fetchm2 0.1.2__tar.gz → 0.1.4__tar.gz

{fetchm2-0.1.2/src/fetchm2.egg-info → fetchm2-0.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fetchm2
-Version: 0.1.2
+Version: 0.1.4
 Summary: Standalone comprehensive genome metadata standardization and sequence download toolkit.
 Author-email: Tasnimul Arabi Anik <arabianik987@gmail.com>
 License-Expression: MIT
@@ -68,7 +68,7 @@ fetchm2 run --input ncbi_dataset.tsv --outdir results --download
 ```bash
 python -m venv fetchm2-env
 source fetchm2-env/bin/activate
-pip install fetchm2
+pip install fetchm2==0.1.4
 ```
 
 Verify:

{fetchm2-0.1.2 → fetchm2-0.1.4}/README.md

@@ -32,7 +32,7 @@ fetchm2 run --input ncbi_dataset.tsv --outdir results --download
 ```bash
 python -m venv fetchm2-env
 source fetchm2-env/bin/activate
-pip install fetchm2
+pip install fetchm2==0.1.4
 ```
 
 Verify:

{fetchm2-0.1.2 → fetchm2-0.1.4}/docs/VALIDATION_REPORT.md

@@ -1,7 +1,7 @@
 # FetchM2 Validation Report
 
 Validation date: 2026-05-05
-Current validation target: `fetchm2 0.1.2`
+Current validation target: `fetchm2 0.1.4`
 
 ## Source Baselines
 
@@ -234,3 +234,49 @@ Known scope notes for `0.1.2`:
 - host lineage is bundled for common hosts and optionally enriched with `taxonkit` when installed
 - embeddings/BGE are intentionally not used in production standardization
 - large-scale sequence download was not run during this validation to avoid unnecessary NCBI load
+
+## Additional 0.1.3 Documentation Validation
+
+The 0.1.3 patch updates the README installation command to use the pinned current PyPI release:
+
+```bash
+pip install fetchm2==0.1.3
+```
+
+No runtime behavior changed from 0.1.2.
+
+## Additional 0.1.4 Sequence Download Validation
+
+The 0.1.4 patch fixes a sequence-download cache issue found during remote-user-style testing.
+
+Remote-user-style `0.1.3` validation:
+
+```text
+Fresh PyPI install: passed
+fetchm2 --version: fetchm2 0.1.3
+Live metadata run: production gate PASS
+Sequence selection: selected 2 genomes
+Sequence download: failed 2 / 2
+Failure reason: SQLite sequence cache connection was created on the main thread and used inside download worker threads
+```
+
+0.1.4 fix:
+
+```text
+DirectoryCache now opens SQLite with check_same_thread=False
+DirectoryCache serializes cache reads/writes with a lock
+Added threaded DirectoryCache regression test
+pytest: 12 passed
+```
+
+Patched local real-download validation:
+
+```text
+Command: fetchm2 seq --input fetchm2_clean.csv --outdir /tmp/fetchm2_fixed_real_seq_download --max-genomes 2 --download-workers 1 --retries 2 --retry-delay 1
+Sequences selected: 2
+Sequences downloaded: 2
+Sequences failed: 0
+Downloaded files:
+- GCA_006094395.1_ASM609439v1_genomic.fna
+- GCF_006094395.1_ASM609439v1_genomic.fna
+```

{fetchm2-0.1.2 → fetchm2-0.1.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "fetchm2"
-version = "0.1.2"
+version = "0.1.4"
 description = "Standalone comprehensive genome metadata standardization and sequence download toolkit."
 readme = "README.md"
 requires-python = ">=3.10"

{fetchm2-0.1.2 → fetchm2-0.1.4}/src/fetchm2/__init__.py

@@ -2,4 +2,4 @@
 
 from __future__ import annotations
 
-__version__ = "0.1.2"
+__version__ = "0.1.4"

