path: root/test/test_oracle.ml

(* Task 16: oracle harness vs missalemeum (sibling project's snapshot of
   missalemeum.com/Divinum Officium data), EF only, 2026-2027 -- validation
   layer 4 of the design spec's five (colitur CLAUDE.md "Validation" section;
   layer 3, the lectio differential, is test_differential.ml, already green).

   *** WHY THIS LAYER EXISTS, AND WHAT IT CAN DO THAT THE LECTIO DIFFERENTIAL
   CANNOT (test_differential.ml's own header comment, limit 1) ***

   The lectio differential compares colitur against data colitur was itself
   BOOTSTRAPPED from (data/ef/sanctoral.sexp comes from lectio's tridentine-
   calendar.ini) -- it cannot catch an error inherited from that bootstrap,
   and it explicitly does not compare commemorations at all (lectio's
   trailing tokens are losing candidates, not an RG 111 admitted set, per
   that file's own limit 1). missalemeum is INDEPENDENT of colitur's
   bootstrap chain, and its JSON carries a real admitted-commemorations
   array (its own RG 111-shaped selection, not lectio's rejects) -- so this
   file compares THREE axes the lectio differential cannot touch at all:
   rank, colour (as SET membership, see below), and commemoration presence/
   count. Slug IDENTITY is deliberately NOT compared (the brief: needs a
   title->slug mapping, which is the data audit's business -- see the task
   report -- not this automated comparator's).

   *** THE FIXTURE'S OWN SHAPE (fixtures/missalemeum-ef-2026-2027.txt,
   fixtures/missalemeum-ef-2026-2027.provenance, tools/
   extract_missalemeum_oracle.py) ***

   info.id (e.g. "sancti:01-02:1:w") encodes the PROPERS REUSED that day,
   not the day's own rank or colour -- 137 of 730 days (19%) disagree
   between the id-embedded rank and info.rank itself (task brief's own
   premise was wrong here; the brief's extraction note has been corrected).
   This file, like the extraction script, reads ONLY info.rank and
   info.colors, never parses anything out of info.id.

   info.colors is an ARRAY -- 14 of 730 days carry two colours (rose+violet
   on Gaudete/Laetare per RG 131's indult, red+violet on Palm Sunday, black+
   violet on Good Friday, violet+white on Holy Saturday -- one colour per
   liturgical ACTION within that one civil day, which colitur's one-colour-
   per-day model cannot represent, register §3b's own RG 126 note). So the
   colour axis below is MEMBERSHIP (colitur's single colour must be one of
   the oracle's set), never equality.

   Four days carry more than one Mass in the JSON array (Christmas, All
   Souls) -- the extraction script takes entry[0] throughout, VERIFIED
   (not assumed) identical to every other Mass of the same day on every
   field this file reads (see that script's own header and the task
   report).

   *** THE ALLOW-LIST (data/ef/expected-divergences-missalemeum.sexp) ***

   A SEPARATE file from data/ef/expected-divergences.sexp (the lectio
   allow-list): the two oracles disagree with colitur in different places
   and for different reasons, and this file's own convention differs in one
   deliberate way -- [verdict] is not always "colitur". Some entries are
   genuine DATA GAPS this task found and could not fix here (data/ef/
   sanctoral.sexp is bootstrapped from lectio, which is itself missing the
   entries; RG 110's inseparable-Peter/Paul commemoration is unimplemented
   code, a real feature this task did not build) -- honestly verdicted
   [missalemeum] (colitur is short a feature or a row, not right), never
   silently absorbed as if colitur were correct. TWO entries (M11 and
   M13) are [verdict open] -- CORRECTED, final fix wave, item 7: this
   comment previously said "one entry (M13)", missing M11, whose own
   verdict was changed from [colitur] to [open] in fix round 1 (see M11's
   own entry below for why) but this summary was never updated to match.
   Both are adjudicated as unresolved, not resolved either way -- the
   brief's own explicit permission ("say so as an open item") used for
   real, not defaulted past. See the task report for every entry's full
   reasoning and primary-source citation. *)

module Cal = Colitur_kernel.Calendar
module Layer = Colitur_kernel.Layer
module Overlay = Colitur_kernel.Overlay
module LD = Colitur_kernel.Liturgical_day
module Slug = Colitur_kernel.Slug
module Date = Colitur_kernel.Date
module Cel = Colitur_kernel.Celebration
module Colour = Colitur_kernel.Colour
module V = Rite_ef.Vocab_ef

