aboutsummaryrefslogtreecommitdiff
path: root/tests
diff options
context:
space:
mode:
Diffstat (limited to 'tests')
-rw-r--r--tests/Makefile2
-rw-r--r--tests/regcount.test35
-rw-r--r--tests/regexp2.test909
-rw-r--r--tests/utf8.test207
-rw-r--r--tests/utftcl.test290
5 files changed, 1236 insertions, 207 deletions
diff --git a/tests/Makefile b/tests/Makefile
index 285fb9e..02c6c1e 100644
--- a/tests/Makefile
+++ b/tests/Makefile
@@ -9,4 +9,4 @@ test:
make -C .. all
clean:
- rm -f gorp.file2 cat gorp.file sleep exit wc sh echo
+ rm -f gorp.file2 cat gorp.file sleep exit wc sh echo test1
diff --git a/tests/regcount.test b/tests/regcount.test
new file mode 100644
index 0000000..4b4d106
--- /dev/null
+++ b/tests/regcount.test
@@ -0,0 +1,35 @@
+source testing.tcl
+
+# Test regexp counted repetitions
+
+set n 0
+foreach {pat str exp} {
+ a+ bac 1
+ a{1,} bac 1
+ a* bac 1
+ a{0,} bac 1
+ aa+ bac 0
+ a{2,} bac 0
+ a{2,} bacaad 1
+ a{3,} bacaad 0
+ a{2,}$ bacaad 0
+ a{2,}$ bacaa 1
+ a{2,}$ ba 0
+ a{2,}$ aa 1
+ a{0,0}b$ b 1
+ a{1,1}b$ b 0
+ a{1,1}b$ cab 1
+ a{2,2}b$ cab 0
+ a{2,2}b$ cabaabx 0
+ a{2,2}b$ cacaab 1
+ ca{2,4}b cacaab 1
+ ca{2,3}b cacaab 1
+ ca{2,3}b cacaaab 1
+ c(a|b){2,3}d xcbad 1
+ c(a|b){2,3}d xcabbd 1
+ c(a|b){2,3}d xcbaaad 0
+} {
+ test regcount-1.[incr n] "Test: regexp $pat" [list regexp -- $pat $str] $exp
+}
+
+testreport
diff --git a/tests/regexp2.test b/tests/regexp2.test
new file mode 100644
index 0000000..a061e8b
--- /dev/null
+++ b/tests/regexp2.test
@@ -0,0 +1,909 @@
+# Commands covered: regexp, regsub
+#
+# This file contains a collection of tests for one or more of the Tcl
+# built-in commands. Sourcing this file into Tcl runs the tests and
+# generates output for errors. No output means no errors were found.
+#
+# Copyright (c) 1991-1993 The Regents of the University of California.
+# Copyright (c) 1998 Sun Microsystems, Inc.
+# Copyright (c) 1998-1999 by Scriptics Corporation.
+#
+# See the file "license.terms" for information on usage and redistribution
+# of this file, and for a DISCLAIMER OF ALL WARRANTIES.
+#
+# RCS: @(#) $Id$
+
+source testing.tcl
+
+catch {package require regexp}
+if {[info commands regexp] eq "" || [regexp {\d} 1] == 0} {
+ # No regexp, or not using a sufficiently capable regexp implementation
+ puts " --- skipped"
+ exit 0
+}
+
+
+# Procedure to evaluate a script within a proc, to test compilation
+# functionality
+
+proc evalInProc { script } {
+ proc testProc {} $script
+ set status [catch {
+ testProc
+ } result]
+ rename testProc {}
+ return $result
+ #return [list $status $result]
+}
+
+catch {unset foo}
+test regexpComp-1.1 {basic regexp operation} {
+ evalInProc {
+ regexp ab*c abbbc
+ }
+} 1
+test regexpComp-1.2 {basic regexp operation} {
+ evalInProc {
+ regexp ab*c ac
+ }
+} 1
+test regexpComp-1.3 {basic regexp operation} {
+ evalInProc {
+ regexp ab*c ab
+ }
+} 0
+test regexpComp-1.4 {basic regexp operation} {
+ evalInProc {
+ regexp -- -gorp abc-gorpxxx
+ }
+} 1
+test regexpComp-1.5 {basic regexp operation} {
+ evalInProc {
+ regexp {^([^ ]*)[ ]*([^ ]*)} "" a
+ }
+} 1
+test regexpComp-1.6 {basic regexp operation} {
+ list [catch {regexp {} abc} msg] $msg
+} {0 1}
+test regexpComp-1.7 {regexp utf compliance} {
+ # if not UTF-8 aware, result is "0 1"
+ evalInProc {
+ set foo "\u4e4eb q"
+ regexp "\u4e4eb q" "a\u4e4eb qw\u5e4e\x4e wq" bar
+ list [string compare $foo $bar] [regexp 4 $bar]
+ }
+} {0 0}
+
+test regexpComp-2.1 {getting substrings back from regexp} {
+ evalInProc {
+ set foo {}
+ list [regexp ab*c abbbbc foo] $foo
+ }
+} {1 abbbbc}
+test regexpComp-2.2 {getting substrings back from regexp} {
+ evalInProc {
+ set foo {}
+ set f2 {}
+ list [regexp a(b*)c abbbbc foo f2] $foo $f2
+ }
+} {1 abbbbc bbbb}
+test regexpComp-2.3 {getting substrings back from regexp} {
+ evalInProc {
+ set foo {}
+ set f2 {}
+ list [regexp a(b*)(c) abbbbc foo f2] $foo $f2
+ }
+} {1 abbbbc bbbb}
+test regexpComp-2.4 {getting substrings back from regexp} {
+ evalInProc {
+ set foo {}
+ set f2 {}
+ set f3 {}
+ list [regexp a(b*)(c) abbbbc foo f2 f3] $foo $f2 $f3
+ }
+} {1 abbbbc bbbb c}
+test regexpComp-2.5 {getting substrings back from regexp} {
+ evalInProc {
+ set foo {}; set f1 {}; set f2 {}; set f3 {}; set f4 {}; set f5 {};
+ set f6 {}; set f7 {}; set f8 {}; set f9 {}; set fa {}; set fb {};
+ list [regexp (1*)(2*)(3*)(4*)(5*)(6*)(7*)(8*)(9*)(a*)(b*) \
+ 12223345556789999aabbb \
+ foo f1 f2 f3 f4 f5 f6 f7 f8 f9 fa fb] $foo $f1 $f2 $f3 $f4 $f5 \
+ $f6 $f7 $f8 $f9 $fa $fb
+ }
+} {1 12223345556789999aabbb 1 222 33 4 555 6 7 8 9999 aa bbb}
+test regexpComp-2.6 {getting substrings back from regexp} {
+ evalInProc {
+ set foo 2; set f2 2; set f3 2; set f4 2
+ list [regexp (a)(b)? xay foo f2 f3 f4] $foo $f2 $f3 $f4
+ }
+} {1 a a {} {}}
+test regexpComp-2.7 {getting substrings back from regexp} {
+ evalInProc {
+ set foo 1; set f2 1; set f3 1; set f4 1
+ list [regexp (a)(b)?(c) xacy foo f2 f3 f4] $foo $f2 $f3 $f4
+ }
+} {1 ac a {} c}
+test regexpComp-2.8 {getting substrings back from regexp} {
+ evalInProc {
+ set match {}
+ list [regexp {^a*b} aaaab match] $match
+ }
+} {1 aaaab}
+
+test regexpComp-3.1 {-indices option to regexp} {
+ evalInProc {
+ set foo {}
+ list [regexp -indices ab*c abbbbc foo] $foo
+ }
+} {1 {0 5}}
+test regexpComp-3.2 {-indices option to regexp} {
