Generate whole regexp by default

s9e · Apr 5, 2022 · 759c9e8 · 759c9e8
1 parent db93fc1
commit 759c9e8
Show file tree

Hide file tree

Showing 4 changed files with 38 additions and 23 deletions.
diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
 s9e\RegexpBuilder is a single-purpose library that generates a regular expression that matches a given list of strings. It is best suited for efficiently finding a list of literals inside of a text.
 
-Simply put, given `['foo', 'bar', 'baz']` as input, the library will generate `(?:ba[rz]|foo)`, a regular expression that can match any of the strings `foo`, `bar`, or `baz`.
+Simply put, given `['foo', 'bar', 'baz']` as input, the library will generate `ba[rz]|foo`, a regular expression that can match any of the strings `foo`, `bar`, or `baz`.
 
 [![Build status](https://github.com/s9e/RegexpBuilder/actions/workflows/build.yml/badge.svg)](https://github.com/s9e/RegexpBuilder/actions/workflows/build.yml)
 [![Code Coverage](https://scrutinizer-ci.com/g/s9e/RegexpBuilder/badges/coverage.png?b=master)](https://scrutinizer-ci.com/g/s9e/RegexpBuilder/?branch=master)
@@ -14,7 +14,7 @@ $builder = new s9e\RegexpBuilder\Builder;
 echo '/', $builder->build(['foo', 'bar', 'baz']), '/';
 ```
 ```
-/(?:ba[rz]|foo)/
+/ba[rz]|foo/
 ```
 
 
@@ -181,7 +181,7 @@ $builder = new s9e\RegexpBuilder\Builder([
 echo '/', $builder->build(['foo?', 'bar*']), '/';
 ```
 ```
-/(?:bar.*|foo.)/
+/bar.*|foo./
 ```
 
 In the following example, we map `X` to `\d`. Note that sequences produced by meta-characters may appear in character classes if the result is valid.

diff --git a/src/Builder.php b/src/Builder.php
@@ -41,6 +41,12 @@ class Builder
 	*/
 	public Serializer $serializer;
 
+	/**
+	* @var bool Whether the expression generated is meant to be used whole. If not, alternations
+	*           will be put into a non-capturing group
+	*/
+	public bool $standalone = true;
+
 	/**
 	* @param array $config
 	*/
@@ -80,7 +86,7 @@ public function build(array $strings): string
 		$strings = $this->meta->replaceMeta($strings);
 		$strings = $this->runner->run($strings);
 
-		return $this->serializer->serializeStrings($strings);
+		return $this->serializer->serializeStrings($strings, !$this->standalone);
 	}
 
 	/**

diff --git a/tests/BuilderTest.php b/tests/BuilderTest.php
@@ -10,6 +10,15 @@
 */
 class BuilderTest extends TestCase
 {
+	public function testStandalone()
+	{
+		$builder = new Builder;
+		$this->assertEquals('bar|foo', $builder->build(['foo', 'bar']));
+
+		$builder->standalone = false;
+		$this->assertEquals('(?:bar|foo)', $builder->build(['foo', 'bar']));
+	}
+
 	/**
 	* @dataProvider getBuilderTests
 	*/
@@ -31,15 +40,15 @@ public function getBuilderTests()
 					'foo',
 					'bar'
 				],
-				'(?:bar|foo)'
+				'bar|foo'
 			],
 			[
 				[
 					'foo',
 					'fool',
 					'bar'
 				],
-				'(?:bar|fool?)'
+				'bar|fool?'
 			],
 			[
 				[
@@ -91,7 +100,7 @@ public function getBuilderTests()
 					"\xEF\xA4\x80\xEF\xA4\x80",
 					"\xF0\x9F\x98\x80\xF0\x9F\x98\x80"
 				],
-				'(?:\\x{D7FB}\\x{D7FB}|\\x{F900}\\x{F900}|\\x{1F600}\\x{1F600})',
+				'\\x{D7FB}\\x{D7FB}|\\x{F900}\\x{F900}|\\x{1F600}\\x{1F600}',
 				['input' => 'Utf8', 'output' => 'PHP']
 			],
 			[
@@ -100,7 +109,7 @@ public function getBuilderTests()
 					"\xEF\xA4\x80\xEF\xA4\x80",
 					"\xF0\x9F\x98\x80"
 				],
-				'(?:\\uD7FB\\uD7FB|\\uF900\\uF900|\\uD83D\\uDE00)',
+				'\\uD7FB\\uD7FB|\\uF900\\uF900|\\uD83D\\uDE00',
 				[
 					'input'        => 'Utf8',
 					'inputOptions' => ['useSurrogates' => true],
@@ -129,7 +138,7 @@ public function getBuilderTests()
 			],
 			[
 				["\n", '.'],
-				'(?:\\n|.)',
+				'\\n|.',
 				['meta' => ['.' => '.'], 'output' => 'PHP']
 			],
 			[

