uniprotlib 0.1.0__py3-none-any.whl

uniprotlib/__init__.py

@@ -0,0 +1,11 @@
+from .models import DbReference, Gene, Organism, Sequence, UniProtEntry
+from .parser import parse_xml
+
+__all__ = [
+    "DbReference",
+    "Gene",
+    "Organism",
+    "Sequence",
+    "UniProtEntry",
+    "parse_xml",
+]

uniprotlib/models.py

@@ -0,0 +1,47 @@
+from dataclasses import dataclass
+
+
+@dataclass(slots=True)
+class Organism:
+    scientific_name: str | None
+    common_name: str | None
+    tax_id: str | None
+    lineage: list[str]
+
+
+@dataclass(slots=True)
+class Gene:
+    primary: str | None
+    synonyms: list[str]
+    ordered_locus_names: list[str]
+    orf_names: list[str]
+
+
+@dataclass(slots=True)
+class Sequence:
+    value: str
+    length: int
+    mass: int
+    checksum: str
+
+
+@dataclass(slots=True)
+class DbReference:
+    type: str
+    id: str
+    molecule: str | None
+    properties: dict[str, str]
+
+
+@dataclass(slots=True)
+class UniProtEntry:
+    primary_accession: str
+    accessions: list[str]
+    entry_name: str
+    dataset: str
+    protein_name: str | None
+    gene: Gene | None
+    organism: Organism
+    sequence: Sequence
+    keywords: list[str]
+    db_references: list[DbReference]

uniprotlib/parser.py

@@ -0,0 +1,193 @@
+from __future__ import annotations
+
+import gzip
+from collections.abc import Iterator
+from pathlib import Path
+
+from lxml import etree
+
+from .models import DbReference, Gene, Organism, Sequence, UniProtEntry
+
+_NS_HTTP = "http://uniprot.org/uniprot"
+_NS_HTTPS = "https://uniprot.org/uniprot"
+
+
+def _detect_namespace(path: Path) -> str:
+    """Detect which namespace variant a UniProt XML file uses.
+
+    Single-entry downloads use http://, bulk FTP downloads use https://.
+    """
+    opener = gzip.open if path.suffix == ".gz" else open
+    with opener(path, "rb") as f:  # type: ignore[arg-type]
+        chunk = f.read(2048)
+    if b"https://uniprot.org/uniprot" in chunk:
+        return _NS_HTTPS
+    return _NS_HTTP
+
+
+def _tag(ns: str, name: str) -> str:
+    return f"{{{ns}}}{name}"
+
+
+def _parse_gene(ns: str, entry: etree._Element) -> Gene | None:
+    gene_elem = entry.find(_tag(ns, "gene"))
+    if gene_elem is None:
+        return None
+
+    primary = None
+    synonyms: list[str] = []
+    ordered_locus: list[str] = []
+    orfs: list[str] = []
+
+    for name_elem in gene_elem.findall(_tag(ns, "name")):
+        name_type = name_elem.attrib.get("type")
+        text = name_elem.text or ""
+        if name_type == "primary":
+            primary = text
+        elif name_type == "synonym":
+            synonyms.append(text)
+        elif name_type == "ordered locus":
+            ordered_locus.append(text)
+        elif name_type == "ORF":
+            orfs.append(text)
+
+    return Gene(
+        primary=primary,
+        synonyms=synonyms,
+        ordered_locus_names=ordered_locus,
+        orf_names=orfs,
+    )
+
+
+def _parse_organism(ns: str, entry: etree._Element) -> Organism:
+    org_elem = entry.find(_tag(ns, "organism"))
+
+    scientific_name = None
+    common_name = None
+    tax_id = None
+    lineage: list[str] = []
+
+    if org_elem is not None:
+        for name_elem in org_elem.findall(_tag(ns, "name")):
+            name_type = name_elem.attrib.get("type")
+            if name_type == "scientific":
+                scientific_name = name_elem.text
+            elif name_type == "common":
+                common_name = name_elem.text
+
+        tax_ref = org_elem.find(
+            f"{_tag(ns, 'dbReference')}[@type='NCBI Taxonomy']"
+        )
+        if tax_ref is not None:
+            tax_id = tax_ref.attrib.get("id")
+
+        lineage_elem = org_elem.find(_tag(ns, "lineage"))
+        if lineage_elem is not None:
+            lineage = [
+                t.text or ""
+                for t in lineage_elem.findall(_tag(ns, "taxon"))
+            ]
+
+    return Organism(
+        scientific_name=scientific_name,
+        common_name=common_name,
+        tax_id=tax_id,
+        lineage=lineage,
+    )
+
+
+def _parse_sequence(ns: str, entry: etree._Element) -> Sequence:
+    seq_elem = entry.find(_tag(ns, "sequence"))
+    raw = seq_elem.text or ""
+    value = raw.replace("\n", "").replace(" ", "")
+
+    return Sequence(
+        value=value,
+        length=int(seq_elem.attrib.get("length", 0)),
+        mass=int(seq_elem.attrib.get("mass", 0)),
+        checksum=seq_elem.attrib.get("checksum", ""),
+    )
+
+
+def _parse_db_references(ns: str, entry: etree._Element) -> list[DbReference]:
+    refs: list[DbReference] = []
+    for elem in entry.findall(_tag(ns, "dbReference")):
+        molecule_elem = elem.find(_tag(ns, "molecule"))
+        molecule = molecule_elem.attrib.get("id") if molecule_elem is not None else None
+
+        properties = {
+            prop.attrib["type"]: prop.attrib["value"]
+            for prop in elem.findall(_tag(ns, "property"))
+        }
+
+        refs.append(DbReference(
+            type=elem.attrib["type"],
+            id=elem.attrib["id"],
+            molecule=molecule,
+            properties=properties,
+        ))
+    return refs
+
+
+def _parse_entry(ns: str, entry: etree._Element) -> UniProtEntry:
+    accessions = [
+        acc.text or ""
+        for acc in entry.findall(_tag(ns, "accession"))
+    ]
+
+    names = entry.findall(_tag(ns, "name"))
+    entry_name = names[0].text or "" if names else ""
+
+    protein_name = None
+    name_elem = entry.find(
+        f"{_tag(ns, 'protein')}/{_tag(ns, 'recommendedName')}/{_tag(ns, 'fullName')}"
+    )
+    if name_elem is not None:
+        protein_name = name_elem.text
+
+    keywords = [
+        kw.text or ""
+        for kw in entry.findall(_tag(ns, "keyword"))
+    ]
+
+    return UniProtEntry(
+        primary_accession=accessions[0] if accessions else "",
+        accessions=accessions,
+        entry_name=entry_name,
+        dataset=entry.attrib.get("dataset", ""),
+        protein_name=protein_name,
+        gene=_parse_gene(ns, entry),
+        organism=_parse_organism(ns, entry),
+        sequence=_parse_sequence(ns, entry),
+        keywords=keywords,
+        db_references=_parse_db_references(ns, entry),
+    )
+
+
+def _parse_single_file(path: Path) -> Iterator[UniProtEntry]:
+    ns = _detect_namespace(path)
+    opener = gzip.open if path.suffix == ".gz" else open
+
+    with opener(path, "rb") as f:  # type: ignore[arg-type]
+        context = etree.iterparse(f, events=("end",), tag=_tag(ns, "entry"))
+
+        for _event, entry in context:
+            yield _parse_entry(ns, entry)
+
+            # memory cleanup — critical for multi-GB files
+            entry.clear()
+            while entry.getprevious() is not None:
+                del entry.getparent()[0]
+
+
+def parse_xml(*paths: str | Path) -> Iterator[UniProtEntry]:
+    """Stream-parse one or more UniProt XML files, yielding UniProtEntry objects.
+
+    Accepts plain XML or gzip-compressed files (auto-detected from .gz extension).
+    Files are processed sequentially. Memory stays bounded regardless of file size.
+    """
+    if not paths:
+        raise ValueError("At least one path is required")
+
+    for p in paths:
+        yield from _parse_single_file(Path(p))