+ evalInProc {
+ set foo {}
+ set f2 {}
+ list [regexp -indices a(b*)c abbbbc foo f2] $foo $f2
+ }
+} {1 {0 5} {1 4}}
+test regexpComp-3.3 {-indices option to regexp} {
+ evalInProc {
+ set foo {}
+ set f2 {}
+ list [regexp -indices a(b*)(c) abbbbc foo f2] $foo $f2
+ }
+} {1 {0 5} {1 4}}
+test regexpComp-3.4 {-indices option to regexp} {
+ evalInProc {
+ set foo {}
+ set f2 {}
+ set f3 {}
+ list [regexp -indices a(b*)(c) abbbbc foo f2 f3] $foo $f2 $f3
+ }
+} {1 {0 5} {1 4} {5 5}}
+test regexpComp-3.5 {-indices option to regexp} {
+ evalInProc {
+ set foo {}; set f1 {}; set f2 {}; set f3 {}; set f4 {}; set f5 {};
+ set f6 {}; set f7 {}; set f8 {}; set f9 {}
+ list [regexp -indices (1*)(2*)(3*)(4*)(5*)(6*)(7*)(8*)(9*) \
+ 12223345556789999 \
+ foo f1 f2 f3 f4 f5 f6 f7 f8 f9] $foo $f1 $f2 $f3 $f4 $f5 \
+ $f6 $f7 $f8 $f9
+ }
+} {1 {0 16} {0 0} {1 3} {4 5} {6 6} {7 9} {10 10} {11 11} {12 12} {13 16}}
+test regexpComp-3.6 {getting substrings back from regexp} {
+ evalInProc {
+ set foo 2; set f2 2; set f3 2; set f4 2
+ list [regexp -indices (a)(b)? xay foo f2 f3 f4] $foo $f2 $f3 $f4
+ }
+} {1 {1 1} {1 1} {-1 -1} {-1 -1}}
+test regexpComp-3.7 {getting substrings back from regexp} {
+ evalInProc {
+ set foo 1; set f2 1; set f3 1; set f4 1
+ list [regexp -indices (a)(b)?(c) xacy foo f2 f3 f4] $foo $f2 $f3 $f4
+ }
+} {1 {1 2} {1 1} {-1 -1} {2 2}}
+
+test regexpComp-4.1 {-nocase option to regexp} {
+ evalInProc {
+ regexp -nocase foo abcFOo
+ }
+} 1
+test regexpComp-4.2 {-nocase option to regexp} {
+ evalInProc {
+ set f1 22
+ set f2 33
+ set f3 44
+ list [regexp -nocase {a(b*)([xy]*)z} aBbbxYXxxZ22 f1 f2 f3] $f1 $f2 $f3
+ }
+} {1 aBbbxYXxxZ Bbb xYXxx}
+test regexpComp-4.3 {-nocase option to regexp} {
+ evalInProc {
+ regexp -nocase FOo abcFOo
+ }
+} 1
+set ::x abcdefghijklmnopqrstuvwxyz1234567890
+set ::x $x$x$x$x$x$x$x$x$x$x$x$x
+test regexpComp-4.4 {case conversion in regexp} {
+ evalInProc {
+ list [regexp -nocase $::x $::x foo] $foo
+ }
+} "1 $x"
+catch {unset ::x}
+
+test regexpComp-5.1 {exercise cache of compiled expressions} {
+ evalInProc {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*a bbba
+ }
+} 1
+test regexpComp-5.2 {exercise cache of compiled expressions} {
+ evalInProc {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*b xxxb
+ }
+} 1
+test regexpComp-5.3 {exercise cache of compiled expressions} {
+ evalInProc {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*c yyyc
+ }
+} 1
+test regexpComp-5.4 {exercise cache of compiled expressions} {
+ evalInProc {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*d 1d
+ }
+} 1
+test regexpComp-5.5 {exercise cache of compiled expressions} {
+ evalInProc {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*e xe
+ }
+} 1
+
+test regexpComp-6.4 {regexp errors} {
+ evalInProc {
+ list [catch {regexp a( b} msg] $msg
+ }
+} {1 {couldn't compile regular expression pattern: parentheses () not balanced}}
+test regexpComp-6.5 {regexp errors} {
+ evalInProc {
+ list [catch {regexp a( b} msg] $msg
+ }
+} {1 {couldn't compile regular expression pattern: parentheses () not balanced}}
+test regexpComp-6.6 {regexp errors} {
+ evalInProc {
+ list [catch {regexp a a f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1 f1} msg] $msg
+ }
+} {0 1}
+test regexpComp-6.7 {regexp errors} {
+ evalInProc {
+ list [catch {regexp (x)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.) xyzzy} msg] $msg
+ }
+} {0 0}
+test regexpComp-6.8 {regexp errors} {
+ evalInProc {
+ catch {unset f1}
+ set f1 44
+ catch {regexp abc abc f1(f2)} msg
+ }
+} {1}
+test regexpComp-6.9 {regexp errors, -start bad int check} {
+ evalInProc {
+ list [catch {regexp -start bogus {^$} {}} msg] $msg
+ }
+} {1 {bad index "bogus": must be integer?[+-]integer? or end?[+-]integer?}}
+
+test regexpComp-7.1 {basic regsub operation} {
+ evalInProc {
+ list [regsub aa+ xaxaaaxaa 111&222 foo] $foo
+ }
+} {1 xax111aaa222xaa}
+test regexpComp-7.2 {basic regsub operation} {
+ evalInProc {
+ list [regsub aa+ aaaxaa &111 foo] $foo
+ }
+} {1 aaa111xaa}
+test regexpComp-7.3 {basic regsub operation} {
+ evalInProc {
+ list [regsub aa+ xaxaaa 111& foo] $foo
+ }
+} {1 xax111aaa}
+test regexpComp-7.4 {basic regsub operation} {
+ evalInProc {
+ list [regsub aa+ aaa 11&2&333 foo] $foo
+ }
+} {1 11aaa2aaa333}
+test regexpComp-7.5 {basic regsub operation} {
+ evalInProc {
+ list [regsub aa+ xaxaaaxaa &2&333 foo] $foo
+ }
+} {1 xaxaaa2aaa333xaa}
+test regexpComp-7.6 {basic regsub operation} {
+ evalInProc {
+ list [regsub aa+ xaxaaaxaa 1&22& foo] $foo
+ }
+} {1 xax1aaa22aaaxaa}
+test regexpComp-7.7 {basic regsub operation} {
+ evalInProc {
+ list [regsub a(a+) xaxaaaxaa {1\122\1} foo] $foo
+ }
+} {1 xax1aa22aaxaa}
+test regexpComp-7.8 {basic regsub operation} {
+ evalInProc {
+ list [regsub a(a+) xaxaaaxaa {1\\\122\1} foo] $foo
+ }
+} "1 {xax1\\aa22aaxaa}"
+test regexpComp-7.9 {basic regsub operation} {
+ evalInProc {
+ list [regsub a(a+) xaxaaaxaa {1\\122\1} foo] $foo
+ }
+} "1 {xax1\\122aaxaa}"
+test regexpComp-7.10 {basic regsub operation} {
+ evalInProc {
+ list [regsub a(a+) xaxaaaxaa {1\\&\1} foo] $foo
+ }
+} "1 {xax1\\aaaaaxaa}"
+test regexpComp-7.11 {basic regsub operation} {
+ evalInProc {
+ list [regsub a(a+) xaxaaaxaa {1\&\1} foo] $foo
+ }
+} {1 xax1&aaxaa}
+test regexpComp-7.12 {basic regsub operation} {
