chemparseplot 0.0.2__tar.gz

chemparseplot-0.0.2/.gitignore

@@ -0,0 +1,166 @@
+### Generated by gibo (https://github.com/simonwhitaker/gibo)
+### https://raw.github.com/github/gitignore/4488915eec0b3a45b5c63ead28f286819c0917de/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+/_version.py
+/.pdm-python
+*.ipynb

chemparseplot-0.0.2/LICENSE

@@ -0,0 +1,19 @@
+MIT License Copyright (c) 2023 Rohit Goswami (HaoZeke) <rog32[at]hi.is>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is furnished
+to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice (including the next
+paragraph) shall be included in all copies or substantial portions of the
+Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS
+OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF
+OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

chemparseplot-0.0.2/PKG-INFO

@@ -0,0 +1,111 @@
+Metadata-Version: 2.1
+Name: chemparseplot
+Version: 0.0.2
+Summary: Parsers and plotting tools for computational chemistry
+Project-URL: Documentation, https://github.com/HaoZeke/chemparseplot#readme
+Project-URL: Issues, https://github.com/HaoZeke/chemparseplot/issues
+Project-URL: Source, https://github.com/HaoZeke/chemparseplot
+Author-email: Rohit Goswami <rog32@hi.is>
+License: MIT
+License-File: LICENSE
+Keywords: compchem,parser,plot
+Classifier: Development Status :: 4 - Beta
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Requires-Python: >=3.9
+Requires-Dist: numpy>=1.26.2
+Requires-Dist: pint>=0.22
+Provides-Extra: doc
+Requires-Dist: mdit-py-plugins>=0.3.4; extra == 'doc'
+Requires-Dist: myst-nb>=1.0.0; extra == 'doc'
+Requires-Dist: myst-parser>=2.0.0; extra == 'doc'
+Requires-Dist: sphinx-autodoc2>=0.5.0; extra == 'doc'
+Requires-Dist: sphinx-copybutton>=0.5.2; extra == 'doc'
+Requires-Dist: sphinx-library>=1.1.2; extra == 'doc'
+Requires-Dist: sphinx-sitemap>=2.5.1; extra == 'doc'
+Requires-Dist: sphinx-togglebutton>=0.3.2; extra == 'doc'
+Requires-Dist: sphinx>=7.2.6; extra == 'doc'
+Requires-Dist: sphinxcontrib-apidoc>=0.4.0; extra == 'doc'
+Provides-Extra: plot
+Requires-Dist: matplotlib>=3.8.2; extra == 'plot'
+Description-Content-Type: text/markdown
+
+
+# Table of Contents
+
+1.  [About](#orgea43256)
+    1.  [Features](#org6a31408)
+        1.  [Supported Engines [WIP]](#orgbfa09d8)
+    2.  [Rationale](#org4c00d67)
+2.  [License](#orge2168a3)
+
+
+<a id="orgea43256"></a>
+
+# About
+
+![img](branding/logo/chemparseplot_logo.png)
+
+[![Hatch project](https://img.shields.io/badge/%F0%9F%A5%9A-Hatch-4051b5.svg)](https://github.com/pypa/hatch)
+
+A **pure-python**<sup><a id="fnr.1" class="footref" href="#fn.1" role="doc-backlink">1</a></sup> project to provide unit-aware uniform visualizations
+of common computational chemistry tasks. Essentially this means we provide:
+
+-   Plotting scripts for specific workflows
+-   Parsers for various software outputs
+
+This is a spin-off from `wailord` ([here](https://wailord.xyz)) which is meant to handle aggregated
+runs in a specific workflow, while here the goal is to do no input handling and
+very pragmatic output parsing, with the goal of generating uniform plots.
+
+
+<a id="org6a31408"></a>
+
+## Features
+
+-   [Scientific color maps](https://www.fabiocrameri.ch/colourmaps/) for the plots
+    -   Camera ready
+-   Unit preserving
+    -   Via `pint`
+
+
+<a id="orgbfa09d8"></a>
+
+### Supported Engines [WIP]
+
+-   ORCA (**5.x**)
+    -   Scanning energies over a degree of freedom (`OPT` scans)
+    -   Nudged elastic band (`NEB`) visualizations (over the "linearized" reaction
+        coordinate)
+
+
+<a id="org4c00d67"></a>
+
+## Rationale
+
+`wailord` is for production runs, however often there is a need to collect
+"spot" calculation visualizations, which should nevertheless be uniform, i.e.
+either Bohr/Hartree or Angstron/eV or whatever.
+
+Also I couldn't find (m)any scripts using the scientific colorschemes.
+
+
+<a id="orge2168a3"></a>
+
+# License
+
+MIT. However, this is an academic resource, so **please cite** as much as possible
+via:
+
+-   The Zenodo DOI for general use.
+-   The `wailord` paper for ORCA usage
+
+
+# Footnotes
+
+<sup><a id="fn.1" href="#fnr.1">1</a></sup> To distinguish it from my other thin-python wrapper projects

