Skip to content
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

Improve the identifier detection regex to support non-ascii identifiers #291

Merged
merged 1 commit into from
Jul 5, 2023
Merged

Improve the identifier detection regex to support non-ascii identifiers #291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 12 additions & 7 deletions src/DynamicExpresso.Core/Detector.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,11 +11,11 @@ internal class Detector
{
private readonly ParserSettings _settings;

private static readonly string Type = @"\b(?<type>[a-zA-Z_]\w*)\b";
private static readonly string Id = @"\b(?<id>[a-zA-Z_]\w*)\b";
private static readonly Regex LambdaDetectionRegex = new Regex($@"(\((((?<withtype>({Type}\s+)?{Id}))(\s*,\s*)?)+\)|(?<withtype>{Id}))\s*=>", RegexOptions.Compiled);
private static readonly Regex IdentifiersDetectionRegex = new Regex(@"(?<id>@?[\p{L}\p{Nl}_][\p{L}\p{Nl}\p{Nd}\p{Mn}\p{Mc}\p{Pc}\p{Cf}_]*)", RegexOptions.Compiled);

private static readonly Regex IdentifiersDetectionRegex = new Regex(@"([^\.]|^)\b(?<id>[a-zA-Z_]\w*)\b", RegexOptions.Compiled);
private static readonly string Id = IdentifiersDetectionRegex.ToString();
private static readonly string Type = Id.Replace("<id>", "<type>");
private static readonly Regex LambdaDetectionRegex = new Regex($@"(\((((?<withtype>({Type}\s+)?{Id}))(\s*,\s*)?)+\)|(?<withtype>{Id}))\s*=>", RegexOptions.Compiled);

private static readonly Regex StringDetectionRegex = new Regex(@"(?<!\\)?"".*?(?<!\\)""", RegexOptions.Compiled);
private static readonly Regex CharDetectionRegex = new Regex(@"(?<!\\)?'.{1,2}?(?<!\\)'", RegexOptions.Compiled);
Expand Down Expand Up @@ -57,8 +57,8 @@ public IdentifiersInfo DetectIdentifiers(string expression)
t++;
}

// there might be several lambda parameters with the same name;
// in that case, we ignore the detected type
// there might be several lambda parameters with the same name
// -> in that case, we ignore the detected type
if (lambdaParameters.TryGetValue(identifier, out Identifier already) && already.Expression.Type != type)
type = typeof(object);

Expand All @@ -70,11 +70,16 @@ public IdentifiersInfo DetectIdentifiers(string expression)

foreach (Match match in IdentifiersDetectionRegex.Matches(expression))
{
var identifier = match.Groups["id"].Value;
var idGroup = match.Groups["id"];
var identifier = idGroup.Value;

if (IsReservedKeyword(identifier))
continue;

// don't consider member accesses as identifiers (e.g. "x.Length" will only return x but not Length)
if (idGroup.Index > 0 && expression[idGroup.Index - 1] == '.')
continue;

if (_settings.Identifiers.TryGetValue(identifier, out Identifier knownIdentifier))
knownIdentifiers.Add(knownIdentifier);
else if (lambdaParameters.TryGetValue(identifier, out Identifier knownLambdaParam))
Expand Down
89 changes: 57 additions & 32 deletions test/DynamicExpresso.UnitTest/DetectIdentifiersTest.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ public void Detect_unknown_identifiers()
var detectedIdentifiers = target.DetectIdentifiers("x + y");

CollectionAssert.AreEqual(
new []{ "x", "y"},
new[] { "x", "y" },
detectedIdentifiers.UnknownIdentifiers.ToArray());
}

Expand Down Expand Up @@ -161,36 +161,30 @@ public void Detect_known_identifiers_types()
}

[Test]
public void Detect_identifiers_inside_other_expressions()
[TestCase("x + y")]
[TestCase("x + y + 654")]
[TestCase("x + y + 654.564")]
[TestCase("x.method + y[0]")]
[TestCase("x+y")]
[TestCase("x[y]")]
[TestCase("x.method1.method2(y)")]
[TestCase("x + y + \"z\"")]
[TestCase("x + y + \"lorem ipsum\"")]
[TestCase(@"x + y + ""literal \""2""")]
[TestCase("x + y + \"\"")]
[TestCase("x + y + 'z'")]
[TestCase("x + y + '\\a'")]
[TestCase("x + y + '\\''")]
[TestCase("x+y")]
public void Detect_identifiers_inside_other_expressions(string testCase)
{
var testCases = new[] {
"x + y",
"x + y + 654",
"x + y + 654.564",
"x.method + y[0]",
"x+y",
"x[y]",
"x.method1.method2(y)",
"x + y + \"z\"",
"x + y + \"lorem ipsum\"",
@"x + y + ""literal \""2""",
"x + y + \"\"",
"x + y + 'z'",
"x + y + '\\a'",
"x + y + '\\''",
"x+y",
};

foreach (var testCase in testCases)
{
var target = new Interpreter();
var target = new Interpreter();

var detectedIdentifiers = target.DetectIdentifiers(testCase);
var detectedIdentifiers = target.DetectIdentifiers(testCase);

