gedcomkit 0.1.6__tar.gz → 0.1.8__tar.gz

{gedcomkit-0.1.6 → gedcomkit-0.1.8}/CHANGELOG.md

@@ -5,6 +5,72 @@ 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.
 
+## [0.1.8] - 2026-09-27
+
+### Added
+
+- Python wheels for Windows (x86_64) and macOS (Apple silicon and Intel)
+  on PyPI, beside the Linux wheel, so installing on those platforms no
+  longer compiles Rust from the source distribution. All three are
+  cross-compiled on the Linux release runner — macOS with zig, Windows with
+  cargo-xwin — and, being abi3, each serves Python 3.9 onward. (PyO3 links
+  `python3.dll` by raw-dylib, so the Windows build needs no Windows Python.)
+
+## [0.1.7] - 2026-09-27
+
+### Added
+
+- `dates::GedcomDate::to_gedcom_7`, the reading written in GEDCOM 7.0's own
+  date grammar (`about 5 January 1882` → `ABT 5 JAN 1882`), or `None` when
+  that grammar cannot hold it without loss — no `INT`, no dual year, and the
+  calendar as a bare word (`JULIAN 10 MAR 1700`).
+- Python and JavaScript/WASM: `parse_date` / `parseDate`'s reading gained a
+  `gedcom7` key alongside `gedcom551`.
+- `convert::to_version_7_with`'s owned-extension-tags parameter, now exposed
+  by both bindings: Python's `Gedcom.to_version7(owned=[(tag, uri), ...])`
+  and WASM's `toVersion7([[tag, uri], ...])`, either omittable.
+
+### Changed
+
+- `convert::to_version_7` now rewrites every `DATE` payload the lenient
+  reader understands but that is not version 7's own grammar — `29 May
+  1823`, `about 1575`, `13. september 1900`, `<1873>`, `ABT Oct 1803`,
+  `1740/41`, `@#DJULIAN@ 10 MAR 1700`, `44 B.C.`, and the like — instead of
+  passing most of them through unreported. Each becomes the version 7
+  reading (or, when none exists — an unparsed expression, a dual year, a
+  calendar version 7 cannot spell — an empty `DATE`), with the original kept
+  verbatim in a `PHRASE` substructure and the change named in the report. A
+  payload already in version 7's grammar is left untouched, byte for byte.
+- `convert::to_version_7` now converts `OBJE.FILE.FORM`'s file extension
+  (`jpg`, `png`, `pdf`, `html`, `txt`, …) to a version 7 media type
+  (`image/jpeg`, `image/png`, `application/pdf`, `text/html`,
+  `text/plain`, …) and `FORM.MEDI`'s source medium to version 7's
+  enumeration, upper case (`PHOTO`, `NEWSPAPER`, …), folding anything else
+  into `OTHER` with the original kept as a `PHRASE`. An extension with no
+  known media type is kept as written and reported as kept rather than
+  guessed. Both are named in the report under new `FILE.FORM` and
+  `FORM.MEDI` notes, alongside the existing `OBJE.FORM` note for the move
+  from object to file. This covers 5.5.1's own layout, where `FORM` already
+  sits under `FILE` and the source medium is `TYPE` (renamed `MEDI`), as
+  well as 5.5's `FORM` on the object. Known extensions now include `heic`,
+  `webp`, `svg`, `json`, `xml`, `eml` and `mp4`.
+- `convert::to_version_7` percent-encodes a `FILE` path that is not a URI
+  reference, as version 7 requires — a space, a backslash, anything outside
+  ASCII — and reports it under a `FILE` note. A path that is already a URI
+  reference, escapes included, is untouched.
+
+### Fixed
+
+- A `DATE` rewritten by the version 7 conversion no longer keeps the
+  `CONT`/`CONC` lines its old payload was split across, which a later read
+  folded back into the new payload. A `DATE` that already carries a
+  `PHRASE` is left as it is and reported as kept, rather than given a
+  second `PHRASE`.
+- `GedcomDate::to_gedcom_7` returns `None` for a Hebrew or French
+  Republican date with a month, rather than spelling that month with a
+  Gregorian abbreviation (`FRENCH_R 22 MAR 5`). A bare year is still
+  written.
+
 ## [0.1.6] - 2026-09-25
 
 ### Added

{gedcomkit-0.1.6 → gedcomkit-0.1.8}/Cargo.lock

@@ -35,7 +35,7 @@ dependencies = [
 
 [[package]]
 name = "gedcomkit"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "flate2",
  "serde",

{gedcomkit-0.1.6 → gedcomkit-0.1.8}/Cargo.toml

@@ -3,7 +3,7 @@
 # was checked on crates.io, npm, and PyPI before the initial release.
 [package]
 name = "gedcomkit"
-version = "0.1.6"
+version = "0.1.8"
 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

{gedcomkit-0.1.6 → gedcomkit-0.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gedcomkit
-Version: 0.1.6
+Version: 0.1.8
 Classifier: Development Status :: 3 - Alpha
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython

