Expand small value sets to all case permutations in SearchValues<string>#98902

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
MihaZupan merged 2 commits into from
Mar 2, 2024
Merged

Expand small value sets to all case permutations in SearchValues<string> #98902

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0d381fb
Expand small value sets to all case permutations in SearchValues<string>
MihaZupan Feb 25, 2024
ac5966c
Use the constant in one more place
MihaZupan Feb 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
81 changes: 79 additions & 2 deletions src/libraries/System.Private.CoreLib/src/System/SearchValues/Strings/StringSearchValues.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@

using System.Collections.Generic;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Globalization;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.Arm;
Expand All@@ -14,6 +15,8 @@ namespace System.Buffers
{
internal static class StringSearchValues
{
private const int TeddyBucketCount = 8;

private static readonly SearchValues<char> s_asciiLetters =
SearchValues.Create("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");

Expand DownExpand Up@@ -248,6 +251,18 @@ static SearchValues<string> PickAhoCorasickImplementation<TCaseSensitivity>(AhoC

Debug.Assert(!(asciiStartLettersOnly && asciiStartUnaffectedByCaseConversion));

// If we still have empty buckets we could use and we're ignoring case, we may be able to
// generate all possible permutations of the first N characters and switch to case-sensitive searching.
// E.g. ["ab", "c!"] => ["ab", "Ab" "aB", "AB", "c!", "C!"].
Comment thread
MihaZupan marked this conversation as resolved.
Comment thread
MihaZupan marked this conversation as resolved.
// This won't apply to inputs with many letters (e.g. "abc" => 8 permutations on its own).
if (!asciiStartUnaffectedByCaseConversion &&
values.Length < TeddyBucketCount &&
TryGenerateAllCasePermutationsForPrefixes(values, n, TeddyBucketCount, out string[]? newValues))
{
asciiStartUnaffectedByCaseConversion = true;
values = newValues;
}

if (asciiStartUnaffectedByCaseConversion)
{
return nonAsciiAffectedByCaseConversion
Expand DownExpand Up@@ -278,9 +293,9 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
Debug.Assert(values.Length > 1);
Debug.Assert(n is 2 or 3);

if (values.Length > 8)
if (values.Length > TeddyBucketCount)
{
string[][] buckets = TeddyBucketizer.Bucketize(values, bucketCount: 8, n);
string[][] buckets = TeddyBucketizer.Bucketize(values, TeddyBucketCount, n);

// Potential optimization: We don't have to pick the first N characters for the fingerprint.
// Different offset selection can noticeably improve throughput (e.g. 2x).
Expand All@@ -297,6 +312,68 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
}
}

private static bool TryGenerateAllCasePermutationsForPrefixes(ReadOnlySpan<string> values, int n, int maxValues, [NotNullWhen(true)] out string[]? newValues)
{
Debug.Assert(n is 2 or 3);
Debug.Assert(values.Length < maxValues);

// Count how many possible permutations there are.
int newValuesCount = 0;

foreach (string value in values)
{
int permutations = 1;

foreach (char c in value.AsSpan(0, n))
Comment thread
MihaZupan marked this conversation as resolved.
{
Debug.Assert(char.IsAscii(c));
Comment thread
MihaZupan marked this conversation as resolved.

if (char.IsAsciiLetter(c))
{
permutations *= 2;
}
}

newValuesCount += permutations;
}

Debug.Assert(newValuesCount > values.Length, "Shouldn't have been called if there were no letters present");

if (newValuesCount > maxValues)
{
newValues = null;
return false;
}

// Generate the permutations.
newValues = new string[newValuesCount];
newValuesCount = 0;

foreach (string value in values)
{
int start = newValuesCount;

newValues[newValuesCount++] = value;

for (int i = 0; i < n; i++)
{
char c = value[i];

if (char.IsAsciiLetter(c))
{
// Copy all the previous permutations of this value but change the casing of the i-th character.
foreach (string previous in newValues.AsSpan(start, newValuesCount - start))
{
newValues[newValuesCount++] = $"{previous.AsSpan(0, i)}{(char)(c ^ 0x20)}{previous.AsSpan(i + 1)}";
}
}
}
}

Debug.Assert(newValuesCount == newValues.Length);
return true;
}

private static SearchValues<string> CreateForSingleValue(
string value,
HashSet<string>? uniqueValues,
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Expand small value sets to all case permutations in SearchValues<string>#98902

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

MihaZupan
merged 2 commits into

from

Mar 2, 2024
 Merged


Expand small value sets to all case permutations in SearchValues<string>
#98902
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
0d381fb

