Merge branch 'rewrite' into header

DESCRIPTION.rst

@@ -0,0 +1,32 @@
+The SEG Y file format is one of several standards developed by the Society of Exploration Geophysicists for storing
+geophysical seismic data. It is an open standard, and is controlled by the SEG Technical Standards Committee, a
+non-profit organization.
+
+This project aims to implement an open SEG Y module in Python for transporting seismic data between SEG Y files and
+Python data structures in pure Python.
+
+
+Status
+======
+
+*Segpy 2* is currently in alpha, so expect rough edges. That said, it seems to broadly work and is largely feature
+complete.
+
+
+What It Does
+============
+
+How To Get It
+=============
+
+*Segpy* is available on the Python Package index and can be installed with ``pip``::
+
+  $ pip install segpy
+
+
+Requirements
+============
+
+*Segpy 2* work with Python 3.2 and higher (and 2.7 for now).  For the majority of use *Segpy 2* has no external
+dependencies.  Optional modules with further dependencies such as *Numpy* are included in the ``segpy.ext`` package of
+extras.

README.rst

@@ -1,6 +1,6 @@
-=====
-Segpy
-=====
+=======
+Segpy 2
+=======
 
 Status
 ======
@@ -18,4 +18,11 @@ geophysical seismic data. It is an open standard, and is controlled by the SEG T
 non-profit organization.
 
 This project aims to implement an open SEG Y module in Python for transporting seismic data between SEG Y files and
-Numpy arrays. Segpy is a package for reading, writing and manipulating SEG Y data in pure Python.
+Python data structures in pure Python.
+
+Segpy Versions
+==============
+
+Segpy 2.0 is a complete re-imagining of a SEG Y reader in Python and represents a complete break from Segpy 1.0 in terms
+of the interface it presents to clients and the implementation behind those interfaces.   Segpy 1.0 should be considered
+unmaintained legacy software. The present and future of Segpy is Segpy 2.

examples/timeslice.py

@@ -0,0 +1,137 @@
+"""Extract a timeslice from a 3D seismic volume to a Numpy array.
+
+Usage: timeslice.py [-h] [--dtype DTYPE] [--null NULL]
+                    segy-file npy-file slice-index
+
+Positional arguments:
+  segy-file      Path to an existing SEG Y file of 3D seismic data
+  npy-file       Path to the Numpy array file to be created for the timeslice
+  slice-index    Zero based index of the time slice to be extracted
+
+Optional arguments:
+  -h, --help     show this help message and exit
+  --dtype DTYPE  Numpy data type. If not provided a dtype compatible with the
+                 SEG Y data will be used.
+  --null NULL    Sample value to use for missing or short traces.
+
+Example:
+
+  timeslice.py stack_final_int8.sgy slice_800.npy 800 --null=42.0 --dtype=f
+"""
+from __future__ import print_function
+
+import argparse
+import os
+import sys
+import traceback
+
+import numpy as np
+
+from segpy.reader import create_reader
+from segpy_numpy.numpy.dtypes import make_dtype
+
+
+class DimensionalityError(Exception):
+    pass
+
+
+def extract_timeslice(segy_filename, out_filename, slice_index, dtype=None, null=0):
+    """Extract a timeslice from a 3D SEG Y file to a Numpy NPY file.
+
+    Args:
+        segy_filename: Filename of a SEG Y file.
+
+        out_filename: Filename of the NPY file.
+
+        slice_index: The zero-based index (increasing with depth) of the slice to be extracted.
+
+        dtype: Optional Numpy dtype for the result array. If not provided a dtype compatible with
+            the SEG Y data will be used.
+
+        null: Optional sample value to use for missing or short traces. Defaults to zero.
+    """
+    with open(segy_filename, 'rb') as segy_file:
+
+        segy_reader = create_reader(segy_file)
+
+        if dtype is None:
+            dtype = make_dtype(segy_reader.data_sample_format)
+
+        if segy_reader.dimensionality != 3:
+            raise DimensionalityError("Cannot slice {n} dimensional seismic.".format(segy_reader.dimensionality))
+
+        i_line_range = segy_reader.inline_range()
+        x_line_range = segy_reader.xline_range()
+
+        i_size = len(i_line_range)
+        x_size = len(x_line_range)
+        t_size = segy_reader.max_num_trace_samples()
+
+        if not (0 <= slice_index < t_size):
+            raise ValueError("Time slice index {0} out of range {} to {}".format(slice_index, 0, t_size))
+
+        timeslice = np.full((x_size, i_size), null, dtype)
+
+        for inline_num, xline_num in segy_reader.inline_xline_numbers():
+            trace_index = segy_reader.trace_index((inline_num, xline_num))
+            trace = segy_reader.trace_samples(trace_index)
+
+            try:
+                sample = trace[slice_index]
+            except IndexError:
+                sample = null
+
+            i_index = inline_num - i_line_range.start
+            x_index = xline_num - x_line_range.start
+            timeslice[x_index, i_index] = sample
+
+        np.save(out_filename, timeslice)
+
+
+def nullable_dtype(s):
+    return None if s == "" else np.dtype(s)
+
+
+def main(argv=None):
+    parser = argparse.ArgumentParser()
+    parser.add_argument("segy_file", metavar="segy-file",
+                        help="Path to an existing SEG Y file of 3D seismic data")
+
+    parser.add_argument("npy_file", metavar="npy-file",
+                        help="Path to the Numpy array file to be created for the timeslice")
+
+    parser.add_argument("slice_index", metavar="slice-index", type=int,
+                        help="Zero based index of the time slice to be extracted", )
+
+    parser.add_argument("--dtype", type=nullable_dtype, default="",
+                        help="Numpy data type. If not provided a dtype compatible with the SEG Y data will be used.")
+
+    parser.add_argument("--null",  type=float, default=0.0,
+                        help="Sample value to use for missing or short traces.")
+
+    if argv is None:
+        argv = sys.argv[1:]
+
+    args = parser.parse_args(argv)
+
+    try:
+        extract_timeslice(args.segy_file,
+                          args.npy_file,
+                          args.slice_index,
+                          args.dtype,
+                          args.null)
+    except (FileNotFoundError, IsADirectoryError) as e:
+        print(e, file=sys.stderr)
+        return os.EX_NOINPUT
+    except PermissionError as e:
+        print(e, file=sys.stderr)
+        return os.EX_NOPERM
+    except Exception as e:
+        traceback.print_exception(type(e), e, e.__traceback__, file=sys.stderr)
+        return os.EX_SOFTWARE
+    return os.EX_OK
+
+
+if __name__ == '__main__':
+    sys.exit(main())
+

