This is an automated email from the ASF dual-hosted git repository.
github-actions[bot] pushed a commit to branch gh-pages
in repository https://gitbox.apache.org/repos/asf/datasketches-cpp.git
The following commit(s) were added to refs/heads/gh-pages by this push:
new f852710 deploy: 5e18631727ae996f5ab4a47aed60c34d4197f655
f852710 is described below
commit f852710aafcb2284f4c2142d23eaa6085762ffc1
Author: leerho <[email protected]>
AuthorDate: Mon Aug 31 20:23:30 2026 +0000
deploy: 5e18631727ae996f5ab4a47aed60c34d4197f655
---
...a__set__difference__base__impl_8hpp_source.html | 90 +++++++++++-----------
1 file changed, 46 insertions(+), 44 deletions(-)
diff --git a/docs/master/theta__set__difference__base__impl_8hpp_source.html
b/docs/master/theta__set__difference__base__impl_8hpp_source.html
index 7786b99..5ae2336 100644
--- a/docs/master/theta__set__difference__base__impl_8hpp_source.html
+++ b/docs/master/theta__set__difference__base__impl_8hpp_source.html
@@ -122,51 +122,53 @@ $(document).ready(function() { init_codefold(0); });
<div class="line"><a id="l00039" name="l00039"></a><span class="lineno">
39</span>CS theta_set_difference_base<EN, EK, CS,
A>::compute(FwdSketch&& a, <span class="keyword">const</span>
Sketch& b, <span class="keywordtype">bool</span> ordered)<span
class="keyword"> const </span>{</div>
<div class="line"><a id="l00040" name="l00040"></a><span class="lineno">
40</span> <span class="keywordflow">if</span> (a.is_empty() ||
(a.get_num_retained() > 0 && b.is_empty())) <span
class="keywordflow">return</span> CS(a, ordered);</div>
<div class="line"><a id="l00041" name="l00041"></a><span class="lineno">
41</span> <span class="keywordflow">if</span> (a.get_seed_hash() !=
seed_hash_) <span class="keywordflow">throw</span> std::invalid_argument(<span
class="stringliteral">"A seed hash mismatch"</span>);</div>
-<div class="line"><a id="l00042" name="l00042"></a><span class="lineno">
42</span> <span class="keywordflow">if</span> (b.get_seed_hash() !=
seed_hash_) <span class="keywordflow">throw</span> std::invalid_argument(<span
class="stringliteral">"B seed hash mismatch"</span>);</div>
-<div class="line"><a id="l00043" name="l00043"></a><span class="lineno">
43</span> </div>
-<div class="line"><a id="l00044" name="l00044"></a><span class="lineno">
44</span> <span class="keyword">const</span> uint64_t theta =
std::min(a.get_theta64(), b.get_theta64());</div>
-<div class="line"><a id="l00045" name="l00045"></a><span class="lineno">
45</span> std::vector<EN, A> entries(allocator_);</div>
-<div class="line"><a id="l00046" name="l00046"></a><span class="lineno">
46</span> <span class="keywordtype">bool</span> is_empty = a.is_empty();</div>
-<div class="line"><a id="l00047" name="l00047"></a><span class="lineno">
47</span> </div>
-<div class="line"><a id="l00048" name="l00048"></a><span class="lineno">
48</span> <span class="keywordflow">if</span> (b.get_num_retained() == 0)
{</div>
-<div class="line"><a id="l00049" name="l00049"></a><span class="lineno">
49</span> std::copy_if(forward_begin(std::forward<FwdSketch>(a)),
forward_end(std::forward<FwdSketch>(a)),
std::back_inserter(entries),</div>
-<div class="line"><a id="l00050" name="l00050"></a><span class="lineno">
50</span> key_less_than<uint64_t, EN, EK>(theta));</div>
-<div class="line"><a id="l00051" name="l00051"></a><span class="lineno">
51</span> } <span class="keywordflow">else</span> {</div>
-<div class="line"><a id="l00052" name="l00052"></a><span class="lineno">
52</span> <span class="keywordflow">if</span> (a.is_ordered() &&
b.is_ordered()) { <span class="comment">// sort-based</span></div>
-<div class="line"><a id="l00053" name="l00053"></a><span class="lineno">
53</span>
std::set_difference(forward_begin(std::forward<FwdSketch>(a)),
forward_end(std::forward<FwdSketch>(a)), b.begin(), b.end(),</div>
-<div class="line"><a id="l00054" name="l00054"></a><span class="lineno">
54</span> conditional_back_inserter(entries,
key_less_than<uint64_t, EN, EK>(theta)), comparator());</div>
-<div class="line"><a id="l00055" name="l00055"></a><span class="lineno">