Expand small value sets to all case permutations in SearchValues<string>


MihaZupan Feb 25, 2024
ac5966c

Use the constant in one more place


MihaZupan Feb 25, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


81 changes: 79 additions & 2 deletions
src/libraries/System.Private.CoreLib/src/System/SearchValues/Strings/StringSearchValues.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@

using System.Collections.Generic;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Globalization;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.Arm;
Expand All@@ -14,6 +15,8 @@ namespace System.Buffers
{
 internal static class StringSearchValues
 {
 private const int TeddyBucketCount = 8;

 private static readonly SearchValues<char> s_asciiLetters =
 SearchValues.Create("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");

Expand DownExpand Up@@ -248,6 +251,18 @@ static SearchValues<string> PickAhoCorasickImplementation<TCaseSensitivity>(AhoC

 Debug.Assert(!(asciiStartLettersOnly && asciiStartUnaffectedByCaseConversion));

 // If we still have empty buckets we could use and we're ignoring case, we may be able to
 // generate all possible permutations of the first N characters and switch to case-sensitive searching.
 // E.g. ["ab", "c!"] => ["ab", "Ab" "aB", "AB", "c!", "C!"].
Comment thread
MihaZupan marked this conversation as resolved.

Comment thread
MihaZupan marked this conversation as resolved.

 // This won't apply to inputs with many letters (e.g. "abc" => 8 permutations on its own).
 if (!asciiStartUnaffectedByCaseConversion &&
 values.Length < TeddyBucketCount &&
 TryGenerateAllCasePermutationsForPrefixes(values, n, TeddyBucketCount, out string[]? newValues))
 {
 asciiStartUnaffectedByCaseConversion = true;
 values = newValues;
 }

 if (asciiStartUnaffectedByCaseConversion)
 {
 return nonAsciiAffectedByCaseConversion
Expand DownExpand Up@@ -278,9 +293,9 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 Debug.Assert(values.Length > 1);
 Debug.Assert(n is 2 or 3);

 if (values.Length > 8)
 if (values.Length > TeddyBucketCount)
 {
 string[][] buckets = TeddyBucketizer.Bucketize(values, bucketCount: 8, n);
 string[][] buckets = TeddyBucketizer.Bucketize(values, TeddyBucketCount, n);

 // Potential optimization: We don't have to pick the first N characters for the fingerprint.
 // Different offset selection can noticeably improve throughput (e.g. 2x).
Expand All@@ -297,6 +312,68 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 }
 }

 private static bool TryGenerateAllCasePermutationsForPrefixes(ReadOnlySpan<string> values, int n, int maxValues, [NotNullWhen(true)] out string[]? newValues)
 {
 Debug.Assert(n is 2 or 3);
 Debug.Assert(values.Length < maxValues);

 // Count how many possible permutations there are.
 int newValuesCount = 0;

 foreach (string value in values)
 {
 int permutations = 1;

 foreach (char c in value.AsSpan(0, n))
Comment thread
MihaZupan marked this conversation as resolved.

 {
 Debug.Assert(char.IsAscii(c));
Comment thread
MihaZupan marked this conversation as resolved.


 if (char.IsAsciiLetter(c))
 {
 permutations *= 2;
 }
 }

 newValuesCount += permutations;
 }

 Debug.Assert(newValuesCount > values.Length, "Shouldn't have been called if there were no letters present");

 if (newValuesCount > maxValues)
 {
 newValues = null;
 return false;
 }

 // Generate the permutations.
 newValues = new string[newValuesCount];
 newValuesCount = 0;

 foreach (string value in values)
 {
 int start = newValuesCount;

 newValues[newValuesCount++] = value;

 for (int i = 0; i < n; i++)
 {
 char c = value[i];

 if (char.IsAsciiLetter(c))
 {
 // Copy all the previous permutations of this value but change the casing of the i-th character.
 foreach (string previous in newValues.AsSpan(start, newValuesCount - start))
 {
 newValues[newValuesCount++] = $"{previous.AsSpan(0, i)}{(char)(c ^ 0x20)}{previous.AsSpan(i + 1)}";
 }
 }
 }
 }

 Debug.Assert(newValuesCount == newValues.Length);
 return true;
 }

 private static SearchValues<string> CreateForSingleValue(
 string value,
 HashSet<string>? uniqueValues,
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Expand small value sets to all case permutations in SearchValues<string>#98902

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

MihaZupan
merged 2 commits into

from

Mar 2, 2024
 Merged


Expand small value sets to all case permutations in SearchValues<string>
#98902
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
0d381fb