Assert.AreEqual("x", detectedIdentifiers.UnknownIdentifiers.ElementAt(0));
Assert.AreEqual("y", detectedIdentifiers.UnknownIdentifiers.ElementAt(1));
Assert.AreEqual(2, detectedIdentifiers.UnknownIdentifiers.Count());
}
Assert.AreEqual(2, detectedIdentifiers.UnknownIdentifiers.Count());
Assert.AreEqual("x", detectedIdentifiers.UnknownIdentifiers.ElementAt(0));
Assert.AreEqual("y", detectedIdentifiers.UnknownIdentifiers.ElementAt(1));
}

[Test]
Expand Down Expand Up @@ -233,15 +227,15 @@ public void Detect_identifiers_inside_lambda_expression_multiple_params()
{
var target = new Interpreter(InterpreterOptions.Default | InterpreterOptions.LambdaExpressions);

var detectedIdentifiers = target.DetectIdentifiers("(x, y) => x + y");
var detectedIdentifiers = target.DetectIdentifiers("(x, _1y) => x + _1y");
Assert.IsEmpty(detectedIdentifiers.UnknownIdentifiers);

Assert.AreEqual(2, detectedIdentifiers.Identifiers.Count());

Assert.AreEqual("x", detectedIdentifiers.Identifiers.ElementAt(0).Name);
Assert.AreEqual(typeof(object), detectedIdentifiers.Identifiers.ElementAt(0).Expression.Type);

Assert.AreEqual("y", detectedIdentifiers.Identifiers.ElementAt(1).Name);
Assert.AreEqual("_1y", detectedIdentifiers.Identifiers.ElementAt(1).Name);
Assert.AreEqual(typeof(object), detectedIdentifiers.Identifiers.ElementAt(1).Expression.Type);
}

Expand All @@ -250,7 +244,7 @@ public void Detect_identifiers_inside_lambda_expression_multiple_params_with_typ
{
var target = new Interpreter(InterpreterOptions.Default | InterpreterOptions.LambdaExpressions);

var detectedIdentifiers = target.DetectIdentifiers("(int x, string y) => x + y");
var detectedIdentifiers = target.DetectIdentifiers("(int x, string @class) => x + @class");
Assert.IsEmpty(detectedIdentifiers.UnknownIdentifiers);

Assert.AreEqual(2, detectedIdentifiers.Types.Count());
Expand All @@ -264,7 +258,7 @@ public void Detect_identifiers_inside_lambda_expression_multiple_params_with_typ
Assert.AreEqual("x", detectedIdentifiers.Identifiers.ElementAt(0).Name);
Assert.AreEqual(typeof(int), detectedIdentifiers.Identifiers.ElementAt(0).Expression.Type);

Assert.AreEqual("y", detectedIdentifiers.Identifiers.ElementAt(1).Name);
Assert.AreEqual("@class", detectedIdentifiers.Identifiers.ElementAt(1).Name);
Assert.AreEqual(typeof(string), detectedIdentifiers.Identifiers.ElementAt(1).Expression.Type);
}

Expand Down Expand Up @@ -299,5 +293,36 @@ public void Detect_identifiers_inside_lambda_expression_duplicate_param_name()
Assert.AreEqual("b", detectedIdentifiers.Identifiers.ElementAt(4).Name);
Assert.AreEqual(typeof(string), detectedIdentifiers.Identifiers.ElementAt(4).Expression.Type);
}

[Test]
[TestCase("@class")]
[TestCase("français_holé")]
[TestCase("中文")]
[TestCase("_1中0文")]
[TestCase("日本語")]
[TestCase("русский")]
public void Detect_all_identifiers_including_not_ascii(string identifier)
{
var code = $"1 + {identifier}.Method()";

var target = new Interpreter(InterpreterOptions.Default | InterpreterOptions.LambdaExpressions);
var detectedIdentifiers = target.DetectIdentifiers(code);

Assert.AreEqual(1, detectedIdentifiers.UnknownIdentifiers.Count());
Assert.AreEqual(identifier, detectedIdentifiers.UnknownIdentifiers.ElementAt(0));
}

[Test]
public void Dont_detect_members_with_at()
{
var code = "@class.@if()";

var target = new Interpreter(InterpreterOptions.Default | InterpreterOptions.LambdaExpressions);
var detectedIdentifiers = target.DetectIdentifiers(code);

// @class should be detected as an identifier, but not the @if because it's a member
Assert.AreEqual(1, detectedIdentifiers.UnknownIdentifiers.Count());
Assert.AreEqual("@class", detectedIdentifiers.UnknownIdentifiers.ElementAt(0));
}
}
}