Fix UP031 errors - Part 6

Also:
- Update ruff to 0.8.2
- Add type annotations.
- Small refactorings.

lib/galaxy/datatypes/binary.py

@@ -1196,7 +1196,7 @@ def set_meta(
         # Create the bcf index
         dataset_symlink = os.path.join(
             os.path.dirname(index_file.get_file_name()),
-            "__dataset_%d_%s" % (dataset.id, os.path.basename(index_file.get_file_name())),
+            f"__dataset_{dataset.id}_{os.path.basename(index_file.get_file_name())}",
         )
         os.symlink(dataset.get_file_name(), dataset_symlink)
         try:
@@ -1677,15 +1677,15 @@ def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
             def _makelayerstrings(layer, count, names):
                 "Format the layers."
                 if layer in tmp.layers_names:
-                    return "\n[%s]: %d %s\n    %s" % (
+                    return "\n[{}]: {} {}\n    {}".format(
                         layer,
                         count,
                         "layer" if count == 1 else "layers",
                         ", ".join(sorted(names)),
                     )
                 return ""
 
-            peekstr = "[n_obs x n_vars]\n    %d x %d" % tuple(tmp.shape)
+            peekstr = "[n_obs x n_vars]\n    {} x {}".format(*tuple(tmp.shape))
             peekstr += _makelayerstrings("obs", tmp.obs_count, tmp.obs_layers)
             peekstr += _makelayerstrings("var", tmp.var_count, tmp.var_layers)
             peekstr += _makelayerstrings("obsm", tmp.obsm_count, tmp.obsm_layers)

lib/galaxy/datatypes/converters/bed_to_gff_converter.py

@@ -3,8 +3,6 @@
 
 import sys
 
-assert sys.version_info[:2] >= (2, 6)
-
 
 def __main__():
     input_name = sys.argv[1]
@@ -30,7 +28,7 @@ def __main__():
                         try:
                             feature = elems[3]
                         except Exception:
-                            feature = "feature%d" % (i + 1)
+                            feature = f"feature{i + 1}"
                     start = int(elems[1]) + 1
                     end = int(elems[2])
                     try:
@@ -44,17 +42,13 @@ def __main__():
                     try:
                         group = elems[3]
                     except Exception:
-                        group = "group%d" % (i + 1)
+                        group = f"group{i + 1}"
                     if complete_bed:
                         out.write(
-                            "%s\tbed2gff\t%s\t%d\t%d\t%s\t%s\t.\t%s %s;\n"
-                            % (chrom, feature, start, end, score, strand, feature, group)
+                            f"{chrom}\tbed2gff\t{feature}\t{start}\t{end}\t{score}\t{strand}\t.\t{feature} {group};\n"
                         )
                     else:
-                        out.write(
-                            "%s\tbed2gff\t%s\t%d\t%d\t%s\t%s\t.\t%s;\n"
-                            % (chrom, feature, start, end, score, strand, group)
-                        )
+                        out.write(f"{chrom}\tbed2gff\t{feature}\t{start}\t{end}\t{score}\t{strand}\t.\t{group};\n")
                     if complete_bed:
                         # We have all the info necessary to annotate exons for genes and mRNAs
                         block_count = int(elems[9])
@@ -64,8 +58,7 @@ def __main__():
                             exon_start = int(start) + int(block_starts[j])
                             exon_end = exon_start + int(block_sizes[j]) - 1
                             out.write(
-                                "%s\tbed2gff\texon\t%d\t%d\t%s\t%s\t.\texon %s;\n"
-                                % (chrom, exon_start, exon_end, score, strand, group)
+                                f"{chrom}\tbed2gff\texon\t{exon_start}\t{exon_end}\t{score}\t{strand}\t.\texon {group};\n"
                             )
                 except Exception:
                     skipped_lines += 1
@@ -75,12 +68,9 @@ def __main__():
                 skipped_lines += 1
                 if not first_skipped_line:
                     first_skipped_line = i + 1
-    info_msg = "%i lines converted to GFF version 2.  " % (i + 1 - skipped_lines)
+    info_msg = f"{i + 1 - skipped_lines} lines converted to GFF version 2.  "
     if skipped_lines > 0:
-        info_msg += "Skipped %d blank/comment/invalid lines starting with line #%d." % (
-            skipped_lines,
-            first_skipped_line,
-        )
+        info_msg += f"Skipped {skipped_lines} blank/comment/invalid lines starting with line #{first_skipped_line}."
     print(info_msg)
 