(* Same relative paths test_differential.ml uses: dune test runs from
   _build/default/test/. *)
let sanctoral_path = "../data/ef/sanctoral.sexp"
let adjustments_path = "../data/ef/adjustments.sexp"
let fixture_path = "fixtures/missalemeum-ef-2026-2027.txt"
let allow_list_path = "../data/ef/expected-divergences-missalemeum.sexp"

(* fixtures/missalemeum-ef-2026-2027.provenance carries the same digest and
   the exact regeneration command. Asserted (not merely documented) for the
   same reason test_differential.ml's own [fixture_sha256] is: a hand-edit
   or partial re-extraction would otherwise silently turn the oracle into
   an unlabelled snapshot of whatever someone last ran. *)
let fixture_sha256 = "718eff1a03fa09c3927ef18d19fe7921c2d4d7611890c22566058b81fd7cc5ea"

(* Identical technique to test_differential.ml's own [sha256_of_file]
   (that file's own comment explains why: shelling out to [sha256sum]
   rather than adding a crypto library dependency Task 15/16's frozen deps
   do not include). Duplicated, not shared, for the same reason
   [real_layer] below is -- neither file exposes an .mli the other could
   depend on, and this is three lines. *)
let sha256_of_file path =
  let tmp = Filename.temp_file "colitur_oracle_sha256" ".txt" in
  Fun.protect
    ~finally:(fun () -> try Sys.remove tmp with Sys_error _ -> ())
    (fun () ->
      let cmd = Printf.sprintf "sha256sum %s > %s" (Filename.quote path) (Filename.quote tmp) in
      let rc = Sys.command cmd in
      if rc <> 0 then Alcotest.failf "sha256sum exited %d for %s (is it on PATH?)" rc path;
      let ic = open_in tmp in
      let line =
        try input_line ic
        with End_of_file ->
          close_in ic;
          Alcotest.failf "sha256sum produced no output for %s" path
      in
      close_in ic;
      match String.index_opt line ' ' with
      | Some i -> String.sub line 0 i
      | None -> Alcotest.failf "unexpected sha256sum output for %s: %S" path line)

let real_layer () =
  let layer =
    match Layer.load V.rank_of_sexp sanctoral_path with
    | Ok l -> l
    | Error e -> Alcotest.failf "%s: failed to load: %s" sanctoral_path e
  in
  let overlay =
    match Overlay.load V.rank_of_sexp adjustments_path with
    | Ok o -> o
    | Error e -> Alcotest.failf "%s: failed to load: %s" adjustments_path e
  in
  let layer, diagnostics = Overlay.apply layer overlay in
  Alcotest.(check (list string)) "the committed overlay applies cleanly, no diagnostics" []
    (List.map Overlay.diagnostic_to_string diagnostics);
  layer

(* ---------------------------------------------------------------------- *)
(* The oracle side: one line per day, as tools/extract_missalemeum_oracle  *)
(* .py's own header documents.                                            *)
(* ---------------------------------------------------------------------- *)

type oracle_row = {
  o_date : string;
  o_rank : int;
  o_colours : char list;
  o_title : string;
  o_commemorations : string list;
  o_displaced : string list;
}

let explode s = List.init (String.length s) (String.get s)

let split_list_field f = if f = "-" then [] else String.split_on_char ';' f

let oracle_row_of_line line =
  match String.split_on_char '|' line with
  | [ date; rank; colours; title; _tempora; commemorations; displaced; _n_masses ] ->
      { o_date = date;
        o_rank = int_of_string rank;
        o_colours = explode colours;
        o_title = title;
        o_commemorations = split_list_field commemorations;
        o_displaced = split_list_field displaced }
  | _ -> Alcotest.failf "malformed fixture line (expected 8 '|'-separated fields): %S" line

let read_lines path =
  let ic = open_in path in
  let rec loop acc =
    match input_line ic with
    | line -> loop (line :: acc)
    | exception End_of_file ->
        close_in ic;
        List.rev acc
  in
  loop []

let oracle_rows () = List.map oracle_row_of_line (read_lines fixture_path)