+ evalInProc {
+ list [regsub a(a+) xaxaaaxaa {\1\1\1\1&&} foo] $foo
+ }
+} {1 xaxaaaaaaaaaaaaaaxaa}
+test regexpComp-7.13 {basic regsub operation} {
+ evalInProc {
+ set foo xxx
+ list [regsub abc xyz 111 foo] $foo
+ }
+} {0 xyz}
+test regexpComp-7.14 {basic regsub operation} {
+ evalInProc {
+ set foo xxx
+ list [regsub ^ xyz "111 " foo] $foo
+ }
+} {1 {111 xyz}}
+test regexpComp-7.15 {basic regsub operation} {
+ evalInProc {
+ set foo xxx
+ list [regsub -- -foo abc-foodef "111 " foo] $foo
+ }
+} {1 {abc111 def}}
+test regexpComp-7.16 {basic regsub operation} {
+ evalInProc {
+ set foo xxx
+ list [regsub x "" y foo] $foo
+ }
+} {0 {}}
+test regexpComp-7.17 {regsub utf compliance} {
+ evalInProc {
+ # if not UTF-8 aware, result is "0 1"
+ set foo "xyz555ijka\u4e4ebpqr"
+ regsub a\u4e4eb xyza\u4e4ebijka\u4e4ebpqr 555 bar
+ list [string compare $foo $bar] [regexp 4 $bar]
+ }
+} {0 0}
+
+test regexpComp-8.1 {case conversion in regsub} {
+ evalInProc {
+ list [regsub -nocase a(a+) xaAAaAAay & foo] $foo
+ }
+} {1 xaAAaAAay}
+test regexpComp-8.2 {case conversion in regsub} {
+ evalInProc {
+ list [regsub -nocase a(a+) xaAAaAAay & foo] $foo
+ }
+} {1 xaAAaAAay}
+test regexpComp-8.3 {case conversion in regsub} {
+ evalInProc {
+ set foo 123
+ list [regsub a(a+) xaAAaAAay & foo] $foo
+ }
+} {0 xaAAaAAay}
+test regexpComp-8.4 {case conversion in regsub} {
+ evalInProc {
+ set foo 123
+ list [regsub -nocase a CaDE b foo] $foo
+ }
+} {1 CbDE}
+test regexpComp-8.5 {case conversion in regsub} {
+ evalInProc {
+ set foo 123
+ list [regsub -nocase XYZ CxYzD b foo] $foo
+ }
+} {1 CbD}
+test regexpComp-8.6 {case conversion in regsub} {
+ evalInProc {
+ set x abcdefghijklmnopqrstuvwxyz1234567890
+ set x $x$x$x$x$x$x$x$x$x$x$x$x
+ set foo 123
+ list [regsub -nocase $x $x b foo] $foo
+ }
+} {1 b}
+
+test regexpComp-9.1 {-all option to regsub} {
+ evalInProc {
+ set foo 86
+ list [regsub -all x+ axxxbxxcxdx |&| foo] $foo
+ }
+} {4 a|xxx|b|xx|c|x|d|x|}
+test regexpComp-9.2 {-all option to regsub} {
+ evalInProc {
+ set foo 86
+ list [regsub -nocase -all x+ aXxXbxxcXdx |&| foo] $foo
+ }
+} {4 a|XxX|b|xx|c|X|d|x|}
+test regexpComp-9.3 {-all option to regsub} {
+ evalInProc {
+ set foo 86
+ list [regsub x+ axxxbxxcxdx |&| foo] $foo
+ }
+} {1 a|xxx|bxxcxdx}
+test regexpComp-9.4 {-all option to regsub} {
+ evalInProc {
+ set foo 86
+ list [regsub -all bc axxxbxxcxdx |&| foo] $foo
+ }
+} {0 axxxbxxcxdx}
+test regexpComp-9.5 {-all option to regsub} {
+ evalInProc {
+ set foo xxx
+ list [regsub -all node "node node more" yy foo] $foo
+ }
+} {2 {yy yy more}}
+test regexpComp-9.6 {-all option to regsub} {
+ evalInProc {
+ set foo xxx
+ list [regsub -all ^ xxx 123 foo] $foo
+ }
+} {1 123xxx}
+
+#test regexpComp-10.1 {expanded syntax in regsub} {
+# evalInProc {
+# set foo xxx
+# list [regsub -expanded ". \#comment\n . \#comment2" abc def foo] $foo
+# }
+#} {1 defc}
+test regexpComp-10.2 {newline sensitivity in regsub} {
+ evalInProc {
+ set foo xxx
+ list [regsub -line {^a.*b$} "dabc\naxyb\n" 123 foo] $foo
+ }
+} "1 {dabc\n123\n}"
+test regexpComp-10.3 {newline sensitivity in regsub} {
+ evalInProc {
+ set foo xxx
+ list [regsub -line {^a.*b$} "dabc\naxyb\nxb" 123 foo] $foo
+ }
+} "1 {dabc\n123\nxb}"
+#test regexpComp-10.4 {partial newline sensitivity in regsub} {
+# evalInProc {
+# set foo xxx
+# list [regsub -lineanchor {^a.*b$} "da\naxyb\nxb" 123 foo] $foo
+# }
+#} "1 {da\n123}"
+#test regexpComp-10.5 {inverse partial newline sensitivity in regsub} {
+# evalInProc {
+# set foo xxx
+# list [regsub -linestop {a.*b} "da\nbaxyb\nxb" 123 foo] $foo
+# }
+#} "1 {da\nb123\nxb}"
+
+#test regexpComp-11.1 {regsub errors} {
+# evalInProc {
+# list [catch {regsub a b} msg] $msg
+# }
+#} {1 {wrong # args: should be "regsub ?-switch ...? exp string subSpec ?varName?"}}
+#test regexpComp-11.2 {regsub errors} {
+# evalInProc {
+# list [catch {regsub -nocase a b} msg] $msg
+# }
+#} {1 {wrong # args: should be "regsub ?-switch ...? exp string subSpec ?varName?"}}
+#test regexpComp-11.3 {regsub errors} {
+# evalInProc {
+# list [catch {regsub -nocase -all a b} msg] $msg
+# }
+#} {1 {wrong # args: should be "regsub ?-switch ...? exp string subSpec ?varName?"}}
+#test regexpComp-11.4 {regsub errors} {
+# evalInProc {
+# list [catch {regsub a b c d e f} msg] $msg
+# }
+#} {1 {wrong # args: should be "regsub ?-switch ...? exp string subSpec ?varName?"}}
+#test regexpComp-11.5 {regsub errors} {
+# evalInProc {
+# list [catch {regsub -gorp a b c} msg] $msg
+# }
+#} {1 {bad switch "-gorp": must be -all, -nocase, -expanded, -line, -linestop, -lineanchor, -start, or --}}
+#test regexpComp-11.6 {regsub errors} {
+# evalInProc {
+# list [catch {regsub -nocase a( b c d} msg] $msg
+# }
+#} {1 {couldn't compile regular expression pattern: parentheses () not balanced}}
+test regexpComp-11.7 {regsub errors} {
+ evalInProc {
+ catch {unset f1}
+ set f1 44
+ catch {regsub -nocase aaa aaa xxx f1(f2)} msg
+ }
+} {1}
+test regexpComp-11.8 {regsub errors, -start bad int check} {
+ evalInProc {
+ list [catch {regsub -start bogus pattern string rep var} msg] $msg
+ }
+} {1 {bad index "bogus": must be integer?[+-]integer? or end?[+-]integer?}}
+
+# This test crashes on the Mac unless you increase the Stack Space to about 1
+# Meg. This is probably bigger than most users want...
