给出一个城市:
// Allow write files to the path "images/*", subject to the constraints:
// 1) File is less than 5MB
// 2) Content type is an image
// 3) Uploaded content type matches existing content type
// 4) File name (stored in imageId wildcard variable) is less than 32 characters
match /{imageId} {
allow write: if request.resource.size < 5 * 1024 * 1024
&& request.resource.contentType.matches('image/.*')
&& request.resource.contentType == resource.contentType
&& imageId.size() < 32
我在文件中列出了将近3,000,000个城市(以及城镇和村庄等)。该文件被读入内存;我一直在玩数组,列表,字典(键= {public class City
{
public int Id { get; set; }
public string Name { get; set; }
public string Country { get; set; }
public LatLong Location { get; set; }
}
)等。
我想尽快找到所有匹配子字符串(不区分大小写)的城市。因此,当我搜索“ yor”时,我希望尽快获得所有匹配项(超过1000次)(匹配“ Yor k Town”,“ Villa Ma yor ”,“ New < strong>您 k',...)。
在功能上,您可以这样写:
Id
读取文件时,我不介意进行一些预处理;事实上:这就是我最想要的。读取文件,在数据上“咀嚼”,创建某种索引或...,然后准备回答诸如“ yor”之类的查询。
我希望它是独立的,独立的。我不想添加像RDBMS,ElasticSearch之类的依赖项。我不介意在内存中多次(部分)列表。我不介意在数据结构上花费一些内存来帮助我快速找到结果。我不要库或包。我想要一种可以自己实现的算法。
基本上我想要上面的LINQ语句,但是针对我的情况进行了优化;目前浏览大约3,000,000条记录大约需要+/- 2秒。我希望此时间少于0.1秒,因此我可以使用搜索并将其结果显示为“自动完成”。
创建“索引”(类似)结构可能是我所需要的。在撰写本文时,我还记得有关“ bloom过滤器”的内容,但不确定是否有助于甚至支持子字符串搜索。现在将对此进行调查。
非常感谢任何提示,指针,帮助您。
答案 0 :(得分:1)
您可以使用后缀树:https://en.wikipedia.org/wiki/Suffix_tree
它需要足够的空间才能在内存中存储大约20倍的单词列表
后缀数组是节省空间的替代方法:https://en.wikipedia.org/wiki/Suffix_array
答案 1 :(得分:1)
我创建了一些基于后缀数组/字典的混合体。感谢saibot首先提出建议,并感谢其他所有人的帮助和建议。
这是我想出的:
public class CitiesCollection
{
private Dictionary<int, City> _cities;
private SuffixDict<int> _suffixdict;
public CitiesCollection(IEnumerable<City> cities, int minLen)
{
_cities = cities.ToDictionary(c => c.Id);
_suffixdict = new SuffixDict<int>(minLen, _cities.Values.Count);
foreach (var c in _cities.Values)
_suffixdict.Add(c.Name, c.Id);
}
public IEnumerable<City> Find(string find)
{
var normalizedFind = _suffixdict.NormalizeString(find);
foreach (var id in _suffixdict.Get(normalizedFind).Where(v => _cities[v].Name.IndexOf(normalizedFind, StringComparison.OrdinalIgnoreCase) >= 0))
yield return _cities[id];
}
}
public class SuffixDict<T>
{
private readonly int _suffixsize;
private ConcurrentDictionary<string, IList<T>> _dict;
public SuffixDict(int suffixSize, int capacity)
{
_suffixsize = suffixSize;
_dict = new ConcurrentDictionary<string, IList<T>>(Environment.ProcessorCount, capacity);
}
public void Add(string suffix, T value)
{
foreach (var s in GetSuffixes(suffix))
AddDict(s, value);
}
public IEnumerable<T> Get(string suffix)
{
return Find(suffix).Distinct();
}
private IEnumerable<T> Find(string suffix)
{
foreach (var s in GetSuffixes(suffix))
{
if (_dict.TryGetValue(s, out var result))
foreach (var i in result)
yield return i;
}
}
public string NormalizeString(string value)
{
return value.Normalize().ToLowerInvariant();
}
private void AddDict(string suffix, T value)
