dd: fix conv=ascii, conv=ebcdic, conv=ibm to match POSIX

Problem reported by Don Baggett in <http:/bugs.gnu.org/17422>.
* NEWS:
* doc/coreutils.texi (dd invocation): Document this.
* src/dd.c (conversions): conv=ascii implies conv=unblock.
conv=ebcdic and conv=ibm imply conv=block.
(ascii_to_ebcdic, ebcdic_to_ascii): Correct to match
POSIX 1003.1-2013.
* tests/dd/ascii.sh: New file.
* tests/local.mk (all_tests): Add it.

5 files changed, 122 insertions, 19 deletions

diff --git a/NEWS b/NEWS
index f7b511273..4efd60d2e 100644
--- a/NEWS
+++ b/NEWS
@@ -23,6 +23,27 @@ GNU coreutils NEWS                                    -*- outline -*-
   date could crash or go into an infinite loop when parsing a malformed TZ="".
   [bug introduced with the --date='TZ="" ..' parsing feature in coreutils-5.3.0]
 
+  dd's ASCII and EBCDIC conversions were incompatible with common practice and
+  with POSIX, and have been corrected as follows.  First, conv=ascii now
+  implies conv=unblock, and conv=ebcdic and conv=ibm now imply conv=block.
+  Second, the translation tables for dd conv=ascii and conv=ebcdic have been
+  corrected as shown in the following table, where A is the ASCII value, W is
+  the old, wrong EBCDIC value, and E is the new, corrected EBCDIC value; all
+  values are in octal.
+
+      A   W   E
+     041 117 132
+     133 112 255
+     135 132 275
+     136 137 232
+     174 152 117
+     176 241 137
+     313 232 152
+     325 255 112
+     345 275 241
+
+  [These dd bugs were present in "the beginning".]
+
   head --bytes=-N and --lines=-N now handles devices more
   consistently, not ignoring data from virtual devices like /dev/zero,
   or on BSD systems data from tty devices.
diff --git a/doc/coreutils.texi b/doc/coreutils.texi
index a949ffcac..789cd68e5 100644
--- a/doc/coreutils.texi
+++ b/doc/coreutils.texi
@@ -8621,21 +8621,26 @@ Conversions:
 Convert EBCDIC to ASCII,
 using the conversion table specified by POSIX@.
 This provides a 1:1 translation for all 256 bytes.
+This option implies @samp{conv=unblock}; input is converted to
+ASCII before trailing spaces are deleted.
 
 @item ebcdic
 @opindex ebcdic@r{, converting to}
 Convert ASCII to EBCDIC@.
 This is the inverse of the @samp{ascii} conversion.
+This option implies @samp{conv=block}; trailing spaces are added
+before being converted to EBCDIC@.
 
 @item ibm
 @opindex alternate ebcdic@r{, converting to}
-Convert ASCII to alternate EBCDIC,
-using the alternate conversion table specified by POSIX@.
+This acts like @samp{conv=ebcdic}, except it
+uses the alternate conversion table specified by POSIX@.
 This is not a 1:1 translation, but reflects common historical practice
 for @samp{~}, @samp{[}, and @samp{]}.
 
 The @samp{ascii}, @samp{ebcdic}, and @samp{ibm} conversions are
-mutually exclusive.
+mutually exclusive.  If you use any of these options, you should also
+use the @samp{cbs=} option.
 
 @item block
 @opindex block @r{(space-padding)}
diff --git a/src/dd.c b/src/dd.c
index c7909e725..1e387f3d8 100644
--- a/src/dd.c
+++ b/src/dd.c
@@ -274,9 +274,9 @@ struct symbol_value
 /* Conversion symbols, for conv="...".  */
 static struct symbol_value const conversions[] =
 {
-  {"ascii", C_ASCII | C_TWOBUFS},	/* EBCDIC to ASCII. */
-  {"ebcdic", C_EBCDIC | C_TWOBUFS},	/* ASCII to EBCDIC. */
-  {"ibm", C_IBM | C_TWOBUFS},	/* Slightly different ASCII to EBCDIC. */
+  {"ascii", C_ASCII | C_UNBLOCK | C_TWOBUFS},	/* EBCDIC to ASCII. */
+  {"ebcdic", C_EBCDIC | C_BLOCK | C_TWOBUFS},	/* ASCII to EBCDIC. */
+  {"ibm", C_IBM | C_BLOCK | C_TWOBUFS},	/* Different ASCII to EBCDIC. */
   {"block", C_BLOCK | C_TWOBUFS},	/* Variable to fixed length records. */
   {"unblock", C_UNBLOCK | C_TWOBUFS},	/* Fixed to variable length records. */
   {"lcase", C_LCASE | C_TWOBUFS},	/* Translate upper to lower case. */
@@ -381,24 +381,29 @@ static struct symbol_value const statuses[] =
 /* Translation table formed by applying successive transformations. */
 static unsigned char trans_table[256];
 