(* ---------------------------------------------------------------------- *)
(* The colitur side: the SAME pipeline bin/main.ml's `colitur day` and     *)
(* test_differential.ml's own [colitur_rows_2005_2050] use --              *)
(* Colitur_kernel.Calendar over the real committed data. Restricted to     *)
(* 2026-2027 (indexing 2025 too, for the same reason test_differential.ml  *)
(* indexes [y-1]: Calendar.year resolves one Advent-anchored liturgical    *)
(* year, which straddles two civil years). *)
(* ---------------------------------------------------------------------- *)

type colitur_row = { c_date : string; c_rank : int; c_colour : char; c_commemorations : string list }

let rank_to_int = function V.Class1 -> 1 | V.Class2 -> 2 | V.Class3 -> 3 | V.Class4 -> 4

let colour_to_char = function
  | Colour.White -> 'w'
  | Colour.Red -> 'r'
  | Colour.Green -> 'g'
  | Colour.Violet -> 'v'
  | Colour.Rose -> 'p'
  | Colour.Black -> 'b'

let colitur_rows_2026_2027 () =
  let layer = real_layer () in
  let by_rata : (int, (V.season, V.rank) LD.t) Hashtbl.t = Hashtbl.create 800 in
  for y = 2025 to 2027 do
    let days = Cal.year Rite_ef.context layer y in
    Array.iter (fun (d : (V.season, V.rank) LD.t) -> Hashtbl.replace by_rata (Date.to_rata d.LD.date) d) days
  done;
  let mk y m d = match Date.make ~year:y ~month:m ~day:d with Ok t -> t | Error e -> failwith e in
  let rows = ref [] in
  let d = ref (mk 2026 1 1) in
  let stop = mk 2027 12 31 in
  while Date.compare !d stop <= 0 do
    (match Hashtbl.find_opt by_rata (Date.to_rata !d) with
    | Some day ->
        let cel = day.LD.observed in
        let commemoration_slugs =
          List.map (fun (c, _) -> Slug.to_string c.Cel.slug) day.LD.commemorations
        in
        rows :=
          { c_date = Date.to_iso8601 day.LD.date;
            c_rank = rank_to_int cel.Cel.rank;
            c_colour = colour_to_char cel.Cel.colour;
            c_commemorations = commemoration_slugs
          }
          :: !rows
    | None -> Alcotest.failf "internal error: no resolved day for %s" (Date.to_iso8601 !d));
    d := Date.add_days !d 1
  done;
  List.rev !rows

(* ---------------------------------------------------------------------- *)
(* Field-diff computation: the four axes the oracle actually supports     *)
(* (identity-by-slug is deliberately out of scope, see this file's own    *)
(* header). *)
(* ---------------------------------------------------------------------- *)

type field = Rank | Colour_f | Comm_presence | Comm_count

let field_name = function
  | Rank -> "rank"
  | Colour_f -> "colour"
  | Comm_presence -> "commemoration-presence"
  | Comm_count -> "commemoration-count"

let diff_fields (c : colitur_row) (o : oracle_row) =
  let c_has = c.c_commemorations <> [] and o_has = o.o_commemorations <> [] in
  List.filter_map
    (fun x -> x)
    [ (if c.c_rank = o.o_rank then None else Some Rank);
      (if List.mem c.c_colour o.o_colours then None else Some Colour_f);
      (if c_has = o_has then None else Some Comm_presence);
      (* Count is only meaningful once presence already agrees (both non-empty):
         a presence mismatch already flags the row via [Comm_presence] above,
         and comparing lengths across a 0-vs-N split would just restate that
         same disagreement under a second name. *)
      (if c_has && o_has && List.length c.c_commemorations <> List.length o.o_commemorations then
         Some Comm_count
       else None)
    ]