{
_dict.AddOrUpdate(suffix, (s) => new List<T>() { value }, (k, v) => { v.Add(value); return v; });
}
private IEnumerable<string> GetSuffixes(string value)
{
var nv = NormalizeString(value);
for (var i = 0; i <= nv.Length - _suffixsize ; i++)
yield return nv.Substring(i, _suffixsize);
}
}
用法(我假设mycities
是IEnumerable<City>
,并带有问题中给定的City
对象)
var cc = new CitiesCollection(mycities, 3);
var results = cc.Find("york");
一些结果:
Find: sterda elapsed: 00:00:00.0220522 results: 32
Find: york elapsed: 00:00:00.0006212 results: 155
Find: dorf elapsed: 00:00:00.0086439 results: 6095
内存使用非常非常可以接受。只有650MB的内存可存储300万个城市的整个集合。
在上面的代码中,我将ID存储在“ SuffixDict
”中,并且具有一定程度的间接性(字典查找以查找id => city)。可以进一步简化为:
public class CitiesCollection
{
private SuffixDict<City> _suffixdict;
public CitiesCollection(IEnumerable<City> cities, int minLen, int capacity = 1000)
{
_suffixdict = new SuffixDict<City>(minLen, capacity);
foreach (var c in cities)
_suffixdict.Add(c.Name, c);
}
public IEnumerable<City> Find(string find, StringComparison stringComparison = StringComparison.OrdinalIgnoreCase)
{
var normalizedFind = SuffixDict<City>.NormalizeString(find);
var x = _suffixdict.Find(normalizedFind).ToArray();
foreach (var city in _suffixdict.Find(normalizedFind).Where(v => v.Name.IndexOf(normalizedFind, stringComparison) >= 0))
yield return city;
}
}
public class SuffixDict<T>
{
private readonly int _suffixsize;
private ConcurrentDictionary<string, IList<T>> _dict;
public SuffixDict(int suffixSize, int capacity = 1000)
{
_suffixsize = suffixSize;
_dict = new ConcurrentDictionary<string, IList<T>>(Environment.ProcessorCount, capacity);
}
public void Add(string suffix, T value)
{
foreach (var s in GetSuffixes(suffix, _suffixsize))
AddDict(s, value);
}
public IEnumerable<T> Find(string suffix)
{
var normalizedfind = NormalizeString(suffix);
var find = normalizedfind.Substring(0, Math.Min(normalizedfind.Length, _suffixsize));
if (_dict.TryGetValue(find, out var result))
foreach (var i in result)
yield return i;
}
private void AddDict(string suffix, T value)
{
_dict.AddOrUpdate(suffix, (s) => new List<T>() { value }, (k, v) => { v.Add(value); return v; });
}
public static string NormalizeString(string value)
{
return value.Normalize().ToLowerInvariant();
}
private static IEnumerable<string> GetSuffixes(string value, int suffixSize)
{
var nv = NormalizeString(value);
if (value.Length < suffixSize)
{
yield return nv;
}
else
{
for (var i = 0; i <= nv.Length - suffixSize; i++)
yield return nv.Substring(i, suffixSize);
}
}
}
这将使加载时间从00:00:16.3899085
增加到00:00:25.6113214
,内存使用量从650MB减少到486MB。由于我们的间接访问级别较低,因此查找/搜索的性能要好一些。
Find: sterda elapsed: 00:00:00.0168616 results: 32
Find: york elapsed: 00:00:00.0003945 results: 155
Find: dorf elapsed: 00:00:00.0062015 results: 6095
到目前为止,我对结果感到满意。我会做一些修饰和重构,然后称之为一天!谢谢大家的帮助!
