em 04: codegen — generate the refactoring, round-trip check, unified-diff preview

RefactoringGenerator emits the new method (promoted signature, parameter
names = source symbol names) plus the rewritten call site for every
em 02/03 bucket shape (return slot declared inside/outside, tuple
deconstruction, ref write-back, return-call when the selection ends a
non-void method) and refuses loudly where v1 cannot be sound (composite
trailing return, return not ending the method).

The transformed tree must compile with zero diagnostics (the yak's
round-trip check, enforced in both the CLI and the tests).

Findings that shaped the implementation, all enforced by tests:
- NormalizeWhitespace on the WHOLE root corrupts doc-comment trivia so
  Roslyn's XML-doc writer fails with CS1569 ('count (-3) must be
  non-negative') — and it would reformat the entire file, killing the
  diff. Only generated nodes are normalized; original trivia is kept and
  indentation/end-of-line is grafted onto the inserted statements/method.
- ParseTypeName("void") yields a node rejected as a method return type
  (CS1547) — a void signature must be PredefinedType(Token(VoidKeyword)).
- NormalizeWhitespace drops the space after the contextual keyword 'var'
  before '(' — the parsed 'var (x, y) = ...' deconstruction skeleton is
  used verbatim; builder-made statements are normalized.
- The new method is normalized inside a throwaway class wrapper: the
  normalizer computes indentation from nesting depth, and a bare method
  has none.

v1 decision: print a unified-diff PREVIEW to stdout (hand-rolled LCS
unified diff), never an in-place rewrite. Also fixes the hunk header
off-by-one from the phantom trailing empty line of Split('\n').
This commit is contained in:
2026-09-12 21:15:28 +01:00
parent 49a5633a7d
commit cdadafe676
6 changed files with 892 additions and 6 deletions
@@ -115,4 +115,37 @@ public class Demo
{
return (double)total / _seed;
}
/// <summary>Bucket (em 04 codegen): a local DECLARED BEFORE the selection
/// that the selection writes and the tail reads — the promoted signature
/// keeps it as a <c>ref</c> parameter (the write-back already flows the
/// value out, so the result is not re-returned; void) and the call site
/// is a plain call, no assignment: <c>Extract(ref acc, n);</c>.</summary>
public int Accumulate(int n)
{
int acc = 0;
for (int i = 0; i < n; i++)
{
acc += i;
}
return acc * 2;
}
/// <summary>Bucket (em 04 codegen): TWO locals declared inside, both
/// written inside and read after — the promoted signature returns a
/// tuple <c>(int, int)</c> and the call site deconstructs it:
/// <c>var (x, y) = Extract(n);</c>.</summary>
public (int, int) Pairwise(int n)
{
int x = 0;
int y = 1;
for (int i = 0; i < n; i++)
{
x += i;
y += i * 2;
}
return (x + y, x - y);
}
}
@@ -0,0 +1,227 @@
using ExtractMethod.Tooling;
using Microsoft.CodeAnalysis;
using Microsoft.CodeAnalysis.CSharp;
using Microsoft.CodeAnalysis.CSharp.Syntax;
namespace BeforeAfter.Tests.ExtractMethod;
/// <summary>
/// Tests for yak em 04 (codegen): generate the refactoring from the em 03
/// suggestion — new method (promoted signature, parameter names from the
/// source symbols) + rewritten call site + transformed tree — and the
/// round-trip check (the transformed tree compiles with zero diagnostics).
///
/// Fixture line anchors: the em 01/02/03 anchors (ScoreReads 56..58,
/// Summarize 68..76 / partial 68..72, Heaviest 87..93) plus the em 04
/// additions Accumulate for-loop 127..130 and Pairwise 141..147.
/// </summary>
public class RefactoringTests
{
// ---------------------------------------------------------------------
// Summarize partial (68..72): the declared-inside `total` promotes to the
// plain return of the new method; at the call site it is re-declared from
// the result. The new body gains the appended `return total;`.
// ---------------------------------------------------------------------
[Fact]
public void Summarize_partial_selection_generates_returning_method_and_declaration_call()
{
var (method, calls, tree) = Generate(68, 72);
Assert.Equal("Extract", method.Identifier.ValueText);
Assert.Equal("int", method.ReturnType.ToString());
Assert.Equal(new[] { "int limit" }, method.ParameterList.Parameters.Select(p => p.ToString()));
var body = (BlockSyntax)method.Body!;
Assert.Equal(3, body.Statements.Count); // total declaration, for-loop, appended return
Assert.Equal("return total;", body.Statements[2].ToString());
// `total` was declared inside the selection: re-declared at the call
// site from the result.
Assert.Single(calls);
Assert.Equal("int total = Extract(limit);", calls[0].ToString());
VerifyZeroDiagnostics(tree);
}
// ---------------------------------------------------------------------
// Summarize full body (68..76): the selection ends the (non-void)
// enclosing method and the trailing `return message;` is nameable — the
// call site becomes `return Extract(limit);` and NO extra return is
// appended to the new body (the existing one is kept).