chemparseplot-0.0.2/_version.py

@@ -0,0 +1,16 @@
+# file generated by setuptools_scm
+# don't change, don't track in version control
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple, Union
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+else:
+    VERSION_TUPLE = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+
+__version__ = version = '0.0.2'
+__version_tuple__ = version_tuple = (0, 0, 2)

chemparseplot-0.0.2/chemparseplot/__init__.py

@@ -0,0 +1,5 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+
+from chemparseplot import basetypes, parse, units

chemparseplot-0.0.2/chemparseplot/basetypes.py

@@ -0,0 +1,47 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+from collections import namedtuple
+
+# namedtuple for storing NEB iteration data
+nebiter = namedtuple("nebiter", ["iteration", "nebpath"])
+"""
+A namedtuple representing an iteration of a Nudged Elastic Band (NEB) calculation.
+
+Parameters
+----------
+iteration : int
+    The iteration number of the NEB calculation.
+nebpath : nebpath namedtuple
+    The data for the NEB path at this iteration.
+
+See Also
+--------
+nebpath : Stores the normalized arclength, actual arclength, and energy data for
+    the NEB path.
+"""
+
+# namedtuple for storing the NEB path data
+nebpath = namedtuple("nebpath", ["norm_dist", "arc_dist", "energy"])
+"""
+A namedtuple representing the NEB path data.
+
+Parameters
+----------
+norm_dist : float
+    Normalized Arclength (0 to 1), representing the progression along the reaction path.
+    Calculated as xcoord2 = arcS[img] / arcS[nim-1].
+arc_dist : float
+    Actual Arclength at each point along the reaction path. Calculated as
+    xcoord = arcS[img] + dx(ii).
+energy : float
+    Interpolated Energy at each point, calculated using cubic polynomial
+    interpolation. The energy is calculated using the formula:
+    p = a*pow(dx(ii), 3.0) + b*pow(dx(ii), 2.0) + c*dx(ii) + d,
+    where a, b, c, and d are coefficients of the cubic polynomial.
+
+Notes
+-----
+The `nebpath` namedtuple is used within the `nebiter` namedtuple to store
+detailed path information for each NEB iteration.
+"""

chemparseplot-0.0.2/chemparseplot/parse/__init__.py

@@ -0,0 +1,5 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+
+from chemparseplot.parse import orca, patterns

chemparseplot-0.0.2/chemparseplot/parse/converter.py

@@ -0,0 +1,11 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+from io import StringIO
+
+import numpy as np
+
+
+def np_txt(matched_data):
+    datio = StringIO(matched_data)
+    return np.loadtxt(datio)

chemparseplot-0.0.2/chemparseplot/parse/orca/__init__.py

@@ -0,0 +1,5 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+
+from chemparseplot.parse.orca import geomscan

