deepdiff-rs 0.6.1__tar.gz → 0.6.2__tar.gz

{deepdiff_rs-0.6.1 → deepdiff_rs-0.6.2}/Cargo.lock

@@ -605,7 +605,7 @@ checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
 
 [[package]]
 name = "onix-arrow"
-version = "0.6.1"
+version = "0.6.2"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -615,7 +615,7 @@ dependencies = [
 
 [[package]]
 name = "onix-cli"
-version = "0.6.1"
+version = "0.6.2"
 dependencies = [
  "onix-core",
  "serde_json",
@@ -623,7 +623,7 @@ dependencies = [
 
 [[package]]
 name = "onix-core"
-version = "0.6.1"
+version = "0.6.2"
 dependencies = [
  "proptest",
  "serde",
@@ -633,7 +633,7 @@ dependencies = [
 
 [[package]]
 name = "onix-py"
-version = "0.6.1"
+version = "0.6.2"
 dependencies = [
  "arrow-array",
  "arrow-schema",

{deepdiff_rs-0.6.1 → deepdiff_rs-0.6.2}/Cargo.toml

@@ -3,7 +3,7 @@ resolver = "3"
 members = ["crates/onix-core", "crates/onix-py", "crates/onix-arrow"]
 
 [workspace.package]
-version = "0.6.1"
+version = "0.6.2"
 edition = "2024"
 license = "MIT"
 

{deepdiff_rs-0.6.1 → deepdiff_rs-0.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdiff-rs
-Version: 0.6.1
+Version: 0.6.2
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Rust
 Classifier: License :: OSI Approved :: MIT License
@@ -162,6 +162,7 @@ Type comparison uses the full logical Arrow type (timestamp unit and timezone, d
 - Adversarially deep input raises `MaxDepthError` instead of crashing: the default `max_depth` is 512 and the hard ceiling is `MAX_DEPTH_CEILING` (20,000). See [`crates/onix-py/src/guard.rs`](crates/onix-py/src/guard.rs).
 - `ignore_order` pairing is `O(N^2)` in unpaired elements per side and carries a polynomial cost in both time and memory with input depth; it has no `max_passes`/`max_diffs` cutoff, so bound the size and depth of untrusted input yourself. See [`crates/onix-core/src/ignore_order/mod.rs`](crates/onix-core/src/ignore_order/mod.rs).
 - A `values_changed` between two multi-line strings runs a `difflib`-style `O(N*M)` line diff on the default path with no opt-out, worst when changes are spread evenly through the text (about 35 s for a heavily edited 1 MB string and growing quadratically, so a few megabytes is minutes), so bound the size of untrusted strings yourself. See [`crates/onix-core/src/unified_diff.rs`](crates/onix-core/src/unified_diff.rs).
+- Ordered sequences (`list` or `tuple`) of scalars (null, bool, number, string, datetime, date) run a `difflib`-style `O(N*M)` matcher on the default path with its popular-element (autojunk) purge disabled for `DeepDiff` parity, worst for sequences of a few repeated values with dense edits (about 620 s for two 8,000-element lists of two repeated values with every other element changed, growing faster than quadratically), so bound the size of untrusted sequences yourself. See [`crates/onix-core/src/lcs.rs`](crates/onix-core/src/lcs.rs).
 - In `diff_tables`, a column name containing an embedded NUL byte (`\0`) arrives truncated at the NUL through the Arrow C Data Interface, and the report shows the truncated name; such names are rare in practice.
 - In `diff_tables`, a list of structs named exactly `key`/`value` with a nullable key and a real map are not distinguished, so a migration between the two is not reported as a type change (polars exports both as the same Arrow type); see `map_entries` in [`crates/onix-arrow/src/schema.rs`](crates/onix-arrow/src/schema.rs).
 - In `diff_tables`, DuckDB labels a `TIMESTAMP WITH TIME ZONE` column with the connection's *session* time zone when it exports to Arrow (a UTC session as `Timestamp(µs, "UTC")`, an `America/New_York` session as `Timestamp(µs, "America/New_York")`), so on a non-UTC machine such a column can be reported as a type change against a UTC column from another library. Run `SET TimeZone='UTC'` on the DuckDB connection first for a deterministic, machine-independent result.

