chore: Convert str.format to f-strings (#138)

altamisa/apps/isatab2dot.py

@@ -34,18 +34,15 @@ def print_dot(
 ):
     print(indent + "/* materials */", file=outf)
     for name, mat in obj.materials.items():
-        label = json.dumps("{}:\n{}\n({})".format(mat.type, mat.name if mat.name else "-", name))
+        label = json.dumps(f"{mat.type}:\n{mat.name if mat.name else '-'}\n({name})")
         print(
-            "{}{} [label={},shape={},color={},fontcolor={}]".format(
-                indent, json.dumps(name), label, mat_shape, mat_color, mat_color
-            ),
+            f"{indent}{json.dumps(name)} [label={label},shape={mat_shape},color={mat_color},fontcolor={mat_color}]",
             file=outf,
         )
     print(indent + "/* processes */", file=outf)
     for name, proc in obj.processes.items():
         label = json.dumps(
-            "{}:\n{}\n{}\n({})".format(
-                "Process",
+            "Process:\n{}\n{}\n({})".format(
                 proc.protocol_ref if proc.protocol_ref else "-",
                 proc.name if proc.name else "-",
                 name,
@@ -59,7 +56,7 @@ def print_dot(
         )
     print(indent + "/* arcs */", file=outf)
     for arc in obj.arcs:
-        print("{}{} -> {};".format(indent, json.dumps(arc.tail), json.dumps(arc.head)), file=outf)
+        print(f"{indent}{json.dumps(arc.tail)} -> {json.dumps(arc.head)};", file=outf)
 
 
 def run(args: Arguments):
@@ -79,27 +76,25 @@ def run(args: Arguments):
 
         for s, study_info in enumerate(investigation.studies):
             if not study_info.info.path:
-                print("  /* no file for study {} */".format(s + 1), file=output_file)
+                print(f"  /* no file for study {s + 1} */", file=output_file)
                 continue
             with open(os.path.join(path, study_info.info.path), "rt") as inputf:
-                study = StudyReader.from_stream("S{}".format(s + 1), inputf).read()
-            print("  /* study {} */".format(study_info.info.path), file=output_file)
-            print("  subgraph clusterStudy{} {{".format(s), file=output_file)
-            print('    label = "Study: {}"'.format(study_info.info.path), file=output_file)
+                study = StudyReader.from_stream(f"S{s + 1}", inputf).read()
+            print(f"  /* study {study_info.info.path} */", file=output_file)
+            print(f"  subgraph clusterStudy{s} {{", file=output_file)
+            print(f'    label = "Study: {study_info.info.path}"', file=output_file)
             print_dot(study, output_file)
             print("  }", file=output_file)
 
             for a, assay_info in enumerate(study_info.assays):
                 if not assay_info.path:
-                    print("  /* no file for assay {} */".format(a + 1), file=output_file)
+                    print(f"  /* no file for assay {a + 1} */", file=output_file)
                     continue
                 with open(os.path.join(path, assay_info.path), "rt") as inputf:
-                    assay = AssayReader.from_stream(
-                        "S{}".format(s + 1), "A{}".format(a + 1), inputf
-                    ).read()
-                print("  /* assay {} */".format(assay_info.path), file=output_file)
-                print("  subgraph clusterAssayS{}A{} {{".format(s, a), file=output_file)
-                print('    label = "Assay: {}"'.format(assay_info.path), file=output_file)
+                    assay = AssayReader.from_stream(f"S{s + 1}", f"A{a + 1}", inputf).read()
+                print(f"  /* assay {assay_info.path} */", file=output_file)
+                print(f"  subgraph clusterAssayS{s}A{a} {{", file=output_file)
+                print(f'    label = "Assay: {assay_info.path}"', file=output_file)
                 print_dot(assay, output_file)
                 print("  }", file=output_file)
 

altamisa/apps/isatab2isatab.py

@@ -61,8 +61,7 @@ def run_warnings_caught(args: Arguments):
     path_in = os.path.realpath(os.path.dirname(args.input_investigation_file))
     path_out = os.path.realpath(os.path.dirname(args.output_investigation_file))
     if path_in == path_out:
-        tpl = "Can't output ISA-tab files to same directory as as input: {} == {}"
-        msg = tpl.format(path_in, path_out)
+        msg = f"Can't output ISA-tab files to same directory as as input: {path_in} == {path_out}"
         raise IsaException(msg)
 
