Merge pull request #1 from DLR-Institute-of-Future-Fuels/binary_database_feature

Binary database feature: This feature alows reading the thermdynamic data from a binary file to minimize memory usage and loading time.

.flake8

@@ -13,7 +13,9 @@ exclude =
     build,
     dist,
     .conda,
-    tests/autogenerated_*
+    tests/autogenerated_*,
+    .venv,
+    venv
 
 # Enable specific plugins or options
 # Example: Enabling flake8-docstrings

.github/workflows/ci.yml

@@ -15,30 +15,29 @@ jobs:
         python-version: ["3.10", 3.11, 3.12, 3.13]
 
     steps:
-    # Step 1: Check out the code from the repository
     - name: Check out code
       uses: actions/checkout@v4
 
-    # Step 2: Set up Python
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
 
-    # Step 3: Install dependencies
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
         python -m pip install -e .[dev]
 
-    # Step 4: Lint with flake8
+    - name: Prepare data and compile thermo database
+      run: |
+        python thermo_data/combine_data.py thermo_data/combined_data.yaml thermo_data/nasa9*.yaml thermo_data/nasa9*.xml
+        python thermo_data/compile_to_bin.py thermo_data/combined_data.yaml src/gaspype/data/therm_data.bin
+
     - name: Lint code with flake8
       run: flake8
 
-    # Step 5: Check types with mypy
     - name: Type checking with mypy
       run: mypy
 
-    # Step 6: Run tests
     - name: Run tests with pytest
       run: pytest

.gitignore

@@ -10,3 +10,7 @@ __pycache__
 tests/autogenerated_*.py
 docs/build/
 docs/source/modules.md
+venv/
+.venv/
+thermo_data/combined_data.yaml
+src/gaspype/data/therm_data.bin

pyproject.toml

@@ -13,7 +13,6 @@ classifiers = [
     "Operating System :: OS Independent",
 ]
 dependencies = [
-  "pyyaml>=6.0.1",
   "numpy>2.0.0",
   "scipy>1.12.0",
 ]
@@ -30,7 +29,7 @@ build-backend = "setuptools.build_meta"
 where = ["src"]
 
 [tool.setuptools.package-data]
-gaspype = ["data/*.yaml"]
+gaspype = ["data/therm_data.bin"]
 
 [project.optional-dependencies]
 dev = [
@@ -39,6 +38,7 @@ dev = [
     "pytest",
     "pandas",
     "cantera",
+    "pyyaml>=6.0.1",
     "types-PyYAML",
     "scipy-stubs"
 ]

src/gaspype/__init__.py

@@ -2,9 +2,9 @@ import numpy as np
 from numpy.typing import NDArray
 from typing import Literal, Sequence, Callable, Any, TypeVar, Iterator, overload
 from math import log as ln, ceil, exp
-import yaml
 from scipy.optimize import minimize, root
 from scipy.linalg import null_space
+from gaspype._phys_data import atomic_weights, db_reader
 import re
 import pkgutil
 
@@ -14,15 +14,9 @@ FloatArray = NDArray[NDFloat]
 
 _T = TypeVar('_T', 'fluid', 'elements')
 
-
-def _get_data(path: str) -> Any:
-    data = pkgutil.get_data(__name__, path)
-    assert data is not None
-    return yaml.safe_load(data)
-
-
-_atomic_weights = _get_data('data/atomic_prop.yaml')['atomic_weights']['data']
-_species_data = {s['name']: s for s in _get_data('data/therm_prop.yaml')['species']}
+data = pkgutil.get_data(__name__, 'data/therm_data.bin')
+assert data is not None, 'Could not load thermodynamic data'
+species_db = db_reader(data)
 
 kB = 1.380649e-23  # J/K
 NA = 6.02214076e23  # 1/mol
@@ -82,21 +76,22 @@ def species(pattern: str = '*', element_names: str | list[str] = [], use_regex:
         elements = set(element_names)
 
     for el in elements:
-        assert el in _atomic_weights, f'element {el} unknown'
+        assert el in atomic_weights, f'element {el} unknown'
 
     if not use_regex:
-        el_pattern = '|'.join([el for el in _atomic_weights.keys()])
+        el_pattern = '|'.join([el for el in atomic_weights.keys()])
         pattern = pattern.replace('*', '.*')
         pattern = pattern.replace('#', '\\d*')
         pattern = pattern.replace('$', '(' + el_pattern + ')')
         pattern = '^' + pattern + '(,.*)?$'
 
-    return sorted(list(
-        [
-            s['name'] for s in _species_data.values()
-            if re.fullmatch(pattern, s['name']) and
-            (len(elements) == 0 or set(s['composition'].keys()).issubset(elements))
-        ]))
+    if element_names == []:
+        return [sn for sn in species_db.names if re.fullmatch(pattern, sn)]
+    else:
+        return [
+            s.name for s in species_db
+            if re.fullmatch(pattern, s.name) and
+            (len(elements) == 0 or set(s.composition.keys()).issubset(elements))]
 
 
 def set_solver(solver: Literal['gibs minimization', 'system of equations']) -> None:
@@ -162,17 +157,17 @@ class fluid_system:
         self._t_offset = int(t_min)
         self.species = species
         self.active_species = species
-        element_compositions: list[dict[str, float]] = list()
+        element_compositions: list[dict[str, int]] = list()
 
         for i, s in enumerate(species):
-            if s not in _species_data:
+            species_data = species_db.read(s)
+            if not species_data:
                 raise Exception(f'Species {s} not found')
-            element_compositions.append(_species_data[s]['composition'])
+            element_compositions.append(species_data.composition)
 
-            data = _species_data[s]['thermo']
-            assert data['model'] == 'NASA9'
+            assert species_data.model == 9, 'Only NASA9 polynomials are supported'
 
-            for t1, t2, a in zip(data['temperature-ranges'][:-1], data['temperature-ranges'][1:], data['data']):
+            for t1, t2, a in zip(species_data.t_range[:-1], species_data.t_range[1:], species_data.data):
 
                 for j, T in enumerate(temperature_base_points):
                     if t2 >= T >= t1:
@@ -193,7 +188,7 @@ class fluid_system:
         self.elements: list[str] = sorted(list(set(k for ac in element_compositions for k in ac.keys())))
         self.array_species_elements = np.array([[ec[el] if el in ec else 0.0 for el in self.elements] for ec in element_compositions])
 
-        self.array_atomic_mass = np.array([_atomic_weights[el] for el in self.elements]) * 1e-3  # kg/mol
+        self.array_atomic_mass = np.array([atomic_weights[el] for el in self.elements]) * 1e-3  # kg/mol
         self.array_molar_mass: FloatArray = np.sum(self.array_atomic_mass * self.array_species_elements, axis=-1)  # kg/mol
 
         self.array_stoichiometric_coefficients: FloatArray = np.array(null_space(self.array_species_elements.T), dtype=NDFloat).T
@@ -315,7 +310,7 @@ class fluid:
 
         self.array_composition: FloatArray = comp_array
         self.total: FloatArray | float = np.sum(self.array_composition, axis=-1, dtype=NDFloat)
-        self.array_fractions = self.array_composition / (np.expand_dims(self.total, -1) + _epsy)
+        self.array_fractions: FloatArray = self.array_composition / (np.expand_dims(self.total, -1) + _epsy)
         self.shape: _Shape = self.array_composition.shape[:-1]
         self.fs = fs
         self.array_elemental_composition: FloatArray = np.dot(self.array_composition, fs.array_species_elements)
@@ -899,7 +894,7 @@ def _equilibrium_eq(fs: fluid_system, element_composition: FloatArray, t: float,
 
         return (np.hstack([eq_resid, ab_resid]), np.concatenate([j_eq, j_ab], axis=0))
 
