allelix 2.2.2__py3-none-any.whl → 2.2.3__py3-none-any.whl

allelix/annotators/gnomad.py

@@ -247,34 +247,29 @@ class GnomadAnnotator(Annotator):
             return {}
         conn = self._connection()
         result: dict[tuple[str, int], list[tuple[str, str, str]]] = {}
-        # GH #134: issue a single combined SQL statement per chunk
-        # using SQLite's row-value ``(chrom, pos) IN ((?, ?), ...)``
-        # form instead of grouping by chromosome and issuing one
-        # statement per (chrom, chunk) pair. On WGS input each batch
-        # touches all ~24 chromosomes; the per-chrom shape was a 24x
-        # query multiplier the new ``idx_gnomad_position`` index could
-        # not amortize away. The row-value IN form keeps the same
-        # carrier-rule contract — both ``chrom`` and ``pos`` must
-        # match the input pair simultaneously — and the
-        # ``idx_gnomad_position`` covering index on (chrom, pos)
-        # serves the lookup directly. ``_BULK_BATCH_SIZE`` here
-        # refers to (chrom, pos) PAIRS not single ints, so each
-        # chunk binds 2 * batch_size parameters.
+        # Issue a single combined SQL statement per chunk using SQLite's
+        # row-value ``(chrom, pos) IN ((?, ?), ...)`` form instead of
+        # grouping by chromosome and issuing one statement per
+        # (chrom, chunk) pair. On WGS input each batch touches all ~24
+        # chromosomes; the per-chrom shape was a 24x query multiplier
+        # the ``idx_gnomad_position`` index could not amortize away. The
+        # row-value IN form keeps the same carrier-rule contract — both
+        # ``chrom`` and ``pos`` must match the input pair simultaneously
+        # — and the ``idx_gnomad_position`` covering index on
+        # ``(chrom, pos)`` serves the lookup directly.
         #
-        # SQLite parameter-limit awareness: 2 * _BULK_BATCH_SIZE =
-        # 1800 bind parameters per chunk. The historical SQLite
-        # ``SQLITE_MAX_VARIABLE_NUMBER`` default was 999, raised to
-        # 32766 in SQLite 3.32 (2020-05-22). Every Python version
-        # Allelix supports (>= 3.11) ships with SQLite >= 3.34, so
-        # the 1800-param chunk is well within the modern limit. If a
-        # future change bumps ``_BULK_BATCH_SIZE`` toward 16000 or
-        # the project drops Python's bundled SQLite for a system
-        # ``libsqlite3`` of unknown vintage, re-check this against
-        # the runtime ``sqlite3.sqlite_version`` before assuming
-        # capacity.
+        # Each input pair binds 2 SQLite parameters (chrom + pos), so
+        # the chunk size is ``_BULK_BATCH_SIZE // 2`` to stay inside the
+        # 999-param convention every other annotator and gnomAD's own
+        # multi-param queries respect (``bulk_lookup_by_alt`` does the
+        # same 2-param shape with the same ``// 2``;
+        # ``bulk_lookup_by_position`` uses ``// 4`` for its 4-param
+        # shape, same convention scaled). Net effective batch size:
+        # 450 pairs x 2 = 900 params per chunk.
+        chunk_pairs = _BULK_BATCH_SIZE // 2
         position_list = list(positions)
-        for i in range(0, len(position_list), _BULK_BATCH_SIZE):
-            batch = position_list[i : i + _BULK_BATCH_SIZE]
+        for i in range(0, len(position_list), chunk_pairs):
+            batch = position_list[i : i + chunk_pairs]
             placeholders = ",".join("(?, ?)" for _ in batch)
             params: list[str | int] = []
             for chrom, pos in batch:

allelix/parsers/twentythreeandme.py

@@ -42,7 +42,26 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger(__name__)
 
