Pádraig Brady wrote:
I've also attached an alternative patch for df (in your name).
That still has problems, since it can generate improperly-encoded strings in
UTF-8 locales (if the inputs are improperly encoded), and can replace parts of
multibyte characters with '?' in non-UTF-8 locales. Please try the attached
patch instead, which attempts to address these issues. This is more along the
lines that Bruno suggested, except it doesn't use mbsiter as I figured it was
simpler overall just to use mbrtowc directly for this one thing.
From 17a1a37549344cdfd95cc84b1848dafa256be5a0 Mon Sep 17 00:00:00 2001
From: Paul Eggert <egg...@cs.ucla.edu>
Date: Sun, 22 Jul 2018 08:09:01 -0700
Subject: [PATCH] df: avoid multibyte character corruption on macOS
Problem reported by Chih-Hsuan Yen (Bug#32236).
* NEWS: Mention the bug fix.
* src/df.c: Include wchar.h and wctype.h instead of mbswidth.h.
(hide_problematic_chars): Return number of screen columns.
All callers changed. Use iswcntrl, not iscntrl.
(get_header, get_dev): Rely on hide_problematic_chars width,
not mbswidth. Scan the cell once, instead of two or three times.
---
NEWS | 4 ++++
src/df.c | 46 +++++++++++++++++++++++++++++++---------------
2 files changed, 35 insertions(+), 15 deletions(-)
diff --git a/NEWS b/NEWS
index af1a990..aa3b4f9 100644
--- a/NEWS
+++ b/NEWS
@@ -2,6 +2,10 @@ GNU coreutils NEWS -*- outline -*-
* Noteworthy changes in release ?.? (????-??-??) [?]
+** Bug fixes
+
+ df no longer corrupts displayed multibyte characters on macOS.
+
* Noteworthy changes in release 8.30 (2018-07-01) [stable]
diff --git a/src/df.c b/src/df.c
index 1178865..664b88b 100644
--- a/src/df.c
+++ b/src/df.c
@@ -23,6 +23,8 @@
#include <sys/types.h>
#include <getopt.h>
#include <assert.h>
+#include <wchar.h>
+#include <wctype.h>
#include "system.h"
#include "canonicalize.h"
@@ -31,7 +33,6 @@
#include "fsusage.h"
#include "human.h"
#include "mbsalign.h"
-#include "mbswidth.h"
#include "mountlist.h"
#include "quote.h"
#include "find-mount-point.h"
@@ -272,20 +273,36 @@ static struct option const long_options[] =
};
/* Replace problematic chars with '?'.
- Since only control characters are currently considered,
- this should work in all encodings. */
+ Return the number of screen columns. */
-static char*
+static size_t
hide_problematic_chars (char *cell)
{
- char *p = cell;
- while (*p)
+ char *srcend = cell + strlen (cell);
+ char *dst = cell;
+ mbstate_t mbstate = { 0, };
+ size_t n;
+ size_t width = 0;
+
+ for (char *src = cell; src != srcend; src += n)
{
- if (iscntrl (to_uchar (*p)))
- *p = '?';
- p++;
+ wchar_t wc;
+ n = mbrtowc (&wc, src, srcend - src, &mbstate);
+ if (n < (size_t) -2 && !iswcntrl (wc))
+ {
+ memcpy (dst, src, n);
+ dst += n;
+ }
+ else
+ {
+ *dst++ = '?';
+ memset (&mbstate, 0, sizeof mbstate);
+ }
+ width++;
}
- return cell;
+
+ *dst = '\0';
+ return width;
}
/* Dynamically allocate a row of pointers in TABLE, which
@@ -569,11 +586,10 @@ get_header (void)
if (!cell)
xalloc_die ();
- hide_problematic_chars (cell);
-
table[nrows - 1][col] = cell;
- columns[col]->width = MAX (columns[col]->width, mbswidth (cell, 0));
+ size_t cell_width = hide_problematic_chars (cell);
+ columns[col]->width = MAX (columns[col]->width, cell_width);
}
}
@@ -1182,8 +1198,8 @@ get_dev (char const *disk, char const *mount_point, char const* file,
if (!cell)
assert (!"empty cell");
- hide_problematic_chars (cell);
- columns[col]->width = MAX (columns[col]->width, mbswidth (cell, 0));
+ size_t cell_width = hide_problematic_chars (cell);
+ columns[col]->width = MAX (columns[col]->width, cell_width);
table[nrows - 1][col] = cell;
}
free (dev_name);
--
2.7.4