(* ---------------------------------------------------------------------- *)
(* The cited allow-list (data/ef/expected-divergences-missalemeum.sexp).  *)
(* Each predicate is gated on an EXACT, literal date set (never a date    *)
(* range or a slug pattern -- with at most 4 dates per id, a literal list *)
(* costs nothing and cannot silently widen to absorb an unrelated future  *)
(* mismatch the way a range could), AND an exact/subset diff shape, the   *)
(* same double-gate test_differential.ml's own [layer_c_reason] uses.     *)
(* ---------------------------------------------------------------------- *)

let subset xs ys = List.for_all (fun x -> List.mem x ys) xs

let contains_substring s ~needle =
  let ls = String.length s and ln = String.length needle in
  let rec at i = i + ln <= ls && (String.sub s i ln = needle || at (i + 1)) in
  ln = 0 || at 0

(* M1 -- RG 33 (corrected, precedence_ef.ml's own [is_omissible_vigil]):
   missalemeum does not implement RG 33's mandatory omission of a II/III-
   class vigil impeded by a Sunday -- 28 June 2026 (Vigil of Sts Peter &
   Paul, II class) still shows a commemoration of the vigil on the V Sunday
   after Pentecost; 9 August 2026 (Vigil of St Lawrence, III class) shows
   the vigil as the day's FULL OBSERVED OFFICE, not merely a commemoration,
   displacing the XI Sunday after Pentecost entirely. Both wrong per RG 33's
   own "in dominica quavis" (ANY Sunday, unqualified) -- verdict colitur. *)
let m1_dates = [ "2026-06-28"; "2026-08-09" ]

(* M2 -- RG 91 entry 27 ("Officium sanctae Mariae in sabbato"): every
   otherwise-unoccupied IV-class Saturday should carry the votive Office of
   the BVM (white; missalemeum's own title cycles "I".."V Mass of the
   B. V. M. - Salve, Sancta Parens"), a genuinely DISTINCT office from an
   ordinary green/violet feria. temporal_ef.ml's [band] already carries an
   entry-27 comment acknowledging this row of RG 91 exists, but nothing in
   [Temporal_ef.temporal]'s actual CONSTRUCTION builds this office -- an
   unimpeded Time-after-Epiphany/-Pentecost Saturday still gets the bare
   ferial slug and [season_colour]'s green. A genuine, primary-attested
   FEATURE GAP (not a citation dispute) -- verdict missalemeum: colitur is
   short a whole office here, not merely differently-opinioned. Registered
   as an open item (register §6) rather than built in this task: it needs
   its own proper texts/citations, the same scope line "Major Litanies"
   (M5 below) already sits on. Matched on the oracle's own title substring,
   not a hardcoded date list -- the title IS the distinguishing evidence,
   and every Paschaltide occurrence (where colitur's season colour is
   already white, RG 119) never reaches this predicate at all, since its
   diffs are already empty before [layer_m_reason] is ever called. *)
let bvm_saturday_title = "Salve, Sancta Parens"

(* M3 -- RG 87 (Minor Litanies/Rogations): the SAME gap the lectio
   differential's own C8 already names (data/ef/expected-divergences.sexp)
   -- missalemeum, like lectio, computes no Rogation day at all and shows
   the plain paschaltide-week feria instead. Only ONE date in this window
   shows it (3 May 2027, Rogation Monday) because every other Rogation day
   here is won by a saint anyway (both sides then agree on the SAINT's own
   identity, with only the underlying temporal identity differing, which
   this comparator's rank/colour/commemoration axes do not expose). Verdict
   colitur, same citation as lectio's own C8. *)
let m3_dates = [ "2027-05-03" ]

(* M4 -- a genuine DATA GAP, primary-source-confirmed: the 1962 calendarium
   itself lists, under 28 January, "S. Petri Nolasci Conf., III classis. /
   Com. S. Agnetis Virg. et Mart., secundo" -- a second commemoration of
   St Agnes (distinct from her main 21 January feast) that data/ef/
   sanctoral.sexp does not carry at all. Traced upstream: lectio's own
   tridentine-calendar.ini has no 01-28 entry beyond [peter-nolasco]
   either, so colitur inherited the gap from its bootstrap source, not
   from the bootstrap tool mis-reading a present entry. Cannot be fixed in
   this task (data/ef/sanctoral.sexp is bootstrapped from lectio, per
   CLAUDE.md's binding decision 3; lectio itself needs the entry first,
   and this task does not touch ~/git/projects/lectio) -- verdict
   missalemeum, tracked as a register §6 open item. *)
let m4_dates = [ "2026-01-28"; "2027-01-28" ]

