Added support for using local data files.

HISTORY.rst

@@ -1,6 +1,13 @@
 =======
 History
 =======
+2024.6.27 -- Added support for using local data files.
+    * Added support in the Flowchart and Node classes for using local data files for
+      e.g. forcefields. This allows the user to specify a local file, which is copied to
+      the working directory of the job.
+    * Also added a flag to both the Flowchart and Node classes indicating that the job
+      is running in the JobServer rather than command-line.
+
 2024.5.27 -- Bugfix: Error saving results table.
 
 2024.5.26 -- Bugfix: Error when clicking "Cancel" on some dialogs

seamm/flowchart.py

@@ -6,12 +6,12 @@
 however, the flow starts at the 'start' node and follows the connections,
 so isolated nodes and fragments will not be executed."""
 
-from datetime import datetime
 import hashlib
 import json
 import logging
 import os
 import os.path
+from pathlib import Path
 import stat
 
 from packaging.version import Version
@@ -76,15 +76,21 @@ def __init__(
         # and make sure that the start node exists
         self.add_node(seamm.StartNode(flowchart=self))
 
-        # And the root directory
+        # And the root directory and other information
         self.root_directory = directory
+        self.in_jobserver = False
 
         # And the parser associated with this flowchart
         self._parser = None
 
     def __iter__(self):
         return self.graph.__iter__()
 
+    @property
+    def data_path(self):
+        """A path to local and user data, such as forcefields."""
+        return self._data_path
+
     @property
     def executor(self):
         """The executor for tasks."""
@@ -94,6 +100,24 @@ def executor(self):
     def executor(self, value):
         self._executor = value
 
+    @property
+    def in_jobserver(self):
+        """Whether running in a JobServer."""
+        return self._in_jobserver
+
+    @in_jobserver.setter
+    def in_jobserver(self, value):
+        self._in_jobserver = value
+        if value:
+            self._data_path = [
+                Path(self.root_directory) / "data",
+            ]  # path for local data in JobServer
+        else:
+            self._data_path = [
+                Path.home() / ".seamm.d" / "data",
+                Path.home() / "SEAMM" / "data",
+            ]  # path for local data on local machine
+
     @property
     def is_development(self):
         """Check if any of nodes are development versions."""
@@ -106,9 +130,7 @@ def is_development(self):
     def root_directory(self):
         """The root directory for files, etc for this flowchart"""
         if self._root_directory is None:
-            self._root_directory = os.path.join(
-                os.getcwd(), datetime.now().isoformat(sep="_", timespec="seconds")
-            )
+            self._root_directory = os.getcwd()
         return self._root_directory
 
     @root_directory.setter
@@ -214,6 +236,9 @@ def get_nodes(self):
             nodes.append(next_node)
             next_node = next_node.next()
         logger.debug("Finished getting nodes")
+
+        self.reset_visited()
+
         return nodes
 
     def last_node(self, node="1"):

seamm/node.py

@@ -222,6 +222,11 @@ def calculation(self):
         """The type of calculation for filtering available results."""
         return self._calculation
 
+    @property
+    def data_path(self):
+        """A path to local and user data, such as forcefields."""
+        return self.flowchart.data_path
+
     @property
     def description(self):
         """A textual description of this node"""
@@ -254,6 +259,16 @@ def header(self):
             ".".join(str(e) for e in self._id), self.title, self.version
         )
 
+    @property
+    def data_files(self):
+        """tuples of short name and path for any data files needed"""
+        return self.list_data_files()
+
+    @property
+    def in_jobserver(self):
+        """Whether running in a jobserver"""
+        return self.flowchart.in_jobserver
+
     @property
     def indent(self):
         """The amount to indent the output of this step in **job.out**."""
@@ -435,6 +450,31 @@ def reset_id(self):
         """Reset the id for node"""
         self._id = None
 
+    def find_data_file(self, filename):
+        """Using the data_path, find a file.
+
+        Parameters
+        ----------
+        filename : str or pathlib.Path
+            Name of the file to find -- a relative path
+
+        Returns
+        -------
+        path : pathlib.Path
+            The path to the file
+
+        Exceptions
+        ----------
+        FileNotFoundError if the file does not exist.
+        """
+        for path in self.data_path:
+            tmp = path / filename
+            self.logger.debug(f"  trying {tmp}")
+            if tmp.exists():
+                return tmp.expanduser().resolve()
+        self.logger.debug(f"Did not find {filename}")
+        raise FileNotFoundError(f"Data file '{filename}' not found.")
+
     def get_gui_data(self, key, gui=None):
         """Return an element from the GUI dictionary"""
         if gui is None:
@@ -602,6 +642,28 @@ def get_table(self, tablename, create=True):
         table_handle = self.get_variable(tablename)
         return table_handle["table"]
 
+    def glob_data_files(self, pattern):
+        """Using the data_path, glob for files.
+
+        Parameters
+        ----------
+        filename : str or pathlib.Path
+            Name of the file to find -- a relative path
+
+        Returns
+        -------
+        paths : [pathlib.Path]
+            A list of paths to the files
+
+        Exceptions
+        ----------
+        FileNotFoundError if the file does not exist.
+        """
+        paths = []
+        for path in self.data_path:
+            paths.extend(path.glob(pattern))
+        return paths
+
     def connections(self):
         """Return a list of all the incoming and outgoing edges
         for this node, giving the anchor points and other node
@@ -710,6 +772,16 @@ def existing_tables(self):
 
         return sorted(tables)
 
+    def list_data_files(self):
+        """Returns a list of auxilliary data files needed, like forcefields.
+
+        Returns
+        -------
+        (shortname, pathlib.Path)
+            Tuples with the local path or URI for the file, and its full pathlib.Path
+        """
+        return []
+
     def run(self, printer=None):
         """Do whatever we need to do! The base class does nothing except
         return the next node.