-    ret = root(residuals, logn_start, jac=True, tol=1e-30)  # type: ignore
+    ret = root(residuals, logn_start, jac=True, tol=1e-30)
     n = np.exp(np.array(ret['x'], dtype=NDFloat))
 
     return n * el_max

src/gaspype/_phys_data.py

@@ -0,0 +1,137 @@
+import struct
+from typing import Generator, Iterator
+
+
+class SpeciesData():
+    """Class to hold the physical data for a species.
+    Attributes:
+        comp: Dictionary of species composition with element symbols as keys and their counts as values.
+        model: Number of polynomial coefficients used in the model.
+        ref_string: Reference string for the data source.
+        t_range: List of temperatures nodes marking intervals.
+        data: List of lists containing physical data for each temperature interval.
+    """
+
+    def __init__(self, name: str, comp: dict[str, int], model: int, ref: str, t_range: list[float], data: list[list[float]]):
+        self.name = name
+        self.composition: dict[str, int] = comp
+        self.model: int = model
+        self.ref_string: str = ref
+        self.t_range: list[float] = t_range
+        self.data: list[list[float]] = data
+
+    def __repr__(self) -> str:
+        return (f"Name: {self.name}\n" +
+                f"Composition: {self.composition}\n" +
+                f"Model: {self.model}\n" +
+                f"Reference: {self.ref_string}\n" +
+                f"Temperatures: {self.t_range}\n" +
+                f"Data: {self.data}".replace('),', '),\n'))
+
+
+class db_reader():
+    """Class to read and parse the binary gas phase species database.
+
+    Attributes:
+        names: An iterator over the names of species in the database.
+    """
+
+    header_len = 8
+
+    def __init__(self, inp_data: bytes):
+        """ Initializes the database reader with binary data.
+        Args:
+            inp_data: The binary data of the gas phase species database.
+        """
+        assert inp_data[:4] == b'gapy', 'Unknown data format'
+        self._bin_data = inp_data
+        self._name_count = struct.unpack('<I', self._bin_data[4:8])[0]
+        species_names = self._bin_data[db_reader.header_len:(db_reader.header_len + self._name_count)].decode('ASCII').split(' ')
+        self._index = {s: i for i, s in enumerate(species_names)}
+
+    @property
+    def names(self) -> Iterator[str]:
+        return iter(self._index.keys())
+
+    def __iter__(self) -> Generator[SpeciesData, None, None]:
+        return (d for d in (self.read(species) for species in self._index.keys()) if d is not None)
+
+    def __contains__(self, name: str) -> bool:
+        """ Checks if a species name is present in the database.
+        Args:
+            name: The name of the species to check.
+
+        Returns:
+            bool: True if the species name is present
+        """
+        return name in self._index
+
+    def __getitem__(self, name: str) -> SpeciesData:
+        species_data = self.read(name)
+        assert species_data, f"Species '{name}' not found in the database."
+        return species_data
+
+    def read(self, name: str) -> SpeciesData | None:
+        """ Reads the physical data for a given species name from the binary data.
+        Args:
+            name (str): The name of the species to read data for.
+
+        Returns:
+            phys_data: An instance of the phys_data class containing the physical data.
+        """
+        if name not in self._index:
+            return None
+
+        head_offset = self._name_count + db_reader.header_len + self._index[name] * db_reader.header_len
+
+        head = struct.unpack('<I4B', self._bin_data[head_offset:head_offset + db_reader.header_len])
+
+        offset = head[0]
+        composition_count = head[1]
+        model = head[2]
+        temperature_count = head[3]
+        ref_string_len = head[4]
+
+        td_data_num = (temperature_count - 1) * model
+        data_len = composition_count * 3 + (temperature_count + td_data_num) * 4 + ref_string_len
+
+        format_string = '<' + '2sB' * composition_count + f'{temperature_count}f{td_data_num}f{ref_string_len}s'
+
+        bindat = struct.unpack(format_string, self._bin_data[offset:offset + data_len])
+        comp = {bindat[i * 2].strip().decode('ASCII'): bindat[i * 2 + 1] for i in range(composition_count)}
+
+        noffs = composition_count * 2
+        t_range = list(bindat[noffs:noffs + temperature_count])
+
+        noffs += temperature_count
+        data = [list(bindat[(noffs + i * model):(noffs + (i + 1) * model)]) for i in range(temperature_count - 1)]
+        ref = bindat[-1].decode('utf-8')
+
+        return SpeciesData(name, comp, model, ref, t_range, data)
+
+
+"""
+Atomic weights values are used from CIAAW.
+when a single value is given. Available online at
+http://www.ciaaw.org/atomic-weights.htm
+When a range of values is given in the CIAAW table, the "conventional
+atomic weight" from the IUPAC Periodic Table is used. Available
+online at https://iupac.org/wp-content/uploads/2018/12/IUPAC_Periodic_Table-01Dec18.pdf
+"""
+atomic_weights = {'H': 1.008, 'He': 4.002602, 'Li': 6.94, 'Be': 9.0121831, 'B': 10.81, 'C': 12.011,
+                  'N': 14.007, 'O': 15.999, 'F': 18.998403163, 'Ne': 20.1797, 'Na': 22.98976928,
+                  'Mg': 24.305, 'Al': 26.9815384, 'Si': 28.085, 'P': 30.973761998, 'S': 32.06,
+                  'Cl': 35.45, 'Ar': 39.95, 'K': 39.0983, 'Ca': 40.078, 'Sc': 44.955908,
+                  'Ti': 47.867, 'V': 50.9415, 'Cr': 51.9961, 'Mn': 54.938043, 'Fe': 55.845,
+                  'Co': 58.933194, 'Ni': 58.6934, 'Cu': 63.546, 'Zn': 65.38, 'Ga': 69.723,
+                  'Ge': 72.63, 'As': 74.921595, 'Se': 78.971, 'Br': 79.904, 'Kr': 83.798,
+                  'Rb': 85.4678, 'Sr': 87.62, 'Y': 88.90584, 'Zr': 91.224, 'Nb': 92.90637,
+                  'Mo': 95.95, 'Ru': 101.07, 'Rh': 102.90549, 'Pd': 106.42, 'Ag': 107.8682,
+                  'Cd': 112.414, 'In': 114.818, 'Sn': 118.71, 'Sb': 121.76, 'Te': 127.6,
+                  'I': 126.90447, 'Xe': 131.293, 'Cs': 132.90545196, 'Ba': 137.327, 'La': 138.90547,
+                  'Ce': 140.116, 'Pr': 140.90766, 'Nd': 144.242, 'Sm': 150.36, 'Eu': 151.964,
+                  'Gd': 157.25, 'Tb': 158.925354, 'Dy': 162.5, 'Ho': 164.930328, 'Er': 167.259,
+                  'Tm': 168.934218, 'Yb': 173.045, 'Lu': 174.9668, 'Hf': 178.49, 'Ta': 180.94788,
+                  'W': 183.84, 'Re': 186.207, 'Os': 190.23, 'Ir': 192.217, 'Pt': 195.084,
+                  'Au': 196.96657, 'Hg': 200.592, 'Tl': 204.38, 'Pb': 207.2, 'Bi': 208.9804,
+                  'Th': 232.0377, 'Pa': 231.03588, 'U': 238.02891}