+# 8.2.3 regexp reduced stack space requirements, but this should be
+# tested again
+test regexpComp-12.1 {Tcl_RegExpExec: large number of subexpressions} {
+ evalInProc {
+ list [regexp (.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.) abcdefghijklmnopqrstuvwxyz all a b c d e f g h i j k l m n o p q r s t u v w x y z] $all $a $b $c $d $e $f $g $h $i $j $k $l $m $n $o $p $q $r $s $t $u $v $w $x $y $z
+ }
+} {1 abcdefghijklmnopqrstuvwxyz a b c d e f g h i j k l m n o p q r s t u v w x y z}
+
+test regexpComp-13.1 {regsub of a very large string} {
+ # This test is designed to stress the memory subsystem in order
+ # to catch Bug #933. It only fails if the Tcl memory allocator
+ # is in use.
+
+ set line {BEGIN_TABLE ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; END_TABLE}
+ set filedata [string repeat $line 200]
+ for {set i 1} {$i<10} {incr i} {
+ regsub -all "BEGIN_TABLE " $filedata "" newfiledata
+ }
+ set x done
+} {done}
+
+test regexpComp-14.1 {CompileRegexp: regexp cache} {
+ evalInProc {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ set x .
+ append x *a
+ regexp $x bbba
+ }
+} 1
+test regexpComp-14.2 {CompileRegexp: regexp cache, different flags} {
+ evalInProc {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ set x .
+ append x *a
+ regexp -nocase $x bbba
+ }
+} 1
+
+test regexpComp-15.1 {regexp -start} {
+ catch {unset x}
+ list [regexp -start -10 {\d} 1abc2de3 x] $x
+} {1 1}
+test regexpComp-15.2 {regexp -start} {
+ catch {unset x}
+ list [regexp -start 2 {\d} 1abc2de3 x] $x
+} {1 2}
+test regexpComp-15.3 {regexp -start} {
+ catch {unset x}
+ list [regexp -start 4 {\d} 1abc2de3 x] $x
+} {1 2}
+test regexpComp-15.4 {regexp -start} {
+ catch {unset x}
+ list [regexp -start 5 {\d} 1abc2de3 x] $x
+} {1 3}
+test regexpComp-15.5 {regexp -start, over end of string} {
+ catch {unset x}
+ list [regexp -start [string length 1abc2de3] {\d} 1abc2de3 x] [info exists x]
+} {0 0}
+test regexpComp-15.6 {regexp -start, loss of ^$ behavior} {
+ list [regexp -start 2 {^$} {}]
+} {0}
+
+test regexpComp-16.1 {regsub -start} {
+ catch {unset x}
+ list [regsub -all -start 2 {\d} a1b2c3d4e5 {/&} x] $x
+} {4 a1b/2c/3d/4e/5}
+test regexpComp-16.2 {regsub -start} {
+ catch {unset x}
+ list [regsub -all -start -25 {z} hello {/&} x] $x
+} {0 hello}
+test regexpComp-16.3 {regsub -start} {
+ catch {unset x}
+ list [regsub -all -start 3 {z} hello {/&} x] $x
+} {0 hello}
+#test regexpComp-16.4 {regsub -start, \A behavior} {
+# set out {}
+# lappend out [regsub -start 0 -all {\A(\w)} {abcde} {/\1} x] $x
+# lappend out [regsub -start 2 -all {\A(\w)} {abcde} {/\1} x] $x
+#} {5 /a/b/c/d/e 3 ab/c/d/e}
+
+test regexpComp-17.1 {regexp -inline} {
+ regexp -inline b ababa
+} {b}
+test regexpComp-17.2 {regexp -inline} {
+ regexp -inline (b) ababa
+} {b b}
+test regexpComp-17.3 {regexp -inline -indices} {
+ regexp -inline -indices (b) ababa
+} {{1 1} {1 1}}
+test regexpComp-17.4 {regexp -inline} {
+ regexp -inline {\w(\d+)\w} " hello 23 there456def "
+} {e456d 456}
+test regexpComp-17.5 {regexp -inline no matches} {
+ regexp -inline {\w(\d+)\w} ""
+} {}
+test regexpComp-17.6 {regexp -inline no matches} {
+ regexp -inline hello goodbye
+} {}
+test regexpComp-17.7 {regexp -inline, no matchvars allowed} {
+ list [catch {regexp -inline b abc match} msg] $msg
+} {1 {regexp match variables not allowed when using -inline}}
+
+test regexpComp-18.1 {regexp -all} {
+ regexp -all b bbbbb
+} {5}
+test regexpComp-18.2 {regexp -all} {
+ regexp -all b abababbabaaaaaaaaaab
+} {6}
+test regexpComp-18.3 {regexp -all -inline} {
+ regexp -all -inline b abababbabaaaaaaaaaab
+} {b b b b b b}
+test regexpComp-18.4 {regexp -all -inline} {
+ regexp -all -inline {\w(\w)} abcdefg
+} {ab b cd d ef f}
+test regexpComp-18.5 {regexp -all -inline} {
+ regexp -all -inline {\w(\w)$} abcdefg
+} {fg g}
+test regexpComp-18.6 {regexp -all -inline} {
+ regexp -all -inline {\d+} 10:20:30:40
+} {10 20 30 40}
+test regexpComp-18.7 {regexp -all -inline} {
+ list [catch {regexp -all -inline b abc match} msg] $msg
+} {1 {regexp match variables not allowed when using -inline}}
+test regexpComp-18.8 {regexp -all} {
+ # This should not cause an infinite loop
+ regexp -all -inline {a*} a
+} {a}
+test regexpComp-18.9 {regexp -all} {
+ # Yes, the expected result is {a {}}. Here's why:
+ # Start at index 0; a* matches the "a" there then stops.
