.append(child_chunk)
+        else: 
+             break
 
     return ListChunkDescriptor(signature=signature, children=children)
 
-def parse_chunk(stream):
+def parse_chunk(stream, rf64_context=None):
     ident = stream.read(4)
     if len(ident) != 4:
         return
 
     sizeb = stream.read(4)
     size  = struct.unpack('<I',sizeb)[0]
-
+    
+    if size == 0xFFFFFFFF:
+        if rf64_context is None and ident == b'RF64':
+            rf64_context = parse_rf64(stream=stream)
+        
+        size = rf64_context.bigchunk_table[ident] 
+            
     displacement = size
     if displacement % 2 is not 0:
         displacement = displacement + 1
 
-    if ident in [b'RIFF',b'LIST']:
+    if ident in [b'RIFF',b'LIST', b'RF64']:
-        return parse_list_chunk(stream=stream, length=size)
+        #print("Parsing list chunk with ident: ", ident)
+        return parse_list_chunk(stream=stream, length=size, rf64_context=rf64_context)
     else:
         start = stream.tell()
         stream.seek(displacement,1)
-        return ChunkDescriptor(ident=ident, start=start, length=size)
+        #print("Parsing chunk with start=%i, ident=%s" % (start, ident))
-
+        return ChunkDescriptor(ident=ident, start=start, length=size, rf64_context=rf64_context)
-
-
 
 

wavinfo/wave_bext_reader.py

@@ -2,31 +2,12 @@ import struct
 
 class WavBextReader:
     def __init__(self,bext_data,encoding):
-        # description[256]
+        """
-
+        Read Broadcast-WAV extended metadata.
-        # originator[32]
+        :param best_data: The bytes-like data.
-        # originatorref[32]
+        "param encoding: The encoding to use when decoding the text fields of the
-        # originatordate[10]   "YYYY:MM:DD"
+                 BEXT metadata scope. According to EBU Rec 3285 this shall be ASCII.
-        # originatortime[8]    "HH:MM:SS"
+        """
-        # lowtimeref U32
-        # hightimeref U32
-        # version U16
-        #
-        # V1 field
-        # umid[64]
-        #
-        # V2 fields
-        # loudnessvalue S16    (in LUFS*100)
-        # loudnessrange S16    (in LUFS*100)
-        # maxtruepeak   S16    (in dbTB*100)
-        # maxmomentaryloudness S16 (LUFS*100)
-        # maxshorttermloudness S16 (LUFS*100)
-        #
-        # reserved[180]
-        # codinghistory []
-        if bext_data is None:
-            return None
-
         packstring = "<256s"+ "32s" + "32s" + "10s" + "8s" + "QH" + "64s" + "hhhhh" + "180s"
 
         rest_starts = struct.calcsize(packstring)
@@ -42,20 +23,38 @@ class WavBextReader:
             decoded = trimmed.decode(encoding)
             return decoded
 
+        #: Description. A free-text field up to 256 characters long.
         self.description     = sanatize_bytes(unpacked[0])
+        #: Originator. Usually the name of the encoding application, sometimes
+        #: a artist name.
         self.originator      = sanatize_bytes(unpacked[1])
+        #: A unique identifer for the file, a serial number.
         self.originator_ref  = sanatize_bytes(unpacked[2])
+        #: Date of the recording, in the format YYY-MM-DD
         self.originator_date = sanatize_bytes(unpacked[3])
+        #: Time of the recording, in the format HH:MM:SS.
         self.originator_time = sanatize_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.version         = unpacked[6]
+        #: A variable-length text field containing a list of processes and
-        self.umid            = None
+        #: and conversions performed on the file.
-        self.loudness_value          = None
-        self.loudness_range          = None
-        self.max_true_peak           = None
-        self.max_momentary_loudness  = None
-        self.max_shortterm_loudness  = None
         self.coding_history  = sanatize_bytes(bext_data[rest_starts:])
+        #: BEXT version. 
+        self.version         = 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
+        #: EBU R128 Integrated loudness, in LUFS.
+        self.loudness_value          = None
+        #: EBU R128 Loudness rante, in LUFS.
+        self.loudness_range          = None
+        #: True peak level, in dBFS TP
+        self.max_true_peak           = None
+        #: EBU R128 Maximum momentary loudness, in LUFS
+        self.max_momentary_loudness  = None
+        #: EBU R128 Maximum short-term loudness, in LUFS.
+        self.max_shortterm_loudness  = None
 
         if self.version > 0:
             self.umid = unpacked[7]

wavinfo/wave_info_reader.py

@@ -14,19 +14,42 @@ class WavInfoChunkReader:
 
