From 9b8821f7b914c94f5b2c8eeda05407ee921b3d5a Mon Sep 17 00:00:00 2001 From: Lukasz Kasprzak Date: Wed, 26 Aug 2026 13:30:09 +0200 Subject: feat(of-lectionary): disclose the citation-conversion residual in the header Fix option (c) from the I2 review finding, done alongside the parser fix itself rather than deferred: tools/bootstrap_lectionary_of.ml now runs every emitted reference through Colitur_citation.Parse.parse at generation time and adds a fourth COVERAGE item plus a named listing to data/of/lectionary.sexp's own header, so the 41-reference residual (all chapter-crossing hyphen ranges, see the citation-fix commit) is disclosed in the artifact a reader actually opens, not only in a task report or test file. Regenerated against the pinned lectio snapshot (dune exec tools/bootstrap_lectionary_of.exe -- ../lectio/internal/caldata/ of-lectionary.ini data/of/lectionary.sexp); diffed against the pre-change file to confirm the change is header-only, zero lines removed, the sexp payload byte-identical. Re-pins the file's own SHA-256 in test_lectionary_of.ml accordingly (re-derived with sha256sum, not transcribed from generator stdout, matching that test's own stated discipline). --- data/of/lectionary.sexp | 56 ++++++++++++++++++++++++++++++++++++++++ test/test_lectionary_of.ml | 9 ++++++- tools/bootstrap_lectionary_of.ml | 49 ++++++++++++++++++++++++++++++++++- tools/dune | 7 ++++- 4 files changed, 118 insertions(+), 3 deletions(-) diff --git a/data/of/lectionary.sexp b/data/of/lectionary.sexp index 167a7c7..8cc1d63 100644 --- a/data/of/lectionary.sexp +++ b/data/of/lectionary.sexp @@ -75,9 +75,65 @@ ; ferial (Lectionary_of.readings' own step 2 -> step 3) -- this is ; OLM norms working as designed for a saint with no proper of ; their own, not a gap in this data. +; (4) Citation-siglum conversion (fix wave I2, 2026-08-26 review): of +; 1540 emitted (First, Gospel) citation fields, 41 distinct +; references (out of the full 1540) do not parse -- every one a +; hyphen range that crosses a chapter boundary ("2:29-3:6"), a +; {!Colitur_citation.Parse.t} shape this parser's [part]/ +; [verse_range] types do not represent, deliberately not built +; this task (see book.ml's own [is_single_chapter] neighbourhood +; for what WAS fixed: 345 previously-unregistered book names and +; verse sub-letter markers, both closed at the parser/book-table +; level, not here). Such a reference still prints, verbatim, +; never a crash or a dropped citation -- {!Colitur_citation.Sigla +; .format}'s own documented contract on a parse miss. Pinned +; exactly, both directions, by test/test_citation_coverage_of.ml. +; Named below. ; Regenerate with: ; eval $(opam env) && dune exec tools/bootstrap_lectionary_of.exe -- ../lectio/internal/caldata/of-lectionary.ini data/of/lectionary.sexp ; Unmapped lectio bases (0): +; Citations that do not parse (41 distinct, all chapter-crossing ranges): +; 1 Corinthians 12:31-13:13 +; 1 John 1:5-2:2 +; 1 John 2:29-3:6 +; 1 John 3:22-4:6 +; 1 John 4:19-5:4 +; 2 Corinthians 3:15-4:1,3-6 +; 2 Samuel 18:9-10,14b,24-25a,30-19:3 +; Colossians 1:24-2:3 +; Ecclesiastes 11:9-12:8 +; Ephesians 4:32-5:8 +; Exodus 11:10-12:14 +; Exodus 14:21-15:1 +; Ezekiel 2:8-3:4 +; Galatians 4:22-24,26-27,31-5:1 +; Genesis 1:1-2:2 +; Genesis 1:20-2:4a +; Habakkuk 1:12-2:4 +; Hebrews 7:25-8:6 +; Isaiah 52:13-53:12 +; Isaiah 8:23b-9:3 +; John 15:26-16:4a +; John 18:1-19:42 +; Jonah 1:1-2:2,11 +; Luke 7:36-8:3 +; Malachi 1:14b-2:2b,8-10 +; Mark 2:23-3:6 +; Mark 8:34-9:1 +; Matthew 10:34-11:1 +; Matthew 18:21-19:1 +; Matthew 