Merge branch 'feature-smpl' into maint-poetry

Now reads from command line and WavInfoReader interface.

.gitignore

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

docs/source/references.rst

@@ -36,6 +36,11 @@ iXML
 * `Gallery Software iXML Specification <http://www.gallery.co.uk/ixml/>`_
 
 
+Sampler Metadata
+----------------
+
+* `RecordingBlogs.com — Sample chunk (of a Wave file)<https://www.recordingblogs.com/wiki/sample-chunk-of-a-wave-file>`_
+
 RIFF Metadata
 -------------
 * `1991. Multimedia Programming Interface and Data Specifications 1.0 <https://www.aelius.com/njh/wavemetatools/doc/riffmci.pdf>`_

examples/demo.ipynb

@@ -46,6 +46,7 @@
     "  * `adm`: EBU Audio Defintion Model metadata, as used by Dolby Atmos.\n",
     "  * `cues`: Cue marker metadata, including labels and notes \n",
     "  * `dolby`: Dolby recorder and playback metadata\n",
+    "  * `smpl`: Sampler midi note and loop metadata\n",
     "\n",
     "Each of these is an attribute of a `WavInfoReader` object.\n",
     "\n",
@@ -304,7 +305,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.12.5"
   }
  },
  "nbformat": 4,

pyproject.toml

@@ -1,13 +1,16 @@
-[build-system]
+# https://python-poetry.org/docs/pyproject/
-requires = ["flit_core >=3.2,<4"]
-build-backend = "flit_core.buildapi"
 
-[project]
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry]
 name = "wavinfo"
-authors = [{name = "Jamie Hardt", email = "jamiehardt@me.com"}]
+version = "3.0.1"
+description = "Probe WAVE files for all metadata"
+authors = ["Jamie Hardt <jamiehardt@me.com>"]
+license = "MIT" 
 readme = "README.md"
-dynamic = ["version", "description"]
-requires-python = "~=3.8"
 classifiers = [
     'Development Status :: 5 - Production/Stable',
     'License :: OSI Approved :: MIT License',
@@ -20,9 +23,10 @@ classifiers = [
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13"
 ]
-dependencies = [
+homepage = "https://github.com/iluvcapra/wavinfo"
-    "lxml ~= 5.3.0"
+repository = "https://github.com/iluvcapra/wavinfo.git"
-]
+documentation = "https://wavinfo.readthedocs.io/"
+urls.Tracker = 'https://github.com/iluvcapra/wavinfo/issues' 
 keywords = [
     'waveform', 
     'metadata', 
@@ -35,29 +39,17 @@ keywords = [
     'broadcast' 
 ]
 
-[tool.flit.module]
+[tool.poetry.extras]
-name = "wavinfo"
+doc = ['sphinx', 'sphinx_rtd_theme']
 
-[project.optional-dependencies]
+[tool.poetry.scripts]
-doc = [
-    'sphinx >= 5.3.0',
-    'sphinx_rtd_theme >= 1.1.1',
-]
-
-[project.urls]
-Home = "https://github.com/iluvcapra/wavinfo"
-Documentation = "https://wavinfo.readthedocs.io/"
-Source = "https://github.com/iluvcapra/wavinfo.git"
-Issues = 'https://github.com/iluvcapra/wavinfo/issues' 
-
-[project.entry_points.console_scripts]
 wavinfo = 'wavinfo.__main__:main'
 
-[project.scripts]
+[tool.poetry.dependencies]
-wavinfo = "wavinfo.__main__:main"
+python = "^3.8"
-
+lxml = "~= 5.3.0"
-[tool.flit.external-data]
+sphinx_rtd_theme = {version= '>= 1.1.1', optional=true}
-directory = "data"
+sphinx = {version= '>= 5.3.0', optional=true}
 
 [tool.pyright]
 typeCheckingMode = "basic"

tests/test_smpl.py

@@ -0,0 +1,15 @@
+from unittest import TestCase
+from glob import glob
+
+import wavinfo
+
+class TestSmpl(TestCase):
+    def setUp(self) -> None:
+        self.test_files = glob("tests/test_files/smpl/*.wav")
+        return super().setUp()
+
+    def test_each(self):
+        for file in self.test_files:
+            w = wavinfo.WavInfoReader(file)
+            d = w.walk()
+            self.assertIsNotNone(d)

wavinfo/__init__.py

@@ -4,6 +4,3 @@ Probe WAVE Files for iXML, Broadcast-WAVE and other metadata.
 
 from .wave_reader import WavInfoReader
 from .riff_parser import WavInfoEOFError
-
-__version__ = '3.0.0'
-__short_version__ = '3.0.0'

wavinfo/__main__.py

@@ -1,17 +1,21 @@
-import datetime
 from . import WavInfoReader
-from . import __version__
 