(* M5 -- register §6's OWN already-open item, independently confirmed by
   the oracle: "Major Litanies (25 April, RG 80) are not yet computed" --
   missalemeum's commemoration "Pro rogationibus" ("for the Rogations") on
   St Mark's day (25 April, the Major Litanies' fixed date) is exactly the
   missing office. Not a new finding; recorded here so the automated
   comparator does not report it as an unexplained mismatch, and cross-
   referenced from the register so a reader sees both. Verdict missalemeum
   (colitur is missing a real, cited office; register §6 already tracks
   it). Only ONE date below, not two: 25 April 2026 is a Saturday (Mark
   wins outright, colitur's commemoration list is empty where the oracle's
   is not -- a visible presence gap); 25 April 2027 is a Sunday, where the
   Sunday wins on BOTH sides and each side's own single slot goes to a
   DIFFERENT candidate (colitur: Mark himself, admitted under RG 111(b)'s
   "de festo II classis"; missalemeum: the Major Litanies) -- both
   non-empty, same count, so this comparator's deliberately-not-slug-
   identity axes cannot see that year's instance at all (see the task
   report). *)
let m5_dates = [ "2026-04-25" ]

(* M6 -- the reverse of M4/M7/M9: the primary calendarium's own row for 14
   August reads, in full, "Vigilia, II classis." -- nothing else. No
   commemoration is listed for that date anywhere in the source this
   project treats as authoritative (CLAUDE.md binding decision 1). data/ef/
   sanctoral.sexp agrees (a single entry, [vigil-of-the-assumption], 14
   Aug). missalemeum's own "St. Eusebius" commemoration for that date has
   no support in the 1962 universal calendar found here (a DIFFERENT St
   Eusebius, bishop and martyr, is genuinely commemorated 16 December,
   matching lectio's own [eusebius] entry at that date -- not this one).
   Verdict colitur: this is the one direction among M4/M6/M7/M9 where the
   oracle itself appears to be carrying data outside the 1962 universal
   calendar (a pre-1955 survival or a different edition), not colitur
   missing something real. *)
let m6_dates = [ "2026-08-14"; "2027-08-14" ]

(* M7 -- a genuine DATA GAP, primary-source-confirmed, the same shape as
   M4: the calendarium's own 26 October row reads "Com. S. Evaristi Papæ
   et Mart." (Commemoration of St Evaristus, Pope and Martyr) -- absent
   from data/ef/sanctoral.sexp, and absent from lectio's own tridentine-
   calendar.ini for 10-26 (no entry at all for that date), so this is
   another bootstrap-source gap, not fixable without touching lectio.
   Verdict missalemeum, register §6 open item. *)
let m7_dates = [ "2026-10-26"; "2027-10-26" ]

(* M8 -- RG 109(a) ("of a Sunday" is always privileged) + RG 111(a) ("on
   I-class days... none save one privileged"): when a FIXED I-class feast
   (All Saints, 1 Nov; the Assumption, 15 Aug) lands on an ordinary Sunday,
   the impeded Sunday IS the one privileged commemoration RG 111(a) admits
   -- already an established, independently-tested rule in this codebase
   (test_precedence_ef.ml's "RG95/RG109(a): an impeded I-class SUNDAY does
   NOT transfer -- it is Commemorated and Privileged"). missalemeum shows
   no commemoration at all on either occurrence in this window. Verdict
   colitur. *)
let m8_dates = [ "2026-11-01"; "2027-08-15" ]

(* M9 -- a genuine DATA GAP, the same shape as M4/M7: the calendarium's own
   9 November row reads, alongside the Dedication of the Archbasilica (II
   class), "Com. S. Theodori Mart." (Commemoration of St Theodore,
   Martyr) -- absent from data/ef/sanctoral.sexp and from lectio's own
   11-09 entry (dedication-of-the-archbasilica-of-our-holy-savior alone,
   no second entry for that date). Verdict missalemeum, register §6 open
   item. *)
let m9_dates = [ "2026-11-09"; "2027-11-09" ]