9:35-10:1,5a,6-8 +; Matthew 9:36-10:8 +; Numbers 13:1-2,25-14:1,26a-29a,34-35 +; Philippians 3:17-4:1 +; Revelation 20:1-4,11-21:2 +; Sirach 27:30-28:7 +; The Acts 12:24-13:5a +; The Acts 17:15,22-18:1 +; The Acts 7:51-8:1a +; Wisdom 11:22-12:2 +; Wisdom 2:23-3:9 +; Wisdom 7:22b-8:1 ; Temporal_of slugs (2004-2051) with no lectionary entry (1, informational -- ; most are the Christmas-season/late-Advent date-vs-weekday gap named above): ; of-nativity diff --git a/test/test_lectionary_of.ml b/test/test_lectionary_of.ml index 03838be..a9fcdb1 100644 --- a/test/test_lectionary_of.ml +++ b/test/test_lectionary_of.ml @@ -178,8 +178,15 @@ let sha256_of_file path = don't transcribe it from generator stdout" discipline test_calendar_of_data.ml's own [test_sha256] already follows. *) let test_sha256_pinned () = + (* Fix wave I2 (final-review.md, 2026-08-25-colitur-of-phases-3-5): the + hash changed because the header grew a new "Citation-siglum + conversion" census -- the payload (parse this test's siblings assert + against) is byte-identical; only the disclosure comment above it is + new. Re-derived with `sha256sum data/of/lectionary.sexp`, not + transcribed from generator stdout, the same discipline this test's own + header states. *) Alcotest.(check string) "data/of/lectionary.sexp SHA-256" - "2277e3dc302e853d78b72608884f59eb67671bfdcca4f5e4c99358ee12811f89" (sha256_of_file lectionary_path) + "aba7817ace8add740a5722f5fdb401a119869545eda9082e41e203df4ac27ee5" (sha256_of_file lectionary_path) (* lectio's OWN of-lectionary.ini SHA-256, pinned inside data/of/ lectionary.sexp's own provenance header (tools/bootstrap_lectionary_of diff --git a/tools/bootstrap_lectionary_of.ml b/tools/bootstrap_lectionary_of.ml index da37bd9..a679b01 100644 --- a/tools/bootstrap_lectionary_of.ml +++ b/tools/bootstrap_lectionary_of.ml @@ -825,6 +825,34 @@ let temporal_day_gap ~lectionary ~year_start = done; (!count, !total, List.rev !misses) +(* Fix wave I2 (final-review.md, 2026-08-25-colitur-of-phases-3-5): every + reference this file emits, run through the SAME parser [colitur readings] + itself uses to convert to Latin sigla ({!Colitur_citation.Sigla.format} + -> {!Colitur_citation.Parse.parse} on a miss). Disclosed here, at + generation time, rather than left for a reader to discover as a silent + "- | -"-shaped surprise or an unconverted English fragment sitting next + to Latin ones -- this is what I2's own review finding asked for as the + minimum acceptable fix if full conversion could not be reached, and it + was not: see test/test_citation_coverage_of.ml for the pinned, exact + residual and book.ml's own citation for why it remains (chapter-crossing + hyphen ranges -- "2:29-3:6" -- a {!Colitur_citation.Parse.t} shape this + parser does not represent, deliberately not built this task; every OTHER + shape this file's data used to expose, including 345 previously- + unregistered book names, is now fixed at the source). *) +let citation_conversion_census lect = + let total = ref 0 and bad = ref [] in + List.iter + (fun (_slug, cits) -> + List.iter + (fun (c : Citation.t) -> + incr total; + match Colitur_citation.Parse.parse c.Citation.reference with + | Ok _ -> () + | Error _ -> if not (List.mem c.Citation.reference !bad) then bad := c.Citation.reference :: !bad) + cits) + (Lectionary.entries lect); + (!total, List.sort compare !bad) + let sha256 path = let ic = Unix.open_process_in (Printf.sprintf "sha256sum %s" (Filename.quote path)) in let line = try input_line ic with End_of_file -> die "sha256sum failed" in @@ -846,6 +874,7 @@ let () = let gap_count, gap_total, gap_misses = temporal_day_gap ~lectionary:lect ~year_start:Rite_of.Temporal_of.year_start in + let cit_total, cit_bad = citation_conversion_census lect in let oc = open_out dst in Printf.fprintf oc "; data/of/lectionary.sexp -- OF (2002) temporal + sanctoral lectionary\n\ @@ -926,15 +955,33 @@ pairs -> %d colitur slugs mapped, %d ini bases genuinely excluded (structurally\ ; ferial (Lectionary_of.readings' own step 2 -> step 3) -- this is\n\ ; OLM norms working as designed for a saint with no proper of\n\ ; their own, not a gap in this data.\n\ + ; (4) Citation-siglum conversion (fix wave I2, 2026-08-26 review): of\n\ + ; %d emitted (First, Gospel) citation fields, %d distinct\n\ + ; references (out of the full %d) do not parse -- every one a\n\ + ; hyphen range that crosses a chapter boundary (\"2:29-3:6\"), a\n\ + ; {!Colitur_citation.Parse.t} shape this parser's [part]/\n\ + ; [verse_range] types do not represent, deliberately not built\n\ + ; this task (see book.ml's own [is_single_chapter] neighbourhood\n\ + ; for what WAS fixed: 345 previously-unregistered book names and\n\ + ; verse sub-letter markers, both closed at the parser/book-table\n\ + ; level, not here). Such a reference still prints, verbatim,\n\ + ; never a crash or a dropped citation -- {!Colitur_citation.Sigla\n\ + ; .format}'s own documented contract on a parse miss. Pinned\n\ + ; exactly, both directions, by test/test_citation_coverage_of.ml.\n\ + ; Named below.\n\ ; Regenerate with:\n\ ; eval $(opam env) && dune exec tools/bootstrap_lectionary_of.exe -- %s %s\n" src (sha256 src) (List.length secs) (List.length resolved) report.mapped (List.length excluded_bases) (List.length report.unmapped) (List.length entries) gap_total gap_count (List.length report.unmapped) (List.length resolved) (Hashtbl.length sanctoral_slugs) report.sanctoral_passthrough - (Hashtbl.length sanctoral_slugs - report.sanctoral_passthrough) src dst; + (Hashtbl.length sanctoral_slugs - report.sanctoral_passthrough) + cit_total (List.length cit_bad) cit_total src dst; Printf.fprintf oc "; Unmapped lectio bases (%d):\n" (List.length report.unmapped); List.iter (fun b -> Printf.fprintf oc "; %s\n" b) report.unmapped; + Printf.fprintf oc "; Citations that do not parse (%d distinct, all chapter-crossing ranges):\n" + (List.length cit_bad); + List.iter (fun r -> Printf.fprintf oc "; %s\n" r) cit_bad; Printf.fprintf oc "; Temporal_of slugs (2004-2051) with no lectionary entry (%d, informational --\n\ ; most are the Christmas-season/late-Advent date-vs-weekday gap named above):\n" (List.length uncovered_temporal); diff --git a/tools/dune b/tools/dune index 40e9836..7cf4440 100644 --- a/tools/dune +++ b/tools/dune @@ -34,9 +34,14 @@ ; sanctoral_slugs] reads data/of/calendar-2002.sexp and data/of/amendments/ ; by a repo-root-relative path, unlike bootstrap_lectionary.ml's own ; source/dest arguments, which are caller-supplied). +; `colitur_citation` (fix wave I2, final-review.md): the emitted header now +; runs every emitted reference through Colitur_citation.Parse.parse itself +; and names the count and the exact set that fail, so the limit is +; disclosed in the artifact a reader actually sees rather than only in a +; task report. (executable (name bootstrap_lectionary_of) - (libraries colitur_kernel rite_of unix sexplib)) + (libraries colitur_kernel colitur_citation rite_of unix sexplib)) ; Task 6 (2026-08-21-colitur-celebrant-rubrics-phase1): turns pdftotext's ; -layout dump of the Latin Mass Society Ordo into test/fixtures/ -- cgit v1.3