aboutsummaryrefslogtreecommitdiff
path: root/test/test_citation.ml
diff options
context:
space:
mode:
authorLukasz Kasprzak <lukas@labunix.xyz>2026-08-26 13:30:02 +0200
committerLukasz Kasprzak <lukas@labunix.xyz>2026-08-26 13:30:02 +0200
commit9cc763c169a6ce4ebbdbed506c5eb2dad1f9f3c1 (patch)
treeb38d6e418c7de49766478a47f5654086157e66e0 /test/test_citation.ml
parent1a3046e2a3793fe52ec518818b19a6f15aadbb75 (diff)
downloadcolitur-9cc763c169a6ce4ebbdbed506c5eb2dad1f9f3c1.tar.gz
colitur-9cc763c169a6ce4ebbdbed506c5eb2dad1f9f3c1.zip
fix(citation): recognise English-canonical OF books, verse sub-letters
35% of OF citation fields (259/730 on colitur readings --rite of 2026) printed unconverted -- 1 John renders on 2 January but not 3 January. Two independent causes, both in the citation/siglum path, neither in the OF data itself: 1. Book.table only ever surveyed the three EF citation-bearing files, so 345 references citing a book no EF file happens to use (Job, Ruth, Judges, 1/2 Samuel, 1/2 Chronicles, 1/2 Maccabees, Baruch, Ecclesiastes, Habakkuk, Haggai, Nahum, Zechariah, Zephaniah, Deuteronomy, Amos, Micah, Lamentations, Ezra, Joshua, 2/3 John, Jude, Philemon, plus "Isaiah"/"Jeremiah"/"Ezekiel"/"Malachi"/"Mat"/ "The Acts"/"Tobit"/"Song of Solomon" spelling variants of books EF already knows) failed as "unknown book". Added as a new, separate of_lectionary_table rather than folded into the EF-surveyed table: none of these 25 new books is attested in the EF's own scans, and lang/la.ini's own header refuses to fabricate an uncited Latin title, so they are resolvable (parse + render, falling back to their own English spelling) but deliberately excluded from Book.all -- test_lang_coverage.ml's la.ini-completeness promise is preserved exactly for the ids it already covered, not silently weakened. 2. Parse's grammar could not read a verse number carrying a lectionary sub-verse letter ("11a", "1bcde") at all -- the dominant remaining failure shape once (1) was fixed. verse_range now carries a verse_num { n; suffix } on each boundary, PRESERVED through rendering rather than dropped (dropping would silently lose real precision the source text carries). Chapter numbers are untouched (nothing in the data ever attaches a letter to one). A third, subtler bug surfaced by (1): registering "jude"/"philemon"/ "2 John"/"3 John" exposed Parse's existing "leading comma-number is a chapter" heuristic misreading a single-chapter book's bare verse list ("Jude 17,20b-25") as chapter 17 -- a wrong PARSE, worse than the previous safe "unknown book" failure. Book.is_single_chapter now tells Parse to skip that heuristic for the four one-chapter books and default to chapter 1. Residual, honestly enumerated rather than forced to zero: 41 distinct references (of 1540) are hyphenated ranges crossing a chapter boundary ("2:29-3:6") -- a Parse.t shape verse_range/part do not represent, a type restructuring deliberately not attempted this task. Pinned exactly by the new test_citation_coverage_of.ml, both directions (a new failure or one of these 41 starting to convert both go red), and disclosed in data/of/lectionary.sexp's own regenerated provenance header (tools/ bootstrap_lectionary_of.ml now runs the same parser at generation time and names the count and the set). Verified EF-unaffected: git diff v1.0.0..HEAD -- lib/kernel/ lib/rites/rite_ef/ data/ef/ is empty, and `colitur day`/`readings` output for 2027 is byte-identical against the pre-fix binary.
Diffstat (limited to 'test/test_citation.ml')
-rw-r--r--test/test_citation.ml9
1 files changed, 6 insertions, 3 deletions
diff --git a/test/test_citation.ml b/test/test_citation.ml
index dae4610..3cbc8c6 100644
--- a/test/test_citation.ml
+++ b/test/test_citation.ml
@@ -267,10 +267,11 @@ module P = Colitur_citation.Parse
(* Render a parse back to a debug string so a test can assert shape
compactly: "book|chapter:v-v,v-v|chapter:v". *)
let show (t : P.t) =
+ let num (v : P.verse_num) = string_of_int v.P.n ^ v.P.suffix in
let range (r : P.verse_range) =
match r.P.last with
- | None -> string_of_int r.P.first
- | Some l -> Printf.sprintf "%d-%d" r.P.first l
+ | None -> num r.P.first
+ | Some l -> Printf.sprintf "%s-%s" (num r.P.first) (num l)
in
let part (p : P.part) =
Printf.sprintf "%d:%s" p.P.chapter
@@ -396,7 +397,9 @@ let test_subst_unknown_placeholder_alone () =
the assertion isolates exactly the numeral and nothing else. *)
let roman_of n =
let luke = match B.of_token "Luke" with Some id -> id | None -> assert false in
- let t : P.t = { P.book = luke; parts = [ { P.chapter = n; verses = [ { P.first = 1; last = None } ] } ] } in
+ let t : P.t =
+ { P.book = luke; parts = [ { P.chapter = n; verses = [ { P.first = { P.n = 1; suffix = "" }; last = None } ] } ] }
+ in
let style = R.style_of_fields [ ("book_sep", ""); ("chapter_verse", "{chapter_roman}") ] in
R.render style ~names:(fun _ _ -> "") t