// ---------------------------------------------------------------------
[Fact]
public void Summarize_full_body_selection_becomes_return_call()
{
var (method, calls, tree) = Generate(68, 76);
Assert.Equal("Extract", method.Identifier.ValueText);
Assert.Equal("string", method.ReturnType.ToString());
Assert.Equal(new[] { "int limit" }, method.ParameterList.Parameters.Select(p => p.ToString()));
var body = (BlockSyntax)method.Body!;
Assert.Equal(5, body.Statements.Count); // total, for, scaled, message, return — unchanged
Assert.Equal("return message;", body.Statements[^1].ToString());
Assert.Single(calls);
Assert.Equal("return Extract(limit);", calls[0].ToString());
VerifyZeroDiagnostics(tree);
}
// ---------------------------------------------------------------------
// Heaviest full body (87..93): the trailing `return best;` names the
// single return slot, which matches the enclosing method's return type —
// again a `return Extract(...)` call site, with the widgets/count
// parameters as plain in-params.
// ---------------------------------------------------------------------
[Fact]
public void Heaviest_full_body_selection_becomes_return_call()
{
var (method, calls, tree) = Generate(87, 93);
Assert.Equal("Widget", method.ReturnType.ToString());
Assert.Equal(new[] { "int count", "List<Widget> widgets" },
method.ParameterList.Parameters.Select(p => p.ToString()));
var body = (BlockSyntax)method.Body!;
Assert.Equal(3, body.Statements.Count);
Assert.Equal("return best;", body.Statements[^1].ToString());
Assert.Single(calls);
Assert.Equal("return Extract(count, widgets);", calls[0].ToString());
VerifyZeroDiagnostics(tree);
}
// ---------------------------------------------------------------------
// ScoreReads (56..58): the enclosing method returns int but the selection
// ends with the COMPOSITE `return score + bonus;` — not nameable in v1,
// so the promoted signature is void and codegen must REFUSE (the report
// note already says: extract a local first, then re-run).
// ---------------------------------------------------------------------
[Fact]
public void ScoreReads_refuses_when_the_composite_trailing_return_is_not_nameable()
{
var (tree, compilation) = DemoFixture.Load();
var model = compilation.GetSemanticModel(tree);
var resolved = SelectionResolver.Resolve(tree, 56, 58);
Assert.True(resolved.Succeeded, resolved.Error);
var suggestion = DataFlowClassifier.Classify(model, resolved);
var signature = SignatureBuilder.Build(model, resolved, suggestion);
Assert.Equal("void", signature.ReturnType);
var ex = Assert.Throws<InvalidOperationException>(
() => RefactoringGenerator.Generate(model, resolved, signature));
Assert.Contains("extract it into a local first", ex.Message, StringComparison.Ordinal);
}
// ---------------------------------------------------------------------
// Accumulate for-loop (127..130): `acc` is declared BEFORE the selection,
// written inside and read after — the promoted signature keeps it as a
// ref parameter (the write-back flows the value out; void return, no
// return slot) and the call site is a plain call with `ref acc`.
// ---------------------------------------------------------------------
[Fact]
public void Accumulate_forloop_selection_calls_with_ref_write_back()
{
var (method, calls, tree) = Generate(127, 130);
Assert.Equal("void", method.ReturnType.ToString());
Assert.Equal(new[] { "ref int acc", "int n" },
method.ParameterList.Parameters.Select(p => p.ToString()));
var body = (BlockSyntax)method.Body!;
Assert.Single(body.Statements); // the for-loop; no return appended (void)
Assert.Single(calls);
Assert.Equal("Extract(ref acc, n);", calls[0].ToString());
VerifyZeroDiagnostics(tree);
}
// ---------------------------------------------------------------------
// Pairwise (141..147): two declared-inside locals both written inside and
// read after — the promoted signature returns the tuple `(int, int)` and
// the call site deconstructs it; the new body gains `return (x, y);`.
// ---------------------------------------------------------------------
[Fact]
public void Pairwise_selection_generates_tuple_return_and_deconstruction_call()
{
var (method, calls, tree) = Generate(141, 147);
Assert.Equal("(int, int)", method.ReturnType.ToString());
Assert.Equal(new[] { "int n" }, method.ParameterList.Parameters.Select(p => p.ToString()));
var body = (BlockSyntax)method.Body!;
Assert.Equal(4, body.Statements.Count); // x, y, for-loop, appended tuple return
Assert.Equal("return (x, y);", body.Statements[^1].ToString());
Assert.Single(calls);
Assert.Equal("var (x, y) = Extract(n);", calls[0].ToString());
VerifyZeroDiagnostics(tree);
}
// ---------------------------------------------------------------------
// The unified diff, pinned exactly for a minimal edit (hunk header,
// context, deletion before insertion).