segpy-ext/segpy-numpy/DESCRIPTION.rst

@@ -0,0 +1,20 @@
+Segpy-Numpy offers tools for working with both *Segpy* and *Numpy*. See the *Segpy* documentation for further details.
+
+
+What It Does
+============
+
+How To Get It
+=============
+
+*Segpy-Numpy* is available on the Python Package index and can be installed with ``pip``::
+
+  $ pip install segpy-numpy
+
+
+Requirements
+============
+
+*Segpy-Numpy* should work with Python 3.2 and higher (and 2.7 for now).  For the majority of use *Segpy 2* has no
+externaldependencies.  Optional modules with further dependencies such as *Numpy* are included in the ``segpy.ext``
+package of extras.

segpy-ext/segpy-numpy/__init__.py

@@ -0,0 +1 @@
+

segpy-ext/segpy-numpy/segpy_numpy/__init__.py

@@ -0,0 +1,10 @@
+print("segpy_numpy.__init__ imported")
+
+from pkgutil import extend_path
+
+#__path__ = extend_path(__path__, __name__)
+__version__ = '2.0.0a1'
+
+
+def load():
+    pass

segpy-ext/segpy-numpy/segpy_numpy/numpy/__init__.py

@@ -0,0 +1 @@
+

segpy-ext/segpy-numpy/segpy_numpy/numpy/dtypes.py

@@ -2,11 +2,11 @@
 
 import numpy
 
-NUMPY_DTYPES = {'ibm': numpy.dtype('f4'),
-                'l':   numpy.dtype('i4'),
-                'h':   numpy.dtype('i2'),
-                'f':   numpy.dtype('f4'),
-                'b':   numpy.dtype('i1')}
+NUMPY_DTYPES = {'ibm':     numpy.dtype('f4'),
+                'int32':   numpy.dtype('i4'),
+                'int16':   numpy.dtype('i2'),
+                'float32': numpy.dtype('f4'),
+                'int8':    numpy.dtype('i1')}
 
 
 def make_dtype(data_sample_format):

segpy-ext/segpy-numpy/setup.cfg

@@ -0,0 +1,5 @@
+[bdist_wheel]
+# This flag says that the code is written to work on both Python 2 and Python
+# 3. If at all possible, it is good practice to do this. If you cannot, you
+# will need to generate wheels for each Python version that you support.
+universal=1