 

lib/galaxy/datatypes/converters/fasta_to_len.py

@@ -6,8 +6,6 @@
 """
 import sys
 
-assert sys.version_info[:2] >= (2, 4)
-
 
 def compute_fasta_length(fasta_file, out_file, keep_first_char, keep_first_word=False):
     infile = fasta_file
@@ -34,7 +32,7 @@ def compute_fasta_length(fasta_file, out_file, keep_first_char, keep_first_word=
                     if first_entry is False:
                         if keep_first_word:
                             fasta_title = fasta_title.split()[0]
-                        out.write("%s\t%d\n" % (fasta_title[1:keep_first_char], seq_len))
+                        out.write(f"{fasta_title[1:keep_first_char]}\t{seq_len}\n")
                     else:
                         first_entry = False
                     fasta_title = line
@@ -45,7 +43,7 @@ def compute_fasta_length(fasta_file, out_file, keep_first_char, keep_first_word=
         # last fasta-entry
         if keep_first_word:
             fasta_title = fasta_title.split()[0]
-        out.write("%s\t%d\n" % (fasta_title[1:keep_first_char], seq_len))
+        out.write(f"{fasta_title[1:keep_first_char]}\t{seq_len}\n")
 
 
 if __name__ == "__main__":

lib/galaxy/datatypes/converters/fastqsolexa_to_fasta_converter.py

@@ -15,12 +15,6 @@
 """
 import sys
 
-assert sys.version_info[:2] >= (2, 4)
-
-
-def stop_err(msg):
-    sys.exit(f"{msg}")
-
 
 def __main__():
     infile_name = sys.argv[1]
@@ -39,7 +33,7 @@ def __main__():
                 if not seq_title_startswith:
                     seq_title_startswith = line_startswith
                 if seq_title_startswith != line_startswith:
-                    stop_err("Invalid fastqsolexa format at line %d: %s." % (i + 1, line))
+                    sys.exit(f"Invalid fastqsolexa format at line {i + 1}: {line}.")
                 outfile.write(f">{line[1:]}\n")
             elif fastq_block_lines == 2:
                 # line 2 is nucleotides

lib/galaxy/datatypes/converters/fastqsolexa_to_qual_converter.py

@@ -15,12 +15,6 @@
 """
 import sys
 
-assert sys.version_info[:2] >= (2, 4)
-
-
-def stop_err(msg):
-    sys.exit(f"{msg}")
-
 
 def __main__():
     infile_name = sys.argv[1]
@@ -42,7 +36,7 @@ def __main__():
                 if not seq_title_startswith:
                     seq_title_startswith = line_startswith
                 if line_startswith != seq_title_startswith:
-                    stop_err("Invalid fastqsolexa format at line %d: %s." % (i + 1, line))
+                    sys.exit(f"Invalid fastqsolexa format at line {i + 1}: {line}.")
                 read_title = line[1:]
             elif fastq_block_lines == 2:
                 # second line is nucleotides
@@ -52,12 +46,11 @@ def __main__():
                 if not qual_title_startswith:
                     qual_title_startswith = line_startswith
                 if line_startswith != qual_title_startswith:
-                    stop_err("Invalid fastqsolexa format at line %d: %s." % (i + 1, line))
+                    sys.exit(f"Invalid fastqsolexa format at line {i + 1}: {line}.")
                 quality_title = line[1:]
                 if quality_title and read_title != quality_title:
-                    stop_err(
-                        'Invalid fastqsolexa format at line %d: sequence title "%s" differes from score title "%s".'
-                        % (i + 1, read_title, quality_title)
+                    sys.exit(
+                        f'Invalid fastqsolexa format at line {i + 1}: sequence title "{read_title}" differes from score title "{quality_title}".'
                     )
                 if not quality_title:
                     outfile_score.write(f">{read_title}\n")
@@ -87,9 +80,8 @@ def __main__():
                     elif quality_score_length == read_length:
                         quality_score_startswith = default_coding_value
                     else:
-                        stop_err(
-                            "Invalid fastqsolexa format at line %d: the number of quality scores ( %d ) is not the same as bases ( %d )."
-                            % (i + 1, quality_score_length, read_length)
+                        sys.exit(
+                            f"Invalid fastqsolexa format at line {i + 1}: the number of quality scores ( {quality_score_length} ) is not the same as bases ( {read_length} )."
                         )
                     for char in line:
                         score = ord(char) - quality_score_startswith  # 64

