X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=tests%2Flibpspp%2Fu8-istream.at;h=9cedc0eedf7b02ce6c0424148f9c2ae5f762903e;hb=ee254a81d976fae12a67e799a4aedee47c6b0bed;hp=985805d7ee0e6605bc24651e0c61a6167f53fda1;hpb=085dfff1c41d6ee305f00aa7177286ca8965efbc;p=pspp

diff --git a/tests/libpspp/u8-istream.at b/tests/libpspp/u8-istream.at
index 985805d7ee..9cedc0eedf 100644
--- a/tests/libpspp/u8-istream.at
+++ b/tests/libpspp/u8-istream.at
@@ -1,3 +1,19 @@
+dnl PSPP - a program for statistical analysis.
+dnl Copyright (C) 2017 Free Software Foundation, Inc.
+dnl
+dnl This program is free software: you can redistribute it and/or modify
+dnl it under the terms of the GNU General Public License as published by
+dnl the Free Software Foundation, either version 3 of the License, or
+dnl (at your option) any later version.
+dnl
+dnl This program is distributed in the hope that it will be useful,
+dnl but WITHOUT ANY WARRANTY; without even the implied warranty of
+dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+dnl GNU General Public License for more details.
+dnl
+dnl You should have received a copy of the GNU General Public License
+dnl along with this program.  If not, see <http://www.gnu.org/licenses/>.
+dnl
 AT_BANNER([u8_istream])
 
 AT_SETUP([read ASCII])
@@ -9,11 +25,18 @@ AT_CLEANUP
 
 AT_SETUP([read UTF-8])
 AT_KEYWORDS([u8_istream])
+# Without byte-order-mark.
 AT_CHECK([printf '\346\227\245\346\234\254\350\252\236\n' | u8-istream-test read - UTF-8], [0], [dnl
 UTF-8 mode
 日本語
 UTF-8 mode
 ])
+# With byte-order-mark.
+AT_CHECK([printf '\357\273\277\346\227\245\346\234\254\350\252\236\n' | u8-istream-test read - UTF-8], [0], [dnl
+UTF-8 mode
+日本語
+UTF-8 mode
+])
 AT_CLEANUP
 
 AT_SETUP([read EUC-JP])
@@ -28,7 +51,7 @@ AT_CLEANUP
 AT_SETUP([read UTF-8 with character split across input buffers])
 AT_KEYWORDS([u8_istream])
 buffer_size=`u8-istream-test buffer-size`
-($PERL -e "print 'x' x ($buffer_size - 16)"
+($PYTHON3 -c "import sys; sys.stdout.write('x' * ($buffer_size - 16))";
  printf '\343\201\201\343\201\202\343\201\203\343\201\204\343\201\205\343\201\206\343\201\207\343\201\210\343\201\211\343\201\212\n') > input
 (echo "UTF-8 mode"
  cat input
@@ -48,7 +71,7 @@ AT_CLEANUP
 AT_SETUP([read UTF-8 with character split across input and output buffers])
 AT_KEYWORDS([u8_istream])
 buffer_size=`u8-istream-test buffer-size`
-($PERL -e "print 'x' x ($buffer_size - 16)"
+($PYTHON3 -c "import sys; sys.stdout.write('x' * ($buffer_size - 16))";
  printf '\343\201\201\343\201\202\343\201\203\343\201\204\343\201\205\343\201\206\343\201\207\343\201\210\343\201\211\343\201\212\n') > input
 (echo "UTF-8 mode"
  cat input
@@ -60,10 +83,10 @@ AT_SETUP([read EUC-JP with character split across input buffers])
 AT_KEYWORDS([u8_istream])
 AT_CHECK([i18n-test supports_encodings EUC-JP])
 buffer_size=`u8-istream-test buffer-size`
-($PERL -e "print 'x' x ($buffer_size - 16)"
+($PYTHON3 -c "import sys; sys.stdout.write('x' * ($buffer_size - 16))";
  printf '\244\241 \244\242 \244\243 \244\244 \244\245 \244\246 \244\247 '
  printf '\244\250 \244\251 \244\252\n') > input
-($PERL -e "print 'x' x ($buffer_size - 16)"
+($PYTHON3 -c "import sys; sys.stdout.write('x' * ($buffer_size - 16))";
  printf '\343\201\201\040\343\201\202\040\343\201\203\040\343\201\204\040'
  printf '\343\201\205\040\343\201\206\040\343\201\207\040\343\201\210\040'
  printf '\343\201\211\040\343\201\212\n') > expout
@@ -83,10 +106,10 @@ AT_SETUP([read EUC-JP with character split across input and output buffers])
 AT_KEYWORDS([u8_istream])
 AT_CHECK([i18n-test supports_encodings EUC-JP])
 buffer_size=`u8-istream-test buffer-size`
-($PERL -e "print 'x' x ($buffer_size - 16)"
+($PYTHON3 -c "import sys; sys.stdout.write('x' * ($buffer_size - 16))";
  printf 'xyz\244\241\244\242\244\243\244\244\244\245\244\246\244\247\244\250'
  printf '\244\251\244\252\n') > input
-($PERL -e "print 'x' x ($buffer_size - 16)"
+($PYTHON3 -c "import sys; sys.stdout.write('x' * ($buffer_size - 16))";
  printf '\170\171\172\343\201\201\343\201\202\343\201\203\343\201\204\343'
  printf '\201\205\343\201\206\343\201\207\343\201\210\343\201\211\343\201'
  printf '\212\n') > expout
@@ -104,20 +127,28 @@ AT_CLEANUP
 