{deepdiff_rs-0.6.1 → deepdiff_rs-0.6.2}/README.md

@@ -144,6 +144,7 @@ Type comparison uses the full logical Arrow type (timestamp unit and timezone, d
 - Adversarially deep input raises `MaxDepthError` instead of crashing: the default `max_depth` is 512 and the hard ceiling is `MAX_DEPTH_CEILING` (20,000). See [`crates/onix-py/src/guard.rs`](crates/onix-py/src/guard.rs).
 - `ignore_order` pairing is `O(N^2)` in unpaired elements per side and carries a polynomial cost in both time and memory with input depth; it has no `max_passes`/`max_diffs` cutoff, so bound the size and depth of untrusted input yourself. See [`crates/onix-core/src/ignore_order/mod.rs`](crates/onix-core/src/ignore_order/mod.rs).
 - A `values_changed` between two multi-line strings runs a `difflib`-style `O(N*M)` line diff on the default path with no opt-out, worst when changes are spread evenly through the text (about 35 s for a heavily edited 1 MB string and growing quadratically, so a few megabytes is minutes), so bound the size of untrusted strings yourself. See [`crates/onix-core/src/unified_diff.rs`](crates/onix-core/src/unified_diff.rs).
+- Ordered sequences (`list` or `tuple`) of scalars (null, bool, number, string, datetime, date) run a `difflib`-style `O(N*M)` matcher on the default path with its popular-element (autojunk) purge disabled for `DeepDiff` parity, worst for sequences of a few repeated values with dense edits (about 620 s for two 8,000-element lists of two repeated values with every other element changed, growing faster than quadratically), so bound the size of untrusted sequences yourself. See [`crates/onix-core/src/lcs.rs`](crates/onix-core/src/lcs.rs).
 - In `diff_tables`, a column name containing an embedded NUL byte (`\0`) arrives truncated at the NUL through the Arrow C Data Interface, and the report shows the truncated name; such names are rare in practice.
 - In `diff_tables`, a list of structs named exactly `key`/`value` with a nullable key and a real map are not distinguished, so a migration between the two is not reported as a type change (polars exports both as the same Arrow type); see `map_entries` in [`crates/onix-arrow/src/schema.rs`](crates/onix-arrow/src/schema.rs).
 - In `diff_tables`, DuckDB labels a `TIMESTAMP WITH TIME ZONE` column with the connection's *session* time zone when it exports to Arrow (a UTC session as `Timestamp(µs, "UTC")`, an `America/New_York` session as `Timestamp(µs, "America/New_York")`), so on a non-UTC machine such a column can be reported as a type change against a UTC column from another library. Run `SET TimeZone='UTC'` on the DuckDB connection first for a deterministic, machine-independent result.

{deepdiff_rs-0.6.1 → deepdiff_rs-0.6.2}/crates/onix-core/src/diff/array.rs

@@ -22,9 +22,9 @@ use super::{
 /// `_diff_iterable_in_order` dispatch exactly (see the parent `diff` module's
 /// "List diffing" doc section for the full, empirically-verified spec):
 ///
-/// - **When every element of *both* `a` and `b` is a JSON scalar** (null,
-///   bool, number, or string — `DeepDiff`'s "basic hashable" check, see
-///   [`crate::lcs::all_basic_scalars`]), an LCS/`difflib`-style "cheapest
+/// - **When every element of *both* `a` and `b` is a scalar** (null, bool,
+///   number, string, plus datetime and date — `DeepDiff`'s "basic hashable"
+///   check, see [`crate::lcs::all_basic_scalars`]), an LCS/`difflib`-style "cheapest
 ///   edit" match ([`lcs_array_diff`]) is tried first. `DeepDiff` only trusts
 ///   that match unconditionally when it produces at most one finding;
 ///   otherwise it *also* computes the plain index-aligned result below and

{deepdiff_rs-0.6.1 → deepdiff_rs-0.6.2}/crates/onix-core/src/lcs.rs

@@ -20,9 +20,10 @@
 //!
 //! `DeepDiff`'s default (non-`ignore_order`) list comparison is *not*
 //! always a simple index-aligned scan: when
-//! every element of *both* lists is a JSON scalar (`DeepDiff`'s own
-//! `_all_values_basic_hashable` check — null/bool/number/string; a dict or
-//! list anywhere in either list disqualifies the whole comparison), it
+//! every element of *both* lists is a scalar (`DeepDiff`'s own
+//! `_all_values_basic_hashable` check — null/bool/number/string, plus
+//! datetime and date from `helper.basic_types`; a dict or list anywhere in
+//! either list disqualifies the whole comparison), it
 //! additionally runs a `difflib.SequenceMatcher`-based "cheapest edit"
 //! match and, only when that produces more than one finding, compares its
 //! finding *count* against the plain index-aligned algorithm's, keeping