         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')
+        #: 'IPRD' Product
         self.product        = self._get_field(f,b'IPRD')
+        #: 'IGNR' Genre
         self.genre          = self._get_field(f,b'IGNR')
+        #: 'ISBJ' Supject
+        self.subject        = self._get_field(f,b'ISBJ')
+        #: 'IART' Artist, composer, author
         self.artist         = self._get_field(f,b'IART')
+        #: 'ICMT' Comment
         self.comment        = self._get_field(f,b'ICMT')
+        #: 'ISFT' Software, encoding application
         self.software       = self._get_field(f,b'ISFT')
+        #: 'ICRD' Created date
         self.created_date   = self._get_field(f,b'ICRD')
+        #: 'IENG' Engineer
         self.engineer       = self._get_field(f,b'IENG')
+        #: 'ITCH' Technician
+        self.technician     = self._get_field(f,b'ITCH')
+        #: 'IKEY' Keywords, keyword list
         self.keywords       = self._get_field(f,b'IKEY')
+        #: 'INAM' Name, title
         self.title          = self._get_field(f,b'INAM')
+        #: 'ISRC' Source
         self.source         = self._get_field(f,b'ISRC')
+        #: 'TAPE' Tape
         self.tape           = self._get_field(f,b'TAPE')
+        #: 'IARL' Archival Location
+        self.archival_location = 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')
+        
 
 
     def _get_field(self, f, field_ident):
@@ -43,6 +66,9 @@ class WavInfoChunkReader:
 
 
     def to_dict(self):
+        """
+        A dictionary with all of the key/values read from the INFO scope.
+        """
         return {'copyright':    self.copyright,
                 'product':  self.product,
                 'genre':    self.genre,
@@ -54,7 +80,12 @@ class WavInfoChunkReader:
                 'keywords': self.keywords,
                 'title':    self.title,
                 'source':   self.source,
-                'tape':     self.tape
+                'tape':     self.tape,
+                'commissioned': self.commissioned,
+                'software': self.software,
+                'archival_location':self.archival_location,
+                'subject':  self.subject,
+                'technician':self.technician
                 }
 
 

wavinfo/wave_ixml_reader.py

@@ -1,14 +1,26 @@
-import xml.etree.ElementTree as ET
+#import xml.etree.ElementTree as ET
+from lxml import etree as ET
 import io
 
 class WavIXMLFormat:
     """
-    iXML recorder metadata, as defined by iXML 2.0
+    iXML recorder metadata.
     """
     def __init__(self, xml):
+        """
+        Parse iXML.
+        :param xml: A bytes-like object containing the iXML payload.
+        """
         self.source = xml
         xmlBytes = io.BytesIO(xml)
-        self.parsed = ET.parse(xmlBytes)
+        try:
+            parser = ET.XMLParser(recover=True)
+            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):
         e = self.parsed.find("./" + xpath)
@@ -17,26 +29,45 @@ class WavIXMLFormat:
 
     @property
     def project(self):
+        """
+        The project/film name entered for the recording.
+        """
         return self._get_text_value("PROJECT")
 
     @property
     def scene(self):
+        """
+        Scene/slate.
+        """
         return self._get_text_value("SCENE")
 
     @property
     def take(self):
+        """
+        Take number.
+        """
         return self._get_text_value("TAKE")
 
     @property
     def tape(self):
+        """
+        Tape name.
+        """
         return self._get_text_value("TAPE")
 
     @property
     def family_uid(self):
+        """
+        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.
+        """
         return self._get_text_value("FILE_SET/FAMILY_UID")
 
     @property
     def family_name(self):
+        """
+        The name of this file's file family.
+        """
         return self._get_text_value("FILE_SET/FAMILY_NAME")
 
