format 2.1: ocda-read, the readers folded in

ocda-read, one reader where there were two. The .ssp reader and the
.ocda.db reader each had their own parser; this one is built on the
library, so every mode reads a .ssp, a .ocda.db and a pod, and says
the same thing of each. Its output modules are the .ssp reader's,
copied (the reader repositories are kept, frozen) and moved onto the
library's model; --languages and --files come from the database
reader.

  ocda-read [--tree|--html|--llm-text|--llm-jsonl|--images|
             --verify --image-dir=<d>|--languages|--files|
             --report-unknown|--validate] <file> [lang]

In D every mode of both readers; in Gleam the modes the Gleam readers
had (the summary, --tree, --languages, --files, --report-unknown),
whose output is the D reader's, byte for byte. In each language it
lives in src/read/ and is not part of the library: dub configurations
keep it out of a dependant's build in D, and Gleam compiles all of
src/ but a dependant need not use it.

Checked over the markup document samples: against the .ssp reader on
a .ssp, byte for byte after the first line in every D mode but the
summary, whose closing hint differs; against the database reader on a
.ocda.db, --files and --languages (its id column left out); the same
output from the .ssp, the .ocda.db and the .sisupod; and D == Gleam.
The database reader's --outline is not reproduced: it ordered
headings within their own section, so that other sections' headings
fell among the body's. --outline here is --tree.

What writing it found in the library: the database loader could not
say what it had not understood. It asked for columns by name and so
never saw the rest, and reported that it had understood everything.
It now counts them on the conditions under which the .ssp writes the
same property, and --report-unknown is the same from every form.

ocda.inventory answers two questions about the file rather than the
document: its languages, in the manifest's order, each with the
markup it was made from and the sha256 of its .ssp, for every form
alike; and what a .ocda.db carries besides the abstraction. In Gleam
the sha256 comes from OTP's crypto through a four line Erlang FFI.

The flake's default is all three D programs in one result: built
separately into the same link, each replaced the one before.

(assisted by Claude-Code)

1 files changed, 138 insertions, 0 deletions

diff --git a/gleam/src/ocda/inventory.gleam b/gleam/src/ocda/inventory.gleam
new file mode 100644
index 0000000..6047313
--- /dev/null
+++ b/gleam/src/ocda/inventory.gleam
@@ -0,0 +1,138 @@
+//// What a source holds, beyond the one document the model is loaded from.
+////
+//// The model is one language of one document. Two questions a reader asks
+//// are about the file instead: which languages it holds, and, for a
+//// database, what else it carries. They are here rather than in a reader
+//// because the answer depends on the input form, which is the library's to
+//// know, and so that a reader asking them does not learn which form it was
+//// handed. A mirror of the D library's `ocda.inventory`.
+////
+//// `languages` answers for every form, and answers the same: the languages
+//// in the order the manifest gave them (which every `.ssp` records, in
+//// `@source languages`), each with the markup file it was made from and the
+//// sha256 of its `.ssp`. The database stores that digest; for a `.ssp` and a
+//// pod it is taken from the bytes, which are the same bytes.
+////
+//// `carried` is the database's: a `.ocda.db` holds the markup, images,
+//// configuration and catalogues it was built from, a `.ssp` holds none of
+//// them, and a pod's are its archive entries rather than anything the
+//// abstraction says.
+
+import gleam/bit_array
+import gleam/dict
+import gleam/list
+import gleam/result
+import gleam/string
+import ocda/load
+import ocda/load_db
+import ocda/load_pod
+import ocda/load_ssp
+import ocda/zip
+import simplifile
+
+pub type Language {
+  Language(lang: String, source_filename: String, ssp_digest: String)
+}
+
+pub type Carried {
+  Carried(
+    role: String,
+    compression: String,
+    count: String,
+    bytes: String,
+    stored: String,
+  )
+}
+
+pub fn languages(path: String) -> Result(List(Language), String) {
+  case load.source_of(path) {
+    load.OcdaDb -> {
+      use held <- result.try(load_db.languages_of_file(path))
+      Ok(
+        list.map(held, fn(l) {
+          Language(l.lang, l.source_filename, l.ssp_digest)
+        }),
+      )
+    }
+    load.Ssp -> {
+      use bytes <- result.try(
+        simplifile.read_bits(path)
+        |> result.map_error(fn(e) { path <> ": " <> simplifile.describe_error(e) }),
+      )
+      use text <- result.try(
+        bit_array.to_string(bytes)
+        |> result.replace_error(path <> ": not valid UTF-8"),
+      )
+      let doc = load_ssp.parse(text)
+      Ok([
+        Language(
+          source_value(doc.source, "language"),
+          doc.source_filename,
+          sha256_hex(bytes),
+        ),
+      ])
+    }
+    load.Pod -> {
+      use archive <- result.try(load_pod.archive_bytes(path))
+      use entries <- result.try(zip.entries(archive))
+      use found <- result.try(
+        zip.find_suffix(entries, ".ssp")
+        |> list.try_map(fn(e) {
+          use bytes <- result.try(zip.read(archive, e))
+          use text <- result.try(
+            bit_array.to_string(bytes)
+            |> result.replace_error(e.name <> ": not valid UTF-8"),
+          )
+          let doc = load_ssp.parse(text)
+          let lang = result.unwrap(load_pod.lang_of(e.name), "")
+          Ok(#(
+            Language(lang, doc.source_filename, sha256_hex(bytes)),
+            string.split(source_value(doc.source, "languages"), " "),
+          ))
+        }),
+      )
+      let order = case found {
+        [#(_, o), ..] -> list.filter(o, fn(l) { l != "" })
+        [] -> []
+      }
+      let by_lang = list.map(found, fn(f) { #({ f.0 }.lang, f.0) }) |> dict.from_list
+      // the manifest's order, and anything it did not name after it
+      let named = list.filter_map(order, fn(l) { dict.get(by_lang, l) })
+      let rest =
+        list.filter(found, fn(f) { !list.contains(order, { f.0 }.lang) })
+        |> list.map(fn(f) { f.0 })
+      Ok(list.append(named, rest))
+    }
+    load.Unknown -> Error(path <> ": " <> load.source_name(load.Unknown))
+  }
+}
+
+/// Only a `.ocda.db` carries files.
+pub fn is_carrier(path: String) -> Bool {
+  load.source_of(path) == load.OcdaDb
+}
+
+pub fn carried(path: String) -> Result(List(Carried), String) {
+  case is_carrier(path) {
+    False -> Ok([])
+    True -> {
+      use rows <- result.try(load_db.carried_of_file(path))
+      Ok(
+        list.filter_map(rows, fn(r) {
+          case r {
+            [role, compression, n, bytes, stored] ->
+              Ok(Carried(role, compression, n, bytes, stored))
+            _ -> Error(Nil)
+          }
+        }),
+      )
+    }
+  }
+}
+
+fn source_value(source: dict.Dict(String, String), key: String) -> String {
+  result.unwrap(dict.get(source, key), "")
+}
+
+@external(erlang, "ocda_ffi", "sha256_hex")
+fn sha256_hex(bytes: BitArray) -> String