Merge pull request #169 from deepmodeling/master

Sync devel with master

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,25 @@
+---
+name: Bug report
+about: Create a bug report to help us eliminate issues and improve dpdata. If this
+  doesn’t look right, [choose a different type](https://github.com/deepmodeling/dpdata/issues/new/choose).
+title: "[BUG] _Replace With Suitable Title_"
+labels: bug
+assignees: ''
+
+---
+
+**Summary**
+
+<!--Please provide a clear and concise description of what the bug is.-->
+
+<!--Please provide necessary information including the version of software and installation way, input file, running commands, error log , etc., AS  DETAILED AS POSSIBLE to help locate and reproduce your problem. -->
+
+<!--If applicable, specify what platform you are running on. -->
+
+**Steps to Reproduce**
+
+<!--Describe the steps required to (quickly) reproduce the issue. You can attach (small) files to the section below or add URLs where to download an archive with all necessary files. Please try to create an input set that is as minimal and small as possible and reproduces the bug as quickly as possible. **NOTE:** the less effort and time it takes to reproduce your reported bug, the more likely it becomes, that somebody will look into it and fix the problem.-->
+
+**Further Information, Files, and Links**
+
+<!--Put any additional information here, attach relevant text or image files and URLs to external sites, e.g. relevant publications-->

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,21 @@
+---
+name: Feature request
+about: Suggest an idea for this project. If this doesn’t work right, [choose a different
+  type]( https://github.com/deepmodeling/dpdata/issues/new/choose).
+title: "[Feature Request] _Replace with Title_"
+labels: enhancement
+assignees: ''
+
+---
+
+**Summary**
+
+<!--Please provide a brief and concise description of the suggested feature or change-->
+
+**Detailed Description**
+
+<!--Please explain how you would like to see dpdata enhanced, what feature(s) you are looking for, what specific data format this will support or what specific problems this will solve. If possible, provide references to relevant background information like publications or web pages, and whether you are planning to implement the enhancement yourself or would like to participate in the implementation. If applicable add a reference to an existing bug report or issue that this will address.-->
+
+**Further Information, Files, and Links**
+
+<!--Put any additional information here, attach relevant text or image files and URLs to external sites, e.g. relevant publications-->

.github/ISSUE_TEMPLATE/generic-issue.md

@@ -0,0 +1,17 @@
+---
+name: Generic issue
+about: For issues that do not fit any of the other categories. If this doesn’t work
+  right, [choose a different type]( https://github.com/deepmodeling/dpdata/issues/new/choose).
+title: ''
+labels: wontfix
+assignees: ''
+
+---
+
+**Summary**
+
+<!--Please provide a clear and concise description of what the question is.-->
+
+**Details**
+
+<!--Please explain the issue in detail here-->

.github/ISSUE_TEMPLATE/request-for-help.md

@@ -0,0 +1,21 @@
+---
+name: Request for Help
+about: Don't post help requests here, go to [discussions](https://github.com/deepmodeling/dpdata/discussions)
+  instead. If this doesn’t look right, choose a different type.
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+Before asking questions, you can
+
+search the previous issues or discussions
+check the [README](https://github.com/deepmodeling/dpdata/#readme).
+
+Please **do not** post requests for help (e.g. with installing or using dpdata) here. 
+Instead go to [discussions](https://github.com/deepmodeling/dpdata/discussions).
+
+This issue tracker is for tracking dpdata development related issues only.
+
+Thanks for your cooperation.

