diff options
Diffstat (limited to 'test/pbmtext-utf8.test')
| -rwxr-xr-x | test/pbmtext-utf8.test | 194 |
1 files changed, 154 insertions, 40 deletions
diff --git a/test/pbmtext-utf8.test b/test/pbmtext-utf8.test index cf495b7c..9203607f 100755 --- a/test/pbmtext-utf8.test +++ b/test/pbmtext-utf8.test @@ -2,68 +2,101 @@ # This script tests: pbmtext # Also requires: -# This test requires the en_US.utf8 locale -# Skip this test if it is not available +LANG=C +LC_ALL=C +export LANG LC_ALL + + +# This test requires a working UTF-8 locale +# Skip this test if it is are not available iconv /dev/null if [ $? -ne 0 ] then echo "iconv command not available." 1>&2 echo "Skipping." 1>&2 - exit 80; + exit 80; fi -echo "A" | LC_ALL=en_US.utf8 pbmtext -wchar > /dev/null -if [ $? -ne 0 ] - then echo "LC_ALL could not be set to en_US.utf8." 1>&2 +tmpdir=${tmpdir:-/tmp} +utf_locale_list=${tmpdir}/utf_locale_list + +locale_to_test="en_US.utf8" # Initial value +# Edit the above value if necessary + +# Make a list of available locales which end in "utf8" +locale -a | grep "\.utf8$" > ${utf_locale_list} + +# Hunt for a valid utf8 locale +# Submit each candidate to a trial pbmtext run until one that works is +# encountered + +i=0 +until [ -z ${locale_to_test} ] || \ + echo "A" | LC_ALL=${locale_to_test} pbmtext -wchar > /dev/null + do + let i=$(($i+1)); + locale_to_test=`sed "$i"p -n ${utf_locale_list}`; + done; + +rm ${utf_locale_list}; +if [ -z ${locale_to_test} ] + then echo "No utf-8 locale available." 1>&2 echo "Skipping." 1>&2 - exit 80; -fi + exit 80; + else + echo "Testing with locale set to ${locale_to_test}" 1>&2 +fi; + +locale_for_test=${locale_to_test} + # Test 1. # Two rows # Should print 2066913605 5110 twice -LC_ALL=C \ + +echo "Test 1" + awk 'BEGIN { for (i=32; i<=126;++i) printf("%c",i); print ""; \ for (i=161;i<=255;++i) printf("%c",i); }' | \ pbmtext -builtin bdf | cksum -LC_ALL=C \ awk 'BEGIN { for (i=32; i<=126;++i) printf("%c",i); print ""; \ - for (i=161;i<=255;++i) printf("%c",i); }' | \ - iconv -f iso8859-1 -t utf-8 | \ - LC_ALL=en_US.utf8 pbmtext -builtin bdf -wchar | cksum + for (i=161;i<=191;++i) printf("%c%c",194,i); \ + for (i=128;i<=191;++i) printf("%c%c",195,i); }' | \ + LC_ALL=${locale_for_test} pbmtext -builtin bdf -wchar | cksum # Test 2. # One row # Should print 2920616515 2301 twice -LC_ALL=C \ + +echo "Test 2" + awk 'BEGIN { for (i=32; i<=126;++i) printf("%c",i); print "" }' | \ pbmtext -builtin bdf | cksum -LC_ALL=C \ awk 'BEGIN { for (i=32; i<=126;++i) printf("%c",i); print ""}' | \ - LC_ALL=en_US.utf8 pbmtext -builtin bdf -wchar | cksum - + LC_ALL=${locale_for_test} pbmtext -builtin bdf -wchar | cksum -tmpdir=${tmpdir:-/tmp} output=${tmpdir}/output # Test 3. # Two rows -# Output may be affected by locale. Compare with cmp. -# Should print 0 -LC_ALL=C \ +# Compare with cmp. +# Should print 0 0 0 : 0 + +echo "Test 3" + awk 'BEGIN { for (i=32; i<=126;++i) printf("%c",i); print ""; \ - for (i=161;i<=255;++i) printf("%c",i); print "" }' | \ - iconv -f iso8859-1 -t utf-8 > ${output} + for (i=161;i<=191;++i) printf("%c%c",194,i); \ + for (i=128;i<=191;++i) printf("%c%c",195,i); print ""}' \ + > ${output} -LC_ALL=C \ awk 'BEGIN { for (i=32; i<=126;++i) printf("%c",i); print ""; \ - for (i=161;i<=255;++i) printf("%c",i); print "" }' | \ - iconv -f iso8859-1 -t utf-8 | \ - LC_ALL=en_US.utf8 pbmtext -builtin bdf -wchar -text-dump | \ + for (i=161;i<=191;++i) printf("%c%c",194,i); \ + for (i=128;i<=191;++i) printf("%c%c",195,i); print ""}' | \ + LC_ALL=${locale_for_test} pbmtext -builtin bdf -wchar -text-dump | \ cmp --quiet - ${output} echo ${PIPESTATUS[@]} ":" $? @@ -71,25 +104,106 @@ rm ${output} # Test 4. -# One row +# One row ASCII 7-bit range # Should print the following twice: # !