chemparseplot-0.0.2/chemparseplot/parse/orca/geomscan.py

@@ -0,0 +1,63 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+"""
+For parsing outputs from input files like this:
+!OPT UHF def2-SVP
+%geom Scan
+  B 0 1 = 7.5589039543, 0.2116708996, 33
+ end
+end
+*xyzfile 0 1 h2_base.xyz
+"""
+import re
+
+import chemparseplot.parse.converter as conv
+import chemparseplot.parse.patterns as pat
+from chemparseplot.units import Q_
+
+
+def extract_energy_data(data: str, energy_type: str) -> tuple[Q_, Q_]:
+    """
+    Extracts and converts the energy data for a specified energy type.
+
+    This function assumes the input data is a blob of text. It searches for
+    'Calculated Surface' followed by the specified energy type ('Actual' or 'SCF')
+    and extracts the two-column data (distance and energy values) following it.
+    Energies are returned in Hartree and distances in Bohr, as these are the default
+    units used in ORCA.
+
+    Parameters
+    ----------
+    data : str
+        The blob of text containing energy data.
+    energy_type : str
+        The type of energy to search for ('Actual' or 'SCF').
+
+    Returns
+    -------
+    tuple[Q_, Q_]
+        A tuple containing two `Quantity` objects from the `pint` library.
+        The first element is an array of distances in Bohr, and the second
+        element is an array of energies in Hartree.
+
+    """
+    # Regular expression to find the energy type and the two-column data following it
+    # https://regex101.com/r/RF6b4V/2
+    # fmt: off
+    pattern = (
+        r".*? Calculated Surface.*?"
+        rf"{energy_type}.*?"
+    ) + pat.TWO_COL_NUM
+    matchr = re.search(pattern, data, re.MULTILINE)
+    # fmt: on
+    if not matchr:
+        xdu = Q_([], "bohr")
+        ydu = Q_([], "hartree")
+        return xdu, ydu
+
+    energytxt = matchr.group("twocolnum")
+    xydat = conv.np_txt(energytxt)
+    xdu = Q_(xydat[:, 0], "bohr")
+    ydu = Q_(xydat[:, 1], "hartree")
+    return xdu, ydu

chemparseplot-0.0.2/chemparseplot/parse/orca/neb/interp.py

@@ -0,0 +1,40 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+"""
+For parsing .interp files from inputs like:
+!B3LYP def2-SVP NEB-CI
+%neb
+nimages = 7
+Product "prod.xyz"
+end
+*xyzfile 0 1 react.xyz
+"""
+import re
+
+import chemparseplot.parse.converter as conv
+import chemparseplot.parse.patterns as pat
+from chemparseplot.basetypes import nebiter, nebpath
+from chemparseplot.units import Q_
+
+# fmt: off
+INTERP_PAT = (
+    r"Iteration:\s*(?P<iteration>\d+)\s*\n"  # Capture iteration number
+    r"Images: Distance\s+\(Bohr\), Energy \(Eh\)\s*\n"  # Match 'Images:' line
+    + pat.THREE_COL_NUM
+)
+# fmt: on
+
+
+def extract_interp_points(text: str) -> list[int, Q_, Q_]:
+    data = []
+    for match in re.finditer(INTERP_PAT, text, re.DOTALL):
+        iteration = int(match.group("iteration"))
+        energytxt = match.group("threecolnum")
+        ixydat = conv.np_txt(energytxt)
+        nxdu = Q_(ixydat[:, 0], "dimensionless")
+        xdu = Q_(ixydat[:, 1], "bohr")
+        ydu = Q_(ixydat[:, 2], "hartree")
+        tnp = nebpath(norm_dist=nxdu, arc_dist=xdu, energy=ydu)
+        data.append(nebiter(iteration=iteration, nebpath=tnp))
+    return data