+ # Go to index 1; a* matches the lambda (or {}) there then stops. Recall
+ # that a* matches zero or more "a"'s; thus it matches the string "b", as
+ # there are zero or more "a"'s there.
+ # Go to index 2; this is past the end of the string, so stop.
+ regexp -all -inline {a*} ab
+} {a {}}
+test regexpComp-18.10 {regexp -all} {
+ # Yes, the expected result is {a {} a}. Here's why:
+ # Start at index 0; a* matches the "a" there then stops.
+ # Go to index 1; a* matches the lambda (or {}) there then stops. Recall
+ # that a* matches zero or more "a"'s; thus it matches the string "b", as
+ # there are zero or more "a"'s there.
+ # Go to index 2; a* matches the "a" there then stops.
+ # Go to index 3; this is past the end of the string, so stop.
+ regexp -all -inline {a*} aba
+} {a {} a}
+test regexpComp-18.11 {regexp -all} {
+ evalInProc {
+ regexp -all -inline {^a} aaaa
+ }
+} {a}
+test regexpComp-18.12 {regexp -all -inline -indices} {
+ evalInProc {
+ regexp -all -inline -indices a(b(c)d|e(f)g)h abcdhaefgh
+ }
+} {{0 4} {1 3} {2 2} {-1 -1} {5 9} {6 8} {-1 -1} {7 7}}
+
+test regexpComp-19.1 {regsub null replacement} {
+ evalInProc {
+ regsub -all {@} {@hel@lo@} "\0a\0" result
+ list $result [string length $result]
+ }
+} "\0a\0hel\0a\0lo\0a\0 14"
+
+test regexpComp-20.1 {regsub shared object shimmering} {
+ evalInProc {
+ # Bug #461322
+ set a abcdefghijklmnopqurstuvwxyz
+ set b $a
+ set c abcdefghijklmnopqurstuvwxyz0123456789
+ regsub $a $c $b d
+ list $d [string length $d] [string bytelength $d]
+ }
+} [list abcdefghijklmnopqurstuvwxyz0123456789 37 37]
+#test regexpComp-20.2 {regsub shared object shimmering with -about} {
+# evalInProc {
+# eval regexp -about abc
+# }
+#} {0 {}}
+
+test regexpComp-21.1 {regexp command compiling tests} {
+ evalInProc {
+ regexp foo bar
+ }
+} 0
+test regexpComp-21.2 {regexp command compiling tests} {
+ evalInProc {
+ regexp {^foo$} dogfood
+ }
+} 0
+test regexpComp-21.3 {regexp command compiling tests} {
+ evalInProc {
+ set a foo
+ regexp {^foo$} $a
+ }
+} 1
+test regexpComp-21.4 {regexp command compiling tests} {
+ evalInProc {
+ regexp foo dogfood
+ }
+} 1
+test regexpComp-21.5 {regexp command compiling tests} {
+ evalInProc {
+ regexp -nocase FOO dogfod
+ }
+} 0
+test regexpComp-21.6 {regexp command compiling tests} {
+ evalInProc {
+ regexp -n foo dogfoOd
+ }
+} 1
+test regexpComp-21.7 {regexp command compiling tests} {
+ evalInProc {
+ regexp -no -- FoO dogfood
+ }
+} 1
+test regexpComp-21.8 {regexp command compiling tests} {
+ evalInProc {
+ regexp -- foo dogfod
+ }
+} 0
+test regexpComp-21.9 {regexp command compiling tests} {
+ evalInProc {
+ list [catch {regexp -- -nocase foo dogfod} msg] $msg
+ }
+} {0 0}
+test regexpComp-21.10 {regexp command compiling tests} {
+ evalInProc {
+ list [regsub -all "" foo bar str] $str
+ }
+} {3 barfbarobaro}
+# This useless expression fails. Jim returns "bar"
+#test regexpComp-21.11 {regexp command compiling tests} {
+# evalInProc {
+# list [regsub -all "" "" bar str] $str
+# }
+#} {0 {}}
+
+# We can forgive the underlying regexp engine for not supporting this.
+# Why not use this instead? "((^X)*|\$)"
+#test regexpComp-22.0.1 {Bug 1810038} {
+# evalInProc {
+# regexp ($|^X)* {}
+# }
+#} 1
+
+set i 0
+foreach {str exp result} {
+ foo ^foo 1
+ foobar ^foobar$ 1
+ foobar bar$ 1
+ foobar ^$ 0
+ "" ^$ 1
+ anything $ 1
+ anything ^.*$ 1
+ anything ^.*a$ 0
+ anything ^.*a.*$ 1
+ anything ^.*.*$ 1
+ anything ^.*..*$ 1
+ anything ^.*b$ 0
+ anything ^a.*$ 1
+} {
+ test regexpComp-22.[incr i] {regexp command compiling tests} \
+ [subst {evalInProc {set a "$str"; regexp {$exp} \$a}}] $result
+}
+
+set i 0
+foreach {str exp result} {
+ foo ^foo 1
+ foobar ^foobar$ 1
+ foobar bar$ 1
+ foobar ^$ 0
+ "" ^$ 1
+ anything $ 1
+ anything ^.*$ 1
+ anything ^.*a$ 0
+ anything ^.*a.*$ 1
+ anything ^.*.*$ 1
+ anything ^.*..*$ 1
+ anything ^.*b$ 0
+ anything ^a.*$ 1
+} {
+ test regexpComp-23.[incr i] {regexp command compiling tests INST_REGEXP} \
+ [list regexp $exp $str] $result
+}
+
+test regexpComp-24.1 {regexp command compiling tests} {
+ evalInProc {
+ set re foo
+ regexp -nocase $re bar
+ }
+} 0
+test regexpComp-24.2 {regexp command compiling tests} {
+ evalInProc {
+ set re {^foo$}
+ regexp $re dogfood
+ }
+} 0
+test regexpComp-24.3 {regexp command compiling tests} {
+ evalInProc {
+ set a foo
+ set re {^foo$}
+ regexp $re $a
+ }
+} 1
+test regexpComp-24.4 {regexp command compiling tests} {
+ evalInProc {
+ set re foo
+ regexp $re dogfood
+ }
+} 1
+test regexpComp-24.5 {regexp command compiling tests} {
+ evalInProc {
+ set re FOO
+ regexp -nocase $re dogfod
+ }
+} 0
+test regexpComp-24.6 {regexp command compiling tests} {
+ evalInProc {
+ set re foo
+ regexp -n $re dogfoOd
+ }
+} 1
+test regexpComp-24.7 {regexp command compiling tests} {
+ evalInProc {
+ set re FoO
+ regexp -no -- $re dogfood
+ }
+} 1
+test regexpComp-24.8 {regexp command compiling tests} {
+ evalInProc {
+ set re foo
+ regexp -- $re dogfod
+ }
+} 0
+test regexpComp-24.9 {regexp command compiling tests} {
+ evalInProc {
+ set re "("
+ list [catch {regexp -- $re dogfod} msg] $msg
+ }
+} {1 {couldn't compile regular expression pattern: parentheses () not balanced}}
+test regexpComp-24.10 {regexp command compiling tests} {
+ # Bug 1902436 - last * escaped
+ evalInProc {
+ set text {this is *bold* !}
+ set re {\*bold\*}
+ regexp -- $re $text
+ }
+} 1
+test regexpComp-24.11 {regexp command compiling tests} {
+ # Bug 1902436 - last * escaped
+ evalInProc {
+ set text {this is *bold* !}
+ set re {\*bold\*.*!}
+ regexp -- $re $text
+ }
+} 1
+
+test regexp-25.1 {Repeat on escaped char} {
+ regexp {\x41\x42*} bc
+} 0
+
+testreport
diff --git a/tests/utf8.test b/tests/utf8.test
index ba39128..ecb5111 100644
--- a/tests/utf8.test
+++ b/tests/utf8.test
@@ -121,212 +121,7 @@ test utf8-7.1 "string reverse" {
string reverse \ub5Test\u2702
} \u2702tseT\ub5
-# This file contains a collection of tests for tclUtf.c
-# Sourcing this file into Tcl runs the tests and generates output for
-# errors. No output means no errors were found.