-_CANONICAL_PREFIX = "# This data file generated by 23andMe"
+# Known canonical first-line banner variants 23andMe wraps raw exports in.
+# The original v2/v3/v4-era exports used the verbatim ``generated by`` form;
+# the June 2026 v5 export prose was edited to ``is generated by`` (with a
+# trailing period in some samples). Match either; future vendor banner
+# edits get a new entry here.
+#
+# Why a tuple of exact prefixes instead of a loose ``"23andMe" in line``
+# substring match: a bare substring check false-positives on transcoded
+# fixtures and third-party tool output. Files that strip the canonical
+# banner entirely (WGSExtract output, Genetic Lifehacks converter output,
+# privacy-conscious users who delete the comment block) are out of scope
+# for this parser by design — they are handled by ``GenericTsvParser`` at
+# the end of the dispatch chain (planned, see GH #146 / GH #127). That
+# two-layer design keeps banner-bearing 23andMe files attributed to
+# "23andMe" and banner-less 23andMe-shape files attributed to "generic-tsv"
+# without guessing a vendor.
+_CANONICAL_PREFIXES: tuple[str, ...] = (
+    "# This data file generated by 23andMe",
+    "# This data file is generated by 23andMe",
+)
 SNIFF_LINE_LIMIT = 50
 EXPECTED_COLUMNS = 4
 
@@ -58,10 +77,13 @@ class TwentyThreeAndMeParser(GenotypeParser):
     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: ...``.
+        Real exports start with one of the variants in ``_CANONICAL_PREFIXES``:
+        the historical ``# This data file generated by 23andMe at: ...`` form
+        or the June 2026 v5 ``# This data file is generated by 23andMe.`` form.
         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.
+        scan loop reads up to ``SNIFF_LINE_LIMIT`` comment lines. A bare
+        "23andMe" substring mention without one of the canonical prefixes is
+        rejected (see ``_CANONICAL_PREFIXES`` rationale).
         """
         try:
             with file_path.open("r", encoding="utf-8") as fh:
@@ -71,7 +93,7 @@ class TwentyThreeAndMeParser(GenotypeParser):
                         return False
                     if not line.startswith("#"):
                         return False
-                    if line.startswith(_CANONICAL_PREFIX):
+                    if any(line.startswith(p) for p in _CANONICAL_PREFIXES):
                         return True
         except (OSError, UnicodeDecodeError):
             return False

{allelix-2.2.2.dist-info → allelix-2.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: allelix
-Version: 2.2.2
+Version: 2.2.3
 Summary: Open-source genotype analysis toolkit. Format-agnostic ingestion, database-agnostic annotation, offline-first.
 Author: Allelix
 Maintainer-email: dial481 <dial481@users.noreply.github.com>
@@ -190,8 +190,10 @@ disease findings. Wherever you write them via `--output <path>`,
 that's where they sit until you delete them. Allelix doesn't
 auto-clean and won't warn you when you write to `/tmp/` or any
 other shared location. Treat the files as personal data: read them,
-move them somewhere you control, or delete when you're done. A
-data-lifecycle subcommand is planned for v2.1.
+move them somewhere you control, or delete when you're done.
+`allelix db clean` (shipped in v2.2.0) handles the cache side of
+the lifecycle; output reports are still the user's responsibility
+to manage.
 