chemparseplot-0.0.2/chemparseplot/parse/patterns.py

@@ -0,0 +1,32 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+
+# https://regex101.com/r/jHAG2T/1
+# DIGIT pattern for a floating-point number, possibly negative
+DIGIT = r"-?\d+\.\d+"
+
+
+def create_multicol_pattern(num_cols, pname="multicolnum"):
+    if num_cols < 1:
+        error_message = "Number of columns must be at least 1"
+        raise ValueError(error_message)
+
+    # Building the pattern for N columns
+    pattern = (
+        r"\s*"  # Optional leading whitespace
+        rf"(?P<{pname}>"  # Named group
+        r"(?:"
+    )
+
+    # Add DIGIT pattern for each column, with whitespace
+    for _ in range(num_cols):
+        pattern += r"\s*"  # Optional whitespace before each number
+        pattern += DIGIT
+    pattern += r")+"  # Repeat for multiple lines
+    pattern += r")"  # End of named group
+    return pattern
+
+
+TWO_COL_NUM = create_multicol_pattern(2, "twocolnum")
+THREE_COL_NUM = create_multicol_pattern(3, "threecolnum")

chemparseplot-0.0.2/chemparseplot/plot/__init__.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT

chemparseplot-0.0.2/chemparseplot/units.py

@@ -0,0 +1,15 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+import warnings
+
+import pint
+
+ureg = pint.UnitRegistry(cache_folder=":auto:")
+ureg.define("kcal_mol = kcal / 6.02214076e+23 = kcm")
+Q_ = ureg.Quantity
+
+# Silence NEP 18 warning
+with warnings.catch_warnings():
+    warnings.simplefilter("ignore")
+    Q_([])