-#
-# Copyright (c) 1997 Sun Microsystems, Inc.
-# Copyright (c) 1998-1999 by Scriptics Corporation.
-#
-# See the file "license.terms" for information on usage and redistribution
-# of this file, and for a DISCLAIMER OF ALL WARRANTIES.
-#
-# RCS: @(#) $Id: utf.test,v 1.7 2000/04/10 17:19:05 ericm Exp $
-
-catch {unset x}
-
-section "utf tests"
-
-test utf-1.1 {Tcl_UniCharToUtf: 1 byte sequences} {
- set x \u01
-} [bytestring "\x01"]
-test utf-1.2 {Tcl_UniCharToUtf: 2 byte sequences} {
- set x "\u80"
-} [bytestring "\xc2\x80"]
-test utf-1.3 {Tcl_UniCharToUtf: 2 byte sequences} {
- set x "\ue0"
-} [bytestring "\xc3\xa0"]
-test utf-1.4 {Tcl_UniCharToUtf: 3 byte sequences} {
- set x "\u4e4e"
-} [bytestring "\xe4\xb9\x8e"]
-
-test utf-2.1 {Tcl_UtfToUniChar: low ascii} {
- string length "abc"
-} {3}
-test utf-2.4 {Tcl_UtfToUniChar: lead (2-byte) followed by trail} {
- string length [bytestring "\xC2\xa2"]
-} {1}
-test utf-2.7 {Tcl_UtfToUniChar: lead (3-byte) followed by 2 trail} {
- string length [bytestring "\xE4\xb9\x8e"]
-} {1}
-
-test utf-3.1 {Tcl_UtfCharComplete} {
-} {}
-
-test utf-4.1 {Tcl_NumUtfChars: zero length} {
- string length ""
-} {0}
-test utf-4.2 {Tcl_NumUtfChars: length 1} {
- string length [bytestring "\xC2\xA2"]
-} {1}
-test utf-4.3 {Tcl_NumUtfChars: long string} {
- string length [bytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"]
-} {7}
-
-test utf-5.1 {Tcl_UtfFindFirsts} {
-} {}
-
-test utf-6.1 {Tcl_UtfNext} {
-} {}
-
-test utf-7.1 {Tcl_UtfPrev} {
-} {}
-
-test utf-8.1 {Tcl_UniCharAtIndex: index = 0} {
- string index abcd 0
-} {a}
-test utf-8.2 {Tcl_UniCharAtIndex: index = 0} {
- string index \u4e4e\u25a 0
-} "\u4e4e"
-test utf-8.3 {Tcl_UniCharAtIndex: index > 0} {
- string index abcd 2
-} {c}
-test utf-8.4 {Tcl_UniCharAtIndex: index > 0} {
- string index \u4e4e\u25a\uff\u543 2
-} "\uff"
-
-test utf-9.1 {Tcl_UtfAtIndex: index = 0} {
- string range abcd 0 2
-} {abc}
-test utf-9.2 {Tcl_UtfAtIndex: index > 0} {
- string range \u4e4e\u25a\uff\u543klmnop 1 5
-} "\u25a\uff\u543kl"
-
-
-test utf-10.1 {Tcl_UtfBackslash: dst == NULL} {
- set x \n
-} {
-}
-test utf-10.2 {Tcl_UtfBackslash: \u subst} {
- set x \ua2
-} [bytestring "\xc2\xa2"]
-test utf-10.3 {Tcl_UtfBackslash: longer \u subst} {
- set x \u4e21
-} [bytestring "\xe4\xb8\xa1"]
-test utf-10.4 {Tcl_UtfBackslash: stops at first non-hex} {
- set x \u4e2k
-} "[bytestring \xd3\xa2]k"
-test utf-10.5 {Tcl_UtfBackslash: stops after 4 hex chars} {
- set x \u4e216
-} "[bytestring \xe4\xb8\xa1]6"
-proc bsCheck {char num} {
- global errNum
- test utf-10.$errNum "backslash substitution ($num)" {
- scan $char %c value
- set value
- } $num
- incr errNum
-}
-set errNum 6
-bsCheck \b 8
-bsCheck \e 101
-bsCheck \f 12
-bsCheck \n 10
-bsCheck \r 13
-bsCheck \t 9
-bsCheck \v 11
-bsCheck \{ 123
-bsCheck \} 125
-bsCheck \[ 91
-bsCheck \] 93
-bsCheck \$ 36
-bsCheck \ 32
-bsCheck \; 59
-bsCheck \\ 92
-bsCheck \Ca 67
-bsCheck \Ma 77
-bsCheck \CMa 67
-# prior to 8.3, this returned 8, as \8 as accepted as an
-# octal value - but it isn't! [Bug: 3975]
-bsCheck \8a 56
-bsCheck \14 12
-bsCheck \141 97
-bsCheck b\0 98
-bsCheck \x 120
-bsCheck \xa 10
-bsCheck \xA 10
-bsCheck \x41 65
-#bsCheck \x541 65
-bsCheck \u 117
-bsCheck \uk 117
-bsCheck \u41 65
-bsCheck \ua 10
-bsCheck \uA 10
-bsCheck \ue0 224
-bsCheck \ua1 161
-bsCheck \u4e21 20001
-
-test utf-11.1 {Tcl_UtfToUpper} {
- string toupper {}
-} {}
-test utf-11.2 {Tcl_UtfToUpper} {
- string toupper abc
-} ABC
-test utf-11.3 {Tcl_UtfToUpper} {
- string toupper \u00e3ab
-} \u00c3AB
-test utf-11.4 {Tcl_UtfToUpper} {
- string toupper \u01e3ab
-} \u01e2AB
-
-test utf-12.1 {Tcl_UtfToLower} {
- string tolower {}
-} {}
-test utf-12.2 {Tcl_UtfToLower} {
- string tolower ABC
-} abc
-test utf-12.3 {Tcl_UtfToLower} {
- string tolower \u00c3AB
-} \u00e3ab
-test utf-12.4 {Tcl_UtfToLower} {
- string tolower \u01e2AB
-} \u01e3ab
-
-
-test utf-14.1 {Tcl_UtfNcasecmp} {
- string compare -nocase a b
-} -1
-test utf-14.2 {Tcl_UtfNcasecmp} {
- string compare -nocase b a
-} 1
-test utf-14.3 {Tcl_UtfNcasecmp} {
- string compare -nocase B a
-} 1
-test utf-14.4 {Tcl_UtfNcasecmp} {
- string compare -nocase aBcB abca
-} 1
-
-test utf-15.1 {Tcl_UniCharToUpper, negative delta} {
- string toupper aA
-} AA
-test utf-15.2 {Tcl_UniCharToUpper, positive delta} {
- string toupper \u0178\u00ff
-} \u0178\u0178
-test utf-15.3 {Tcl_UniCharToUpper, no delta} {
- string toupper !
