seqstatx 0.1.0__tar.gz

seqstatx-0.1.0/PKG-INFO

@@ -0,0 +1,90 @@
+Metadata-Version: 2.4
+Name: seqstatx
+Version: 0.1.0
+Summary: Fast sequence statistics for FASTA/FASTQ files — N50, GC%, length distributions and more
+Author-email: Wendy Bui <wendybuinta@gmail.com>
+License: MIT
+Keywords: bioinformatics,genomics,fasta,fastq,sequence,qc
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+
+# seqstats
+
+[![CI](https://github.com/perhapsstrawberries/seqstats/actions/workflows/ci.yml/badge.svg)](https://github.com/perhapsstrawberries/seqstats/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/seqstatx)](https://pypi.org/project/seqstatx/)
+![Python](https://img.shields.io/badge/python-3.10%2B-blue)
+![License](https://img.shields.io/badge/license-MIT-green)
+
+Fast sequence statistics for FASTA and FASTQ files — works on plain or gzipped inputs, no dependencies.
+
+```
+file                            seqs      total_bp      gc%      mean_len    min_len   max_len   N50         N90
+-----------------------------------------------------------------------------------------------------------------
+GRCh38.primary_assembly.fa      194       3,088,286,401  40.93   15,918,992  970       248,956,422  153,373,213  40,103,529
+SRR10045678_1.fastq.gz          10000000  1,510,000,000  50.21   151.0       151       151          151          151
+```
+
+## Install
+
+```bash
+pip install seqstatx
+```
+
+Or for development:
+
+```bash
+git clone https://github.com/perhapsstrawberries/seqstats.git
+cd seqstats
+pip install -e .
+```
+
+## Usage
+
+```bash
+# single file
+seqstatx genome.fa
+
+# multiple files, gzipped FASTQ
+seqstatx sample1.fastq.gz sample2.fastq.gz
+
+# TSV output for downstream parsing
+seqstatx --tsv *.fa > stats.tsv
+
+# pipe to column for alignment
+seqstatx --tsv *.fastq.gz | column -t
+```
+
+## Metrics
+
+| Column | Description |
+|--------|-------------|
+| `seqs` | Number of sequences / reads |
+| `total_bp` | Total base pairs |
+| `gc%` | GC content (%) |
+| `mean_len` | Mean sequence length |
+| `min_len` / `max_len` | Shortest / longest sequence |
+| `N50` | 50% of total assembly is in sequences ≥ this length |
+| `N90` | 90% of total assembly is in sequences ≥ this length |
+
+## Supported formats
+
+| Extension | Format |
+|-----------|--------|
+| `.fa` `.fna` `.fasta` | FASTA |
+| `.fq` `.fastq` | FASTQ |
+| `.fa.gz` `.fastq.gz` etc. | gzipped variants |
+
+## Why
+
+Existing tools (seqkit, seqtk) are great but require installation of compiled binaries.  
+`seqstats` is pure Python 3.10+, zero dependencies, pip-installable from any HPC or Conda environment.
+
+## License
+
+MIT