src/gaspype/data/atomic_prop.yaml

@@ -1,90 +0,0 @@
-atomic_weights:
-  data:
-    Ag: 107.8682
-    Al: 26.9815384
-    Ar: 39.95
-    As: 74.921595
-    Au: 196.96657
-    B: 10.81
-    Ba: 137.327
-    Be: 9.0121831
-    Bi: 208.9804
-    Br: 79.904
-    C: 12.011
-    Ca: 40.078
-    Cd: 112.414
-    Ce: 140.116
-    Cl: 35.45
-    Co: 58.933194
-    Cr: 51.9961
-    Cs: 132.90545196
-    Cu: 63.546
-    Dy: 162.5
-    Er: 167.259
-    Eu: 151.964
-    F: 18.998403163
-    Fe: 55.845
-    Ga: 69.723
-    Gd: 157.25
-    Ge: 72.63
-    H: 1.008
-    He: 4.002602
-    Hf: 178.49
-    Hg: 200.592
-    Ho: 164.930328
-    I: 126.90447
-    In: 114.818
-    Ir: 192.217
-    K: 39.0983
-    Kr: 83.798
-    La: 138.90547
-    Li: 6.94
-    Lu: 174.9668
-    Mg: 24.305
-    Mn: 54.938043
-    Mo: 95.95
-    N: 14.007
-    Na: 22.98976928
-    Nb: 92.90637
-    Nd: 144.242
-    Ne: 20.1797
-    Ni: 58.6934
-    O: 15.999
-    Os: 190.23
-    P: 30.973761998
-    Pa: 231.03588
-    Pb: 207.2
-    Pd: 106.42
-    Pr: 140.90766
-    Pt: 195.084
-    Rb: 85.4678
-    Re: 186.207
-    Rh: 102.90549
-    Ru: 101.07
-    S: 32.06
-    Sb: 121.76
-    Sc: 44.955908
-    Se: 78.971
-    Si: 28.085
-    Sm: 150.36
-    Sn: 118.71
-    Sr: 87.62
-    Ta: 180.94788
-    Tb: 158.925354
-    Te: 127.6
-    Th: 232.0377
-    Ti: 47.867
-    Tl: 204.38
-    Tm: 168.934218
-    U: 238.02891
-    V: 50.9415
-    W: 183.84
-    Xe: 131.293
-    Y: 88.90584
-    Yb: 173.045
-    Zn: 65.38
-    Zr: 91.224
-  note: Atomic weights values are used from CIAAW.when a single value is given. Available
-    online athttp://www.ciaaw.org/atomic-weights.htmWhen a range of values is given
-    in the CIAAW table, the "conventionalatomic weight" from the IUPAC Periodic Table
-    is used. Availableonline at https://iupac.org/wp-content/uploads/2018/12/IUPAC_Periodic_Table-01Dec18.pdf