{gedcomkit-0.1.6 → gedcomkit-0.1.8}/bindings/gedcomkit-py/Cargo.lock

@@ -35,7 +35,7 @@ dependencies = [
 
 [[package]]
 name = "gedcomkit"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "flate2",
  "serde",
@@ -43,7 +43,7 @@ dependencies = [
 
 [[package]]
 name = "gedcomkit-py"
-version = "0.1.6"
+version = "0.1.8"
 dependencies = [
  "gedcomkit",
  "pyo3",

{gedcomkit-0.1.6 → gedcomkit-0.1.8}/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 = "0.1.6"
+version = "0.1.8"
 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-0.1.6 → gedcomkit-0.1.8}/bindings/gedcomkit-py/gedcomkit.pyi

@@ -60,7 +60,12 @@ class Gedcom:
     def set_logical_value(self, xref: str, path: list[int], value: str) -> None: ...
     def to_text(self) -> str: ...
     def to_bytes(self) -> bytes: ...
-    def to_version7(self) -> tuple[Gedcom, list[dict[str, Any]]]: ...
+    def to_version7(
+        self, owned: list[tuple[str, str]] | None = None
+    ) -> tuple[Gedcom, list[dict[str, Any]]]:
+        """Convert to GEDCOM 7.0. ``owned`` declares the caller's own
+        extension tags as ``(tag, uri)`` pairs; any other extension is
+        declared as undocumented rather than dropped."""
     def to_version551(self) -> tuple[Gedcom, list[dict[str, Any]]]: ...
     def __len__(self) -> int: ...
 
@@ -81,4 +86,5 @@ class ArchiveFileWriter:
 
 def archive_total_size(data: bytes) -> int: ...
 def parse_date(text: str) -> dict[str, Any]:
-    """A date reading; its ``gedcom551`` key is the 5.5.1 spelling, or None."""
+    """A date reading; its ``gedcom551`` and ``gedcom7`` keys are the 5.5.1
+    and 7.0 spellings, each ``None`` when that grammar cannot hold it."""

{gedcomkit-0.1.6 → gedcomkit-0.1.8}/bindings/gedcomkit-py/src/lib.rs

@@ -283,8 +283,24 @@ impl Gedcom {
 
     /// An explicit conversion to GEDCOM 7.0: the converted document and the
     /// notes naming every construct touched, dropped, or kept.
-    fn to_version7(&self, py: Python<'_>) -> PyResult<(Self, Vec<Py<PyAny>>)> {
-        let outcome = gedcomkit::convert::to_version_7(&self.document);
+    ///
+    /// `owned` names the extension tags the caller writes itself, each paired
+    /// with the URI it is documented at — `[("_PRIM", "https://example.com/PRIM")]`.
+    /// Those are declared by name; any other extension in the file is
+    /// declared as undocumented rather than dropped, because it is somebody's
+    /// data either way.
+    #[pyo3(signature = (owned = None))]
+    fn to_version7(
+        &self,
+        py: Python<'_>,
+        owned: Option<Vec<(String, String)>>,
+    ) -> PyResult<(Self, Vec<Py<PyAny>>)> {
+        let owned = owned.unwrap_or_default();
+        let owned: Vec<(&str, &str)> = owned
+            .iter()
+            .map(|(tag, uri)| (tag.as_str(), uri.as_str()))
+            .collect();
+        let outcome = gedcomkit::convert::to_version_7_with(&self.document, &owned);
         let notes = outcome
             .notes
             .iter()
@@ -466,20 +482,23 @@ fn os_error(path: &std::path::Path, error: &std::io::Error) -> PyErr {
     PyOSError::new_err(format!("{}: {error}", path.display()))
 }
 
-/// A date reading, with the two renderings a caller most often wants.
+/// A date reading, with the renderings a caller most often wants.
 #[derive(Serialize)]
 struct DateReading<'a> {
     #[serde(flatten)]
     date: &'a GedcomDate,
     display: String,
     gedcom551: Option<String>,
+    gedcom7: Option<String>,
 }
 
 /// Reads a date as the library reads any `DATE` payload — every language
 /// and spelling it knows — and returns the reading as a dict: `original`,
 /// `calendar`, `kind`, `earliest`, `latest`, `phrase`, the `display` form,
-/// and `gedcom551`, the reading in GEDCOM 5.5.1's own grammar (`ABT 5 JAN
-/// 1882`), or `None` when that grammar cannot hold it without loss.
+/// `gedcom551`, the reading in GEDCOM 5.5.1's own grammar (`ABT 5 JAN
+/// 1882`), and `gedcom7`, the reading in GEDCOM 7.0's own grammar (`ABT 5
+/// JAN 1882`, with no `INT` and no dual year) — either `None` when that
+/// grammar cannot hold it without loss.
 #[pyfunction]
 fn parse_date(py: Python<'_>, text: &str) -> PyResult<Py<PyAny>> {
     let date = GedcomDate::parse(text);
@@ -488,6 +507,7 @@ fn parse_date(py: Python<'_>, text: &str) -> PyResult<Py<PyAny>> {
         &DateReading {
             display: date.display(),
             gedcom551: date.to_gedcom_5_5_1(),
+            gedcom7: date.to_gedcom_7(),
             date: &date,
         },
     )