diff options
Diffstat (limited to 'test/test_citation.ml')
| -rw-r--r-- | test/test_citation.ml | 32 |
1 files changed, 26 insertions, 6 deletions
diff --git a/test/test_citation.ml b/test/test_citation.ml index 1efaa10..133553b 100644 --- a/test/test_citation.ml +++ b/test/test_citation.ml @@ -117,8 +117,7 @@ let starts_with_at content pos prefix = [Str]/regex -- a plain forward scan for the marker, then read to the closing quote. Mirrors the coordinator's own survey command (grep -oh over the reference marker, quote-delimited). *) -let references content = - let marker = "(reference \"" in +let references_with marker content = let mlen = String.length marker in let len = String.length content in let rec loop pos acc = @@ -151,14 +150,35 @@ let book_token r = let stop = if !i < len && r.[!i] = '.' then !i + 1 else !i in String.sub r 0 stop +(* A citation is written TWO ways in this project's data, and a survey that + knows only one of them silently under-reads the corpus: + (reference "Isa 60:1-6") -- lectionary/sanctoral/commons + (Set_citation First "Wis 7:7-14") -- adjustments.sexp, an overlay + Both markers are scanned below. *) +let references content = + (* Each marker must include the OPENING QUOTE. [references_with] returns + the text between the marker and the next '"', so a marker stopping at + "(Set_citation " yields "First " / "Gospel " -- the part label, never + the citation -- and every entry is then silently discarded. That was + this function's first version, and it read the file while extracting + nothing at all. *) + references_with "(reference \"" content + @ references_with "(Set_citation First \"" content + @ references_with "(Set_citation Gospel \"" content + let test_every_data_file_token_resolves () = (* The check whose absence caused fix round 1: the brief surveyed only the lectionary and missed 21 tokens, several common, living in - sanctoral.sexp and commons.sexp. Read all three files at test time and - re-derive the token set from them, rather than hardcoding a list, so - this keeps working when the data changes. *) + sanctoral.sexp and commons.sexp. + + adjustments.sexp was then missed AGAIN, by this very test, because it + writes citations as `Set_citation` rather than `(reference ...)` -- the + same "one file too few" shape twice over. All FOUR shipped files are + read here, and the token set is re-derived from them at test time + rather than hardcoded, so this keeps working when the data changes. *) let files = - [ "../data/ef/lectionary.sexp"; "../data/ef/sanctoral.sexp"; "../data/ef/commons.sexp" ] + [ "../data/ef/lectionary.sexp"; "../data/ef/sanctoral.sexp"; + "../data/ef/commons.sexp"; "../data/ef/adjustments.sexp" ] in let tokens = files |