diff options
| author | Lukasz Kasprzak <lukas@labunix.xyz> | 2026-08-19 08:41:23 +0200 |
|---|---|---|
| committer | Lukasz Kasprzak <lukas@labunix.xyz> | 2026-08-19 08:41:23 +0200 |
| commit | 063d4058346f7dc03eb0aa5ba394b9a872d3f1e3 (patch) | |
| tree | 93d1ff06c91affc6586c64dc0326460b675f9e9b /lib | |
| parent | 5828571fa31a0480838d1ede210002ab50768c64 (diff) | |
| download | colitur-063d4058346f7dc03eb0aa5ba394b9a872d3f1e3.tar.gz colitur-063d4058346f7dc03eb0aa5ba394b9a872d3f1e3.zip | |
feat(render): CSV and JSON emitters, and the published contract
Both consume the VIEW, not the kernel, so every emitter and every
template describe exactly the same fields -- there is one vocabulary,
not five.
CSV is RFC 4180: a field with a comma is quoted. That is live on real
data, not hypothetical -- 'St. Joseph, Spouse of the Bl. Virgin Mary'
would otherwise split into two columns.
JSON is hand-rolled because the dependency list is frozen and escaping
is the only subtlety. Control characters below 0x20 are \u-escaped per
RFC 8259 section 7.
There are no numbers in the view, deliberately: a consumer never has to
guess whether week is 2 or "2".
schema/day-v1.json pins the shape. Once a phone subscribes or a site
fetches this, it is a promise to strangers -- adding a field is minor,
renaming one means /v2/.
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/render/emit_csv.ml | 44 | ||||
| -rw-r--r-- | lib/render/emit_csv.mli | 9 | ||||
| -rw-r--r-- | lib/render/emit_json.ml | 47 | ||||
| -rw-r--r-- | lib/render/emit_json.mli | 10 |
4 files changed, 110 insertions, 0 deletions
diff --git a/lib/render/emit_csv.ml b/lib/render/emit_csv.ml new file mode 100644 index 0000000..b478265 --- /dev/null +++ b/lib/render/emit_csv.ml @@ -0,0 +1,44 @@ +(* emit_csv.ml *) +module T = Template + +let escape_field s = + let needs = + String.exists (fun c -> c = ',' || c = '"' || c = '\n' || c = '\r') s + in + if not needs then s + else begin + let b = Buffer.create (String.length s + 8) in + Buffer.add_char b '"'; + String.iter (fun c -> if c = '"' then Buffer.add_string b "\"\"" else Buffer.add_char b c) s; + Buffer.add_char b '"'; + Buffer.contents b + end + +let get v k = match v with T.Obj kvs -> List.assoc_opt k kvs | _ -> None +let s v k = match get v k with Some (T.Str x) -> x | _ -> "" +let nested v a b = match get v a with Some inner -> s inner b | None -> "" + +let columns = + [ "date"; "rite"; "season"; "week"; "slug"; "rank"; "colour"; "subject"; + "name_la"; "name_en"; "first"; "gospel"; "comms" ] + +let row ~rite d = + let comms = + match get d "comms" with + | Some (T.List l) -> String.concat " " (List.map (fun c -> s c "slug") l) + | _ -> "" + in + String.concat "," + (List.map escape_field + [ s d "iso"; rite; s d "season"; s d "week"; s d "slug"; s d "rank"; + s d "colour"; s d "subject"; nested d "name" "la"; nested d "name" "en"; + s d "first"; s d "gospel"; comms ]) + +let year v = + let rite = s v "rite" in + let days = match get v "days" with Some (T.List l) -> l | _ -> [] in + let b = Buffer.create (64 * 400) in + Buffer.add_string b (String.concat "," columns); + Buffer.add_char b '\n'; + List.iter (fun d -> Buffer.add_string b (row ~rite d); Buffer.add_char b '\n') days; + Buffer.contents b diff --git a/lib/render/emit_csv.mli b/lib/render/emit_csv.mli new file mode 100644 index 0000000..262f660 --- /dev/null +++ b/lib/render/emit_csv.mli @@ -0,0 +1,9 @@ +(* emit_csv.mli *) +(** One row per day, RFC 4180. Consumes the VIEW, not the kernel, so every + emitter describes exactly the same fields as every template. *) + +(** RFC 4180 section 2: quote a field containing a comma, a quote or a newline; + double an embedded quote. Exposed for testing. *) +val escape_field : string -> string + +val year : Template.value -> string diff --git a/lib/render/emit_json.ml b/lib/render/emit_json.ml new file mode 100644 index 0000000..272e4ca --- /dev/null +++ b/lib/render/emit_json.ml @@ -0,0 +1,47 @@ +(* emit_json.ml *) +module T = Template + +let escape_string s = + let b = Buffer.create (String.length s + 8) in + Buffer.add_char b '"'; + String.iter + (fun c -> + match c with + | '"' -> Buffer.add_string b "\\\"" + | '\\' -> Buffer.add_string b "\\\\" + | '\n' -> Buffer.add_string b "\\n" + | '\r' -> Buffer.add_string b "\\r" + | '\t' -> Buffer.add_string b "\\t" + | c when Char.code c < 0x20 -> Buffer.add_string b (Printf.sprintf "\\u%04x" (Char.code c)) + | c -> Buffer.add_char b c) + s; + Buffer.add_char b '"'; + Buffer.contents b + +(* Emit the view tree directly. Bools stay bools; everything else is a string, + an array or an object -- there are no numbers in the view, deliberately, so a + consumer never has to guess whether "week" is 2 or "2". *) +let rec write b (v : T.value) = + match v with + | T.Str s -> Buffer.add_string b (escape_string s) + | T.Bool x -> Buffer.add_string b (if x then "true" else "false") + | T.List l -> + Buffer.add_char b '['; + List.iteri (fun i x -> if i > 0 then Buffer.add_char b ','; write b x) l; + Buffer.add_char b ']' + | T.Obj kvs -> + Buffer.add_char b '{'; + List.iteri + (fun i (k, x) -> + if i > 0 then Buffer.add_char b ','; + Buffer.add_string b (escape_string k); + Buffer.add_char b ':'; + write b x) + kvs; + Buffer.add_char b '}' + +let year v = + let b = Buffer.create (64 * 1024) in + write b v; + Buffer.add_char b '\n'; + Buffer.contents b diff --git a/lib/render/emit_json.mli b/lib/render/emit_json.mli new file mode 100644 index 0000000..91c8f48 --- /dev/null +++ b/lib/render/emit_json.mli @@ -0,0 +1,10 @@ +(* emit_json.mli *) +(** JSON writer. Hand-rolled: the dependency list is frozen (spec section 1), + and writing JSON is a page of code where escaping is the only subtlety. + Output shape is pinned by schema/day-v1.json, the published contract. *) + +(** RFC 8259 section 7, including \u-escaping of control characters below 0x20. + Returns the value WITH its surrounding quotes. Exposed for testing. *) +val escape_string : string -> string + +val year : Template.value -> string |