src/gaspype/data/units.yaml

@@ -1,562 +0,0 @@
-prefixes:
-  - symbol: 'y'
-    name: yocto
-    value: 1.0e-24
-  - symbol: z
-    name: zepto
-    value: 1.0e-21
-  - symbol: a
-    name: atto
-    value: 1.0e-18
-  - symbol: f
-    name: femto
-    value: 1.0e-15
-  - symbol: p
-    name: pico
-    value: 1.0e-12
-  - symbol: 'n'
-    name: nano
-    value: 1.0e-9
-  - symbol: µ
-    name: micro
-    value: 1.0e-6
-  - symbol: m
-    name: milli
-    value: 1.0e-3
-  - symbol: c
-    name: centi
-    value: 1.0e-2
-  - symbol: d
-    name: deci
-    value: 1.0e-2
-  - symbol: da
-    name: deca
-    value: 1.0e+1
-  - symbol: h
-    name: hecto
-    value: 1.0e+2
-  - symbol: k
-    name: kilo
-    value: 1.0e+3
-  - symbol: M
-    name: mega
-    value: 1.0e+6
-  - symbol: G
-    name: giga
-    value: 1.0e+9
-  - symbol: T
-    name: tera
-    value: 1.0e+12
-  - symbol: P
-    name: peta
-    value: 1.0e+15
-  - symbol: E
-    name: exa
-    value: 1.0e+18
-  - symbol: Z
-    name: zetta
-    value: 1.0e+21
-  - symbol: 'Y'
-    name: yotta
-    value: 1.0e+24
-
-units:
-  - symbol: Pa
-    alt_identifier: [pascal]
-    si_base_unit:
-      kg: 1
-      m: -1
-      s: -2
-    typical_si_prefixes: [m, h, k, M, G]
-    si_factor: 1.0
-    usage: [pressure, strain]
-
-  - symbol: 'N'
-    alt_identifier: [newton]
-    si_base_unit:
-      kg: 1
-      m: 1
-      s: -2
-    typical_si_prefixes: [m, k, M, G]
-    si_factor: 1.0
-    usage: [force]
-
-  - symbol: lbf
-    alt_identifier: [pound]
-    si_base_unit:
-      kg: 1
-      m: 1
-      s: -2
-    si_factor: 4.4482
-    usage: [force]
-
-  - symbol: dyn
-    alt_identifier: [dyne]
-    si_base_unit:
-      kg: 1
-      m: 1
-      s: -2
-    typical_si_prefixes: []
-    si_factor: 1.0e-5
-    usage: [force]
-
-  - symbol: atm
-    alt_identifier: [atmosphere]
-    si_base_unit:
-      kg: 1
-      m: -1
-      s: -2
-    typical_si_prefixes: []
-    si_factor: 101325.0
-    usage: [pressure]
-
-  - symbol: t
-    alt_identifier: [ton]
-    si_base_unit:
-      kg: 1
-    typical_si_prefixes: []
-    si_factor: 1000.0
-    usage: [mass]
-
-  - symbol: u
-    alt_identifier: [atomic mass unit]
-    si_base_unit:
-      kg: 1
-    typical_si_prefixes: []
-    si_factor: 1.66053906660e-27
-    usage: [mass]
-
-  - symbol: g
-    alt_identifier: [gram]
-    si_base_unit:
-      kg: 1
-    typical_si_prefixes: [k]
-    si_factor: 0.001
-    usage: [mass]
-
-  - symbol: bar
-    alt_identifier: [bar]
-    si_base_unit:
-      kg: 1
-      m: -1
-      s: -2
-    typical_si_prefixes: []
-    si_factor: 100000.0
-    usage: [pressure]
-
-  - symbol: kgf
-    alt_identifier: [kilogram-force]
-    si_base_unit:
-      kg: 1
-      m: 1
-      s: -2
-    typical_si_prefixes: []
-    si_factor: 9.80665
-    usage: [force]
-
-  - symbol: psi
-    alt_identifier: [pound-force per square inch]
-    si_base_unit:
-      kg: 1
-      m: -1
-      s: -2
-    typical_si_prefixes: []
-    si_factor: 6894.75729
-    usage: [pressure]
-
-  - symbol: oz
-    alt_identifier: [ounce]
-    si_base_unit:
-      kg: 1
-    typical_si_prefixes: []
-    si_factor: 0.0283495
-    usage: [mass]
-
-  - symbol: carat
-    alt_identifier: [carat]
-    si_base_unit:
-      kg: 1
-    typical_si_prefixes: []
-    si_factor: 0.0002
-    usage: [mass]
-
-  - symbol: grain
-    alt_identifier: [grain]
-    si_base_unit:
-      kg: 1
-    typical_si_prefixes: []
-    si_factor: 0.00006479891
-    usage: [mass]
-
-  - symbol: torr
-    alt_identifier: [torr, mmHg]
-    si_base_unit:
-      kg: 1
-      m: -1
-      s: -2
-    typical_si_prefixes: []
-    si_factor: 133.322
-    usage: [pressure]
-
-  - symbol: mol
-    alt_identifier: [mole]
-    si_base_unit:
-      mol: 1
-    typical_si_prefixes: [m, k]
-    si_factor: 1.0
-    usage: [amount of substance]
-
-  - symbol: m
-    alt_identifier: [meter]
-    si_base_unit:
-      m: 1
-    typical_si_prefixes: [p, 'n', µ, m, c, d, k]
-    si_factor: 1.0
-    usage: [length]
-
-  - symbol: mm
-    alt_identifier: [millimeter]
-    si_base_unit:
-      m: 1
-    typical_si_prefixes: []
-    si_factor: 0.001
-    usage: [length]
-
-  - symbol: in
-    alt_identifier: [inch]
-    si_base_unit:
-      m: 1
-    typical_si_prefixes: []
-    si_factor: 0.0254
-    usage: [length]
-
-  - symbol: ft
-    alt_identifier: [foot]
-    si_base_unit:
-      m: 1
-    typical_si_prefixes: []
-    si_factor: 0.3048
-    usage: [length]
-
-  - symbol: yd
-    alt_identifier: [yard]
-    si_base_unit:
-      m: 1
-    typical_si_prefixes: []
-    si_factor: 0.9144
-    usage: [length]
-
-  - symbol: mi
-    alt_identifier: [mile]
-    si_base_unit:
-      m: 1
-    typical_si_prefixes: []
-    si_factor: 1609.34
-    usage: [length]
-
-  - symbol: m²
-    alt_identifier: [square meter]
-    si_base_unit:
-      m: 2
-    typical_si_prefixes: []
-    si_factor: 1.0
-    usage: [area]
-
-  - symbol: cm²
-    alt_identifier: [square centimeter]
-    si_base_unit:
-      m: 2
-    typical_si_prefixes: []
-    si_factor: 1.0e+4
-    usage: [area]
-
-  - symbol: mm²
-    alt_identifier: [square millimeter]
-    si_base_unit:
-      m: 2
-    typical_si_prefixes: []
-    si_factor: 1.0e+6
-    usage: [area]
-
-  - symbol: km²
-    alt_identifier: [square kilometer]
-    si_base_unit:
-      m: 2
-    typical_si_prefixes: []
-    si_factor: 1.0e-6
-    usage: [area]
-
-  - symbol: ac
-    alt_identifier: [acre]
-    si_base_unit:
-      m: 2
-    typical_si_prefixes: []
-    si_factor: 4046.86
-    usage: [area]
-
-  - symbol: ha
-    alt_identifier: [hectare]
-    si_base_unit:
-      m: 2
-    typical_si_prefixes: []
-    si_factor: 10000.0
-    usage: [area]
-
-  - symbol: l
-    alt_identifier: [liter]
-    si_base_unit:
-      m: 3
-    typical_si_prefixes: ['n', µ, m, c, d, h]
-    si_factor: 0.001
-    usage: [volume]
-
-  - symbol: m³
-    alt_identifier: [cubic meter]
-    si_base_unit:
-      m: 3
-    typical_si_prefixes: []
-    si_factor: 1.0
-    usage: [volume]
-
-  - symbol: cm³
-    alt_identifier: [cubic centimeter]
-    si_base_unit:
-      m: 3
-    typical_si_prefixes: []
-    si_factor: 1.0e+6
-    usage: [volume]
-
-  - symbol: dm³
-    alt_identifier: [cubic decimeter]
-    si_base_unit:
-      m: 3
-    typical_si_prefixes: []
-    si_factor: 1.0e+3
-    usage: [volume]
-
-  - symbol: mm³
-    alt_identifier: [cubic millimeter]
-    si_base_unit:
-      m: 3
-    typical_si_prefixes: []
-    si_factor: 1.0e+9
-    usage: [volume]
-
-  - symbol: km³
-    alt_identifier: [cubic kilometer]
-    si_base_unit:
-      m: 3
-    typical_si_prefixes: []
-    si_factor: 1.0e-9
-    usage: [volume]
-
-  - symbol: gal
-    alt_identifier: [gallon]
-    si_base_unit:
-      m: 3
-    typical_si_prefixes: []
-    si_factor: 0.00378541
-    usage: [volume]
-
-  - symbol: K
-    alt_identifier: [kelvin]
-    si_base_unit:
-      K: 3
-    typical_si_prefixes: [m]
-    si_factor: 1.0
-    usage: [temperature]
-
-  - symbol: C
-    alt_identifier: [celsius]
-    si_base_unit:
-      K: 3
-    typical_si_prefixes: [m]
-    si_factor: 1.0
-    offset: 273.15
-    usage: [temperature]
-
-  - symbol: F
-    alt_identifier: [fahrenheit]
-    si_base_unit:
-      K: 1
-    typical_si_prefixes: []
-    si_factor: 0.5555555555
-    offset: 255.372222
-    usage: [temperature]
-
-  - symbol: R
-    alt_identifier: [rankine]
-    si_base_unit:
-      K: 1
-    typical_si_prefixes: []
-    si_factor: 0.5555555555
-    offset: 0
-    usage: [temperature]
-
-  - symbol: V
-    alt_identifier: [volt]
-    si_base_unit:
-      kg: 1
-      m: 2
-      K: -3
-      A: -1
-    typical_si_prefixes: ['n', µ, m, k, M]
-    si_factor: 0.55555555555555
-    usage: [voltage]
-
-  - symbol: A
-    alt_identifier: [ampere]
-    si_base_unit:
-      A: 1
-    typical_si_prefixes: [p, 'n', µ, m, k]
-    si_factor: 0.555555555555555
-    usage: [current]
-
-  - symbol: Barrer
-    alt_identifier: [barrer]
-    si_base_unit:
-      mol: 1
-      s: 1
-      kg: -1
-    typical_si_prefixes: []
-    si_factor: 3.35e-16
-    usage: [permeability]
-
-  - symbol: C
-    alt_identifier: [coulomb]
-    si_base_unit:
-      s: 1
-      A: 1
-    typical_si_prefixes: []
-    si_factor: 1.0
-    usage: [charge]
-
-  - symbol: Ah
-    alt_identifier: [ampere-hour, amp-hour]
-    si_base_unit:
-      s: 1
-      A: 1
-    typical_si_prefixes: [m]
-    si_factor: 3600.0
-    usage: [charge]
-
-  - symbol: F
-    alt_identifier: [farad]
-    si_base_unit:
-      kg: -1
-      m: -2
-      s: 4
-      A: 2
-    typical_si_prefixes: [p, 'n', µ, m]
-    si_factor: 1.0
-    usage: [capacitance]
-
-  - symbol: S
-    alt_identifier: [siemens, moh]
-    si_base_unit:
-      kg: -1
-      m: -2
-      s: 3
-      A: 2
-    typical_si_prefixes: [µ, m]
-    si_factor: 1.0
-    usage: [conductance]
-
-  - symbol: Ω
-    alt_identifier: [ohm]
-    si_base_unit:
-      kg: 11
-      m: 2
-      s: -3
-      A: -2
-    typical_si_prefixes: [m, k, M, G]
-    si_factor: 1.0
-    usage: [resistance]
-
-  - symbol: s
-    alt_identifier: [second, sec]
-    si_base_unit:
-      s: 1
-    typical_si_prefixes: ['n', µ, m]
-    si_factor: 1
-    usage: [time]
-
-  - symbol: min
-    alt_identifier: [minute]
-    si_base_unit:
-      s: 1
-    typical_si_prefixes: []
-    si_factor: 60
-    usage: [time]
-
-  - symbol: h
-    alt_identifier: [hour]
-    si_base_unit:
-      s: 1
-    typical_si_prefixes: []
-    si_factor: 3600
-    usage: [time]
-
-  - symbol: d
-    alt_identifier: [day]
-    si_base_unit:
-      s: 1
-    typical_si_prefixes: []
-    si_factor: 86400
-    usage: [time]
-
-  - symbol: wk
-    alt_identifier: [week]
-    si_base_unit:
-      s: 1
-    typical_si_prefixes: []
-    si_factor: 604800
-    usage: [time]
-
-  - symbol: yr
-    alt_identifier: [year]
-    si_base_unit:
-      s: 1
-    typical_si_prefixes: []
-    si_factor: 31557600
-    usage: [time]
-
-  - symbol: J
-    alt_identifier: [joule]
-    si_base_unit:
-      kg: 1
-      m: 2
-      s: -2
-    typical_si_prefixes: ['n', µ, m, k, M, G, T, P]
-    si_factor: 1
-    usage: [energy]
-
-  - symbol: cal
-    alt_identifier: [calorie]
-    si_base_unit:
-      kg: 1
-      m: 2
-      s: -2
-    typical_si_prefixes: [k]
-    si_factor: 4.184
-    usage: [energy]
-
-  - symbol: Wh
-    alt_identifier: [watt-hour]
-    si_base_unit:
-      kg: 1
-      m: 2
-      s: -2
-    typical_si_prefixes: [m, k, M, G, T]
-    si_factor: 3600
-    usage: [energy]
-
-  - symbol: eV
-    alt_identifier: [electronvolt]
-    si_base_unit:
-      kg: 1
-      m: 2
-      s: -2
-    typical_si_prefixes: [k, M]
-    si_factor: 1.602176634e-19
-    usage: [energy]

