gedcomkit 0.1.10__tar.gz → 0.1.12__tar.gz

{gedcomkit-0.1.10 → gedcomkit-0.1.12}/CHANGELOG.md

@@ -5,6 +5,76 @@ format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and
 the project uses semantic versioning within the usual pre-1.0 compatibility
 rules.
 
+## [0.1.12] - 2026-09-30
+
+### Fixed
+
+- `convert::to_version_7` / `to_version_7_with` now fold every `CONC`
+  continuation into the text it continues. GEDCOM 7.0 removed `CONC` (and
+  every line length limit), but the conversion left each one in place, so a
+  file converted from 5.5.1 — one that had fitted its lines to 255 bytes
+  with `CONC` — was written as "7.0" with thousands of them. The folding is
+  `Node::logical_value`'s own, so the value reads exactly as before and a
+  space at a split is kept; `CONT` lines stay, and a `CONT` that took a
+  `CONC` is the only continuation rewritten. Structures with no `CONC`
+  keep their bytes, and a node gives up its own source line only when its own
+  payload changed, never because a descendant did. The report gets one
+  `CONC` note (converted) per record, with the counts (including structures
+  that had no payload, whose text became it), however many lines were folded.
+  A `CONC` is left in place, and reported as kept per structure with the
+  words "not valid version 7", when: it continues a pointer payload; folding
+  would make the text begin with `@` (a pointer, or the unescaped `@` version
+  7 forbids); a `CONC` carries an identifier or substructures; it sits under
+  a `CONT`/`CONC` line; or the joined line would pass 15 MiB. The
+  rewrites of a `DATE`, `FILE`, `FORM` or source medium are likewise
+  refused, and reported, when a continuation line of theirs has
+  substructures, so nothing is dropped.
+- The folding is linear in the number of continuation lines. A multimedia
+  `FORM` moved beneath each `FILE` gives up its source lines (they carry
+  their level), so a non-canonically spaced one no longer writes a file that
+  fails to read back. `to_version_5_5_1` keeps every `PHRASE` (reported) when
+  a date has more than one instead of dropping all but one. A `PHRASE` the
+  conversion writes with a leading `@` (a `@#DJULIAN@` calendar escape) has
+  it doubled, as 7.0 requires, and a `DATE` whose `CONC` starts with `@` is
+  no longer reported as kept before the rewrite that consumes it.
+- `Limits::DEFAULT.line_bytes` is now 16 MiB (was 64 KiB). 7.0 has no line
+  limit and no `CONC`, so a long note becomes one long line, and a document
+  this crate converts has to read back under its own defaults. It remains a
+  bound: the input stays capped by `input_bytes`.
+- `convert::to_version_5_5_1` no longer panics on a 7.0 `PHRASE` with a
+  `CONT`: a date or phrase that spans lines, or a phrase with substructures,
+  is kept as a `PHRASE` and reported (5.5.1 does not define it).
+- `convert::to_version_5_5_1` fits to 255 bytes the lines of the structures
+  it changed (a `DATE` folded back into `INT date (phrase)`, a renamed
+  `UID`, a `SNOTE` record made a `NOTE`), by the same `CONC` splitting as
+  `Node::fit_line_limit`. A line over 255 bytes in a structure it did not
+  change is left as written, since an untouched node is written back byte
+  for byte, and is reported as kept with a count per record;
+  `Document::wrap_long_lines` fits them on request.
+
+## [0.1.11] - 2026-09-28
+
+### Added
+
+- A `ts` feature (off by default; implies `serde`) that derives
+  `ts_rs::TS` on every type the `serde` feature serializes — the views, the
+  date, encoding, conversion, and validation reports — so a caller that
+  sends them to a TypeScript frontend can generate its types from these
+  definitions rather than keep hand-written copies in step. The definitions
+  follow the JSON exactly: camelCase field names, `null` for an absent
+  value, and unit enums as their variant names. `StructureView::kind`, a
+  `&'static str`, is declared as the five words it can hold
+  (`"record" | "event" | "attribute" | "structure" | "unknown"`). Pulls in
+  `ts-rs` 12 (MIT) and its proc-macro only when enabled.
+
+  Two things a caller should know. ts-rs declares a 64-bit integer as
+  `bigint` by default, while the JSON carries a number: export with
+  `Config::with_large_int("number")` (as `tests/typescript.rs` does) for
+  definitions that match what `serde_json` writes. And a
+  `#[non_exhaustive]` enum becomes a closed TypeScript union, so a variant
+  added in a later patch release — additive in Rust — can break an
+  exhaustive `switch` in TypeScript until the definitions are regenerated.
+
 ## [0.1.10] - 2026-09-27
 
