Merge pull request #60 from molssi-seamm/dev

Enhancements to SDF and XYZ files

HISTORY.rst

@@ -1,6 +1,15 @@
 =======
 History
 =======
+2025.1.3 -- Enhancements to SDF and XYZ files
+  * Added more keywords to the header of XYZ files to allow for more flexibility in
+    reading them. Specifically 'title', 'model', and 'name', which can be used to name
+    the system and/or configuration.
+  * When reading SDF files, 'keep current name' will use the encoded system name in SDF
+    files written by SEAMM, if it exists.
+  * Fixed minor issue writing SDF files where the 'configurations' widget was displayed
+    when writing the current configuration. The widget is now correctly hidden.
+
 2024.12.29 -- Bugfix: Issue with reusing systems matching SDF files.
   * The logic was faulty, so if the first structure in an SDF file was a configuration
     of an existing system, it was not added to the system correctly.

read_structure_step/formats/sdf/sdf.py

@@ -9,6 +9,7 @@
 import string
 import subprocess
 import time
+import traceback
 
 from openbabel import openbabel
 
@@ -209,15 +210,15 @@ def load_sdf(
             # See if either the system or configuration names are "title"
             if (
                 system_name is not None
-                and system_name.lower() == "title"
+                and system_name.lower() in ("keep current name", "title")
                 and have_sysname
             ):
                 # Reuse the system if it exists
                 if system_db.system_exists(sysname):
                     system = system_db.get_system(sysname)
                 elif structure_no > 1:
                     system = system_db.create_system()
-                if configuration_name.lower() == "title":
+                if configuration_name.lower() in ("keep current name", "title"):
                     names = system.configuration_names
                     if confname in names:
                         cid = system.get_configuration_id(confname)
@@ -238,6 +239,9 @@ def load_sdf(
                 printer("")
                 printer(f"    Error handling entry {record_no} in the SDF file:")
                 printer("        " + str(e))
+                printer(60 * "-")
+                printer("\n".join(traceback.format_exception(e)))
+                printer(60 * "-")
                 printer("    Text of the entry is")
                 printer("    " + 60 * "-")
                 for line in text.splitlines():
@@ -253,7 +257,7 @@ def load_sdf(
             # Set the system name
             if system_name is not None and system_name != "":
                 lower_name = system_name.lower()
-                if lower_name == "title":
+                if lower_name in ("keep current name", "title"):
                     if sysname != "":
                         system.name = sysname
                     else:
@@ -276,7 +280,7 @@ def load_sdf(
             # And the configuration name
             if configuration_name is not None and configuration_name != "":
                 lower_name = configuration_name.lower()
-                if lower_name == "title":
+                if lower_name in ("keep current name", "title"):
                     if confname != "":
                         configuration.name = confname
                     else:

read_structure_step/formats/xyz/xyz.py

@@ -393,6 +393,9 @@ def load_xyz(
                     ):
                         logger.warning(f"{structure_no}: {tmp}")
 
+                # Extract any additional information from the title
+                extra = {}
+
                 if file_type == "Minnesota":
                     # Record the charge, and the spin state
                     configuration.charge = charge
@@ -415,8 +418,17 @@ def load_xyz(
                                     configuration.spin_multiplicity = int(val)
                                 except Exception:
                                     pass
-                            elif key == "CSD_code":
+                            elif key in ("CSD_code", "title"):
                                 title = val
+                            elif key == "model":
+                                extra["model"] = val
+                            elif key == "name":
+                                extra["name"] = val
+                            elif key == "symmetry":
+                                extra["symmetry"] = val
+                        else:
+                            if tmp == "TS":
+                                extra["target"] = "TS"
 
                 # Set the system name
                 if system_name is not None and system_name != "":
@@ -438,6 +450,10 @@ def load_xyz(
                         system.name = configuration.inchi
                     elif "formula" in lower_name:
                         system.name = configuration.formula[0]
+                    elif "name" in lower_name and "name" in extra:
+                        system.name = extra["name"]
+                    elif "model" in lower_name and "model" in extra:
+                        system.name = extra["model"]
                     else:
                         system.name = system_name
 
@@ -463,6 +479,10 @@ def load_xyz(
                         configuration.name = str(structure_no)
                     elif "formula" in lower_name:
                         configuration.name = configuration.formula[0]
+                    elif "name" in lower_name and "name" in extra:
+                        configuration.name = extra["name"]
+                    elif "model" in lower_name and "model" in extra:
+                        configuration.name = extra["model"]
                     else:
                         configuration.name = configuration_name
 

read_structure_step/tk_write_structure.py

@@ -46,7 +46,7 @@ def create_dialog(self):
             self[key] = P[key].widget(frame)
 
         # Set bindings
-        for name in ("file", "file type"):
+        for name in ("file", "file type", "structures"):
             combobox = self[name].combobox
             combobox.bind("<<ComboboxSelected>>", self.reset_dialog)
             combobox.bind("<Return>", self.reset_dialog)
@@ -72,6 +72,7 @@ def reset_dialog(self, widget=None):
         extension = ""
         filename = self["file"].get().strip()
         file_type = self["file type"].get()
+        structures = self["structures"].get()
 
         if self.is_expr(filename) or self.is_expr(file_type):
             extension = "all"
@@ -100,7 +101,8 @@ def reset_dialog(self, widget=None):
         items = []
         if extension == "all" or not metadata["single_structure"]:
             items.append("structures")
-            items.append("configurations")
+            if structures != "current configuration":
+                items.append("configurations")
             items.append("ignore missing")
             items.append("number per file")
         items.append("remove hydrogens")