tests/test_db_reader.py

@@ -0,0 +1,19 @@
+from gaspype._phys_data import db_reader
+
+
+def test_db_reader():
+    with open('src/gaspype/data/therm_data.bin', 'rb') as f:
+        db = db_reader(f.read())
+
+    assert 'HCl' in db
+    assert 'TEST' not in db
+    assert db['HCl'].name == 'HCl'
+    assert db['CH4'].composition == {'C': 1, 'H': 4}
+    assert db['H2O'].model == 9
+
+    for species in db:
+        print(species.name)
+        assert species.model == 9
+        assert len(species.name) > 0
+        assert len(species.composition) > 0
+        assert any(el in species.name for el in species.composition.keys())

thermo_data/README.md

@@ -0,0 +1,66 @@
+# Data preparation
+Gaspype uses a binary format for thermodynamic data to minimize memory usage and startup time.
+
+## Combine and prepare data
+To prepare the data from YAML and XML sources:
+
+``` bash
+python combine_data.py combined_data.yaml nasa9*.yaml nasa9*.xml
+```
+General Syntax is: ```python combine_data.py OUTPUT_YAML_FILE INPUT_FILE_PATTERN_1 INPUT_FILE_PATTERN_2 ...```
+
+Example output format for a single file entry:
+``` yaml
+- name: HCl
+  composition: {Cl: 1, H: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [20625.88287, -309.3368855, 5.27541885, -0.00482887422, 6.1957946e-06, -3.040023782e-09, 4.91679003e-13, -10677.82299, -7.309305408]
+    - [915774.951, -2770.550211, 5.97353979, -0.000362981006, 4.73552919e-08, 2.810262054e-12, -6.65610422e-16, 5674.95805, -16.42825822]
+    note: Gurvich,1989 pt1 p186 pt2 p93. [tpis89]
+```
+
+Compile ```combined_data.yaml``` to the binary gaspype format:
+``` bash
+python compile_to_bin.py combined_data.yaml ../src/gaspype/data/therm_data.bin
+```
+General syntax is: ```python compile_to_bin.py YAML_INPUT_FILE BINARY_OUTPUT_FILE```
+
+The binary format is structured like this, it uses little-endian and IEEE 754 floats:
+```
+[4 Byte magic number: 'gapy']
+[8 Byte: 32 Bit integer for length of all species names (NAMES_LENGTH)]
+[NAMES_LENGTH Bytes: ASCII encoded string with all species names separated by space]
+[Index
+    [For each species
+        [4 Bytes: 32 Bit uint with offset of species data in file]
+        [1 Byte:   8 Bit uint with number of elements]
+        [1 Byte:   8 Bit uint for polygon length, value = 9]
+        [1 Byte:   8 Bit uint for number of temperature supporting points (NUM_TEMPS)]
+        [1 Byte:   8 Bit uint for length of reference string (REF_LEN)]
+    ]
+]
+[Data
+    [For each species
+        [For each species element
+            [2 Byte: element name in ASCII, 0x20 padded]
+            [1 Byte: 8 Bit uint for number of atoms]
+        ]
+        [For Range(NUM_TEMPS)
+            [4 Byte: 32 Bit float with temperature supporting point]
+        ]
+        [For Range(NUM_TEMPS - 1)
+            [36 Bytes: 9 x 32 Bit float with NASA9-Polynomial for a temperature interval]
+        ]
+        [REF_LEN Bytes: ASCII string of the data reference]
+    ]
+]
+```
+
+## Notes
+- Original source of the data compilation: https://ntrs.nasa.gov/citations/20020085330
+- nasa9_*.yaml files are exported from https://cearun.grc.nasa.gov/ThermoBuild/ and
+  converted with ck2yaml (https://cantera.org/stable/userguide/thermobuild.html)
+- nasa9polynomials.xml is from: https://github.com/guillemborrell/thermopy/tree/master/databases

