libexpr: Canonicalize TOML timestamps for toml11 > 4.0

This addresses several changes from toml11 4.0 bump in
nixpkgs [1].

1. Added more regression tests for timestamp formats.
   Special attention needs to be paid to the precision
   of the subsecond range for local-time. Prior versions select the closest
   (upwards) multiple of 3 with a hard cap of 9 digits.

2. Normalize local datetime and offset datetime to always
   use the uppercase separator `T`. This is actually the issue
   surfaced in [2]. This canonicalization is basically a requirement
   by (a certain reading) of rfc3339 section 5.6 [3].

3. If using toml11 >= 4.0 also keep the old behavior wrt
   to the number of digits used for subsecond part of the local-time.
   Newer versions cap it at 6 digits unconditionally.

[1]: https://www.github.com/NixOS/nixpkgs/pull/331649
[2]: https://www.github.com/NixOS/nix/issues/11441
[3]: https://datatracker.ietf.org/doc/html/rfc3339

Author: xokdvium

src/libexpr/meson.build

@@ -71,6 +71,12 @@ toml11 = dependency(
   method : 'cmake',
   include_type : 'system',
 )
+
+configdata_priv.set(
+  'HAVE_TOML11_4',
+  toml11.version().version_compare('>= 4.0.0').to_int(),
+)
+
 deps_other += toml11
 
 config_priv_h = configure_file(

src/libexpr/primops/fromTOML.cc

@@ -1,12 +1,91 @@
 #include "nix/expr/primops.hh"
 #include "nix/expr/eval-inline.hh"
 
+#include "expr-config-private.hh"
+
 #include <sstream>
 
 #include <toml.hpp>
 
 namespace nix {
 
+#if HAVE_TOML11_4
+
+/**
+ * This is what toml11 < 4.0 did when choosing the subsecond precision.
+ * TOML 1.0.0 spec doesn't define how sub-millisecond ranges should be handled and calls it
+ * implementation defined behavior. For a lack of a better choice we stick with what older versions
+ * of toml11 did [1].
+ *
+ * [1]: https://github.com/ToruNiina/toml11/blob/dcfe39a783a94e8d52c885e5883a6fbb21529019/toml/datetime.hpp#L282
+ */
+static size_t normalizeSubsecondPrecision(toml::local_time lt)
+{
+    auto millis = lt.millisecond;
+    auto micros = lt.microsecond;
+    auto nanos = lt.nanosecond;
+    if (millis != 0 || micros != 0 || nanos != 0) {
+        if (micros != 0 || nanos != 0) {
+            if (nanos != 0)
+                return 9;
+            return 6;
+        }
+        return 3;
+    }
+    return 0;
+}
+
+/**
+ * Normalize date/time formats to serialize to the same strings as versions prior to toml11 4.0.
+ *
+ * Several things to consider:
+ *
+ * 1. Sub-millisecond range is represented the same way as in toml11 versions prior to 4.0. Precisioun is rounded
+ *    towards the next multiple of 3 or capped at 9 digits.
+ * 2. Seconds must be specified. This may become optional in (yet unreleased) TOML 1.1.0, but 1.0.0 defined local time
+ *    in terms of RFC3339 [1].
+ * 3. date-time separator (`t`, `T` or space ` `) is canonicalized to an upper T. This is compliant with RFC3339
+ *    [1] 5.6:
+ *    > Applications that generate this format SHOULD use upper case letters.
+ *
+ * [1]: https://datatracker.ietf.org/doc/html/rfc3339#section-5.6
+ */
+static void normalizeDatetimeFormat(toml::value & t)
+{
+    if (t.is_local_datetime()) {
+        auto & ldt = t.as_local_datetime();
+        t.as_local_datetime_fmt() = {
+            .delimiter = toml::datetime_delimiter_kind::upper_T,
+            // https://datatracker.ietf.org/doc/html/rfc3339#section-5.6
+            .has_seconds = true, // Mandated by TOML 1.0.0
+            .subsecond_precision = normalizeSubsecondPrecision(ldt.time),
+        };
+        return;
+    }
+
+    if (t.is_offset_datetime()) {
+        auto & odt = t.as_offset_datetime();
+        t.as_offset_datetime_fmt() = {
+            .delimiter = toml::datetime_delimiter_kind::upper_T,
+            // https://datatracker.ietf.org/doc/html/rfc3339#section-5.6
+            .has_seconds = true, // Mandated by TOML 1.0.0
+            .subsecond_precision = normalizeSubsecondPrecision(odt.time),
+        };
+        return;
+    }
+
+    if (t.is_local_time()) {
+        auto & lt = t.as_local_time();
+        t.as_local_time_fmt() = {
+            .has_seconds = true, // Mandated by TOML 1.0.0
+            .subsecond_precision = normalizeSubsecondPrecision(lt),
+        };
+        return;
+    }
+}
+
+#endif
+
 static void prim_fromTOML(EvalState & state, const PosIdx pos, Value ** args, Value & val)
 {
     auto toml = state.forceStringNoCtx(*args[0], pos, "while evaluating the argument passed to builtins.fromTOML");
@@ -53,6 +132,9 @@ static void prim_fromTOML(EvalState & state, const PosIdx pos, Value ** args, Va
         case toml::value_t::local_date:
         case toml::value_t::local_time: {
             if (experimentalFeatureSettings.isEnabled(Xp::ParseTomlTimestamps)) {
+#if HAVE_TOML11_4
+                normalizeDatetimeFormat(t);
+#endif
                 auto attrs = state.buildBindings(2);
                 attrs.alloc("_type").mkString("timestamp");
                 std::ostringstream s;
@@ -72,7 +154,17 @@ static void prim_fromTOML(EvalState & state, const PosIdx pos, Value ** args, Va
     };
 
     try {
-        visit(visit, val, toml::parse(tomlStream, "fromTOML" /* the "filename" */));
+        visit(
+            visit,
+            val,
+            toml::parse(
+                tomlStream,
+                "fromTOML" /* the "filename" */
+#if HAVE_TOML11_4
+                ,
+                toml::spec::v(1, 0, 0) // Be explicit that we are parsing TOML 1.0.0 without extensions
+#endif
+                ));
     } catch (std::exception & e) { // TODO: toml::syntax_error
         state.error<EvalError>("while parsing TOML: %s", e.what()).atPos(pos).debugThrow();
     }