// ---------------------------------------------------------------------
[Fact]
public void UnifiedDiff_pins_the_hunk_format()
{
var diff = UnifiedDiff.Diff(
"a\nb\nc\n", "a\nX\nc\nd\n", "Demo.cs", "Demo.cs (generated)");
Assert.Equal(
"--- Demo.cs\n" +
"+++ Demo.cs (generated)\n" +
"@@ -1,3 +1,4 @@\n" +
" a\n" +
"-b\n" +
"+X\n" +
" c\n" +
"+d\n",
diff);
}
// ---------------------------------------------------------------------
// Identical texts produce a header with no hunks.
// ---------------------------------------------------------------------
[Fact]
public void UnifiedDiff_of_identical_texts_is_header_only()
{
Assert.Equal("--- a\n+++ b\n", UnifiedDiff.Diff("same\n", "same\n", "a", "b"));
}
// ---------------------------------------------------------------------
private static (MethodDeclarationSyntax Method, List<StatementSyntax> Calls, SyntaxTree Tree)
Generate(int startLine, int endLine)
{
var (tree, compilation) = DemoFixture.Load();
var model = compilation.GetSemanticModel(tree);
var resolved = SelectionResolver.Resolve(tree, startLine, endLine);
Assert.True(resolved.Succeeded, resolved.Error);
var suggestion = DataFlowClassifier.Classify(model, resolved);
var signature = SignatureBuilder.Build(model, resolved, suggestion);
var refactoring = RefactoringGenerator.Generate(model, resolved, signature);
return (refactoring.NewMethod, refactoring.CallStatements.ToList(), refactoring.TransformedTree);
}
/// <summary>
/// The yak's round-trip check: the transformed tree must compile with
/// ZERO diagnostics under the same scratch compilation the input file
/// compiles under.
/// </summary>
private static void VerifyZeroDiagnostics(SyntaxTree tree)
{
var compilation = CompilationLoader.CreateCompilation(tree, "DemoFixture");
var diagnostics = compilation.GetDiagnostics().ToList();
Assert.True(diagnostics.Count == 0, string.Join("\n", diagnostics));
}
}
+38 -4
View File
@@ -46,18 +46,52 @@ if (!resolved.Succeeded)
}
// 4. compose the full suggestion (em 02 buckets + em 03 extract-first and
// signature) and print the report. A composition failure is a semantic
// resolution error: same exit code as the resolver, message on stderr,
// but never a stack trace.
// signature), generate the refactoring (em 04), verify it and print the
// diff. Any failure is a clean error: message on stderr, same exit code
// as the resolver, never a stack trace.
var model = compilation.GetSemanticModel(tree);
try
{
var extraction = ExtractionReporter.Compose(model, resolved);
Console.Write(ReportFormatter.Format(extraction));
// 5. generate the refactoring from the suggestion (em 04 codegen): new
// method + rewritten call site + transformed tree.
var refactoring = RefactoringGenerator.Generate(model, resolved, extraction.Signature);
// 6. round-trip check: the generated code must compile with zero
// diagnostics (same scratch-compilation path as the input file).
var transformedCompilation = CompilationLoader.CreateCompilation(
refactoring.TransformedTree, Path.GetFileNameWithoutExtension(file));
var diagnostics = transformedCompilation.GetDiagnostics().ToList();
if (diagnostics.Count > 0)
{
Console.Error.WriteLine(
$"error: round-trip check failed — the generated code has {diagnostics.Count} diagnostic(s):");
foreach (var diagnostic in diagnostics)
{
Console.Error.WriteLine($" {diagnostic}");
}
Console.Error.WriteLine("---- generated code ----");
Console.Error.Write(refactoring.TransformedText);
return SelectionResolver.ExitError;
}
// 7. v1 decision (em 04): print a unified diff to stdout — PREVIEW, never
// an in-place file rewrite. Applying the diff (or a future --write
// flag with backup semantics) is a deliberate next step, because
// mutating the caller's file is a different safety policy than
// generating code.
Console.Write(UnifiedDiff.Diff(
tree.ToString(),
refactoring.TransformedText,
Path.GetFileName(file),
Path.GetFileName(file) + " (generated)"));
}
catch (Exception e) when (e is InvalidOperationException or ArgumentException)
{
Console.Error.WriteLine($"error: data-flow analysis failed: {e.Message}");
Console.Error.WriteLine($"error: {e.Message}");
return SelectionResolver.ExitError;
}
@@ -0,0 +1,399 @@
using Microsoft.CodeAnalysis;
using Microsoft.CodeAnalysis.CSharp;
using Microsoft.CodeAnalysis.CSharp.Syntax;
namespace ExtractMethod.Tooling;
/// <summary>
/// The generated extract-method refactoring (yak em 04 codegen): the NEW
/// method (the em 03 promoted signature; parameter names come straight from
/// the source symbols), the CALL STATEMENTS that replace the selection in the
/// enclosing method, and the fully transformed syntax tree.
