diff options
Diffstat (limited to 'test/test_citation_coverage_of.ml')
| -rw-r--r-- | test/test_citation_coverage_of.ml | 109 |
1 files changed, 48 insertions, 61 deletions
diff --git a/test/test_citation_coverage_of.ml b/test/test_citation_coverage_of.ml index 7badd96..af8d161 100644 --- a/test/test_citation_coverage_of.ml +++ b/test/test_citation_coverage_of.ml @@ -3,48 +3,46 @@ (* Fix wave I2 (final-review.md, 2026-08-25-colitur-of-phases-3-5): the OF counterpart of test_citation_coverage.ml. That file's own header states the rule this one follows: "every citation the engine can emit must - parse". EF reaches zero unconverted citations; OF does not, and this - file is the honest record of exactly where it falls short, mirroring the - review's own explicit instruction -- "enumerate them rather than - lowering the bar to fit". + parse". At the time this file was first written, EF reached zero + unconverted citations and OF did not; this file was the honest record of + exactly where it fell short. - MEASURED, not estimated: before this fix wave, 259 of 730 citation - fields in `colitur readings --rite of 2026` (35%) printed unconverted -- - 345 distinct book spellings unregistered ({!Colitur_citation.Book}), - plus verse sub-letter markers ("11a") and a handful of single-chapter- - book misreads ({!Colitur_citation.Book.is_single_chapter}) the parser - could not read at all. All of that is now fixed at the source (book.ml's - own [of_lectionary_table] and parse.ml's own [verse_num]/[single_chapter] - additions), closing every genuinely fixable shape. What remains, walking - the FULL data/of/lectionary.sexp (not merely what one civil year happens - to observe -- a stricter check than EF's own year-walk, and the same one - tools/bootstrap_lectionary_of.ml's own generated header now runs and - discloses): 41 distinct references, out of 1542 total, EVERY ONE a - hyphenated range crossing a chapter boundary ("2:29-3:6", "1 John") -- - a {!Colitur_citation.Parse.t} shape [part]/[verse_range] do not - represent (a [part] is one chapter and a list of within-chapter ranges; - representing a cross-chapter range would need restructuring that type - and {!Colitur_citation.Render}'s own consumption of it), deliberately - not built this task. + MEASURED, not estimated: before fix wave I2, 259 of 730 citation fields + in `colitur readings --rite of 2026` (35%) printed unconverted -- 345 + distinct book spellings unregistered ({!Colitur_citation.Book}), plus + verse sub-letter markers ("11a") and a handful of single-chapter-book + misreads ({!Colitur_citation.Book.is_single_chapter}) the parser could + not read at all. All of that was fixed at the source (book.ml's own + [of_lectionary_table] and parse.ml's own [verse_num]/[single_chapter] + additions). What remained, walking the FULL data/of/lectionary.sexp (not + merely what one civil year happens to observe -- a stricter check than + EF's own year-walk, and the same one tools/bootstrap_lectionary_of.ml's + own generated header runs and discloses): a hyphenated verse range whose + two endpoints lie in different chapters ("2:29-3:6", "1 John") -- a + {!Colitur_citation.Parse.t} shape [part]/[verse_range] did not + represent. Fix wave I7 (2026-08-26) grew the population from 1542 to + 1725 citation fields (a new Second-reading extraction) and the residual + from 41 to 49 references, same shape, no new failure mode. - UPDATED, fix wave I7 (final-review.md, 2026-08-25-colitur-of-phases-3-5, - 2026-08-26): {!Rite.t.citation_shapes} (kernel change) plus - tools/bootstrap_lectionary_of.ml's own [cite] now also extract a Second - reading on every Sunday-cycle (Sunday/solemnity) entry, so the total grew - 1542 -> 1725 (+183, exactly the count data/of/lectionary.sexp's own - header COVERAGE (5) now discloses) and the unparseable residual grew - 41 -> 49: the same chapter-crossing shape, now also hit by 8 of the 183 - new Second-reading references. Not a new failure MODE, just a bigger - population drawing from the same, already-understood one -- confirmed - below by [looks_chapter_crossing], unchanged, still holding for all 49. + CLOSED (W4, this task): {!Colitur_citation.Parse.verse_end} now lets a + range's [last] endpoint name its own, later chapter, and + {!Colitur_citation.Render}'s [one_range] renders it back through the + part's own [chapter_verse] template. Every one of the 49 pinned + references now parses and round-trips -- including the COMPOUND shape + ("Matthew 9:35-10:1,5a,6-8": a crossing range followed by further, + same-chapter verse references in the same comma list) and a crossing + that is not the list's first or only piece ("2 Samuel + 18:9-10,14b,24-25a,30-19:3"). The residual below is therefore now EMPTY, + over the full 1725-field population -- measured, not merely no longer + observed on a sample. - This file pins that residual EXACTLY -- not merely "at least these fail" - -- so it fails loudly in BOTH directions: a NEW unconverted reference - appearing (a regression) and one of these 49 starting to convert (this - list going stale, e.g. because a future task builds cross-chapter - support) are both caught, the same discipline every allow-list in this - project's suite already follows (`expected_rows`, `expected_bands`, the - litcal/missalemeum comparators). *) + The pinning discipline is kept rather than deleted: this file still + fails LOUDLY, in both directions, if the unconverted set ever stops + being empty -- a real regression (a genuinely new unparseable shape) and + a silently corrupted lectionary file are both caught by the same + mechanism every allow-list in this project's suite already follows + (`expected_rows`, `expected_bands`, the litcal/missalemeum + comparators). *) let lectionary_path = "../data/of/lectionary.sexp" @@ -53,25 +51,12 @@ let lectionary () = | Ok l -> l | Error e -> Alcotest.failf "%s: %s" lectionary_path e -(* The exact, pinned residual -- copied from data/of/lectionary.sexp's own - generated "Citations that do not parse" listing, itself produced by the - SAME {!Colitur_citation.Parse.parse} call this test makes, so the two - can never silently drift apart without one of them visibly failing to - regenerate/re-test clean. *) -let known_cross_chapter_residual = - [ "1 Corinthians 10:31-11:1"; "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"; "1 Thessalonians 3:12-4:2"; "2 Corinthians 3:15-4:1,3-6"; - "2 Corinthians 4:13-5:1"; "2 Samuel 18:9-10,14b,24-25a,30-19:3"; "2 Thessalonians 1:11-2:2"; - "2 Thessalonians 2:16-3:5"; "2 Timothy 3:14-4:2"; "Colossians 1:24-2:3"; "Ecclesiastes 11:9-12:8"; - "Ephesians 4:30-5:2"; "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"; - "James 3:16-4:3"; "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" ] +(* The exact, pinned residual -- EMPTY since W4 closed the cross-chapter gap + (see this file's own header). Kept as a named binding, not inlined as + [[]] at each use site, so a future partial regression has one place to + list what it could not fix, exactly as the pre-W4 version of this file + did for the 49 references it once named here. *) +let known_cross_chapter_residual = [] (* Every failure this walk finds really is a chapter-crossing hyphen range (a "-" whose right side itself contains a ":") -- checked mechanically, @@ -107,8 +92,8 @@ let test_of_citations_convert_or_are_the_known_cross_chapter_residual () = Alcotest.(check int) "1725 citation fields in data/of/lectionary.sexp today -- if this changes, the \ pinned residual below may need updating too, not just this count" 1725 !total; - Alcotest.(check (list string)) "the unconverted set is EXACTLY the known cross-chapter residual, no \ - more and no fewer" + Alcotest.(check (list string)) "the unconverted set is EXACTLY the known cross-chapter residual (empty, \ + since W4) -- no more and no fewer" (List.sort compare known_cross_chapter_residual) bad; List.iter (fun r -> @@ -119,7 +104,9 @@ let test_of_citations_convert_or_are_the_known_cross_chapter_residual () = (* Everything OUTSIDE the pinned residual round-trips through Sigla, the same structural (not textual) comparison test_citation_coverage.ml's own - EF version makes, and for the identical reason its own header gives. *) + EF version makes, and for the identical reason its own header gives. + Since the residual is now empty, this exercises the FULL 1725-field + population, cross-chapter shapes included. *) let test_round_trip_outside_the_residual () = let sg = Colitur_citation.Sigla.make ~style:Colitur_citation.Render.default_style |