 ## Configuration
 

{allelix-2.2.2.dist-info → allelix-2.2.3.dist-info}/RECORD

@@ -8,7 +8,7 @@ allelix/annotators/alphamissense.py,sha256=GT5y35jQ97oZW3X9SqJgTcmqYn-GgK2_WbSvl
 allelix/annotators/base.py,sha256=emwF6-zs8I7v_m24bC_ocsUeppp2gP9vtGCfMyQQOTo,7994
 allelix/annotators/cadd.py,sha256=BT7JqbHabdEhz9PiQ7nzPJjv25lu3tMDMuoMYQfsUf4,11065
 allelix/annotators/clinvar.py,sha256=VUyDDf3L5VT_MRrTHVXZZKl9Z6RFln3TvRAky9itxv4,35894
-allelix/annotators/gnomad.py,sha256=aJUvHFGAgh3M5lo6NK0eDL30xjSuAbbcnJlxHAsyIIQ,15013
+allelix/annotators/gnomad.py,sha256=A4HGEvZT-x-OWxJwXQ8LYs5T3XGYwlwcP7ZAUkRudLI,14725
 allelix/annotators/gwas.py,sha256=ZsZokbb65HDdJON_oMlIprny0LexrHvWDQPNjClxc5M,18786
 allelix/annotators/pharmgkb.py,sha256=1knBbMtDoZd4ZdH3gIeAfr63tZsfMOaOkImrKE3KxHQ,21008
 allelix/annotators/snpedia.py,sha256=WI0eaSKkr4qoQChpayyqkPLGE5XX_l8L4ZWIhu1zDmY,13844
@@ -48,7 +48,7 @@ allelix/parsers/ftdna_illumina.py,sha256=ZbejAa6vWT8wdwkdpCzsXA7g_1WoltbUEpO2K5t
 allelix/parsers/livingdna.py,sha256=18-3Vjc3L7fVR3gHGjrVnPPEqC0Ype2nOb4Ltz1VzRc,5368
 allelix/parsers/myhappygenes.py,sha256=3i8yKMA1WBs6vBPFNkIm7q5hVqNJBu_CZUmlyDMp-QE,4911
 allelix/parsers/myheritage.py,sha256=N6aCdj9SD0tiW8S_yylNlVZy8CrUGazdQvTpr7rT29Y,4311
-allelix/parsers/twentythreeandme.py,sha256=cdTj8YjFff8nYB4V5z_SwtV2l6FAmhyRiVzOytbsSHc,5608
+allelix/parsers/twentythreeandme.py,sha256=757nA1mw7aEsG4nOdOFbHdKbwIIz0p05oaSzI90x268,6932
 allelix/parsers/vcf.py,sha256=6KhqEyb29pL58ZniaC7zm87QELudEJG_R_VwLZeENNM,28105
 allelix/reports/__init__.py,sha256=9WK8hR03DV1dP2bM7AloJfzSOTVQoFd6AOnaKjQyScs,1408
 allelix/reports/_pipeline.py,sha256=SkT2WqnakB2I60Z-BCox6SIrmQCSFNCK_Na8Kxuggrs,40925
@@ -61,9 +61,9 @@ allelix/reports/terminal.py,sha256=cPdG3mwUsmty26WIdfbkLtgPF6CTr91ZMk7o2siTumQ,1
 allelix/utils/__init__.py,sha256=ALRku0gzoAbTA6gipnMr0aEFYRyI2DUaTB25DHkXXLw,138
 allelix/utils/allele.py,sha256=d7cT1b-XxcD6jID9bLDhvVCOxoK_2Ga4-nXcHRN-h4Q,9620
 allelix/utils/build_detect.py,sha256=Sxlg0OXyL9vDuJAl04pQZQ8oizSVeUV4Gte9tVEvKu0,8718
-allelix-2.2.2.dist-info/licenses/LICENSE,sha256=QWRhgdtPnw-Xay85rhILM_cxYofYh91NfTOWwI_AOQI,34841
-allelix-2.2.2.dist-info/METADATA,sha256=rVzYuKPpBDujZaFbuNjvwirGF3QmwAvExzhIvw26Epk,31707
-allelix-2.2.2.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
-allelix-2.2.2.dist-info/entry_points.txt,sha256=n75_TahJixgNPt1Xhk2V1wDR3RNCiKq4xAKa4_skYNI,45
-allelix-2.2.2.dist-info/top_level.txt,sha256=2SoebaRt4WWVq8Ynk-5uNN1ATE_dJtOqsgj39oCHVbk,8
-allelix-2.2.2.dist-info/RECORD,,
+allelix-2.2.3.dist-info/licenses/LICENSE,sha256=QWRhgdtPnw-Xay85rhILM_cxYofYh91NfTOWwI_AOQI,34841
+allelix-2.2.3.dist-info/METADATA,sha256=9KMuC0LRIevmywag657PaoUeuCCOU3tMbPEyTohkh10,31800
+allelix-2.2.3.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+allelix-2.2.3.dist-info/entry_points.txt,sha256=n75_TahJixgNPt1Xhk2V1wDR3RNCiKq4xAKa4_skYNI,45
+allelix-2.2.3.dist-info/top_level.txt,sha256=2SoebaRt4WWVq8Ynk-5uNN1ATE_dJtOqsgj39oCHVbk,8
+allelix-2.2.3.dist-info/RECORD,,