+/* Standard translation tables, taken from POSIX 1003.1-2013.
+   Beware of imitations; there are lots of ASCII<->EBCDIC tables
+   floating around the net, perhaps valid for some applications but
+   not correct here.  */
+
 static char const ascii_to_ebcdic[] =
 {
   '\000', '\001', '\002', '\003', '\067', '\055', '\056', '\057',
   '\026', '\005', '\045', '\013', '\014', '\015', '\016', '\017',
   '\020', '\021', '\022', '\023', '\074', '\075', '\062', '\046',
   '\030', '\031', '\077', '\047', '\034', '\035', '\036', '\037',
-  '\100', '\117', '\177', '\173', '\133', '\154', '\120', '\175',
+  '\100', '\132', '\177', '\173', '\133', '\154', '\120', '\175',
   '\115', '\135', '\134', '\116', '\153', '\140', '\113', '\141',
   '\360', '\361', '\362', '\363', '\364', '\365', '\366', '\367',
   '\370', '\371', '\172', '\136', '\114', '\176', '\156', '\157',
   '\174', '\301', '\302', '\303', '\304', '\305', '\306', '\307',
   '\310', '\311', '\321', '\322', '\323', '\324', '\325', '\326',
   '\327', '\330', '\331', '\342', '\343', '\344', '\345', '\346',
-  '\347', '\350', '\351', '\112', '\340', '\132', '\137', '\155',
+  '\347', '\350', '\351', '\255', '\340', '\275', '\232', '\155',
   '\171', '\201', '\202', '\203', '\204', '\205', '\206', '\207',
   '\210', '\211', '\221', '\222', '\223', '\224', '\225', '\226',
   '\227', '\230', '\231', '\242', '\243', '\244', '\245', '\246',
-  '\247', '\250', '\251', '\300', '\152', '\320', '\241', '\007',
+  '\247', '\250', '\251', '\300', '\117', '\320', '\137', '\007',
   '\040', '\041', '\042', '\043', '\044', '\025', '\006', '\027',
   '\050', '\051', '\052', '\053', '\054', '\011', '\012', '\033',
   '\060', '\061', '\032', '\063', '\064', '\065', '\066', '\010',
@@ -408,10 +413,10 @@ static char const ascii_to_ebcdic[] =
   '\130', '\131', '\142', '\143', '\144', '\145', '\146', '\147',
   '\150', '\151', '\160', '\161', '\162', '\163', '\164', '\165',
   '\166', '\167', '\170', '\200', '\212', '\213', '\214', '\215',
-  '\216', '\217', '\220', '\232', '\233', '\234', '\235', '\236',
-  '\237', '\240', '\252', '\253', '\254', '\255', '\256', '\257',
+  '\216', '\217', '\220', '\152', '\233', '\234', '\235', '\236',
+  '\237', '\240', '\252', '\253', '\254', '\112', '\256', '\257',
   '\260', '\261', '\262', '\263', '\264', '\265', '\266', '\267',
-  '\270', '\271', '\272', '\273', '\274', '\275', '\276', '\277',
+  '\270', '\271', '\272', '\273', '\274', '\241', '\276', '\277',
   '\312', '\313', '\314', '\315', '\316', '\317', '\332', '\333',
   '\334', '\335', '\336', '\337', '\352', '\353', '\354', '\355',
   '\356', '\357', '\372', '\373', '\374', '\375', '\376', '\377'
@@ -464,21 +469,21 @@ static char const ebcdic_to_ascii[] =
   '\220', '\221', '\026', '\223', '\224', '\225', '\226', '\004',
   '\230', '\231', '\232', '\233', '\024', '\025', '\236', '\032',
   '\040', '\240', '\241', '\242', '\243', '\244', '\245', '\246',
-  '\247', '\250', '\133', '\056', '\074', '\050', '\053', '\041',
+  '\247', '\250', '\325', '\056', '\074', '\050', '\053', '\174',
   '\046', '\251', '\252', '\253', '\254', '\255', '\256', '\257',
-  '\260', '\261', '\135', '\044', '\052', '\051', '\073', '\136',
+  '\260', '\261', '\041', '\044', '\052', '\051', '\073', '\176',
   '\055', '\057', '\262', '\263', '\264', '\265', '\266', '\267',
-  '\270', '\271', '\174', '\054', '\045', '\137', '\076', '\077',
+  '\270', '\271', '\313', '\054', '\045', '\137', '\076', '\077',
   '\272', '\273', '\274', '\275', '\276', '\277', '\300', '\301',
   '\302', '\140', '\072', '\043', '\100', '\047', '\075', '\042',
   '\303', '\141', '\142', '\143', '\144', '\145', '\146', '\147',
   '\150', '\151', '\304', '\305', '\306', '\307', '\310', '\311',
