summaryrefslogtreecommitdiffhomepage
path: root/gleam/src
diff options
context:
space:
mode:
Diffstat (limited to 'gleam/src')
-rw-r--r--gleam/src/ocda/inventory.gleam138
-rw-r--r--gleam/src/ocda/load_db.gleam108
-rw-r--r--gleam/src/ocda/load_pod.gleam6
-rw-r--r--gleam/src/ocda/load_ssp.gleam2
-rw-r--r--gleam/src/ocda_ffi.erl7
-rw-r--r--gleam/src/ocda_lib.gleam14
-rw-r--r--gleam/src/read/main.gleam459
7 files changed, 726 insertions, 8 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
diff --git a/gleam/src/ocda/load_db.gleam b/gleam/src/ocda/load_db.gleam
index 641923e..3ae4f0b 100644
--- a/gleam/src/ocda/load_db.gleam
+++ b/gleam/src/ocda/load_db.gleam
@@ -5,7 +5,7 @@
//// then a function from the model to bytes and cannot tell which
//// serialisation it was given, exactly as spine's own writers cannot.
////
-//// Written against `ocda-db-format-specification.md`, whose section 4
+//// Written against `ocda-db-format-specification.org`, whose section 4
//// gives the column by column correspondence this module implements.
import gleam/dict
@@ -112,6 +112,7 @@ pub fn load_file(
)
let document = metadata(conn, chosen.doc_id, document)
let document = objects(conn, chosen.doc_id, document)
+ let document = count_unread(conn, chosen.doc_id, document)
Ok(document)
}
@@ -561,3 +562,108 @@ fn json_joined(value: String) -> String {
parts -> string.join(parts, "|")
}
}
+
+/// What the database holds and the model does not.
+///
+/// The text loader meets every property line and counts those it does not
+/// keep, so a reader can say what was read and not understood. This loader
+/// asks for columns by name, and would never see the ones it did not ask
+/// for: it would report that it had understood everything, which is the
+/// silence the count exists to prevent. So it counts them, on the
+/// conditions under which the `.ssp` writes the same property
+/// (specification section 6.3), and the report is the same from either
+/// form, as the D loader's is.
+fn count_unread(
+ conn: sqlight.Connection,
+ doc_id: Int,
+ document: Document,
+) -> Document {
+ let id = int.to_string(doc_id)
+ let counts = [
+ #("ancestors_collapsed", "coalesce(ancestors_collapsed,'') != ''"),
+ #("dom_status", "coalesce(dom_status,'') != ''"),
+ #("dom_status_collapsed", "coalesce(dom_status_collapsed,'') != ''"),
+ #("heading_lev_collapsed", "heading_lev_collapsed is not null"),
+ #("parent_lev", "coalesce(parent_lev,0) != 0"),
+ #("segment_lv4_is", "coalesce(segment_lv4_is,'') != ''"),
+ #("attrib", "coalesce(attrib,'') != ''"),
+ ]
+ let property =
+ list.fold(counts, document.unknown.property, fn(acc, c) {
+ let n =
+ count(
+ conn,
+ "select count(*) from objects where doc_id = " <> id <> " and " <> c.1,
+ )
+ case n > 0 {
+ True -> dict.insert(acc, c.0, n)
+ False -> acc
+ }
+ })
+ let property = case has(conn, "object_subtoc") {
+ False -> property
+ True -> {
+ let n =
+ count(
+ conn,
+ "select count(*) from object_subtoc s join objects o
+ on o.id = s.object_id where o.doc_id = " <> id,
+ )
+ case n > 0 {
+ True -> dict.insert(property, "lev4_subtoc", n)
+ False -> property
+ }
+ }
+ }
+ model.Document(
+ ..document,
+ unknown: model.Unknown(..document.unknown, property: property),
+ )
+}
+
+fn count(conn: sqlight.Connection, sql: String) -> Int {
+ let d = decode.field(0, decode.int, decode.success)
+ case sqlight.query(sql, on: conn, with: [], expecting: d) {
+ Ok([n, ..]) -> n
+ _ -> 0
+ }
+}
+
+/// Every language the database at `path` holds, in manifest order.