(* M14 -- a genuine DATA GAP, the same shape as M4/M7/M9: the calendarium's
   own 14 May row reads "Com. S. Bonifatii Mart." (a commemoration-only St
   Boniface, Martyr -- DIFFERENT from the II-class St Boniface, Bishop and
   Martyr, of 5 June, which data/ef/sanctoral.sexp and lectio both already
   carry correctly) -- absent from data/ef/sanctoral.sexp and from lectio's
   own tridentine-calendar.ini for 05-14 (no entry at all for that date).
   Verdict missalemeum, register §6 open item. *)
let m14_dates = [ "2027-05-14" ]

(* M10 -- RG 109(e), unqualified text ("de feriis Adventus, Quadragesimae
   et Passionis" -- OF THE FERIAS OF ADVENT, not "of the Advent ferias 17-
   23 December only"; that narrower window is RG 91 entry 18's own
   OCCURRENCE-table dignity, a different axis from RG 109's commemoration-
   privilege list, register §4's own citations keep the two separate).
   colitur commemorates the losing early-Advent feria (the Monday after
   Advent I, 30 Nov; the Tuesday/Wednesday after Advent II, 8 Dec) when a
   saint wins those days -- missalemeum shows nothing on these specific
   four rows, even though it DOES show equivalent later-Advent-feria
   commemorations elsewhere in this same window (2-21 December, matching
   colitur exactly on every one of those -- see the task report), which is
   why this reads as a missalemeum-side inconsistency on these four
   particular rows rather than a textually-narrower rule this task missed.
   Verdict colitur. *)
let m10_dates = [ "2026-11-30"; "2027-11-30"; "2026-12-08"; "2027-12-08" ]

(* M11 -- CORRECTED, fix round 1 (F3): this used to claim "no RG paragraph
   found" and verdict colitur. WRONG. RG 67 ("dies infra octavam sunt II
   classis") + RG 109(c) ("de diebus infra octavam Nativitatis Domini") +
   the calendarium's own explicit note under 26/27/28 December ("S.
   STEPHANI PROTOMARTYRIS, II classis. / Com. octavae Nativitatis.", same
   pattern for John the Evangelist and the Holy Innocents) all confirm a
   REAL commemoration is due here -- and it is a genuine regression: before
   Task 16's own commemoration-eligibility fix, colitur happened to
   commemorate the day's generic Christmastide loser unconditionally
   (matching presence, for the wrong reason); the fix (correctly) stopped
   that, but the 26-28 December window's own temporal candidate has the
   WRONG ferial rank to begin with ([ferial_rank]'s Christmastide catch-all
   gives it Class4; RG 67 says II) -- and a naive fix gets RG 69's Sunday
   case backwards (the Sunday, when this window falls on one, commemorates
   the NAMED feast, not the generic octave placeholder). Needs new
   architecture (a commemoration attached to whichever named feast wins,
   not a competing RG 92-95 candidate) or a more careful fix than this
   round attempted. Verdict now OPEN, not colitur -- see the sexp entry's
   own full note and the task report. *)
let m11_dates = [ "2026-12-26"; "2026-12-28"; "2027-12-27"; "2027-12-28" ]

(* M12 -- RG 110, primary text: "In Officio et Missa S. Petri semper fit
   commemoratio S. Pauli, et vicissim" -- in the Office and Mass of EITHER
   Peter or Paul, a commemoration of the OTHER is ALWAYS made (the
   "inseparable commemoration"), uncapped by RG 111's ordinary admission
   count ("in numero orationum computando, pro unica habeantur" -- counted
   as one for counting purposes, i.e. it rides alongside whatever RG 111
   already admits). Unimplemented in this codebase -- confirmed by the one
   row in this window where it is visible: 22 February 2027 (Chair of
   St Peter) shows only the privileged Lent feria commemorated in colitur,
   while missalemeum shows that AND "St. Paul". A genuine, primary-cited
   feature gap -- verdict missalemeum, register §6 open item. Real but
   NARROW: every other Peter/Paul office in this window (29 June, both
   years; 1 August M4-adjacent dates were checked and found clean) either
   had no room for the extra commemoration to become visible against this
   comparator's axes, or fell on a day this predicate does not otherwise
   touch -- see the task report for the specific check. *)
let m12_dates = [ "2027-02-22" ]