segpy-ext/segpy-numpy/setup.py

@@ -0,0 +1,127 @@
+import io
+import os
+import re
+from setuptools import setup, find_packages  # Always prefer setuptools over distutils
+from codecs import open  # To use a consistent encoding
+from os import path
+
+
+def read(*names, **kwargs):
+    with io.open(
+        os.path.join(os.path.dirname(__file__), *names),
+        encoding=kwargs.get("encoding", "utf8")
+    ) as fp:
+        return fp.read()
+
+
+def find_version(*file_paths):
+    version_file = read(*file_paths)
+    version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]",
+                              version_file, re.M)
+    if version_match:
+        return version_match.group(1)
+    raise RuntimeError("Unable to find version string.")
+
+
+here = path.abspath(path.dirname(__file__))
+
+
+def local_file(name):
+    return os.path.join(here, name)
+
+
+
+# Get the long description from the relevant file
+with open(local_file('DESCRIPTION.rst'), encoding='utf-8') as f:
+    long_description = f.read()
+
+setup(
+    name='segpy-numpy',
+
+    # Versions should comply with PEP440.  For a discussion on single-sourcing
+    # the version across setup.py and the project code, see
+    # https://packaging.python.org/en/latest/single_source_version.html
+    version=find_version("segpy_numpy/__init__.py"),
+
+    description='Interoperability between Numpy with Segpy.',
+    long_description=long_description,
+
+    # The project's main homepage.
+    url='https://github.com/rob-smallshire/segpy',
+
+    # Author details
+    author='Robert Smallshire',
+    author_email='robert@smallshire.org.uk',
+
+    # Choose your license
+    license='GPL',
+
+    # See https://pypi.python.org/pypi?%3Aaction=list_classifiers
+    classifiers=[
+        # How mature is this project? Common values are
+        #   3 - Alpha
+        #   4 - Beta
+        #   5 - Production/Stable
+        'Development Status :: 3 - Alpha',
+
+        # Indicate who your project is intended for
+        'Intended Audience :: Developers',
+        'Topic :: Scientific/Engineering',
+        'Topic :: Software Development :: Libraries',
+
+        # Pick your license as you wish (should match "license" above)
+        'License :: OSI Approved :: MIT License',
+
+        # Specify the Python versions you support here. In particular, ensure
+        # that you indicate whether you support Python 2, Python 3 or both.
+        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.3',
+        'Programming Language :: Python :: 3.4',
+    ],
+
+    # What does your project relate to?
+    keywords='seismic geocomputing geophysics numpy',
+
+    # You can just specify the packages manually here if your project is
+    # simple. Or you can use find_packages().
+    packages=find_packages(here, exclude=['segpy', 'contrib', 'docs', 'test*']),
+
+    # List run-time dependencies here.  These will be installed by pip when your
+    # project is installed. For an analysis of "install_requires" vs pip's
+    # requirements files see:
+    # https://packaging.python.org/en/latest/requirements.html
+    install_requires=['numpy'],
+
+    # List additional groups of dependencies here (e.g. development dependencies).
+    # You can install these using the following syntax, for example:
+    # $ pip install -e .[dev,test]
+    extras_require = {
+        'dev': ['check-manifest', 'wheel'],
+        'doc': ['sphinx', 'cartouche'],
+        'test': ['coverage', 'hypothesis'],
+    },
+
+    # If there are data files included in your packages that need to be
+    # installed, specify them here.  If using Python 2.6 or less, then these
+    # have to be included in MANIFEST.in as well.
+    package_data={
+    },
+
+    # Although 'package_data' is the preferred approach, in some case you may
+    # need to place data files outside of your packages.
+    # see http://docs.python.org/3.4/distutils/setupscript.html#installing-additional-files
+    # In this case, 'data_file' will be installed into '<sys.prefix>/my_data'
+    data_files=[],
+
+    # To provide executable scripts, use entry points in preference to the
+    # "scripts" keyword. Entry points provide cross-platform support and allow
+    # pip to create the appropriate form of executable for the target platform.
+
+    # Declare entry-points to modules.
+    entry_points={
+        'segpy.ext': 'segpy-numpy = segpy_numpy'
+    },
+)
+
+

segpy/__init__.py

@@ -1 +1 @@
-
+__version__ = '2.0.0a1'

segpy/ext/__init__.py

@@ -1 +1,20 @@
+import pkg_resources
 
+loaded = set()
+
+
+def load_entry_points(name=None):
+    """Load extension packages into the segpy.ext namespace.
+
+    Any packages registered against the 'segpy.ext' entry-point group will be
+    installed dynamically into the segpy.ext namespace.
+    """
+    for entry_point in pkg_resources.iter_entry_points(group='segpy.ext', name=name):
+        package = entry_point.load()
+        if package not in loaded:
+            loaded.add(package)
+            __path__.extend(package.__path__)
+            package.load()
+
+
+load_entry_points()