diff --git a/tests/ValidationTest.php b/tests/ValidationTest.php
@@ -40,7 +40,7 @@ public function getValidationTests()
 			],
 			[
 				// CoalesceSingleCharacterPrefix
-				'(?:[ab]b|c)',
+				'[ab]b|c',
 				['ab', 'bb', 'c']
 			],
 			[
@@ -130,7 +130,7 @@ public function getValidationTests()
 				['best', 'boost', 'bust']
 			],
 			[
-				'(?:b(?:oo)?st|cool)',
+				'b(?:oo)?st|cool',
 				['boost', 'bst', 'cool']
 			],
 			[
@@ -166,13 +166,13 @@ public function getValidationTests()
 				['axx', 'ayy', 'bbxx', 'bbyy']
 			],
 			[
-				'(?:a(?:xx|yy)|bb(?:xx|yy)|c)',
+				'a(?:xx|yy)|bb(?:xx|yy)|c',
 				['axx', 'ayy', 'bbxx', 'bbyy', 'c']
 			],
 			[
 				// Ensure it doesn't become (?:c|(?:a|bb)(?:xx|yy)|azz) even though it would be
 				// shorter, because having fewer alternations at the top level is more important
-				'(?:a(?:xx|yy|zz)|bb(?:xx|yy)|c)',
+				'a(?:xx|yy|zz)|bb(?:xx|yy)|c',
 				['axx', 'ayy', 'azz', 'bbxx', 'bbyy', 'c']
 			],
 			[
@@ -192,7 +192,7 @@ public function getValidationTests()
 				['ax', 'ay', 'bx', 'by']
 			],
 			[
-				'(?:[ab][xy]|c)',
+				'[ab][xy]|c',
 				['ax', 'ay', 'bx', 'by', 'c']
 			],
 			[
@@ -204,15 +204,15 @@ public function getValidationTests()
 				['03', '04', '13', '14', '3', '4']
 			],
 			[
-				'(?:a[xy]|bb[xy]|c)',
+				'a[xy]|bb[xy]|c',
 				['ax', 'ay', 'bbx', 'bby', 'c']
 			],
 			[
-				'(?:[ab][xy]|c|dd[xy])',
+				'[ab][xy]|c|dd[xy]',
 				['ax', 'ay', 'bx', 'by', 'c', 'ddx', 'ddy']
 			],
 			[
-				'(?:[ab][xy]|[cd][XY]|[ef]|gg)',
+				'[ab][xy]|[cd][XY]|[ef]|gg',
 				['ax', 'ay', 'bx', 'by', 'cX', 'cY', 'dX', 'dY', 'e', 'f', 'gg']
 			],
 			[
@@ -235,15 +235,15 @@ public function getValidationTests()
 				[]
 			],
 			[
-				'(?:[yz]|bar|foo)',
+				'[yz]|bar|foo',
 				['foo', 'bar', 'y', 'z']
 			],
 			[
-				'(?:[yz]|ba[rz]|foo)',
+				'[yz]|ba[rz]|foo',
 				['foo', 'bar', 'baz', 'y', 'z']
 			],
 			[
-				'(?:a(?:a(?:cc|dd))?|bb(?:cc|dd))',
+				'a(?:a(?:cc|dd))?|bb(?:cc|dd)',
 				['a', 'aacc', 'aadd', 'bbcc', 'bbdd']
 			],
 			[
@@ -259,7 +259,7 @@ public function getValidationTests()
 				]
 			],
 			[
-				'(?:[1-7][0-7]?|0)',
+				'[1-7][0-7]?|0',
 				array_map('decoct', range(0, 63))
 			],
 			[
@@ -279,7 +279,7 @@ public function getValidationTests()
 				]
 			],
 			[
-				'(?:12?3?|23?|3)',
+				'12?3?|23?|3',
 				['1', '12', '123', '13', '2', '23', '3']
 			],
 			[
@@ -332,7 +332,7 @@ function ($n)
 			[
 				// CoalesceSingleCharacterPrefix should ignore expressions that do not represent a
 				// single character
-				'(?:[\\dab]x|\\bx|\\d+x|zz)',
+				'[\\dab]x|\\bx|\\d+x|zz',
 				['ax', 'bx', '?x', '*x', '#x', 'zz'],
 				['meta' => ['*' => '\\d+', '#' => '\\b', '?' => '\\d']]
 			],