From d4dbf03884769b61c8faa89c494575b7d1919893 Mon Sep 17 00:00:00 2001
From: "Jose R. Gonzalez" <komish@flutes.dev>
Date: Wed, 26 Jun 2024 15:54:37 -0500
Subject: [PATCH] Ensure files and links have missing parent dirs created.
 Support hard links

Signed-off-by: Jose R. Gonzalez <komish@flutes.dev>
---
 internal/engine/engine.go      | 66 ++++++++++++++++++++++++++++++++--
 internal/engine/engine_test.go | 15 ++++++++
 2 files changed, 79 insertions(+), 2 deletions(-)

diff --git a/internal/engine/engine.go b/internal/engine/engine.go
index 546302cb..7cbd6f97 100644
--- a/internal/engine/engine.go
+++ b/internal/engine/engine.go
@@ -412,6 +412,13 @@ func untar(ctx context.Context, dst string, r io.Reader) error {
 
 		// if it's a file create it
 		case tar.TypeReg:
+			// If the file's parent dir doesn't exist, create it.
+			dirname := filepath.Dir(target)
+			if _, err := os.Stat(dirname); err != nil {
+				if err := os.MkdirAll(dirname, 0o755); err != nil {
+					return err
+				}
+			}
 			f, err := os.OpenFile(target, os.O_CREATE|os.O_RDWR, os.FileMode(header.Mode))
 			if err != nil {
 				return err
@@ -429,15 +436,70 @@ func untar(ctx context.Context, dst string, r io.Reader) error {
 
 			// if it's a link create it
 		case tar.TypeSymlink:
-			err := os.Symlink(header.Linkname, filepath.Join(dst, header.Name))
+			nobaseLinkname, nobaseName := resolveLinkPaths(header.Linkname, header.Name)
+			fullLinkname := filepath.Join(dst, nobaseLinkname)
+			fullName := filepath.Join(dst, nobaseName)
+			// Safeguard for cases where we're trying to link to something
+			// outside of our base fs.
+			if !strings.HasPrefix(fullLinkname, dst) {
+				logger.V(log.DBG).Info("Error processing symlink. Symlink would reach outside of the image archive. Skipping this link", "link", header.Name, "linkedTo", header.Linkname, "resolvedTo", fullLinkname)
+				continue
+			}
+			// Create the new link's directory if it doesn't exist.
+			dirname := filepath.Dir(fullName)
+			if _, err := os.Stat(dirname); err != nil {
+				if err := os.MkdirAll(dirname, 0o755); err != nil {
+					return err
+				}
+			}
+			err := os.Symlink(fullLinkname, fullName)
+			if err != nil {
+				logger.V(log.DBG).Info(fmt.Sprintf("Error creating symlink: %s. Ignoring.", header.Name), "link", fullName, "linkedTo", fullLinkname, "reason", err)
+				continue
+			}
+		case tar.TypeLink:
+			// We assume hard links will not contain relative pathing in the archive.
+			original := filepath.Join(dst, header.Linkname)
+			// Create the new link's directory if it doesn't exist.
+			if !strings.HasPrefix(original, dst) {
+				logger.V(log.DBG).Info("Error processing symlink. Symlink would reach outside of the image archive. Skipping this link", "link", header.Name, "linkedTo", header.Linkname, "resolvedTo", original)
+				continue
+			}
+			dirname := filepath.Dir(target)
+			if _, err := os.Stat(dirname); err != nil {
+				if err := os.MkdirAll(dirname, 0o755); err != nil {
+					return err
+				}
+			}
+			err := os.Link(original, target)
 			if err != nil {
-				logger.V(log.DBG).Info(fmt.Sprintf("Error creating link: %s. Ignoring.", header.Name))
+				logger.V(log.DBG).Info(fmt.Sprintf("Error creating hard link: %s. Ignoring.", header.Name), "link", target, "linkedTo", original, "reason", err)
 				continue
 			}
 		}
 	}
 }
 
+// resolveLinkPaths determines if oldname is an absolute path or a relative
+// path, and returns oldname relative to newname if necessary.
+func resolveLinkPaths(oldname, newname string) (string, string) {
+	if filepath.IsAbs(oldname) {
+		return oldname, newname
+	}
+
+	linkDir := filepath.Dir(newname)
+	// If the newname is at the root of the filesystem, but the oldname is
+	// relative, we'll swap out the value we get from filepath.Dir for a / to
+	// allow relative pathing to resolve. This strips `..` references given the
+	// link exists at the very base of the filesystem. In effect, it converts
+	// oldname to an absolute path
+	if linkDir == "." {
+		linkDir = "/"
+	}
+
+	return filepath.Join(linkDir, oldname), newname
+}
+
 // writeCertImage takes imageRef and writes it to disk as JSON representing a pyxis.CertImage
 // struct. The file is written at path certification.DefaultCertImageFilename.
 //
diff --git a/internal/engine/engine_test.go b/internal/engine/engine_test.go
index 5f2ea471..834b0ccb 100644
--- a/internal/engine/engine_test.go
+++ b/internal/engine/engine_test.go
@@ -379,6 +379,21 @@ var _ = Describe("Check Name Queries", func() {
 	})
 })
 
+var _ = Describe("Link Path Resolution", func() {
+	DescribeTable(
+		"Link targets should resolve correctly",
+		func(old, new, expectedOld, expectedNew string) {
+			resO, resN := resolveLinkPaths(old, new)
+			Expect(resO).To(Equal(expectedOld))
+			Expect(resN).To(Equal(expectedNew))
+		},
+		Entry("Link at root with relative origin", "../usr/lib/file", "file", "/usr/lib/file", "file"),
+		Entry("Origin is absolute", "/usr/lib/file", "file", "/usr/lib/file", "file"),
+		Entry("Link in dir with relative origin", "../usr/lib/file", "etc/file", "usr/lib/file", "etc/file"),
+		Entry("Link in dir with relative origin and up multiple levels", "../../cfg/file", "etc/foo/file", "cfg/file", "etc/foo/file"),
+	)
+})
+
 // writeTarball writes a tar archive to out with filename containing contents at the base path
 // with extra bytes written at the end of length extraBytes.
 // note: this should only be used as a helper function in tests