merge devel to master for v0.2.18 (#628)

.github/dependabot.yml

@@ -0,0 +1,7 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    target-branch: "devel"

.github/workflows/test.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9]
+        python-version: ["3.7", "3.8", "3.12"]
 
     steps:
     - uses: actions/checkout@v2
@@ -26,7 +26,9 @@ jobs:
     - name: Test
       run: cd tests && coverage run --source=../dpdata -m unittest && cd .. && coverage combine tests/.coverage && coverage report
     - name: Run codecov
-      uses: codecov/codecov-action@v3
+      uses: codecov/codecov-action@v4
+      env:
+        CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
   pass:
     needs: [build]
     runs-on: ubuntu-latest

.gitignore

@@ -28,3 +28,4 @@ docs/drivers.csv
 docs/minimizers.csv
 docs/api/
 docs/formats/
+.DS_Store

.pre-commit-config.yaml

@@ -17,16 +17,15 @@ repos:
     -   id: check-symlinks
     -   id: check-toml
 # Python
--   repo: https://github.com/psf/black
-    rev: 23.10.1
-    hooks:
-    -   id: black-jupyter
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.1.3
+    rev: v0.3.5
     hooks:
     - id: ruff
       args: ["--fix"]
+      types_or: [python, pyi, jupyter]
+    - id: ruff-format
+      types_or: [python, pyi, jupyter]
 # numpydoc
 -   repo: https://github.com/Carreau/velin
     rev: 0.0.12

MANIFEST.in

@@ -0,0 +1,3 @@
+prune docs
+prune tests
+prune plugin_example

docs/make_format.py

@@ -224,8 +224,9 @@ def generate_sub_format_pages(formats: dict):
                     buff.append("""   :noindex:""")
                 buff.append("")
                 if docstring is None or method not in format.__dict__:
-                    docstring = """   Convert this format to :class:`%s`.""" % (
-                        method_classes[method]
+                    docstring = (
+                        """   Convert this format to :class:`%s`."""
+                        % (method_classes[method])
                     )
                 doc_obj = SphinxDocString(docstring)
                 if len(doc_obj["Parameters"]) > 0:
@@ -293,8 +294,8 @@ def generate_sub_format_pages(formats: dict):
                         and "to_system" in format.__dict__
                     )
                 ):
-                    docstring = "Convert :class:`%s` to this format." % (
-                        method_classes[method]
+                    docstring = (
+                        "Convert :class:`%s` to this format." % (method_classes[method])
                     )
                 doc_obj = SphinxDocString(docstring)
                 if len(doc_obj["Parameters"]) > 0:

dpdata/abacus/scf.py

@@ -10,6 +10,16 @@
 ry2ev = EnergyConversion("rydberg", "eV").value()
 kbar2evperang3 = PressureConversion("kbar", "eV/angstrom^3").value()
 
+ABACUS_STRU_KEYS = [
+    "ATOMIC_SPECIES",
+    "NUMERICAL_ORBITAL",
+    "LATTICE_CONSTANT",
+    "LATTICE_VECTORS",
+    "ATOMIC_POSITIONS",
+    "NUMERICAL_DESCRIPTOR",
+    "PAW_FILES",
+]
+
 
 def CheckFile(ifile):
     if not os.path.isfile(ifile):
@@ -43,6 +53,29 @@ def get_block(lines, keyword, skip=0, nlines=None):
     return ret
 
 
+def get_stru_block(lines, keyword):
+    # return the block of lines after keyword in STRU file, and skip the blank lines
+
+    def clean_comment(line):
+        return re.split("[#]", line)[0]
+
+    ret = []
+    found = False
+    for i in range(len(lines)):
+        if clean_comment(lines[i]).strip() == keyword:
+            found = True
+            for j in range(i + 1, len(lines)):
+                if clean_comment(lines[j]).strip() == "":
+                    continue
+                elif clean_comment(lines[j]).strip() in ABACUS_STRU_KEYS:
+                    break
+                else:
+                    ret.append(clean_comment(lines[j]))
+    if not found:
+        return None
+    return ret
+
+
 def get_geometry_in(fname, inlines):
     geometry_path_in = os.path.join(fname, "STRU")
     for line in inlines:
@@ -64,8 +97,8 @@ def get_path_out(fname, inlines):
 
 
 def get_cell(geometry_inlines):
-    cell_lines = get_block(geometry_inlines, "LATTICE_VECTORS", skip=0, nlines=3)
-    celldm_lines = get_block(geometry_inlines, "LATTICE_CONSTANT", skip=0, nlines=1)
+    cell_lines = get_stru_block(geometry_inlines, "LATTICE_VECTORS")
+    celldm_lines = get_stru_block(geometry_inlines, "LATTICE_CONSTANT")
 
