Merge pull request #65 from moshi4/develop

Bump to v1.4.1

src/pygenomeviz/__init__.py

@@ -2,7 +2,7 @@
 
 from pygenomeviz.genomeviz import GenomeViz
 
-__version__ = "1.4.0"
+__version__ = "1.4.1"
 
 __all__ = [
     "GenomeViz",

src/pygenomeviz/align/coord.py

@@ -233,7 +233,7 @@ def parse_pmauve_file(
         align_coords : list[AlignCoord]
             Align coord list
         """
-        with open(bbone_file) as f:
+        with open(bbone_file, encoding="utf-8") as f:
             reader = csv.reader(f, delimiter="\t")
             header_row = next(reader)
             genome_num = int(len(header_row) / 2)
@@ -316,7 +316,7 @@ def write(
         elif isinstance(outfile, io.BytesIO):
             outfile.write(bytes(contents, encoding="utf-8"))
         else:
-            with open(outfile, "w") as f:
+            with open(outfile, "w", encoding="utf-8") as f:
                 f.write(contents)
 
     @staticmethod
@@ -334,7 +334,7 @@ def read(align_coords_file: str | Path) -> list[AlignCoord]:
             Alignment coords
         """
         align_coords = []
-        with open(align_coords_file) as f:
+        with open(align_coords_file, encoding="utf-8") as f:
             reader = csv.reader(f, delimiter="\t")
             next(reader)
             for row in reader:

src/pygenomeviz/align/tool/base.py

@@ -111,7 +111,7 @@ def run_cmd(
             # Write stdout result if stdout_file is set
             if stdout_file:
                 logger.info(f"> Save cmd stdout results to '{stdout_file}'")
-                with open(stdout_file, "w") as f:
+                with open(stdout_file, "w", encoding="utf-8") as f:
                     f.write(cmd_res.stdout)
         else:
             logger.error("Failed to run command below!!")
@@ -183,7 +183,7 @@ def _parse_input_gbk_and_fasta_seqs(
             if isinstance(seq, Path):
                 suffix = seq.suffix
                 if suffix == ".gz" and len(seq.suffixes) >= 2:
-                    suffix = seq.suffixes[-2].join("")
+                    suffix = "".join(seq.suffixes[-2])
                 if suffix in gbk_suffixes:
                     parse_seqs.append(Genbank(seq))
                 elif suffix in fasta_suffixes:

src/pygenomeviz/align/tool/mmseqs.py

@@ -129,7 +129,7 @@ def _parse_coords_file(
         """
         align_coords = []
         dup_check_list = []
-        with open(rbh_result_file) as f:
+        with open(rbh_result_file, encoding="utf-8") as f:
             reader = csv.reader(f, delimiter="\t")
             for row in reader:
                 # Query [e.g. `GENE000001_NC_XXXXXX.X|name|8205_8559_1|`]

src/pygenomeviz/genomeviz.py

@@ -632,7 +632,7 @@ def savefig_html(
         elif isinstance(html_outfile, io.BytesIO):
             html_outfile.write(bytes(viewer_html, encoding="utf-8"))
         else:
-            with open(html_outfile, "w") as f:
+            with open(html_outfile, "w", encoding="utf-8") as f:
                 f.write(viewer_html)
 
     ############################################################

src/pygenomeviz/parser/fasta.py

@@ -120,7 +120,7 @@ def write_genome_fasta(self, outfile: str | Path) -> None:
         outfile : str | Path
             Output genome fasta file
         """
-        with open(outfile, "w") as f:
+        with open(outfile, "w", encoding="utf-8") as f:
             for seqid, seq in self.get_seqid2seq().items():
                 f.write(f">{seqid}\n{seq}\n")
 
@@ -142,14 +142,16 @@ def _parse_fasta_file(self, fasta_file: str | Path) -> list[SeqRecord]:
             SeqRecord list
         """
         if Path(fasta_file).suffix == ".gz":
-            with gzip.open(fasta_file, mode="rt") as f:
+            with gzip.open(fasta_file, mode="rt", encoding="utf-8") as f:
                 return list(SeqIO.parse(f, "fasta"))
         elif Path(fasta_file).suffix == ".bz2":
-            with bz2.open(fasta_file, mode="rt") as f:
+            with bz2.open(fasta_file, mode="rt", encoding="utf-8") as f:
                 return list(SeqIO.parse(f, "fasta"))
         elif Path(fasta_file).suffix == ".zip":
             with zipfile.ZipFile(fasta_file) as zip:
                 with zip.open(zip.namelist()[0]) as f:
-                    return list(SeqIO.parse(TextIOWrapper(f), "fasta"))
+                    io = TextIOWrapper(f, encoding="utf-8")
+                    return list(SeqIO.parse(io, "fasta"))
         else:
-            return list(SeqIO.parse(fasta_file, "fasta"))
+            with open(fasta_file, encoding="utf-8") as f:
+                return list(SeqIO.parse(f, "fasta"))

src/pygenomeviz/parser/genbank.py

@@ -368,7 +368,7 @@ def write_genome_fasta(self, outfile: str | Path) -> None:
         outfile : str | Path
             Output genome fasta file
         """
-        with open(outfile, "w") as f:
+        with open(outfile, "w", encoding="utf-8") as f:
             for seqid, seq in self.get_seqid2seq().items():
                 f.write(f">{seqid}\n{seq}\n")
 