+import datetime
 from optparse import OptionParser
 import sys
+import os
 import json
 from enum import Enum
+import importlib.metadata
+from base64 import b64encode
 
 
 class MyJSONEncoder(json.JSONEncoder):
     def default(self, o):
         if isinstance(o, Enum):
             return o._name_
+        elif isinstance(o, bytes):
+            return b64encode(o).decode('ascii')
         else:
             return super().default(o)
 
@@ -21,10 +25,22 @@ class MissingDataError(RuntimeError):
 
 
 def main():
+    version = importlib.metadata.version('wavinfo')
+    manpath = os.path.dirname(__file__) + "/man"
     parser = OptionParser()
 
     parser.usage = 'wavinfo (--adm | --ixml) <FILE> +'
 
+    # parser.add_option('--install-manpages',
+    #                   help="Install manual pages for wavinfo",
+    #                   default=False,
+    #                   action='store_true')
+
+    parser.add_option('--man',
+                      help="Read the manual and exit.",
+                      default=False,
+                      action='store_true')
+
     parser.add_option('--adm', dest='adm',
                       help='Output ADM XML',
                       default=False,
@@ -36,6 +52,26 @@ def main():
                       action='store_true')
 
     (options, args) = parser.parse_args(sys.argv)
+
+    # if options.install_manpages:
+    #     print("Installing manpages...")
+    #     print(f"Docfiles at {__file__}")
+    #     return
+
+    if options.man:
+        import shlex
+        print("Which man page?")
+        print("1) wavinfo usage")
+        print("7) General info on Wave file metadata")
+        m = input("?> ")
+
+        args = ["man", "-M", manpath, "1", "wavinfo"]
+        if m.startswith("7"):
+            args[3] = "7"
+
+        os.system(shlex.join(args))
+        return
+
     for arg in args[1:]:
         try:
             this_file = WavInfoReader(path=arg)
@@ -53,9 +89,9 @@ def main():
                 ret_dict = {
                     'filename': arg,
                     'run_date': datetime.datetime.now().isoformat(),
-                    'application': "wavinfo " + __version__,
+                    'application': f"wavinfo {version}",
                     'scopes': {}
-                    }
+                }
                 for scope, name, value in this_file.walk():
                     if scope not in ret_dict['scopes'].keys():
                         ret_dict['scopes'][scope] = {}

wavinfo/man/man1/wavinfo.1

@@ -17,7 +17,7 @@ With no options,
 will emit a JSON (Javascript Object Notation) object containing all 
 detected metadata.
 .IP "\-\-adm"
-Output any Audio Definition Model (ADM) metadata in 
+Output Audio Definition Model (ADM) XML metadata in 
 .BR FILE .
 .IP "\-\-ixml"
 Output any iXML metdata in 

wavinfo/wave_reader.py

@@ -5,6 +5,7 @@ from typing import Optional, Generator, Any, NamedTuple
 
 import pathlib
 
+
 from .riff_parser import parse_chunk, ChunkDescriptor, ListChunkDescriptor
 from .wave_ixml_reader import WavIXMLFormat
 from .wave_bext_reader import WavBextReader
@@ -12,9 +13,11 @@ from .wave_info_reader import WavInfoChunkReader
 from .wave_adm_reader import WavADMReader
 from .wave_dbmd_reader import WavDolbyMetadataReader
 from .wave_cues_reader import WavCuesReader
-
+from .wave_smpl_reader import WavSmplReader
 
 #: Calculated statistics about the audio data.
+
+
 class WavDataDescriptor(NamedTuple):
     byte_count: int
     frame_count: int
@@ -80,6 +83,9 @@ class WavInfoReader:
         #: RIFF cues markers, labels, and notes.
         self.cues: Optional[WavCuesReader] = None
 
+        #: Sampler `smpl` metadata
+        self.smpl: Optional[WavSmplReader] = None
+
         if hasattr(path, 'read'):
             self.get_wav_info(path)
             self.url = 'about:blank'
@@ -110,6 +116,7 @@ class WavInfoReader:
         self.info = self._get_info(wavfile, encoding=self.info_encoding)
         self.dolby = self._get_dbmd(wavfile)
         self.cues = self._get_cue(wavfile)
+        self.smpl = self._get_sampler_loops(wavfile)
         self.data = self._describe_data()
 
     def _find_chunk_data(self, ident, from_stream,
@@ -203,6 +210,10 @@ class WavInfoReader:
         return WavCuesReader.read_all(f, cue, labls, ltxts, notes,
                                       fallback_encoding=self.info_encoding)
 
+    def _get_sampler_loops(self, f):
+        sampler_data = self._find_chunk_data(b'smpl', f, default_none=True)
+        return WavSmplReader(sampler_data) if sampler_data else None
+
     # FIXME: this should probably be named "iter()"
     def walk(self) -> Generator[str, str, Any]:
         """
@@ -210,11 +221,12 @@ class WavInfoReader:
 