     with ExitStack() as stack:
@@ -98,15 +97,13 @@ def run_reading(
     for s, study_info in enumerate(investigation.studies):
         if study_info.info.path:
             with open(os.path.join(path_in, study_info.info.path), "rt") as inputf:
-                studies[s] = StudyReader.from_stream("S{}".format(s + 1), inputf).read()
+                studies[s] = StudyReader.from_stream(f"S{s + 1}", inputf).read()
         if study_info.assays:
             assays[s] = {}
         for a, assay_info in enumerate(study_info.assays):
             if assay_info.path:
                 with open(os.path.join(path_in, assay_info.path), "rt") as inputf:
-                    assays[s][a] = AssayReader.from_stream(
-                        "S{}".format(s + 1), "A{}".format(a + 1), inputf
-                    ).read()
+                    assays[s][a] = AssayReader.from_stream(f"S{s + 1}", f"A{a + 1}", inputf).read()
 
     # Validate studies and assays
     for s, study_info in enumerate(investigation.studies):

altamisa/apps/isatab_validate.py

@@ -82,15 +82,13 @@ def run_warnings_caught(args: Arguments):
     for s, study_info in enumerate(investigation.studies):
         if study_info.info.path:
             with open(os.path.join(path_in, study_info.info.path), "rt") as inputf:
-                studies[s] = StudyReader.from_stream("S{}".format(s + 1), inputf).read()
+                studies[s] = StudyReader.from_stream(f"S{s + 1}", inputf).read()
         if study_info.assays:
             assays[s] = {}
         for a, assay_info in enumerate(study_info.assays):
             if assay_info.path:
                 with open(os.path.join(path_in, assay_info.path), "rt") as inputf:
-                    assays[s][a] = AssayReader.from_stream(
-                        "S{}".format(s + 1), "A{}".format(a + 1), inputf
-                    ).read()
+                    assays[s][a] = AssayReader.from_stream(f"S{s + 1}", f"A{a + 1}", inputf).read()
 
     # Validate studies and assays
     for s, study_info in enumerate(investigation.studies):

altamisa/isatab/headers.py

@@ -446,8 +446,7 @@ def _parse_next(self):
                         raise ParseIsatabException(msg)
                     return self._parse_labeled_column_header(val, label, type_)
         # None of the if-statements above was taken
-        tpl = 'Header "{}" unknown, processing unclear'
-        msg = tpl.format(val)
+        msg = f'Header "{val}" unknown, processing unclear'
         raise ParseIsatabException(msg)
 
     def _parse_term_source_ref(self):
@@ -471,8 +470,7 @@ def _parse_simple_column_header(self, type_):
     def _parse_labeled_column_header(self, val, key, type_):
         tok = val[len(key) :]  # strip '^{key}'
         if not tok or tok[0] != "[" or tok[-1] != "]":
-            tpl = "Problem parsing labeled header {}"
-            msg = tpl.format(val)
+            msg = f"Problem parsing labeled header {val}"
             raise ParseIsatabException(msg)
         self.col_no += 1
         return type_(self.col_no - 1, tok[1:-1])

altamisa/isatab/helpers.py

@@ -21,7 +21,6 @@ def list_strip(line: List[str]) -> List[str]:
     """Remove trailing space from strings in a list (e.g. a csv line)"""
     new_line = [field.strip() for field in line]
     if new_line != line:
-        tpl = "Removed trailing whitespaces in fields of line: {}"
-        msg = tpl.format(line)
+        msg = f"Removed trailing whitespaces in fields of line: {line}"
         warnings.warn(msg, ParseIsatabWarning)
     return new_line

altamisa/isatab/models.py

@@ -509,7 +509,7 @@ def __getitem__(self, idx):
         elif idx == 1:
             return self.head
         else:
-            raise IndexError("Invalid index: %d" % idx)  # pragma: no cover
+            raise IndexError(f"Invalid index: {idx}")  # pragma: no cover
 