/// </summary>
/// <param name="NewMethod">The extracted method, ready to be read. Built
/// with SyntaxFactory and NORMALIZED (whitespace) before insertion, so its
/// text is the readable shape that lands in the file — not the trivia-less
/// builder output.</param>
/// <param name="CallStatements">The statement(s) that replace the selected
/// run at the call site (one statement, or a capture + destructure pair for
/// a mixed tuple return), normalized like <see cref="NewMethod"/>.</param>
/// <param name="TransformedTree">The whole input tree with the selection
/// moved out and the new method added next to the enclosing one — the
/// round-trip check compiles exactly this tree.</param>
public sealed record Refactoring(
MethodDeclarationSyntax NewMethod,
IReadOnlyList<StatementSyntax> CallStatements,
SyntaxTree TransformedTree)
{
public string TransformedText => TransformedTree.ToString();
}
/// <summary>
/// Emits the refactoring behind the em 03 suggestion.
///
/// WHY no identifier rewriting at all: the suggested parameter names ARE the
/// source variable names (em 02/03 promotion), so the moved statements bind
/// unchanged — every local/parameter read inside the selection is a parameter
/// of the new method, every variable declared inside moves with the body, and
/// the remaining reads are type members visible from the same class
/// (the new method is inserted into the SAME containing type). This is the
/// property the resolver (one method body, whole statements) and the
/// classifier (params bucket = exactly the local/parameter reads) jointly
/// guarantee; a generic SyntaxRewriter renaming pass would be dead weight in
/// v1. What IS generated structurally:
/// - the new method declaration (signature line, static-ness mirrored from
/// the enclosing method, body = selected statements + appended
/// <c>return ...</c> for return slots the selection did not already end
/// with a return of),
/// - the call statement(s) replacing the selection,
/// - the insertion of the new method right after the enclosing one.
///
/// CALL-SITE RULES (per promoted return slots, v1):
/// - void → a plain call expression statement. A ref parameter already flows
/// the value back (e.g. Accumulate: <c>Extract(ref acc, n);</c>).
/// - one slot DECLARED inside the selection → redeclared at the call site
/// from the result: <c>int total = Extract(limit);</c>.
/// - one slot declared OUTSIDE → plain assignment: <c>acc = Extract(...);</c>.
/// - several slots ALL declared inside → tuple deconstruction:
/// <c>var (x, y) = Extract(n);</c>.
/// - several slots, any declared outside → capture + ItemN assignments
/// (the result is evaluated ONCE, then assigned member-wise).
/// - the enclosing method's return type is non-void and the selection ends
/// the method → the call site must be <c>return Extract(...);</c> and the
/// suggested return type must equal the enclosing one (otherwise: refuse).
///
/// REFUSALS (loud, never a silent wrong refactoring):
/// - the selection contains a return that does NOT end the enclosing method
/// (v1: select to the end of the method);
/// - the suggested return type does not match the enclosing method's return
/// type — including the em 03 "composite trailing return" case, where the
/// signature is void although the enclosing method returns a value (the
/// report's note already says: extract a local first, then re-run).
///
/// BUILDER STYLE: single-slot declarations and assignments are hand-built
/// with SyntaxFactory; the deconstruction call <c>var (x, y) = ...;</c> and
/// the tuple return <c>return (x, y);</c> are PARSED from a text skeleton and
/// the call slot swapped in via ReplaceNode — the parser knows the
/// designation/tuple-element shapes a v1 builder would get wrong. (Parse
/// diagnostics would surface as red nodes and fail the round-trip check
/// loudly, not silently.)
///
/// KNOWN v1 APPROXIMATIONS: type display strings are re-parsed for the
/// generated declarations (a tuple return with a comma-bearing generic type
/// element is not supported); the capture name <c>result</c> could in theory
/// collide with an enclosing local; the name check "suggested return type ==
/// enclosing return type" is a string comparison, not symbol equality.
/// </summary>
public static class RefactoringGenerator
{
public static Refactoring Generate(SemanticModel model, SelectionReport selection, SignatureSuggestion signature)
{
var method = selection.Method!;
var body = method.Body!;
var declaredInside = SignatureBuilder.DeclaredInsideNames(model, selection);
var slots = signature.ReturnSlots.ToList();
var slotNames = slots.Select(s => s.Name).ToList();
var containsReturn = selection.Statements.OfType<ReturnStatementSyntax>().Any();
var selectionEndsBody = ReferenceEquals(selection.Statements[^1], body.Statements[^1]);
var enclosingNonVoid = method.ReturnType is not PredefinedTypeSyntax voidType
|| !voidType.Keyword.IsKind(SyntaxKind.VoidKeyword);
var enclosingReturnType = method.ReturnType.ToString();
// ---- soundness refusals (see class comment) ----
if (containsReturn && enclosingNonVoid)
{
if (!selectionEndsBody)
{
throw new InvalidOperationException(
"the selection contains a return that does not end the enclosing method — select to the end of the method (v1 codegen)");
}
if (signature.ReturnType != enclosingReturnType)
{
throw new InvalidOperationException(
signature.ReturnType == "void"
? "the selection ends with the method's return, but its value is not nameable in v1 — " +
"extract it into a local first (see the report note), then re-run"
: $"the suggested return type {signature.ReturnType} does not match the enclosing method's " +
$"return type {enclosingReturnType} — refusing to generate");
}
}
// ---- the call expression (parameter names = source names, ref-ness kept) ----
var arguments = signature.Params
.Select(p =>
{
var argument = SyntaxFactory.Argument(SyntaxFactory.IdentifierName(p.Name));
return p.ByRef
? argument.WithRefOrOutKeyword(SyntaxFactory.Token(SyntaxKind.RefKeyword))
: argument;
})
.ToList();
var invocation = SyntaxFactory.InvocationExpression(
SyntaxFactory.IdentifierName(signature.MethodName))
.WithArgumentList(SyntaxFactory.ArgumentList(SyntaxFactory.SeparatedList(arguments)))
// Normalized once, here: the PARSED deconstruction skeleton (see
// BuildCallStatements) must not be re-normalized (the normalizer
// drops the space after the contextual keyword `var` before `(`),
// so it receives the invocation already properly spaced.
