hyperguild/ingestion/internal/extract/callsites_test.go

package extract

import (
	"go/ast"
	"go/parser"
	"go/token"
	"os"
	"path/filepath"
	"strconv"
	"strings"
	"testing"
)

const extractPkg = "github.com/mathiasbq/hyperguild/ingestion/internal/extract"

// parseNonTest parses every non-test Go file under the module.
func parseNonTest(t *testing.T) map[string]*ast.File {
	t.Helper()
	fset := token.NewFileSet()
	out := map[string]*ast.File{}
	err := filepath.WalkDir(filepath.Join("..", ".."), func(p string, d os.DirEntry, err error) error {
		if err != nil {
			return err
		}
		if d.IsDir() && (d.Name() == "vendor" || d.Name() == ".git") {
			return filepath.SkipDir
		}
		if d.IsDir() || !strings.HasSuffix(p, ".go") || strings.HasSuffix(p, "_test.go") {
			return nil
		}
		f, perr := parser.ParseFile(fset, p, nil, 0)
		if perr != nil {
			return perr
		}
		out[filepath.ToSlash(p)] = f
		return nil
	})
	if err != nil {
		t.Fatal(err)
	}
	return out
}

// PR #156 review: reading a caller-chosen path by name reopens it after the
// containment check (hyperguild#153 item 3). Outside this package, nothing
// may reference extract.Text — called OR taken as a value — under whatever
// name the package is imported (round 2: an alias and a func value slipped
// past a plain text search).
func TestNoPackageReferencesExtractTextOutsideExtract(t *testing.T) {
	for path, f := range parseNonTest(t) {
		if strings.Contains(path, "internal/extract/") {
			continue
		}
		names := map[string]bool{}
		for _, imp := range f.Imports {
			if p, _ := strconv.Unquote(imp.Path.Value); p == extractPkg {
				name := "extract"
				if imp.Name != nil {
					name = imp.Name.Name
				}
				if name == "." {
					t.Errorf("%s dot-imports extract; import it by name so its use stays checkable", path)
				}
				names[name] = true
			}
		}
		if len(names) == 0 {
			continue
		}
		ast.Inspect(f, func(n ast.Node) bool {
			if sel, ok := n.(*ast.SelectorExpr); ok {
				if id, ok := sel.X.(*ast.Ident); ok && names[id.Name] && sel.Sel.Name == "Text" {
					t.Errorf("%s references %s.Text; use extract.TextIn through an os.Root", path, id.Name)
				}
			}
			return true
		})
	}
}

// PR #156 review round 2: the FIFO fix (open non-blocking, check the handle)
// lives in OpenRegular, and reverting any caller to a plain Root.Open stayed
// green. In the three raw/ reader FILES parsed below (and only those: a
// wrapper in another file is not seen), no Open/OpenFile/ReadFile selector
// may appear outside OpenRegular, called or taken as a method value. This is
// a second layer; the behavioural race tests in internal/api and
// internal/watcher are what catch a rewrite through any API (round 3).
// osOpenAllowed names the functions in guarded files that may call os.Open*
// on a path that is not a raw/ read.
var osOpenAllowed = map[string]bool{
	"internal/watcher/watcher.go:appendWatcherLog": true, // ingest log append, not a raw/ read
	// Text reads by path; outside this package only TextIn's temp copy reaches
	// it (TestNoPackageReferencesExtractTextOutsideExtract enforces that).
	"internal/extract/extract.go:Text": true,
}

func TestRawReaderFilesUseNoOpenOrReadFileOutsideOpenRegular(t *testing.T) {
	guarded := []string{"internal/api/rawroot.go", "internal/extract/extract.go", "internal/watcher/watcher.go"}
	files := parseNonTest(t)
	for _, g := range guarded {
		var f *ast.File
		for p, af := range files {
			if strings.HasSuffix(p, g) {
				f = af
			}
		}
		if f == nil {
			t.Fatalf("guarded file %s not found", g)
		}
		for _, decl := range f.Decls {
			fn, ok := decl.(*ast.FuncDecl)
			if !ok || fn.Name.Name == "OpenRegular" {
				continue
			}
			ast.Inspect(fn, func(n ast.Node) bool {
				sel, ok := n.(*ast.SelectorExpr)
				if !ok {
					return true
				}
				if sel.Sel.Name == "Open" || sel.Sel.Name == "OpenFile" || sel.Sel.Name == "ReadFile" {
					if id, ok := sel.X.(*ast.Ident); ok && id.Name == "os" && osOpenAllowed[g+":"+fn.Name.Name] {
						return true // a named non-raw write (the ingest log append)
					}
					t.Errorf("%s: %s calls .%s; raw/ reads must go through OpenRegular", g, fn.Name.Name, sel.Sel.Name)
				}
				return true
			})
		}
	}
}