(* M13 -- OPEN, NOT adjudicated (the brief's own explicit permission,
   "say so as an open item rather than absorbing it"). 19 March 2027: St
   Joseph (I class, 19 March) falls on the Friday of Passion Week. The
   1962 calendarium's own March table carries a standing note, "Feria VI
   post dominicam I Passionis: Commemoratio septem Dolorum B. Mariae
   Virg." (a fixed commemoration of Our Lady's Seven Sorrows for that
   Friday, EVERY year, confirmed real) -- and missalemeum shows Joseph
   entirely DISPLACED that year, with the Friday's own office (III class,
   violet) observed and the Seven Sorrows commemorated instead. RG 91's
   plain table (entry 11-13, I-class feast, vs entry 22, an ordinary III-
   class Passiontide feria) gives Joseph the day outright, with no general
   RG 96 collision requiring a transfer -- so either (a) colitur's plain
   reading is right and missalemeum is wrong, (b) a MORE SPECIFIC rubric
   (most plausibly attached to St Joseph's own Proprium Sanctorum entry,
   the same shape as the Annunciation's own Attamen clause, register §4)
   overrides the general table for this exact collision and this task did
   not find its text, or (c) the Seven Sorrows commemoration itself
   somehow outranks an ordinary I-class feast on this one Friday, which
   nothing found here supports either. Extensive but non-exhaustive
   primary-source search (see the task report) did not settle it.
   Separately, but confirmed regardless of the adjudication above: colitur
   does not implement the Seven-Sorrows-of-Passion-Friday commemoration at
   all, in any year -- a real, primary-attested gap, register §6 open
   item. *)
let m13_dates = [ "2027-03-19" ]

let layer_m_reason (c : colitur_row) (o : oracle_row) diffs =
  if diffs = [] then None
  else if List.mem c.c_date m1_dates && subset diffs [ Rank; Colour_f; Comm_presence ] then Some "M1"
  else if contains_substring o.o_title ~needle:bvm_saturday_title && diffs = [ Colour_f ] then Some "M2"
  else if List.mem c.c_date m3_dates && diffs = [ Colour_f ] then Some "M3"
  else if List.mem c.c_date m4_dates && diffs = [ Comm_presence ] then Some "M4"
  else if List.mem c.c_date m5_dates && diffs = [ Comm_presence ] then Some "M5"
  else if List.mem c.c_date m6_dates && diffs = [ Comm_presence ] then Some "M6"
  else if List.mem c.c_date m7_dates && diffs = [ Comm_presence ] then Some "M7"
  else if List.mem c.c_date m8_dates && diffs = [ Comm_presence ] then Some "M8"
  else if List.mem c.c_date m9_dates && diffs = [ Comm_presence ] then Some "M9"
  else if List.mem c.c_date m14_dates && diffs = [ Comm_presence ] then Some "M14"
  else if List.mem c.c_date m10_dates && diffs = [ Comm_presence ] then Some "M10"
  else if List.mem c.c_date m11_dates && diffs = [ Comm_presence ] then Some "M11"
  else if List.mem c.c_date m12_dates && diffs = [ Comm_count ] then Some "M12"
  else if List.mem c.c_date m13_dates && subset diffs [ Rank; Colour_f ] then Some "M13"
  else None

(* ---------------------------------------------------------------------- *)
(* data/ef/expected-divergences-missalemeum.sexp loading -- same shape as  *)
(* test_differential.ml's own [allow_entry]/[load_allow_list]. *)
(* ---------------------------------------------------------------------- *)

open Sexplib0.Sexp_conv

type allow_entry = { id : string; citation : string; verdict : string; note : string; expected_rows : int }
[@@deriving sexp]

let load_allow_list () =
  let sexps =
    try Sexplib.Sexp.load_sexps allow_list_path
    with e -> Alcotest.failf "%s: failed to load: %s" allow_list_path (Printexc.to_string e)
  in
  List.map allow_entry_of_sexp sexps