seqstatx-0.1.0/README.md

@@ -0,0 +1,74 @@
+# seqstats
+
+[![CI](https://github.com/perhapsstrawberries/seqstats/actions/workflows/ci.yml/badge.svg)](https://github.com/perhapsstrawberries/seqstats/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/seqstatx)](https://pypi.org/project/seqstatx/)
+![Python](https://img.shields.io/badge/python-3.10%2B-blue)
+![License](https://img.shields.io/badge/license-MIT-green)
+
+Fast sequence statistics for FASTA and FASTQ files — works on plain or gzipped inputs, no dependencies.
+
+```
+file                            seqs      total_bp      gc%      mean_len    min_len   max_len   N50         N90
+-----------------------------------------------------------------------------------------------------------------
+GRCh38.primary_assembly.fa      194       3,088,286,401  40.93   15,918,992  970       248,956,422  153,373,213  40,103,529
+SRR10045678_1.fastq.gz          10000000  1,510,000,000  50.21   151.0       151       151          151          151
+```
+
+## Install
+
+```bash
+pip install seqstatx
+```
+
+Or for development:
+
+```bash
+git clone https://github.com/perhapsstrawberries/seqstats.git
+cd seqstats
+pip install -e .
+```
+
+## Usage
+
+```bash
+# single file
+seqstatx genome.fa
+
+# multiple files, gzipped FASTQ
+seqstatx sample1.fastq.gz sample2.fastq.gz
+
+# TSV output for downstream parsing
+seqstatx --tsv *.fa > stats.tsv
+
+# pipe to column for alignment
+seqstatx --tsv *.fastq.gz | column -t
+```
+
+## Metrics
+
+| Column | Description |
+|--------|-------------|
+| `seqs` | Number of sequences / reads |
+| `total_bp` | Total base pairs |
+| `gc%` | GC content (%) |
+| `mean_len` | Mean sequence length |
+| `min_len` / `max_len` | Shortest / longest sequence |
+| `N50` | 50% of total assembly is in sequences ≥ this length |
+| `N90` | 90% of total assembly is in sequences ≥ this length |
+
+## Supported formats
+
+| Extension | Format |
+|-----------|--------|
+| `.fa` `.fna` `.fasta` | FASTA |
+| `.fq` `.fastq` | FASTQ |
+| `.fa.gz` `.fastq.gz` etc. | gzipped variants |
+
+## Why
+
+Existing tools (seqkit, seqtk) are great but require installation of compiled binaries.  
+`seqstats` is pure Python 3.10+, zero dependencies, pip-installable from any HPC or Conda environment.
+
+## License
+
+MIT

seqstatx-0.1.0/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "seqstatx"
+version = "0.1.0"
+description = "Fast sequence statistics for FASTA/FASTQ files — N50, GC%, length distributions and more"
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.10"
+authors = [{ name = "Wendy Bui", email = "wendybuinta@gmail.com" }]
+keywords = ["bioinformatics", "genomics", "fasta", "fastq", "sequence", "qc"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+]
+dependencies = []
+
+[project.scripts]
+seqstatx = "seqstats.cli:main"
+
+[project.optional-dependencies]
+dev = ["pytest", "pytest-cov"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q"

seqstatx-0.1.0/seqstats/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

seqstatx-0.1.0/seqstats/cli.py

@@ -0,0 +1,84 @@
+"""Command-line interface for seqstats."""
+
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+
+from seqstats.core import SeqStats, parse_file
+from seqstats import __version__
+
+_COLS = ["file", "seqs", "total_bp", "gc%", "mean_len", "min_len", "max_len", "N50", "N90"]
+_COL_W = [30, 8, 12, 7, 10, 8, 8, 10, 10]
+
+
+def _fmt(stats: SeqStats) -> list[str]:
+    return [
+        stats.name[:29],
+        str(stats.n_seqs),
+        str(stats.total_bases),
+        f"{stats.gc_pct:.2f}",
+        f"{stats.mean_len:.1f}",
+        str(stats.min_len),
+        str(stats.max_len),
+        str(stats.n50),
+        str(stats.n90),
+    ]
+
+
+def _header() -> str:
+    return "  ".join(c.ljust(w) for c, w in zip(_COLS, _COL_W))
+
+
+def _row(stats: SeqStats) -> str:
+    return "  ".join(v.ljust(w) for v, w in zip(_fmt(stats), _COL_W))
+
+
+def _tsv_header() -> str:
+    return "\t".join(_COLS)
+
+
+def _tsv_row(stats: SeqStats) -> str:
+    return "\t".join(_fmt(stats))
+
+
+def main(argv: list[str] | None = None) -> None:
+    parser = argparse.ArgumentParser(
+        prog="seqstatx",
+        description="Compute sequence statistics for FASTA/FASTQ files.",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""examples:
+  seqstatx genome.fa
+  seqstatx *.fastq.gz
+  seqstatx --tsv reads.fq.gz > stats.tsv
+  seqstatx --tsv sample1.fa sample2.fa | column -t""",
+    )
+    parser.add_argument("files", nargs="+", type=Path, metavar="FILE")
+    parser.add_argument("--tsv", action="store_true", help="output tab-separated values")
+    parser.add_argument("--version", action="version", version=f"seqstatx {__version__}")
+
+    args = parser.parse_args(argv)
+
+    missing = [f for f in args.files if not f.exists()]
+    if missing:
+        for f in missing:
+            print(f"[seqstats] file not found: {f}", file=sys.stderr)
+        sys.exit(1)
+
+    if args.tsv:
+        print(_tsv_header())
+    else:
+        print(_header())
+        print("-" * sum(_COL_W) + "-" * (2 * (len(_COL_W) - 1)))
+
+    for path in args.files:
+        stats = parse_file(path)
+        if args.tsv:
+            print(_tsv_row(stats))
+        else:
+            print(_row(stats))
+
+
+if __name__ == "__main__":
+    main()

