MergeInto names the changed files that are compiled programs, read in the workspace, so a check can refuse build output (issue 1577)

go/buildstep/programs.go

@@ -0,0 +1,72 @@
+package buildstep
+
+import (
+	"bytes"
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+)
+
+// Program is a changed file whose first bytes are an executable binary: a compiled program, which is build output and not
+// source (novox/hq issue 1577: `go build` in a module's folder writes one beside go.mod, and `git add -A` takes it).
+type Program struct {
+	Path string `json:"path"`
+	Kind string `json:"kind"` // ELF, Mach-O or PE
+}
+
+// ExecutableKind says what executable format the first bytes of a file are, or "" when they are none. A PE needs its header
+// ("PE\0\0" at the offset in bytes 0x3c) so a text starting with "MZ" is not one; a fat Mach-O (0xCAFEBABE) is told from a
+// Java class by its architecture count (bytes 4 to 7, fewer than 0x20; a class has its version there).
+func ExecutableKind(head []byte) string {
+	switch {
+	case bytes.HasPrefix(head, []byte("\x7fELF")):
+		return "ELF"
+	case bytes.HasPrefix(head, []byte("MZ")):
+		if len(head) >= 0x40 {
+			off := int(head[0x3c]) | int(head[0x3d])<<8 | int(head[0x3e])<<16 | int(head[0x3f])<<24
+			if off >= 0 && off+4 <= len(head) && bytes.Equal(head[off:off+4], []byte("PE\x00\x00")) {
+				return "PE"
+			}
+		}
+	case bytes.HasPrefix(head, []byte{0xcf, 0xfa, 0xed, 0xfe}), bytes.HasPrefix(head, []byte{0xce, 0xfa, 0xed, 0xfe}),
+		bytes.HasPrefix(head, []byte{0xfe, 0xed, 0xfa, 0xcf}), bytes.HasPrefix(head, []byte{0xfe, 0xed, 0xfa, 0xce}),
+		bytes.HasPrefix(head, []byte{0xca, 0xfe, 0xba, 0xbe}) && len(head) >= 8 && head[4] == 0 && head[5] == 0 && head[6] == 0 && head[7] < 0x20:
+		return "Mach-O"
+	}
+	return ""
+}
+
+// programHeadSize is how many bytes of a file are read to tell its format: enough for a PE header at its usual offsets.
+const programHeadSize = 0x100
+
+// programsIn reads the output of `git diff --raw -z --no-renames --diff-filter=AM` (":<old mode> <new mode> <old sha> <new
+// sha> <status>\0<path>\0" per file) and names each added or modified regular file of the tree dir that is a compiled
+// program, from its first bytes read locally. A symlink (mode 120000) and a submodule (160000) are not read. It never
+// answers nil, so a caller can tell no programs from none reported.
+func programsIn(dir, raw string) []Program {
+	out := []Program{}
+	f := strings.Split(raw, "\x00")
+	for i := 0; i+1 < len(f); i += 2 {
+		meta := strings.Fields(strings.TrimPrefix(f[i], ":"))
+		if len(meta) < 2 || (meta[1] != "100644" && meta[1] != "100755") {
+			continue
+		}
+		p := f[i+1]
+		full := filepath.Join(dir, filepath.FromSlash(p))
+		if st, err := os.Lstat(full); err != nil || !st.Mode().IsRegular() {
+			continue
+		}
+		fh, err := os.Open(full)
+		if err != nil {
+			continue
+		}
+		head := make([]byte, programHeadSize)
+		n, _ := io.ReadFull(fh, head)
+		fh.Close()
+		if k := ExecutableKind(head[:n]); k != "" {
+			out = append(out, Program{Path: p, Kind: k})
+		}
+	}
+	return out
+}