.NormalizeWhitespace();
// Normalizing only the GENERATED nodes keeps the original trivia —
// and therefore the doc comments — untouched (a whole-root
// NormalizeWhitespace corrupts doc-comment trivia in a way Roslyn's
// XML-doc writer rejects with CS1569, and it would also reformat the
// entire file, making the printed diff useless). The call statements
// and the new method get their indentation/end-of-line grafted from
// the selection they replace, so the edit slots into the original
// formatting.
var callStatements = BuildCallStatements(slots, slotNames, invocation, declaredInside,
callMustReturn: containsReturn && enclosingNonVoid).ToList();
var indent = SyntaxFactory.TriviaList(
selection.Statements[0].GetLeadingTrivia().Where(t => t.IsKind(SyntaxKind.WhitespaceTrivia)));
for (var index = 0; index < callStatements.Count; index++)
{
var call = callStatements[index].WithLeadingTrivia(indent);
if (index == callStatements.Count - 1)
{
// The replaced statement's trailing end-of-line kept the
// following token (the next statement or the closing brace)
// on its own line — carry it over.
call = call.WithTrailingTrivia(selection.Statements[^1].GetTrailingTrivia());
}
callStatements[index] = call;
}
// Normalize the new method INSIDE a throwaway class wrapper: the
// normalizer computes indentation from nesting depth, and a bare
// method node has none — its body would come out flush-left. At class
// depth the signature lands one level in and the body two. The grafted
// leading/trailing trivia below replaces whatever the wrapper put
// around the member.
var newMethod = (MethodDeclarationSyntax)SyntaxFactory.ClassDeclaration("__normalizer__")
.WithMembers(SyntaxFactory.SingletonList<MemberDeclarationSyntax>(
BuildNewMethod(method, selection, signature, slots, slotNames)))
.NormalizeWhitespace()
.Members[0];
var methodIndent = method.GetLeadingTrivia()
.LastOrDefault(t => t.IsKind(SyntaxKind.WhitespaceTrivia));
newMethod = newMethod
.WithLeadingTrivia(SyntaxFactory.TriviaList(SyntaxFactory.EndOfLine("\n"), methodIndent))
.WithTrailingTrivia(SyntaxFactory.EndOfLine("\n"));
// ---- apply to the tree: swap the selection for the call, add the method ----
var allStatements = body.Statements;
var firstIndex = allStatements.IndexOf(selection.Statements[0]); // reference identity: same tree
var newStatements = new List<StatementSyntax>();
newStatements.AddRange(allStatements.Take(firstIndex));
newStatements.AddRange(callStatements);
newStatements.AddRange(allStatements.Skip(firstIndex + selection.Statements.Count));
var rewrittenMethod = method.WithBody(body.WithStatements(SyntaxFactory.List(newStatements)));
// The new method lands right after the enclosing one, in the SAME type
// (that is what keeps the extract-first own-class members in scope).
var containingType = method.AncestorsAndSelf().OfType<TypeDeclarationSyntax>().First();
var memberIndex = containingType.Members.IndexOf(method);
var newType = containingType.WithMembers(
containingType.Members.Replace(method, rewrittenMethod).Insert(memberIndex + 1, newMethod));
var tree = model.SyntaxTree;
var visited = new SingleNodeReplacer(containingType, newType).Visit(tree.GetRoot());
if (visited is null)
{
throw new InvalidOperationException("the type replacement rewrote the root away (internal error)");
}
return new Refactoring(newMethod, callStatements, tree.WithRootAndOptions(visited, tree.Options));
}
/// <summary>
/// The one place a SyntaxRewriter enters this tool (yak em 04's stated
/// curriculum): swapping a single node by REFERENCE identity. The typed
/// With*-slices (WithBody, WithMembers) cover the local changes; only the
/// "put the rewritten type back into the root" step is a whole-tree walk.