Expand small value sets to all case permutations in SearchValues<string>


MihaZupan Feb 25, 2024
ac5966c

Use the constant in one more place


MihaZupan Feb 25, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


81 changes: 79 additions & 2 deletions
src/libraries/System.Private.CoreLib/src/System/SearchValues/Strings/StringSearchValues.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@

using System.Collections.Generic;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Globalization;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.Arm;
Expand All@@ -14,6 +15,8 @@ namespace System.Buffers
{
 internal static class StringSearchValues
 {
 private const int TeddyBucketCount = 8;

 private static readonly SearchValues<char> s_asciiLetters =
 SearchValues.Create("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");

Expand DownExpand Up@@ -248,6 +251,18 @@ static SearchValues<string> PickAhoCorasickImplementation<TCaseSensitivity>(AhoC

 Debug.Assert(!(asciiStartLettersOnly && asciiStartUnaffectedByCaseConversion));

 // If we still have empty buckets we could use and we're ignoring case, we may be able to
 // generate all possible permutations of the first N characters and switch to case-sensitive searching.
 // E.g. ["ab", "c!"] => ["ab", "Ab" "aB", "AB", "c!", "C!"].
Comment thread
MihaZupan marked this conversation as resolved.

Comment thread
MihaZupan marked this conversation as resolved.

 // This won't apply to inputs with many letters (e.g. "abc" => 8 permutations on its own).
 if (!asciiStartUnaffectedByCaseConversion &&
 values.Length < TeddyBucketCount &&
 TryGenerateAllCasePermutationsForPrefixes(values, n, TeddyBucketCount, out string[]? newValues))
 {
 asciiStartUnaffectedByCaseConversion = true;
 values = newValues;
 }

 if (asciiStartUnaffectedByCaseConversion)
 {
 return nonAsciiAffectedByCaseConversion
Expand DownExpand Up@@ -278,9 +293,9 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 Debug.Assert(values.Length > 1);
 Debug.Assert(n is 2 or 3);

 if (values.Length > 8)
 if (values.Length > TeddyBucketCount)
 {
 string[][] buckets = TeddyBucketizer.Bucketize(values, bucketCount: 8, n);
 string[][] buckets = TeddyBucketizer.Bucketize(values, TeddyBucketCount, n);

 // Potential optimization: We don't have to pick the first N characters for the fingerprint.
 // Different offset selection can noticeably improve throughput (e.g. 2x).
Expand All@@ -297,6 +312,68 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 }
 }

 private static bool TryGenerateAllCasePermutationsForPrefixes(ReadOnlySpan<string> values, int n, int maxValues, [NotNullWhen(true)] out string[]? newValues)
 {
 Debug.Assert(n is 2 or 3);
 Debug.Assert(values.Length < maxValues);

 // Count how many possible permutations there are.
 int newValuesCount = 0;

 foreach (string value in values)
 {
 int permutations = 1;

 foreach (char c in value.AsSpan(0, n))
Comment thread
MihaZupan marked this conversation as resolved.

 {
 Debug.Assert(char.IsAscii(c));
Comment thread
MihaZupan marked this conversation as resolved.


 if (char.IsAsciiLetter(c))
 {
 permutations *= 2;
 }
 }

 newValuesCount += permutations;
 }

 Debug.Assert(newValuesCount > values.Length, "Shouldn't have been called if there were no letters present");

 if (newValuesCount > maxValues)
 {
 newValues = null;
 return false;
 }

 // Generate the permutations.
 newValues = new string[newValuesCount];
 newValuesCount = 0;

 foreach (string value in values)
 {
 int start = newValuesCount;

 newValues[newValuesCount++] = value;

 for (int i = 0; i < n; i++)
 {
 char c = value[i];

 if (char.IsAsciiLetter(c))
 {
 // Copy all the previous permutations of this value but change the casing of the i-th character.
 foreach (string previous in newValues.AsSpan(start, newValuesCount - start))
 {
 newValues[newValuesCount++] = $"{previous.AsSpan(0, i)}{(char)(c ^ 0x20)}{previous.AsSpan(i + 1)}";
 }
 }
 }
 }

 Debug.Assert(newValuesCount == newValues.Length);
 return true;
 }

 private static SearchValues<string> CreateForSingleValue(
 string value,
 HashSet<string>? uniqueValues,
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Expand small value sets to all case permutations in SearchValues<string>#98902

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

MihaZupan
merged 2 commits into

from

Mar 2, 2024
 Merged


Expand small value sets to all case permutations in SearchValues<string>
#98902
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
0d381fb

