blob: c13de2adc8a80711faf0e871b95b4cd20654ab42 [file] [log] [blame]
<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/git/checkouts/tantivy-65d0bbbddbbd5d02/433372d/src/fastfield/multivalued/index.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>index.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../../../normalize.css"><link rel="stylesheet" href="../../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../../../ayu.css" disabled><link rel="stylesheet" href="../../../../dark.css" disabled><link rel="stylesheet" href="../../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../../storage.js"></script><script defer src="../../../../source-script.js"></script><script defer src="../../../../source-files.js"></script><script defer src="../../../../main.js"></script><noscript><link rel="stylesheet" href="../../../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../../../tantivy/index.html"><div class="logo-container">
<img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../../tantivy/index.html">
<img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span>
<span id="2">2</span>
<span id="3">3</span>
<span id="4">4</span>
<span id="5">5</span>
<span id="6">6</span>
<span id="7">7</span>
<span id="8">8</span>
<span id="9">9</span>
<span id="10">10</span>
<span id="11">11</span>
<span id="12">12</span>
<span id="13">13</span>
<span id="14">14</span>
<span id="15">15</span>
<span id="16">16</span>
<span id="17">17</span>
<span id="18">18</span>
<span id="19">19</span>
<span id="20">20</span>
<span id="21">21</span>
<span id="22">22</span>
<span id="23">23</span>
<span id="24">24</span>
<span id="25">25</span>
<span id="26">26</span>
<span id="27">27</span>
<span id="28">28</span>
<span id="29">29</span>
<span id="30">30</span>
<span id="31">31</span>
<span id="32">32</span>
<span id="33">33</span>
<span id="34">34</span>
<span id="35">35</span>
<span id="36">36</span>
<span id="37">37</span>
<span id="38">38</span>
<span id="39">39</span>
<span id="40">40</span>
<span id="41">41</span>
<span id="42">42</span>
<span id="43">43</span>
<span id="44">44</span>
<span id="45">45</span>
<span id="46">46</span>
<span id="47">47</span>
<span id="48">48</span>
<span id="49">49</span>
<span id="50">50</span>
<span id="51">51</span>
<span id="52">52</span>
<span id="53">53</span>
<span id="54">54</span>
<span id="55">55</span>
<span id="56">56</span>
<span id="57">57</span>
<span id="58">58</span>
<span id="59">59</span>
<span id="60">60</span>
<span id="61">61</span>
<span id="62">62</span>
<span id="63">63</span>
<span id="64">64</span>
<span id="65">65</span>
<span id="66">66</span>
<span id="67">67</span>
<span id="68">68</span>
<span id="69">69</span>
<span id="70">70</span>
<span id="71">71</span>
<span id="72">72</span>
<span id="73">73</span>
<span id="74">74</span>
<span id="75">75</span>
<span id="76">76</span>
<span id="77">77</span>
<span id="78">78</span>
<span id="79">79</span>
<span id="80">80</span>
<span id="81">81</span>
<span id="82">82</span>
<span id="83">83</span>
<span id="84">84</span>
<span id="85">85</span>
<span id="86">86</span>
<span id="87">87</span>
<span id="88">88</span>
<span id="89">89</span>
<span id="90">90</span>
<span id="91">91</span>
<span id="92">92</span>
<span id="93">93</span>
<span id="94">94</span>
<span id="95">95</span>
<span id="96">96</span>
<span id="97">97</span>
<span id="98">98</span>
<span id="99">99</span>
<span id="100">100</span>
<span id="101">101</span>
<span id="102">102</span>
<span id="103">103</span>
<span id="104">104</span>
<span id="105">105</span>
<span id="106">106</span>
<span id="107">107</span>
<span id="108">108</span>
<span id="109">109</span>
<span id="110">110</span>
<span id="111">111</span>
<span id="112">112</span>
<span id="113">113</span>
<span id="114">114</span>
<span id="115">115</span>
<span id="116">116</span>
<span id="117">117</span>
<span id="118">118</span>
<span id="119">119</span>
<span id="120">120</span>
<span id="121">121</span>
<span id="122">122</span>
<span id="123">123</span>
<span id="124">124</span>
<span id="125">125</span>
<span id="126">126</span>
<span id="127">127</span>
<span id="128">128</span>
<span id="129">129</span>
<span id="130">130</span>
<span id="131">131</span>
<span id="132">132</span>
<span id="133">133</span>
<span id="134">134</span>
<span id="135">135</span>
<span id="136">136</span>
<span id="137">137</span>
<span id="138">138</span>
<span id="139">139</span>
<span id="140">140</span>
<span id="141">141</span>
<span id="142">142</span>
<span id="143">143</span>
<span id="144">144</span>
<span id="145">145</span>
<span id="146">146</span>
<span id="147">147</span>
<span id="148">148</span>
</pre><pre class="rust"><code><span class="kw">use </span>std::ops::Range;
<span class="kw">use </span>std::sync::Arc;
<span class="kw">use </span>fastfield_codecs::Column;
<span class="kw">use </span><span class="kw">crate</span>::DocId;
<span class="attribute">#[derive(Clone)]
</span><span class="doccomment">/// Index to resolve value range for given doc_id.