/// </summary>
private sealed class SingleNodeReplacer : CSharpSyntaxRewriter
{
private readonly SyntaxNode _oldNode;
private readonly SyntaxNode _newNode;
public SingleNodeReplacer(SyntaxNode oldNode, SyntaxNode newNode)
{
_oldNode = oldNode;
_newNode = newNode;
}
public override SyntaxNode? Visit(SyntaxNode? node)
=> ReferenceEquals(node, _oldNode) ? _newNode : base.Visit(node);
}
/// <summary>The call statement(s) replacing the selection (see class comment).</summary>
private static IReadOnlyList<StatementSyntax> BuildCallStatements(
IReadOnlyList<ReturnSuggestion> slots,
IReadOnlyList<string> slotNames,
InvocationExpressionSyntax invocation,
ISet<string> declaredInside,
bool callMustReturn)
{
if (callMustReturn)
{
// The selection ends the enclosing (non-void) method: the call is
// the return value, the slots live in the new method.
return [Norm(SyntaxFactory.ReturnStatement(invocation))];
}
if (slots.Count == 0)
{
return [Norm(SyntaxFactory.ExpressionStatement(invocation))];
}
if (slots.Count == 1)
{
var slot = slots[0];
if (declaredInside.Contains(slot.Name))
{
// Declared inside the selection: redeclare it at the call site
// from the result (the declaration statement moved with the body).
var declarator = SyntaxFactory.VariableDeclarator(slot.Name)
.WithInitializer(SyntaxFactory.EqualsValueClause(invocation));
var declaration = SyntaxFactory.VariableDeclaration(
ParseType(slot.Type), SyntaxFactory.SingletonSeparatedList(declarator));
return [Norm(SyntaxFactory.LocalDeclarationStatement(declaration))];
}
// Declared outside: the caller already owns it (a parameter, or a
// local declared before the selection) — plain assignment.
return [Norm(SyntaxFactory.ExpressionStatement(SyntaxFactory.AssignmentExpression(
SyntaxKind.SimpleAssignmentExpression,
SyntaxFactory.IdentifierName(slot.Name),
invocation)))];
}
// Several return slots.
if (slots.All(s => declaredInside.Contains(s.Name)))
{
// All declared inside: tuple deconstruction at the call site.
// Parsed from a skeleton (see class comment — builder style), the
// call swapped in at the placeholder identifier. NOT normalized:
// the skeleton text is already well-spaced, and NormalizeWhitespace
// would drop the space after the contextual keyword `var` (it is
// an identifier token to the normalizer, so `var (` becomes
// `var(`).
return [ParseStatementWithCall($"var ({string.Join(", ", slotNames)}) = __call__;", invocation)];
}
// Mixed: evaluate the call ONCE into a capture, then assign each slot
// from the matching ItemN. (Capture name collision with an enclosing
// local is a documented v1 limitation.)
var statements = new List<StatementSyntax>
{
Norm(SyntaxFactory.LocalDeclarationStatement(SyntaxFactory.VariableDeclaration(
SyntaxFactory.PredefinedType(SyntaxFactory.Token(SyntaxKind.VarKeyword)),
SyntaxFactory.SingletonSeparatedList(SyntaxFactory.VariableDeclarator("result")
.WithInitializer(SyntaxFactory.EqualsValueClause(invocation)))))),
};
for (var index = 0; index < slots.Count; index++)
{
statements.Add(Norm(SyntaxFactory.ExpressionStatement(SyntaxFactory.AssignmentExpression(
SyntaxKind.SimpleAssignmentExpression,
SyntaxFactory.IdentifierName(slots[index].Name),
SyntaxFactory.MemberAccessExpression(SyntaxKind.SimpleMemberAccessExpression,
SyntaxFactory.IdentifierName("result"),
SyntaxFactory.IdentifierName($"Item{index + 1}"))))));
}
return statements;
}
/// <summary>
/// Normalizes a builder-made statement: SyntaxFactory tokens carry no
/// trivia, so without this <c>return</c> and <c>Extract</c> would render
/// glued together. Only used for BUILDER statements — the parsed skeleton
/// statements are already well-spaced (see the deconstruction comment).
/// </summary>
private static StatementSyntax Norm(StatementSyntax statement) => statement.NormalizeWhitespace();
/// <summary>
/// Parses <paramref name="statementText"/> (containing the placeholder
/// identifier <c>__call__</c>) and swaps the placeholder for the built
/// <paramref name="invocation"/> — the parser supplies the syntax shapes
/// (tuple designations, tuple elements) the v1 builder avoids.
/// </summary>
private static StatementSyntax ParseStatementWithCall(string statementText, InvocationExpressionSyntax invocation)
{
var parsed = SyntaxFactory.ParseStatement(statementText);
var placeholder = parsed.DescendantNodes()
.OfType<IdentifierNameSyntax>()
.First(n => n.Identifier.ValueText == "__call__");
return parsed.ReplaceNode(placeholder, invocation);
}
/// <summary>
/// The extracted method: the promoted signature, static-ness mirrored from
/// the enclosing method, body = the selected statements plus an appended
/// <c>return</c> for the return slots (skipped when the selection already
/// ends in a return — a second one would be unreachable). The appended
/// tuple return is parsed from its text skeleton (see class comment).