README.md

@@ -252,3 +252,14 @@ print(syst.get_charge()) # return the total charge of the system
 ```
 
 If a valence of 3 is detected on carbon, the formal charge will be assigned to -1. Because for most cases (in alkynyl anion, isonitrile, cyclopentadienyl anion), the formal charge on 3-valence carbon is -1, and this is also consisent with the 8-electron rule.
+
+# Plugins
+
+One can follow [a simple example](plugin_example/) to add their own format by creating and installing plugins. It's crirical to add the [Format](dpdata/format.py) class to `entry_points['dpdata.plugins']` in `setup.py`:
+```py
+    entry_points={
+        'dpdata.plugins': [
+            'random=dpdata_random:RandomFormat'
+        ]
+    },
+```

dpdata/__init__.py

@@ -12,7 +12,8 @@
 
 # BondOrder System has dependency on rdkit
 try:
-    import rdkit
+    # prevent conflict with dpdata.rdkit
+    import rdkit as _
     USE_RDKIT = True
 except ModuleNotFoundError:
     USE_RDKIT = False

dpdata/bond_order_system.py

@@ -1,7 +1,6 @@
 #%%
 # Bond Order System
-from dpdata.system import Register, System, LabeledSystem, check_System
-import rdkit.Chem
+from dpdata.system import System, LabeledSystem, check_System, load_format
 import dpdata.rdkit.utils
 from dpdata.rdkit.sanitize import Sanitizer, SanitizeError
 from copy import deepcopy
@@ -87,8 +86,16 @@ def __init__(self,
         if type_map:
             self.apply_type_map(type_map)
 
-    register_from_funcs = Register()
-    register_to_funcs = System.register_to_funcs + Register()
+    def from_fmt_obj(self, fmtobj, file_name, **kwargs):
+        mol = fmtobj.from_bond_order_system(file_name, **kwargs)
+        self.from_rdkit_mol(mol)
+        if hasattr(fmtobj.from_bond_order_system, 'post_func'):
+            for post_f in fmtobj.from_bond_order_system.post_func:
+                self.post_funcs.get_plugin(post_f)(self)
+        return self
+
+    def to_fmt_obj(self, fmtobj, *args, **kwargs):
+        return fmtobj.to_bond_order_system(self.data, self.rdkit_mol, *args, **kwargs)
 
     def __repr__(self):
         return self.__str__()
@@ -164,36 +171,3 @@ def from_rdkit_mol(self, rdkit_mol):
         self.data = dpdata.rdkit.utils.mol_to_system_data(rdkit_mol)
         self.data['bond_dict'] = dict([(f'{int(bond[0])}-{int(bond[1])}', bond[2]) for bond in self.data['bonds']])
         self.rdkit_mol = rdkit_mol
-
-    @register_from_funcs.register_funcs('mol')
-    def from_mol_file(self, file_name):
-        mol = rdkit.Chem.MolFromMolFile(file_name, sanitize=False, removeHs=False)
-        self.from_rdkit_mol(mol)
-
-    @register_to_funcs.register_funcs("mol")
-    def to_mol_file(self, file_name, frame_idx=0):
-        assert (frame_idx < self.get_nframes())
-        rdkit.Chem.MolToMolFile(self.rdkit_mol, file_name, confId=frame_idx)
-
-    @register_from_funcs.register_funcs("sdf")
-    def from_sdf_file(self, file_name):
-        '''
-        Note that it requires all molecules in .sdf file must be of the same topology
-        '''
-        mols = [m for m in rdkit.Chem.SDMolSupplier(file_name, sanitize=False, removeHs=False)]
-        if len(mols) > 1:
-            mol = dpdata.rdkit.utils.combine_molecules(mols)
-        else:
-            mol = mols[0]
-        self.from_rdkit_mol(mol)
-
-    @register_to_funcs.register_funcs("sdf")
-    def to_sdf_file(self, file_name, frame_idx=-1):
-        sdf_writer = rdkit.Chem.SDWriter(file_name)
-        if frame_idx == -1:
-            for ii in self.get_nframes():
-                sdf_writer.write(self.rdkit_mol, confId=ii)
-        else:
-            assert (frame_idx < self.get_nframes())
-            sdf_writer.write(self.rdkit_mol, confId=frame_idx)
-        sdf_writer.close()

dpdata/cp2k/output.py

@@ -278,20 +278,20 @@ def get_frames (fname) :
 
     #conver to float array and add extra dimension for nframes
     cell = np.array(cell)
-    cell = cell.astype(np.float)
+    cell = cell.astype(float)
     cell = cell[np.newaxis, :, :]
     coord = np.array(coord)
-    coord = coord.astype(np.float)
+    coord = coord.astype(float)
     coord = coord[np.newaxis, :, :]
     atom_symbol_list = np.array(atom_symbol_list)
     force = np.array(force)
-    force = force.astype(np.float)
+    force = force.astype(float)
     force = force[np.newaxis, :, :]
 
     # virial is not necessary
     if stress:
         stress = np.array(stress)
-        stress = stress.astype(np.float)
+        stress = stress.astype(float)