这就是它在2,972,036个城市中的表现:
通过修改以下代码,它已演变为不区分大小写,不区分重音的搜索:
public static class ExtensionMethods
{
public static T FirstOrDefault<T>(this IEnumerable<T> src, Func<T, bool> testFn, T defval)
{
return src.Where(aT => testFn(aT)).DefaultIfEmpty(defval).First();
}
public static int IndexOf(this string source, string match, IEqualityComparer<string> sc)
{
return Enumerable.Range(0, source.Length) // for each position in the string
.FirstOrDefault(i => // find the first position where either
// match is Equals at this position for length of match (or to end of string) or
sc.Equals(source.Substring(i, Math.Min(match.Length, source.Length - i)), match) ||
// match is Equals to on of the substrings beginning at this position
Enumerable.Range(1, source.Length - i - 1).Any(ml => sc.Equals(source.Substring(i, ml), match)),
-1 // else return -1 if no position matches
);
}
}
public class CaseAccentInsensitiveEqualityComparer : IEqualityComparer<string>
{
private static readonly CompareOptions _compareoptions = CompareOptions.IgnoreCase | CompareOptions.IgnoreNonSpace | CompareOptions.IgnoreKanaType | CompareOptions.IgnoreWidth | CompareOptions.IgnoreSymbols;
private static readonly CultureInfo _cultureinfo = CultureInfo.InvariantCulture;
public bool Equals(string x, string y)
{
return string.Compare(x, y, _cultureinfo, _compareoptions) == 0;
}
public int GetHashCode(string obj)
{
return obj != null ? RemoveDiacritics(obj).ToUpperInvariant().GetHashCode() : 0;
}
private string RemoveDiacritics(string text)
{
return string.Concat(
text.Normalize(NormalizationForm.FormD)
.Where(ch => CharUnicodeInfo.GetUnicodeCategory(ch) != UnicodeCategory.NonSpacingMark)
).Normalize(NormalizationForm.FormC);
}
}
public class CitiesCollection
{
private SuffixDict<City> _suffixdict;
private HashSet<string> _countries;
private Dictionary<int, City> _cities;
private readonly IEqualityComparer<string> _comparer = new CaseAccentInsensitiveEqualityComparer();
public CitiesCollection(IEnumerable<City> cities, int minLen, int capacity = 1000)
{
_suffixdict = new SuffixDict<City>(minLen, _comparer, capacity);
_countries = new HashSet<string>();
_cities = new Dictionary<int, City>(capacity);
foreach (var c in cities)
{
_suffixdict.Add(c.Name, c);
_countries.Add(c.Country);
_cities.Add(c.Id, c);
}
}
public City this[int index] => _cities[index];
public IEnumerable<string> Countries => _countries;
public IEnumerable<City> Find(string find, StringComparison stringComparison = StringComparison.OrdinalIgnoreCase)
{
foreach (var city in _suffixdict.Find(find).Where(v => v.Name.IndexOf(find, _comparer) >= 0))
yield return city;
}
}
public class SuffixDict<T>
{
private readonly int _suffixsize;
private ConcurrentDictionary<string, IList<T>> _dict;
public SuffixDict(int suffixSize, IEqualityComparer<string> stringComparer, int capacity = 1000)
{
_suffixsize = suffixSize;
_dict = new ConcurrentDictionary<string, IList<T>>(Environment.ProcessorCount, capacity, stringComparer);
}
public void Add(string suffix, T value)
{
foreach (var s in GetSuffixes(suffix, _suffixsize))
AddDict(s, value);
}
public IEnumerable<T> Find(string suffix)
{
var find = suffix.Substring(0, Math.Min(suffix.Length, _suffixsize));
if (_dict.TryGetValue(find, out var result))
{
foreach (var i in result)
yield return i;
}
}
private void AddDict(string suffix, T value)
{
_dict.AddOrUpdate(suffix, (s) => new List<T>() { value }, (k, v) => { v.Add(value); return v; });
}
private static IEnumerable<string> GetSuffixes(string value, int suffixSize)
{
if (value.Length < 2)
{
yield return value;
}
else
{
for (var i = 0; i <= value.Length - suffixSize; i++)
yield return value.Substring(i, suffixSize);
}
}
}
答案 2 :(得分:-5)
包含的索引要比indexOf> 0快得多
cities.Values.Where(c => c.Name.Contans("yor"))