thermo_data/combine_data.py

@@ -0,0 +1,80 @@
+import yaml
+import xml.etree.ElementTree as ET
+import glob
+import sys
+
+
+def main():
+    output_file = sys.argv[1]
+    input_files = sys.argv[2:]
+
+    inp_therm_prop: list[dict] = []
+
+    for glop_filter in input_files:
+        for file_name in glob.glob(glop_filter):
+            print(f'Processing file: {file_name}...')
+            if file_name.endswith('.xml'):
+                inp_therm_prop += get_xml_data(file_name)
+            else:
+                with open(file_name, 'r') as f:
+                    inp_therm_prop += yaml.safe_load(f)['species']
+
+    therm_prop = []
+    added_species_names: set[str] = set()
+
+    for species in inp_therm_prop:
+        name = species['name']
+        assert isinstance(name, str)
+        for element in species['composition']:
+            name = name.replace(element.upper(), element)
+        if name not in added_species_names and 'E' not in species['composition']:
+            species['name'] = name
+            therm_prop.append(species)
+            added_species_names.add(name)
+
+    with open(output_file, 'w') as f:
+        f.write('species:\n')
+        for species in sorted(therm_prop, key=lambda s: s['name']):
+            f.write('\n- ' + yaml.dump({'name': species['name']}, default_flow_style=False))
+            f.write(f'  composition: {yaml.dump(species["composition"], default_flow_style=True)}')
+            f.write('  thermo:\n')
+            f.write(f'    model: {species["thermo"]["model"]}\n')
+            f.write(f'    temperature-ranges: {yaml.dump(species["thermo"]["temperature-ranges"], default_flow_style=True)}')
+            f.write('    data:\n')
+            for d in species['thermo']['data']:
+                f.write(f'    - {d}\n')
+            f.write('    ' + yaml.dump({'note': species['thermo']['note']}, default_flow_style=False))
+
+    print('Added: ', ', '.join(sorted(added_species_names)))
+
+
+def get_xml_data(file_name: str) -> list[dict]:
+    xml_data_list: list[dict] = []
+    tree = ET.parse(file_name)
+    root = tree.getroot()
+    for i, child in enumerate(root):
+
+        elements = {el[0]: int(el[1]) for c in child.find('elements').findall('element') for el in c.items()}
+
+        values_temp = [tr for tr in child.findall('T_range')]
+        t_ranges = [float(v.attrib['Tlow']) for v in values_temp] + [float(values_temp[-1].attrib['Thigh'])]
+        data = [[float(v.text) for v in tr] for tr in values_temp]
+
+        is_gas = child.find('condensed').text == 'False'
+
+        if is_gas:
+            xml_data_list.append({
+                'name': child.attrib['inp_file_name'],
+                'composition': elements,
+                'thermo': {
+                    'model': 'NASA9',
+                    'temperature-ranges': t_ranges,
+                    'data': data,
+                    'note': child.find('comment').text
+                }
+            })
+    return xml_data_list
+
+
+if __name__ == "__main__":
+    main()

thermo_data/compile_to_bin.py

@@ -0,0 +1,71 @@
+import yaml
+import struct
+import sys
+import os
+
+
+def main():
+    input_file = sys.argv[1]
+    output_file = sys.argv[2]
+
+    assert not output_file.endswith('.yml') and not output_file.endswith('.yaml'), 'Binary output file should not have yaml-extension'
+
+    with open(input_file) as f:
+        data = yaml.safe_load(f)
+
+    data = list({v['name']: v for v in data['species']}.values())
+
+    species_names = ' '.join(s['name'] for s in data)
+
+    header_len = 8
+
+    offset = 8 + len(species_names) + len(data) * header_len
+
+    header_list = []
+    body_list = []
+    added_list = set()
+
+    for dat in data:
+        if dat['name'] not in added_list:
+
+            composition_count = len(dat['composition'])
+            model = {'NASA9': 9}[dat['thermo']['model']]
+            temperatures = dat['thermo']['temperature-ranges']
+            ref_string = dat['thermo']['note'].encode('utf-8')
+            header = struct.pack('<I4B', offset, composition_count, model, len(temperatures), len(ref_string))
+
+            assert len(header) == header_len
+
+            header_list.append(header)
+
+            composition = [el for k, v in dat['composition'].items() for el in [k.ljust(2).encode('ASCII'), v]]
+            data_vals = [d for darr in dat['thermo']['data'] for d in darr[:model]]
+
+            assert len(dat['thermo']['data']) == len(temperatures) - 1, f"Temperature data length mismatch for {dat['name']}."
+
+            if any(len(d) != model for d in dat['thermo']['data']):
+                print(f"Warning: Data length mismatch for {dat['name']}. Expected {model} coefficients, got {len(dat['thermo']['data'][0])}.")
+
+            format_string = '<' + '2sB' * composition_count + f'{len(temperatures)}f{len(data_vals)}f{len(ref_string)}s'
+
+            body = struct.pack(format_string, *(composition + temperatures + data_vals + [ref_string]))
+            body_list.append(body)
+
+            offset += len(body)
+            added_list.add(dat['name'])
+
+    # Ensure the output directory exists
+    os.makedirs(os.path.dirname(output_file), exist_ok=True)
+
+    with open(output_file, 'wb') as f:
+        f.write(b'gapy')
+        f.write(struct.pack('<I', len(species_names)))
+        f.write(species_names.encode('ASCII'))
+        for dat in header_list:
+            f.write(dat)
+        for dat in body_list:
+            f.write(dat)
+
+
+if __name__ == '__main__':
+    main()

