Add verbose options for mol2 and element (#729)

* add verbose options to reduce warnings for parsing elements and mol2 file

* adjust unit tests

Author: daico007

gmso/core/element.py

@@ -64,7 +64,7 @@ class Config:
         allow_mutation = False
 
 
-def element_by_symbol(symbol):
+def element_by_symbol(symbol, verbose=False):
     """Search for an element by its symbol.
 
     Look up an element from a list of known elements by symbol.
@@ -73,7 +73,9 @@ def element_by_symbol(symbol):
     Parameters
     ----------
     symbol : str
-        Element symbol to look for, digits and spaces are removed before search
+        Element symbol to look for, digits and spaces are removed before search.
+    verbose : bool, optional, default=False
+        If True, raise warnings if symbol has been trimmed before search.
 
     Returns
     -------
@@ -83,7 +85,7 @@ def element_by_symbol(symbol):
     """
     symbol_trimmed = sub(r"[0-9 -]", "", symbol).capitalize()
 
-    if symbol_trimmed != symbol:
+    if symbol_trimmed != symbol and verbose:
         msg = (
             f"Numbers and spaces are not considered when searching by element symbol.\n"
             f"{symbol} became {symbol_trimmed}"
@@ -94,7 +96,7 @@ def element_by_symbol(symbol):
     return matched_element
 
 
-def element_by_name(name):
+def element_by_name(name, verbose=False):
     """Search for an element by its name.
 
     Look up an element from a list of known elements by name.
@@ -103,7 +105,9 @@ def element_by_name(name):
     Parameters
     ----------
     name : str
-        Element name to look for, digits and spaces are removed before search
+        Element name to look for, digits and spaces are removed before search.
+    verbose : bool, optional, default=False
+        If True, raise warnings if name has been trimmed before search.
 
     Returns
     -------
@@ -113,7 +117,7 @@ def element_by_name(name):
     """
     name_trimmed = sub(r"[0-9 -]", "", name).lower()
 
-    if name_trimmed != name:
+    if name_trimmed != name and verbose:
         msg = (
             "Numbers and spaces are not considered when searching by element name. \n"
             f"{name} became {name_trimmed}"
@@ -124,7 +128,7 @@ def element_by_name(name):
     return matched_element
 
 
-def element_by_atomic_number(atomic_number):
+def element_by_atomic_number(atomic_number, verbose=False):
     """Search for an element by its atomic number.
 
     Look up an element from a list of known elements by atomic number.
@@ -134,7 +138,9 @@ def element_by_atomic_number(atomic_number):
     ----------
     atomic_number : int
         Element atomic number that need to look for
-        if a string is provided, only numbers are considered during the search
+        if a string is provided, only numbers are considered during the search.
+    verbose : bool, optional, default=False
+        If True, raise warnings if atomic_number has been trimmed before search.
 
     Returns
     -------
@@ -146,7 +152,7 @@ def element_by_atomic_number(atomic_number):
         atomic_number_trimmed = int(
             sub("[a-z -]", "", atomic_number.lower()).lstrip("0")
         )
-        if str(atomic_number_trimmed) != atomic_number:
+        if str(atomic_number_trimmed) != atomic_number and verbose:
             msg = (
                 f"Letters and spaces are not considered when searching by element atomic number. \n "
                 f"{atomic_number} became {atomic_number_trimmed}"
@@ -162,7 +168,7 @@ def element_by_atomic_number(atomic_number):
     return matched_element
 
 
-def element_by_mass(mass, exact=True):
+def element_by_mass(mass, exact=True, verbose=False):
     """Search for an element by its mass.
 
     Look up an element from a list of known elements by mass.
@@ -173,11 +179,13 @@ def element_by_mass(mass, exact=True):
     ----------
     mass : int, float
         Element mass that need to look for, if a string is provided,
-        only numbers are considered during the search
-        Mass unyt is assumed to be u.amu, unless specfied (which will be converted to u.amu)
+        only numbers are considered during the search.
+        Mass unyt is assumed to be u.amu, unless specfied (which will be converted to u.amu).
     exact : bool, optional,  default=True
         This method can be used to search for an exact mass (up to the first decimal place)
-        or search for an element  mass closest to the mass entered
+        or search for an element  mass closest to the mass entered.
+    verbose : bool, optional, default=False
+        If True, raise warnings if mass has been trimmed before search.
 