(* ---------------------------------------------------------------------- *)
(* The comparison itself. *)
(* ---------------------------------------------------------------------- *)

type outcome = Matched | Explained of string | Unexplained of field list

let compare_streams () =
  let oracle = oracle_rows () in
  let colitur = colitur_rows_2026_2027 () in
  (oracle, colitur)

let classify oracle colitur =
  List.map2
    (fun (o : oracle_row) (c : colitur_row) ->
      if not (String.equal o.o_date c.c_date) then
        Alcotest.failf "streams misaligned: oracle %s vs colitur %s" o.o_date c.c_date;
      let diffs = diff_fields c o in
      if diffs = [] then (c, o, Matched)
      else
        match layer_m_reason c o diffs with
        | Some id -> (c, o, Explained id)
        | None -> (c, o, Unexplained diffs))
    oracle colitur

let describe_unexplained (c : colitur_row) (o : oracle_row) diffs =
  Printf.sprintf "%s: %s differ -- colitur=(rank=%d colour=%c comms=[%s]) oracle=(rank=%d colours=[%s] \
                   title=%S comms=[%s] displaced=[%s])"
    c.c_date
    (String.concat "," (List.map field_name diffs))
    c.c_rank c.c_colour
    (String.concat ";" c.c_commemorations)
    o.o_rank
    (String.concat "" (List.map (String.make 1) o.o_colours))
    o.o_title
    (String.concat ";" o.o_commemorations)
    (String.concat ";" o.o_displaced)

let test_fixture_checksum () =
  Alcotest.(check string) "fixture SHA-256 matches its provenance note" fixture_sha256
    (sha256_of_file fixture_path)

let test_dates_align () =
  let oracle, colitur = compare_streams () in
  Alcotest.(check int) "both streams have 730 rows (2026 + 2027, both non-leap)" 730 (List.length oracle);
  Alcotest.(check int) "colitur recomputed the same number of rows" (List.length oracle) (List.length colitur);
  let mismatched =
    List.filter_map
      (fun (o, c) -> if String.equal o.o_date c.c_date then None else Some (o.o_date, c.c_date))
      (List.combine oracle colitur)
  in
  Alcotest.(check (list (pair string string))) "no misaligned dates" [] mismatched

(* The core assertion: every one of the 42 raw differences across all four
   axes (rank, colour-membership, commemoration-presence, commemoration-
   count) is named in the cited allow-list. Nothing else passes silently. *)
let test_no_unexplained_differences () =
  let oracle, colitur = compare_streams () in
  let classified = classify oracle colitur in
  let unexplained =
    List.filter_map
      (fun (c, o, outcome) ->
        match outcome with Unexplained diffs -> Some (describe_unexplained c o diffs) | _ -> None)
      classified
  in
  Alcotest.(check (list string)) "no differences outside the cited allow-list" [] unexplained

(* Teeth, not just green: EVERY allow-list id's actual row count over this
   fixture must equal what data/ef/expected-divergences-missalemeum.sexp
   declares, in BOTH directions -- the same double-check test_differential
   .ml's own "Layer C counts match citations" test makes for the lectio
   allow-list. *)
let test_layer_m_counts_match_citations () =
  let oracle, colitur = compare_streams () in
  let classified = classify oracle colitur in
  let actual_counts = Hashtbl.create 16 in
  List.iter
    (fun (_, _, outcome) ->
      match outcome with
      | Explained id ->
          Hashtbl.replace actual_counts id (1 + Option.value ~default:0 (Hashtbl.find_opt actual_counts id))
      | _ -> ())
    classified;
  let declared = load_allow_list () in
  let expected = List.sort compare (List.map (fun e -> (e.id, e.expected_rows)) declared) in
  let actual = List.sort compare (Hashtbl.fold (fun id n acc -> (id, n) :: acc) actual_counts []) in
  Alcotest.(check (list (pair string int)))
    "every allow-list id's actual row count matches its citation's expected_rows, and no id is unused or \
     undeclared"
    expected actual

let suite =
  ( "oracle (missalemeum, EF, 2026-2027)",
    [ Alcotest.test_case "fixture SHA-256 matches its provenance note" `Quick test_fixture_checksum;
      Alcotest.test_case "streams are 730 rows each, dates aligned 1:1" `Quick test_dates_align;
      Alcotest.test_case "every difference is named in the cited allow-list -- none unexplained" `Quick
        test_no_unexplained_differences;
      Alcotest.test_case "allow-list counts match data/ef/expected-divergences-missalemeum.sexp exactly"
        `Quick test_layer_m_counts_match_citations
    ] )