allelix 1.8.1__py3-none-any.whl

allelix/parsers/myheritage.py

@@ -0,0 +1,118 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+# Copyright (C) 2026 dial481
+"""Parser for MyHeritage DNA raw genotype export files.
+
+Format reference (from real sample files and snps package):
+
+    # MyHeritage, https://www.myheritage.com
+    RSID,CHROMOSOME,POSITION,RESULT
+    "rs4477212","1","82154","AA"
+    "rs3094315","1","752566","AG"
+    "rs9001001","1","100000","--"
+
+Specifics:
+    - CSV format, comma-delimited. Structurally identical to FTDNA.
+    - Detection key: ``MyHeritage`` in the first comment line.
+    - Header line: ``RSID,CHROMOSOME,POSITION,RESULT`` (quoted or unquoted).
+    - Data fields are double-quoted; some exports double-double-quote
+      fields (``""rs1""``). ``split_csv_line`` handles both.
+    - RESULT column is concatenated genotype (e.g., "AG" not "A","G").
+    - Haploid calls on MT/Y appear as single characters (e.g., "A").
+    - No-calls represented as ``--``.
+    - Build: not declared in file; position-based detection required.
+      Defaults to GRCh37.
+"""
+
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING, ClassVar
+
+from allelix.models import DEFAULT_BUILD, Variant
+from allelix.parsers._helpers import split_csv_line, split_genotype
+from allelix.parsers.base import GenotypeMetadata, GenotypeParser
+from allelix.parsers.ftdna import HEADER_CANONICAL, _is_header_line
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+    from pathlib import Path
+
+logger = logging.getLogger(__name__)
+
+SIGNATURE = "MyHeritage"
+SNIFF_LINE_LIMIT = 50
+EXPECTED_COLUMNS = 4
+
+
+class MyHeritageParser(GenotypeParser):
+    """Parser for MyHeritage DNA consumer genotype files."""
+
+    name: ClassVar[str] = "myheritage"
+    display_name: ClassVar[str] = "MyHeritage DNA"
+    file_extensions: ClassVar[list[str]] = [".csv"]
+    url: ClassVar[str] = "https://www.myheritage.com"
+
+    def can_parse(self, file_path: Path) -> bool:
+        """Recognize the file by ``MyHeritage`` in the first comment line."""
+        try:
+            with file_path.open("r", encoding="utf-8") as fh:
+                first_line = fh.readline()
+                return SIGNATURE in first_line
+        except (OSError, UnicodeDecodeError):
+            return False
+
+    def parse(self, file_path: Path) -> Iterator[Variant]:
+        """Stream Variant objects, skipping comments and malformed lines."""
+        with file_path.open("r", encoding="utf-8") as fh:
+            header_seen = False
+            for lineno, raw in enumerate(fh, start=1):
+                line = raw.rstrip("\r\n")
+                if not line or line.startswith("#"):
+                    continue
+                if not header_seen:
+                    if _is_header_line(line):
+                        header_seen = True
+                        continue
+                    logger.warning(
+                        "Line %d: expected %s header, got %r — skipping",
+                        lineno,
+                        HEADER_CANONICAL,
+                        line,
+                    )
+                    continue
+
+                parts = split_csv_line(line)
+                if len(parts) != EXPECTED_COLUMNS:
+                    logger.warning(
+                        "Line %d: expected %d columns, got %d — skipping",
+                        lineno,
+                        EXPECTED_COLUMNS,
+                        len(parts),
+                    )
+                    continue
+
+                rsid, chrom, pos_str, genotype = parts
+                try:
+                    position = int(pos_str)
+                except ValueError:
+                    logger.warning("Line %d: invalid position %r — skipping", lineno, pos_str)
+                    continue
+
+                allele1, allele2 = split_genotype(genotype)
+
+                yield Variant(
+                    rsid=rsid,
+                    chromosome=chrom,
+                    position=position,
+                    allele1=allele1,
+                    allele2=allele2,
+                    build=DEFAULT_BUILD,
+                )
+
+    def get_metadata(self, file_path: Path) -> GenotypeMetadata:
+        """Extract metadata. MyHeritage files have no sample ID or build field."""
+        return GenotypeMetadata(
+            format=self.name,
+            sample_id="",
+            build=DEFAULT_BUILD,
+        )