+pub fn languages_of_file(path: String) -> Result(List(Language), String) {
+ use conn <- with_connection("file:" <> path <> "?mode=ro", path)
+ Ok(languages(conn))
+}
+
+/// What the database at `path` carries besides the abstraction, by role
+/// and storage: role, compression, count, original bytes, stored bytes.
+pub fn carried_of_file(path: String) -> Result(List(List(String)), String) {
+ use conn <- with_connection("file:" <> path <> "?mode=ro", path)
+ case has(conn, "files") {
+ False -> Ok([])
+ True -> {
+ let d = {
+ use role <- decode.field(0, decode.string)
+ use compression <- decode.field(1, decode.string)
+ use n <- decode.field(2, decode.int)
+ use bytes <- decode.field(3, decode.int)
+ use stored <- decode.field(4, decode.int)
+ decode.success([
+ role,
+ compression,
+ int.to_string(n),
+ int.to_string(bytes),
+ int.to_string(stored),
+ ])
+ }
+ sqlight.query(
+ "select role, compression, count(*), sum(bytes), sum(length(data))
+ from files group by role, compression order by role",
+ on: conn,
+ with: [],
+ expecting: d,
+ )
+ |> result.map_error(fn(e) { path <> ": " <> e.message })
+ }
+ }
+}
diff --git a/gleam/src/ocda/load_pod.gleam b/gleam/src/ocda/load_pod.gleam
index 35483c6..05f7add 100644
--- a/gleam/src/ocda/load_pod.gleam
+++ b/gleam/src/ocda/load_pod.gleam
@@ -89,7 +89,7 @@ fn langs(entries: List(zip.Entry)) -> List(String) {
}
/// `<uid>.<lang>.ssp` -> `<lang>`
-fn lang_of(name: String) -> Result(String, Nil) {
+pub fn lang_of(name: String) -> Result(String, Nil) {
case string.ends_with(name, ".ssp") {
False -> Error(Nil)
True -> {
@@ -104,7 +104,7 @@ fn lang_of(name: String) -> Result(String, Nil) {
/// The bytes decide, not the name: a file misnamed either way is treated by
/// what it holds.
-fn archive_bytes(path: String) -> Result(BitArray, String) {
+pub fn archive_bytes(path: String) -> Result(BitArray, String) {
case simplifile.read_bits(path) {
Error(e) -> Error(path <> ": " <> simplifile.describe_error(e))
Ok(bytes) ->
@@ -133,6 +133,6 @@ fn is_zstd_frame(bytes: BitArray) -> Bool {
@external(erlang, "unicode", "characters_to_binary")
fn bit_array_to_string_ffi(b: BitArray) -> String
-fn bit_array_to_string(b: BitArray) -> Result(String, Nil) {
+pub fn bit_array_to_string(b: BitArray) -> Result(String, Nil) {
Ok(bit_array_to_string_ffi(b))
}
diff --git a/gleam/src/ocda/load_ssp.gleam b/gleam/src/ocda/load_ssp.gleam
index ec93ef5..324319e 100644
--- a/gleam/src/ocda/load_ssp.gleam
+++ b/gleam/src/ocda/load_ssp.gleam
@@ -4,7 +4,7 @@
//// apart by its first character, so the loader is a fold over the lines
//// carrying the state the shapes need.
////
-//// Written against `ssp-format-specification.md`. Where it and the D
+//// Written against `ssp-format-specification.org`. Where it and the D
//// library differ the D library is the bug, or this is: they are meant to
//// give the same model, and `ocda-dump` says whether they do.
diff --git a/gleam/src/ocda_ffi.erl b/gleam/src/ocda_ffi.erl
new file mode 100644
index 0000000..2e395cd
--- /dev/null
+++ b/gleam/src/ocda_ffi.erl
@@ -0,0 +1,7 @@
+%% The one thing ocda-lib asks of Erlang directly: a sha256, which OTP's
+%% crypto has and the Gleam standard library does not. Upper case hex, as
+%% the database stores it and the D library writes it.
+-module(ocda_ffi).
+-export([sha256_hex/1]).
+
+sha256_hex(Bin) -> binary:encode_hex(crypto:hash(sha256, Bin)).
diff --git a/gleam/src/ocda_lib.gleam b/gleam/src/ocda_lib.gleam
index 1e8a5ae..6eccaff 100644
--- a/gleam/src/ocda_lib.gleam
+++ b/gleam/src/ocda_lib.gleam
@@ -1,10 +1,11 @@
//// ocda-lib, in Gleam: the abstraction as a library, put to the question.