55</span> } <span class="keywordflow">else</span> { <span class="comment">//
hash-based</span></div>
-<div class="line"><a id="l00056" name="l00056"></a><span class="lineno">
56</span> <span class="keyword">const</span> uint8_t lg_size =
lg_size_from_count(b.get_num_retained(), hash_table::REBUILD_THRESHOLD);</div>
-<div class="line"><a id="l00057" name="l00057"></a><span class="lineno">
57</span> hash_table table(lg_size, lg_size,
hash_table::resize_factor::X1, 1, 0, 0, allocator_); <span class="comment">//
theta and seed are not used here</span></div>
-<div class="line"><a id="l00058" name="l00058"></a><span class="lineno">
58</span> <span class="keywordflow">for</span> (<span
class="keyword">const</span> <span class="keyword">auto</span>& entry: b)
{</div>
-<div class="line"><a id="l00059" name="l00059"></a><span class="lineno">
59</span> <span class="keyword">const</span> uint64_t hash =
EK()(entry);</div>
-<div class="line"><a id="l00060" name="l00060"></a><span class="lineno">
60</span> <span class="keywordflow">if</span> (hash < theta) {</div>
-<div class="line"><a id="l00061" name="l00061"></a><span class="lineno">
61</span> table.insert(table.find(hash).first, hash);</div>
-<div class="line"><a id="l00062" name="l00062"></a><span class="lineno">
62</span> } <span class="keywordflow">else</span> <span
class="keywordflow">if</span> (b.is_ordered()) {</div>
-<div class="line"><a id="l00063" name="l00063"></a><span class="lineno">
63</span> <span class="keywordflow">break</span>; <span
class="comment">// early stop</span></div>
-<div class="line"><a id="l00064" name="l00064"></a><span class="lineno">
64</span> }</div>
-<div class="line"><a id="l00065" name="l00065"></a><span class="lineno">
65</span> }</div>
-<div class="line"><a id="l00066" name="l00066"></a><span class="lineno">
66</span> </div>
-<div class="line"><a id="l00067" name="l00067"></a><span class="lineno">
67</span> <span class="comment">// scan A lookup B</span></div>
-<div class="line"><a id="l00068" name="l00068"></a><span class="lineno">
68</span> <span class="keywordflow">for</span> (<span
class="keyword">auto</span>&& entry: a) {</div>
-<div class="line"><a id="l00069" name="l00069"></a><span class="lineno">
69</span> <span class="keyword">const</span> uint64_t hash =
EK()(entry);</div>
-<div class="line"><a id="l00070" name="l00070"></a><span class="lineno">
70</span> <span class="keywordflow">if</span> (hash < theta) {</div>
-<div class="line"><a id="l00071" name="l00071"></a><span class="lineno">
71</span> <span class="keyword">auto</span> result =
table.find(hash);</div>
-<div class="line"><a id="l00072" name="l00072"></a><span class="lineno">
72</span> <span class="keywordflow">if</span> (!result.second)
entries.emplace_back(conditional_forward<FwdSketch>(entry));</div>
-<div class="line"><a id="l00073" name="l00073"></a><span class="lineno">
73</span> } <span class="keywordflow">else</span> <span
class="keywordflow">if</span> (a.is_ordered()) {</div>
-<div class="line"><a id="l00074" name="l00074"></a><span class="lineno">
74</span> <span class="keywordflow">break</span>; <span
class="comment">// early stop</span></div>
-<div class="line"><a id="l00075" name="l00075"></a><span class="lineno">
75</span> }</div>
-<div class="line"><a id="l00076" name="l00076"></a><span class="lineno">
76</span> }</div>
-<div class="line"><a id="l00077" name="l00077"></a><span class="lineno">
77</span> }</div>
-<div class="line"><a id="l00078" name="l00078"></a><span class="lineno">
78</span> }</div>
-<div class="line"><a id="l00079" name="l00079"></a><span class="lineno">
79</span> <span class="keywordflow">if</span> (entries.empty() &&
theta == theta_constants::MAX_THETA) is_empty = <span
class="keyword">true</span>;</div>
-<div class="line"><a id="l00080" name="l00080"></a><span class="lineno">
80</span> <span class="keywordflow">if</span> (ordered &&
!a.is_ordered()) std::sort(entries.begin(), entries.end(), comparator());</div>
-<div class="line"><a id="l00081" name="l00081"></a><span class="lineno">
81</span> <span class="keywordflow">return</span> CS(is_empty, a.is_ordered()
|| ordered, seed_hash_, theta, std::move(entries));</div>