         stress = stress[np.newaxis, :, :]
         # stress to virial conversion, default unit in cp2k is GPa
         # note the stress is virial = stress * volume

dpdata/format.py

@@ -0,0 +1,116 @@
+"""Implement the format plugin system."""
+import os
+from collections import abc
+from abc import ABC
+
+from .plugin import Plugin
+
+
+class Format(ABC):
+    __FormatPlugin = Plugin()
+    __FromPlugin = Plugin()
+    __ToPlugin = Plugin()
+
+    @staticmethod
+    def register(key):
+        return Format.__FormatPlugin.register(key)
+
+    @staticmethod
+    def register_from(key):
+        return Format.__FromPlugin.register(key)
+
+    @staticmethod
+    def register_to(key):
+        return Format.__ToPlugin.register(key)
+
+    @staticmethod
+    def get_formats():
+        return Format.__FormatPlugin.plugins
+
+    @staticmethod
+    def get_from_methods():
+        return Format.__FromPlugin.plugins
+
+    @staticmethod
+    def get_to_methods():
+        return Format.__ToPlugin.plugins
+
+    @staticmethod
+    def post(func_name):
+        def decorator(object):
+            if not isinstance(func_name, (list, tuple, set)):
+                object.post_func = (func_name,)
+            else:
+                object.post_func = func_name
+            return object
+        return decorator
+
+    def from_system(self, file_name, **kwargs):
+        """System.from
+
+        Parameters
+        ----------
+        file_name: str
+            file name
+
+        Returns
+        -------
+        data: dict
+            system data
+        """
+        raise NotImplementedError("%s doesn't support System.from" %(self.__class__.__name__))
+
+    def to_system(self, data, *args, **kwargs):
+        """System.to
+
+        Parameters
+        ----------
+        data: dict
+            system data
+        """
+        raise NotImplementedError("%s doesn't support System.to" %(self.__class__.__name__))
+
+    def from_labeled_system(self, file_name, **kwargs):
+        raise NotImplementedError("%s doesn't support LabeledSystem.from" %(self.__class__.__name__))
+
+    def to_labeled_system(self, data, *args, **kwargs):
+        return self.to_system(data, *args, **kwargs)
+
+    def from_bond_order_system(self, file_name, **kwargs):
+        raise NotImplementedError("%s doesn't support BondOrderSystem.from" %(self.__class__.__name__))
+
+    def to_bond_order_system(self, data, rdkit_mol, *args, **kwargs):
+        return self.to_system(data, *args, **kwargs)
+
+    class MultiModes:
+        """File mode for MultiSystems
+        0 (default): not implemented
+        1: every directory under the top-level directory is a system
+        """
+        NotImplemented = 0
+        Directory = 1
+
+    MultiMode = MultiModes.NotImplemented
+
+    def from_multi_systems(self, directory, **kwargs):
+        """MultiSystems.from
+        
+        Parameters
+        ----------
+        directory: str
+            directory of system
+        
+        Returns
+        -------
+        filenames: list[str]
+            list of filenames
+        """
+        if self.MultiMode == self.MultiModes.Directory:
+            return [name for name in os.listdir(directory) if os.path.isdir(os.path.join(directory, name))]
+        raise NotImplementedError("%s doesn't support MultiSystems.from" %(self.__class__.__name__))
+
+    def to_multi_systems(self, formulas, directory, **kwargs):
+        if self.MultiMode == self.MultiModes.Directory:
+            return [os.path.join(directory, ff) for ff in formulas]
+        raise NotImplementedError("%s doesn't support MultiSystems.to" %(self.__class__.__name__))
+

dpdata/plugin.py

@@ -0,0 +1,36 @@
+"""Base of plugin systems."""
+
+
+class Plugin:
+    """A class to register plugins.
+
+    Examples
+    --------
+    >>> Plugin = Register()
+    >>> @Plugin.register("xx")
+        def xxx():
+            pass
+    >>> print(Plugin.plugins['xx'])
+    """
+    def __init__(self):
+        self.plugins = {}
+
+    def register(self, key):
+        """Register a plugin.
+        
+        Parameter
+        ---------
+        key: str
+            Key of the plugin.
+        """
+        def decorator(object):
+            self.plugins[key] = object
+            return object
+        return decorator
+
+    def get_plugin(self, key):
+        return self.plugins[key]
+
+    def __add__(self, other):
+        self.plugins.update(other.plugins)
+        return self