chemparseplot-0.0.2/pyproject.toml

@@ -0,0 +1,216 @@
+[build-system]
+build-backend = "hatchling.build"
+requires = [
+  "hatch-vcs",
+  "hatchling",
+]
+
+[tool.hatch.build.hooks.vcs]
+version-file = "_version.py"
+
+[tool.hatch.build]
+include = [
+  "chemparseplot/**/*.py",
+  "chemparseplot/*.py",
+  "/tests",
+]
+
+
+
+[tool.pdm.dev-dependencies]
+lint = [
+    "ruff>=0.1.6",
+]
+test = [
+    "pytest>=7.4.3",
+    "pytest-cov>=4.1.0",
+]
+nbdoc = [
+    "jupyterlab>=4.0.9",
+    "jupytext>=1.15.2",
+    "ase>=3.22.1",
+]
+release_aid = [
+    "tbump>=6.11.0",
+    "towncrier>=23.11.0",
+]
+
+[tool.pdm.scripts]
+check_ruff = "ruff ."
+ruff_fix = "ruff --fix ."
+ruff_format = "ruff format ."
+lint = {composite = ["ruff_fix", "ruff_format"]}
+test = "pytest --cov=chemparseplot tests"
+
+[project]
+name = "chemparseplot"
+description = "Parsers and plotting tools for computational chemistry"
+readme = "readme.md"
+keywords = [
+  "compchem",
+  "parser",
+  "plot",
+]
+license = {text = "MIT"}
+authors = [
+    { name = "Rohit Goswami", email = "rog32@hi.is" },
+]
+requires-python = ">=3.9"
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: Implementation :: CPython",
+]
+dynamic = [
+  "version",
+]
+dependencies = [
+  "numpy>=1.26.2",
+  "pint>=0.22",
+]
+[project.optional-dependencies]
+plot = [
+  "matplotlib>=3.8.2",
+]
+doc = [
+    "sphinx>=7.2.6",
+    "myst-parser>=2.0.0",
+    "sphinxcontrib-apidoc>=0.4.0",
+    "sphinx-copybutton>=0.5.2",
+    "sphinx-sitemap>=2.5.1",
+    "sphinx-togglebutton>=0.3.2",
+    "sphinx-library>=1.1.2",
+    "sphinx-autodoc2>=0.5.0",
+    "mdit-py-plugins>=0.3.4",
+    "myst-nb>=1.0.0",
+]
+[project.urls]
+Documentation = "https://github.com/HaoZeke/chemparseplot#readme"
+Issues = "https://github.com/HaoZeke/chemparseplot/issues"
+Source = "https://github.com/HaoZeke/chemparseplot"
+
+[tool.hatch.version]
+source = "vcs"
+
+[tool.ruff]
+target-version = "py312"
+line-length = 90
+select = [
+  "A",
+  "ARG",
+  "B",
+  "C",
+  "DTZ",
+  "E",
+  "EM",
+  "F",
+  "FBT",
+  "I",
+  "ICN",
+  "ISC",
+  "N",
+  "PLC",
+  "PLE",
+  "PLR",
+  "PLW",
+  "Q",
+  "RUF",
+  "S",
+  "T",
+  "TID",
+  "UP",
+  "W",
+  "YTT",
+]
+ignore = [
+  # Implicitly concatenated string literals on one line
+  "ISC001",
+  # Allow non-abstract empty methods in abstract base classes
+  "B027",
+  # Allow boolean positional values in function calls, like `dict.get(... True)`
+  "FBT003",
+  # Ignore checks for possible passwords
+  "S105", "S106", "S107",
+  # Ignore complexity
+  "C901", "PLR0911", "PLR0912", "PLR0913", "PLR0915",
+]
+unfixable = [
+  # Don't touch unused imports
+  "F401",
+]
+
+[tool.ruff.isort]
+known-first-party = ["chemparseplot"]
+
+[tool.ruff.flake8-tidy-imports]
+ban-relative-imports = "all"
+
+[tool.ruff.per-file-ignores]
+# Tests can use magic values, assertions, and relative imports
+"tests/**/*" = ["PLR2004", "S101", "TID252"]
+# __init__.py can import without use
+"__init__.py" = ["F401"]
+
+[tool.coverage.run]
+source_pkgs = ["chemparseplot"]
+branch = true
+parallel = true
+omit = [
+  "_version.py",
+]
+
+[tool.coverage.paths]
+chemparseplot = ["src/chemparseplot", "*/chemparseplot/src/chemparseplot"]
+tests = ["tests"]
+
+[tool.coverage.report]
+exclude_lines = [
+  "no cov",
+  "if __name__ == .__main__.:",
+  "if TYPE_CHECKING:",
+]
+
+[tool.towncrier]
+start_string = "<!-- towncrier release notes start -->\n"
+underlines = ["", "", ""]
+single_file = true
+filename = "CHANGELOG.md"
+directory = "doc/release/upcoming_changes/"
+issue_format = "[#{issue}](https://github.com/HaoZeke/chemparseplot/issues/{issue})"
+title_format = "## [{version}](https://github.com/HaoZeke/chemparseplot/tree/{version}) - {project_date}"
+all_bullets = false
+
+[[tool.towncrier.type]]
+directory = "removed"
+name = "Removed"
+showcontent = true
+
+[[tool.towncrier.type]]
+directory = "deprecated"
+name = "Deprecated"
+showcontent = true
+
+[[tool.towncrier.type]]
+directory = "added"
+name = "Added"
+showcontent = true
+
+[[tool.towncrier.type]]
+directory = "changed"
+name = "Changed"
+showcontent = true
+
+[[tool.towncrier.type]]
+directory = "fixed"
+name = "Fixed"
+showcontent = true
+
+[[tool.towncrier.type]]
+directory = "misc"
+name = "Miscellaneous"
+showcontent = true

