1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
use crate::error::SketchError;
use apache_datasketches_sys::array_of_doubles_compact::ffi as sys;
use cxx::UniquePtr;
/// An immutable, serializable snapshot of an ArrayOfDoubles Tuple sketch.
/// Produced by [`super::ArrayOfDoublesSketch::compact`], by any set
/// operation's result, or by [`Self::deserialize`].
pub struct CompactArrayOfDoublesSketch {
pub(crate) inner: UniquePtr<sys::CompactArrayOfDoublesSketchShim>,
}
unsafe impl Send for CompactArrayOfDoublesSketch {}
impl CompactArrayOfDoublesSketch {
pub(crate) fn from_shim(inner: UniquePtr<sys::CompactArrayOfDoublesSketchShim>) -> Self {
Self { inner }
}
/// Deserializes bytes produced by [`Self::serialize`]. Returns
/// [`SketchError::Deserialization`] if the bytes are truncated, corrupt,
/// or not an ArrayOfDoubles sketch.
pub fn deserialize(bytes: &[u8]) -> Result<Self, SketchError> {
let inner = sys::compact_array_of_doubles_sketch_deserialize(bytes)
.map_err(|e| SketchError::Deserialization(e.what().to_string()))?;
Ok(Self { inner })
}
/// Serializes this sketch. Unlike Theta, this family has exactly one
/// serialization format upstream — there is no compressed variant — and
/// no `ordered` parameter: orderedness is fixed when the snapshot was
/// created (e.g. via
/// [`ArrayOfDoublesSketch::compact`](super::ArrayOfDoublesSketch::compact)).
pub fn serialize(&self) -> Vec<u8> {
self.inner.serialize()
}
/// Returns the current estimate of the number of distinct keys in this
/// sketch.
pub fn get_estimate(&self) -> f64 {
self.inner.get_estimate()
}
/// Returns the lower bound of the confidence interval around
/// [`Self::get_estimate`]. See
/// [`ArrayOfDoublesSketch::get_lower_bound`](super::ArrayOfDoublesSketch::get_lower_bound)
/// for the meaning of `num_std_dev`.
pub fn get_lower_bound(&self, num_std_dev: u8) -> Result<f64, SketchError> {
self.inner
.get_lower_bound(num_std_dev)
.map_err(|e| SketchError::InvalidConfig(e.what().to_string()))
}
/// Returns the upper bound of the confidence interval around
/// [`Self::get_estimate`]. See
/// [`ArrayOfDoublesSketch::get_lower_bound`](super::ArrayOfDoublesSketch::get_lower_bound)
/// for the meaning of `num_std_dev`.
pub fn get_upper_bound(&self, num_std_dev: u8) -> Result<f64, SketchError> {
self.inner
.get_upper_bound(num_std_dev)
.map_err(|e| SketchError::InvalidConfig(e.what().to_string()))
}
/// Returns `true` if this sketch represents an empty set.
pub fn is_empty(&self) -> bool {
self.inner.is_empty()
}
/// Returns `true` if this sketch's theta threshold is below `1.0`
/// (i.e. [`Self::get_estimate`] is a statistical estimate rather than an
/// exact count).
pub fn is_estimation_mode(&self) -> bool {
self.inner.is_estimation_mode()
}
/// Returns `true` if this sketch's retained entries are sorted by hash
/// value.
pub fn is_ordered(&self) -> bool {
self.inner.is_ordered()
}
/// Returns the current theta threshold (`1.0` if not in estimation mode).
pub fn get_theta(&self) -> f64 {
self.inner.get_theta()
}
/// Returns the number of entries retained by this sketch.
pub fn get_num_retained(&self) -> u32 {
self.inner.get_num_retained()
}
/// Returns the fixed number of `f64` values each retained entry carries.
pub fn get_num_values(&self) -> u8 {
self.inner.get_num_values()
}
/// Iterates the retained entries as `(hash, values)` pairs, where
/// `values.len() == self.get_num_values()`. Ordered by hash if
/// [`Self::is_ordered`] is `true`.
///
/// The entries are copied out of C++ in two FFI calls up front (cxx
/// cannot hand back a live C++ iterator), so each item owns its `Vec`
/// rather than borrowing from the sketch.
pub fn entries(&self) -> impl Iterator<Item = (u64, Vec<f64>)> {
let num_values = self.inner.get_num_values() as usize;
let hashes: Vec<u64> = self.inner.entry_hashes().into_iter().collect();
let values: Vec<f64> = self.inner.entry_values().into_iter().collect();
let grouped: Vec<Vec<f64>> = if num_values == 0 {
Vec::new()
} else {
values.chunks(num_values).map(|c| c.to_vec()).collect()
};
hashes.into_iter().zip(grouped)
}
}