Teach prim_file:set_cwd() to avoid entering non-translatable directories

We have decided that we don't want to deal with the compilations
of prim_file:get_cwd() returning a binary when the current
directory name cannot be translated losslessly to a list (i.e.
when the run-time system was started with +fnu and the current directory
name contains bytes that are not part of a valid UTF-8 sequence).

Therefore, if prim_file:set_cwd() is given a binary as the pathname,
we will need to check the binary to make sure it can be translated
to a list. We will introduce a new BIF, called prim_file:is_translatable/1,
which will check both filename encoding mode, and if it is one of
Unicode modes, the binary as well.

We don't need to do anything special if prim_file:set_cwd() is passed
a list.

2 files changed, 47 insertions, 0 deletions

diff --git a/erts/emulator/beam/bif.tab b/erts/emulator/beam/bif.tab
index 4aaf466008..e313188901 100644
--- a/erts/emulator/beam/bif.tab
+++ b/erts/emulator/beam/bif.tab
@@ -522,6 +522,7 @@ bif erlang:nif_error/2
 bif prim_file:internal_name2native/1
 bif prim_file:internal_native2name/1
 bif prim_file:internal_normalize_utf8/1
+bif prim_file:is_translatable/1
 bif file:native_name_encoding/0
 
 #
diff --git a/erts/emulator/beam/erl_unicode.c b/erts/emulator/beam/erl_unicode.c
index 8d7930e5fa..80982f3760 100644
--- a/erts/emulator/beam/erl_unicode.c
+++ b/erts/emulator/beam/erl_unicode.c
@@ -2657,6 +2657,52 @@ BIF_RETTYPE prim_file_internal_normalize_utf8_1(BIF_ALIST_1)
     BIF_RET(ret);
 }  
 
+BIF_RETTYPE prim_file_is_translatable_1(BIF_ALIST_1)
+{
+    ERTS_DECLARE_DUMMY(Eterm real_bin);
+    ERTS_DECLARE_DUMMY(Uint offset);
+    Uint size;
+    Uint num_chars;
+    Uint bitsize;
+    ERTS_DECLARE_DUMMY(Uint bitoffs);
+    byte *temp_alloc = NULL;
+    byte *bytes;
+    byte *err_pos;
+    int status;
+
+    if (is_not_binary(BIF_ARG_1)) {
+	BIF_ERROR(BIF_P,BADARG);
+    }
+    size = binary_size(BIF_ARG_1);
+    ERTS_GET_REAL_BIN(BIF_ARG_1, real_bin, offset, bitoffs, bitsize);
+    if (bitsize != 0) {
+	BIF_ERROR(BIF_P,BADARG);
+    }
+    if (size == 0) {
+	BIF_RET(am_true);
+    }
+
+    /*
+     * If the encoding is latin1, the pathname is always translatable.
+     */
+    switch (erts_get_native_filename_encoding()) {
+    case ERL_FILENAME_LATIN1:
+	BIF_RET(am_true);
+    case ERL_FILENAME_WIN_WCHAR:
+	if (erts_get_user_requested_filename_encoding() == ERL_FILENAME_LATIN1) {
+	    BIF_RET(am_true);
+	}
+    }
+
+    /*
+     * Check whether the binary contains legal UTF-8 sequences.
+     */
+    bytes = erts_get_aligned_binary_bytes(BIF_ARG_1, &temp_alloc);
+    status = erts_analyze_utf8(bytes, size, &err_pos, &num_chars, NULL);
+    erts_free_aligned_binary_bytes(temp_alloc);
+    BIF_RET(status == ERTS_UTF8_OK ? am_true : am_false);
+}  
+
 BIF_RETTYPE file_native_name_encoding_0(BIF_ALIST_0)
 {
     switch (erts_get_native_filename_encoding()) {