seqstatx-0.1.0/seqstats/core.py

@@ -0,0 +1,125 @@
+"""Core sequence statistics logic."""
+
+from __future__ import annotations
+
+import gzip
+import sys
+from dataclasses import dataclass, field
+from pathlib import Path
+
+
+@dataclass
+class SeqStats:
+    name: str
+    n_seqs: int = 0
+    total_bases: int = 0
+    gc_count: int = 0
+    _lengths: list[int] = field(default_factory=list, repr=False)
+
+    def add(self, seq: str) -> None:
+        n = len(seq)
+        self.n_seqs += 1
+        self.total_bases += n
+        self.gc_count += seq.count("G") + seq.count("C") + seq.count("g") + seq.count("c")
+        self._lengths.append(n)
+
+    @property
+    def gc_pct(self) -> float:
+        return 100.0 * self.gc_count / self.total_bases if self.total_bases else 0.0
+
+    @property
+    def mean_len(self) -> float:
+        return self.total_bases / self.n_seqs if self.n_seqs else 0.0
+
+    @property
+    def min_len(self) -> int:
+        return min(self._lengths) if self._lengths else 0
+
+    @property
+    def max_len(self) -> int:
+        return max(self._lengths) if self._lengths else 0
+
+    @property
+    def n50(self) -> int:
+        if not self._lengths:
+            return 0
+        sorted_lens = sorted(self._lengths, reverse=True)
+        threshold = self.total_bases / 2
+        cumsum = 0
+        for length in sorted_lens:
+            cumsum += length
+            if cumsum >= threshold:
+                return length
+        return 0
+
+    @property
+    def n90(self) -> int:
+        if not self._lengths:
+            return 0
+        sorted_lens = sorted(self._lengths, reverse=True)
+        threshold = self.total_bases * 0.9
+        cumsum = 0
+        for length in sorted_lens:
+            cumsum += length
+            if cumsum >= threshold:
+                return length
+        return 0
+
+
+def _open(path: Path):
+    """Open plain or gzipped file."""
+    if path.suffix in (".gz", ".gzip"):
+        return gzip.open(path, "rt")
+    return open(path, "r")
+
+
+def parse_fasta(path: Path) -> SeqStats:
+    stats = SeqStats(name=path.name)
+    current: list[str] = []
+
+    def flush():
+        if current:
+            stats.add("".join(current))
+            current.clear()
+
+    with _open(path) as fh:
+        for line in fh:
+            line = line.rstrip()
+            if not line:
+                continue
+            if line.startswith(">"):
+                flush()
+            else:
+                current.append(line)
+    flush()
+    return stats
+
+
+def parse_fastq(path: Path) -> SeqStats:
+    stats = SeqStats(name=path.name)
+    with _open(path) as fh:
+        while True:
+            header = fh.readline()
+            if not header:
+                break
+            seq = fh.readline().rstrip()
+            fh.readline()  # +
+            fh.readline()  # quality
+            if seq:
+                stats.add(seq)
+    return stats
+
+
+def parse_file(path: Path) -> SeqStats:
+    """Detect format by extension and parse."""
+    name = path.name.lower()
+    if any(name.endswith(ext) for ext in (".fa", ".fna", ".fasta", ".fa.gz", ".fna.gz", ".fasta.gz")):
+        return parse_fasta(path)
+    if any(name.endswith(ext) for ext in (".fq", ".fastq", ".fq.gz", ".fastq.gz")):
+        return parse_fastq(path)
+    # fallback: try FASTA
+    try:
+        return parse_fasta(path)
+    except Exception:
+        print(f"[seqstats] could not detect format for {path.name}", file=sys.stderr)
+        sys.exit(1)

