Commit 7d3a31872eda55438259b54818baaa90b6ecd74c | zig

author	Igor Anić <igor.anic@gmail.com> 2023-12-18 21:39:07+01:00
committer	Andrew Kelley <andrew@ziglang.org> 2024-01-13 19:37:33-07:00
log	7d3a31872eda55438259b54818baaa90b6ecd74c
tree	0f37119cde4ccd495925d05ca70a7b939c252f16
parent	7923a53996f8d24ad27823db3a45a6dd4a2bf317

tar: improve diagnostic reporting

Using Python testtar file (mentioned in #14310) to test diagnostic
reporting.
Added computing checksum by using both unsigned and signed header bytes
values.
Added skipping gnu exteneded sparse headers while reporting unsupported
header in diagnostic.

Note on testing:

wget https://github.com/python/cpython/raw/3.11/Lib/test/testtar.tar -O
/tmp/testtar.tar

```
test "Python testtar.tar file" {
    const file_name = "testtar.tar";

    var file = try std.fs.cwd().openFile("/tmp/" ++ file_name, .{});
    defer file.close();

    var diag = Options.Diagnostics{ .allocator = std.testing.allocator };
    defer diag.deinit();

    var iter = iterator(file.reader(), &diag);
    while (try iter.next()) |f| {
        std.debug.print("supported: {} {s} {d}\n", .{ f.kind, f.name, f.size });
        try f.skip();
    }
    for (diag.errors.items) |e| {
        switch (e) {
            .unsupported_file_type => |u| {
                std.debug.print("unsupported: {} {s}\n", .{ u.file_type, u.file_name });
            },
            else => unreachable,
        }
    }
}
```

1 files changed, 31 insertions(+), 9 deletions(-)

lib
- std
  - tar.zig

lib/std/tar.zig+31-9

 @@ -105,6 +105,8 @@ pub const Header = struct {
         // used to store the path or link name for the next file.
         gnu_long_name = 'L',
         gnu_long_link = 'K',
+        gnu_sparse = 'S',
+        solaris_extended_header = 'X',
         _,
     };
 @@ -194,16 +196,21 @@ pub const Header = struct {
         return std.fmt.parseInt(u64, rtrimmed, 8) catch return error.TarHeader;
     }
+    const Chksums = struct {
+        unsigned: u64,
+        signed: i64,
+    };
     // Sum of all bytes in the header block. The chksum field is treated as if
     // it were filled with spaces (ASCII 32).
-    fn computeChksum(header: Header) u64 {
+    fn computeChksum(header: Header) Chksums {
-        var sum: u64 = 0;
+        var cs: Chksums = .{ .signed = 0, .unsigned = 0 };
-        for (header.bytes, 0..) |b, i| {
+        for (header.bytes, 0..) |v, i| {
-            if (148 <= i and i < 156) continue; // skip chksum field bytes
+            const b = if (148 <= i and i < 156) 32 else v; // Treating chksum bytes as spaces.
-            sum += b;
+            cs.unsigned += b;
+            cs.signed += @as(i8, @bitCast(b));
         }
-        // Treating chksum bytes as spaces. 256 = 8 * 32, 8 spaces.
+        return cs;
-        return if (sum > 0) sum + 256 else 0;
     }
     // Checks calculated chksum with value of chksum field.
 @@ -211,8 +218,9 @@ pub const Header = struct {
     // Zero value indicates empty block.
     pub fn checkChksum(header: Header) !u64 {
         const field = try header.chksum();
-        const computed = header.computeChksum();
+        const cs = header.computeChksum();
-        if (field != computed) return error.TarHeaderChksum;
+        if (field == 0 and cs.unsigned == 256) return 0;
+        if (field != cs.unsigned and field != cs.signed) return error.TarHeaderChksum;
         return field;
     }
 };
 @@ -387,11 +395,25 @@ fn Iterator(comptime ReaderType: type) type {
                             .file_name = try d.allocator.dupe(u8, header.name()),
                             .file_type = kind,
                         } });
+                        if (kind == .gnu_sparse) {
+                            try self.skipGnuSparseExtendedHeaders(header);
+                        }
+                        self.reader.skipBytes(size, .{}) catch return error.TarHeadersTooBig;
                     },
                 }
             }
             return null;
         }
+        fn skipGnuSparseExtendedHeaders(self: *Self, header: Header) !void {
+            var is_extended = header.bytes[482] > 0;
+            while (is_extended) {
+                var buf: [Header.SIZE]u8 = undefined;
+                const n = try self.reader.readAll(&buf);
+                if (n < Header.SIZE) return error.UnexpectedEndOfStream;
+                is_extended = buf[504] > 0;
+            }
+        }
     };
 }