Expand small value sets to all case permutations in SearchValues<string>


MihaZupan Feb 25, 2024
ac5966c

Use the constant in one more place


MihaZupan Feb 25, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


81 changes: 79 additions & 2 deletions
src/libraries/System.Private.CoreLib/src/System/SearchValues/Strings/StringSearchValues.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@

using System.Collections.Generic;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Globalization;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.Arm;
Expand All@@ -14,6 +15,8 @@ namespace System.Buffers
{
 internal static class StringSearchValues
 {
 private const int TeddyBucketCount = 8;

 private static readonly SearchValues<char> s_asciiLetters =
 SearchValues.Create("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");

Expand DownExpand Up@@ -248,6 +251,18 @@ static SearchValues<string> PickAhoCorasickImplementation<TCaseSensitivity>(AhoC

 Debug.Assert(!(asciiStartLettersOnly && asciiStartUnaffectedByCaseConversion));

 // If we still have empty buckets we could use and we're ignoring case, we may be able to
 // generate all possible permutations of the first N characters and switch to case-sensitive searching.
 // E.g. ["ab", "c!"] => ["ab", "Ab" "aB", "AB", "c!", "C!"].
Comment thread
MihaZupan marked this conversation as resolved.

Comment thread
MihaZupan marked this conversation as resolved.

 // This won't apply to inputs with many letters (e.g. "abc" => 8 permutations on its own).
 if (!asciiStartUnaffectedByCaseConversion &&
 values.Length < TeddyBucketCount &&
 TryGenerateAllCasePermutationsForPrefixes(values, n, TeddyBucketCount, out string[]? newValues))
 {
 asciiStartUnaffectedByCaseConversion = true;
 values = newValues;
 }

 if (asciiStartUnaffectedByCaseConversion)
 {
 return nonAsciiAffectedByCaseConversion
Expand DownExpand Up@@ -278,9 +293,9 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 Debug.Assert(values.Length > 1);
 Debug.Assert(n is 2 or 3);

 if (values.Length > 8)
 if (values.Length > TeddyBucketCount)
 {
 string[][] buckets = TeddyBucketizer.Bucketize(values, bucketCount: 8, n);
 string[][] buckets = TeddyBucketizer.Bucketize(values, TeddyBucketCount, n);

 // Potential optimization: We don't have to pick the first N characters for the fingerprint.
 // Different offset selection can noticeably improve throughput (e.g. 2x).
Expand All@@ -297,6 +312,68 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 }
 }

 private static bool TryGenerateAllCasePermutationsForPrefixes(ReadOnlySpan<string> values, int n, int maxValues, [NotNullWhen(true)] out string[]? newValues)
 {
 Debug.Assert(n is 2 or 3);
 Debug.Assert(values.Length < maxValues);

 // Count how many possible permutations there are.
 int newValuesCount = 0;

 foreach (string value in values)
 {
 int permutations = 1;

 foreach (char c in value.AsSpan(0, n))
Comment thread
MihaZupan marked this conversation as resolved.

 {
 Debug.Assert(char.IsAscii(c));
Comment thread
MihaZupan marked this conversation as resolved.


 if (char.IsAsciiLetter(c))
 {
 permutations *= 2;
 }
 }

 newValuesCount += permutations;
 }

 Debug.Assert(newValuesCount > values.Length, "Shouldn't have been called if there were no letters present");

 if (newValuesCount > maxValues)
 {
 newValues = null;
 return false;
 }

 // Generate the permutations.
 newValues = new string[newValuesCount];
 newValuesCount = 0;

 foreach (string value in values)
 {
 int start = newValuesCount;

 newValues[newValuesCount++] = value;

 for (int i = 0; i < n; i++)
 {
 char c = value[i];

 if (char.IsAsciiLetter(c))
 {
 // Copy all the previous permutations of this value but change the casing of the i-th character.
 foreach (string previous in newValues.AsSpan(start, newValuesCount - start))
 {
 newValues[newValuesCount++] = $"{previous.AsSpan(0, i)}{(char)(c ^ 0x20)}{previous.AsSpan(i + 1)}";
 }
 }
 }
 }

 Debug.Assert(newValuesCount == newValues.Length);
 return true;
 }

 private static SearchValues<string> CreateForSingleValue(
 string value,
 HashSet<string>? uniqueValues,
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Expand small value sets to all case permutations in SearchValues<string>#98902

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

MihaZupan
merged 2 commits into

from

Mar 2, 2024
 Merged


Expand small value sets to all case permutations in SearchValues<string>
#98902
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
0d381fb