@@ -391,19 +391,23 @@ def _parse_gbk_source(
         list[SeqRecord]
             Genbank SeqRecords
         """
-        # Parse compressed file
+        # Parse file
         if isinstance(gbk_source, (str, Path)):
             if Path(gbk_source).suffix == ".gz":
-                with gzip.open(gbk_source, mode="rt") as f:
+                with gzip.open(gbk_source, mode="rt", encoding="utf-8") as f:
                     return list(SeqIO.parse(f, "genbank"))
             elif Path(gbk_source).suffix == ".bz2":
-                with bz2.open(gbk_source, mode="rt") as f:
+                with bz2.open(gbk_source, mode="rt", encoding="utf-8") as f:
                     return list(SeqIO.parse(f, "genbank"))
             elif Path(gbk_source).suffix == ".zip":
                 with zipfile.ZipFile(gbk_source) as zip:
                     with zip.open(zip.namelist()[0]) as f:
-                        return list(SeqIO.parse(TextIOWrapper(f), "genbank"))
-        # Parse no compressed file or TextIOWrapper
+                        io = TextIOWrapper(f, encoding="utf-8")
+                        return list(SeqIO.parse(io, "genbank"))
+            else:
+                with open(gbk_source, encoding="utf-8") as f:
+                    return list(SeqIO.parse(f, "genbank"))
+        # Parse TextIOWrapper
         return list(SeqIO.parse(gbk_source, "genbank"))
 
     def _is_straddle_feature(self, feature: SeqFeature) -> bool:

src/pygenomeviz/parser/gff.py

@@ -287,18 +287,18 @@ def _parse_gff(
         """
         gff_file = Path(gff_file)
         if gff_file.suffix == ".gz":
-            with gzip.open(gff_file, mode="rt") as f:
+            with gzip.open(gff_file, mode="rt", encoding="utf-8") as f:
                 gff_records, start, end = self._parse_gff_textio(f, target_seqid)
         elif gff_file.suffix == ".bz2":
-            with bz2.open(gff_file, mode="rt") as f:
+            with bz2.open(gff_file, mode="rt", encoding="utf-8") as f:
                 gff_records, start, end = self._parse_gff_textio(f, target_seqid)
         elif gff_file.suffix == ".zip":
             with zipfile.ZipFile(gff_file) as zip:
                 with zip.open(zip.namelist()[0]) as f:
-                    io = TextIOWrapper(f)
+                    io = TextIOWrapper(f, encoding="utf-8")
                     gff_records, start, end = self._parse_gff_textio(io, target_seqid)
         else:
-            with open(gff_file) as f:
+            with open(gff_file, encoding="utf-8") as f:
                 gff_records, start, end = self._parse_gff_textio(f, target_seqid)
 
         return gff_records, start, end

src/pygenomeviz/utils/download.py

@@ -287,7 +287,7 @@ def fetch_genbank_by_accid(
     )
     if gbk_outfile is not None:
         gbk_text = gbk_fetch_data.read()
-        with open(gbk_outfile, "w") as f:
+        with open(gbk_outfile, "w", encoding="utf-8") as f:
             f.write(gbk_text)
         gbk_fetch_data = StringIO(gbk_text)
 

src/pygenomeviz/viewer/__init__.py

@@ -14,7 +14,7 @@ def _concat_target_files_contents(files: list[Path], target_ext: str) -> str:
     contents = "\n"
     target_files = [file for file in files if file.suffix == target_ext]
     for target_file in target_files:
-        with open(target_file) as f:
+        with open(target_file, encoding="utf-8") as f:
             contents += f.read() + "\n"
     return contents
 
@@ -70,7 +70,7 @@ def setup_viewer_html(
             err_msg = "Failed to save HTML viewer. Check if target figure is generated by 'gv.plotfig(fast_render=False)' method call."  # noqa: E501
             raise ValueError(err_msg)
     # Read template html file
-    with open(TEMPLATE_HTML_FILE) as f:
+    with open(TEMPLATE_HTML_FILE, encoding="utf-8") as f:
         viewer_html = f.read()
     # Replace template strings
     return (

tests/parser/test_fasta.py

@@ -24,7 +24,7 @@
 def test_fasta_property(tmp_path: Path):
     """Test Fasta instance properties"""
     fasta_file = tmp_path / "test.fa"
-    with open(fasta_file, "w") as f:
+    with open(fasta_file, "w", encoding="utf-8") as f:
         f.write(fasta_txt)
     fasta = Fasta(fasta_file)
 

tests/parser/test_genbank.py

@@ -82,7 +82,7 @@ def test_genbank_write_genome_fasta(multi_record_gbk_file: Path, tmp_path: Path)
     assert outfile.exists()
 
     # Check number of genome fasta
-    with open(outfile) as f:
+    with open(outfile, encoding="utf-8") as f:
         lines = f.read().splitlines()
     fasta_count = len([line for line in lines if line.startswith(">")])
     assert fasta_count == 8