-} !
-
-test utf-16.1 {Tcl_UniCharToLower, negative delta} {
- string tolower aA
-} aa
-test utf-16.2 {Tcl_UniCharToLower, positive delta} {
- string tolower \u0178\u00ff
-} \u00ff\u00ff
-test utf-17.1 {Tcl_UniCharToLower, no delta} {
- string tolower !
-} !
-
-test utf-18.1 {append counts correctly} {
+test utf8-7.2 {append counts correctly} {
set x \u2702XYZ
append x \u2702XYZ
list [string length $x] [string bytelength $x]
diff --git a/tests/utftcl.test b/tests/utftcl.test
new file mode 100644
index 0000000..468cff1
--- /dev/null
+++ b/tests/utftcl.test
@@ -0,0 +1,290 @@
+# This file contains a collection of tests for tclUtf.c
+# Sourcing this file into Tcl runs the tests and generates output for
+# errors. No output means no errors were found.
+#
+# Copyright (c) 1997 Sun Microsystems, Inc.
+# Copyright (c) 1998-1999 by Scriptics Corporation.
+#
+# See the file "license.terms" for information on usage and redistribution
+# of this file, and for a DISCLAIMER OF ALL WARRANTIES.
+#
+# RCS: @(#) $Id: utf.test,v 1.14 2007/05/02 01:37:28 kennykb Exp $
+
+source testing.tcl
+
+ifutf8 {
+
+catch {unset x}
+
+test utf-1.1 {Tcl_UniCharToUtf: 1 byte sequences} {
+ set x \x01
+} [bytestring "\x01"]
+test utf-1.2 {Tcl_UniCharToUtf: 2 byte sequences} {
+ set x "\u80"
+} [bytestring "\xc2\x80"]
+test utf-1.3 {Tcl_UniCharToUtf: 2 byte sequences} {
+ set x "\ue0"
+} [bytestring "\xc3\xa0"]
+test utf-1.4 {Tcl_UniCharToUtf: 3 byte sequences} {
+ set x "\u4e4e"
+} [bytestring "\xe4\xb9\x8e"]
+test utf-1.5 {Tcl_UniCharToUtf: negative Tcl_UniChar} {
+ string length [format %c -1]
+} 1
+
+test utf-2.1 {Tcl_UtfToUniChar: low ascii} {
+ string length "abc"
+} {3}
+test utf-2.2 {Tcl_UtfToUniChar: naked trail bytes} {
+ string length [bytestring "\x82\x83\x84"]
+} {3}
+test utf-2.3 {Tcl_UtfToUniChar: lead (2-byte) followed by non-trail} {
+ string length [bytestring "\xC2"]
+} {1}
+test utf-2.4 {Tcl_UtfToUniChar: lead (2-byte) followed by trail} {
+ string length [bytestring "\xC2\xa2"]
+} {1}
+test utf-2.5 {Tcl_UtfToUniChar: lead (3-byte) followed by non-trail} {
+ string length [bytestring "\xE2"]
+} {1}
+test utf-2.6 {Tcl_UtfToUniChar: lead (3-byte) followed by 1 trail} {
+ string length [bytestring "\xE2\xA2"]
+} {2}
+test utf-2.7 {Tcl_UtfToUniChar: lead (3-byte) followed by 2 trail} {
+ string length [bytestring "\xE4\xb9\x8e"]
+} {1}
+test utf-2.8 {Tcl_UtfToUniChar: longer UTF sequences not supported} {
+ string length [bytestring "\xF4\xA2\xA2\xA2"]
+} {4}
+
+test utf-3.1 {Tcl_UtfCharComplete} {
+} {}
+
+proc testnumutfchars {a {n ""}} {
+ string length $a
+}
+
+test utf-4.1 {Tcl_NumUtfChars: zero length} {
+ testnumutfchars ""
+} {0}
+test utf-4.2 {Tcl_NumUtfChars: length 1} {
+ testnumutfchars [bytestring "\xC2\xA2"]
+} {1}
+test utf-4.3 {Tcl_NumUtfChars: long string} {
+ testnumutfchars [bytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"]
+} {7}
+test utf-4.4 {Tcl_NumUtfChars: #u0000} {
+ testnumutfchars [bytestring "\xC0\x80"]
+} {1}
+test utf-4.5 {Tcl_NumUtfChars: zero length, calc len} {
+ testnumutfchars "" 1
+} {0}
+test utf-4.6 {Tcl_NumUtfChars: length 1, calc len} {
+ testnumutfchars [bytestring "\xC2\xA2"] 1
+} {1}
+test utf-4.7 {Tcl_NumUtfChars: long string, calc len} {
+ testnumutfchars [bytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"] 1
+} {7}
+test utf-4.8 {Tcl_NumUtfChars: #u0000, calc len} {
+ testnumutfchars [bytestring "\xC0\x80"] 1
+} {1}
+
+test utf-5.1 {Tcl_UtfFindFirsts} {
+} {}
+
+test utf-6.1 {Tcl_UtfNext} {
+} {}
+
+test utf-7.1 {Tcl_UtfPrev} {
+} {}
+
+test utf-8.1 {Tcl_UniCharAtIndex: index = 0} {
+ string index abcd 0
+} {a}
+test utf-8.2 {Tcl_UniCharAtIndex: index = 0} {
+ string index \u4e4e\u25a 0
+} "\u4e4e"
+test utf-8.3 {Tcl_UniCharAtIndex: index > 0} {
+ string index abcd 2
+} {c}
+test utf-8.4 {Tcl_UniCharAtIndex: index > 0} {
+ string index \u4e4e\u25a\uff\u543 2
+} "\uff"
+
+test utf-9.1 {Tcl_UtfAtIndex: index = 0} {
+ string range abcd 0 2
+} {abc}
+test utf-9.2 {Tcl_UtfAtIndex: index > 0} {
+ string range \u4e4e\u25a\xff\u543klmnop 1 5