Expand small value sets to all case permutations in SearchValues<string>


MihaZupan Feb 25, 2024
ac5966c

Use the constant in one more place


MihaZupan Feb 25, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


81 changes: 79 additions & 2 deletions
src/libraries/System.Private.CoreLib/src/System/SearchValues/Strings/StringSearchValues.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@

using System.Collections.Generic;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Globalization;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.Arm;
Expand All@@ -14,6 +15,8 @@ namespace System.Buffers
{
 internal static class StringSearchValues
 {
 private const int TeddyBucketCount = 8;

 private static readonly SearchValues<char> s_asciiLetters =
 SearchValues.Create("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");

Expand DownExpand Up@@ -248,6 +251,18 @@ static SearchValues<string> PickAhoCorasickImplementation<TCaseSensitivity>(AhoC

 Debug.Assert(!(asciiStartLettersOnly && asciiStartUnaffectedByCaseConversion));

 // If we still have empty buckets we could use and we're ignoring case, we may be able to
 // generate all possible permutations of the first N characters and switch to case-sensitive searching.
 // E.g. ["ab", "c!"] => ["ab", "Ab" "aB", "AB", "c!", "C!"].
Comment thread
MihaZupan marked this conversation as resolved.

Comment thread
MihaZupan marked this conversation as resolved.

 // This won't apply to inputs with many letters (e.g. "abc" => 8 permutations on its own).
 if (!asciiStartUnaffectedByCaseConversion &&
 values.Length < TeddyBucketCount &&
 TryGenerateAllCasePermutationsForPrefixes(values, n, TeddyBucketCount, out string[]? newValues))
 {
 asciiStartUnaffectedByCaseConversion = true;
 values = newValues;
 }

 if (asciiStartUnaffectedByCaseConversion)
 {
 return nonAsciiAffectedByCaseConversion
Expand DownExpand Up@@ -278,9 +293,9 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 Debug.Assert(values.Length > 1);
 Debug.Assert(n is 2 or 3);

 if (values.Length > 8)
 if (values.Length > TeddyBucketCount)
 {
 string[][] buckets = TeddyBucketizer.Bucketize(values, bucketCount: 8, n);
 string[][] buckets = TeddyBucketizer.Bucketize(values, TeddyBucketCount, n);

 // Potential optimization: We don't have to pick the first N characters for the fingerprint.
 // Different offset selection can noticeably improve throughput (e.g. 2x).
Expand All@@ -297,6 +312,68 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 }
 }

 private static bool TryGenerateAllCasePermutationsForPrefixes(ReadOnlySpan<string> values, int n, int maxValues, [NotNullWhen(true)] out string[]? newValues)
 {
 Debug.Assert(n is 2 or 3);
 Debug.Assert(values.Length < maxValues);

 // Count how many possible permutations there are.
 int newValuesCount = 0;

 foreach (string value in values)
 {
 int permutations = 1;

 foreach (char c in value.AsSpan(0, n))
Comment thread
MihaZupan marked this conversation as resolved.

 {
 Debug.Assert(char.IsAscii(c));
Comment thread
MihaZupan marked this conversation as resolved.


 if (char.IsAsciiLetter(c))
 {
 permutations *= 2;
 }
 }

 newValuesCount += permutations;
 }

 Debug.Assert(newValuesCount > values.Length, "Shouldn't have been called if there were no letters present");

 if (newValuesCount > maxValues)
 {
 newValues = null;
 return false;
 }

 // Generate the permutations.
 newValues = new string[newValuesCount];
 newValuesCount = 0;

 foreach (string value in values)
 {
 int start = newValuesCount;

 newValues[newValuesCount++] = value;

 for (int i = 0; i < n; i++)
 {
 char c = value[i];

 if (char.IsAsciiLetter(c))
 {
 // Copy all the previous permutations of this value but change the casing of the i-th character.
 foreach (string previous in newValues.AsSpan(start, newValuesCount - start))
 {
 newValues[newValuesCount++] = $"{previous.AsSpan(0, i)}{(char)(c ^ 0x20)}{previous.AsSpan(i + 1)}";
 }
 }
 }
 }

 Debug.Assert(newValuesCount == newValues.Length);
 return true;
 }

 private static SearchValues<string> CreateForSingleValue(
 string value,
 HashSet<string>? uniqueValues,
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Expand small value sets to all case permutations in SearchValues<string>#98902