setup.cfg

@@ -0,0 +1,5 @@
+[bdist_wheel]
+# This flag says that the code is written to work on both Python 2 and Python
+# 3. If at all possible, it is good practice to do this. If you cannot, you
+# will need to generate wheels for each Python version that you support.
+universal=1

setup.py

@@ -0,0 +1,119 @@
+import io
+import os
+import re
+from setuptools import setup, find_packages  # Always prefer setuptools over distutils
+from codecs import open  # To use a consistent encoding
+from os import path
+
+
+def read(*names, **kwargs):
+    with io.open(
+        os.path.join(os.path.dirname(__file__), *names),
+        encoding=kwargs.get("encoding", "utf8")
+    ) as fp:
+        return fp.read()
+
+
+def find_version(*file_paths):
+    version_file = read(*file_paths)
+    version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]",
+                              version_file, re.M)
+    if version_match:
+        return version_match.group(1)
+    raise RuntimeError("Unable to find version string.")
+
+
+here = path.abspath(path.dirname(__file__))
+
+# Get the long description from the relevant file
+with open(path.join(here, 'DESCRIPTION.rst'), encoding='utf-8') as f:
+    long_description = f.read()
+
+setup(
+    name='segpy',
+
+    # Versions should comply with PEP440.  For a discussion on single-sourcing
+    # the version across setup.py and the project code, see
+    # https://packaging.python.org/en/latest/single_source_version.html
+    version=find_version("segpy/__init__.py"),
+
+    description='Transfer of seismic data to and from SEG Y files',
+    long_description=long_description,
+
+    # The project's main homepage.
+    url='https://github.com/rob-smallshire/segpy',
+
+    # Author details
+    author='Robert Smallshire',
+    author_email='robert@smallshire.org.uk',
+
+    # Choose your license
+    license='GPL',
+
+    # See https://pypi.python.org/pypi?%3Aaction=list_classifiers
+    classifiers=[
+        # How mature is this project? Common values are
+        #   3 - Alpha
+        #   4 - Beta
+        #   5 - Production/Stable
+        'Development Status :: 3 - Alpha',
+
+        # Indicate who your project is intended for
+        'Intended Audience :: Developers',
+        'Topic :: Scientific/Engineering',
+        'Topic :: Software Development :: Libraries',
+
+        # Pick your license as you wish (should match "license" above)
+        'License :: OSI Approved :: MIT License',
+
+        # Specify the Python versions you support here. In particular, ensure
+        # that you indicate whether you support Python 2, Python 3 or both.
+        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.3',
+        'Programming Language :: Python :: 3.4',
+    ],
+
+    # What does your project relate to?
+    keywords='seismic geocomputing geophysics',
+
+    # You can just specify the packages manually here if your project is
+    # simple. Or you can use find_packages().
+    packages=find_packages(exclude=['contrib', 'docs', 'test*']),
+
+    # List run-time dependencies here.  These will be installed by pip when your
+    # project is installed. For an analysis of "install_requires" vs pip's
+    # requirements files see:
+    # https://packaging.python.org/en/latest/requirements.html
+    install_requires=[],
+
+    # List additional groups of dependencies here (e.g. development dependencies).
+    # You can install these using the following syntax, for example:
+    # $ pip install -e .[dev,test]
+    extras_require = {
+        'dev': ['check-manifest', 'wheel'],
+        'doc': ['sphinx', 'cartouche'],
+        'test': ['coverage', 'hypothesis'],
+    },
+
+    # If there are data files included in your packages that need to be
+    # installed, specify them here.  If using Python 2.6 or less, then these
+    # have to be included in MANIFEST.in as well.
+    package_data={
+    },
+
+    # Although 'package_data' is the preferred approach, in some case you may
+    # need to place data files outside of your packages.
+    # see http://docs.python.org/3.4/distutils/setupscript.html#installing-additional-files
+    # In this case, 'data_file' will be installed into '<sys.prefix>/my_data'
+    data_files=[],
+
+    # To provide executable scripts, use entry points in preference to the
+    # "scripts" keyword. Entry points provide cross-platform support and allow
+    # pip to create the appropriate form of executable for the target platform.
+    entry_points={
+        'console_scripts': [
+        ],
+    },
+)
+

test/test_util.py

@@ -15,7 +15,7 @@ class TestBatched(unittest.TestCase):
         self.assertTrue(all(len(batch) == batch_size for batch in batches[:-1]))
 
     @given([int],
-            integers_in_range(1, 1000))
+           integers_in_range(1, 1000))
     def test_final_batch_sizes(self, items, batch_size):
         assume(len(items) > 0)
         assume(batch_size > 0)