seqstatx-0.1.0/seqstatx.egg-info/PKG-INFO

@@ -0,0 +1,90 @@
+Metadata-Version: 2.4
+Name: seqstatx
+Version: 0.1.0
+Summary: Fast sequence statistics for FASTA/FASTQ files — N50, GC%, length distributions and more
+Author-email: Wendy Bui <wendybuinta@gmail.com>
+License: MIT
+Keywords: bioinformatics,genomics,fasta,fastq,sequence,qc
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+
+# seqstats
+
+[![CI](https://github.com/perhapsstrawberries/seqstats/actions/workflows/ci.yml/badge.svg)](https://github.com/perhapsstrawberries/seqstats/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/seqstatx)](https://pypi.org/project/seqstatx/)
+![Python](https://img.shields.io/badge/python-3.10%2B-blue)
+![License](https://img.shields.io/badge/license-MIT-green)
+
+Fast sequence statistics for FASTA and FASTQ files — works on plain or gzipped inputs, no dependencies.
+
+```
+file                            seqs      total_bp      gc%      mean_len    min_len   max_len   N50         N90
+-----------------------------------------------------------------------------------------------------------------
+GRCh38.primary_assembly.fa      194       3,088,286,401  40.93   15,918,992  970       248,956,422  153,373,213  40,103,529
+SRR10045678_1.fastq.gz          10000000  1,510,000,000  50.21   151.0       151       151          151          151
+```
+
+## Install
+
+```bash
+pip install seqstatx
+```
+
+Or for development:
+
+```bash
+git clone https://github.com/perhapsstrawberries/seqstats.git
+cd seqstats
+pip install -e .
+```
+
+## Usage
+
+```bash
+# single file
+seqstatx genome.fa
+
+# multiple files, gzipped FASTQ
+seqstatx sample1.fastq.gz sample2.fastq.gz
+
+# TSV output for downstream parsing
+seqstatx --tsv *.fa > stats.tsv
+
+# pipe to column for alignment
+seqstatx --tsv *.fastq.gz | column -t
+```
+
+## Metrics
+
+| Column | Description |
+|--------|-------------|
+| `seqs` | Number of sequences / reads |
+| `total_bp` | Total base pairs |
+| `gc%` | GC content (%) |
+| `mean_len` | Mean sequence length |
+| `min_len` / `max_len` | Shortest / longest sequence |
+| `N50` | 50% of total assembly is in sequences ≥ this length |
+| `N90` | 90% of total assembly is in sequences ≥ this length |
+
+## Supported formats
+
+| Extension | Format |
+|-----------|--------|
+| `.fa` `.fna` `.fasta` | FASTA |
+| `.fq` `.fastq` | FASTQ |
+| `.fa.gz` `.fastq.gz` etc. | gzipped variants |
+
+## Why
+
+Existing tools (seqkit, seqtk) are great but require installation of compiled binaries.  
+`seqstats` is pure Python 3.10+, zero dependencies, pip-installable from any HPC or Conda environment.
+
+## License
+
+MIT

seqstatx-0.1.0/seqstatx.egg-info/SOURCES.txt

@@ -0,0 +1,13 @@
+README.md
+pyproject.toml
+seqstats/__init__.py
+seqstats/cli.py
+seqstats/core.py
+seqstatx.egg-info/PKG-INFO
+seqstatx.egg-info/SOURCES.txt
+seqstatx.egg-info/dependency_links.txt
+seqstatx.egg-info/entry_points.txt
+seqstatx.egg-info/requires.txt
+seqstatx.egg-info/top_level.txt
+tests/test_cli.py
+tests/test_core.py