 

wavinfo/wave_reader.py

@@ -1,52 +1,67 @@
+#-*- coding: utf-8 -*-
 import struct
-
+import os
+import sys
 from collections import namedtuple
 
+if sys.version[0] == '3':
+    import pathlib
+else:
+    import urlparse, urllib
+
 from .riff_parser import parse_chunk, ChunkDescriptor, ListChunkDescriptor
 from .wave_ixml_reader import WavIXMLFormat
 from .wave_bext_reader import WavBextReader
 from .wave_info_reader import WavInfoChunkReader
 
+#: Calculated statistics about the audio data.
 WavDataDescriptor = namedtuple('WavDataDescriptor','byte_count frame_count')
 
-WavInfoFormat = namedtuple("WavInfoFormat",'audio_format channel_count sample_rate byte_rate block_align bits_per_sample')
+#: The format of the audio samples.
-
+WavAudioFormat = namedtuple('WavAudioFormat','audio_format channel_count sample_rate byte_rate block_align bits_per_sample')
-WavBextFormat = namedtuple("WavBextFormat",'description originator originator_ref ' +
-    'originator_date originator_time time_reference version umid ' +
-    'loudness_value loudness_range max_true_peak max_momentary_loudness max_shortterm_loudness ' +
-    'coding_history')
-
 
 class WavInfoReader():
     """
-    format : WAV format
+    Parse a WAV audio file for metadata.
-    bext   : The Broadcast-WAV extension as definied by EBU Tech 3285 v2 (2011)
-
     """
 
     def __init__(self, path, info_encoding='latin_1', bext_encoding='ascii'):
         """
-        Parse a WAV audio file for metadata.
+        Create a new reader object.
 
-        * `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.
 
-        * `info_encoding`: The text encoding of the INFO metadata fields.
+        :param info_encoding: The text encoding of the INFO metadata fields.
-          `latin_1`/Win CP1252 has always been a pretty good guess for this.
+          latin_1/Win CP1252 has always been a pretty good guess for this.
 
-        * `bext_encoding`: The text encoding to use when decoding the string
+        :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 werido.
-
         """
+        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:
             chunks = parse_chunk(f)
 
             self.main_list = chunks.children
             f.seek(0)
 
+            #: :class:`wavinfo.wave_reader.WavAudioFormat`
             self.fmt    = self._get_format(f)
+
+            #: :class:`wavinfo.wave_bext_reader.WavBextReader` with Broadcast-WAV metadata
             self.bext   = self._get_bext(f, encoding=bext_encoding)
+
+            #: :class:`wavinfo.wave_ixml_reader.WavIXMLFormat` with iXML metadata
             self.ixml   = self._get_ixml(f)
+
+            #: :class:`wavinfo.wave_info_reader.WavInfoChunkReader` with RIFF INFO metadata
             self.info   = self._get_info(f, encoding=info_encoding)
             self.data   = self._describe_data(f)
 
@@ -94,7 +109,7 @@ class WavInfoReader():
         #0xFFFE	WAVE_FORMAT_EXTENSIBLE	Determined by SubFormat
 
         #https://sno.phy.queensu.ca/~phil/exiftool/TagNames/RIFF.html
-        return WavInfoFormat(audio_format = unpacked[0],
+        return WavAudioFormat(audio_format = unpacked[0],
                     channel_count   = unpacked[1],
                     sample_rate     = unpacked[2],
                     byte_rate       = unpacked[3],
@@ -111,17 +126,30 @@ class WavInfoReader():
 
     def _get_bext(self, f, encoding):
         bext_data = self._find_chunk_data(b'bext',f,default_none=True)
-        return WavBextReader(bext_data, encoding)
+        if bext_data:
+            return WavBextReader(bext_data, encoding)
+        else:
+            return None
 
     def _get_ixml(self,f):
         ixml_data = self._find_chunk_data(b'iXML',f,default_none=True)
         if ixml_data is None:
             return None
 
-        ixml_string = ixml_data
+        ixml_string = ixml_data.rstrip(b'\0')
         return WavIXMLFormat(ixml_string)
 
+    def walk(self):
+        """
+        Walk all of the available metadata fields.
 
+        :yields: a string, the :scope: of the metadatum, the string :name: of the
+        metadata field, and the value.
+        """
 
+        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)