-<div class="line"><a id="l00082" name="l00082"></a><span class="lineno">
82</span>}</div>
-<div class="line"><a id="l00083" name="l00083"></a><span class="lineno">
83</span> </div>
-<div class="line"><a id="l00084" name="l00084"></a><span class="lineno">
84</span>} <span class="comment">/* namespace datasketches */</span></div>
+<div class="line"><a id="l00042" name="l00042"></a><span class="lineno">
42</span> <span class="comment">// an empty sketch has no hashes, so its seed
hash is meaningless and must be ignored,</span></div>
+<div class="line"><a id="l00043" name="l00043"></a><span class="lineno">
43</span> <span class="comment">// consistent with deserialization,
theta_union::update() and theta_intersection::update()</span></div>
+<div class="line"><a id="l00044" name="l00044"></a><span class="lineno">
44</span> <span class="keywordflow">if</span> (!b.is_empty() &&
b.get_seed_hash() != seed_hash_) <span class="keywordflow">throw</span>
std::invalid_argument(<span class="stringliteral">"B seed hash
mismatch"</span>);</div>
+<div class="line"><a id="l00045" name="l00045"></a><span class="lineno">
45</span> </div>
+<div class="line"><a id="l00046" name="l00046"></a><span class="lineno">
46</span> <span class="keyword">const</span> uint64_t theta =
std::min(a.get_theta64(), b.get_theta64());</div>
+<div class="line"><a id="l00047" name="l00047"></a><span class="lineno">
47</span> std::vector<EN, A> entries(allocator_);</div>
+<div class="line"><a id="l00048" name="l00048"></a><span class="lineno">
48</span> <span class="keywordtype">bool</span> is_empty = a.is_empty();</div>
+<div class="line"><a id="l00049" name="l00049"></a><span class="lineno">
49</span> </div>
+<div class="line"><a id="l00050" name="l00050"></a><span class="lineno">
50</span> <span class="keywordflow">if</span> (b.get_num_retained() == 0)
{</div>
+<div class="line"><a id="l00051" name="l00051"></a><span class="lineno">
51</span> std::copy_if(forward_begin(std::forward<FwdSketch>(a)),
forward_end(std::forward<FwdSketch>(a)),
std::back_inserter(entries),</div>
+<div class="line"><a id="l00052" name="l00052"></a><span class="lineno">
52</span> key_less_than<uint64_t, EN, EK>(theta));</div>
+<div class="line"><a id="l00053" name="l00053"></a><span class="lineno">
53</span> } <span class="keywordflow">else</span> {</div>
+<div class="line"><a id="l00054" name="l00054"></a><span class="lineno">
54</span> <span class="keywordflow">if</span> (a.is_ordered() &&
b.is_ordered()) { <span class="comment">// sort-based</span></div>
+<div class="line"><a id="l00055" name="l00055"></a><span class="lineno">
55</span>
std::set_difference(forward_begin(std::forward<FwdSketch>(a)),
forward_end(std::forward<FwdSketch>(a)), b.begin(), b.end(),</div>
+<div class="line"><a id="l00056" name="l00056"></a><span class="lineno">
56</span> conditional_back_inserter(entries,
key_less_than<uint64_t, EN, EK>(theta)), comparator());</div>
+<div class="line"><a id="l00057" name="l00057"></a><span class="lineno">
57</span> } <span class="keywordflow">else</span> { <span class="comment">//
hash-based</span></div>
+<div class="line"><a id="l00058" name="l00058"></a><span class="lineno">
58</span> <span class="keyword">const</span> uint8_t lg_size =
lg_size_from_count(b.get_num_retained(), hash_table::REBUILD_THRESHOLD);</div>
+<div class="line"><a id="l00059" name="l00059"></a><span class="lineno">
59</span> hash_table table(lg_size, lg_size,
hash_table::resize_factor::X1, 1, 0, 0, allocator_); <span class="comment">//
theta and seed are not used here</span></div>
+<div class="line"><a id="l00060" name="l00060"></a><span class="lineno">
60</span> <span class="keywordflow">for</span> (<span
class="keyword">const</span> <span class="keyword">auto</span>& entry: b)
{</div>
+<div class="line"><a id="l00061" name="l00061"></a><span class="lineno">
61</span> <span class="keyword">const</span> uint64_t hash =
EK()(entry);</div>
+<div class="line"><a id="l00062" name="l00062"></a><span class="lineno">
62</span> <span class="keywordflow">if</span> (hash < theta) {</div>
+<div class="line"><a id="l00063" name="l00063"></a><span class="lineno">