seqstatx-0.1.0/seqstatx.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

seqstatx-0.1.0/seqstatx.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+seqstatx = seqstats.cli:main

seqstatx-0.1.0/seqstatx.egg-info/requires.txt

@@ -0,0 +1,4 @@
+
+[dev]
+pytest
+pytest-cov

seqstatx-0.1.0/seqstatx.egg-info/top_level.txt

@@ -0,0 +1 @@
+seqstats

seqstatx-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

seqstatx-0.1.0/tests/test_cli.py

@@ -0,0 +1,57 @@
+"""Tests for the seqstats CLI."""
+
+import subprocess
+import sys
+
+import pytest
+
+from seqstats.cli import main
+
+FASTA_TEXT = ">seq1\nACGTACGTGG\n>seq2\nGGGGCCCCAAAATTTT\n>seq3\nATAT\n"
+
+
+def test_cli_default_output(tmp_path, capsys):
+    p = tmp_path / "test.fa"
+    p.write_text(FASTA_TEXT)
+    main([str(p)])
+    out = capsys.readouterr().out
+    assert "test.fa" in out
+    assert "N50" in out
+    assert "gc%" in out
+
+
+def test_cli_tsv_output(tmp_path, capsys):
+    p = tmp_path / "test.fa"
+    p.write_text(FASTA_TEXT)
+    main(["--tsv", str(p)])
+    out = capsys.readouterr().out
+    lines = out.strip().split("\n")
+    assert lines[0].startswith("file\tseqs")
+    # data row has tab-separated fields matching header count
+    assert len(lines[1].split("\t")) == len(lines[0].split("\t"))
+
+
+def test_cli_missing_file_exits(tmp_path):
+    with pytest.raises(SystemExit) as exc:
+        main([str(tmp_path / "nope.fa")])
+    assert exc.value.code == 1
+
+
+def test_cli_multiple_files(tmp_path, capsys):
+    p1 = tmp_path / "a.fa"
+    p2 = tmp_path / "b.fa"
+    p1.write_text(FASTA_TEXT)
+    p2.write_text(FASTA_TEXT)
+    main(["--tsv", str(p1), str(p2)])
+    out = capsys.readouterr().out
+    lines = out.strip().split("\n")
+    assert len(lines) == 3  # header + 2 rows
+
+
+def test_cli_version():
+    result = subprocess.run(
+        [sys.executable, "-m", "seqstats.cli", "--version"],
+        capture_output=True,
+        text=True,
+    )
+    assert "seqstatx" in result.stdout