////
-//// A library has no binary, so this is the two programs that test its
-//// claims.
+//// A library has no binary, so this is the programs over it: the reader,
+//// and the two that test its claims.
////
//// ocda-lib dump [--unknown] <file>.ssp|<file>.ocda.db [lang]
//// ocda-lib agree <doc>.ssp <doc>.ocda.db [lang]
+//// ocda-lib read [options] <file> [lang] (also installed as ocda-read)
////
//// `dump` writes the whole loaded model out canonically, byte for byte as
//// the D library's `ocda-dump` writes it, so that the two implementations
@@ -20,6 +21,7 @@ import gleam/string
import ocda/dump
import ocda/load
import ocda/model.{type Document}
+import read/main as reader
pub fn main() {
case argv.load().arguments {
@@ -29,6 +31,11 @@ pub fn main() {
["dump", path, lang] -> dump_file(path, lang, False)
["agree", ssp, db] -> agree(ssp, db, "")
["agree", ssp, db, lang] -> agree(ssp, db, lang)
+ ["read", ..rest] ->
+ case reader.run(rest) {
+ 0 -> Nil
+ code -> halt(code)
+ }
_ -> usage()
}
}
@@ -36,7 +43,8 @@ pub fn main() {
fn usage() -> Nil {
io.println_error(
"usage: ocda-lib dump [--unknown] <file>.ssp|<file>.ocda.db [lang]
- ocda-lib agree <doc>.ssp <doc>.ocda.db [lang]",
+ ocda-lib agree <doc>.ssp <doc>.ocda.db [lang]
+ ocda-lib read [--help] [options] <file> [lang]",
)
halt(2)
}
diff --git a/gleam/src/read/main.gleam b/gleam/src/read/main.gleam
new file mode 100644
index 0000000..307b8d8
--- /dev/null
+++ b/gleam/src/read/main.gleam
@@ -0,0 +1,459 @@
+//// ocda-read, in Gleam: reads the abstraction, in any of the forms the
+//// library reads, and says what is in it.
+////
+//// ocda-read [--tree|--outline|--languages|--files|--report-unknown]
+//// <file>.ssp | <file>.ocda.db | <file>.zip [lang]
+////
+//// The modes the Gleam readers had (the summary, the outline, the unknown
+//// report, and the database's languages and files), over the library, so
+//// that each reads every form. Their output is the D ocda-read's, byte for
+//// byte: two readers in unrelated languages, neither written from the other
+//// line by line, agreeing is what says each has read the model and not its
+//// own idea of it. A `.sisupod` is the one form the Gleam library cannot
+//// open (its zstd frame; see `ocda/load_pod`), and it says so.
+
+import gleam/dict
+import gleam/int
+import gleam/io
+import gleam/list
+import gleam/result
+import gleam/string
+import ocda/inventory.{type Language}
+import ocda/load
+import ocda/model.{type Document, type Object}
+
+/// The format major this reader knows.
+const major_read = "2"
+
+type Options {
+ Options(
+ tree: Bool,
+ languages: Bool,
+ files: Bool,
+ report_unknown: Bool,
+ any_version: Bool,
+ lang: String,
+ positional: List(String),
+ )
+}
+
+/// Run with the arguments after the program name; returns the exit status.
