fix: parse RFC 3339 created_at and improve IndexConfig repr (#3558)

The server now serializes an index's `created_at` as an RFC 3339 string
(e.g. `"2026-06-18T21:37:36.637Z"`), but the client deserializer only
accepted a unix timestamp in milliseconds. This caused `list_indices` to
fail with:

```
Failed to parse list_indices response: invalid type: string "2026-06-18T21:37:36.637Z", expected a unix timestamp in milliseconds
```

This PR replaces the fixed millisecond deserializer with a custom one
that accepts both an RFC 3339 string (current server) and a
unix-millisecond integer (legacy deployments), so the client works
against any server version.

It also improves the `IndexConfig` repr in the Python bindings.
Previously it printed only three fields (`Index(FTS, columns=["text"],
name="text_idx")`), hiding the metadata that `list_indices` returns. It
now renders every populated field, omitting any that are `None`. Each
value is valid Python — integer counts use `_` thousands separators and
`created_at` uses the `datetime` repr — so values round-trip. The real
repr is a single line; it's wrapped here for readability:

```python
>>> table.list_indices()
[IndexConfig(
    name="text_idx",
    index_type="FTS",
    columns=["text"],
    index_uuid="aefd3e00-2f95-4bdc-92ac-06de84442bf1",
    type_url="/lance.table.InvertedIndexDetails",
    created_at=datetime.datetime(2026, 6, 18, 21, 37, 36, 637000, tzinfo=datetime.timezone.utc),
    num_indexed_rows=2,
    size_bytes=3_669,
    num_segments=1,
    index_version=1,
    index_details={
        'lance_tokenizer': None,
        'base_tokenizer': 'simple',
        'language': 'English',
        'with_position': False,
        'max_token_length': 40,
        'lower_case': True,
        'stem': True,
        'remove_stop_words': True,
        'custom_stop_words': None,
        'ascii_folding': True,
        'min_ngram_length': 3,
        'max_ngram_length': 3,
        'prefix_only': False,
    },
)]
```

Fixes #3556

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Will Jones
2026-06-19 10:40:56 -07:00
committed by GitHub
parent c46d59d2ee
commit 85d870b397
3 changed files with 165 additions and 13 deletions

View File

@@ -319,11 +319,53 @@ pub struct IndexConfig {
#[pymethods]
impl IndexConfig {
pub fn __repr__(&self) -> String {
format!(
"Index({}, columns={:?}, name=\"{}\")",
self.index_type, self.columns, self.name
)
pub fn __repr__(&self, py: Python<'_>) -> String {
let mut fields = vec![
format!("name={:?}", self.name),
format!("index_type={:?}", self.index_type),
format!("columns={:?}", self.columns),
];
if let Some(v) = &self.index_uuid {
fields.push(format!("index_uuid={:?}", v));
}
if let Some(v) = &self.type_url {
fields.push(format!("type_url={:?}", v));
}
if let Some(v) = self.created_at {
// Render the datetime's own Python repr so the value round-trips,
// falling back to RFC 3339 if the conversion ever fails.
let rendered = v
.into_pyobject(py)
.ok()
.and_then(|obj| obj.into_any().repr().ok())
.map(|r| r.to_string())
.unwrap_or_else(|| v.to_rfc3339());
fields.push(format!("created_at={}", rendered));
}
if let Some(v) = self.num_indexed_rows {
fields.push(format!("num_indexed_rows={}", fmt_thousands(v)));
}
if let Some(v) = self.num_unindexed_rows {
fields.push(format!("num_unindexed_rows={}", fmt_thousands(v)));
}
if let Some(v) = self.size_bytes {
fields.push(format!("size_bytes={}", fmt_thousands(v)));
}
if let Some(v) = self.num_segments {
fields.push(format!("num_segments={}", v));
}
if let Some(v) = self.index_version {
fields.push(format!("index_version={}", v));
}
if let Some(v) = &self.index_details {
let details = v
.bind(py)
.repr()
.map(|r| r.to_string())
.unwrap_or_else(|_| "<unavailable>".to_string());
fields.push(format!("index_details={}", details));
}
format!("IndexConfig({})", fields.join(", "))
}
// For backwards-compatibility with the old sync SDK, we also support getting
@@ -352,6 +394,23 @@ impl IndexConfig {
}
}
/// Format an integer with `_` thousands separators, e.g. `24_500_213`.
///
/// Underscores are valid Python int-literal syntax, so the repr stays
/// copy-pasteable and machine-parseable while remaining readable.
fn fmt_thousands(n: u64) -> String {
let digits = n.to_string();
let bytes = digits.as_bytes();
let mut out = String::with_capacity(digits.len() + digits.len() / 3);
for (i, b) in bytes.iter().enumerate() {
if i > 0 && (bytes.len() - i).is_multiple_of(3) {
out.push('_');
}
out.push(*b as char);
}
out
}
fn parse_index_details(py: Python<'_>, s: String) -> Py<PyAny> {
let json = py.import("json").expect("json module is always available");
match json.call_method1("loads", (s.as_str(),)) {