63</span> table.insert(table.find(hash).first, hash);</div>
+<div class="line"><a id="l00064" name="l00064"></a><span class="lineno">
64</span> } <span class="keywordflow">else</span> <span
class="keywordflow">if</span> (b.is_ordered()) {</div>
+<div class="line"><a id="l00065" name="l00065"></a><span class="lineno">
65</span> <span class="keywordflow">break</span>; <span
class="comment">// early stop</span></div>
+<div class="line"><a id="l00066" name="l00066"></a><span class="lineno">
66</span> }</div>
+<div class="line"><a id="l00067" name="l00067"></a><span class="lineno">
67</span> }</div>
+<div class="line"><a id="l00068" name="l00068"></a><span class="lineno">
68</span> </div>
+<div class="line"><a id="l00069" name="l00069"></a><span class="lineno">
69</span> <span class="comment">// scan A lookup B</span></div>
+<div class="line"><a id="l00070" name="l00070"></a><span class="lineno">
70</span> <span class="keywordflow">for</span> (<span
class="keyword">auto</span>&& entry: a) {</div>
+<div class="line"><a id="l00071" name="l00071"></a><span class="lineno">
71</span> <span class="keyword">const</span> uint64_t hash =
EK()(entry);</div>
+<div class="line"><a id="l00072" name="l00072"></a><span class="lineno">
72</span> <span class="keywordflow">if</span> (hash < theta) {</div>
+<div class="line"><a id="l00073" name="l00073"></a><span class="lineno">
73</span> <span class="keyword">auto</span> result =
table.find(hash);</div>
+<div class="line"><a id="l00074" name="l00074"></a><span class="lineno">
74</span> <span class="keywordflow">if</span> (!result.second)
entries.emplace_back(conditional_forward<FwdSketch>(entry));</div>
+<div class="line"><a id="l00075" name="l00075"></a><span class="lineno">
75</span> } <span class="keywordflow">else</span> <span
class="keywordflow">if</span> (a.is_ordered()) {</div>
+<div class="line"><a id="l00076" name="l00076"></a><span class="lineno">
76</span> <span class="keywordflow">break</span>; <span
class="comment">// early stop</span></div>
+<div class="line"><a id="l00077" name="l00077"></a><span class="lineno">
77</span> }</div>
+<div class="line"><a id="l00078" name="l00078"></a><span class="lineno">
78</span> }</div>
+<div class="line"><a id="l00079" name="l00079"></a><span class="lineno">
79</span> }</div>
+<div class="line"><a id="l00080" name="l00080"></a><span class="lineno">
80</span> }</div>
+<div class="line"><a id="l00081" name="l00081"></a><span class="lineno">
81</span> <span class="keywordflow">if</span> (entries.empty() &&
theta == theta_constants::MAX_THETA) is_empty = <span
class="keyword">true</span>;</div>
+<div class="line"><a id="l00082" name="l00082"></a><span class="lineno">
82</span> <span class="keywordflow">if</span> (ordered &&
!a.is_ordered()) std::sort(entries.begin(), entries.end(), comparator());</div>
+<div class="line"><a id="l00083" name="l00083"></a><span class="lineno">
83</span> <span class="keywordflow">return</span> CS(is_empty, a.is_ordered()
|| ordered, seed_hash_, theta, std::move(entries));</div>
+<div class="line"><a id="l00084" name="l00084"></a><span class="lineno">
84</span>}</div>
<div class="line"><a id="l00085" name="l00085"></a><span class="lineno">
85</span> </div>
-<div class="line"><a id="l00086" name="l00086"></a><span class="lineno">
86</span><span class="preprocessor">#endif</span></div>
+<div class="line"><a id="l00086" name="l00086"></a><span class="lineno">
86</span>} <span class="comment">/* namespace datasketches */</span></div>
+<div class="line"><a id="l00087" name="l00087"></a><span class="lineno">
87</span> </div>
+<div class="line"><a id="l00088" name="l00088"></a><span class="lineno">
88</span><span class="preprocessor">#endif</span></div>
<div class="ttc" id="anamespacedatasketches_html"><div class="ttname"><a
href="namespacedatasketches.html">datasketches</a></div><div
class="ttdoc">DataSketches namespace.</div><div class="ttdef"><b>Definition</b>
binomial_bounds.hpp:38</div></div>
</div><!-- fragment --></div><!-- contents -->
<!-- start footer part -->
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]