 ### Added

{gedcomkit-0.1.10 → gedcomkit-0.1.12}/Cargo.lock

@@ -35,10 +35,11 @@ dependencies = [
 
 [[package]]
 name = "gedcomkit"
-version = "0.1.10"
+version = "0.1.12"
 dependencies = [
  "flate2",
  "serde",
+ "ts-rs",
 ]
 
 [[package]]
@@ -96,7 +97,7 @@ checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 3.0.5",
 ]
 
 [[package]]
@@ -105,6 +106,17 @@ version = "0.3.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3a219298ac11a56ea9a6d2120044824d6f01aeb034955e7af7bc16858527deea"
 
+[[package]]
+name = "syn"
+version = "2.0.119"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "872831b642d1a07999a962a351ed35b955ea2cfc8f3862091e2a240a84f17297"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
 [[package]]
 name = "syn"
 version = "3.0.5"
@@ -116,8 +128,83 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "termcolor"
+version = "1.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "06794f8f6c5c898b3275aebefa6b8a1cb24cd2c6c79397ab15774837a0bc5755"
+dependencies = [
+ "winapi-util",
+]
+
+[[package]]
+name = "thiserror"
+version = "2.0.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09e52cb86a36cede5cb101bf8908837b3e4c6e5e59fe7fd85c23fb56200d189e"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "2.0.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fe5197923287db20a58125f0bc85c062f7f2c892de97b18c356f9efb14b28524"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 3.0.5",
+]
+
+[[package]]
+name = "ts-rs"
+version = "12.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "756050066659291d47a554a9f558125db17428b073c5ffce1daf5dcb0f7231d8"
+dependencies = [
+ "thiserror",
+ "ts-rs-macros",
+]
+
+[[package]]
+name = "ts-rs-macros"
+version = "12.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "38d90eea51bc7988ef9e674bf80a85ba6804739e535e9cab48e4bb34a8b652aa"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+ "termcolor",
+]
+
 [[package]]
 name = "unicode-ident"
 version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+
+[[package]]
+name = "winapi-util"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
+dependencies = [
+ "windows-sys",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
+
+[[package]]
+name = "windows-sys"
+version = "0.61.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
+dependencies = [
+ "windows-link",
+]

{gedcomkit-0.1.10 → gedcomkit-0.1.12}/Cargo.toml

@@ -3,7 +3,7 @@
 # was checked on crates.io, npm, and PyPI before the initial release.
 [package]
 name = "gedcomkit"
-version = "0.1.10"
+version = "0.1.12"
 description = "A byte-preserving GEDCOM document model: decoding, parsing, readings, version conversion, plausibility checks, and the GEDZIP container, for GEDCOM 5.5 through 7.x."
 edition = "2024"
 # The true minimum, not the workspace's toolchain: a parser library is a leaf
@@ -42,6 +42,11 @@ gedzip = ["dep:flate2"]
 # Serialization of the read-only views, for callers that send them somewhere —
 # a webview, a JSON API. Off by default: a parser needs no serializer.
 serde = ["dep:serde"]
+# TypeScript definitions of those same serialized shapes (`ts_rs::TS` on every
+# type `serde` serializes), for a caller that generates its frontend's types
+# from them rather than writing them by hand. Off by default, and meant for a
+# build step or a test rather than a shipped binary.
+ts = ["serde", "dep:ts-rs"]
 # Generates a deterministic synthetic tree of any size, for performance and
 # stress fixtures. Off by default: nothing an application ships needs it.
 fixture = []
@@ -50,6 +55,9 @@ fixture = []
 # `rust_backend` keeps deflate in pure Rust, so no system zlib is needed.
 flate2 = { version = "1.1.2", default-features = false, features = ["rust_backend"], optional = true }
 serde = { version = "1", features = ["derive"], optional = true }
+# MIT; its default `serde-compat` reads the serde attributes, so the
+# definitions follow the JSON the `serde` feature writes.
+ts-rs = { version = "12.0.1", optional = true }
 