 AT_SETUP([read UTF-8 as Auto])
 AT_KEYWORDS([u8_istream])
+# Without byte-order mark.
 AT_CHECK([printf 'entr\303\251e\n' | u8-istream-test read - Auto], [0], [dnl
 Auto mode
 entrée
 UTF-8 mode
 ])
+# With byte-order mark.
+AT_CHECK([printf '\357\273\277entr\303\251e\n' | u8-istream-test read - Auto], [0], [dnl
+UTF-8 mode
+entrée
+UTF-8 mode
+])
 AT_CLEANUP
 
 AT_SETUP([read ISO-8859-1 as Auto,ISO-8859-1])
 AT_KEYWORDS([u8_istream])
 AT_CHECK([i18n-test supports_encodings ISO-8859-1])
 buffer_size=`u8-istream-test buffer-size`
-($PERL -e "print 'x' x int($buffer_size * 2.5)"; printf 'entr\351e\n') > input
+($PYTHON3 -c "import sys; sys.stdout.write('xyzzy\n' * ($buffer_size * 5 // 14))"
+ printf 'entr\351e\n') > input
 (echo "Auto mode"
- $PERL -e "print 'x' x int($buffer_size * 2.5)"
+ $PYTHON3 -c "import sys; sys.stdout.write('xyzzy\n' * ($buffer_size * 5 // 14))"
  printf 'entr\303\251e\n') > expout
 AT_CHECK([u8-istream-test read input Auto,ISO-8859-1], [0], [expout])
 AT_CLEANUP
@@ -126,16 +157,62 @@ dnl UTF-16BE is not ASCII compatible so this doesn't start out in Auto mode.
 AT_SETUP([read UTF-16BE as Auto,UTF-16BE])
 AT_KEYWORDS([u8_istream])
 AT_CHECK([i18n-test supports_encodings UTF-16BE])
-AT_CHECK([printf '\0e\0n\0t\0r\0\351\0e\0\n' | u8-istream-test read - Auto,UTF-16BE], 
+# Without byte-order mark.
+AT_CHECK([printf '\0e\0n\0t\0r\0\351\0e\0\n' | u8-istream-test read - Auto,UTF-16BE],
   [0], [dnl
 entrée
 ])
+# With byte-order mark.
+AT_CHECK([printf '\376\377\0e\0n\0t\0r\0\351\0e\0\n' | u8-istream-test read - Auto,UTF-16BE],
+  [0], [dnl
+entrée
+])
+AT_CLEANUP
+
+AT_SETUP([read UTF-16 as Auto])
+AT_KEYWORDS([u8_istream slow])
+AT_CHECK([i18n-test supports_encodings UTF-16 UTF-16BE UTF-16LE])
+# Without byte-order mark.
+dnl The "sleep 1" checks for a bug in which u8-istream did not properly
+dnl handle receiving data in multiple chunks.
+AT_CHECK([{ printf '\0e\0n\0t\0'; sleep 1; printf 'r\0\351\0e\0\n'; } | u8-istream-test read - Auto],
+  [0], [entrée
+])
+AT_CHECK([printf 'e\0n\0t\0r\0\351\0e\0\n\0' | u8-istream-test read - Auto],
+  [0], [entrée
+])
+# With byte-order mark.
+AT_CHECK([printf '\376\377\0e\0n\0t\0r\0\351\0e\0\n' | u8-istream-test read - Auto],
+  [0], [entrée
+])
+AT_CHECK([printf '\377\376e\0n\0t\0r\0\351\0e\0\n\0' | u8-istream-test read - Auto],
+  [0], [entrée
+])
+AT_CLEANUP
+
+AT_SETUP([read UTF-32 as Auto])
+AT_KEYWORDS([u8_istream])
+AT_CHECK([i18n-test supports_encodings UTF-16 UTF-16BE UTF-16LE])
+# Without byte-order mark.
+AT_CHECK([printf '\0\0\0e\0\0\0n\0\0\0t\0\0\0r\0\0\0\351\0\0\0e\0\0\0\n' | u8-istream-test read - Auto],
+  [0], [entrée
+])
+AT_CHECK([printf 'e\0\0\0n\0\0\0t\0\0\0r\0\0\0\351\0\0\0e\0\0\0\n\0\0\0' | u8-istream-test read - Auto],
+  [0], [entrée
+])
+# With byte-order mark.
+AT_CHECK([printf '\0\0\376\377\0\0\0e\0\0\0n\0\0\0t\0\0\0r\0\0\0\351\0\0\0e\0\0\0\n' | u8-istream-test read - Auto],
+  [0], [entrée
+])
+AT_CHECK([printf '\377\376\0\0e\0\0\0n\0\0\0t\0\0\0r\0\0\0\351\0\0\0e\0\0\0\n\0\0\0' | u8-istream-test read - Auto],
+  [0], [entrée
+])
 AT_CLEANUP
 
 AT_SETUP([read EUC-JP as Auto,EUC-JP])
 AT_KEYWORDS([u8_istream])
 AT_CHECK([i18n-test supports_encodings EUC-JP])
-AT_CHECK([printf 'entr\217\253\261e\n' | u8-istream-test read - Auto,EUC-JP], 
+AT_CHECK([printf 'entr\217\253\261e\n' | u8-istream-test read - Auto,EUC-JP],
   [0], [entrée
 ])
 AT_CLEANUP