{fetchm2-0.1.2 → fetchm2-0.1.4}/src/fetchm2/sequence.py

@@ -4,6 +4,7 @@ import gzip
 import re
 import shutil
 import sqlite3
+import threading
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from pathlib import Path
 from typing import Any
@@ -32,28 +33,32 @@ def build_parent_url(accession: str) -> str:
 
 class DirectoryCache:
     def __init__(self, path: Path) -> None:
-        self.conn = sqlite3.connect(path)
+        self.conn = sqlite3.connect(path, check_same_thread=False)
+        self.lock = threading.Lock()
         self.conn.execute(
             "CREATE TABLE IF NOT EXISTS assembly_directory_cache (accession TEXT PRIMARY KEY, assembly_name TEXT, directory TEXT)"
         )
         self.conn.commit()
 
     def get(self, accession: str, name: str) -> str | None:
-        row = self.conn.execute(
-            "SELECT directory FROM assembly_directory_cache WHERE accession = ? AND assembly_name = ?",
-            (accession, normalize_assembly_name(name)),
-        ).fetchone()
+        with self.lock:
+            row = self.conn.execute(
+                "SELECT directory FROM assembly_directory_cache WHERE accession = ? AND assembly_name = ?",
+                (accession, normalize_assembly_name(name)),
+            ).fetchone()
         return None if row is None else str(row[0])
 
     def set(self, accession: str, name: str, directory: str) -> None:
-        self.conn.execute(
-            "INSERT OR REPLACE INTO assembly_directory_cache (accession, assembly_name, directory) VALUES (?, ?, ?)",
-            (accession, normalize_assembly_name(name), directory),
-        )
-        self.conn.commit()
+        with self.lock:
+            self.conn.execute(
+                "INSERT OR REPLACE INTO assembly_directory_cache (accession, assembly_name, directory) VALUES (?, ?, ?)",
+                (accession, normalize_assembly_name(name), directory),
+            )
+            self.conn.commit()
 
     def close(self) -> None:
-        self.conn.close()
+        with self.lock:
+            self.conn.close()
 
 
 def resolve_assembly_directory(accession: str, name: str, cache: DirectoryCache) -> str:

{fetchm2-0.1.2 → fetchm2-0.1.4/src/fetchm2.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fetchm2
-Version: 0.1.2
+Version: 0.1.4
 Summary: Standalone comprehensive genome metadata standardization and sequence download toolkit.
 Author-email: Tasnimul Arabi Anik <arabianik987@gmail.com>
 License-Expression: MIT
@@ -68,7 +68,7 @@ fetchm2 run --input ncbi_dataset.tsv --outdir results --download
 ```bash
 python -m venv fetchm2-env
 source fetchm2-env/bin/activate
-pip install fetchm2
+pip install fetchm2==0.1.4
 ```
 
 Verify:

{fetchm2-0.1.2 → fetchm2-0.1.4}/tests/test_cli.py

@@ -1,11 +1,13 @@
 from __future__ import annotations
 
+from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
 
 import pandas as pd
 
 from fetchm2.cli import build_parser, main
 from fetchm2.metadata import MetadataCache, RequestRateLimiter, fetch_biosample_metadata
+from fetchm2.sequence import DirectoryCache
 
 
 def test_metadata_cli_offline(tmp_path: Path, monkeypatch) -> None:
@@ -79,6 +81,25 @@ def test_sequence_check_only_cli(tmp_path: Path, monkeypatch) -> None:
     assert (seq_out / "sequence_download_summary.csv").exists()
 
 
+def test_sequence_directory_cache_is_thread_safe(tmp_path: Path) -> None:
+    cache = DirectoryCache(tmp_path / "sequence_cache.sqlite3")
+
+    def write_and_read(index: int) -> str | None:
+        accession = f"GCA_000000{index:03d}.1"
+        name = f"Assembly {index}"
+        directory = f"{accession}_Assembly_{index}"
+        cache.set(accession, name, directory)
+        return cache.get(accession, name)
+
+    try:
+        with ThreadPoolExecutor(max_workers=4) as executor:
+            results = list(executor.map(write_and_read, range(12)))
+    finally:
+        cache.close()
+
+    assert results == [f"GCA_000000{index:03d}.1_Assembly_{index}" for index in range(12)]
+
+
 def test_analyze_cli_generates_figures(tmp_path: Path, monkeypatch) -> None:
     input_path = Path(__file__).resolve().parents[1] / "examples" / "offline_metadata.tsv"
     meta_out = tmp_path / "meta"