+pub fn run(args: List(String)) -> Int {
+ case parse(args, Options(False, False, False, False, False, "", [])) {
+ Error(message) -> {
+ io.println_error("ocda-read: " <> message <> "; --help lists the options")
+ 2
+ }
+ Ok(Options(positional: [], ..)) -> {
+ help()
+ 0
+ }
+ Ok(options) -> read(options)
+ }
+}
+
+fn parse(args: List(String), o: Options) -> Result(Options, String) {
+ case args {
+ [] -> Ok(Options(..o, positional: list.reverse(o.positional)))
+ ["--help", ..] | ["-h", ..] -> Ok(Options(..o, positional: []))
+ ["--tree", ..rest] | ["--outline", ..rest] ->
+ parse(rest, Options(..o, tree: True))
+ ["--languages", ..rest] -> parse(rest, Options(..o, languages: True))
+ ["--files", ..rest] -> parse(rest, Options(..o, files: True))
+ ["--report-unknown", ..rest] ->
+ parse(rest, Options(..o, report_unknown: True))
+ ["--any-version", ..rest] -> parse(rest, Options(..o, any_version: True))
+ ["--lang", code, ..rest] -> parse(rest, Options(..o, lang: code))
+ [flag, ..rest] ->
+ case string.starts_with(flag, "--lang=") {
+ True -> parse(rest, Options(..o, lang: string.drop_start(flag, 7)))
+ False ->
+ case string.starts_with(flag, "-") {
+ True ->
+ case
+ list.contains(
+ [
+ "--html", "--llm-text", "--llm-jsonl", "--images", "--verify",
+ "--validate",
+ ],
+ flag,
+ )
+ {
+ True ->
+ Error(flag <> " is a mode of the D ocda-read, not of this one")
+ False -> Error("Unrecognized option " <> flag)
+ }
+ False ->
+ parse(rest, Options(..o, positional: [flag, ..o.positional]))
+ }
+ }
+ }
+}
+
+fn help() -> Nil {
+ io.println("ocda-read - reads the document abstraction, in any of its forms")
+ io.println("")
+ io.println(
+ "Usage: ocda-read [options] <file>.ssp|<file>.ocda.db|<file>.zip [lang]",
+ )
+ io.println("")
+ io.println(" --tree the headings, as a tree")
+ io.println(" --outline the same as --tree")
+ io.println(" --languages the languages the file holds")
+ io.println(" --files what a .ocda.db carries besides the abstraction")
+ io.println(" --report-unknown what was read and not understood")
+ io.println(" --lang=<code> the language to read (default: the first)")
+ io.println(" --any-version read a format major this reader does not know")
+}
+
+fn read(o: Options) -> Int {
+ let assert [path, ..more] = o.positional
+ let lang = case o.lang, more {
+ "", [given, ..] -> given
+ l, _ -> l
+ }
+ let lang_named = lang != ""
+ let loaded = {
+ use held <- result.try(inventory.languages(path))
+ let lang = case lang, held {
+ "", [first, ..] -> first.lang
+ l, _ -> l
+ }
+ use _ <- result.try(case
+ held != [] && !list.any(held, fn(l) { l.lang == lang })
+ {
+ True ->
+ Error(
+ "no language '"
+ <> lang
+ <> "' in "
+ <> path
+ <> "; it holds: "
+ <> string.join(list.map(held, fn(l) { l.lang }), " "),
+ )
+ False -> Ok(Nil)
+ })
+ use doc <- result.try(load.load(path, lang, o.any_version))
+ Ok(#(held, lang, doc))
+ }
+ case loaded {
+ Error(message) -> {
+ io.println_error("Error reading " <> path <> ": " <> message)
+ 2
+ }
+ Ok(#(held, lang, doc)) ->
+ case gate(path, doc, o.any_version) {
+ False -> 3
+ True -> {
+ summary(path, doc, held, lang, lang_named)
+ case o.languages {
+ True -> print_languages(held)
+ False -> Nil
+ }
+ case o.files {
+ True -> print_files(path)
+ False -> Nil
+ }
+ case o.tree {
+ True -> tree(doc)
+ False -> Nil
+ }
+ case o.report_unknown {
+ True -> report_unknown(doc)
+ False -> Nil
+ }
+ case o.tree || o.languages || o.files || o.report_unknown {
+ True -> Nil
+ False ->
+ io.println(
+ "\n(this is the summary: --help lists the modes, each adding its output)",
+ )
+ }
+ 0
+ }
+ }
+ }
+}
+
+/// The major part, and refuse what is not known.
+fn gate(path: String, doc: Document, any_version: Bool) -> Bool {
+ case doc.format_version, model.version_major(doc) == major_read, any_version {
+ "", _, _ -> {
+ io.println_error("warning: " <> path <> " declares no format version")
+ True
+ }
+ _, True, _ -> True
+ v, False, True -> {
+ io.println_error(
+ "warning: "
+ <> path
+ <> " is format v"
+ <> v
+ <> ", this reader knows v"
+ <> major_read
+ <> ".x; reading anyway",
+ )
+ True
+ }
+ v, False, False -> {
+ io.println_error(
+ "error: "
+ <> path
+ <> " is format v"
+ <> v
+ <> ", this reader knows v"
+ <> major_read
+ <> ".x",
+ )
+ io.println_error(
+ " a major version differs: a property may have changed meaning or gone away.",
+ )
+ io.println_error(" --any-version reads it regardless.")
