Add docs (#13)

AlexeyKozhevin · web-flow · commit 34dea8813e79 · 2024-07-30T18:03:58.000+03:00
* Update docstrings and add docs
diff --git a/.github/workflows/doc.yml b/.github/workflows/doc.yml
@@ -0,0 +1,28 @@
+name: documentation
+
+on: [push, pull_request, workflow_dispatch]
+
+permissions:
+  contents: write
+
+jobs:
+  docs:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v3
+      - name: Install dependencies
+        run: |
+          pip install sphinx sphinx_rtd_theme myst_parser
+          pip install .
+      - name: Sphinx build
+        run: |
+          sphinx-build docs _build
+      - name: Deploy to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v3
+        if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' }}
+        with:
+          publish_branch: gh-pages
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: _build/
+          force_orphan: true
diff --git a/docs/Makefile b/docs/Makefile
@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(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)
diff --git a/docs/api/segfast.loader.rst b/docs/api/segfast.loader.rst
@@ -0,0 +1,5 @@
+======
+Loader
+======
+
+.. automethod:: segfast.loader.open
diff --git a/docs/api/segfast.memmap_loader.rst b/docs/api/segfast.memmap_loader.rst
@@ -0,0 +1,8 @@
+============
+MemmapLoader
+============
+
+.. autoclass:: segfast.memmap_loader.MemmapLoader
+   :members:
+   :undoc-members:
+   :member-order: bysource
diff --git a/docs/api/segfast.rst b/docs/api/segfast.rst
@@ -0,0 +1,12 @@
+===
+API
+===
+
+.. toctree::
+   :maxdepth: 5
+
+   segfast.loader
+   segfast.memmap_loader
+   segfast.segyio_loader
+   segfast.trace_header_spec
+   segfast.utils
diff --git a/docs/api/segfast.segyio_loader.rst b/docs/api/segfast.segyio_loader.rst
@@ -0,0 +1,13 @@
+============
+SegyioLoader
+============
+
+.. autoclass:: segfast.segyio_loader.SegyioLoader
+   :members:
+   :undoc-members:
+   :member-order: bysource
+
+.. autoclass:: segfast.segyio_loader.SafeSegyioLoader
+   :members:
+   :undoc-members:
+   :member-order: bysource
diff --git a/docs/api/segfast.trace_header_spec.rst b/docs/api/segfast.trace_header_spec.rst
@@ -0,0 +1,8 @@
+===============
+TraceHeaderSpec
+===============
+
+.. autoclass:: segfast.trace_header_spec.TraceHeaderSpec
+   :members:
+   :undoc-members:
+   :member-order: bysource
diff --git a/docs/api/segfast.utils.rst b/docs/api/segfast.utils.rst
@@ -0,0 +1,5 @@
+=====
+Utils
+=====
+
+.. autoclass:: segfast.utils.ForPoolExecutor
diff --git a/docs/conf.py b/docs/conf.py
@@ -0,0 +1,57 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+import sys, os
+sys.path.insert(0, os.path.abspath('..'))
+import segfast
+
+master_doc = 'index'
+
+project = 'segfast'
+author = 'Analysis Center'
+copyright = '2024, ' + author
+
+release = segfast.__version__
+version = '.'.join(release.split('.'))
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = [
+    'sphinx.ext.autodoc',
+    'sphinx.ext.doctest',
+    'sphinx.ext.coverage',
+    'sphinx.ext.mathjax',
+    'sphinx.ext.viewcode',
+    'sphinx.ext.githubpages',
+    'sphinx.ext.intersphinx',
+    'sphinx.ext.napoleon',
+    'sphinx_rtd_theme',
+]
+
+templates_path = ['_templates']
+exclude_patterns = []
+language = 'en'
+
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_title = "SegFast"
+html_theme = "sphinx_rtd_theme"
+html_static_path = ['_static']
+html_theme_options = {
+    'logo_only': False
+}
+
+# Example configuration for intersphinx: refer to the Python standard library.
+intersphinx_mapping = {
+    'python': ('https://docs.python.org/', None),
+    'numpy': ('https://docs.scipy.org/doc/numpy/', None),
+    'segyio': ('https://segyio.readthedocs.io/en/latest/', None)
+}
diff --git a/docs/index.rst b/docs/index.rst
@@ -0,0 +1,40 @@
+.. segfast documentation master file, created by
+   sphinx-quickstart on Thu Feb  1 14:09:14 2024.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+segfast documentation
+=====================
+
+**segfast** is a library for interacting with SEG-Y seismic data. Main features are:
+
+* Faster access to read data: both traces headers and values
+* Optional bufferization, where the user can provide a preallocated memory to load the data into
+* Convenient API that relies on :class:`numpy.memmap` for most operations, while providing
+  `segyio <https://segyio.readthedocs.io/en/latest/>`_ as a fallback engine
+
+
+Implementation details
+----------------------
+We rely on **segyio** to infer file-wide parameters.
+
+For headers and traces, we use custom methods of reading binary data.
+
+Main differences to **segyio** C++ implementation:
+   - we read all of the requested headers in one file-wide sweep, speeding up by an order of magnitude
+     compared to the **segyio** sequential read of every requested header.
+     Also, we do that in multiple processes across chunks.
+
+   - a memory map over trace data is used for loading values. Avoiding redundant copies and leveraging
+     :mod:`numpy` superiority allows to speed up reading, especially in case of trace slicing along the samples axis.
+     This is extra relevant in the case of loading horizontal (depth) slices.
+
+
+.. toctree::
+   :maxdepth: 1
+   :titlesonly:
+
+   installation
+   start
+   segy
+   api/segfast
diff --git a/docs/installation.rst b/docs/installation.rst
@@ -0,0 +1,14 @@
+Installation
+============
+
+* With ``pip``/``pip3``:
+
+   .. code-block:: bash
+
+    pip3 install segfast
+
+* Developer version (add ``--depth 1`` if needed)
+
+   .. code-block:: bash
+
+    git clone https://github.com/analysiscenter/segfast.git
diff --git a/docs/make.bat b/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
+
+%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.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd
diff --git a/docs/segy.rst b/docs/segy.rst
@@ -0,0 +1,29 @@
+SEG-Y description
+=================
+
+The most complete description can be found in `the official SEG-Y specification <https://library.seg.org/pb-assets/technical-standards/seg_y_rev2_0-mar2017-1686080998003.pdf>`_ but here we give
+a brief intro into SEG-Y format.
+
+The SEG-Y is a binary file divided into several blocks:
+
+- file-wide information block which in most cases takes the first 3600 bytes:
+
+  - **textual header**: the first 3200 bytes are reserved for textual info about the file. Most of the software uses
+    this header to keep acquisition meta, date of creation, author, etc.
+  - **binary header**: 3200–3600 bytes contain file-wide headers, which describe the number of traces, the format used
+    for storing numbers, the number of samples for each trace, acquisition parameters, etc.
+  - (optional) 3600+ bytes can be used to store the **extended textual information**. If there is such a header,
+    then this is indicated by the value in one of the 3200–3600 bytes.
+
+- a sequence of traces, where each trace is a combination of its header and signal data:
+
+  - **trace header** takes the first 240 bytes and describes the meta info about its trace: shot/receiver coordinates,
+    the method of acquisition, current trace length, etc. Analogously to binary file header, each trace also
+    can have extended headers.
+  - **trace data** is usually an array of amplitude values, which can be stored in various numerical types.
+    As the original SEG-Y is quite old (1975), one of those numerical formats is IBM float,
+    which is very different from standard IEEE floats; therefore, special caution is required to
+    correctly decode values from such files.
+
+For the most part, SEG-Y files are written with a constant size of each trace, although the standard itself allows
+for variable-sized traces. We do not work with such files.
diff --git a/docs/start.rst b/docs/start.rst
@@ -0,0 +1,31 @@
+Quick start
+===========
+
+* Open the file:
+
+   .. code-block:: python
+
+    import segfast
+    segy_file = segfast.open('/path/to/file.sgy')
+
+* Load headers:
+
+   .. code-block:: python
+
+    headers = segy_file.load_headers(['CDP_X', 'CDP_Y', 'INLINE_3D', 'CROSSLINE_3D'])
+
+* Load inline:
+
+   .. code-block:: python
+
+    traces_idx = headers[headers['INLINE_3D'] == INLINE_IDX].index
+    inline = segy_file.load_traces(traces_idx)
+
+* Load certain depths from all traces:
+
+   .. code-block:: python
+
+    segy_file.load_depth_slices(DEPTHS)
+
+   The resulting array will have shape ``(n_traces, len(DEPTHS))`` so it must be processed to be transformed
+   to an array of the field shape.
diff --git a/pylintrc b/pylintrc
@@ -15,7 +15,7 @@ variable-rgx=(.*[a-z][a-z0-9_]{1,30}|[a-z_])$ # snake_case + single letters
 argument-rgx=(.*[a-z][a-z0-9_]{1,30}|[a-z_])$ # snake_case + single letters
 