     Returns
     -------
@@ -188,7 +196,7 @@ def element_by_mass(mass, exact=True):
     if isinstance(mass, str):
         # Convert to float if a string is provided
         mass_trimmed = np.round(float(sub(r"[a-z -]", "", mass.lower())))
-        if str(mass_trimmed) != mass:
+        if str(mass_trimmed) != mass and verbose:
             msg1 = (
                 f"Letters and spaces are not considered when searching by element mass.\n"
                 f"{mass} became {mass_trimmed}"
@@ -208,13 +216,14 @@ def element_by_mass(mass, exact=True):
         mass_closest = min(
             mass_dict.keys(), key=lambda k: abs(k - mass_trimmed)
         )
-        msg2 = f"Closest mass to {mass_trimmed}: {mass_closest}"
-        warnings.warn(msg2)
+        if verbose:
+            msg2 = f"Closest mass to {mass_trimmed}: {mass_closest}"
+            warnings.warn(msg2)
         matched_element = mass_dict.get(mass_closest)
     return matched_element
 
 
-def element_by_smarts_string(smarts_string):
+def element_by_smarts_string(smarts_string, verbose=False):
     """Search for an element by a given SMARTS string.
 
     Look up an element from a list of known elements by SMARTS string.
@@ -228,6 +237,8 @@ def element_by_smarts_string(smarts_string):
         and look up an Element. Note that this means some SMARTS grammar may
         not be parsed properly. For details, see
         https://github.com/mosdef-hub/foyer/issues/63
+    verbose : bool, optional, default=False
+        If True, raise warnings if smarts_string has been trimmed before search.
 
     Returns
     -------
@@ -267,7 +278,7 @@ def element_by_smarts_string(smarts_string):
     return matched_element
 
 
-def element_by_atom_type(atom_type):
+def element_by_atom_type(atom_type, verbose=False):
     """Search for an element by a given gmso AtomType object.
 
     Look up an element from a list of known elements by atom type.
@@ -280,6 +291,8 @@ def element_by_atom_type(atom_type):
         looked up in the order of mass, name, and finally definition (the
         SMARTS string).  Because of the loose structure of this class, a
         successful lookup is not guaranteed.
+    verbose : bool, optional, default=False
+        If True, raise warnings if atom_type has been trimmed before search.
 
     Returns
     -------
@@ -291,11 +304,15 @@ def element_by_atom_type(atom_type):
     matched_element = None
 
     if matched_element is None and atom_type.mass:
-        matched_element = element_by_mass(atom_type.mass, exact=False)
+        matched_element = element_by_mass(
+            atom_type.mass, exact=False, verbose=verbose
+        )
     if matched_element is None and atom_type.name:
-        matched_element = element_by_symbol(atom_type.name)
+        matched_element = element_by_symbol(atom_type.name, verbose=verbose)
     if matched_element is None and atom_type.definition:
-        matched_element = element_by_smarts_string(atom_type.definition)
+        matched_element = element_by_smarts_string(
+            atom_type.definition, verbose=verbose
+        )
 
     if matched_element is None:
         raise GMSOError(

gmso/formats/mol2.py

@@ -12,7 +12,7 @@
 
 
 @loads_as(".mol2")
-def read_mol2(filename, site_type="atom"):
+def read_mol2(filename, site_type="atom", verbose=False):
     """Read in a TRIPOS mol2 file format into a gmso topology object.
 
     Creates a Topology from a mol2 file structure. This will read in the
@@ -28,6 +28,8 @@ def read_mol2(filename, site_type="atom"):
         tells the reader to consider the elements saved in the mol2 file, and
         if the type is 'lj', to not try to identify the element of the site,
         instead saving the site name.
+    verbose : bool, optional, default=False
+        If True, raise warnings for any assumptions made during the parsing.
 
     Returns
     -------
@@ -79,13 +81,13 @@ def read_mol2(filename, site_type="atom"):
                 "Skipping current section and moving to the next RTI header."
             )
         else:
-            supported_rti[section](topology, sections[section])
+            supported_rti[section](topology, sections[section], verbose)
 
     # TODO: read in parameters to correct attribute as well. This can be saved in various rti sections.
     return topology
 
 
-def _parse_lj(top, section):
+def _parse_lj(top, section, verbose):
     """Parse atom of lj style from mol2 file."""
     for line in section:
         if line.strip():
@@ -95,9 +97,10 @@ def _parse_lj(top, section):
             try:
                 charge = float(content[8])
             except IndexError:
-                warnings.warn(
-                    f"No charge was detected for site {content[1]} with index {content[0]}"
-                )
+                if verbose:
+                    warnings.warn(
+                        f"No charge was detected for site {content[1]} with index {content[0]}"
+                    )
                 charge = None
 
             atom = Atom(
@@ -109,7 +112,7 @@ def _parse_lj(top, section):
             top.add_site(atom)
 