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~ -LC_ALL=C \ + +echo "Test 4" + awk 'BEGIN { for (i=32; i<=126;++i) printf("%c",i); print "" } ' -LC_ALL=C \ awk 'BEGIN { for (i=32; i<=126;++i) printf("%c",i); print ""}' | \ - LC_ALL=en_US.utf8 pbmtext -builtin bdf -wchar -text-dump + LC_ALL=${locale_for_test} pbmtext -builtin bdf -wchar -text-dump + +# Test 5. +# Long input text -echo "Invalid utf-8 sequence as input." 1>&2 -echo "An error message should appear below the line." 1>&2 +echo "Test 5 Invalid" + +long_txt=${tmpdir}/long.txt +test_out=${tmpdir}/test_out + +head -c 4999 /dev/zero | sed 's@\x00@\xc2\xbe@g' > ${long_txt} +cat ${long_txt} | wc -c | tr -d ' ' + +cat ${long_txt} | \ + LC_ALL=${locale_for_test} pbmtext -nomargins -builtin fixed -wchar | cksum + +echo 1>&2 +echo "Test input text which exceeds length limit" 1>&2 +echo "Error messages should appear below the line." 1>&2 echo "-----------------------------------------------------------" 1>&2 -# Test 5. -# Invalid utf-8 sequence -# Should print 1 -LC_ALL=C \ -awk 'BEGIN { for (i=128; i<=129;++i) printf("%c",i); print ""}' | \ - LC_ALL=en_US.utf8 pbmtext -builtin bdf -wchar -text-dump -echo ${PIPESTATUS[@]} ":" $? +printf "z" >> ${long_txt} +cat ${long_txt} | wc -c | tr -d ' ' + +cat ${long_txt} | \ + LC_ALL=${locale_for_test} \ + pbmtext -nomargins -builtin fixed -wchar > ${test_out} || \ + printf "Expected failure 1"; + test -s ${test_out}; echo " "$? + rm -f ${test_out} + +cat ${long_txt} | \ + LC_ALL=${locale_for_test} \ + pbmtext -nomargins -builtin fixed -wchar > ${test_out} || \ + printf "Expected failure 2"; + test -s ${test_out}; echo " "$? + rm -f ${test_out} + +rm ${long_txt} + + +# Test 6. +# Invalid utf-8 sequences +# For each case output should be: +# 6-x : 0 1 : 1 1 + +echo "Invalid utf-8 sequences as input." 1>&2 +echo "Errors message should appear below the line." 1>&2 +echo "-----------------------------------------------------------" 1>&2 + +echo "Test 6 Invalid" + +awk 'BEGIN { printf("%c%c",128,129); print ""}' | \ + LC_ALL=${locale_for_test} \ + pbmtext -builtin bdf -wchar -text-dump > ${test_out} + printf "6-1: ${PIPESTATUS[*]} : $?" + test -s ${test_out}; echo " "$? + rm -f ${test_out} + +awk 'BEGIN { printf("ABC%c%c",192, 193); print ""}' | \ + LC_ALL=${locale_for_test} \ + pbmtext -builtin bdf -wchar -text-dump > ${test_out} + printf "6-2: ${PIPESTATUS[*]} : $?" + test -s ${test_out}; echo " "$? + rm -f ${test_out} + +awk 'BEGIN { printf("abcde%c%c", 254, 253); print ""}' | \ + LC_ALL=${locale_for_test} \ + pbmtext -builtin bdf -wchar -text-dump > ${test_out} + printf "6-3: ${PIPESTATUS[*]} : $?" + test -s ${test_out}; echo " "$? + rm -f ${test_out} + +awk 'BEGIN { printf("abcdefg%c%c", 195, 15); print ""}' | \ + LC_ALL=${locale_for_test} \ + pbmtext -builtin bdf -wchar -text-dump > ${test_out} + printf "6-4: ${PIPESTATUS[*]} : $?" + test -s ${test_out}; echo " "$? + rm -f ${test_out} + +awk 'BEGIN { printf("123456789%c%c%c", 224, 143 ,0); print ""}' | \ + LC_ALL=${locale_for_test} \ + pbmtext -builtin bdf -wchar -text-dump > ${test_out} + printf "6-5: ${PIPESTATUS[*]} : $?" + test -s ${test_out}; echo " "$? + rm -f ${test_out} + +awk 'BEGIN { printf("abcdefg123ABCDEFG%c%c%c%c",247, 135, 135, 7); print ""}' | \ + LC_ALL=${locale_for_test} \ + pbmtext -builtin bdf -wchar -text-dump > ${test_out} + printf "6-6: ${PIPESTATUS[*]} : $?" + test -s ${test_out}; echo " "$? + rm -f ${test_out} |