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

MihaZupan
merged 2 commits into

from

Mar 2, 2024
 Merged


Expand small value sets to all case permutations in SearchValues<string>
#98902
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
0d381fb

Expand small value sets to all case permutations in SearchValues<string>


MihaZupan Feb 25, 2024
ac5966c

Use the constant in one more place


MihaZupan Feb 25, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


81 changes: 79 additions & 2 deletions
src/libraries/System.Private.CoreLib/src/System/SearchValues/Strings/StringSearchValues.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@

using System.Collections.Generic;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Globalization;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.Arm;
Expand All@@ -14,6 +15,8 @@ namespace System.Buffers
{
 internal static class StringSearchValues
 {
 private const int TeddyBucketCount = 8;

 private static readonly SearchValues<char> s_asciiLetters =
 SearchValues.Create("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");

Expand DownExpand Up@@ -248,6 +251,18 @@ static SearchValues<string> PickAhoCorasickImplementation<TCaseSensitivity>(AhoC

 Debug.Assert(!(asciiStartLettersOnly && asciiStartUnaffectedByCaseConversion));

 // If we still have empty buckets we could use and we're ignoring case, we may be able to
 // generate all possible permutations of the first N characters and switch to case-sensitive searching.
 // E.g. ["ab", "c!"] => ["ab", "Ab" "aB", "AB", "c!", "C!"].
Comment thread
MihaZupan marked this conversation as resolved.

Comment thread
MihaZupan marked this conversation as resolved.

 // This won't apply to inputs with many letters (e.g. "abc" => 8 permutations on its own).
 if (!asciiStartUnaffectedByCaseConversion &&
 values.Length < TeddyBucketCount &&
 TryGenerateAllCasePermutationsForPrefixes(values, n, TeddyBucketCount, out string[]? newValues))
 {
 asciiStartUnaffectedByCaseConversion = true;
 values = newValues;
 }

 if (asciiStartUnaffectedByCaseConversion)
 {
 return nonAsciiAffectedByCaseConversion
Expand DownExpand Up@@ -278,9 +293,9 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 Debug.Assert(values.Length > 1);
 Debug.Assert(n is 2 or 3);

 if (values.Length > 8)
 if (values.Length > TeddyBucketCount)
 {
 string[][] buckets = TeddyBucketizer.Bucketize(values, bucketCount: 8, n);
 string[][] buckets = TeddyBucketizer.Bucketize(values, TeddyBucketCount, n);

 // Potential optimization: We don't have to pick the first N characters for the fingerprint.
 // Different offset selection can noticeably improve throughput (e.g. 2x).
Expand All@@ -297,6 +312,68 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 }
 }

 private static bool TryGenerateAllCasePermutationsForPrefixes(ReadOnlySpan<string> values, int n, int maxValues, [NotNullWhen(true)] out string[]? newValues)
 {
 Debug.Assert(n is 2 or 3);
 Debug.Assert(values.Length < maxValues);

 // Count how many possible permutations there are.
 int newValuesCount = 0;

 foreach (string value in values)
 {
 int permutations = 1;

 foreach (char c in value.AsSpan(0, n))
Comment thread
MihaZupan marked this conversation as resolved.

 {
 Debug.Assert(char.IsAscii(c));
Comment thread
MihaZupan marked this conversation as resolved.


 if (char.IsAsciiLetter(c))
 {
 permutations *= 2;
 }
 }

 newValuesCount += permutations;
 }

 Debug.Assert(newValuesCount > values.Length, "Shouldn't have been called if there were no letters present");

 if (newValuesCount > maxValues)
 {
 newValues = null;
 return false;
 }

 // Generate the permutations.
 newValues = new string[newValuesCount];
 newValuesCount = 0;

 foreach (string value in values)
 {
 int start = newValuesCount;

 newValues[newValuesCount++] = value;

 for (int i = 0; i < n; i++)
 {
 char c = value[i];

 if (char.IsAsciiLetter(c))
 {
 // Copy all the previous permutations of this value but change the casing of the i-th character.
 foreach (string previous in newValues.AsSpan(start, newValuesCount - start))
 {
 newValues[newValuesCount++] = $"{previous.AsSpan(0, i)}{(char)(c ^ 0x20)}{previous.AsSpan(i + 1)}";
 }
 }
 }
 }

 Debug.Assert(newValuesCount == newValues.Length);
 return true;
 }

 private static SearchValues<string> CreateForSingleValue(
 string value,
 HashSet<string>? uniqueValues,
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Expand small value sets to all case permutations in SearchValues<string>#98902