+ False
+ }
+ }
+}
+
+const sections = [
+ "head", "toc", "body", "endnotes", "glossary", "bibliography", "bookindex",
+ "blurb", "tail",
+]
+
+/// The sections whose images are counted: every one but the tail, as the D
+/// reader counts them.
+const image_sections = [
+ "head", "toc", "body", "endnotes", "glossary", "bibliography", "bookindex",
+ "blurb",
+]
+
+fn summary(
+ path: String,
+ doc: Document,
+ held: List(Language),
+ lang: String,
+ lang_named: Bool,
+) -> Nil {
+ io.println("Read: " <> path)
+ case doc.format_version {
+ "" -> Nil
+ v -> io.println(" Format: v" <> v)
+ }
+ case dict.get(doc.source, "language") {
+ Error(_) -> Nil
+ Ok(language) -> {
+ let of = case dict.get(doc.source, "languages") {
+ Ok(ls) -> " of " <> ls
+ Error(_) -> ""
+ }
+ let digest = case dict.get(doc.source, "digest") {
+ Ok(d) -> ", markup digest " <> string.slice(d, 0, 16) <> "..."
+ Error(_) -> ""
+ }
+ io.println(" Source: " <> language <> of <> digest)
+ }
+ }
+ case list.length(held) > 1 && !lang_named {
+ True -> io.println(" (reading " <> lang <> "; --lang=<code> for another)")
+ False -> Nil
+ }
+ io.println(" Title: " <> model.meta(doc, "title.main"))
+ io.println(" Author: " <> model.meta(doc, "creator.author"))
+ io.println(
+ " Sections: "
+ <> string.join(
+ list.map(sections, fn(s) {
+ s <> "=" <> int.to_string(list.length(model.section(doc, s)))
+ }),
+ " ",
+ ),
+ )
+ let records =
+ list.fold(image_sections, 0, fn(n, s) {
+ list.fold(model.section(doc, s), n, fn(n, o) {
+ n + list.length(o.images)
+ })
+ })
+ case records {
+ 0 -> Nil
+ 1 -> io.println(" Images: 1 record")
+ n -> io.println(" Images: " <> int.to_string(n) <> " records")
+ }
+}
+
+fn print_languages(held: List(Language)) -> Nil {
+ io.println("")
+ io.println(" lang source ssp digest")
+ list.each(held, fn(l) {
+ let digest = case string.length(l.ssp_digest) > 16 {
+ True -> string.slice(l.ssp_digest, 0, 16) <> "..."
+ False -> l.ssp_digest
+ }
+ io.println(
+ " "
+ <> string.pad_end(l.lang, 7, " ")
+ <> " "
+ <> string.pad_end(l.source_filename, 31, " ")
+ <> " "
+ <> digest,
+ )
+ })
+}
+
+fn print_files(path: String) -> Nil {
+ io.println("")
+ case inventory.is_carrier(path) {
+ False ->
+ io.println(
+ " carried files: only a .ocda.db carries files; this is "
+ <> load.source_name(load.source_of(path)),
+ )
+ True ->
+ case inventory.carried(path) {
+ Error(message) -> io.println_error("error: " <> message)
+ Ok([]) -> io.println(" carries no files")
+ Ok(rows) -> {
+ io.println(" carried files:")
+ io.println(" role stored n original in the file")
+ list.each(rows, fn(r) {
+ io.println(
+ " "
+ <> string.pad_end(r.role, 9, " ")
+ <> " "
+ <> string.pad_end(r.compression, 7, " ")
+ <> " "
+ <> string.pad_end(r.count, 5, " ")
+ <> " "
+ <> string.pad_end(r.bytes, 13, " ")
+ <> " "
+ <> r.stored,
+ )
+ })
+ }
+ }
+ }
+}
+
+/// The headings, as a tree: from the document's root heading, down the
+/// children each heading lists, as the D reader walks it.