thermo_data/nasa9_hydrocarbons_si.yaml

@@ -0,0 +1,293 @@
+generator: ck2yaml
+input-files: [mythermo_si.txt]
+cantera-version: 3.0.1
+date: Sun, 04 Aug 2024 14:04:08 +0000
+
+units: {length: cm, time: s, quantity: mol, activation-energy: cal/mol}
+
+species:
+- name: H
+  composition: {H: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0, 2.0e+04]
+    data:
+    - [0.0, 0.0, 2.5, 0.0, 0.0, 0.0, 0.0, 2.547370801e+04, -0.446682853]
+    - [60.7877425, -0.1819354417, 2.500211817, -1.226512864e-07, 3.73287633e-11,
+      -5.68774456e-15, 3.410210197e-19, 2.547486398e+04, -0.448191777]
+    - [2.173757694e+08, -1.312035403e+05, 33.991742, -3.81399968e-03, 2.432854837e-07,
+      -7.69427554e-12, 9.64410563e-17, 1.067638086e+06, -274.2301051]
+    note: D0(H2):Herzberg,1970. Moore,1972. Gordon,1999. [g 6/97]
+- name: HO2
+  composition: {H: 1, O: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [-7.59888254e+04, 1329.383918, -4.67738824, 0.02508308202, -3.006551588e-05,
+      1.895600056e-08, -4.82856739e-12, -5873.35096, 51.9360214]
+    - [-1.810669724e+06, 4963.19203, -1.039498992, 4.56014853e-03, -1.061859447e-06,
+      1.144567878e-10, -4.76306416e-15, -3.20081719e+04, 40.6685092]
+    note: Hf:Hills,1984 & NASA data. Jacox,1998 p153. [g 4/02]
+- name: H2
+  composition: {H: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0, 2.0e+04]
+    data:
+    - [4.07832321e+04, -800.918604, 8.21470201, -0.01269714457, 1.753605076e-05,
+      -1.20286027e-08, 3.36809349e-12, 2682.484665, -30.43788844]
+    - [5.60812801e+05, -837.150474, 2.975364532, 1.252249124e-03, -3.74071619e-07,
+      5.9366252e-11, -3.6069941e-15, 5339.82441, -2.202774769]
+    - [4.96688412e+08, -3.147547149e+05, 79.8412188, -8.41478921e-03, 4.75324835e-07,
+      -1.371873492e-11, 1.605461756e-16, 2.488433516e+06, -669.572811]
+    note: Ref-Elm. Gurvich,1978 pt1 p103 pt2 p31. [tpis78]
+- name: H2O
+  composition: {H: 2, O: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [-3.94796083e+04, 575.573102, 0.931782653, 7.22271286e-03, -7.34255737e-06,
+      4.95504349e-09, -1.336933246e-12, -3.30397431e+04, 17.24205775]
+    - [1.034972096e+06, -2412.698562, 4.64611078, 2.291998307e-03, -6.83683048e-07,
+      9.42646893e-11, -4.82238053e-15, -1.384286509e+04, -7.97814851]
+    note: Hf:Cox,1989. Woolley,1987. TRC(10/88) tuv25. [g 8/89]
+- name: H2O2
+  composition: {H: 2, O: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [-9.27953358e+04, 1564.748385, -5.97646014, 0.0327074452, -3.93219326e-05,
+      2.509255235e-08, -6.46504529e-12, -2.494004728e+04, 58.7717418]
+    - [1.489428027e+06, -5170.82178, 11.2820497, -8.04239779e-05, -1.818383769e-08,
+      6.94726559e-12, -4.8278319e-16, 1.418251038e+04, -46.5085566]
+    note: Hf:Gurvich,1989 pt1 p127. Gurvich,1978 pt1 p121. [g 6/99]
+- name: O
+  composition: {O: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0, 2.0e+04]
+    data:
+    - [-7953.6113, 160.7177787, 1.966226438, 1.01367031e-03, -1.110415423e-06,
+      6.5175075e-10, -1.584779251e-13, 2.840362437e+04, 8.40424182]
+    - [2.619020262e+05, -729.872203, 3.31717727, -4.28133436e-04, 1.036104594e-07,
+      -9.43830433e-12, 2.725038297e-16, 3.39242806e+04, -0.667958535]
+    - [1.779004264e+08, -1.082328257e+05, 28.10778365, -2.975232262e-03,
+      1.854997534e-07, -5.79623154e-12, 7.191720164e-17, 8.89094263e+05,
+      -218.1728151]
+    note: D0(O2):Brix,1954. Moore,1976. Gordon,1999. [g 5/97]
+- name: OH
+  composition: {O: 1, H: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0, 2.0e+04]
+    data:
+    - [-1998.85899, 93.0013616, 3.050854229, 1.529529288e-03, -3.157890998e-06,
+      3.31544618e-09, -1.138762683e-12, 2991.214235, 4.67411079]
+    - [1.017393379e+06, -2509.957276, 5.11654786, 1.30529993e-04, -8.28432226e-08,
+      2.006475941e-11, -1.556993656e-15, 2.019640206e+04, -11.01282337]
+    - [2.847234193e+08, -1.859532612e+05, 50.082409, -5.14237498e-03, 2.875536589e-07,
+      -8.22881796e-12, 9.56722902e-17, 1.468393908e+06, -402.355558]
+    note: 'D0(H-OH): Ruscic,2002. Gurvich,1978 pt1 p110 pt2 p37. [g 4/02]'
+- name: O2
+  composition: {O: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0, 2.0e+04]
+    data:
+    - [-3.42556342e+04, 484.700097, 1.119010961, 4.29388924e-03, -6.83630052e-07,
+      -2.0233727e-09, 1.039040018e-12, -3391.45487, 18.4969947]
+    - [-1.037939022e+06, 2344.830282, 1.819732036, 1.267847582e-03, -2.188067988e-07,
+      2.053719572e-11, -8.19346705e-16, -1.689010929e+04, 17.38716506]
+    - [4.9752943e+08, -2.866106874e+05, 66.9035225, -6.16995902e-03, 3.016396027e-07,
+      -7.4214166e-12, 7.27817577e-17, 2.293554027e+06, -553.062161]
+    note: Ref-Elm. Gurvich,1989 pt1 p94 pt2 p9. [tpis89]
+- name: O3
+  composition: {O: 3}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [-1.282314507e+04, 589.821664, -2.547496763, 0.02690121526, -3.52825834e-05,
+      2.312290922e-08, -6.04489327e-12, 1.348368701e+04, 38.5221858]
+    - [-3.86966248e+07, 1.023344994e+05, -89.615516, 0.0370614497, -4.13763874e-06,
+      -2.725018591e-10, 5.24818811e-14, -6.51791818e+05, 702.910952]
+    note: Gurvich,1989 pt1 p101 pt2 p15. [g 8/01]
+- name: Si
+  composition: {Si: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0, 2.0e+04]
+    data:
+    - [98.3614081, 154.6544523, 1.87643667, 1.320637995e-03, -1.529720059e-06,
+      8.95056277e-10, -1.95287349e-13, 5.26351031e+04, 9.69828888]
+    - [-6.16929885e+05, 2240.683927, -0.444861932, 1.710056321e-03, -4.10771416e-07,
+      4.55888478e-11, -1.889515353e-15, 3.95355876e+04, 26.79668061]
+    - [-9.28654894e+08, 5.44398989e+05, -120.6739736, 0.01359662698, -7.60649866e-07,
+      2.149746065e-11, -2.474116774e-16, -4.29379212e+06, 1086.382839]
+    note: Hf:Cox,1989. NIST data version1.1 [Online]1997. Gordon,1999. [g
+      8/97]
+- name: SiH
+  composition: {Si: 1, H: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [-6426.6763, 74.1725121, 3.9734916, -4.14940888e-03, 1.022918384e-05,
+      -8.59238636e-09, 2.567093743e-12, 4.2817458e+04, 2.24693715]
