test(api): benchmark levenshtein distance over placenames

refs #371

test/api.benchmarks/Levenshtein/.gitignore

@@ -0,0 +1,265 @@
+## Ignore Visual Studio temporary files, build results, and
+## files generated by popular Visual Studio add-ons.
+
+# User-specific files
+*.suo
+*.user
+*.userosscache
+*.sln.docstates
+
+# User-specific files (MonoDevelop/Xamarin Studio)
+*.userprefs
+
+# Build results
+[Dd]ebug/
+[Dd]ebugPublic/
+[Rr]elease/
+[Rr]eleases/
+x64/
+x86/
+bld/
+[Bb]in/
+[Oo]bj/
+[Ll]og/
+
+# Visual Studio 2015 cache/options directory
+.vs/
+
+# Uncomment if you have tasks that create the project's static files in wwwroot
+#wwwroot/
+
+# MSTest test Results
+[Tt]est[Rr]esult*/
+[Bb]uild[Ll]og.*
+
+# NUNIT
+*.VisualState.xml
+TestResult.xml
+
+# Build Results of an ATL Project
+[Dd]ebugPS/
+[Rr]eleasePS/
+dlldata.c
+
+# DNX
+project.lock.json
+project.fragment.lock.json
+artifacts/
+
+*_i.c
+*_p.c
+*_i.h
+*.ilk
+*.meta
+*.obj
+*.pch
+*.pdb
+*.pgc
+*.pgd
+*.rsp
+*.sbr
+*.tlb
+*.tli
+*.tlh
+*.tmp
+*.tmp_proj
+*.log
+*.vspscc
+*.vssscc
+.builds
+*.pidb
+*.svclog
+*.scc
+
+# Chutzpah Test files
+_Chutzpah*
+
+# Visual C++ cache files
+ipch/
+*.aps
+*.ncb
+*.opendb
+*.opensdf
+*.sdf
+*.cachefile
+*.VC.db
+*.VC.VC.opendb
+
+# Visual Studio profiler
+*.psess
+*.vsp
+*.vspx
+*.sap
+
+# TFS 2012 Local Workspace
+$tf/
+
+# Guidance Automation Toolkit
+*.gpState
+
+# ReSharper is a .NET coding add-in
+_ReSharper*/
+*.[Rr]e[Ss]harper
+*.DotSettings.user
+
+# JustCode is a .NET coding add-in
+.JustCode
+
+# TeamCity is a build add-in
+_TeamCity*
+
+# DotCover is a Code Coverage Tool
+*.dotCover
+
+# NCrunch
+_NCrunch_*
+.*crunch*.local.xml
+nCrunchTemp_*
+
+# MightyMoose
+*.mm.*
+AutoTest.Net/
+
+# Web workbench (sass)
+.sass-cache/
+
+# Benchmarking
+BenchmarkDotNet.Artifacts/
+
+# Installshield output folder
+[Ee]xpress/
+
+# DocProject is a documentation generator add-in
+DocProject/buildhelp/
+DocProject/Help/*.HxT
+DocProject/Help/*.HxC
+DocProject/Help/*.hhc
+DocProject/Help/*.hhk
+DocProject/Help/*.hhp
+DocProject/Help/Html2
+DocProject/Help/html
+
+# Click-Once directory
+publish/
+
+# Publish Web Output
+*.[Pp]ublish.xml
+*.azurePubxml
+# TODO: Comment the next line if you want to checkin your web deploy settings
+# but database connection strings (with potential passwords) will be unencrypted
+#*.pubxml
+*.publishproj
+
+# Microsoft Azure Web App publish settings. Comment the next line if you want to
+# checkin your Azure Web App publish settings, but sensitive information contained
+# in these scripts will be unencrypted
+PublishScripts/
+
+# NuGet Packages
+*.nupkg
+# The packages folder can be ignored because of Package Restore
+**/packages/*
+# except build/, which is used as an MSBuild target.
+!**/packages/build/
+# Uncomment if necessary however generally it will be regenerated when needed
+#!**/packages/repositories.config
+# NuGet v3's project.json files produces more ignoreable files
+*.nuget.props
+*.nuget.targets
+
+# Microsoft Azure Build Output
+csx/
+*.build.csdef
+
+# Microsoft Azure Emulator
+ecf/
+rcf/
+
+# Windows Store app package directories and files
+AppPackages/
+BundleArtifacts/
+Package.StoreAssociation.xml
+_pkginfo.txt
+
+# Visual Studio cache files
+# files ending in .cache can be ignored
+*.[Cc]ache
+# but keep track of directories ending in .cache
+!*.[Cc]ache/
+
+# Others
+ClientBin/
+~$*
+*~
+*.dbmdl
+*.dbproj.schemaview
+*.jfm
+*.pfx
+*.publishsettings
+node_modules/
+orleans.codegen.cs
+
+# Since there are multiple workflows, uncomment next line to ignore bower_components
+# (https://github.com/github/gitignore/pull/1529#issuecomment-104372622)
+#bower_components/
+
+# RIA/Silverlight projects
+Generated_Code/
+
+# Backup & report files from converting an old project file
+# to a newer Visual Studio version. Backup files are not needed,
+# because we have git ;-)
+_UpgradeReport_Files/
+Backup*/
+UpgradeLog*.XML
+UpgradeLog*.htm
+
+# SQL Server files
+*.mdf
+*.ldf
+
+# Business Intelligence projects
+*.rdl.data
+*.bim.layout
+*.bim_*.settings
+
+# Microsoft Fakes
+FakesAssemblies/
+
+# GhostDoc plugin setting file
+*.GhostDoc.xml
+
+# Node.js Tools for Visual Studio
+.ntvs_analysis.dat
+
+# Visual Studio 6 build log
+*.plg
+
+# Visual Studio 6 workspace options file
+*.opt
+
+# Visual Studio LightSwitch build output
+**/*.HTMLClient/GeneratedArtifacts
+**/*.DesktopClient/GeneratedArtifacts
+**/*.DesktopClient/ModelManifest.xml
+**/*.Server/GeneratedArtifacts
+**/*.Server/ModelManifest.xml
+_Pvt_Extensions
+
+# Paket dependency manager
+.paket/paket.exe
+paket-files/
+
+# FAKE - F# Make
+.fake/
+
+# JetBrains Rider
+.idea/
+*.sln.iml
+
+# CodeRush
+.cr/
+
+# Python Tools for Visual Studio (PTVS)
+__pycache__/
+*.pyc