+fn tree(doc: Document) -> Nil {
+ io.println("Document: " <> model.meta(doc, "title.main"))
+ case model.meta(doc, "title.subtitle") {
+ "" -> Nil
+ sub -> io.println(" " <> sub)
+ }
+ io.println("Author: " <> model.meta(doc, "creator.author"))
+ io.println("")
+ let headings =
+ model.section(doc, "body")
+ |> list.filter(fn(o) { o.is_a == "heading" && o.ocn > 0 })
+ |> list.map(fn(o) { #(o.ocn, o) })
+ |> dict.from_list
+ case model.section(doc, "head") {
+ [root, ..] if root.is_a == "heading" -> {
+ io.println(heading_line(root, 0))
+ walk(root, headings, 1)
+ }
+ _ -> Nil
+ }
+}
+
+fn walk(parent: Object, headings: dict.Dict(Int, Object), depth: Int) -> Nil {
+ list.each(parent.children, fn(ocn) {
+ case dict.get(headings, ocn) {
+ Ok(child) -> {
+ io.println(heading_line(child, depth))
+ walk(child, headings, depth + 1)
+ }
+ Error(_) -> Nil
+ }
+ })
+}
+
+fn heading_line(o: Object, depth: Int) -> String {
+ let level = case o.heading_level {
+ "" -> "?"
+ l -> l
+ }
+ let ocn = case o.ocn > 0 {
+ True -> " [" <> int.to_string(o.ocn) <> "]"
+ False -> ""
+ }
+ string.repeat(" ", depth) <> level <> "~" <> ocn <> " " <> strip_markup(o.text)
+}
+
+/// The internal markers a heading's text may carry, removed for display, as
+/// the D reader removes them.
+fn strip_markup(text: String) -> String {
+ text
+ |> string.replace("⑆*", "")
+ |> string.replace("⑆!", "")
+ |> string.replace("⑆/", "")
+ |> string.replace("⑆_", "")
+ |> string.replace("⑆^", "")
+ |> string.replace("⑆,", "")
+ |> string.replace("┨", "")
+ |> string.replace("┣", "")
+ |> string.replace("┙", " ")
+ |> string.replace("┘", "\n")
+}
+
+/// Say what was read and not understood.
+fn report_unknown(doc: Document) -> Nil {
+ let u = doc.unknown
+ case model.any_unknown(u) {
+ False ->
+ io.println(
+ "\nread and understood: every property, block and line was known",
+ )
+ True -> {
+ io.println("\nread and NOT understood:")
+ section_of_unknown(u.property, " properties ignored (", fn(name, n) {
+ " ."
+ <> string.pad_end(name, 26, " ")
+ <> " "
+ <> string.pad_start(int.to_string(n), 8, " ")
+ })
+ section_of_unknown(u.block, " blocks ignored (", fn(name, n) {
+ " @"
+ <> string.pad_end(name, 26, " ")
+ <> " "
+ <> string.pad_start(int.to_string(n), 8, " ")
+ })
+ case dict.size(u.line) {
+ 0 -> Nil
+ _ -> {
+ io.println(" lines of no known shape, by first character:")
+ dict.to_list(u.line)
+ |> list.sort(fn(a, b) { string.compare(a.0, b.0) })
+ |> list.each(fn(e) {
+ io.println(
+ " "
+ <> string.pad_end("\"" <> e.0 <> "\"", 27, " ")
+ <> " "
+ <> string.pad_start(int.to_string(e.1), 8, " "),
+ )
+ })
+ }
+ }
+ io.println(
+ " (ignoring these is conforming within a major version; the count is so that it is not silent)",
+ )
+ }
+ }
+}
+
+fn section_of_unknown(
+ counts: dict.Dict(String, Int),
+ heading: String,
+ line: fn(String, Int) -> String,
+) -> Nil {
+ case dict.size(counts) {
+ 0 -> Nil
+ n -> {
+ io.println(heading <> int.to_string(n) <> " distinct):")
+ dict.to_list(counts)
+ |> list.sort(fn(a, b) { string.compare(a.0, b.0) })
+ |> list.each(fn(e) { io.println(line(e.0, e.1)) })
+ }
+ }
+}
generated by cgit v1.2.3 (git 2.25.1) at 2026-11-15 16:36:54 +0000