allelix/parsers/twentythreeandme.py

@@ -0,0 +1,150 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+# Copyright (C) 2026 dial481
+"""Parser for 23andMe raw genotype export files.
+
+Format reference (from real sample files and snps package):
+
+    # This data file generated by 23andMe at: Mon Jun 01 00:00:00 2020
+    #
+    # This file contains raw genotype data ...
+    #
+    # rsid  chromosome  position  genotype
+    rs4477212	1	82154	AA
+    rs3094315	1	752566	AG
+    i3000043	5	33951693	CT
+    rs9001001	1	100000	--
+
+Specifics:
+    - Comment lines start with `#`.
+    - Tab-delimited, 4 columns of data.
+    - Genotype is concatenated in one column (e.g., "AG" not "A<tab>G").
+    - Haploid calls on X/Y/MT appear as single characters (e.g., "A").
+    - No-calls represented as `--`.
+    - Contains I-prefixed internal probe IDs (i3000043, i5006212)
+      alongside rs-numbers. These are passed through as-is.
+    - Build 37 (older) or Build 38 (newer); check header comments.
+    - Detection key: canonical header ``# This data file generated by 23andMe``.
+      A bare "23andMe" substring in a comment is NOT sufficient — it would
+      false-positive on transcoded fixtures and third-party tool output.
+"""
+
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING, ClassVar
+
+from allelix.models import DEFAULT_BUILD, NO_CALL_MARKER, Variant
+from allelix.parsers.base import GenotypeMetadata, GenotypeParser
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+    from pathlib import Path
+
+logger = logging.getLogger(__name__)
+
+_CANONICAL_PREFIX = "# This data file generated by 23andMe"
+SNIFF_LINE_LIMIT = 50
+EXPECTED_COLUMNS = 4
+
+
+class TwentyThreeAndMeParser(GenotypeParser):
+    """Parser for 23andMe consumer DNA genotype files."""
+
+    name: ClassVar[str] = "23andme"
+    display_name: ClassVar[str] = "23andMe"
+    file_extensions: ClassVar[list[str]] = [".txt"]
+    url: ClassVar[str] = "https://www.23andme.com"
+
+    def can_parse(self, file_path: Path) -> bool:
+        """Recognize a real 23andMe export by its canonical first-line header.
+
+        Real exports start with ``# This data file generated by 23andMe at: ...``.
+        Some files have user-prepended comments before the canonical line; the
+        fallback loop scans up to ``SNIFF_LINE_LIMIT`` comment lines. A bare
+        "23andMe" mention without the canonical prefix is rejected.
+        """
+        try:
+            with file_path.open("r", encoding="utf-8") as fh:
+                for _ in range(SNIFF_LINE_LIMIT):
+                    line = fh.readline()
+                    if not line:
+                        return False
+                    if not line.startswith("#"):
+                        return False
+                    if line.startswith(_CANONICAL_PREFIX):
+                        return True
+        except (OSError, UnicodeDecodeError):
+            return False
+        return False
+
+    def parse(self, file_path: Path) -> Iterator[Variant]:
+        """Stream Variant objects, skipping comments and malformed lines."""
+        with file_path.open("r", encoding="utf-8") as fh:
+            for lineno, raw in enumerate(fh, start=1):
+                line = raw.rstrip("\r\n")
+                if not line or line.startswith("#"):
+                    continue
+
+                parts = line.split("\t")
+                if len(parts) != EXPECTED_COLUMNS:
+                    logger.warning(
+                        "Line %d: expected %d columns, got %d — skipping",
+                        lineno,
+                        EXPECTED_COLUMNS,
+                        len(parts),
+                    )
+                    continue
+
+                rsid, chrom, pos_str, genotype = parts
+                try:
+                    position = int(pos_str)
+                except ValueError:
+                    logger.warning("Line %d: invalid position %r — skipping", lineno, pos_str)
+                    continue
+
+                allele1, allele2 = _split_genotype(genotype)
+
+                yield Variant(
+                    rsid=rsid,
+                    chromosome=chrom,
+                    position=position,
+                    allele1=allele1,
+                    allele2=allele2,
+                    build=DEFAULT_BUILD,
+                )
+
+    def get_metadata(self, file_path: Path) -> GenotypeMetadata:
+        """Extract build from header comments. 23andMe files have no sample ID field."""
+        build = DEFAULT_BUILD
+        with file_path.open("r", encoding="utf-8") as fh:
+            for raw in fh:
+                line = raw.rstrip("\r\n")
+                if not line.startswith("#"):
+                    break
+                lowered = line.lower()
+                if "build 36" in lowered or "hg18" in lowered:
+                    build = "GRCh36"
+                elif "build 37" in lowered or "grch37" in lowered:
+                    build = "GRCh37"
+                elif "build 38" in lowered or "grch38" in lowered:
+                    build = "GRCh38"
+        return GenotypeMetadata(
+            format=self.name,
+            sample_id="",
+            build=build,
+        )
+
+
+def _split_genotype(genotype: str) -> tuple[str, str]:
+    """Split a concatenated genotype field into two alleles.
+
+    "AG" → ("A", "G"), "--" → ("-", "-"), "A" → ("A", "A") (haploid).
+    """
+    if genotype == "--":
+        return NO_CALL_MARKER, NO_CALL_MARKER
+    if len(genotype) == 2:
+        return genotype[0], genotype[1]
+    if len(genotype) == 1:
+        return genotype, genotype
+    logger.warning("Unexpected genotype format %r — treating as no-call", genotype)
+    return NO_CALL_MARKER, NO_CALL_MARKER

allelix/reports/__init__.py

@@ -0,0 +1,40 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+# Copyright (C) 2026 dial481
+"""Report rendering: terminal, JSON, and HTML."""
+
+from __future__ import annotations
+
+import contextlib
+import os
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+# Single source of truth for the project's compliance / regulatory contract.
+# Surfaced verbatim in JSON `regulatory_notice` and the HTML banner. See ADR-0003.
+REGULATORY_NOTICE = (
+    "This report is informational research output. It surfaces classifications "
+    "made by external databases (ClinVar, PharmGKB, …) for variants present in "
+    "the input genotype file. It is not medical advice and not a diagnosis. "
+    "Every classification is attributed to its source database; Allelix does "
+    "not independently classify variants."
+)
+
+
+def atomic_write_text(path: Path, content: str, encoding: str = "utf-8") -> None:
+    """Write `content` to `path` via a `.tmp` sibling + `os.replace`.
+
+    Mirrors `download()` / `load_clinvar_vcf` atomicity: a killed process
+    mid-write leaves either the previous file or no file at the target,
+    never a half-written one.
+    """
+    tmp = path.with_name(path.name + ".tmp")
+    try:
+        tmp.write_text(content, encoding=encoding)
+        os.replace(tmp, path)
+    except Exception:
+        if tmp.exists():
+            with contextlib.suppress(OSError):
+                tmp.unlink()
+        raise