+    - [4.04208649e+05, -2364.796524, 7.62749914, -2.496591233e-03, 1.10843641e-06,
+      -1.943991955e-10, 1.136251507e-14, 5.70473768e+04, -24.48054429]
+    note: Gurvich,1991 pt1 p257 pt2 p234. [tpis91]
+- name: SiH2
+  composition: {Si: 1, H: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [-2.063863564e+04, 330.58622, 2.099271145, 3.54253937e-03, 3.37887667e-06,
+      -5.38384562e-09, 2.081191273e-12, 3.011784298e+04, 12.8233357]
+    - [4.62403937e+06, -1.14343611e+04, 12.6488087, 9.1148995e-04, -8.76661154e-07,
+      1.646297357e-10, -9.96509037e-15, 1.072475101e+05, -66.0607807]
+    note: Gurvich,1991 pt1 p260. Fredin,1985. Dubois,1968. [g 3/01]
+- name: SiH3
+  composition: {Si: 1, H: 3}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [4341.14282, 227.7185085, 0.650825035, 0.01221438558, -4.34760427e-06,
+      -1.774916828e-09, 1.184191367e-12, 2.259993826e+04, 19.68347482]
+    - [6.05632122e+05, -4721.25406, 13.29129523, -1.256824868e-03, 2.68828594e-07,
+      -3.010741582e-11, 1.370945857e-15, 4.97442064e+04, -61.405031]
+    note: Gurvich,1991 pt1 p261 pt2 p236. [g 3/99]
+- name: SiH4
+  composition: {Si: 1, H: 4}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [7.87299329e+04, -552.608705, 2.498944303, 0.01442118274, -8.46710731e-06,
+      2.726164641e-09, -5.43675437e-13, 6269.66906, 4.96546183]
+    - [1.29037874e+06, -7813.39978, 18.28851664, -1.975620946e-03, 4.15650215e-07,
+      -4.59674561e-11, 2.072777131e-15, 4.76688795e+04, -98.0169746]
+    note: Silane. Gurvich,1991 pt1 p263 pt 2 p237. [tpis91]
+- name: SiO
+  composition: {Si: 1, O: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [-4.72277105e+04, 806.313764, -1.636976133, 0.01454275546, -1.723202046e-05,
+      1.04239734e-08, -2.559365273e-12, -1.666585903e+04, 33.557957]
+    - [-1.765134162e+05, -31.9917709, 4.47744193, 4.59176471e-06, 3.55814315e-08,
+      -1.327012559e-11, 1.613253297e-15, -1.35084236e+04, -0.838695733]
+    note: Gurvich,1991 pt1 p247 pt2 p227 [tpis91]
+- name: SiO2
+  composition: {Si: 1, O: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [-3.36294878e+04, 473.407892, 0.2309770671, 0.01850230806, -2.242786671e-05,
+      1.364981554e-08, -3.35193503e-12, -4.22648749e+04, 22.95803206]
+    - [-1.464031193e+05, -626.144106, 7.96456371, -1.854119096e-04, 4.09521467e-08,
+      -4.69720676e-12, 2.17805428e-16, -3.79183477e+04, -20.45285414]
+    note: Gurvich,1991 pt1 p256 pt2 p233. [tpis91]
+- name: Si2
+  composition: {Si: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [1.237596221e+04, -102.4904376, 4.35484852, 1.281063335e-03, -2.531991623e-06,
+      2.265694244e-09, -7.00129014e-13, 6.90694285e+04, 3.2511252]
+    - [1.370060657e+06, -4207.06004, 9.33743289, -2.749217168e-03, 9.58634596e-07,
+      -1.372449748e-10, 6.7650281e-15, 9.51088454e+04, -31.6838519]
+    note: Gurvich,1991 pt1 p240 pt2 p225. [tpis91]
+- name: Si3
+  composition: {Si: 3}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 1000.0, 6000.0]
+    data:
+    - [-1.114208177e+04, 157.5785843, 2.486135003, 0.01631637255, -2.208240021e-05,
+      1.372008287e-08, -3.2623307e-12, 7.32825385e+04, 15.88081347]
+    - [-1.699395561e+06, 4697.81538, 2.618198124, 1.959082075e-03, -2.581160603e-07,
+      6.10344486e-12, 6.08630924e-16, 4.27791681e+04, 25.86540384]
+    note: Gurvich,1991 pt1 p246 pt2 p226. [g 7/95]
+- name: H2O(cr)
+  composition: {H: 2, O: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 273.15]
+    data:
+    - [-4.02677748e+05, 2747.887946, 57.3833663, -0.826791524, 4.41308798e-03,
+      -1.054251164e-05, 9.69449597e-09, -5.53031499e+04, -190.2572063]
+    note: Ice. Gordon,1982. [g11/99]
+- name: H2O(L)
+  composition: {H: 2, O: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [273.15, 373.15, 600.0]
+    data:
+    - [1.326371304e+09, -2.448295388e+07, 1.879428776e+05, -767.899505,
+      1.761556813, -2.151167128e-03, 1.092570813e-06, 1.101760476e+08, -9.77970097e+05]
+    - [1.263631001e+09, -1.680380249e+07, 9.27823479e+04, -272.237395, 0.447924376,
+      -3.91939743e-04, 1.425743266e-07, 8.11317688e+07, -5.13441808e+05]
+    note: Liquid. Cox,1989. Haar,1984. Keenan,1984. Stimson,1969. [g 8/01]
+- name: Si(cr)
+  composition: {Si: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 298.15, 1690.0]
+    data:
+    - [-2.323538208e+04, 0.0, 2.10202168, 1.809220552e-03, 0.0, 0.0, 0.0,
+      -785.063521, -10.38427318]
+    - [-5.23255974e+04, 0.0, 2.850169415, 3.97516697e-04, 0.0, 0.0, 0.0,
+      -1042.947234, -14.38964187]
+    note: Cubic. Ref-Elm. Gurvich,1991 pt1 p236 pt2 p220. [tpis91]
+- name: Si(L)
+  composition: {Si: 1}
+  thermo:
+    model: NASA9
+    temperature-ranges: [1690.0, 6000.0]
+    data:
+    - [0.0, 0.0, 3.271389414, 0.0, 0.0, 0.0, 0.0, 4882.66711, -13.26611073]
+    note: Liquid. Ref-Elm. Gurvich,1991 pt1 p236 pt2 p220. [tpis91]
+- name: SiO2(a-qz)
+  composition: {Si: 1, O: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [200.0, 848.0]
+    data:
+    - [-5.7768955e+05, 7214.66111, -31.45730294, 0.0741217715, -8.67007782e-06,
+      -1.080461312e-07, 8.31632491e-11, -1.462398375e+05, 184.2424399]
+    note: Alpha-quartz,hexagonal. Gurvich,1991 pt1 p250 pt2 p228. [tpis91]
+- name: SiO2(b-qz)
+  composition: {Si: 1, O: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [848.0, 1200.0]
+    data:
+    - [2.317635074e+04, 0.0, 7.026511484, 1.241925261e-03, 0.0, 0.0, 0.0,
+      -1.117012474e+05, -35.80751356]
+    note: Beta-quartz,hexagonal. Gurvich,1991 pt1 p250 pt2 p228. [tpis91]
+- name: SiO2(b-crt)
+  composition: {Si: 1, O: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [1200.0, 1996.0]
+    data:
+    - [-5.356419079e+05, 0.0, 9.331036946, -7.306503931e-04, 3.339944266e-07,
+      0.0, 0.0, -1.134326721e+05, -49.98768383]
+    note: Beta-cristobalite,cubic. Gurvich,1991 pt1 p250 pt2 p228. [tpis91]
+- name: SiO2(L)
+  composition: {Si: 1, O: 2}
+  thermo:
+    model: NASA9
+    temperature-ranges: [1996.0, 6000.0]
+    data:
+    - [0.0, 0.0, 10.04268442, 0.0, 0.0, 0.0, 0.0, -1.140002976e+05, -55.54279592]
+    note: Liquid. Gurvich,1991 pt1 p250 pt2 p228. [tpis91]