+} "\u25a\xff\u543kl"
+
+
+test utf-10.1 {Tcl_UtfBackslash: dst == NULL} {
+ set x \n
+} {
+}
+test utf-10.2 {Tcl_UtfBackslash: \u subst} {
+ set x \ua2
+} [bytestring "\xc2\xa2"]
+test utf-10.3 {Tcl_UtfBackslash: longer \u subst} {
+ set x \u4e21
+} [bytestring "\xe4\xb8\xa1"]
+test utf-10.4 {Tcl_UtfBackslash: stops at first non-hex} {
+ set x \u4e2k
+} "[bytestring \xd3\xa2]k"
+test utf-10.5 {Tcl_UtfBackslash: stops after 4 hex chars} {
+ set x \u4e216
+} "[bytestring \xe4\xb8\xa1]6"
+proc bsCheck {char num} {
+ global errNum
+ test utf-10.$errNum {backslash substitution} {
+ scan $char %c value
+ set value
+ } $num
+ incr errNum
+}
+set errNum 6
+bsCheck \b 8
+bsCheck \e 101
+bsCheck \f 12
+bsCheck \n 10
+bsCheck \r 13
+bsCheck \t 9
+bsCheck \v 11
+bsCheck \{ 123
+bsCheck \} 125
+bsCheck \[ 91
+bsCheck \] 93
+bsCheck \$ 36
+bsCheck \ 32
+bsCheck \; 59
+bsCheck \\ 92
+bsCheck \Ca 67
+bsCheck \Ma 77
+bsCheck \CMa 67
+# prior to 8.3, this returned 8, as \8 as accepted as an
+# octal value - but it isn't! [Bug: 3975]
+bsCheck \8a 56
+bsCheck \14 12
+bsCheck \141 97
+bsCheck b\0 98
+bsCheck \x 120
+bsCheck \ua 10
+bsCheck \uA 10
+bsCheck \u41 65
+bsCheck \u 117
+bsCheck \uk 117
+bsCheck \u41 65
+bsCheck \ua 10
+bsCheck \uA 10
+bsCheck \340 224
+bsCheck \ua1 161
+bsCheck \u4e21 20001
+
+test utf-11.1 {Tcl_UtfToUpper} {
+ string toupper {}
+} {}
+test utf-11.2 {Tcl_UtfToUpper} {
+ string toupper abc
+} ABC
+test utf-11.3 {Tcl_UtfToUpper} {
+ string toupper \u00e3ab
+} \u00c3AB
+test utf-11.4 {Tcl_UtfToUpper} {
+ string toupper \u01e3ab
+} \u01e2AB
+
+test utf-12.1 {Tcl_UtfToLower} {
+ string tolower {}
+} {}
+test utf-12.2 {Tcl_UtfToLower} {
+ string tolower ABC
+} abc
+test utf-12.3 {Tcl_UtfToLower} {
+ string tolower \u00c3AB
+} \u00e3ab
+test utf-12.4 {Tcl_UtfToLower} {
+ string tolower \u01e2AB
+} \u01e3ab
+
+
+test utf-14.1 {Tcl_UtfNcasecmp} {
+ string compare -nocase a b
+} -1
+test utf-14.2 {Tcl_UtfNcasecmp} {
+ string compare -nocase b a
+} 1
+test utf-14.3 {Tcl_UtfNcasecmp} {
+ string compare -nocase B a
+} 1
+test utf-14.4 {Tcl_UtfNcasecmp} {
+ string compare -nocase aBcB abca
+} 1
+
+test utf-15.1 {Tcl_UniCharToUpper, negative delta} {
+ string toupper aA
+} AA
+test utf-15.2 {Tcl_UniCharToUpper, positive delta} {
+ string toupper \u0178\u00ff
+} \u0178\u0178
+test utf-15.3 {Tcl_UniCharToUpper, no delta} {
+ string toupper !
+} !
+
+test utf-16.1 {Tcl_UniCharToLower, negative delta} {
+ string tolower aA
+} aa
+test utf-16.2 {Tcl_UniCharToLower, positive delta} {
+ string tolower \u0178\u00ff
+} \u00ff\u00ff
+test utf-17.1 {Tcl_UniCharToLower, no delta} {
+ string tolower !
+} !
+
+
+#test utf-21.1 {TclUniCharIsAlnum} {
+# # this returns 1 with Unicode 3 compliance
+# string is alnum \u1040\u021f
+#} {1}
+#test utf-21.2 {unicode alnum char in regc_locale.c} {
+# # this returns 1 with Unicode 3 compliance
+# list [regexp {^[[:alnum:]]+$} \u1040\u021f] [regexp {^\w+$} \u1040\u021f]
+#} {1 1}
+
+#test utf-22.1 {TclUniCharIsWordChar} {
+# string wordend "xyz123_bar fg" 0
+#} 10
+#test utf-22.2 {TclUniCharIsWordChar} {
+# string wordend "x\u5080z123_bar\u203c fg" 0
+#} 10
+
+#test utf-23.1 {TclUniCharIsAlpha} {
+# # this returns 1 with Unicode 3 compliance
+# string is alpha \u021f
+#} {1}
+#test utf-23.2 {unicode alpha char in regc_locale.c} {
+# # this returns 1 with Unicode 3 compliance
+# regexp {^[[:alpha:]]+$} \u021f
+#} {1}
+#
+#test utf-24.1 {TclUniCharIsDigit} {
+# # this returns 1 with Unicode 3 compliance
+# string is digit \u1040
+#} {1}
+#test utf-24.2 {unicode digit char in regc_locale.c} {
+# # this returns 1 with Unicode 3 compliance
+# list [regexp {^[[:digit:]]+$} \u1040] [regexp {^\d+$} \u1040]
+#} {1 1}
+#
+#test utf-24.3 {TclUniCharIsSpace} {
+# # this returns 1 with Unicode 3 compliance
+# string is space \u1680
+#} {1}
+#test utf-24.4 {unicode space char in regc_locale.c} {
+# # this returns 1 with Unicode 3 compliance
+# list [regexp {^[[:space:]]+$} \u1680] [regexp {^\s+$} \u1680]
+#} {1 1}
+
+testreport
+
+}
generated by cgit v1.1 at 2024-10-11 11:15:03 +0000