 
 @attr.s(auto_attribs=True, frozen=True)

altamisa/isatab/parse_assay_study.py

@@ -130,8 +130,10 @@ def _assign_column_headers(self):  # noqa: C901
                 header.column_type not in self.name_headers
                 and header.column_type not in self.allowed_column_types
             ):
-                tpl = 'Invalid column type occured "{}" not in {}'
-                msg = tpl.format(header.column_type, self.allowed_column_types)
+                msg = (
+                    "Invalid column type occured "
+                    f'"{header.column_type}" not in {self.allowed_column_types}'
+                )
                 raise ParseIsatabException(msg)
             # Most headers are not secondary, so make this the default state.
             is_secondary = False
@@ -206,7 +208,7 @@ def _assign_column_headers(self):  # noqa: C901
                 ):  # pragma: no cover
                     tpl = (
                         "Ontologies not supported for primary annotation "
-                        "'{}' (in col {}).".format(prev.column_type, "{}")
+                        f"'{prev.column_type}' (in col {{}})."
                     )
                 elif prev.term_source_ref_header:  # pragma: no cover
                     tpl = 'Seen "Term Source REF" header for same entity ' "in col {}"
@@ -232,8 +234,7 @@ def _assign_column_headers(self):  # noqa: C901
 
     @staticmethod
     def _raise_seen_before(name, col_no):  # pragma: no cover
-        tpl = 'Seen "{}" header for same entity in col {}'
-        msg = tpl.format(name, col_no)
+        msg = f'Seen "{name}" header for same entity in col {col_no}'
         raise ParseIsatabException(msg)
 
     def _build_complex(
@@ -256,7 +257,7 @@ def _build_complex(
         unit = self._build_freetext_or_term_ref(header.unit_header, line)
         if unit is not None and not isinstance(unit, (str, models.OntologyTermRef)):
             raise ParseIsatabException(
-                "Unit must be a string or an OntologyTermRef, not {}".format(type(unit))
+                f"Unit must be a string or an OntologyTermRef, not {type(unit)}"
             )
         # Then, constructing ``klass`` is easy
         return klass(header.label, value, unit)
@@ -284,11 +285,10 @@ def _build_freetext_or_term_ref(
                     ]
                     return term_refs
                 else:  # pragma: no cover
-                    tpl = (
+                    msg = (
                         "Irregular numbers of fields in ontology term columns"
-                        "(i.e. ';'-separated fields): {}"
+                        f"(i.e. ';'-separated fields): {line[header.col_no : header2.col_no + 2]}"
                     )
-                    msg = tpl.format(line[header.col_no : header2.col_no + 2])
                     raise ParseIsatabException(msg)
 
             # Else, just create single ontology term references
@@ -348,24 +348,22 @@ def build(self, line: List[str]) -> models.Material:
         # First, build the individual components
         if not self.name_header:
             raise ParseIsatabException(
-                "No name header found for material found for file {}".format(self.filename)
+                f"No name header found for material found for file {self.filename}"
             )
         type_ = self.name_header.column_type
-        assay_id = "-{}".format(self.assay_id) if self.assay_id else ""
+        assay_id = f"-{self.assay_id}" if self.assay_id else ""
         name = line[self.name_header.col_no]
         if name:
             # make material/data names unique by column
             if self.name_header.column_type == table_headers.SOURCE_NAME:
-                unique_name = "{}-{}-{}".format(self.study_id, "source", name)
+                unique_name = f"{self.study_id}-source-{name}"
             elif self.name_header.column_type == table_headers.SAMPLE_NAME:
                 # use static column identifier "sample-", since the same
                 # samples occur in different columns in study and assay
-                unique_name = "{}-{}-{}".format(self.study_id, "sample", name)
+                unique_name = f"{self.study_id}-sample-{name}"
             else:
                 # anything else gets the column id
-                unique_name = "{}{}-{}-COL{}".format(
-                    self.study_id, assay_id, name, self.name_header.col_no + 1
-                )
+                unique_name = f"{self.study_id}{assay_id}-{name}-COL{self.name_header.col_no + 1}"
         else:
             name_val = "{}{}-{} {}-{}-{}".format(
                 self.study_id,
@@ -434,8 +432,7 @@ def build(self, line: List[str]) -> models.Process:
                 try:
                     date = datetime.strptime(line[self.date_header.col_no], "%Y-%m-%d").date()
                 except ValueError as e:  # pragma: no cover
-                    tpl = 'Invalid ISO8601 date "{}"'  # pragma: no cover
-                    msg = tpl.format(line[self.date_header.col_no])
+                    msg = f'Invalid ISO8601 date "{line[self.date_header.col_no]}"'  # pragma: no cover
                     raise ParseIsatabException(msg) from e
             else:
                 date = ""
@@ -479,14 +476,11 @@ def _build_protocol_ref_and_name(
     ) -> Tuple[str, Union[models.AnnotatedStr, str], Optional[str], Optional[str]]:
         # At least one of these headers has to be specified
         if not self.name_header and not self.protocol_ref_header:  # pragma: no cover
-            raise ParseIsatabException(
-                "No protocol reference header found for process found for file {}".format(
-                    self.filename
-                )
-            )
+            msg = f"No protocol reference header found for process found for file {self.filename}"
+            raise ParseIsatabException(msg)
         # Perform case distinction on which case is actually true
         counter_value = self._next_counter()
-        assay_id = "-{}".format(self.assay_id) if self.assay_id else ""
+        assay_id = f"-{self.assay_id}" if self.assay_id else ""
         name = None
         name_type = None
         if not self.name_header:  # and self.protocol_ref_header:
@@ -509,9 +503,7 @@ def _build_protocol_ref_and_name(
             name = line[self.name_header.col_no]
             name_type = self.name_header.column_type
             if name:  # Use name if available
-                unique_name = "{}{}-{}-{}".format(
-                    self.study_id, assay_id, name, self.name_header.col_no + 1
-                )
+                unique_name = f"{self.study_id}{assay_id}-{name}-{self.name_header.col_no + 1}"
             else:  # Empty!  # pragma: no cover
                 name_val = "{}{}-{} {}-{}-{}".format(
                     self.study_id,
@@ -527,9 +519,7 @@ def _build_protocol_ref_and_name(
             name = line[self.name_header.col_no]
             name_type = self.name_header.column_type
             if name:
-                unique_name = "{}{}-{}-{}".format(
-                    self.study_id, assay_id, name, self.name_header.col_no + 1
-                )
+                unique_name = f"{self.study_id}{assay_id}-{name}-{self.name_header.col_no + 1}"
             else:
                 name_val = "{}{}-{}-{}-{}".format(
                     self.study_id,
@@ -544,7 +534,7 @@ def _build_protocol_ref_and_name(
                 tpl = "Missing protocol reference in column {} of file {} "
                 msg = tpl.format(self.protocol_ref_header.col_no + 1, self.filename)
             else:
-                msg = "Missing protocol reference in file {}".format(self.filename)
+                msg = f"Missing protocol reference in file {self.filename}"
             raise ParseIsatabException(msg)
         return protocol_ref, unique_name, name, name_type
 