uniprotlib-0.1.0.dist-info/METADATA

@@ -0,0 +1,72 @@
+Metadata-Version: 2.4
+Name: uniprotlib
+Version: 0.1.0
+Summary: Python library for parsing UniProt XML data
+License-Expression: MIT
+License-File: LICENSE
+Requires-Python: >=3.12
+Requires-Dist: lxml>=6.0.2
+Description-Content-Type: text/markdown
+
+# uniprotlib
+
+> **Note:** This library was vibe coded with Claude. It works, it's tested, but review accordingly.
+
+Python library for parsing UniProt XML files. Handles both single-entry downloads and multi-GB gzip-compressed database dumps with bounded memory usage.
+
+## Installation
+
+```bash
+pip install uniprotlib
+```
+
+Or with [uv](https://docs.astral.sh/uv/):
+
+```bash
+uv add uniprotlib
+```
+
+## Usage
+
+```python
+from uniprotlib import parse_xml
+
+# single file
+for entry in parse_xml("Q9Y261.xml"):
+    print(entry.primary_accession, entry.protein_name)
+
+# gzipped bulk download
+for entry in parse_xml("uniprot_sprot.xml.gz"):
+    print(entry.gene.primary, entry.organism.scientific_name)
+
+# multiple files
+for entry in parse_xml("human.xml.gz", "mouse.xml.gz"):
+    print(entry.primary_accession)
+```
+
+`parse_xml()` returns an iterator that yields `UniProtEntry` objects. Gzip detection is automatic based on the `.gz` extension. Memory stays bounded regardless of file size.
+
+## Parsed fields
+
+| Model | Fields |
+|---|---|
+| `UniProtEntry` | primary_accession, accessions, entry_name, dataset, protein_name, gene, organism, sequence, keywords, db_references |
+| `Gene` | primary, synonyms, ordered_locus_names, orf_names |
+| `Organism` | scientific_name, common_name, tax_id, lineage |
+| `Sequence` | value, length, mass, checksum |
+| `DbReference` | type, id, molecule, properties |
+
+All model classes are dataclasses with full type annotations and `py.typed` support.
+
+## Development
+
+Requires Python >= 3.12 and [uv](https://docs.astral.sh/uv/).
+
+```bash
+uv sync
+uv run pytest tests/ -v
+```
+
+## License
+
+MIT

uniprotlib-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+uniprotlib/__init__.py,sha256=54LDhaTc2DNW8BexoamdJCojpP3WAx3P2q3hsK64tLQ,217
+uniprotlib/models.py,sha256=U5dUj5OT9IMIlF8CLLn_DXGw1KZhP8bfakAz1uQqhp8,849
+uniprotlib/parser.py,sha256=f78uHZ8KkTHSKindS528TIfT_mmJ8J0wNM6l1f0AJmA,5827
+uniprotlib/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+uniprotlib-0.1.0.dist-info/METADATA,sha256=uSNFnNrd71xvjDCSCZuKrpobuBcKXBbrxxduVtwSd74,1861
+uniprotlib-0.1.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+uniprotlib-0.1.0.dist-info/licenses/LICENSE,sha256=7CcQ1452DPAwleU8s7slt_D3J4pn8DTpfljLwk5nQQo,1071
+uniprotlib-0.1.0.dist-info/RECORD,,

uniprotlib-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.28.0
+Root-Is-Purelib: true
+Tag: py3-none-any

uniprotlib-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Martin Preusse
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.