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

MihaZupan
merged 2 commits into

from

Mar 2, 2024
 Merged


Expand small value sets to all case permutations in SearchValues<string>
#98902
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
0d381fb

Expand small value sets to all case permutations in SearchValues<string>


MihaZupan Feb 25, 2024
ac5966c

Use the constant in one more place


MihaZupan Feb 25, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


81 changes: 79 additions & 2 deletions
src/libraries/System.Private.CoreLib/src/System/SearchValues/Strings/StringSearchValues.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@

using System.Collections.Generic;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Globalization;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.Arm;
Expand All@@ -14,6 +15,8 @@ namespace System.Buffers
{
 internal static class StringSearchValues
 {
 private const int TeddyBucketCount = 8;

 private static readonly SearchValues<char> s_asciiLetters =
 SearchValues.Create("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");

Expand DownExpand Up@@ -248,6 +251,18 @@ static SearchValues<string> PickAhoCorasickImplementation<TCaseSensitivity>(AhoC

 Debug.Assert(!(asciiStartLettersOnly && asciiStartUnaffectedByCaseConversion));

 // If we still have empty buckets we could use and we're ignoring case, we may be able to
 // generate all possible permutations of the first N characters and switch to case-sensitive searching.
 // E.g. ["ab", "c!"] => ["ab", "Ab" "aB", "AB", "c!", "C!"].
Comment thread
MihaZupan marked this conversation as resolved.

Comment thread
MihaZupan marked this conversation as resolved.

 // This won't apply to inputs with many letters (e.g. "abc" => 8 permutations on its own).
 if (!asciiStartUnaffectedByCaseConversion &&
 values.Length < TeddyBucketCount &&
 TryGenerateAllCasePermutationsForPrefixes(values, n, TeddyBucketCount, out string[]? newValues))
 {
 asciiStartUnaffectedByCaseConversion = true;
 values = newValues;
 }

 if (asciiStartUnaffectedByCaseConversion)
 {
 return nonAsciiAffectedByCaseConversion
Expand DownExpand Up@@ -278,9 +293,9 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 Debug.Assert(values.Length > 1);
 Debug.Assert(n is 2 or 3);

 if (values.Length > 8)
 if (values.Length > TeddyBucketCount)
 {
 string[][] buckets = TeddyBucketizer.Bucketize(values, bucketCount: 8, n);
 string[][] buckets = TeddyBucketizer.Bucketize(values, TeddyBucketCount, n);

 // Potential optimization: We don't have to pick the first N characters for the fingerprint.
 // Different offset selection can noticeably improve throughput (e.g. 2x).
Expand All@@ -297,6 +312,68 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 }
 }

 private static bool TryGenerateAllCasePermutationsForPrefixes(ReadOnlySpan<string> values, int n, int maxValues, [NotNullWhen(true)] out string[]? newValues)
 {
 Debug.Assert(n is 2 or 3);
 Debug.Assert(values.Length < maxValues);

 // Count how many possible permutations there are.
 int newValuesCount = 0;

 foreach (string value in values)
 {
 int permutations = 1;

 foreach (char c in value.AsSpan(0, n))
Comment thread
MihaZupan marked this conversation as resolved.

 {
 Debug.Assert(char.IsAscii(c));
Comment thread
MihaZupan marked this conversation as resolved.


 if (char.IsAsciiLetter(c))
 {
 permutations *= 2;
 }
 }

 newValuesCount += permutations;
 }

 Debug.Assert(newValuesCount > values.Length, "Shouldn't have been called if there were no letters present");

 if (newValuesCount > maxValues)
 {
 newValues = null;
 return false;
 }

 // Generate the permutations.
 newValues = new string[newValuesCount];
 newValuesCount = 0;

 foreach (string value in values)
 {
 int start = newValuesCount;

 newValues[newValuesCount++] = value;

 for (int i = 0; i < n; i++)
 {
 char c = value[i];

 if (char.IsAsciiLetter(c))
 {
 // Copy all the previous permutations of this value but change the casing of the i-th character.
 foreach (string previous in newValues.AsSpan(start, newValuesCount - start))
 {
 newValues[newValuesCount++] = $"{previous.AsSpan(0, i)}{(char)(c ^ 0x20)}{previous.AsSpan(i + 1)}";
 }
 }
 }
 }

 Debug.Assert(newValuesCount == newValues.Length);
 return true;
 }

 private static SearchValues<string> CreateForSingleValue(
 string value,
 HashSet<string>? uniqueValues,
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Expand small value sets to all case permutations in SearchValues<string>#98902