/// </summary>
private static MethodDeclarationSyntax BuildNewMethod(
MethodDeclarationSyntax enclosingMethod,
SelectionReport selection,
SignatureSuggestion signature,
IReadOnlyList<ReturnSuggestion> slots,
IReadOnlyList<string> slotNames)
{
// A static enclosing method can only read statics and parameters, so
// the extracted body needs no instance — mirror the static modifier.
var modifiers = enclosingMethod.Modifiers.Any(m => m.IsKind(SyntaxKind.StaticKeyword))
? new[] { SyntaxFactory.Token(SyntaxKind.StaticKeyword) }
: Array.Empty<SyntaxToken>();
var parameters = signature.Params
.Select(p =>
{
var parameter = SyntaxFactory.Parameter(SyntaxFactory.Identifier(p.Name))
.WithType(ParseType(p.Type));
return p.ByRef
? parameter.WithModifiers(SyntaxFactory.TokenList(
SyntaxFactory.Token(SyntaxKind.RefKeyword)))
: parameter;
})
.ToList();
var bodyStatements = selection.Statements.ToList();
if (slots.Count > 0 && selection.Statements[^1] is not ReturnStatementSyntax)
{
// The slot order here is the same name-ordered sequence the tuple
// ReturnType was built from, so the emitted value matches the
// declared element types.
bodyStatements.Add(slots.Count == 1
? SyntaxFactory.ReturnStatement(SyntaxFactory.IdentifierName(slotNames[0]))
: SyntaxFactory.ParseStatement($"return ({string.Join(", ", slotNames)});"));
}
return SyntaxFactory.MethodDeclaration(ParseType(signature.ReturnType), SyntaxFactory.Identifier(signature.MethodName))
.WithModifiers(SyntaxFactory.TokenList(modifiers))
.WithParameterList(SyntaxFactory.ParameterList(SyntaxFactory.SeparatedList(parameters)))
.WithBody(SyntaxFactory.Block(SyntaxFactory.List(bodyStatements)));
}
/// <summary>
/// Re-parses a type display string (em 02/03 are plain strings) in type
/// context — <c>ParseTypeName</c> handles plain names, generics and tuple
/// display strings <c>(T1, T2)</c> alike.
///
/// EXCEPT <c>void</c>: parsing "void" in TYPE context yields a node the
/// compiler rejects as a method return type with CS1547 (keyword 'void'
/// cannot be used in this context) — the parser that reads real method
/// declarations produces <c>PredefinedType(Token(VoidKeyword))</c>, so
/// that is what a void signature must be built from.
/// Single choke point for the string-to-syntax hop; its correctness is
/// enforced by the round-trip check and the tests, not by construction.
/// </summary>
private static TypeSyntax ParseType(string text) => text == "void"
? SyntaxFactory.PredefinedType(SyntaxFactory.Token(SyntaxKind.VoidKeyword))
: SyntaxFactory.ParseTypeName(text);
}
@@ -10,10 +10,16 @@ namespace ExtractMethod.Tooling;
/// <param name="MethodName">v1 always suggests <c>Extract</c>.</param>
/// <param name="Params">The coherent parameter list (ref-ness preserved from
/// the classification).</param>
/// <param name="ReturnSlots">The individual return slot candidates (name +
/// type), name-ordered — the same order the tuple <see cref="ReturnType"/>
/// was built from, and the order em 04's codegen emits them in the appended
/// <c>return (...)</c> statement and the call-side declaration. Empty for a
/// void extraction.</param>
public sealed record SignatureSuggestion(
string ReturnType,
string MethodName,
IReadOnlyList<ParamSuggestion> Params);
IReadOnlyList<ParamSuggestion> Params,
IReadOnlyList<ReturnSuggestion> ReturnSlots);
/// <summary>
/// Turns the raw em 02 buckets into ONE coherent signature line. The buckets
@@ -66,7 +72,7 @@ public static class SignatureBuilder
_ => $"({string.Join(", ", returnSlots.Select(r => r.Type))})",
};
return new SignatureSuggestion(returnType, "Extract", parameters);
return new SignatureSuggestion(returnType, "Extract", parameters, returnSlots);
}
/// <summary>
+187
View File
@@ -0,0 +1,187 @@
using System.Text;
namespace ExtractMethod.Tooling;
/// <summary>
/// Line-based unified diff (v1, hand-rolled, no dependencies): an LCS over
/// lines is backtracked into equal/delete/insert runs, and the runs are
/// printed as unified hunks with 3 lines of context (hunks closer than
/// 2×context lines apart merge). The shape is the familiar
/// <c>---/+++/@@</c> one — enough for a human to review the generated
/// refactoring; no patch-file semantics are promised.
/// </summary>
public static class UnifiedDiff
{
private const int Context = 3;
public static string Diff(string original, string modified, string originalLabel, string modifiedLabel)
{
var a = SplitLines(original);
var b = SplitLines(modified);
var sb = new StringBuilder($"--- {originalLabel}\n+++ {modifiedLabel}\n");
foreach (var hunk in BuildHunks(a, b))
{
sb.Append(hunk);
}
return sb.ToString();
}
/// <summary>
/// Split on newlines, dropping a trailing carriage return (CRLF tolerance).