lib/galaxy/datatypes/converters/gff_to_bed_converter.py

@@ -2,8 +2,6 @@
 
 import sys
 
-assert sys.version_info[:2] >= (2, 6)
-
 
 def __main__():
     input_name = sys.argv[1]
@@ -35,12 +33,9 @@ def __main__():
                 skipped_lines += 1
                 if not first_skipped_line:
                     first_skipped_line = i + 1
-    info_msg = "%i lines converted to BED.  " % (i + 1 - skipped_lines)
+    info_msg = f"{i + 1 - skipped_lines} lines converted to BED.  "
     if skipped_lines > 0:
-        info_msg += "Skipped %d blank/comment/invalid lines starting with line #%d." % (
-            skipped_lines,
-            first_skipped_line,
-        )
+        info_msg += f"Skipped {skipped_lines} blank/comment/invalid lines starting with line #{first_skipped_line}."
     print(info_msg)
 
 

lib/galaxy/datatypes/converters/interval_to_bed_converter.py

@@ -5,32 +5,26 @@
 
 import bx.intervals.io
 
-assert sys.version_info[:2] >= (2, 6)
-
-
-def stop_err(msg):
-    sys.exit(msg)
-
 
 def __main__():
     output_name = sys.argv[1]
     input_name = sys.argv[2]
     try:
         chromCol = int(sys.argv[3]) - 1
     except Exception:
-        stop_err(
+        sys.exit(
             f"'{str(sys.argv[3])}' is an invalid chrom column, correct the column settings before attempting to convert the data format."
         )
     try:
         startCol = int(sys.argv[4]) - 1
     except Exception:
-        stop_err(
+        sys.exit(
             f"'{str(sys.argv[4])}' is an invalid start column, correct the column settings before attempting to convert the data format."
         )
     try:
         endCol = int(sys.argv[5]) - 1
     except Exception:
-        stop_err(
+        sys.exit(
             f"'{str(sys.argv[5])}' is an invalid end column, correct the column settings before attempting to convert the data format."
         )
     try:
@@ -63,16 +57,16 @@ def __main__():
                 else:
                     raise IndexError
             except Exception:
-                name = "region_%i" % count
+                name = f"region_{count}"
             try:
-                out.write("%s\t%i\t%i\t%s\t%i\t%s\n" % (region.chrom, region.start, region.end, name, 0, region.strand))
+                out.write(f"{region.chrom}\t{region.start}\t{region.end}\t{name}\t0\t{region.strand}\n")
             except Exception:
                 skipped_lines += 1
                 if not first_skipped_line:
                     first_skipped_line = count + 1
-    print("%i regions converted to BED." % (count + 1 - skipped_lines))
+    print(f"{count + 1 - skipped_lines} regions converted to BED.")
     if skipped_lines > 0:
-        print("Skipped %d blank or invalid lines starting with line # %d." % (skipped_lines, first_skipped_line))
+        print(f"Skipped {skipped_lines} blank or invalid lines starting with line # {first_skipped_line}.")
 
 
 if __name__ == "__main__":

lib/galaxy/datatypes/converters/interval_to_bedstrict_converter.py

@@ -5,16 +5,10 @@
 
 import bx.intervals.io
 
-assert sys.version_info[:2] >= (2, 6)
 