     celldm = float(celldm_lines[0].split()[0]) * bohr2ang  # lattice const is in Bohr
     cell = []
@@ -76,7 +109,7 @@ def get_cell(geometry_inlines):
 
 
 def get_coords(celldm, cell, geometry_inlines, inlines=None):
-    coords_lines = get_block(geometry_inlines, "ATOMIC_POSITIONS", skip=0)
+    coords_lines = get_stru_block(geometry_inlines, "ATOMIC_POSITIONS")
     # assuming that ATOMIC_POSITIONS is at the bottom of the STRU file
     coord_type = coords_lines[0].split()[0].lower()  # cartisan or direct
     atom_names = []  # element abbr in periodic table

dpdata/amber/mask.py

@@ -1,4 +1,5 @@
 """Amber mask."""
+
 try:
     import parmed
 except ImportError:

dpdata/cli.py

@@ -1,4 +1,5 @@
 """Command line interface for dpdata."""
+
 import argparse
 from typing import Optional
 

dpdata/cp2k/output.py

@@ -117,9 +117,7 @@ def get_xyz_block_generator(self):
                     lines.append(self.xyz_file_object.readline())
                 if not lines[-1]:
                     raise RuntimeError(
-                        "this xyz file may lack of lines, should be {};lines:{}".format(
-                            atom_num + 2, lines
-                        )
+                        f"this xyz file may lack of lines, should be {atom_num + 2};lines:{lines}"
                     )
                 yield lines
 

dpdata/deepmd/hdf5.py

@@ -1,4 +1,5 @@
 """Utils for deepmd/hdf5 format."""
+
 from __future__ import annotations
 
 import warnings

dpdata/driver.py

@@ -1,4 +1,5 @@
 """Driver plugin system."""
+
 from abc import ABC, abstractmethod
 from typing import TYPE_CHECKING, Callable, List, Union
 
@@ -163,6 +164,8 @@ def label(self, data: dict) -> dict:
             else:
                 labeled_data["energies"] += lb_data["energies"]
                 labeled_data["forces"] += lb_data["forces"]
+                if "virials" in labeled_data and "virials" in lb_data:
+                    labeled_data["virials"] += lb_data["virials"]
         return labeled_data
 
 

dpdata/format.py

@@ -1,4 +1,5 @@
 """Implement the format plugin system."""
+
 import os
 from abc import ABC
 

dpdata/gaussian/log.py

@@ -11,6 +11,25 @@
 
 
 def to_system_data(file_name, md=False):
+    """Read Gaussian log file.
+
+    Parameters
+    ----------
+    file_name : str
+        file name
+    md : bool, default False
+        whether to read multiple frames
+
+    Returns
+    -------
+    data : dict
+        system data
+
+    Raises
+    ------
+    RuntimeError
+        if the input orientation is not found
+    """
     data = {}
     # read from log lines
     flag = 0
@@ -20,6 +39,7 @@ def to_system_data(file_name, md=False):
     forces_t = []
     cells_t = []
     nopbc = True
+    coords = None
 
     with open(file_name) as fp:
         for line in fp:
@@ -44,6 +64,12 @@ def to_system_data(file_name, md=False):
             elif flag == 4:
                 # forces
                 if line.startswith(" -------"):
+                    if coords is None:
+                        raise RuntimeError(
+                            "Input orientation is not found. Using Gaussian keyword "
+                            "`Geom=PrintInputOrient` to always print the input orientation. "
+                            "See https://gaussian.com/geom/ for more details."
+                        )
                     forces_t.append(forces)
                     energy_t.append(energy)
                     coords_t.append(coords)
@@ -55,6 +81,7 @@ def to_system_data(file_name, md=False):
                             [[100.0, 0.0, 0.0], [0.0, 100.0, 0.0], [0.0, 0.0, 100.0]]
                         )
                     flag = 0
+                    coords = None
                 else:
                     s = line.split()
                     if line[14:16] == "-2":

dpdata/lammps/dump.py

@@ -121,8 +121,8 @@ def safe_get_posi(lines, cell, orig=np.zeros(3), unwrap=False):
                 category=UnwrapWarning,
             )
         return (
-            posis % 1
-        ) @ cell  # Convert scaled coordinates back to Cartesien coordinates with wraping at periodic boundary conditions
+            (posis % 1) @ cell
+        )  # Convert scaled coordinates back to Cartesien coordinates with wraping at periodic boundary conditions
 
 
 def get_dumpbox(lines):