chemparseplot-0.0.2/readme.md

@@ -0,0 +1,74 @@
+
+# Table of Contents
+
+1.  [About](#orgea43256)
+    1.  [Features](#org6a31408)
+        1.  [Supported Engines [WIP]](#orgbfa09d8)
+    2.  [Rationale](#org4c00d67)
+2.  [License](#orge2168a3)
+
+
+<a id="orgea43256"></a>
+
+# About
+
+![img](branding/logo/chemparseplot_logo.png)
+
+[![Hatch project](https://img.shields.io/badge/%F0%9F%A5%9A-Hatch-4051b5.svg)](https://github.com/pypa/hatch)
+
+A **pure-python**<sup><a id="fnr.1" class="footref" href="#fn.1" role="doc-backlink">1</a></sup> project to provide unit-aware uniform visualizations
+of common computational chemistry tasks. Essentially this means we provide:
+
+-   Plotting scripts for specific workflows
+-   Parsers for various software outputs
+
+This is a spin-off from `wailord` ([here](https://wailord.xyz)) which is meant to handle aggregated
+runs in a specific workflow, while here the goal is to do no input handling and
+very pragmatic output parsing, with the goal of generating uniform plots.
+
+
+<a id="org6a31408"></a>
+
+## Features
+
+-   [Scientific color maps](https://www.fabiocrameri.ch/colourmaps/) for the plots
+    -   Camera ready
+-   Unit preserving
+    -   Via `pint`
+
+
+<a id="orgbfa09d8"></a>
+
+### Supported Engines [WIP]
+
+-   ORCA (**5.x**)
+    -   Scanning energies over a degree of freedom (`OPT` scans)
+    -   Nudged elastic band (`NEB`) visualizations (over the "linearized" reaction
+        coordinate)
+
+
+<a id="org4c00d67"></a>
+
+## Rationale
+
+`wailord` is for production runs, however often there is a need to collect
+"spot" calculation visualizations, which should nevertheless be uniform, i.e.
+either Bohr/Hartree or Angstron/eV or whatever.
+
+Also I couldn't find (m)any scripts using the scientific colorschemes.
+
+
+<a id="orge2168a3"></a>
+
+# License
+
+MIT. However, this is an academic resource, so **please cite** as much as possible
+via:
+
+-   The Zenodo DOI for general use.
+-   The `wailord` paper for ORCA usage
+
+
+# Footnotes
+
+<sup><a id="fn.1" href="#fnr.1">1</a></sup> To distinguish it from my other thin-python wrapper projects

chemparseplot-0.0.2/tests/parse/orca/test_geomscan.py

@@ -0,0 +1,55 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+import numpy as np
+
+from chemparseplot.parse.orca.geomscan import extract_energy_data
+from chemparseplot.units import Q_
+
+# Sample data snippet
+sample_data = """
+The Calculated Surface using the 'Actual Energy'
+   7.55890395  -0.74239862
+   7.32930292  -0.74349939
+   7.09970189  -0.74467446
+
+The Calculated Surface using the SCF energy
+   7.55890395  -0.74239862
+   7.32930292  -0.74349939
+   7.09970189  -0.74467446
+"""
+
+
+def test_extract_actual_energy():
+    x_expected = Q_([7.55890395, 7.32930292, 7.09970189], "bohr")
+    y_expected = Q_([-0.74239862, -0.74349939, -0.74467446], "hartree")
+
+    x_actual, y_actual = extract_energy_data(sample_data, "Actual Energy")
+
+    assert np.allclose(x_actual.magnitude, x_expected.magnitude)
+    assert np.allclose(y_actual.magnitude, y_expected.magnitude)
+    assert x_actual.units == x_expected.units
+    assert y_actual.units == y_expected.units
+
+
+def test_extract_scf_energy():
+    x_expected = Q_([7.55890395, 7.32930292, 7.09970189], "bohr")
+    y_expected = Q_([-0.74239862, -0.74349939, -0.74467446], "hartree")
+
+    x_scf, y_scf = extract_energy_data(sample_data, "SCF energy")
+
+    assert np.allclose(x_scf.magnitude, x_expected.magnitude)
+    assert np.allclose(y_scf.magnitude, y_expected.magnitude)
+    assert x_scf.units == x_expected.units
+    assert y_scf.units == y_expected.units
+
+
+def test_empty_data():
+    x_empty, y_empty = extract_energy_data("", "Actual Energy")
+    assert x_empty.size == 0 and y_empty.size == 0
+
+
+def test_malformed_data():
+    malformed_data = "Some random text"
+    x_malformed, y_malformed = extract_energy_data(malformed_data, "Actual Energy")
+    assert x_malformed.size == 0 and y_malformed.size == 0