         :yields: tuples of the *scope*, *key*, and *value* of
             each metadatum. The *scope* value will be one of
-            "fmt", "data", "ixml", "bext", "info", "dolby", "cues" or "adm".
+            "fmt", "data", "ixml", "bext", "info", "dolby", "cues", "adm" or
+            "smpl".
         """
 
         scopes = ('fmt', 'data', 'ixml', 'bext', 'info', 'adm', 'cues',
-                  'dolby')
+                  'dolby', 'smpl')
 
         for scope in scopes:
             if scope in ['fmt', 'data']:
@@ -223,10 +235,10 @@ class WavInfoReader:
                     yield scope, field, attr.__getattribute__(field)
 
             else:
-                dict = self.__getattribute__(scope).to_dict(
+                mdict = self.__getattribute__(scope).to_dict(
                 ) if self.__getattribute__(scope) else {}
-                for key in dict.keys():
+                for key in mdict.keys():
-                    yield scope, key, dict[key]
+                    yield scope, key, mdict[key]
 
     def __repr__(self):
         return 'WavInfoReader({}, {}, {})'.format(self.path,

wavinfo/wave_smpl_reader.py

@@ -0,0 +1,111 @@
+import struct
+
+from typing import Tuple, NamedTuple, List
+
+
+class WaveSmplLoop(NamedTuple):
+    ident: int
+    loop_type: int
+    start: int
+    end: int
+    fraction: int
+    repetition_count: int
+
+    def loop_type_desc(self):
+        if self.loop_type == 0:
+            return 'FORWARD'
+        elif self.loop_type == 1:
+            return 'FORWARD_BACKWARD'
+        elif self.loop_type == 2:
+            return 'BACKWARD'
+        elif 3 <= self.loop_type <= 31:
+            return 'RESERVED'
+        else:
+            return 'VENDOR'
+
+    def to_dict(self):
+        return {
+            'ident': self.ident,
+            'loop_type': self.loop_type,
+            'loop_type_description': self.loop_type_desc(),
+            'start_samples': self.start,
+            'end_samples': self.end,
+            'fraction': self.fraction,
+            'repetition_count': self.repetition_count,
+        }
+
+
+class WavSmplReader:
+
+    def __init__(self, smpl_data: bytes):
+        """
+        Read sampler metadata from smpl chunk.
+        """
+
+        header_field_fmt = "<IIIIIIbbbbII"
+        loop_field_fmt = "<IIIIII"
+        header_size = struct.calcsize(header_field_fmt)
+        loop_size = struct.calcsize(loop_field_fmt)
+
+        unpacked_data = struct.unpack(header_field_fmt,
+                                      smpl_data[0:header_size])
+
+        #: The MIDI Manufacturer's Association code for the sampler
+        #: manufactuer, or 0 if not specific.
+        self.manufacturer: int = unpacked_data[0]
+
+        #: The manufacturer-assigned code for their specific sampler model, or
+        #: 0 if not specific.
+        self.product: int = unpacked_data[1]
+
+        #: The number of nanoseconds in one audio frame.
+        self.sample_period_ns: int = unpacked_data[2]
+
+        #: The MIDI note number for the loops in this sample
+        self.midi_note: int = unpacked_data[3]
+
+        #: The number of semitones above the MIDI note the loops tune for.
+        self.midi_pitch_fraction_semis: int = unpacked_data[4]
+
+        #: SMPTE timecode format, one of (0, 24, 25, 29, 30)
+        self.smpte_format: int = unpacked_data[5]
+
+        #: The SMPTE offset to apply, as a tuple of four ints representing
+        #: hh, mm, ss, ff
+        self.smpte_offset: Tuple[int, int, int, int] = unpacked_data[6:10]
+
+        loop_count = unpacked_data[10]
+        sampler_udata_length = unpacked_data[11]
+
+        #: List of loops in the file.
+        self.sample_loops: List[WaveSmplLoop] = []
+
+        loop_buffer = smpl_data[header_size:
+                                header_size + loop_size * loop_count]
+
+        for unpacked_loop in struct.iter_unpack(loop_field_fmt, loop_buffer):
+            self.sample_loops.append(WaveSmplLoop(
+                ident=unpacked_loop[0],
+                loop_type=unpacked_loop[1],
+                start=unpacked_loop[2],
+                end=unpacked_loop[3],
+                fraction=unpacked_loop[4],
+                repetition_count=unpacked_loop[5]))
+
+        #: Sampler-specific user data.
+        self.sampler_udata: bytes = smpl_data[
+            header_size + loop_size * loop_count:
+            header_size + loop_size * loop_count + sampler_udata_length]
+
+    def to_dict(self):
+        return {
+            'manufactuer': self.manufacturer,
+            'product': self.product,
+            'sample_period_ns': self.sample_period_ns,
+            'midi_note': self.midi_note,
+            'midi_pitch_fraction_semis': self.midi_pitch_fraction_semis,
+            'smpte_format': self.smpte_format,
+            'smpte_offset': "%02i:%02i:%02i:%02i" % self.smpte_offset,
+            'loops': [x.to_dict() for x in self.sample_loops],
+            'sampler_user_data': self.sampler_udata,
+        }