-
-def stop_err(msg):
-    sys.exit(msg)
-
-
-def force_bed_field_count(fields, region_count, force_num_columns):
+def force_bed_field_count(fields, region_count: int, force_num_columns: int):
     if force_num_columns >= 4 and len(fields) < 4:
-        fields.append("region_%i" % (region_count))
+        fields.append(f"region_{region_count}")
     if force_num_columns >= 5 and len(fields) < 5:
         fields.append("0")
     if force_num_columns >= 6 and len(fields) < 6:
@@ -40,19 +34,19 @@ def __main__():
     try:
         chromCol = int(sys.argv[3]) - 1
     except Exception:
-        stop_err(
+        sys.exit(
             f"'{str(sys.argv[3])}' is an invalid chrom column, correct the column settings before attempting to convert the data format."
         )
     try:
         startCol = int(sys.argv[4]) - 1
     except Exception:
-        stop_err(
+        sys.exit(
             f"'{str(sys.argv[4])}' is an invalid start column, correct the column settings before attempting to convert the data format."
         )
     try:
         endCol = int(sys.argv[5]) - 1
     except Exception:
-        stop_err(
+        sys.exit(
             f"'{str(sys.argv[5])}' is an invalid end column, correct the column settings before attempting to convert the data format."
         )
     try:
@@ -176,7 +170,7 @@ def __main__():
                     else:
                         raise IndexError
                 except Exception:
-                    name = "region_%i" % count
+                    name = f"region_{count}"
                 try:
                     fields = [str(item) for item in (region.chrom, region.start, region.end, name, 0, region.strand)]
                     if force_num_columns is not None and len(fields) != force_num_columns:
@@ -186,9 +180,9 @@ def __main__():
                     skipped_lines += 1
                     if first_skipped_line is None:
                         first_skipped_line = count + 1
-    print("%i regions converted to BED." % (count + 1 - skipped_lines))
+    print(f"{count + 1 - skipped_lines} regions converted to BED.")
     if skipped_lines > 0:
-        print("Skipped %d blank or invalid lines starting with line # %d." % (skipped_lines, first_skipped_line))
+        print(f"Skipped {skipped_lines} blank or invalid lines starting with line # {first_skipped_line}.")
 
 
 if __name__ == "__main__":

lib/galaxy/datatypes/converters/interval_to_fli.py

@@ -90,7 +90,7 @@ def main():
     entries = []
     for name in sorted(name_loc_dict.keys()):
         loc = name_loc_dict[name]
-        entry = "{}\t{}\t{}".format(name.lower(), name, "%s:%i-%i" % (loc["contig"], loc["start"], loc["end"]))
+        entry = "{}\t{}\t{}:{}-{}".format(name.lower(), name, loc["contig"], loc["start"], loc["end"])
         if len(entry) > max_len:
             max_len = len(entry)
         entries.append(entry)

lib/galaxy/datatypes/converters/lped_to_fped_converter.py

@@ -81,7 +81,7 @@ def main():
     """
     nparm = 3
     if len(sys.argv) < nparm:
-        sys.exit("## %s called with %s - needs %d parameters \n" % (prog, sys.argv, nparm))
+        sys.exit(f"## {prog} called with {sys.argv} - needs {nparm} parameters \n")
     inpedfilepath = sys.argv[1]
     outhtmlname = sys.argv[2]
     outfilepath = sys.argv[3]

lib/galaxy/datatypes/converters/lped_to_pbed_converter.py

@@ -85,7 +85,7 @@ def main():
     """
     nparm = 4
     if len(sys.argv) < nparm:
-        sys.exit("## %s called with %s - needs %d parameters \n" % (prog, sys.argv, nparm))
+        sys.exit(f"## {prog} called with {sys.argv} - needs {nparm} parameters \n")
     inpedfilepath = sys.argv[1]
     outhtmlname = sys.argv[2]
     outfilepath = sys.argv[3]

lib/galaxy/datatypes/converters/maf_to_fasta_converter.py

@@ -7,8 +7,6 @@
 
 from galaxy.datatypes.util import maf_utilities
 
-assert sys.version_info[:2] >= (2, 6)
-
 
 def __main__():
     output_name = sys.argv.pop(1)
@@ -28,13 +26,13 @@ def __main__():
                         maf_utilities.get_fasta_header(
                             c,
                             {"block_index": count, "species": spec, "sequence_index": spec_counts[spec]},
-                            suffix="%s_%i_%i" % (spec, count, spec_counts[spec]),
+                            suffix=f"{spec}_{count}_{spec_counts[spec]}",
                         )
                     )
                 )
                 out.write(f"{c.text}\n")
             out.write("\n")
-    print("%i MAF blocks converted to FASTA." % (count))
+    print(f"{count} MAF blocks converted to FASTA.")
 
 
 if __name__ == "__main__":