seqstatx-0.1.0/tests/test_core.py

@@ -0,0 +1,135 @@
+"""Tests for seqstats.core — values hand-verified."""
+
+import gzip
+from pathlib import Path
+
+import pytest
+
+from seqstats.core import SeqStats, parse_fasta, parse_fastq, parse_file
+
+
+# ---------------------------------------------------------------------------
+# SeqStats unit tests
+# ---------------------------------------------------------------------------
+
+def test_empty_stats():
+    s = SeqStats(name="empty")
+    assert s.n_seqs == 0
+    assert s.total_bases == 0
+    assert s.gc_pct == 0.0
+    assert s.mean_len == 0.0
+    assert s.min_len == 0
+    assert s.max_len == 0
+    assert s.n50 == 0
+    assert s.n90 == 0
+
+
+def test_single_sequence():
+    s = SeqStats(name="one")
+    s.add("ACGTACGTGG")  # 10 bp, GC = C,G,C,G,G,G -> 2 C + 4 G... let's compute
+    # A C G T A C G T G G -> C:2, G:4 -> GC = 6
+    assert s.n_seqs == 1
+    assert s.total_bases == 10
+    assert s.gc_count == 6
+    assert s.gc_pct == pytest.approx(60.0)
+    assert s.mean_len == 10.0
+    assert s.min_len == s.max_len == 10
+    assert s.n50 == 10
+    assert s.n90 == 10
+
+
+def test_gc_case_insensitive():
+    s = SeqStats(name="mixed")
+    s.add("acgtACGT")  # a c g t A C G T -> c,g,C,G = 4 GC of 8
+    assert s.gc_count == 4
+    assert s.gc_pct == pytest.approx(50.0)
+
+
+def test_n50_n90():
+    # lengths 16, 10, 4 ; total = 30
+    s = SeqStats(name="n50")
+    s.add("G" * 16)
+    s.add("G" * 10)
+    s.add("G" * 4)
+    # N50: sorted desc [16,10,4], half=15 -> 16 reaches 16>=15 -> 16
+    assert s.n50 == 16
+    # N90: 0.9*30 = 27 -> 16 (16), +10 (26), +4 (30>=27) -> 4
+    assert s.n90 == 4
+
+
+def test_n50_classic_example():
+    # Classic: [2,3,4,5,6,7,8,9,10], total=54, half=27
+    s = SeqStats(name="classic")
+    for n in [2, 3, 4, 5, 6, 7, 8, 9, 10]:
+        s.add("A" * n)
+    # sorted desc: 10,9,8,7,6... cumsum: 10,19,27 -> 8 reaches 27>=27 -> 8
+    assert s.n50 == 8
+
+
+# ---------------------------------------------------------------------------
+# Parser tests
+# ---------------------------------------------------------------------------
+
+FASTA_TEXT = ">seq1\nACGTACGTGG\n>seq2\nGGGGCCCCAAAATTTT\n>seq3\nATAT\n"
+FASTQ_TEXT = "@read1\nACGTACGTGC\n+\nIIIIIIIIII\n@read2\nGGCCGGCCAA\n+\nIIIIIIIIII\n"
+
+
+def test_parse_fasta(tmp_path):
+    p = tmp_path / "test.fa"
+    p.write_text(FASTA_TEXT)
+    s = parse_fasta(p)
+    assert s.n_seqs == 3
+    assert s.total_bases == 30  # 10 + 16 + 4
+    assert s.min_len == 4
+    assert s.max_len == 16
+    assert s.gc_pct == pytest.approx(46.666, abs=0.01)
+
+
+def test_parse_fasta_multiline(tmp_path):
+    # Sequence wrapped across multiple lines must be joined
+    p = tmp_path / "wrapped.fa"
+    p.write_text(">seq1\nACGT\nACGT\nGG\n")
+    s = parse_fasta(p)
+    assert s.n_seqs == 1
+    assert s.total_bases == 10
+
+
+def test_parse_fastq(tmp_path):
+    p = tmp_path / "test.fq"
+    p.write_text(FASTQ_TEXT)
+    s = parse_fastq(p)
+    assert s.n_seqs == 2
+    assert s.total_bases == 20
+    assert s.gc_pct == pytest.approx(70.0)
+
+
+def test_parse_gzipped_fastq(tmp_path):
+    p = tmp_path / "test.fq.gz"
+    with gzip.open(p, "wt") as fh:
+        fh.write(FASTQ_TEXT)
+    s = parse_fastq(p)
+    assert s.n_seqs == 2
+    assert s.total_bases == 20
+
+
+def test_parse_file_detects_fasta(tmp_path):
+    p = tmp_path / "genome.fasta"
+    p.write_text(FASTA_TEXT)
+    s = parse_file(p)
+    assert s.n_seqs == 3
+
+
+def test_parse_file_detects_fastq_gz(tmp_path):
+    p = tmp_path / "reads.fastq.gz"
+    with gzip.open(p, "wt") as fh:
+        fh.write(FASTQ_TEXT)
+    s = parse_file(p)
+    assert s.n_seqs == 2
+
+
+def test_parse_fasta_blank_lines(tmp_path):
+    p = tmp_path / "blanks.fa"
+    p.write_text(">seq1\nACGT\n\n>seq2\nGGGG\n\n")
+    s = parse_fasta(p)
+    assert s.n_seqs == 2
+    assert s.total_bases == 8