 [lints.rust]
 unsafe_code = "forbid"

{gedcomkit-0.1.10 → gedcomkit-0.1.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gedcomkit
-Version: 0.1.10
+Version: 0.1.12
 Classifier: Development Status :: 3 - Alpha
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython

{gedcomkit-0.1.10 → gedcomkit-0.1.12}/README.md

@@ -198,6 +198,9 @@ than dropped.
   `default-features = false` the parser core has **no dependencies at all**.
 - `serde` — `Serialize` on the views and reports, for callers that send them
   to a webview or over a wire. Off by default.
+- `ts` — TypeScript definitions of those same serialized shapes
+  (`ts_rs::TS`), for a caller that generates its frontend's types from them.
+  Implies `serde`. Off by default.
 - `fixture` — a deterministic, corpus-shaped synthetic tree generator of any
   size, for performance and stress tests. Off by default.
 

{gedcomkit-0.1.10 → gedcomkit-0.1.12}/bindings/gedcomkit-py/Cargo.lock

@@ -35,7 +35,7 @@ dependencies = [
 
 [[package]]
 name = "gedcomkit"
-version = "0.1.10"
+version = "0.1.12"
 dependencies = [
  "flate2",
  "serde",
@@ -43,7 +43,7 @@ dependencies = [
 
 [[package]]
 name = "gedcomkit-py"
-version = "0.1.10"
+version = "0.1.12"
 dependencies = [
  "gedcomkit",
  "pyo3",

{gedcomkit-0.1.10 → gedcomkit-0.1.12}/bindings/gedcomkit-py/Cargo.toml

@@ -2,7 +2,7 @@
 # abi3 keeps it to one wheel per platform across Python versions.
 [package]
 name = "gedcomkit-py"
-version = "0.1.10"
+version = "0.1.12"
 description = "Python bindings for gedcomkit: an archival-grade GEDCOM library — byte-preserving round-trip, encoding detection, GEDCOM 5.5 through 7.x, GEDZIP."
 edition = "2024"
 rust-version = "1.88"

{gedcomkit-0.1.10 → gedcomkit-0.1.12}/src/build.rs

@@ -171,6 +171,7 @@ impl NodeSpec {
 #[derive(Clone, Debug, PartialEq, Eq)]
 #[non_exhaustive]
 #[cfg_attr(feature = "serde", derive(serde::Serialize))]
+#[cfg_attr(feature = "ts", derive(ts_rs::TS))]
 #[cfg_attr(feature = "serde", serde(rename_all = "camelCase"))]
 pub struct WrappedLine {
     /// The record, by cross-reference identifier — or by tag, for the header
@@ -342,6 +343,17 @@ impl Node {
 }
 
 fn fit_node(node: &mut Node, level: usize, max_line: usize) -> bool {
+    fit_node_inner(node, level, max_line, true)
+}
+
+/// [`Node::fit_line_limit`] for this node's own lines only — its payload and
+/// the `CONT`/`CONC` run continuing it — leaving every other substructure as it
+/// is. For a conversion that changed this node and no other.
+pub(crate) fn fit_own_lines(node: &mut Node, level: usize, max_line: usize) -> bool {
+    fit_node_inner(node, level, max_line, false)
+}
+
+fn fit_node_inner(node: &mut Node, level: usize, max_line: usize, recurse: bool) -> bool {
     let run_len = node
         .children
         .iter()
@@ -396,7 +408,7 @@ fn fit_node(node: &mut Node, level: usize, max_line: usize) -> bool {
 
     let inserted = output.len();
     node.children.splice(0..0, output);
-    for child in node.children.iter_mut().skip(inserted) {
+    for child in node.children.iter_mut().skip(inserted).filter(|_| recurse) {
         changed |= fit_node(child, level + 1, max_line);
     }
     changed