/// Starts at 0.
</span><span class="kw">pub struct </span>MultiValueIndex {
idx: Arc&lt;<span class="kw">dyn </span>Column&lt;u64&gt;&gt;,
}
<span class="kw">impl </span>MultiValueIndex {
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new(idx: Arc&lt;<span class="kw">dyn </span>Column&lt;u64&gt;&gt;) -&gt; <span class="self">Self </span>{
<span class="self">Self </span>{ idx }
}
<span class="doccomment">/// Returns `[start, end)`, such that the values associated with
/// the given document are `start..end`.
</span><span class="attribute">#[inline]
</span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>range(<span class="kw-2">&amp;</span><span class="self">self</span>, doc: DocId) -&gt; Range&lt;u32&gt; {
<span class="kw">let </span>start = <span class="self">self</span>.idx.get_val(doc) <span class="kw">as </span>u32;
<span class="kw">let </span>end = <span class="self">self</span>.idx.get_val(doc + <span class="number">1</span>) <span class="kw">as </span>u32;
start..end
}
<span class="doccomment">/// Given a range of documents, returns the Range of value offsets fo
/// these documents.
///
/// For instance, `given start_doc..end_doc`,
/// if we assume Document #start_doc end #end_doc both
/// have values, this function returns `start..end`
/// such that `value_column.get(start_doc)` is the first value of
/// `start_doc` (well, if there is one), and `value_column.get(end_doc - 1)`
/// is the last value of `end_doc`.
///
/// The passed end range is allowed to be out of bounds, in which case
/// it will be clipped to make it valid.
</span><span class="attribute">#[inline]
</span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>docid_range_to_position_range(<span class="kw-2">&amp;</span><span class="self">self</span>, range: Range&lt;DocId&gt;) -&gt; Range&lt;u32&gt; {
<span class="kw">let </span>end_docid = range.end.min(<span class="self">self</span>.num_docs() - <span class="number">1</span>) + <span class="number">1</span>;
<span class="kw">let </span>start_docid = range.start.min(end_docid);
<span class="kw">let </span>start = <span class="self">self</span>.idx.get_val(start_docid) <span class="kw">as </span>u32;
<span class="kw">let </span>end = <span class="self">self</span>.idx.get_val(end_docid) <span class="kw">as </span>u32;
<span class="macro">assert!</span>(start &lt;= end);
start..end
}
<span class="doccomment">/// returns the num of values associated with a doc_id
</span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>num_vals_for_doc(<span class="kw-2">&amp;</span><span class="self">self</span>, doc: DocId) -&gt; u32 {
<span class="kw">let </span>range = <span class="self">self</span>.range(doc);
range.end - range.start
}
<span class="doccomment">/// Returns the overall number of values in this field.
</span><span class="attribute">#[inline]
</span><span class="kw">pub fn </span>total_num_vals(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u32 {
<span class="self">self</span>.idx.max_value() <span class="kw">as </span>u32
}
<span class="doccomment">/// Returns the number of documents in the index.
</span><span class="attribute">#[inline]
</span><span class="kw">pub fn </span>num_docs(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u32 {
<span class="self">self</span>.idx.num_vals() - <span class="number">1
</span>}
<span class="doccomment">/// Converts a list of positions of values in a 1:n index to the corresponding list of DocIds.
/// Positions are converted inplace to docids.
///
/// Since there is no index for value pos -&gt; docid, but docid -&gt; value pos range, we scan the
/// index.
///
/// Correctness: positions needs to be sorted. idx_reader needs to contain monotonically
/// increasing positions.
///
///
/// TODO: Instead of a linear scan we can employ a exponential search into binary search to
/// match a docid to its value position.