@@ -596,16 +586,16 @@ def _intercept_duplicates(self, start, end):
         ]
         header = [h for h in self.header[start:end] if h.column_type in column_types_to_check]
         names = [
-            "{}[{}]".format(h.column_type, h.label)
-            if isinstance(h, LabeledColumnHeader)
-            else h.column_type
+            f"{h.column_type}[{h.label}]" if isinstance(h, LabeledColumnHeader) else h.column_type
             for h in header
         ]
         duplicates = set([c for c in names if names.count(c) > 1])
         if duplicates:
-            assay = " assay {}".format(self.assay_id) if self.assay_id else ""
-            tpl = "Found duplicated column types in header of study {}{}: {}"
-            msg = tpl.format(self.study_id, assay, ", ".join(duplicates))
+            assay = f" assay {self.assay_id}" if self.assay_id else ""
+            msg = (
+                "Found duplicated column types in header of study "
+                f"{self.study_id}{assay}: {', '.join(duplicates)}"
+            )
             raise ParseIsatabException(msg)
 
     def _make_breaks(self):
@@ -768,23 +758,23 @@ def _construct(self, rows):
                     if (
                         entry.unique_name in processes and entry != processes[entry.unique_name]
                     ):  # pragma: no cover
-                        tpl = (
+                        msg = (
                             "Found processes with same name but different "
-                            "annotation:\nprocess 1: {}\nprocess 2: {}"
+                            f"annotation:\nprocess 1: {entry}\n"
+                            f"process 2: {processes[entry.unique_name]}"
                         )
-                        msg = tpl.format(entry, processes[entry.unique_name])
                         raise ParseIsatabException(msg)
                     processes[entry.unique_name] = entry
                 else:
                     assert isinstance(entry, models.Material)
                     if (
                         entry.unique_name in materials and entry != materials[entry.unique_name]
                     ):  # pragma: no cover
-                        tpl = (
+                        msg = (
                             "Found materials with same name but different "
-                            "annotation:\nmaterial 1: {}\nmaterial 2: {}"
+                            f"annotation:\nmaterial 1: {entry}\n"
+                            f"material 2: {materials[entry.unique_name]}"
                         )
-                        msg = tpl.format(entry, materials[entry.unique_name])
                         raise ParseIsatabException(msg)
                     materials[entry.unique_name] = entry
                 # Collect arc