test/api.benchmarks/Levenshtein/Levenshtein.csproj

@@ -0,0 +1,16 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net8.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="BenchmarkDotNet" Version="0.14.0" />
+    <PackageReference Include="Fastenshtein" Version="1.0.10" />
+    <PackageReference Include="Google.Cloud.BigQuery.V2" Version="3.10.0" />
+  </ItemGroup>
+
+</Project>

test/api.benchmarks/Levenshtein/Program.cs

@@ -0,0 +1,73 @@
+using BenchmarkDotNet.Attributes;
+using BenchmarkDotNet.Running;
+using Fastenshtein;
+using Google.Cloud.BigQuery.V2;
+
+namespace benchmark.levenshtein;
+
+public class LowestDistanceList<T>(int maxSize, IComparer<T> comparer) {
+    private readonly SortedSet<T> _sortedSet = new(comparer);
+    private readonly int _maxSize = maxSize;
+    private readonly IComparer<T> _comparer = comparer;
+
+    public void Add(T item) {
+        if (_sortedSet.Count < _maxSize) {
+            _sortedSet.Add(item);
+        } else if (_comparer.Compare(item, _sortedSet.Max) < 0) {
+            var max = _sortedSet.Max;
+
+            if (max is not null) {
+                _sortedSet.Remove(max);
+            }
+            _sortedSet.Add(item);
+        }
+    }
+
+    public IEnumerable<T> Items => _sortedSet;
+}
+
+public class DistanceComparer : IComparer<Map> {
+    public int Compare(Map? x, Map? y) => (x?.Difference ?? int.MaxValue).CompareTo(y?.Difference ?? int.MaxValue);
+}
+public record Map(int Difference, string Zone);
+
+public class LevenshteinOverPlaceNames {
+    private List<string> _zones { get; set; } = [];
+    private readonly LowestDistanceList<Map> _priorityQueue = new(4, new DistanceComparer());
+    private readonly Levenshtein _lev = new("TAYOLRSVILLE");
+
+    [GlobalSetup]
+    public void Setup() {
+        // get bigquery data
+        var _client = BigQueryClient.Create("ut-dts-agrc-web-api-dev");
+        var table = _client.GetTable("address_grid_mapping_cache", "address_system_mapping");
+
+        var results = _client.ExecuteQuery(
+            $"SELECT Zone FROM {table} WHERE Type=@type ORDER BY Zone", [new("type", BigQueryDbType.String, "place")]);
+
+        foreach (var row in results) {
+            var zone = row["Zone"]?.ToString();
+
+            if (!string.IsNullOrEmpty(zone)) {
+                _zones.Add(zone);
+            }
+        }
+
+        Console.WriteLine($"Loaded {_zones.Count} items");
+    }
+
+    [Benchmark]
+    public Map[] CalculateAllDistances() {
+        foreach (var zone in _zones) {
+            _priorityQueue.Add(new(_lev.DistanceFrom(zone), zone));
+        }
+
+        return _priorityQueue.Items.ToArray();
+    }
+}
+
+public class Program {
+    public static void Main(string[] args) {
+        var _ = BenchmarkRunner.Run<LevenshteinOverPlaceNames>();
+    }
+}