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

MihaZupan
merged 2 commits into

from

Mar 2, 2024
 Merged


Expand small value sets to all case permutations in SearchValues<string>
#98902
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
0d381fb

Expand small value sets to all case permutations in SearchValues<string>


MihaZupan Feb 25, 2024
ac5966c

Use the constant in one more place


MihaZupan Feb 25, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


81 changes: 79 additions & 2 deletions
src/libraries/System.Private.CoreLib/src/System/SearchValues/Strings/StringSearchValues.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@

using System.Collections.Generic;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Globalization;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.Arm;
Expand All@@ -14,6 +15,8 @@ namespace System.Buffers
{
 internal static class StringSearchValues
 {
 private const int TeddyBucketCount = 8;

 private static readonly SearchValues<char> s_asciiLetters =
 SearchValues.Create("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");

Expand DownExpand Up@@ -248,6 +251,18 @@ static SearchValues<string> PickAhoCorasickImplementation<TCaseSensitivity>(AhoC

 Debug.Assert(!(asciiStartLettersOnly && asciiStartUnaffectedByCaseConversion));

 // If we still have empty buckets we could use and we're ignoring case, we may be able to
 // generate all possible permutations of the first N characters and switch to case-sensitive searching.
 // E.g. ["ab", "c!"] => ["ab", "Ab" "aB", "AB", "c!", "C!"].
Comment thread
MihaZupan marked this conversation as resolved.

Comment thread
MihaZupan marked this conversation as resolved.

 // This won't apply to inputs with many letters (e.g. "abc" => 8 permutations on its own).
 if (!asciiStartUnaffectedByCaseConversion &&
 values.Length < TeddyBucketCount &&
 TryGenerateAllCasePermutationsForPrefixes(values, n, TeddyBucketCount, out string[]? newValues))
 {
 asciiStartUnaffectedByCaseConversion = true;
 values = newValues;
 }

 if (asciiStartUnaffectedByCaseConversion)
 {
 return nonAsciiAffectedByCaseConversion
Expand DownExpand Up@@ -278,9 +293,9 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 Debug.Assert(values.Length > 1);
 Debug.Assert(n is 2 or 3);

 if (values.Length > 8)
 if (values.Length > TeddyBucketCount)
 {
 string[][] buckets = TeddyBucketizer.Bucketize(values, bucketCount: 8, n);
 string[][] buckets = TeddyBucketizer.Bucketize(values, TeddyBucketCount, n);

 // Potential optimization: We don't have to pick the first N characters for the fingerprint.
 // Different offset selection can noticeably improve throughput (e.g. 2x).
Expand All@@ -297,6 +312,68 @@ private static SearchValues<string> PickTeddyImplementation<TStartCaseSensitivit
 }
 }

 private static bool TryGenerateAllCasePermutationsForPrefixes(ReadOnlySpan<string> values, int n, int maxValues, [NotNullWhen(true)] out string[]? newValues)
 {
 Debug.Assert(n is 2 or 3);
 Debug.Assert(values.Length < maxValues);

 // Count how many possible permutations there are.
 int newValuesCount = 0;

 foreach (string value in values)
 {
 int permutations = 1;

 foreach (char c in value.AsSpan(0, n))
Comment thread
MihaZupan marked this conversation as resolved.

 {
 Debug.Assert(char.IsAscii(c));
Comment thread
MihaZupan marked this conversation as resolved.


 if (char.IsAsciiLetter(c))
 {
 permutations *= 2;
 }
 }

 newValuesCount += permutations;
 }

 Debug.Assert(newValuesCount > values.Length, "Shouldn't have been called if there were no letters present");

 if (newValuesCount > maxValues)
 {
 newValues = null;
 return false;
 }

 // Generate the permutations.
 newValues = new string[newValuesCount];
 newValuesCount = 0;

 foreach (string value in values)
 {
 int start = newValuesCount;

 newValues[newValuesCount++] = value;

 for (int i = 0; i < n; i++)
 {
 char c = value[i];

 if (char.IsAsciiLetter(c))
 {
 // Copy all the previous permutations of this value but change the casing of the i-th character.
 foreach (string previous in newValues.AsSpan(start, newValuesCount - start))
 {
 newValues[newValuesCount++] = $"{previous.AsSpan(0, i)}{(char)(c ^ 0x20)}{previous.AsSpan(i + 1)}";
 }
 }
 }
 }

 Debug.Assert(newValuesCount == newValues.Length);
 return true;
 }

 private static SearchValues<string> CreateForSingleValue(
 string value,
 HashSet<string>? uniqueValues,
Expand Down