</span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>positions_to_docids(<span class="kw-2">&amp;</span><span class="self">self</span>, doc_id_range: Range&lt;u32&gt;, positions: <span class="kw-2">&amp;mut </span>Vec&lt;u32&gt;) {
<span class="kw">if </span>positions.is_empty() {
<span class="kw">return</span>;
}
<span class="kw">let </span><span class="kw-2">mut </span>cur_doc = doc_id_range.start;
<span class="kw">let </span><span class="kw-2">mut </span>last_doc = <span class="prelude-val">None</span>;
<span class="macro">assert!</span>(<span class="self">self</span>.idx.get_val(doc_id_range.start) <span class="kw">as </span>u32 &lt;= positions[<span class="number">0</span>]);
<span class="kw">let </span><span class="kw-2">mut </span>write_doc_pos = <span class="number">0</span>;
<span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..positions.len() {
<span class="kw">let </span>pos = positions[i];
<span class="kw">loop </span>{
<span class="kw">let </span>end = <span class="self">self</span>.idx.get_val(cur_doc + <span class="number">1</span>) <span class="kw">as </span>u32;
<span class="kw">if </span>end &gt; pos {
positions[write_doc_pos] = cur_doc;
write_doc_pos += <span class="kw">if </span>last_doc == <span class="prelude-val">Some</span>(cur_doc) { <span class="number">0 </span>} <span class="kw">else </span>{ <span class="number">1 </span>};
last_doc = <span class="prelude-val">Some</span>(cur_doc);
<span class="kw">break</span>;
}
cur_doc += <span class="number">1</span>;
}
}
positions.truncate(write_doc_pos);
}
}
<span class="attribute">#[cfg(test)]
</span><span class="kw">mod </span>tests {
<span class="kw">use </span>std::ops::Range;
<span class="kw">use </span>std::sync::Arc;
<span class="kw">use </span>fastfield_codecs::IterColumn;
<span class="kw">use </span><span class="kw">crate</span>::fastfield::MultiValueIndex;
<span class="kw">fn </span>index_to_pos_helper(
index: <span class="kw-2">&amp;</span>MultiValueIndex,
doc_id_range: Range&lt;u32&gt;,
positions: <span class="kw-2">&amp;</span>[u32],
) -&gt; Vec&lt;u32&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>positions = positions.to_vec();
index.positions_to_docids(doc_id_range, <span class="kw-2">&amp;mut </span>positions);
positions
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_positions_to_docid() {
<span class="kw">let </span>offsets = <span class="macro">vec!</span>[<span class="number">0</span>, <span class="number">10</span>, <span class="number">12</span>, <span class="number">15</span>, <span class="number">22</span>, <span class="number">23</span>]; <span class="comment">// docid values are [0..10, 10..12, 12..15, etc.]
</span><span class="kw">let </span>column = IterColumn::from(offsets.into_iter());
<span class="kw">let </span>index = MultiValueIndex::new(Arc::new(column));
<span class="macro">assert_eq!</span>(index.num_docs(), <span class="number">5</span>);
{
<span class="kw">let </span>positions = <span class="macro">vec!</span>[<span class="number">10u32</span>, <span class="number">11</span>, <span class="number">15</span>, <span class="number">20</span>, <span class="number">21</span>, <span class="number">22</span>];
<span class="macro">assert_eq!</span>(index_to_pos_helper(<span class="kw-2">&amp;</span>index, <span class="number">0</span>..<span class="number">5</span>, <span class="kw-2">&amp;</span>positions), <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">3</span>, <span class="number">4</span>]);
<span class="macro">assert_eq!</span>(index_to_pos_helper(<span class="kw-2">&amp;</span>index, <span class="number">1</span>..<span class="number">5</span>, <span class="kw-2">&amp;</span>positions), <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">3</span>, <span class="number">4</span>]);
<span class="macro">assert_eq!</span>(index_to_pos_helper(<span class="kw-2">&amp;</span>index, <span class="number">0</span>..<span class="number">5</span>, <span class="kw-2">&amp;</span>[<span class="number">9</span>]), <span class="macro">vec!</span>[<span class="number">0</span>]);
<span class="macro">assert_eq!</span>(index_to_pos_helper(<span class="kw-2">&amp;</span>index, <span class="number">1</span>..<span class="number">5</span>, <span class="kw-2">&amp;</span>[<span class="number">10</span>]), <span class="macro">vec!</span>[<span class="number">1</span>]);
<span class="macro">assert_eq!</span>(index_to_pos_helper(<span class="kw-2">&amp;</span>index, <span class="number">1</span>..<span class="number">5</span>, <span class="kw-2">&amp;</span>[<span class="number">11</span>]), <span class="macro">vec!</span>[<span class="number">1</span>]);
<span class="macro">assert_eq!</span>(index_to_pos_helper(<span class="kw-2">&amp;</span>index, <span class="number">2</span>..<span class="number">5</span>, <span class="kw-2">&amp;</span>[<span class="number">12</span>]), <span class="macro">vec!</span>[<span class="number">2</span>]);
<span class="macro">assert_eq!</span>(index_to_pos_helper(<span class="kw-2">&amp;</span>index, <span class="number">2</span>..<span class="number">5</span>, <span class="kw-2">&amp;</span>[<span class="number">12</span>, <span class="number">14</span>]), <span class="macro">vec!</span>[<span class="number">2</span>]);
<span class="macro">assert_eq!</span>(index_to_pos_helper(<span class="kw-2">&amp;</span>index, <span class="number">2</span>..<span class="number">5</span>, <span class="kw-2">&amp;</span>[<span class="number">12</span>, <span class="number">14</span>, <span class="number">15</span>]), <span class="macro">vec!</span>[<span class="number">2</span>, <span class="number">3</span>]);
}
}
}
</code></pre></div>
</section></div></main><div id="rustdoc-vars" data-root-path="../../../../" data-current-crate="tantivy" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html>