chemparseplot-0.0.2/tests/parse/orca/test_interp.py

@@ -0,0 +1,44 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+import pytest
+from chemparseplot.parse.orca.neb.interp import extract_interp_points
+from chemparseplot.basetypes import nebiter, nebpath
+from chemparseplot.units import Q_, ureg
+
+def test_extract_interp_points_valid_input():
+    # Example valid text input
+    text_input = """Iteration: 1
+Images: Distance  (Bohr), Energy (Eh)
+13.0 0.0 0.0
+1.0 10.0 -0.5
+Iteration: 2
+Images: Distance  (Bohr), Energy (Eh)
+0.0 0.2 0.3
+1.0 20.0 -1.0
+"""
+    # Extract data
+    result = extract_interp_points(text_input)
+
+    # Check if result is a list of nebiter
+    assert isinstance(result, list)
+    assert all(isinstance(item, nebiter) for item in result)
+
+    # Check if each nebiter contains a nebpath with correct values and units
+    assert result[0].iteration == 1
+    assert result[0].nebpath.norm_dist.magnitude[0] == 13.0
+    assert result[0].nebpath.arc_dist.magnitude[0] == 0.0
+    assert result[0].nebpath.energy.magnitude[0] == 0.0
+    assert result[0].nebpath.norm_dist.units == ureg.Unit('dimensionless')
+    assert result[0].nebpath.arc_dist.units == 'bohr'
+    assert result[0].nebpath.energy.units == 'hartree'
+    assert result[1].nebpath.norm_dist.magnitude[0] == 0.0
+    assert result[1].nebpath.arc_dist.magnitude[0] == 0.2
+    assert result[1].nebpath.energy.magnitude[0] == 0.3
+
+def test_extract_interp_points_invalid_input():
+    # Example invalid text input
+    text_input = """This is not a valid input for the function."""
+    result = extract_interp_points(text_input)
+    # Expecting empty list for invalid input
+    assert result == []

chemparseplot-0.0.2/tests/parse/test_converter.py

@@ -0,0 +1,26 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+import re
+
+import numpy as np
+
+from chemparseplot.parse import converter as conv
+from chemparseplot.parse import patterns as pat
+
+
+def test_numeric_from_match():
+    # Create a sample string that matches the TWO_COL_NUM pattern
+    sample_data = " 1.23 4.56\n7.89 10.11"
+
+    # Generate the regex pattern for two columns
+    pattern = pat.create_multicol_pattern(2, "twocolnum")
+    regex = re.compile(pattern)
+
+    match = regex.search(sample_data)
+    assert match is not None
+
+    matched_data = match.group("twocolnum")
+    result_array = conv.np_txt(matched_data)
+    assert isinstance(result_array, np.ndarray)
+    assert np.array_equal(result_array, np.array([[1.23, 4.56], [7.89, 10.11]]))

chemparseplot-0.0.2/tests/parse/test_patterns.py

@@ -0,0 +1,32 @@
+# SPDX-FileCopyrightText: 2023-present Rohit Goswami <rog32@hi.is>
+#
+# SPDX-License-Identifier: MIT
+import re
+
+import pytest
+
+from chemparseplot.parse import patterns as pat
+
+
+def test_num_cols_less_than_one():
+    with pytest.raises(ValueError):
+        pat.create_multicol_pattern(0)
+
+
+def test_two_col_pattern():
+    pattern = pat.create_multicol_pattern(2)
+    regex = re.compile(pattern)
+    assert regex.search("  1.23  -4.56")
+    assert not regex.search("1.23")
+
+
+def test_three_col_pattern():
+    pattern = pat.create_multicol_pattern(3)
+    regex = re.compile(pattern)
+    assert regex.search(" 1.23 -4.56  7.89")
+    assert not regex.search("1.23 -4.56")
+
+
+def test_custom_pattern_name():
+    pattern = pat.create_multicol_pattern(2, "customname")
+    assert "(?P<customname>" in pattern