/// A trailing newline does NOT start a new line: "a\n" is ONE line, so the
/// phantom empty element a naive Split('\n') leaves at the end is dropped
/// (it would inflate every hunk header by one). The empty string is zero
/// lines.
/// </summary>
private static string[] SplitLines(string text)
{
if (text.Length == 0)
{
return [];
}
var lines = text.Split('\n').Select(line => line.TrimEnd('\r')).ToArray();
return lines[^1].Length == 0 ? lines[..^1] : lines;
}
private enum Op { Equal, Del, Ins }
/// <summary>
/// LCS + backtracking + hunk assembly. <c>lcs[i, j]</c> is the length of
/// the longest common suffix of <c>a[i..]</c> and <c>b[j..]</c>.
/// </summary>
private static IReadOnlyList<string> BuildHunks(string[] a, string[] b)
{
var n = a.Length;
var m = b.Length;
var lcs = new int[n + 1, m + 1];
for (var row = n - 1; row >= 0; row--)
{
for (var col = m - 1; col >= 0; col--)
{
lcs[row, col] = a[row] == b[col]
? lcs[row + 1, col + 1] + 1
: Math.Max(lcs[row + 1, col], lcs[row, col + 1]);
}
}
// Backtrack: equal lines advance both; on a mismatch prefer a deletion
// (ties go to delete, which keeps the printed block old-then-new).
var ops = new List<(Op Tag, int A, int B)>();
var i = 0;
var j = 0;
while (i < n && j < m)
{
if (a[i] == b[j])
{
ops.Add((Op.Equal, i, j));
i++;
j++;
}
else if (lcs[i + 1, j] >= lcs[i, j + 1])
{
ops.Add((Op.Del, i, j));
i++;
}
else
{
ops.Add((Op.Ins, i, j));
j++;
}
}
while (i < n)
{
ops.Add((Op.Del, i, j));
i++;
}
while (j < m)
{
ops.Add((Op.Ins, i, j));
j++;
}
// A "region" is a maximal run of non-equal ops: [AStart, AEnd) ×
// [BStart, BEnd) in the two line arrays.
var regions = new List<(int AStart, int AEnd, int BStart, int BEnd)>();
var index = 0;
while (index < ops.Count)
{
if (ops[index].Tag == Op.Equal)
{
index++;
continue;
}
var first = ops[index];
var regionAStart = first.Tag == Op.Del ? first.A : (index > 0 ? ops[index - 1].A + 1 : 0);
var regionBStart = first.B;
while (index < ops.Count && ops[index].Tag != Op.Equal)
{
index++;
}
var last = ops[index - 1];
regions.Add((regionAStart,
last.Tag == Op.Del ? last.A + 1 : last.A,
regionBStart,
last.Tag == Op.Ins ? last.B + 1 : last.B));
}
// Extend every region by Context lines (clamped), then merge regions
// whose extended ranges overlap.
var hunks = new List<(int AStart, int AEnd, int BStart, int BEnd)>();
foreach (var (aStart, aEnd, bStart, bEnd) in regions)
{
var (haStart, haEnd) = (Math.Max(0, aStart - Context), Math.Min(n, aEnd + Context));
var (hbStart, hbEnd) = (Math.Max(0, bStart - Context), Math.Min(m, bEnd + Context));
if (hunks.Count > 0)
{
var prev = hunks[^1];
if (haStart <= prev.AEnd && hbStart <= prev.BEnd)
{
hunks[^1] = (prev.AStart, Math.Max(prev.AEnd, haEnd), prev.BStart, Math.Max(prev.BEnd, hbEnd));
continue;
}
}
hunks.Add((haStart, haEnd, hbStart, hbEnd));
}
return hunks.Select(hunk => RenderHunk(ops, a, b, hunk.AStart, hunk.AEnd, hunk.BStart, hunk.BEnd)).ToList();
}
private static string RenderHunk(
IReadOnlyList<(Op Tag, int A, int B)> ops,
string[] a,
string[] b,
int aStart,
int aEnd,
int bStart,
int bEnd)
{
var sb = new StringBuilder();
sb.AppendLine($"@@ -{aStart + 1},{aEnd - aStart} +{bStart + 1},{bEnd - bStart} @@");
foreach (var (tag, aIndex, bIndex) in ops)
{
switch (tag)
{
case Op.Equal when aStart <= aIndex && aIndex < aEnd:
sb.Append(' ').AppendLine(a[aIndex]);
break;
case Op.Del when aStart <= aIndex && aIndex < aEnd:
sb.Append('-').AppendLine(a[aIndex]);
break;
case Op.Ins when bStart <= bIndex && bIndex < bEnd:
sb.Append('+').AppendLine(b[bIndex]);
break;
}
}
return sb.ToString();
}
}