   '\312', '\152', '\153', '\154', '\155', '\156', '\157', '\160',
-  '\161', '\162', '\313', '\314', '\315', '\316', '\317', '\320',
-  '\321', '\176', '\163', '\164', '\165', '\166', '\167', '\170',
-  '\171', '\172', '\322', '\323', '\324', '\325', '\326', '\327',
+  '\161', '\162', '\136', '\314', '\315', '\316', '\317', '\320',
+  '\321', '\345', '\163', '\164', '\165', '\166', '\167', '\170',
+  '\171', '\172', '\322', '\323', '\324', '\133', '\326', '\327',
   '\330', '\331', '\332', '\333', '\334', '\335', '\336', '\337',
-  '\340', '\341', '\342', '\343', '\344', '\345', '\346', '\347',
+  '\340', '\341', '\342', '\343', '\344', '\135', '\346', '\347',
   '\173', '\101', '\102', '\103', '\104', '\105', '\106', '\107',
   '\110', '\111', '\350', '\351', '\352', '\353', '\354', '\355',
   '\175', '\112', '\113', '\114', '\115', '\116', '\117', '\120',
diff --git a/tests/dd/ascii.sh b/tests/dd/ascii.sh
new file mode 100755
index 000000000..9ef158f78
--- /dev/null
+++ b/tests/dd/ascii.sh
@@ -0,0 +1,71 @@
+#!/bin/sh
+# test conv=ascii
+
+# Copyright (C) 2014 Free Software Foundation, Inc.
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+. "${srcdir=.}/tests/init.sh"; path_prepend_ ./src
+print_ver_ dd
+
+(
+  # Two lines, EBCDIC " A A" and " A  ", followed by all the bytes in order.
+  printf '\100\301\100\301\100\301\100\100' &&
+  printf $(for i in $(seq 0 255); do printf '\\%03o' $i; done; echo '')
+) >in || framework_failure_
+
+(
+  # The converted lines, with trailing spaces removed.
+  printf ' A A\n A\n' &&
+  printf '\000\001\002\003\n\234\011\206\177\n' &&
+  printf '\227\215\216\013\n\014\015\016\017\n' &&
+  printf '\020\021\022\023\n\235\205\010\207\n' &&
+  printf '\030\031\222\217\n\034\035\036\037\n' &&
+  printf '\200\201\202\203\n\204\012\027\033\n' &&
+  printf '\210\211\212\213\n\214\005\006\007\n' &&
+  printf '\220\221\026\223\n\224\225\226\004\n' &&
+  printf '\230\231\232\233\n\024\025\236\032\n' &&
+  printf '\040\240\241\242\n\243\244\245\246\n' &&
+  printf '\247\250\325\056\n\074\050\053\174\n' &&
+  printf '\046\251\252\253\n\254\255\256\257\n' &&
+  printf '\260\261\041\044\n\052\051\073\176\n' &&
+  printf '\055\057\262\263\n\264\265\266\267\n' &&
+  printf '\270\271\313\054\n\045\137\076\077\n' &&
+  printf '\272\273\274\275\n\276\277\300\301\n' &&
+  printf '\302\140\072\043\n\100\047\075\042\n' &&
+  printf '\303\141\142\143\n\144\145\146\147\n' &&
+  printf '\150\151\304\305\n\306\307\310\311\n' &&
+  printf '\312\152\153\154\n\155\156\157\160\n' &&
+  printf '\161\162\136\314\n\315\316\317\320\n' &&
+  printf '\321\345\163\164\n\165\166\167\170\n' &&
+  printf '\171\172\322\323\n\324\133\326\327\n' &&
+  printf '\330\331\332\333\n\334\335\336\337\n' &&
+  printf '\340\341\342\343\n\344\135\346\347\n' &&
+  printf '\173\101\102\103\n\104\105\106\107\n' &&
+  printf '\110\111\350\351\n\352\353\354\355\n' &&
+  printf '\175\112\113\114\n\115\116\117\120\n' &&
+  printf '\121\122\356\357\n\360\361\362\363\n' &&
+  printf '\134\237\123\124\n\125\126\127\130\n' &&
+  printf '\131\132\364\365\n\366\367\370\371\n' &&
+  printf '\060\061\062\063\n\064\065\066\067\n' &&
+  printf '\070\071\372\373\n\374\375\376\377\n'
+) >exp || framework_failure_
+
+dd if=in of=out conv=ascii cbs=4
+cp ./in ./out ./exp /tmp
+
+fail=0
+compare exp out || fail=1
+
+Exit $fail
diff --git a/tests/local.mk b/tests/local.mk
index 6d4414488..5286bfb34 100644
--- a/tests/local.mk
+++ b/tests/local.mk
@@ -470,6 +470,7 @@ all_tests =					\
   tests/df/no-mtab-status.sh			\
   tests/df/skip-duplicates.sh			\
   tests/df/skip-rootfs.sh			\
+  tests/dd/ascii.sh				\
   tests/dd/direct.sh				\
   tests/dd/misc.sh				\
   tests/dd/no-allocate.sh				\