 [MESSAGE CONTROL]
-disable=no-value-for-parameter, no-self-use, too-few-public-methods, unsubscriptable-object, no-member, too-many-lines,
+disable=no-value-for-parameter, too-few-public-methods, unsubscriptable-object, no-member, too-many-lines,
         arguments-differ, too-many-locals, import-error, cyclic-import, duplicate-code, relative-beyond-top-level,
         unused-argument, too-many-public-methods, invalid-name, attribute-defined-outside-init, arguments-renamed,
         abstract-method, no-name-in-module, import-self
diff --git a/segfast/loader.py b/segfast/loader.py
@@ -5,7 +5,26 @@
 
 
 def Loader(path, engine='memmap', endian='big', strict=False, ignore_geometry=True):
-    """ Selector class for loading SEG-Y with either segyio-based loader or memmap-based one. """
+    """ Selector class for loading SEG-Y with either segyio-based loader or memmap-based one.
+
+    Parameters
+    ----------
+    path : str
+        Path to the SEG-Y file
+    engine : 'memmap' or 'segyio'
+        Engine to load data from file: ``'memmap'`` is based on :class:`numpy.memmap` created for the whole file and
+        ``'segyio'`` is for using **segyio** library instruments. in any case, **segyio** is used to load information
+        about the entire file (e.g. ``'sample_interval'`` or ``'shape'``).
+    endian : 'big' or 'little'
+        Byte order in the file.
+    strict : bool
+        See :func:`segyio.open`
+    ignore_geometry : bool
+        See :func:`segyio.open`
+    Return
+    ------
+    :class:`~.memmap_loader.MemmapLoader` or :class:`~.segyio_loader.SegyioLoader`
+    """
     loader_class = _select_loader_class(engine)
     return loader_class(path=path, endian=endian, strict=strict, ignore_geometry=ignore_geometry)
 open = File = Loader
diff --git a/segfast/memmap_loader.py b/segfast/memmap_loader.py
diff --git a/segfast/segyio_loader.py b/segfast/segyio_loader.py
diff --git a/segfast/trace_header_spec.py b/segfast/trace_header_spec.py
diff --git a/segfast/utils.py b/segfast/utils.py

-Original file line number
+Diff line change
@@ @@ -0,0 +1,5 @@ @@
 +======
 +Loader
 +======
++
 +.. automethod:: segfast.loader.open