 
-def _parse_atom(top, section):
+def _parse_atom(top, section, verbose):
     """Parse atom information from the mol2 file."""
 
     def parse_ele(*symbols):
@@ -127,7 +130,7 @@ def parse_ele(*symbols):
             position = [float(x) for x in content[2:5]] * u.Å
             element = parse_ele(content[5], content[1])
 
-            if not element:
+            if not element and verbose:
                 warnings.warn(
                     f"No element detected for site {content[1]} with index {content[0]}, "
                     "consider manually adding the element to the topology"
@@ -136,9 +139,10 @@ def parse_ele(*symbols):
             try:
                 charge = float(content[8])
             except IndexError:
-                warnings.warn(
-                    f"No charge was detected for site {content[1]} with index {content[0]}"
-                )
+                if verbose:
+                    warnings.warn(
+                        f"No charge was detected for site {content[1]} with index {content[0]}"
+                    )
                 charge = None
             molecule = top.label if top.__dict__.get("label") else top.name
             atom = Atom(
@@ -152,7 +156,7 @@ def parse_ele(*symbols):
             top.add_site(atom)
 
 
-def _parse_bond(top, section):
+def _parse_bond(top, section, verbose):
     """Parse bond information from the mol2 file."""
     for line in section:
         if line.strip():
@@ -166,7 +170,7 @@ def _parse_bond(top, section):
             top.add_connection(bond)
 
 
-def _parse_box(top, section):
+def _parse_box(top, section, verbose):
     """Parse box information from the mol2 file."""
     if top.box:
         warnings.warn(
@@ -182,6 +186,6 @@ def _parse_box(top, section):
             )
 
 
-def _parse_molecule(top, section):
+def _parse_molecule(top, section, verbose):
     """Parse molecule information from the mol2 file."""
     top.label = str(section[0].strip())

gmso/tests/test_element.py

@@ -20,7 +20,7 @@ def test_element(self):
     def test_element_by_name(self):
         for idx, name in enumerate(["Carbon", "carbon", " CarBon 12 "]):
             with pytest.warns(UserWarning if idx != 1 else None):
-                carbon = element.element_by_name(name)
+                carbon = element.element_by_name(name, verbose=True)
 
                 assert carbon.name == element.Carbon.name
                 assert carbon.symbol == element.Carbon.symbol
@@ -29,7 +29,7 @@ def test_element_by_name(self):
     def test_element_by_symbol(self):
         for idx, symbol in enumerate(["N", "n", " N7"]):
             with pytest.warns(UserWarning if idx != 0 else None):
-                nitrogen = element.element_by_symbol(symbol)
+                nitrogen = element.element_by_symbol(symbol, verbose=True)
 
                 assert nitrogen.name == element.Nitrogen.name
                 assert nitrogen.symbol == element.Nitrogen.symbol

gmso/tests/test_mol2.py

@@ -58,7 +58,7 @@ def test_read_mol2(self):
             UserWarning,
             match=r"No charge was detected for site C with index 1",
         ):
-            top = Topology.load(get_fn("ethane.mol2"))
+            top = Topology.load(get_fn("ethane.mol2"), verbose=True)
         assert list(top.sites)[0].charge is None
 
     def test_residue(self):
@@ -96,7 +96,9 @@ def test_no_charge_lj(self):
             match=r"No charge was detected for site .* with index \d+$",
         ):
             top = Topology.load(
-                get_path("methane_missing_charge.mol2"), site_type="lj"
+                get_path("methane_missing_charge.mol2"),
+                site_type="lj",
+                verbose=True,
             )
 
     def test_wrong_path(self):
@@ -118,7 +120,7 @@ def test_broken_files(self):
             UserWarning,
             match=r"This mol2 file has two boxes to be read in, only reading in one with dimensions Box\(a=0.72",
         ):
-            Topology.load(get_fn("broken.mol2"))
+            Topology.load(get_fn("broken.mol2"), verbose=True)
 
     def test_benzene_mol2_elements(self):
         top = Topology.load(get_fn("benzene.mol2"))
@@ -132,7 +134,7 @@ def test_neopentane_mol2_elements(self):
             match=r"No element detected for site .+ with index \d+, "
             r"consider manually adding the element to the topology$",
         ):
-            top = Topology.load(get_fn("neopentane.mol2"))
+            top = Topology.load(get_fn("neopentane.mol2"), verbose=True)
 
     def test_mol2_residues(self):
         top = Topology.load(get_fn("parmed.mol2"))